WIFI-based indoor voice positioning method and device

Abstract

The application discloses a WIFI-based indoor voice positioning method and device. The method utilizes existing terminal equipment and is based on voice acoustic principles. The corresponding terminal equipment can be controlled to emit and receive voice information in a WIFI communication mode, so that the position of the terminal equipment is determined, and the positioning of a sound source is completed. The indoor positioning operation is simplified, the cost of system deployment is reduced, the accuracy of indoor positioning results is increased, and the convenience of indoor positioning in application is improved.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) positioning technology, and in particular to an indoor voice positioning method and device based on Wi-Fi. Background Technology

[0002] Current indoor voice positioning methods, such as those based on acoustic principles, require the pre-establishment of complex positioning systems. The varying performance and operating principles of different devices contribute to system complexity and high deployment costs, resulting in cumbersome and inconvenient operation in practical applications. Therefore, improving the convenience of indoor positioning in real-world scenarios is crucial. Summary of the Invention

[0003] The technical problem this invention aims to solve is to provide a WIFI-based indoor voice positioning method. Utilizing existing terminal devices and based on the principles of voice acoustics, this method controls the transmission and reception of voice information via WIFI communication, thereby determining the location of the terminal devices and ultimately locating the sound source. This simplifies indoor positioning operations, reduces system deployment costs, increases the accuracy of indoor positioning results, and enhances the convenience of indoor positioning applications.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses an indoor voice positioning method based on Wi-Fi, comprising:

[0005] A positioning map of a target area is established, wherein at least two terminal devices are set up in the target area, and the positioning map includes the first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module, wherein the communication module is a module for transmitting voice data based on WIFI.

[0006] The positioning voice signal is obtained by acquiring the sound source signal sent by the sound source to be located by the at least two sound receiving modules in each of the terminal devices;

[0007] Based on the positioning voice signals collected by each of the terminal devices, the second location information of the sound source to be located relative to each terminal device in the positioning map is determined;

[0008] The target location of the sound source to be located in the target area is determined based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map.

[0009] As an optional implementation, each of the terminal devices further includes a voice module, and the step of establishing a positioning map of the target area includes:

[0010] According to a preset order and time interval, each terminal device is controlled to send standard voice signals sequentially.

[0011] Acquire the standard voice signal received by each audio module in each of the terminal devices;

[0012] Based on the standard voice signals received by each terminal device, the first location information of each terminal device is determined;

[0013] A location map of the target area is established based on the first location information of each terminal device.

[0014] As an optional implementation, the method further includes:

[0015] Determine the network information corresponding to the WIFI accessed by each terminal device;

[0016] Based on the network information corresponding to each terminal device, all the terminal devices to be grouped are grouped to obtain at least one terminal device group. The WIFI connected to the terminal devices in each terminal device group is the same network. In any terminal device group, the number of user terminal devices accessing the WIFI of that terminal device group is greater than or equal to 1.

[0017] The step of controlling each terminal device to sequentially send standard voice signals according to a preset order and time interval includes:

[0018] A preset sequence and time interval are determined, and the generation operation of the first control signal corresponding to each user terminal device is executed according to the preset sequence and time interval;

[0019] After determining the first control signal, the first control signal corresponding to each user terminal device is sent to all terminal devices belonging to the same device group as that user terminal device, so as to trigger each target terminal device to perform the following operations after receiving the first control signal:

[0020] Standard voice signals are sent sequentially according to the preset order and time interval indicated by the first control signal.

[0021] As an optional implementation, the sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module;

[0022] The acquisition of the location voice signal collected by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located includes:

[0023] The acoustic characteristics of the sound source signal that each mobile terminal device needs to send are determined, and the generation operation of the second control signal corresponding to each user terminal device is executed according to the acoustic characteristics.

[0024] The acoustic features include one or more of the following: type, frequency, duration, intensity, and content;

[0025] After determining the second control signal, the second control signal corresponding to each user terminal device is sent to each mobile terminal device to trigger each mobile terminal device to perform the following operations upon receiving the second control signal:

[0026] The sound source signal is transmitted according to the acoustic characteristics indicated by the second control signal;

[0027] The location-based voice signal is obtained from the sound source signal collected by the at least two audio receiving modules in each of the terminal devices.

[0028] As an optional implementation, determining the first location information of each terminal device based on the standard voice signal received by each terminal device includes:

[0029] The propagation time of the standard voice signal between the terminal devices is determined by a cooperative ranging method, and the first distance between each pair of the terminal devices is determined.

[0030] Using a generalized cross-correlation algorithm, the time when each of the at least two audio receiving modules of each terminal device receives the same standard voice signal is determined, and the first azimuth angle between each pair of terminal devices is determined.

[0031] Based on the first distance and the first azimuth angle, a first distance matrix and a first angle matrix are obtained for each terminal device, and the first position information of each terminal device is determined based on the first distance matrix and the first angle matrix.

[0032] As an optional implementation, there are at least three microphone modules, wherein the at least three microphone modules are not coplanar in a preset direction, and the preset direction is perpendicular to the ground; determining the first location information of each terminal device based on the standard voice signal received by each terminal device further includes:

[0033] By using a cooperative ranging method, the propagation time of the standard voice signal between the terminal devices is determined, and the second distance between each pair of the terminal devices is determined.

[0034] Using a generalized cross-correlation algorithm, the time when the at least three audio modules of each terminal device receive the same standard voice signal is determined, and the first azimuth angle and first pitch angle between each pair of terminal devices are determined.

[0035] Based on the second distance, the first azimuth angle, and the first pitch angle, a second distance matrix and a second angle matrix are obtained for each of the terminal devices, and the first position information of each of the terminal devices is determined based on the second distance matrix and the second angle matrix.

[0036] The step of determining the second location information of the sound source to be located relative to each terminal device in the positioning map based on the positioning voice signals collected by each of the terminal devices includes:

[0037] Based on the timing of the location voice signal acquired by the at least three sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle and the second elevation angle of the sound source to be located relative to each of the terminal devices are determined by a generalized cross-correlation algorithm.

[0038] Determining the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map includes:

[0039] Based on the second azimuth angle, the second elevation angle, and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0040] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0041] As an optional implementation, the second location information includes a second azimuth angle. The step of determining the second location information of the sound source to be located relative to each terminal device in the location map based on the location voice signals collected by each of the terminal devices includes:

[0042] Based on the time of the location voice signal acquired by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle of the sound source to be located relative to each of the terminal devices is determined by a generalized cross-correlation algorithm.

[0043] The step of determining the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each smart device in the positioning map includes:

[0044] Based on the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0045] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0046] As an optional implementation, determining the target location of the sound source to be located in the target area based on the intersection of the plurality of positioning rays includes:

[0047] If the multiple positioning rays have at least two intersection points, the positioning area of ​​the sound source to be located is determined based on the intersection points of the multiple positioning rays.

[0048] Based on the positioning area, the second location information of the sound source to be located is determined.

[0049] As an optional implementation, after determining the second location information of the sound source to be located relative to each terminal device in the location map, the method further includes:

[0050] If the second location information changes within a preset time period, the trajectory of the sound source to be located is determined.

[0051] Based on the change trajectory, the positioning terminal device among the at least two terminal devices is determined, and the distance between the positioning terminal device and the sound source to be located is less than a preset distance;

[0052] Based on the first location information of the positioning terminal device and the second location information of the sound source to be located relative to the positioning terminal device, the target location of the sound source to be located in the target area is determined.

[0053] Secondly, this application provides an indoor positioning device, the device comprising:

[0054] A map creation module is used to create a location map of a target area. The target area is equipped with at least two terminal devices. The location map includes the first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module. The communication module is a module for transmitting voice data based on WIFI.

[0055] The sound acquisition module is used to acquire the positioning voice signal obtained by acquiring the sound source signal sent by the at least two sound receiving modules of each terminal device to the sound source to be located;

[0056] The location determination module is used to determine the second location information of the sound source to be located relative to each terminal device in the location map based on the location voice signals collected by each terminal device.

[0057] The location determination module is further configured to determine the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the location map.

[0058] As an optional implementation, each of the terminal devices further includes a voice module, and the map building module includes:

[0059] The transmitting unit is used to control each of the terminal devices to transmit standard voice signals sequentially according to a preset order and time interval;

[0060] The acquisition unit is used to acquire the standard voice signal received by each audio module in each of the terminal devices;

[0061] The positioning unit is used to determine the first location information of each terminal device based on the standard voice signal received by each terminal device.

[0062] The map building unit is used to build a positioning map of the target area based on the first location information of each terminal device.

[0063] As an optional implementation, the device further includes a network determination module, used for:

[0064] Determine the network information corresponding to the WIFI accessed by each terminal device;

[0065] Based on the network information corresponding to each terminal device, all the terminal devices to be grouped are grouped to obtain at least one terminal device group. The WIFI connected to the terminal devices in each terminal device group is the same network. In any terminal device group, the number of user terminal devices accessing the WIFI of that terminal device group is greater than or equal to 1.

[0066] The sending unit controls the specific method by which each terminal device sequentially sends standard voice signals according to a preset order and time interval, including:

[0067] A preset sequence and time interval are determined, and the generation operation of the first control signal corresponding to each user terminal device is executed according to the preset sequence and time interval;

[0068] After determining the first control signal, the first control signal corresponding to each user terminal device is sent to all terminal devices belonging to the same device group as that user terminal device, so as to trigger each target terminal device to perform the following operations after receiving the first control signal:

[0069] Standard voice signals are sent sequentially according to the preset order and time interval indicated by the first control signal.

[0070] As an optional implementation, the sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module;

[0071] The specific method by which the sound acquisition module acquires the location voice signal collected by the sound source signal sent by the at least two sound receiving modules in each of the terminal devices to be located, includes:

[0072] The acoustic characteristics of the sound source signal that each mobile terminal device needs to send are determined, and the generation operation of the second control signal corresponding to each user terminal device is executed according to the acoustic characteristics.

[0073] The acoustic features include one or more of the following: type, frequency, duration, intensity, and content;

[0074] After determining the second control signal, the second control signal corresponding to each user terminal device is sent to each mobile terminal device to trigger each mobile terminal device to perform the following operations upon receiving the second control signal:

[0075] The sound source signal is transmitted according to the acoustic characteristics indicated by the second control signal;

[0076] The location-based voice signal is obtained from the sound source signal collected by the at least two audio receiving modules in each of the terminal devices.

[0077] As an optional implementation, the positioning unit includes:

[0078] The distance determination subunit is used to determine the propagation time of the standard voice signal between the terminal devices through a cooperative ranging method, and to determine the first distance between each pair of the terminal devices.

[0079] An angle determination subunit is used to determine, through a generalized cross-correlation algorithm, the time when the at least two audio modules of each terminal device receive the same standard voice signal, and to determine the first azimuth angle between each pair of terminal devices.

[0080] The location determination subunit is used to obtain a first distance matrix and a first angle matrix for each terminal device based on the first distance and the first azimuth angle, and to determine the first location information of each terminal device based on the first distance matrix and the first angle matrix.

[0081] As an optional implementation, there are at least three microphone modules, wherein the at least three microphone modules are not coplanar in a preset direction, and the preset direction is perpendicular to the ground;

[0082] The distance determination subunit is also used to determine the propagation time of the standard voice signal between the terminal devices through a cooperative ranging method, and to determine the second distance between each pair of the terminal devices.

[0083] The angle determination subunit is also used to determine, through a generalized cross-correlation algorithm, the time when the at least three audio modules of each terminal device receive the same standard voice signal, and to determine the first azimuth angle and the first pitch angle between each pair of terminal devices;

[0084] The position determination subunit is further configured to obtain a second distance matrix and a second angle matrix for each terminal device based on the second distance, the first azimuth angle and the first pitch angle, and determine the first position information of each terminal device based on the second distance matrix and the second angle matrix.

[0085] The location determination module is further configured to:

[0086] Based on the timing of the location voice signal acquired by the at least three sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle and the second elevation angle of the sound source to be located relative to each of the terminal devices are determined by a generalized cross-correlation algorithm.

[0087] The location determination module is further configured to:

[0088] Based on the second azimuth angle, the second elevation angle, and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0089] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0090] As an optional implementation, the second location information includes a second azimuth angle, and the location determination module is further configured to:

[0091] Based on the time of the location voice signal acquired by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle of the sound source to be located relative to each of the terminal devices is determined by a generalized cross-correlation algorithm.

[0092] The location determination module is further configured to:

[0093] Based on the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0094] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0095] As an optional implementation, the position determination module is further configured to:

[0096] If the multiple positioning rays have at least two intersection points, the positioning area of ​​the sound source to be located is determined based on the intersection points of the multiple positioning rays.

[0097] Based on the positioning area, the second location information of the sound source to be located is determined.

[0098] As an optional implementation, the device further includes a trajectory determination module, used for:

[0099] After the location determination module determines the second location information of the sound source to be located relative to each terminal device in the location map,

[0100] If the second location information changes within a preset time period, the trajectory of the sound source to be located is determined.

[0101] Based on the change trajectory, the positioning terminal device among the at least two terminal devices is determined, and the distance between the positioning terminal device and the sound source to be located is less than a preset distance;

[0102] Based on the first location information of the positioning terminal device and the second location information of the sound source to be located relative to the positioning terminal device, the target location of the sound source to be located in the target area is determined.

[0103] A third aspect of the present invention discloses another indoor positioning device, the device comprising:

[0104] Memory containing executable program code;

[0105] A processor coupled to the memory;

[0106] The processor calls the executable program code stored in the memory to execute the WIFI-based indoor voice positioning method disclosed in the first aspect of the present invention.

[0107] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute the WIFI-based indoor voice positioning method disclosed in the first aspect of the present invention.

[0108] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: by utilizing existing terminal devices and based on the principle of voice acoustics, the corresponding terminal devices can be controlled to transmit and receive voice information through WIFI communication, thereby determining the location of the terminal devices and completing the location of the sound source. This simplifies indoor positioning operations, reduces the cost of system deployment, and also increases the accuracy of indoor positioning results, thereby improving the convenience of indoor positioning in applications. Attached Figure Description

[0109] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0110] Figure 1 This is a schematic diagram of an indoor positioning scenario disclosed in an embodiment of the present invention;

[0111] Figure 2 This is a flowchart illustrating an indoor voice positioning method based on WIFI disclosed in an embodiment of the present invention.

[0112] Figure 3 This is a flowchart illustrating an indoor voice positioning method based on WIFI disclosed in an embodiment of the present invention.

[0113] Figure 4 This is a schematic diagram of the structure of an indoor positioning device disclosed in an embodiment of the present invention;

[0114] Figure 5 This is a schematic diagram of another indoor positioning device disclosed in an embodiment of the present invention;

[0115] Figure 6 This is a structural schematic diagram of another indoor positioning device disclosed in an embodiment of the present invention. Detailed Implementation

[0116] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0117] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0118] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0119] In this application, references to “each,” “all,” or other related descriptions should be understood to include scenarios where there is only one or multiple corresponding objects, and should not be interpreted literally.

[0120] Currently, indoor positioning provides the technological foundation for many smart home applications, playing a crucial role in areas such as proximity-based wake-up, childcare, and smart elderly care. However, current indoor positioning technology suffers from problems such as complex positioning systems, high system costs, and insufficient positioning accuracy. Please refer to [link / reference]. Figure 1 , Figure 1 This is a schematic diagram of an indoor positioning scenario disclosed in an embodiment of the present invention, used to illustrate the aforementioned scenario. For example... Figure 1 As shown, existing indoor positioning systems are typically based on technologies such as infrared positioning, IoT positioning, and local area network positioning. These systems require the installation of several reference devices on top of existing equipment, and the existing equipment is then combined with these reference devices during the positioning process to ensure positioning effectiveness. Consequently, existing Wi-Fi-based indoor voice positioning methods generally have limitations in terms of deployment costs, maintenance costs, and ease of use.

[0121] In the acoustic principle-based WIFI-based indoor voice localization method, the target to be located in the figure can be understood as a sound source to be located. However, the nature of this sound source should not be limited, nor should the content and form of the sound emitted by the sound source be limited. For example, the sound source to be located can be animal sounds, user commands, regular sound signals emitted by handheld devices, etc. In this application, the specific type of sound source should not be limited either. However, based on the method provided in this application, some implementation forms of the sound source to be located based on WIFI voice are provided in the embodiments, which can be referred to in the relevant descriptions in the embodiments. In addition, it should be noted that the descriptions of "voice" and "sound" in this application can be used interchangeably. The description of "voice" in this application should be interpreted broadly, which can be a sound signal with specific content emitted by a user or device, or a sound signal with a specific frequency, intensity, duration, etc., and not just "voice" as commonly understood.

[0122] A typical application scenario for the Wi-Fi-based indoor voice positioning method provided in this application is an IoT-based smart home scenario. In this scenario, the devices shown in the figure are typically terminal devices with sound receiving capabilities, such as washing machines, televisions, refrigerators, and air conditioners. The reference device in the figure is also used to improve positioning accuracy. Terminal devices with sound receiving capabilities are usually equipped with multiple sound receiving modules, and a sound output module can also be installed on the device. Therefore, the indoor positioning system can be simplified by improving the positioning method. By utilizing existing indoor terminal devices to establish a positioning map and determine the location of the sound source to be located, the indoor positioning system is simplified, eliminating the need for additional reference devices, thereby reducing system deployment costs and improving ease of use.

[0123] This invention discloses an indoor voice positioning method and device based on WIFI. Utilizing existing terminal equipment and based on the principle of voice acoustics, the corresponding terminal equipment can be controlled to transmit and receive voice information via WIFI communication, thereby determining the location of the terminal equipment and locating the sound source. This simplifies indoor positioning operations, reduces system deployment costs, increases the accuracy of indoor positioning results, and enhances the convenience of indoor positioning in applications.

[0124] Example 1

[0125] The WIFI-based indoor voice positioning method provided in this application requires first constructing a positioning map of the target area based on existing terminal devices, such as televisions, refrigerators, air conditioners, washing machines, etc. that support voice and WIFI connectivity. Then, the device in the positioning map is used to collect the sound of the sound source to be located, thereby achieving positioning.

[0126] Please see Figure 2 , Figure 2 This is a flowchart illustrating an indoor voice positioning method based on Wi-Fi disclosed in an embodiment of the present invention. Figure 2 As shown, the WIFI-based indoor voice positioning method may include the following operations:

[0127] S101. Establish a location map of the target area;

[0128] The target area is equipped with at least two terminal devices. The positioning map includes the first location information of each terminal device in the target area, and each terminal device includes at least two audio receiving modules. To ensure the accuracy of the angle information in the acquired location information, each terminal device needs to have at least two audio receiving modules. Accordingly, the positioning map may include the first location information of each terminal device in the target area, and any terminal device can perform the function of a reference device in other positioning methods within the target area. In addition, each terminal device also includes at least one communication module, which is a module for voice data transmission based on WIFI. Through the communication module, each terminal device can connect to WIFI and communicate and control voice data through WIFI data transmission, thereby completing the establishment of the positioning map and the localization of the sound source to be located. For details, please refer to the description in the corresponding implementation.

[0129] S102. Obtain the positioning voice signal obtained by the sound source signal sent by the at least two sound receiving modules of each terminal device to the sound source to be located;

[0130] After the location map is established, the terminal devices in the target area will act as sound receiving devices to receive the sound signals of the sound source to be located. Optionally, the location information described in this application may include angle information. Therefore, in the acquisition of sound signals, it is necessary to acquire the location voice signals obtained by the sound source signals sent by the sound source signals sent by the at least two sound receiving modules in each terminal device to determine the angle information.

[0131] S103. Based on the positioning voice signals collected by each of the terminal devices, determine the second location information of the sound source to be located relative to each terminal device in the positioning map;

[0132] After acquiring the sound signal, the second position information of the sound source to be located relative to each terminal device in the positioning map can be determined. In acoustic-based positioning methods, determining the second position information by acquiring angle and distance information is more practical than directly acquiring the coordinates of each terminal device in the target area.

[0133] S104. Determine the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map.

[0134] After the second location information is collected, the target location of the sound source to be located in the target area can be determined based on the established positioning map, according to the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map, that is, the position of each terminal device and the position of the sound source to be located relative to each terminal device.

[0135] It should be noted that the WIFI-based indoor voice positioning method provided in this application can be applied to positioning in both two-dimensional and three-dimensional scenes. A two-dimensional scene can be viewed as a projection of a three-dimensional scene onto a plane, representing a special form of three-dimensional scene positioning. In this case, it is necessary to determine the positional information of the sound source to be located in at least two dimensions. These two dimensions can be angle information and distance information, or they can be the relatively intuitive horizontal and vertical coordinates on a plane. For positioning methods in three-dimensional space, please refer to the last embodiment in this example; it will not be repeated here.

[0136] The WIFI-based indoor voice positioning method described in this embodiment utilizes existing terminal devices and, based on the principles of voice acoustics, controls the corresponding terminal devices to transmit and receive voice information via WIFI communication, thereby determining the location of the terminal devices and locating the sound source. This simplifies indoor positioning operations, reduces system deployment costs, increases the accuracy of indoor positioning results, and enhances the convenience of indoor positioning in applications.

[0137] In one possible implementation, each of the terminal devices further includes a voice module;

[0138] To establish a location map of the target area, it is necessary to obtain the initial location information of each terminal device. One feasible implementation method is to determine the relative positions between the terminal devices by analyzing their voice output and reception, and then determine the actual position of each terminal device in the target area, thereby completing the location map. Each terminal device may include a voice module, which may be set or integrated into the terminal device, or it may be a separate voice device located in the same position as the terminal device, or other forms. This application should not limit this.

[0139] Meanwhile, if at least one terminal device in the target area does not include a sound module, the corresponding terminal device can be used only for sound reception, or not used in the process of determining the location map. Accordingly, the "each terminal device" described in this embodiment may not include some of the terminal devices in the previous embodiment, but the number still needs to be at least two, and at least one of them should include a sound module. In addition, to ensure the effectiveness of the location map establishment, there should be as many terminal devices in the target area as possible that include a sound module.

[0140] S101 includes:

[0141] According to a preset order and time interval, each terminal device is controlled to send standard voice signals sequentially.

[0142] The process of establishing a target area positioning map requires each terminal device to sequentially send acoustic signals for positioning according to preset rules. Positioning is then completed based on the acoustic signals received by other devices. To ensure that the standard voice signals emitted by each terminal device can be accurately identified, the order and time interval of the standard voice signals sent by each terminal device need to be set. For example, if the maximum distance between terminal devices in a target area is 20 meters, then during the positioning map establishment process, the time interval can be set to any value greater than the maximum distance divided by the speed of sound, and a corresponding order can be set. This ensures that the standard voice signals emitted by each terminal device in the current scenario are received sequentially without mutual interference, reducing the complexity of the algorithm processing. No additional device identification is required; otherwise, it might be necessary to determine the terminal device corresponding to each standard voice signal.

[0143] Acquire the standard voice signal received by each audio module in each of the terminal devices;

[0144] It should be noted that, to improve the accuracy of map creation, the standard voice signals emitted by each terminal device can differ in terms of frequency, harmonics, energy, and other identifying characteristics. The emitted standard voice signals can also include certain semantics, allowing other devices to identify the emitting device. Therefore, the standard voice signal can be correlated with device identity. In this case, a corresponding recognition algorithm can be set without considering the misjudgment problem when standard voice signals emitted by different devices are received by the same device. However, if at least two terminal devices have identical standard voice signals, it is necessary to set the preset order and time interval to avoid confusion between different acoustic signals.

[0145] Based on the standard voice signals received by each terminal device, the first location information of each terminal device is determined;

[0146] The first position information may also include angle information and distance information, or horizontal and vertical coordinates on a two-dimensional plane. For details on how to obtain the angle and distance information, please refer to the relevant description in the next embodiment; it will not be repeated here.

[0147] A positioning map of the target area is established based on the first location information of each terminal device.

[0148] Ultimately, this allows us to obtain the absolute position of each terminal device and the relative position between any two terminal devices, thereby establishing a positioning map of the target area.

[0149] By transmitting and receiving standard voice signals from each terminal device, the location information of each terminal device in the target area can be determined, thereby establishing a positioning map of the target area. This simplifies the establishment of the positioning map, improves the accuracy of the positioning map of the target area, and enhances the convenience of indoor positioning in applications.

[0150] As an optional implementation, the method further includes:

[0151] Determine the network information corresponding to the WIFI accessed by each terminal device;

[0152] Based on the network information corresponding to each terminal device, all the terminal devices to be grouped are grouped to obtain at least one terminal device group. The WIFI connected to the terminal devices in each terminal device group is the same network. In any terminal device group, the number of user terminal devices accessing the WIFI of that terminal device group is greater than or equal to 1.

[0153] Before controlling each terminal device to send standard voice signals sequentially to establish a location map, the terminal devices can be grouped first. Based on the network information corresponding to the WIFI accessed by each terminal device, the WIFI belonging to the same preset group can be determined, and then the grouping of each terminal device accessing the WIFI network of the same preset group can be determined. These terminal devices can access the same WIFI or different WIFIs under the same preset group. The preset group can be set according to the distribution area, user permissions, WIFI type, etc.

[0154] During the grouping process, the current network information of the Wi-Fi network accessed by each device can be referenced, as well as the historical network information of the Wi-Fi network accessed by each device. Based on this, the terminal devices are divided into at least one group. In any given group, the number of user terminal devices accessing the Wi-Fi network of that group is greater than or equal to one. The user terminal device can serve as a medium for generating control signals to control the terminal devices in the same group. It can be in the form of a portable mobile device such as a mobile phone, or a terminal device with an input device such as a touch screen, voice input module, or keyboard.

[0155] The step of controlling each terminal device to sequentially send standard voice signals according to a preset order and time interval includes:

[0156] A preset sequence and time interval are determined, and the generation operation of the first control signal corresponding to each user terminal device is executed according to the preset sequence and time interval;

[0157] The first control signal can be determined directly based on the preset sequence and time interval, or it can be generated and transmitted on the user terminal device through each of the user terminal devices. The preset sequence and time interval can be called or automatically generated according to application habits or operating procedures, or it can be configured by the user in real time through the user terminal device.

[0158] After determining the first control signal, the first control signal corresponding to each user terminal device is sent to all terminal devices belonging to the same device group as that user terminal device, so as to trigger each target terminal device to perform the following operations after receiving the first control signal:

[0159] Standard voice signals are sent sequentially according to the preset order and time interval indicated by the first control signal.

[0160] By grouping the terminal devices into network groups, at least one terminal device group and each terminal device belonging to the corresponding terminal device group are determined. Within each group, a preset order and time interval for each terminal device to send standard voice signals for establishing a positioning map are determined, and a corresponding first control signal is generated. Control is performed through the first control signal, which simplifies the indoor positioning system, reduces the system deployment cost, and improves the convenience of indoor positioning in applications.

[0161] As an optional implementation, the sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module;

[0162] In this embodiment, the sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module. The sound source to be located may also have other implementation forms. In some implementation forms, it may not be necessary to involve the interaction process described in this embodiment. However, when it is necessary to control the sound source to be located through WIFI to achieve related functions, the following steps can be referred to.

[0163] The acquisition of the location voice signal collected by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located includes:

[0164] The acoustic characteristics of the sound source signal that each mobile terminal device needs to send are determined, and the generation operation of the second control signal corresponding to each user terminal device is executed according to the acoustic characteristics.

[0165] The acoustic features include one or more of the following: type, frequency, duration, intensity, and content; see the relevant description in the previous embodiment for details.

[0166] In addition, the second control signal may also include information such as the movement trajectory of the mobile terminal device to achieve mobile positioning function. Mobile positioning can be used as a specific implementation of the solution described in this application, or as a test method during the execution of the solution described in this application to verify accuracy; the specific application direction is not limited.

[0167] After determining the second control signal, the second control signal corresponding to each user terminal device is sent to each mobile terminal device to trigger each mobile terminal device to perform the following operations upon receiving the second control signal:

[0168] The sound source signal is transmitted according to the acoustic characteristics indicated by the second control signal;

[0169] After each of the mobile terminal devices completes the transmission of the sound source signal according to the information indicated by the second control signal, it is necessary to obtain the acquisition and analysis results of the sound source signal of each of the terminal devices in the positioning map in order to determine the positioning voice signal, that is, to obtain the positioning voice signal acquired by the at least two audio receiving modules of each terminal device from the sound source signal.

[0170] By determining the acoustic characteristics of the sound source signal that needs to be sent by each mobile terminal device, a corresponding second control signal is generated and sent to each mobile terminal device. The second control signal controls each mobile terminal device to send the corresponding sound source signal. Finally, the positioning voice signal collected by each terminal device from the sound source signal is obtained, and WIFI-based voice positioning is completed. This simplifies the indoor positioning system, reduces the system deployment cost, and improves the convenience of indoor positioning in application.

[0171] In one possible implementation, determining the first location information of each of the terminal devices based on the standard voice signal received by each of the terminal devices includes:

[0172] The propagation time of the standard voice signal between the terminal devices is determined by a cooperative ranging method, and the first distance between each pair of the terminal devices is determined.

[0173] In the process of establishing a location map, it is necessary to determine the location information of each terminal device. One feasible implementation method is to determine the angle and distance information of each terminal device relative to other terminal devices. Specifically, the distance information can be determined by cooperative ranging or by passive ranging using acoustic radar.

[0174] Passive ranging methods work by emitting sound signals and estimating the round-trip time of the echoes to estimate the distance between a device and an object. Since the energy of the echo attenuates sharply with increasing distance, the effective range of passive ranging is often limited. Furthermore, due to multipath effects, selecting the desired echo from the returned sound signals is also difficult. Therefore, passive ranging methods typically have limitations in indoor positioning applications, while cooperative ranging methods do not have these problems in similar scenarios. The performance of cooperative ranging depends on the physical-level signal design and the application-level signal detection methods.

[0175] Cooperative ranging primarily obtains the relative distance between devices by measuring the time it takes for a sound wave signal to travel from one device to another. Since the speed of sound is known, distance information can be obtained by multiplying the speed by the time. Therefore, cooperative ranging methods can be used to determine the propagation time of the standard voice signal between the terminal devices, and thus determine the initial distance between each pair of terminal devices.

[0176] In collaborative ranging, a commonly used algorithm is the beepbeep algorithm, which achieves centimeter-level ranging accuracy within a 15-meter range, thus making it applicable to the scenario described in this application. Since terminal devices in the same home system typically cannot achieve high-precision time synchronization within 500 microseconds, using the beepbeep algorithm to determine the distance between devices allows multiple terminal devices to simultaneously receive audio and sequentially transmit different standard voice signals at certain delays. By calculating the time difference between the standard voice signals received by different terminal devices from other terminal devices and then subtracting these calculated time differences, the time synchronization error of the multiple terminal devices themselves can be eliminated, yielding the sound propagation delay between the two devices. This optimizes the time calculation error problem caused by the inability to achieve high-precision time synchronization between devices. In addition, algorithms such as RFBeep and SwordFight are also available, and this application should not limit itself to any specific algorithm.

[0177] Using a generalized cross-correlation algorithm, the time when each of the at least two audio modules of each terminal device receives the same standard voice signal is determined, and the first azimuth angle between each pair of terminal devices is determined.

[0178] After determining the first distance, it is also necessary to obtain the first azimuth angle between each terminal device. As mentioned earlier, obtaining the azimuth angle between devices typically requires each device to have at least two receiving modules. The angle can be calculated using the time difference between the arrival of the same acoustic signal at multiple different receiving modules of the same device. Specifically, a generalized cross-correlation algorithm can be used to determine the time when each of the at least two receiving modules of each terminal device receives the same standard speech signal, thereby determining the first azimuth angle between each pair of terminal devices. In this scenario, the time usually refers to the time difference of arrival (TDOA). From this, the azimuth angle of the sound source relative to the receiving device can be calculated. It should be noted that the generalized cross-correlation algorithm is only one method for angle calculation. High-resolution spectral estimation methods, beamforming methods, and other methods can also be used to determine the first azimuth angle. This application should not limit the specific algorithm used.

[0179] Based on the first distance and the first azimuth angle, a first distance matrix and a first angle matrix are obtained for each of the terminal devices, and the first position information of each of the terminal devices is determined based on the first distance matrix and the first angle matrix.

[0180] In fact, the first position information of each terminal device can be determined directly without the matrix acquisition step. To facilitate the operation of the algorithm and data processing, and to make the data more intuitive, the first distance and first orientation angle between each pair of terminal devices can be summarized and listed in matrix form.

[0181] By using a collaborative ranging method, the first distance between each pair of terminal devices is determined, and by using a generalized cross-correlation algorithm, the first azimuth angle between each pair of terminal devices is determined, thereby improving the accuracy of the positioning map and enhancing the convenience of indoor positioning in applications.

[0182] In some scenarios, under the application requirements of 3D positioning, the height can be estimated by the commonly used locations of terminal devices. For example, robot vacuums and electric heaters are near-ground devices, while clothes racks and air conditioners are at ceiling height. The estimated height can then be used in calculations to obtain the position of the sound source to be located in 3D space. However, this method is usually not very accurate, resulting in a large error in the final target position. Therefore, if it is necessary to locate the sound source in 3D space, a 3D positioning map needs to be established according to the aforementioned implementation method. In this case, each terminal device needs at least three non-coplanar sound receiving modules in a preset direction to determine the height information in order to achieve positioning in the 3D scene. The preset direction is perpendicular to the ground. Therefore, the following implementation method, based on any of the above implementation methods, explains how to improve the accuracy of 3D positioning.

[0183] In one possible implementation, there are at least three microphone modules, wherein the at least three microphone modules are not coplanar in a preset direction, and the preset direction is perpendicular to the ground; determining the first location information of each terminal device based on the standard voice signal received by each terminal device further includes:

[0184] By using a cooperative ranging method, the propagation time of the standard voice signal between the terminal devices is determined, and the second distance between each pair of the terminal devices is determined.

[0185] Using a generalized cross-correlation algorithm, the time when the at least three audio modules of each terminal device receive the same standard voice signal is determined, and the first azimuth angle and first pitch angle between each pair of terminal devices are determined.

[0186] Based on the second distance, the first azimuth angle, and the first pitch angle, a second distance matrix and a second angle matrix are obtained for each terminal device, and the first position information of each terminal device is determined based on the second distance matrix and the second angle matrix.

[0187] Based on known targets such as terminal devices, the methods for obtaining the location of the target to be located may include the following: obtaining the horizontal and vertical coordinates and height coordinates of the target to be located relative to the known target on a standard projection plane; or obtaining the distance, direction angle, and height coordinates of the target to be located relative to the known target on a standard projection plane; or directly obtaining the distance, azimuth angle, and pitch angle of the target to be located relative to the known target. According to the application scenario provided in this application, the third solution is a feasible implementation method. Specifically, in this implementation method, the second distance, first azimuth angle, and first pitch angle between each pair of terminal devices are obtained to establish a positioning map, and the second azimuth angle and second pitch angle of the sound source to be located relative to each terminal device are determined to determine the target location. The specific methods for obtaining distance and angle information and establishing the positioning map are not elaborated further; please refer to the relevant descriptions of other implementation methods.

[0188] S103 includes:

[0189] Based on the timing of the location voice signal acquired by the at least three sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle and the second pitch angle of the sound source to be located relative to each of the terminal devices are determined by a generalized cross-correlation algorithm.

[0190] In this embodiment, the second position information includes a second azimuth angle and a second elevation angle. A positioning ray is formed by acquiring the second azimuth angle and the second elevation angle, thereby completing the positioning. Therefore, based on the time of the positioning voice signal obtained by the at least three sound receiving modules in each terminal device from the sound source signal sent by the sound source to be located, the second azimuth angle and the second elevation angle of the sound source to be located relative to each terminal device can be determined by a generalized cross-correlation algorithm.

[0191] S104 includes:

[0192] Based on the second azimuth angle, the second elevation angle, and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0193] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0194] If there is only one intersection point, it can be directly determined as the target location. If there are at least two intersection points, refer to the relevant description in Embodiment 2 to process the intersection points and positioning rays to obtain the final target location.

[0195] By using at least three non-coplanar sound receiving modules in the height direction on each terminal device, a three-dimensional positioning map is determined, and the azimuth and elevation angles of the sound source to be located are determined. In this way, multiple positioning rays are determined to obtain the target position, realizing the application in three-dimensional space, reducing the system deployment cost, improving the accuracy of indoor positioning in three-dimensional space, and enhancing the convenience of indoor positioning in application.

[0196] This embodiment provides a WIFI-based indoor voice positioning method. The method includes: establishing a positioning map of a target area, wherein at least two terminal devices are set in the target area, and the positioning map includes first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module, wherein the communication module is a module for transmitting voice data based on WIFI; acquiring positioning voice signals obtained by the at least two audio receiving modules of each terminal device from sound source signals sent by the sound source to be located; determining second location information of the sound source to be located relative to each terminal device in the positioning map based on the positioning voice signals acquired by each terminal device; and determining the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map. The method involves establishing a positioning map using existing terminal devices in the target area, communicating between terminal devices via a wireless local area network and transmitting corresponding voice commands, then collecting sound signals of the sound source to be located using these terminal devices, determining the position of the sound source to be located relative to each terminal device in the positioning map, and finally determining the target location of the sound source to be located.

[0197] As can be seen, this application utilizes existing terminal equipment and, based on the principle of voice acoustics, can control the corresponding terminal equipment to transmit and receive voice information via WIFI communication, thereby determining the location of the terminal equipment and locating the sound source. This simplifies indoor positioning operations, reduces system deployment costs, increases the accuracy of indoor positioning results, and enhances the convenience of indoor positioning in applications.

[0198] Example 2

[0199] Please see Figure 3 , Figure 3 This is a flowchart illustrating another WIFI-based indoor voice positioning method disclosed in an embodiment of the present invention. Figure 3 As shown, based on any other embodiment, the method includes:

[0200] S201. Establish a location map of the target area;

[0201] S202. Obtain the positioning voice signal obtained by the sound source signal sent by the at least two sound receiving modules of each terminal device to the sound source to be located;

[0202] In Embodiment 2 of the present invention, the description of steps 201 and 202 is the same as that of steps 101 and 102 in Embodiment 1. Embodiment 2 of the present invention will not repeat the description.

[0203] S203. Based on the time of the location speech signal obtained by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle of the sound source to be located relative to each of the terminal devices is determined by a generalized cross-correlation algorithm.

[0204] The second location information includes a second azimuth angle, which indicates the direction of the sound source to be located relative to each terminal device in the location map. Specifically, in obtaining the second location information, the second azimuth angle of the sound source to be located relative to each terminal device can be determined by using a generalized cross-correlation algorithm based on the time of the location voice signal acquired by the at least two audio receiving modules in each terminal device from the sound source signal sent by the sound source to be located.

[0205] S204. Based on the second azimuth angle and the first position information of each terminal device in the target area, determine multiple positioning rays;

[0206] S205. Determine the target location of the sound source to be located in the target area based on the intersection of the multiple positioning rays.

[0207] Based on the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined. Finally, based on the intersection of the multiple positioning rays, the target position of the sound source to be located in the target area is determined. For a detailed description, please refer to the relevant part of Embodiment 1, which will not be repeated here.

[0208] Furthermore, if the number of positioning intersections is at least two, please refer to the relevant description in the next implementation method.

[0209] The WIFI-based indoor voice positioning method described in this embodiment determines the azimuth angle of the sound source to be located relative to the terminal device by measuring the time when the two receiving modules of the terminal device receive the same sound signal. Then, it determines multiple positioning rays by using the second azimuth angle and the first position information of each terminal device in the target area. The target position of the sound source to be located is determined based on the intersection of the positioning rays. This simplifies the indoor positioning system, improves the accuracy of indoor positioning, and enhances the convenience of indoor positioning in applications.

[0210] In one possible implementation, S205 includes:

[0211] If the multiple positioning rays have at least two intersection points, the positioning area of ​​the sound source to be located is determined based on the intersection points of the multiple positioning rays.

[0212] Based on the positioning area, the second location information of the sound source to be located is determined.

[0213] Optionally, if the multiple positioning rays can only form two intersection points, the midpoint of the two intersection points can be directly determined as the second location information; if the multiple positioning rays can form three or more intersection points, the positioning area of ​​the sound source to be located can be determined based on the intersection points of the multiple positioning rays, or a combination of one or two of the multiple positioning rays themselves. Then, the second location information of the sound source to be located is determined based on the positioning area. A primary method for determining the positioning area is to use the area enclosed by the intersection points of the aforementioned multiple positioning rays or the multiple positioning rays themselves as the positioning area.

[0214] In most cases, the second location information of the sound source to be located will fall within the location area enclosed by intersections or rays. However, in a few cases, such as when the centroid of the location area is taken, it may fall outside. The means of determining the second location information based on the location area may include, but are not limited to, one or more combinations of the following: determining the point with the shortest sum of distances to all location rays forming the location area, determining the point with the highest probability in the location area, determining the centroid of the location area, determining the midpoint of all intersections forming the location area, determining the center of the largest inscribed circle of the location area, and determining the center of the smallest circumscribed circle of the location area.

[0215] By using the intersection of multiple positioning rays, the positioning area of ​​the sound source to be located is determined, and based on the positioning area, the second location information of the sound source to be located is determined, which improves the accuracy of indoor positioning and enhances the convenience of indoor positioning in application.

[0216] If the sound source to be located moves within the target area, its trajectory can be recorded, thereby identifying multiple terminal devices that are currently less than a preset distance from the sound source. The identified terminal devices can then provide the next step of positioning services or other tasks.

[0217] In one possible implementation, after S103, the method further includes:

[0218] If the second location information changes within a preset time period, the trajectory of the sound source to be located is determined.

[0219] If the second location information changes within a preset time period, the trajectory of the sound source to be located can be determined according to the corresponding algorithm. At the same time, the trajectory can be recorded so that the system can identify the usage habits of different users through the characteristics of the trajectory.

[0220] Based on the change trajectory, the target terminal device among the at least two terminal devices is determined, and the distance between the target terminal device and the sound source to be located is less than a preset distance;

[0221] The determination of target terminal devices can also be based on the order of distance, determining a preset number of terminal devices as target terminal devices from near to far, or it can be a combination of preset number and preset distance.

[0222] Based on the first location information of the target terminal device and the second location information of the sound source to be located relative to the target terminal device, the target location of the sound source to be located in the target area is determined.

[0223] Locating the sound source by identifying the target terminal devices can reduce the amount of data that the method needs to process. The positioning task can be completed by only using the closest target terminal devices, which simplifies the method and improves the accuracy of positioning.

[0224] By selecting and updating the target terminal equipment, the accuracy of the target terminal equipment in detecting the sound source to be located can be ensured, and the data processed in the indoor positioning process can be simplified, thereby improving the accuracy of indoor positioning and enhancing the convenience of indoor positioning in application.

[0225] It should be noted that this application can also analyze certain features of the location voice signal, such as the variation patterns of frequency, intensity, and harmonics, or semantically meaningful instructions, such as voice control. In this case, the location voice signal can be analyzed and processed according to a corresponding preset algorithm to obtain the action or command indicated by the location voice signal, thereby controlling the terminal device to perform corresponding operations or call corresponding resources.

[0226] This embodiment provides a WIFI-based indoor voice positioning method. The method includes: establishing a positioning map of a target area; acquiring positioning voice signals collected by at least two receiving modules in each terminal device from sound source signals sent by the sound source to be located; determining a second azimuth angle of the sound source to be located relative to each terminal device using a generalized cross-correlation algorithm based on the time of the positioning voice signals collected by the at least two receiving modules in each terminal device from the sound source signals sent by the sound source to be located; determining multiple positioning rays based on the second azimuth angle and the first position information of each terminal device in the target area; and determining the target position of the sound source to be located in the target area based on the intersection of the multiple positioning rays. By determining the azimuth angle of the sound source to be located relative to the terminal device through the time when the two receiving modules of the terminal device receive the same sound signal, and by determining multiple positioning rays based on the second azimuth angle and the first position information of each terminal device in the target area, and by determining the target position of the sound source to be located based on the intersection of the positioning rays, the method simplifies the indoor positioning system, improves the accuracy of indoor positioning, and enhances the convenience of indoor positioning in applications.

[0227] Example 3

[0228] Embodiment 3 of the present invention also provides an indoor positioning device to implement the aforementioned method; please refer to [link to embodiment 3]. Figure 4 , Figure 4 This is a structural schematic diagram of an indoor positioning device disclosed in an embodiment of the present invention. Figure 4 As shown, based on any other embodiment, the apparatus includes:

[0229] Map creation module 31 is used to create a positioning map of a target area. The target area is equipped with at least two terminal devices. The positioning map includes the first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module. The communication module is a module for transmitting voice data based on WIFI.

[0230] The sound acquisition module 32 is used to acquire the positioning voice signal obtained by acquiring the sound source signal sent by the at least two sound receiving modules in each of the terminal devices to be located;

[0231] The location determination module 33 is used to determine the second location information of the sound source to be located relative to each terminal device in the location map based on the location voice signals collected by each terminal device.

[0232] The location determination module 33 is further configured to determine the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map.

[0233] This implementation utilizes existing terminal equipment and, based on the principles of voice acoustics, controls the corresponding terminal equipment to transmit and receive voice information via WIFI communication, thereby determining the location of the terminal equipment and locating the sound source. This simplifies indoor positioning operations, reduces system deployment costs, increases the accuracy of indoor positioning results, and enhances the convenience of indoor positioning in applications.

[0234] In one possible implementation, each of the terminal devices further includes a voice module, and the map building module 31 includes:

[0235] The transmitting unit is used to control each of the terminal devices to transmit standard voice signals sequentially according to a preset order and time interval;

[0236] The acquisition unit is used to acquire the standard voice signal received by each audio module in each of the terminal devices;

[0237] The positioning unit is used to determine the first location information of each terminal device based on the standard voice signal received by each terminal device.

[0238] The map building unit is used to build a positioning map of the target area based on the first location information of each terminal device.

[0239] By transmitting and receiving standard voice signals from each terminal device, the location information of each terminal device in the target area can be determined, thereby establishing a positioning map of the target area. This simplifies the establishment of the positioning map, improves the accuracy of the positioning map of the target area, and enhances the convenience of indoor positioning in applications.

[0240] Please see Figure 5 , Figure 5 This is a schematic diagram of another indoor positioning device disclosed in an embodiment of the present invention. Figure 5 As shown, in an optional implementation, the device further includes a network determination module 34, used for:

[0241] Determine the network information corresponding to the WIFI accessed by each terminal device;

[0242] Based on the network information corresponding to each terminal device, all the terminal devices to be grouped are grouped to obtain at least one terminal device group. The WIFI connected to the terminal devices in each terminal device group is the same network. In any terminal device group, the number of user terminal devices accessing the WIFI of that terminal device group is greater than or equal to 1.

[0243] The sending unit controls the specific method by which each terminal device sequentially sends standard voice signals according to a preset order and time interval, including:

[0244] A preset sequence and time interval are determined, and the generation operation of the first control signal corresponding to each user terminal device is executed according to the preset sequence and time interval;

[0245] After determining the first control signal, the first control signal corresponding to each user terminal device is sent to all terminal devices belonging to the same device group as that user terminal device, so as to trigger each target terminal device to perform the following operations after receiving the first control signal:

[0246] Standard voice signals are sent sequentially according to the preset order and time interval indicated by the first control signal.

[0247] By grouping the terminal devices into network groups, at least one terminal device group and each terminal device belonging to the corresponding terminal device group are determined. Within each group, a preset order and time interval for each terminal device to send standard voice signals for establishing a positioning map are determined, and a corresponding first control signal is generated. Control is performed through the first control signal, which simplifies the indoor positioning system, reduces the system deployment cost, and improves the convenience of indoor positioning in applications.

[0248] As an optional implementation, the sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module;

[0249] The specific method by which the sound acquisition module acquires the location voice signal collected by the sound source signal sent by the at least two sound receiving modules in each of the terminal devices to be located, includes:

[0250] The acoustic characteristics of the sound source signal that each mobile terminal device needs to send are determined, and the generation operation of the second control signal corresponding to each user terminal device is executed according to the acoustic characteristics.

[0251] The acoustic features include one or more of the following: type, frequency, duration, intensity, and content;

[0252] After determining the second control signal, the second control signal corresponding to each user terminal device is sent to each mobile terminal device to trigger each mobile terminal device to perform the following operations upon receiving the second control signal:

[0253] The sound source signal is transmitted according to the acoustic characteristics indicated by the second control signal;

[0254] The location-based voice signal is obtained from the sound source signal collected by the at least two audio receiving modules in each of the terminal devices.

[0255] By determining the acoustic characteristics of the sound source signal that needs to be sent by each mobile terminal device, a corresponding second control signal is generated and sent to each mobile terminal device. The second control signal controls each mobile terminal device to send the corresponding sound source signal. Finally, the positioning voice signal collected by each terminal device from the sound source signal is obtained, and WIFI-based voice positioning is completed. This simplifies the indoor positioning system, reduces the system deployment cost, and improves the convenience of indoor positioning in application.

[0256] In one possible implementation, the positioning unit includes:

[0257] The distance determination subunit is used to determine the propagation time of the standard voice signal between the terminal devices through a cooperative ranging method, and to determine the first distance between each pair of the terminal devices.

[0258] An angle determination subunit is used to determine, through a generalized cross-correlation algorithm, the time when the at least two audio modules of each terminal device receive the same standard voice signal, and to determine the first azimuth angle between each pair of terminal devices.

[0259] The location determination subunit is used to obtain a first distance matrix and a first angle matrix for each terminal device based on the first distance and the first azimuth angle, and to determine the first location information of each terminal device based on the first distance matrix and the first angle matrix.

[0260] By using a collaborative ranging method, the first distance between each pair of terminal devices is determined, and by using a generalized cross-correlation algorithm, the first azimuth angle between each pair of terminal devices is determined, thereby improving the accuracy of the positioning map and enhancing the convenience of indoor positioning in applications.

[0261] In one possible implementation, there are at least three microphone modules, wherein at least three microphone modules are not coplanar in a preset direction, which is perpendicular to the ground.

[0262] The distance determination subunit is also used to determine the propagation time of the standard voice signal between the terminal devices through a cooperative ranging method, and to determine the second distance between each pair of the terminal devices.

[0263] The angle determination subunit is also used to determine, through a generalized cross-correlation algorithm, the time when the at least three audio modules of each terminal device receive the same standard voice signal, and to determine the first azimuth angle and the first pitch angle between each pair of terminal devices;

[0264] The position determination subunit is further configured to obtain a second distance matrix and a second angle matrix for each terminal device based on the second distance, the first azimuth angle and the first pitch angle, and determine the first position information of each terminal device based on the second distance matrix and the second angle matrix.

[0265] The position determination module 33 is also used for:

[0266] Based on the timing of the location voice signal acquired by the at least three sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle and the second pitch angle of the sound source to be located relative to each of the terminal devices are determined by a generalized cross-correlation algorithm.

[0267] The position determination module 33 is also used for:

[0268] Based on the second azimuth angle, the second elevation angle, and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0269] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0270] By using at least three non-coplanar sound receiving modules in the height direction on each terminal device, a three-dimensional positioning map is determined, and the azimuth and elevation angles of the sound source to be located are determined. In this way, multiple positioning rays are determined to obtain the target position, realizing the application in three-dimensional space, reducing the system deployment cost, improving the accuracy of indoor positioning in three-dimensional space, and enhancing the convenience of indoor positioning in application.

[0271] In one possible implementation, the second position information includes a second azimuth angle, and the position determination module 33 is further used for:

[0272] Based on the time of the location voice signal acquired by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle of the sound source to be located relative to each of the terminal devices is determined by a generalized cross-correlation algorithm.

[0273] The position determination module 33 is also used for:

[0274] Based on the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined;

[0275] The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

[0276] By determining the azimuth angle of the sound source to be located relative to the terminal device by receiving the same sound signal from the two receiving modules of the terminal device, and by using the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined. The target position of the sound source to be located is determined based on the intersection of the positioning rays. This simplifies the indoor positioning system, improves the accuracy of indoor positioning, and enhances the convenience of indoor positioning in application.

[0277] In one possible implementation, the position determination module 33 is also used for:

[0278] If the multiple positioning rays have at least two intersection points, the positioning area of ​​the sound source to be located is determined based on the intersection points of the multiple positioning rays.

[0279] Based on the positioning area, the second location information of the sound source to be located is determined.

[0280] By using the intersection of multiple positioning rays, the positioning area of ​​the sound source to be located is determined, and based on the positioning area, the second location information of the sound source to be located is determined, which improves the accuracy of indoor positioning and enhances the convenience of indoor positioning in application.

[0281] In one possible implementation, such as Figure 5 As shown, the device also includes a trajectory determination module 35;

[0282] The trajectory determination module 35 is used for:

[0283] After the location determination module 33 determines the second location information of the sound source to be located relative to each terminal device in the location map.

[0284] If the second location information changes within a preset time period, the trajectory of the sound source to be located is determined.

[0285] Based on the change trajectory, the positioning terminal device among the at least two terminal devices is determined, and the distance between the positioning terminal device and the sound source to be located is less than a preset distance;

[0286] Based on the first location information of the positioning terminal device and the second location information of the sound source to be located relative to the positioning terminal device, the target location of the sound source to be located in the target area is determined.

[0287] By selecting and updating positioning terminal equipment, the accuracy of the positioning terminal equipment in detecting the sound source to be located can be ensured, and the data processed in the indoor positioning process can be simplified, thereby improving the accuracy of indoor positioning and enhancing the convenience of indoor positioning in application.

[0288] Example 4

[0289] Please see Figure 6 , Figure 6 This is a structural schematic diagram of another indoor positioning device disclosed in an embodiment of the present invention. For example... Figure 6 As shown, the indoor positioning device may include:

[0290] The device includes a processor 291 and a memory 292 storing executable program code; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 is coupled to the memory 292, and the processor 291 can call logical instructions (executable program code) in the memory 292 to execute the WIFI-based indoor voice positioning method described in any of the above embodiments.

[0291] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0292] The memory 292, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, thereby implementing the methods in the above-described method embodiments.

[0293] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.

[0294] This invention also provides a computer-readable storage medium storing computer-executable instructions, which, when invoked, are used to implement the method described in any of the embodiments.

[0295] This invention also discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the WIFI-based indoor voice positioning method described in any embodiment.

[0296] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0297] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0298] Finally, it should be noted that the indoor voice positioning method and device based on WIFI disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A WIFI-based indoor voice positioning method, characterized in that, The method includes: A positioning map of a target area is established, wherein at least two terminal devices are set up in the target area, and the positioning map includes the first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module, wherein the communication module is a module for transmitting voice data based on WIFI. Acquire the location voice signal collected by the sound source signal sent by the sound source to be located by the at least two sound receiving modules in each of the terminal devices; Based on the positioning voice signals collected by each of the terminal devices, the second location information of the sound source to be located relative to each terminal device in the positioning map is determined; Based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map, the target location of the sound source to be located in the target area is determined. The establishment of a location map of the target area includes: According to a preset order and time interval, each terminal device is controlled to send standard voice signals sequentially. Acquire the standard voice signal received by each audio module in each of the terminal devices; Based on the standard voice signals received by each terminal device, the first location information of each terminal device is determined; A positioning map of the target area is established based on the first location information of each terminal device. The step of determining the first location information of each terminal device based on the standard voice signal received by each terminal device includes: The propagation time of the standard voice signal between the terminal devices is determined by a cooperative ranging method, and the first distance between each pair of the terminal devices is determined. Using a generalized cross-correlation algorithm, the time when each of the at least two audio modules of each terminal device receives the same standard voice signal is determined, and the first azimuth angle between each pair of terminal devices is determined. Based on the first distance and the first azimuth angle, a first distance matrix and a first angle matrix of each terminal device are obtained, and based on the first distance matrix and the first angle matrix, the first position information of each terminal device is determined. At least three of the aforementioned sound receiving modules are not coplanar in a preset direction, which is perpendicular to the ground; determining the first location information of each of the aforementioned terminal devices based on the standard voice signal received by each of the terminal devices further includes: By using a cooperative ranging method, the propagation time of the standard voice signal between the terminal devices is determined, and the second distance between each pair of the terminal devices is determined. Using a generalized cross-correlation algorithm, the time when the at least three audio modules of each terminal device receive the same standard voice signal is determined, and the first azimuth angle and first pitch angle between each pair of terminal devices are determined. Based on the second distance, the first azimuth angle, and the first pitch angle, a second distance matrix and a second angle matrix are obtained for each terminal device, and the first position information of each terminal device is determined based on the second distance matrix and the second angle matrix. The step of determining the second location information of the sound source to be located relative to each terminal device in the positioning map based on the positioning voice signals collected by each of the terminal devices includes: Based on the timing of the location voice signal acquired by the at least three sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle and the second pitch angle of the sound source to be located relative to each of the terminal devices are determined by a generalized cross-correlation algorithm. The step of determining the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the positioning map includes: Based on the second azimuth angle, the second elevation angle, and the first position information of each terminal device in the target area, multiple positioning rays are determined; The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

2. The method according to claim 1, characterized in that, The method further includes: Determine the network information corresponding to the WIFI accessed by each terminal device; Based on the network information corresponding to each terminal device, all terminal devices to be grouped are grouped to obtain at least one terminal device group. The WIFI connected to the terminal devices in each terminal device group is the same network. In any terminal device group, the number of user terminal devices accessing the WIFI of that terminal device group is greater than or equal to 1. The step of controlling each terminal device to sequentially send standard voice signals according to a preset order and time interval includes: A preset sequence and time interval are determined, and the generation operation of the first control signal corresponding to each user terminal device is executed according to the preset sequence and time interval; After determining the first control signal, the first control signal corresponding to each user terminal device is sent to all terminal devices belonging to the same device group as that user terminal device, so as to trigger each target terminal device to perform the following operations after receiving the first control signal: Standard voice signals are sent sequentially according to the preset order and time interval indicated by the first control signal.

3. The method according to claim 2, characterized in that, The sound source to be located includes at least one mobile terminal device that can access WIFI and has a sound module; The acquisition of the location voice signal collected by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located includes: The acoustic characteristics of the sound source signal that each mobile terminal device needs to send are determined, and the generation operation of the second control signal corresponding to each user terminal device is executed according to the acoustic characteristics. The acoustic features include one or more of the following: type, frequency, duration, intensity, and content; After determining the second control signal, the second control signal corresponding to each user terminal device is sent to each mobile terminal device to trigger each mobile terminal device to perform the following operations upon receiving the second control signal: The sound source signal is transmitted according to the acoustic characteristics indicated by the second control signal; The location-based voice signal is obtained from the sound source signal collected by the at least two audio receiving modules in each of the terminal devices.

4. The method according to claim 1, characterized in that, The second location information includes a second azimuth angle. Determining the second location information of the sound source to be located relative to each terminal device in the location map based on the location voice signals collected by each terminal device includes: Based on the time of the location voice signal acquired by the at least two sound receiving modules in each of the terminal devices from the sound source signal sent by the sound source to be located, the second azimuth angle of the sound source to be located relative to each of the terminal devices is determined by a generalized cross-correlation algorithm. The step of determining the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each smart device in the positioning map includes: Based on the second azimuth angle and the first position information of each terminal device in the target area, multiple positioning rays are determined; The target location of the sound source to be located in the target area is determined based on the intersection of the multiple positioning rays.

5. The method according to claim 4, characterized in that, Determining the target location of the sound source to be located in the target area based on the intersection of the multiple positioning rays includes: If the multiple positioning rays have at least two intersection points, the positioning area of ​​the sound source to be located is determined based on the intersection points of the multiple positioning rays. Based on the positioning area, the second location information of the sound source to be located is determined.

6. The method according to any one of claims 1-5, characterized in that, After determining the second location information of the sound source to be located relative to each terminal device in the location map, the method further includes: If the second location information changes within a preset time period, the trajectory of the sound source to be located is determined. Based on the change trajectory, the positioning terminal device among the at least two terminal devices is determined, and the distance between the positioning terminal device and the sound source to be located is less than a preset distance; Based on the first location information of the positioning terminal device and the second location information of the sound source to be located relative to the positioning terminal device, the target location of the sound source to be located in the target area is determined.

7. An indoor positioning device, characterized in that, The apparatus is used to perform the method as described in any one of claims 1-6, and the apparatus comprises: A map creation module is used to create a location map of a target area. The target area is equipped with at least two terminal devices. The location map includes the first location information of each terminal device in the target area. Each terminal device includes at least two audio receiving modules and at least one communication module. The communication module is a module for transmitting voice data based on WIFI. The sound acquisition module is used to acquire the positioning voice signal obtained by acquiring the sound source signal sent by the at least two sound receiving modules of each terminal device to the sound source to be located; The location determination module is used to determine the second location information of the sound source to be located relative to each terminal device in the location map based on the location voice signals collected by each terminal device. The location determination module is further configured to determine the target location of the sound source to be located in the target area based on the first location information of each terminal device in the target area and the second location information of the sound source to be located relative to each terminal device in the location map.

Images