A device positioning method, a smart terminal, and a storage medium

Abstract

This invention discloses a device positioning method, a smart terminal, and a storage medium. The method includes: acquiring a set of audio files collected by multiple devices from the current environment simultaneously, wherein the audio file set contains multiple audio files; determining multiple candidate devices corresponding to the audio file set based on the gain ratio of each audio file; performing speech recognition on the audio files to generate corresponding text files; and determining the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices. This invention determines the target device corresponding to a user's speech based on the gain ratio of that speech, thereby achieving the positioning of the target device among multiple devices.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a device positioning method, a smart terminal, and a storage medium. Background Technology

[0002] Many devices now have voice recognition capabilities, capable of capturing user speech and executing corresponding functions. However, users need to individually enable voice recognition for each device and disable it afterward. Given the wide variety of smart devices available, including smartphones, smart TVs, and smart air conditioners, requiring each device to be turned on and off for voice recognition is cumbersome. Therefore, some manufacturers have introduced devices capable of real-time voice capture and recognition. However, real-time voice capture and recognition involves collecting highly varied and complex information, making it difficult to accurately determine whether the user's voice is a specific device command. Furthermore, even after identifying a voice command, it's difficult to pinpoint which device it was directed to. This presents challenges when performing subsequent actions based on the command. Summary of the Invention

[0003] The main objective of this invention is to provide a device positioning method, a smart terminal, and a storage medium, aiming to solve the problem that the existing technology cannot accurately locate multiple devices through voice recognition.

[0004] To achieve the above objectives, the present invention provides a device positioning method, the device positioning method comprising the following steps:

[0005] Acquire a set of audio files collected by multiple devices from the current environment at the same time, wherein the audio file set contains multiple audio files;

[0006] Based on the gain ratio of each audio file, multiple candidate devices corresponding to the audio file set are determined in the device;

[0007] Perform speech recognition on the audio file to generate a corresponding text file;

[0008] Based on the device command set corresponding to the candidate devices, determine the target device corresponding to the text file among the candidate devices.

[0009] Optionally, the device location method, wherein determining multiple candidate devices corresponding to the audio file set based on the gain ratio of each audio file specifically includes:

[0010] Calculate the distance weight value corresponding to each device based on the gain ratio of each audio file;

[0011] The device with the smallest corresponding distance weight value is selected as the candidate device.

[0012] Optionally, in the device positioning method, calculating the distance weight value corresponding to each device based on the gain ratio of each audio file specifically includes:

[0013] Calculate the gain ratio based on the audio decibel level of the audio file;

[0014] When the gain ratio is greater than a preset first ratio threshold, the distance weight value corresponding to the device is a preset maximum weight value;

[0015] When the gain ratio is greater than a preset second ratio threshold and less than or equal to the first ratio threshold, the distance weight value corresponding to the device is a preset intermediate weight value.

[0016] When the gain ratio is less than or equal to the second ratio threshold, the distance weight value corresponding to the device is the preset minimum weight value.

[0017] Optionally, in the device positioning method, the step of performing speech recognition on the audio file to generate a corresponding text file specifically includes:

[0018] Based on preset audio filtering rules, determine the qualified files among the audio files;

[0019] The qualified file is subjected to speech recognition to generate a text file corresponding to the audio file.

[0020] Optionally, in the device location method, the device command set includes multiple device commands and the number of times each device command is invoked; determining the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices specifically includes:

[0021] The device command with the highest number of calls in each device command set is selected as the candidate command.

[0022] Calculate the similarity value between the candidate command corresponding to the candidate device and the text file;

[0023] The candidate device with the highest similarity value is selected as the target device corresponding to the text file.

[0024] Optionally, the device positioning method further includes:

[0025] Acquire image files of the current environment captured within the same time period;

[0026] Calculate the physical distance between the target device and the user based on the image file;

[0027] Based on the physical distance, determine the corresponding adjustment parameters.

[0028] Optionally, the device positioning method, after determining the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices, further includes:

[0029] Based on the candidate command corresponding to the target device, control the target device to perform the corresponding operation.

[0030] Optionally, in the device positioning method, the step of controlling the target device to perform a corresponding operation based on the candidate command corresponding to the target device specifically includes:

[0031] Based on preset parameter filtering rules, determine whether instruction parameters exist in the text file;

[0032] If so, then based on the candidate command corresponding to the target device and the instruction parameters, control the target device to perform the corresponding operation;

[0033] If not, then based on the adjustment parameters and the candidate command corresponding to the target device, control the target device to perform the corresponding operation.

[0034] In addition, to achieve the above objectives, the present invention also provides a smart terminal, wherein the smart terminal includes: a memory, a processor, and a device positioning program stored in the memory and executable on the processor, wherein when the device positioning program is executed by the processor, it implements the steps of the device positioning method described above.

[0035] In addition, to achieve the above objectives, the present invention also provides a storage medium, wherein the storage medium stores a device positioning program, which, when executed by a processor, implements the steps of the device positioning method described above.

[0036] This invention first acquires a set of audio files collected by multiple devices simultaneously. Then, based on the gain ratio of the audio files, it identifies multiple candidate devices corresponding to the audio file set. Since the gain ratio of the audio files is determined by the distance between the acquiring device and the sound source, the distance between each device and the user can be determined using the gain ratio, thereby identifying the candidate devices corresponding to the audio file set. Simultaneously with identifying the candidate devices, speech recognition is performed on the audio files to generate corresponding text files. Then, based on the device command set corresponding to the device, the similarity between the device commands in the device command set and the text file is calculated, thereby identifying the target device corresponding to the text file. This invention combines the properties and content of the audio text itself to determine the target device corresponding to the user's voice, thus completing device localization.

[0037] Furthermore, when calculating the similarity between device commands and the text file, the device command with the highest number of calls is selected as a candidate command for similarity calculation, thereby reducing the probability of conflicts caused by similar device commands existing in different sets of device commands. During voice capture, images are also taken, and the distance between the target device and the user in the image file is used to determine adjustment parameters. If no parameters are found in the text file, the adjustment parameters are used as the parameters executed by the target device. Therefore, even when the user issues vague commands lacking parameters, a suitable user experience can be provided. Attached Figure Description

[0038] Figure 1 This is a flowchart of the first embodiment of the device positioning method provided by the present invention;

[0039] Figure 2 This is a schematic diagram of the operating environment of a preferred embodiment of the smart terminal of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0041] The device positioning method described in the preferred embodiment of the present invention, such as... Figure 1 As shown, the device positioning method includes the following steps:

[0042] Step S100: Obtain a set of audio files collected by multiple devices from the current environment at the same time.

[0043] Specifically, in this embodiment, the execution entity is a device positioning program installed on a smart TV. The devices include a smart TV, a smart air conditioner, a smart refrigerator, and a smartphone, and these devices are interconnected. When the user selects to enable the voice recognition function, the smartphone, smart air conditioner, and smart TV all activate their microphones to collect audio from the current environment. Since the environment is fixed, and the user's speech at any given time is consistent, the content of the audio files collected by the devices should also be identical. Then, the audio files collected at the same time are integrated to generate an audio file set.

[0044] Step S200: Based on the gain ratio of each audio file, determine multiple candidate devices in the device that correspond to the audio file set.

[0045] Specifically, since the distance between users and different devices varies, and a user typically needs to be closer to a particular device, and given the different performance levels of each device, they generally apply audio gain to the original audio to obtain a better audio file. Therefore, the greater the distance between the user and the device, the worse the sound quality of the acquired original audio, and thus the higher the gain ratio applied by the device. The audio file gain ratio is calculated, and based on this ratio, the closest candidate device is determined as the candidate device corresponding to the audio file set.

[0046] Further, step S200 includes:

[0047] Step S210: Calculate the distance weight value corresponding to each device based on the gain ratio of each audio file.

[0048] Specifically, when there are many devices, the quality differences between audio files are not significant. Therefore, this embodiment assigns a distance weight value to each device based on the calculated gain ratio. For example, three distance weight values ​​are preset, and each audio file in the audio file set is assigned a different distance weight value according to the gain ratio. For instance, if a user is standing in front of a smart TV, a smart refrigerator is next to the smart TV, a smartphone is on a shoe cabinet, and a smart air conditioner is installed on the wall, the audio gain ratios corresponding to the audio files collected from these three devices are 1, 1, 5, and 9, respectively. Then, a distance weight is assigned to them. This value can be assigned by pre-setting multiple values ​​or by directly using the reciprocal of the gain ratio, etc.

[0049] Further, step S210 includes:

[0050] Step S211: Calculate the gain ratio based on the audio decibels of the audio file;

[0051] Specifically, decibel (dB) is the unit of amplifier gain. The ratio of amplifier output to input is the amplification factor, measured in "times". The audio decibel level of the audio file can be calculated based on the difference between the original audio and the audio file. Decibels are defined in two ways: voltage amplification and power amplification. The gain differs depending on the definition. For example, in voltage amplification, a gain of 3dB is achieved when the amplification factor is 1.4.

[0052] Step S212: When the gain ratio is greater than the preset first ratio threshold, the distance weight value corresponding to the device is the preset highest weight value.

[0053] Specifically, when the gain ratio is greater than a preset first ratio threshold, for example, the first ratio threshold is 7 and the preset maximum weight value is 7, then the distance weight value corresponding to the smart air conditioner is 7.

[0054] Step S213: When the gain ratio is greater than a preset second ratio threshold and less than or equal to the first ratio threshold, the distance weight value corresponding to the device is a preset intermediate weight value.

[0055] Specifically, when the gain ratio is greater than a preset second ratio threshold and less than or equal to the first ratio threshold, for example, when the second ratio threshold is 4 and the preset intermediate weight value is 4, the distance weight value corresponding to the smartphone is 4.

[0056] Step S214: When the gain ratio is less than or equal to the second ratio threshold, the distance weight value corresponding to the device is the preset minimum weight value.

[0057] Specifically, when the gain ratio is less than or equal to the second ratio threshold, for example, for the smart TV and the smart refrigerator, the preset minimum weight value is 2, then the distance weight value corresponding to the smart TV and the smart refrigerator is 2.

[0058] Step S220: Select the device with the smallest corresponding distance weight value as the candidate device.

[0059] Specifically, the device with the smallest distance weight value is selected; there may be one or several such devices as candidate devices. In this embodiment, these are the smart TV and the smart refrigerator.

[0060] Step S300: Perform speech recognition on the audio file to generate a corresponding text file.

[0061] Specifically, there are many speech recognition algorithms currently available, such as Connectionist Temporal Classification (CTC) and End-to-End models, which are common technologies. They will not be elaborated on here. Their principle is mainly to replace a speech with an acoustic symbol, and then use the corresponding acoustic symbol in a speech segment as the processing object. Based on the relationship between the preceding and following parts, the algorithm determines the text that the acoustic symbol is most likely to correspond to, thereby converting a speech segment into text.

[0062] Further, step S300 includes:

[0063] Step S310: Determine qualified files among the audio files according to preset audio filtering rules.

[0064] Specifically, in this embodiment, the audio file set contains multiple audio files. Due to factors such as distance and noise levels, some audio files may not be suitable for speech recognition. Furthermore, since the different audio files were collected at the same time and contain identical content, the content of any one audio file suitable for speech recognition can be determined. The audio filtering rules may include factors such as audio amplitude, signal-to-noise ratio, and effective voice length, comprehensively considering multiple aspects to select qualified files from the multiple audio files.

[0065] Step S320: Perform speech recognition on the qualified file to generate a text file corresponding to the audio file.

[0066] Specifically, after selecting the qualified documents, the aforementioned speech recognition algorithm is used to perform speech recognition on the qualified documents to generate the text file, thereby determining the content spoken by the user.

[0067] Step S400: Determine the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices.

[0068] Specifically, each candidate device has its corresponding set of device commands, which includes multiple device commands. The text file is then compared with each device command in the device command set corresponding to the candidate device to determine the device commands that are equal to or similar to it. Finally, the closest device command is selected from the device commands that are equal to or similar to those in the text file, and the corresponding device is chosen as the target device.

[0069] Further, step S400 includes:

[0070] Step S410: Select the device command with the highest number of calls in each device command set as the candidate command.

[0071] Specifically, the device command set also includes the invocation count of each device command. For example, the device commands for the smart air conditioner include "inverter mode," "increase temperature," and "increase humidity." Each time a user issues these device commands using voice or buttons, the invocation count for each device command is recorded. The device command with the highest invocation count in each device command set is selected as the candidate command corresponding to the text file.

[0072] Step S420: Calculate the similarity value between the candidate command corresponding to the candidate device and the text file.

[0073] Specifically, there are many ways to calculate the similarity value, such as keyword or word matching. Taking keywords as an example, firstly, keywords are extracted from the text file according to preset keyword rules, and then a similarity algorithm, such as the Euclidean algorithm or the cosine similarity algorithm, is used to calculate the similarity value between the keywords and the candidate commands. Word matching involves comparing the candidate commands with the text file one by one; the more identical words there are, the higher the similarity value.

[0074] Step S430: Select the candidate device with the highest similarity value as the target device corresponding to the text file.

[0075] Specifically, since each candidate device has a corresponding set of device commands, each set of device commands has a candidate command, and each candidate command has a similarity value with the text file, the similarity values ​​are compared, and the candidate device with the highest similarity value is selected as the target device corresponding to the text file.

[0076] Because the device command set contains a large number of device commands, and different device command sets may contain identical device commands, such as "turn up the volume," which is a common function in both smartphones and smart TVs, this device command also exists. Therefore, in this embodiment, to avoid this situation, the text file is compared not with all the device commands in the device command set, but with the most frequently invoked device command, thereby reducing workload and avoiding conflicts.

[0077] Furthermore, the device positioning procedure also performs the following steps:

[0078] Step S510: Acquire image files of the current environment collected within the same time period.

[0079] Specifically, when the device captures audio of the current environment, the device positioning program also acquires image files of the current environment at the same time. The image capture can be performed by these devices or by a device with the device positioning program installed. However, it is worth noting that, to ensure the image file can determine the positional relationship between all devices and the user in the current environment, if the device captures the image file, then all images captured by all devices are used as the image file; if the device performs the image capture, then the device needs to be placed in a position that can capture images of all devices.

[0080] Step S520: Calculate the physical distance between the target device and the user based on the image file.

[0081] Specifically, taking the image files captured by the device as an example, the appearance of the target device is obtained in advance from the network according to the model of the target device. Then, based on the appearance, object recognition and human body recognition are performed in the image files to identify the location of the target device and the user. Then, based on the installation coordinates and other parameters obtained during installation, the physical distance between the target device and the user is calculated. If the image files were captured by the device, a 3D model is performed based on multiple image files captured by the device to obtain a 3D model. Finally, based on the 3D model, the physical distance between the target device and the user is calculated.

[0082] Step S530: Determine the corresponding adjustment parameters based on the physical distance.

[0083] Specifically, taking the smart TV as an example, when a user is close to the smart TV, even if the user's voice command is "adjust brightness," the brightness of the smart TV should not be adjusted too high, otherwise it will harm the user's eyes. Furthermore, parameters such as brightness, volume, and the fan speed and direction of the smart air conditioner can all be determined based on the distance between the user and the device.

[0084] Furthermore, after step S530, the method further includes: controlling the target device to perform a corresponding operation based on the candidate command corresponding to the target device. After determining the corresponding target device based on the text file, the candidate command corresponding to the target device should be the instruction to be issued in the text file. Therefore, the target device can be controlled to perform the corresponding operation based on the candidate command.

[0085] The specific process is as follows:

[0086] Step S531: Determine whether instruction parameters exist in the text file according to the preset parameter filtering rules.

[0087] Specifically, a parameter filtering rule is pre-set to determine the instruction parameters in the text file. For example, the filtering rule is a combination of numbers and units, such as "37 degrees" and "40 decibels". If the target device corresponding to the text file is a smart air conditioner, and the text file is "lower the temperature to 24 degrees", since it contains the number "22" and the unit "degree", it can be determined that there is an instruction parameter in the text file, and that it is "22 degrees".

[0088] Step S532: If yes, then control the target device to perform the corresponding operation according to the candidate command corresponding to the target device and the instruction parameters.

[0089] Specifically, if the text file contains instruction parameters, the target device is controlled to perform the corresponding operation directly based on the candidate instruction and the instruction parameters. For example, the smart air conditioner is controlled to adjust the temperature to 22 degrees Celsius.

[0090] Step S533: If not, then control the target device to perform the corresponding operation according to the adjustment parameters and the candidate command corresponding to the target device.

[0091] Specifically, if the text file contains instruction parameters, the target device is controlled to perform the corresponding operation based on the adjustment parameters determined from the image file and the candidate commands. For example, based on the image file, it is determined that the user is close to the smart air conditioner, so the temperature should not be lowered. Therefore, the adjustment parameter is "24 degrees", and the smart air conditioner is controlled to adjust the temperature to 24 degrees.

[0092] In addition, after execution is completed, the invocation count of the candidate command corresponding to the target device is incremented by one.

[0093] This embodiment can intelligently adjust the parameters of the target device based on the distance between the user and the device after the target device has been determined. Even when the user's instructions are unclear, it can still make appropriate operations based on the actual situation.

[0094] Furthermore, such as Figure 2 As shown, based on the above device positioning method, the present invention also provides a smart terminal, which includes a processor 10, a memory 20 and a display 30. Figure 2 Only some components of the smart terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0095] In some embodiments, the memory 20 may be an internal storage unit of the smart terminal, such as a hard drive or memory. In other embodiments, the memory 20 may be an external storage device of the smart terminal, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the smart terminal. Further, the memory 20 may include both internal and external storage units of the smart terminal. The memory 20 is used to store application software and various types of data installed on the smart terminal, such as the program code installed on the smart terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a device positioning program 40, which can be executed by the processor 10 to implement the device positioning method of this application.

[0096] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the device positioning method.

[0097] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the smart terminal and to display a visual user interface. The components 10-30 of the smart terminal communicate with each other via a system bus.

[0098] In one embodiment, when the processor 10 executes the device location program 40 in the memory 20, the following steps are performed:

[0099] Acquire a set of audio files collected by multiple devices from the current environment at the same time, wherein the audio file set contains multiple audio files;

[0100] Based on the gain ratio of each audio file, multiple candidate devices corresponding to the audio file set are determined in the device;

[0101] Perform speech recognition on the audio file to generate a corresponding text file;

[0102] Based on the device command set corresponding to the candidate devices, determine the target device corresponding to the text file among the candidate devices.

[0103] Specifically, determining multiple candidate devices corresponding to the audio file set based on the gain ratio of each audio file includes:

[0104] Calculate the distance weight value corresponding to each device based on the gain ratio of each audio file;

[0105] The device with the smallest corresponding distance weight value is selected as the candidate device.

[0106] Specifically, calculating the distance weight value corresponding to each device based on the gain ratio of each audio file includes:

[0107] Calculate the gain ratio based on the audio decibel level of the audio file;

[0108] When the gain ratio is greater than a preset first ratio threshold, the distance weight value corresponding to the device is a preset maximum weight value;

[0109] When the gain ratio is greater than a preset second ratio threshold and less than or equal to the first ratio threshold, the distance weight value corresponding to the device is a preset intermediate weight value.

[0110] When the gain ratio is less than or equal to the second ratio threshold, the distance weight value corresponding to the device is the preset minimum weight value.

[0111] Specifically, the step of performing speech recognition on the audio file to generate a corresponding text file includes:

[0112] Based on preset audio filtering rules, determine the qualified files among the audio files;

[0113] The qualified file is subjected to speech recognition to generate a text file corresponding to the audio file.

[0114] The device command set includes multiple device commands and the number of times each device command is invoked; determining the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices specifically includes:

[0115] The device command with the highest number of calls in each device command set is selected as the candidate command.

[0116] Calculate the similarity value between the candidate command corresponding to the candidate device and the text file;

[0117] The candidate device with the highest similarity value is selected as the target device corresponding to the text file.

[0118] The device positioning method further includes:

[0119] Acquire image files of the current environment captured within the same time period;

[0120] Calculate the physical distance between the target device and the user based on the image file;

[0121] Based on the physical distance, determine the corresponding adjustment parameters.

[0122] The step of determining the target device corresponding to the text file among the candidate devices based on the device command set corresponding to the candidate devices further includes:

[0123] Based on the candidate command corresponding to the target device, control the target device to perform the corresponding operation.

[0124] Specifically, controlling the target device to perform corresponding operations based on the candidate commands corresponding to the target device includes:

[0125] Based on preset parameter filtering rules, determine whether instruction parameters exist in the text file;

[0126] If so, then based on the candidate command corresponding to the target device and the instruction parameters, control the target device to perform the corresponding operation;

[0127] If not, then based on the adjustment parameters and the candidate command corresponding to the target device, control the target device to perform the corresponding operation.

[0128] The present invention also provides a storage medium, wherein the storage medium stores a device positioning program, which, when executed by a processor, implements the steps of the device positioning method described above.

[0129] In summary, this invention provides a device positioning method, a smart terminal, and a storage medium. The method acquires a set of audio files collected by multiple devices simultaneously from the current environment, wherein the audio file set contains multiple audio files. Based on the gain ratio of each audio file, multiple candidate devices corresponding to the audio file set are determined. Speech recognition is performed on the audio files to generate corresponding text files. Based on the device command set corresponding to the candidate devices, the target device corresponding to the text file among the candidate devices is determined. This invention determines the target device corresponding to a user's speech based on the gain ratio of that speech, thereby achieving the positioning of the target device among multiple devices.

[0130] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a memory, magnetic disk, optical disk, etc.

[0131] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for positioning equipment, characterized in that, The device positioning method includes: Acquire a set of audio files collected by multiple devices from the current environment at the same time, wherein the audio file set contains multiple audio files; Based on the gain ratio of each audio file, multiple candidate devices corresponding to the audio file set are determined in the device; Perform speech recognition on the audio file to generate a corresponding text file; Based on the device command set corresponding to the candidate devices, the target device corresponding to the text file among the candidate devices is determined; the device command set includes multiple device commands and the number of times each device command is invoked; specifically, it includes: The device command with the highest number of calls in each device command set is selected as the candidate command. Calculate the similarity value between the candidate command corresponding to the candidate device and the text file; The candidate device with the highest similarity value is selected as the target device corresponding to the text file; Based on the candidate command corresponding to the target device, control the target device to perform the corresponding operation; specifically including: Based on preset parameter filtering rules, determine whether instruction parameters exist in the text file; If so, then based on the candidate command corresponding to the target device and the instruction parameters, control the target device to perform the corresponding operation; If not, then based on the instruction parameters and the candidate command corresponding to the target device, control the target device to perform the corresponding operation; After execution, the invocation count of the candidate command corresponding to the target device will be incremented by one.

2. The equipment positioning method according to claim 1, characterized in that, The step of determining multiple candidate devices corresponding to the audio file set in the device according to the gain ratio of each audio file specifically includes: Calculate the distance weight value corresponding to each device based on the gain ratio of each audio file; The device with the smallest corresponding distance weight value is selected as the candidate device.

3. The equipment positioning method according to claim 2, characterized in that, The step of calculating the distance weight value corresponding to each device based on the gain ratio of each audio file specifically includes: Calculate the gain ratio based on the audio decibel level of the audio file; When the gain ratio is greater than a preset first ratio threshold, the distance weight value corresponding to the device is a preset maximum weight value; When the gain ratio is greater than a preset second ratio threshold and less than or equal to the first ratio threshold, the distance weight value corresponding to the device is a preset intermediate weight value. When the gain ratio is less than or equal to the second ratio threshold, the distance weight value corresponding to the device is the preset minimum weight value.

4. The equipment positioning method according to claim 1, characterized in that, The step of performing speech recognition on the audio file to generate a corresponding text file specifically includes: Based on preset audio filtering rules, determine the qualified files among the audio files; The qualified file is subjected to speech recognition to generate a text file corresponding to the audio file.

5. The equipment positioning method according to any one of claims 1-4, characterized in that, The device positioning method further includes: Acquire image files of the current environment captured within the same time period; Calculate the physical distance between the target device and the user based on the image file; Based on the physical distance, determine the corresponding adjustment parameters.

6. A smart terminal, characterized in that, The smart terminal includes: a memory, a processor, and a device positioning program stored in the memory and executable on the processor. When the device positioning program is executed by the processor, it implements the steps of the device positioning method as described in any one of claims 1-5.

7. A storage medium, characterized in that, The storage medium stores a device positioning program, which, when executed by a processor, implements the steps of the device positioning method as described in any one of claims 1-5.

Images