Abnormal inflexion voice control stopping method and device and intelligent central control system

Abstract

The invention provides an abnormal inflexion voice control blocking method and device and an intelligent central control system, and the method comprises the steps: detecting a voice instruction sent by a current user in real time, and obtaining a voice signal; detecting an inflexion feature of the voice signal to judge whether the current user has an inflexion operation or not; under the condition that the current user has the inflexion operation, a multi-verification mechanism is executed to obtain a verification result, the verification result is that the current user is a pre-stored permission user or the current user is a non-permission user, and the multi-verification mechanism is a measure for carrying out user identity verification in multiple modes; and when the verification result is that the current user is the non-authorized user and the voice instruction is executed, adjusting the equipment state to an initial state. The problem that in the prior art, inflexion operation is recognized, but inflexion operation is not effectively stopped, so that the system safety is reduced is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of voice change, and in particular to a method for preventing abnormal voice change voice control, a preventing device, a computer-readable storage medium and an intelligent central control system. Background Art

[0002] With the development of smart homes, voice control has become a convenient and fast control method. However, when processing voice commands, existing smart central control systems have difficulty distinguishing between authorized users and visitors / unauthorized users, which can easily lead to misoperation. In addition, the development of voice-changing technology allows some unauthorized users to imitate the voices of authorized users to operate the system, posing a security risk. Therefore, how to effectively identify the voice-changing operations of visitors / unauthorized users in the smart central control system and correct and close them in a timely manner has become an urgent problem to be solved. Summary of the invention

[0003] The main purpose of the present application is to provide a method, a device, a computer-readable storage medium and an intelligent central control system for preventing abnormal voice-changing voice control, so as to at least solve the problem in the prior art of identifying voice-changing operations but failing to effectively prevent voice-changing operations, resulting in reduced system security.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for preventing abnormal voice-changed voice control is provided, including: detecting the voice command issued by the current user in real time to obtain a voice signal; detecting the voice change characteristics of the voice signal to determine whether the current user has a voice change operation; in the case where the current user has the voice change operation, executing a multiple verification mechanism to obtain a verification result, the verification result is that the current user is a pre-stored authorized user or the current user is an unauthorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways; in the case where the verification result is that the current user is the unauthorized user and has executed the voice command, adjusting the device state to an initial state, the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0005] Optionally, the method also includes: inputting the voice signal into a voice recognition model, using the voice recognition model to analyze and transform the voice signal, and outputting corresponding text instructions, wherein the voice recognition model is a convergent model obtained by training a predetermined model using multiple groups of training data, and each group of training data includes a sample voice signal and a sample text instruction corresponding to the sample voice signal.

[0006] Optionally, before detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation, the method further includes: performing voiceprint analysis on the voice signal to extract the voiceprint feature of the current user; matching the voiceprint feature with the voiceprint feature of a pre-stored authorized user to obtain a matching result, wherein the matching result is a successful match or a failed match; detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation, including: when the matching result is the failed match, inputting the voice signal into a voice change detection model to perform voice change detection to obtain a voice change feature, wherein the voice change detection model is a convergent model obtained by training a first predetermined model using multiple groups of first training data, wherein the first training data includes a sample voice signal and the voice change feature corresponding to the sample voice signal; comparing the voice change feature with a preset user feature to obtain a voice change detection result, wherein the voice change detection result is that the current user has performed the voice change operation or that the current user does not perform the voice change operation.

[0007] Optionally, after matching the voiceprint feature with the voiceprint feature of the pre-stored authorized user to obtain a matching result, the method further includes: when the matching result is that the match is successful, controlling the execution of the voice command.

[0008] Optionally, in the presence of the voice changing operation, a multiple verification mechanism is executed, and after obtaining the verification result, the method further includes: in the case where the verification result is that the current user is the unauthorized user and has not executed the voice command, the voice command is not executed, and an early warning message is issued to the pre-stored authorized user, the early warning message is used to prompt the pre-stored authorized user that the unauthorized user is performing a voice operation.

[0009] Optionally, in the presence of the voice change operation, a multiple verification mechanism is executed to obtain a verification result, including: sending a first verification request to the pre-stored permission user, and sending a second verification request to the current user, the first verification request at least including a verification code verification and the text instruction verification, and the second verification is at least a specific voice verification; receiving a first response message to the first verification request and a second response message to the second verification request, the first response message being information obtained in response to the first verification request, and the second response message being information obtained in response to the second verification request; verifying the first response message and the second response message; in a case where the verification of the first response message passes and the verification of the second response message passes, determining that the verification result is that the current user is the pre-stored permission user; in a case where the verification of the first response message fails and / or the verification of the second response message fails, determining that the verification result is that the current user is a non-authorized user.

[0010] Optionally, when the verification result is that the current user is the unauthorized user and has executed the voice command, the device state is adjusted to the initial state, including: performing voiceprint recognition on historical voice signals within a historical time period to obtain historical voiceprint features; performing feature comparison between the historical voiceprint features and the voiceprint features of the current user to obtain a comparison result, wherein the comparison result is that the historical voiceprint features are consistent with the voiceprint features of the current user or the historical voiceprint features are inconsistent with the voiceprint features of the current user; when the comparison result is that the historical voiceprint features are consistent with the voiceprint features of the current user, all historical voice commands executed within the historical time period are revoked, and the device state is adjusted to the initial state, and the historical voice command is the voice command corresponding to the historical voice signal.

[0011] According to another aspect of the present application, a device for preventing voice-changed voice control is provided, the device comprising: a first detection unit, for detecting in real time a voice command issued by a current user to obtain a voice signal; a second detection unit, for detecting a voice-changed feature of the voice signal to determine whether the current user has performed a voice-changed operation; an execution unit, for executing a multiple verification mechanism to obtain a verification result when the current user has performed the voice-changed operation, the verification result being that the current user is a pre-stored authorized user or that the current user is an unauthorized user, the multiple verification mechanism being a measure for user identity verification in multiple ways; an adjustment unit, for adjusting a device state to an initial state when the verification result is that the current user is an unauthorized user and has executed the voice command, the device state being the state of the device after the voice command has been executed, the initial state being the state of the device before the voice command has been executed.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0013] According to another aspect of the present application, an intelligent central control system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0014] Applying the technical solution of the present application, in the method for preventing abnormal voice-changing voice control, first, the voice command issued by the current user is detected in real time to obtain a voice signal; then, the voice-changing feature of the voice signal is detected to determine whether the current user has a voice-changing operation; then, in the case that the current user has the voice-changing operation, a multiple verification mechanism is executed to obtain a verification result, and the verification result is that the current user is a pre-stored authorized user or the current user is an unauthorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways; finally, in the case that the verification result is that the current user is an unauthorized user and has executed the voice command, the device state is adjusted to the initial state, and the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed. The present application comprehensively identifies whether it is an unauthorized user through voice-changing detection and multiple verification mechanisms, and corrects or closes the voice command issued by the unauthorized user, etc., to ensure that the central control system is in the correct state and improve security. The present application solves the problem that the system security is reduced by identifying the voice-changing operation but not effectively preventing the voice-changing operation in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for preventing abnormal voice change voice control provided in an embodiment of the present application is shown;

[0016] Figure 2 A flow chart of a method for preventing abnormally changed voice control provided in accordance with an embodiment of the present application is shown;

[0017] Figure 3 A flowchart of a method for preventing abnormally changed voice control provided in accordance with an embodiment of the present application is shown;

[0018] Figure 4 A structural block diagram of a device for preventing abnormal voice-changing voice control provided according to an embodiment of the present application is shown.

[0019] The above drawings include the following reference numerals:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background technology, the development of voice changing technology in the prior art allows some unauthorized users to imitate the voices of authorized users and operate the system, which brings security risks. In order to solve the problem that the prior art recognizes the voice changing operation but fails to effectively prevent the voice changing operation, resulting in reduced system security, the embodiments of the present application provide a method for preventing abnormal voice changing voice control, a preventing device, a computer-readable storage medium and an intelligent central control system.

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for preventing abnormal voice change voice control according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for preventing abnormal voice change voice control in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific network example may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a method for preventing abnormal voice-changing voice control running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 2 1 is a flow chart of a method for preventing abnormal voice change voice control according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0030] Step S201, detecting the voice command issued by the current user in real time to obtain a voice signal.

[0031] Specifically, after the intelligent central control system is started, it enters a standby state and waits for voice commands from the user. When a voice command is detected, the intelligent central control system receives the voice signal through a microphone.

[0032] Step S202: Detect the voice change feature of the voice signal to determine whether the current user performs a voice change operation.

[0033] Specifically, when the intelligent central control system performs voice change detection, it can detect the voice change features in the voice signal through machine learning algorithms and identify whether there is forgery or voice change.

[0034] Step S203, when the current user has performed the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user. The multiple verification mechanism is a measure to perform user identity authentication in multiple ways.

[0035] Specifically, if a voice change operation is detected, a multiple verification mechanism will be activated to send a verification request to the mobile phone of a user with pre-stored permissions, or require the current user to perform a specific voice verification method to ensure the safety of the operation. This multiple verification mechanism increases the security level of the system and prevents illegal operations by unauthorized users.

[0036] Step S204, when the verification result is that the current user is the non-authorized user and has executed the voice command, adjust the device state to the initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0037] Specifically, for erroneous operations that have been performed, the intelligent central control system will correct them and restore the equipment to the correct state.

[0038] In this embodiment, first, the voice command issued by the current user is detected in real time to obtain a voice signal; then, the voice change feature of the voice signal is detected to determine whether the current user has a voice change operation; then, in the case that the current user has the voice change operation, a multiple verification mechanism is executed to obtain a verification result, and the verification result is that the current user is a pre-stored authorized user or the current user is an unauthorized user. The multiple verification mechanism is a measure to verify the user's identity in multiple ways; finally, in the case that the verification result is that the current user is the unauthorized user and has executed the voice command, the device state is adjusted to the initial state, and the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed. The present application uses voice change detection and multiple verification mechanisms to comprehensively identify whether it is an unauthorized user, and corrects or closes the voice command issued by the unauthorized user, etc., to ensure that the central control system is in the correct state and improve security. The present application solves the problem that the system security is reduced by identifying the voice change operation but not effectively preventing the voice change operation in the prior art.

[0039] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for preventing abnormal voice change voice control of the present application will be described in detail below in combination with specific embodiments.

[0040] In order to improve the accuracy of speech recognition and effectively execute the user's command, in an optional implementation, after the above step S201, the method further includes:

[0041] Step S301, input the above-mentioned voice signal into the voice recognition model, so as to use the above-mentioned voice recognition model to analyze and transform the above-mentioned voice signal, and output corresponding text instructions. The above-mentioned voice recognition model is a convergent model obtained by training a predetermined model using multiple groups of training data, and each group of the above-mentioned training data includes a sample voice signal and a sample text instruction corresponding to the above-mentioned sample voice signal.

[0042] In the above embodiment, if Figure 3 As shown, after receiving the voice signal, voice recognition is performed, and the user's voice signal is converted into text instructions in real time using a voice recognition model. The voice recognition model is a deep learning model, such as RNN (recurrent neural network) or Transformer training. Text instructions provide the system with a structured and standardized way to parse and execute commands, which is more direct and efficient than directly processing voice signals, thereby executing user commands more safely and effectively. In addition, text instructions can also be sent to users with pre-stored permissions, who can reconfirm whether the instructions are correct, thereby improving the accuracy of voice recognition.

[0043] In order to accurately identify whether there is forgery or voice change, in an optional implementation manner, before the above step S202, the method further includes: step S401, performing voiceprint analysis on the above voice signal to extract the voiceprint features of the above current user; step S402, matching the above voiceprint features with the voiceprint features of the pre-stored authorized users to obtain a matching result, the above matching result is a matching success or a matching failure,

[0044] Step S202 includes: step S2021, when the above-mentioned matching result is the above-mentioned matching failure, inputting the above-mentioned voice signal into the voice change detection model for voice change detection to obtain the voice change feature, the above-mentioned voice change detection model is a convergent model obtained by training a first predetermined model using multiple groups of first training data, and the above-mentioned first training data includes a sample voice signal and the above-mentioned voice change feature corresponding to the above-mentioned sample voice signal; step S2022, comparing the above-mentioned voice change feature with the preset user feature to obtain the voice change detection result, the above-mentioned voice change detection result is that the above-mentioned current user has the above-mentioned voice change operation or the above-mentioned current user does not have the above-mentioned voice change operation.

[0045] In the above embodiment, the system performs voiceprint analysis on the received voice signal and uses voiceprint recognition technology to extract the user's voiceprint features, and compares them with the voiceprint features of pre-stored authorized users through feature matching algorithms (such as MFCC, Mel Frequency Cepstral Coefficients). Because voiceprint recognition has high accuracy and uniqueness, it can effectively distinguish different users. The voiceprint features are extracted and compared with the pre-stored authorized user voiceprint database to determine whether the voice command comes from the authorized user. In the case where the matching result is a match failure, that is, if the voiceprint recognition fails to determine the user's identity, the system further performs voice change detection, and at the same time, the text command can be sent to the pre-stored authorized user. Through the machine learning algorithm, the system can detect the voice change features in the voice signal and identify whether there is forgery or voice change. A deep learning model combining convolutional neural network (CNN) and recurrent neural network (RNN) can be used to train the system to recognize the voice change features in the voice signal. These models can learn the subtle differences in voice change and help the system identify forged voices.

[0046] In order to protect the property and information security of the user, in an optional implementation manner, after the above step S401, the method further includes:

[0047] Step S501, when the matching result is successful, controlling the execution of the voice command.

[0048] In the above embodiment, if the above voiceprint features successfully match the voiceprint features of the pre-stored authorized user, it can be said that the user who currently issues the voice command is the pre-stored authorized user in the smart central control system, and the voice command can be executed. By confirming that the voice command is indeed from the authorized user, the system can prevent unauthorized users (such as visitors or imitators) from illegally operating smart home devices through voice changing technology, thereby protecting the user's property and information security.

[0049] In order to enhance the reliability of the intelligent central control system, in an optional implementation manner, after the above step S401, the method further includes:

[0050] Step S501, when the verification result is that the current user is the non-authorized user and has not executed the voice command, the voice command is not executed, and a warning message is sent to the pre-stored authorized user, the warning message is used to remind the pre-stored authorized user that the non-authorized user is performing voice operation.

[0051] In the above embodiment, if it is finally confirmed that the voice command comes from a visitor or unauthorized user, the system will refuse to execute the voice command and send a warning to the pre-authorized user. This can be achieved through SMS, application push notification or email.

[0052] In addition, the intelligent central control system will record the detailed information of the illegal operation, including time, location, and attempted instructions, so that authorized users and security personnel can analyze it. The intelligent central control system can also preset some automatic response measures, such as automatically locking the system or shutting down certain functions when an unauthorized user attempts to operate until the authorized user verifies it. The smart home system can provide timely feedback and response mechanisms while ensuring user safety, thereby enhancing the security and reliability of the entire system.

[0053] In order to effectively identify illegal voice changing operations, in an optional implementation, the above step S203 includes:

[0054] Step S2031, sending a first verification request to the pre-stored permission user, and sending a second verification request to the current user, the first verification request at least includes a verification code verification and the text instruction verification, and the second verification is at least a specific voice verification;

[0055] Step S2032, receiving first response information to the first verification request and second response information to the second verification request, wherein the first response information is information obtained in response to the first verification request, and the second response information is information obtained in response to the second verification request;

[0056] Step S2033, verifying the first response information and the second response information;

[0057] Step S2034, when the verification of the first response information and the verification of the second response information are passed, determining that the verification result is that the current user is the pre-stored permission user;

[0058] Step S2035: When the verification of the first response information fails and / or the verification of the second response information fails, it is determined that the verification result is that the current user is a non-authorized user.

[0059] In the above embodiment, after detecting signs of voice change or unauthorized user, the intelligent central control system will start a multiple verification mechanism, such as sending a verification request to the authorized user's mobile phone, or requiring a specific voice verification. After detecting a voice command, the intelligent central control system will perform preliminary voice recognition and voiceprint analysis. If the voiceprint analysis fails to determine the user's identity, or detects a possible voice change operation, the system will enter the multiple verification stage. The intelligent central control system will send a first verification request to the pre-stored authorized user (i.e., a user who has registered and has operation authority). This request includes at least two parts: the intelligent central control system generates a random verification code and sends it to the pre-stored authorized user through SMS, email or application push. The pre-stored authorized user needs to enter this verification code within a certain period of time to complete the verification. The intelligent central control system includes the previously converted text instruction in the first verification request, requiring the pre-stored authorized user to confirm whether this is the instruction they issued. At the same time, the intelligent central control system will also send a second verification request to the current user who issued the voice command. This request at least includes: the intelligent central control system requires the current user to say a specific phrase or answer to the question to verify his identity. This specific voice verification content should be pre-set and only known to the real authorized user. The intelligent central control system waits for and receives response information from the pre-stored authorized user, which is a reply to the first verification request, including a verification code and a confirmation of the text instruction. At the same time, the intelligent central control system also receives response information from the current user, which is a reply to the second verification request, that is, a recording of a specific voice. The intelligent central control system verifies the received first response information and second response information: checks whether the verification code is correct and whether the text instruction is confirmed by the authorized user. Through voice recognition technology, compare the specific voice spoken by the current user with the pre-stored authorized user voice sample to confirm whether they match. If the verification of the first response information and the second response information passes, the intelligent central control system will confirm that the current user is a pre-stored authorized user and execute the corresponding voice instruction. If any of the first response information or the second response information fails to pass the verification, the intelligent central control system will determine that the current user is a non-authorized user. In this case, the system will refuse to execute the instruction and send a warning notification to the authorized user, and may take further security measures, such as temporarily locking the system or requiring stricter verification. The smart central control system can effectively prevent illegal voice-changing operations and ensure that only truly authorized users can control smart home devices, thereby improving the security and reliability of the smart central control system.

[0060] In order to effectively prevent illegal operations, in an optional implementation, the above step S204 includes:

[0061] Step S2041, performing voiceprint recognition on historical voice signals within a historical time period to obtain historical voiceprint features;

[0062] Step S2042, comparing the historical voiceprint features with the voiceprint features of the current user to obtain a comparison result, wherein the comparison result is that the historical voiceprint features are consistent with the voiceprint features of the current user or the historical voiceprint features are inconsistent with the voiceprint features of the current user;

[0063] Step S2043, when the comparison result is that the historical voiceprint feature is consistent with the voiceprint feature of the current user, all historical voice commands executed in the historical time period are revoked, and the device state is adjusted to the initial state. The historical voice command is the voice command corresponding to the historical voice signal.

[0064] In the above embodiment, after identifying the existence of voice change operation, the intelligent central control system will review and analyze the voice signals collected in the historical time period. These voice signals are records left by previous users when interacting with the intelligent central control system. The intelligent central control system will use voiceprint recognition technology to extract voiceprint features from these historical voice signals. Voiceprint recognition technology is based on the uniqueness of each person's voice and identifies the identity of the speaker by analyzing the physical characteristics of the voice (such as pitch, timbre, rhythm, etc.). Once the system extracts voiceprint features from the historical voice signals, it compares these features with the voiceprint features of the current user. The purpose of the comparison is to determine whether the voiceprint features of the current user are consistent with the voiceprint features in the historical records. If the comparison result shows that the voiceprint features of the current user are consistent with the historical voiceprint features, the system will consider that the current user is an unauthorized user and has issued multiple voice commands for voice control. The system will revoke these commands and adjust the device status back to the initial state. In layman's terms, for the erroneous operations that have been executed, the previously implemented commands with similar voiceprints within a period of time will be rolled back and restored to the initial state of the device. This prevents any unauthorized changes or operations from affecting the system. The smart central control system can effectively identify and prevent illegal operations, ensuring that only authorized users can control smart home devices, thereby improving the security of the entire system.

[0065] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] The embodiment of the present application also provides a device for preventing abnormal voice-changing voice control. It should be noted that the device for preventing abnormal voice-changing voice control in the embodiment of the present application can be used to execute the method for preventing abnormal voice-changing voice control provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions thereof will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0067] The following is an introduction to the device for preventing abnormal voice change voice control provided in an embodiment of the present application.

[0068] Figure 4 1 is a structural block diagram of a device for preventing abnormal voice change control according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0069] The first detection unit 10 is used to detect the voice command issued by the current user in real time to obtain a voice signal.

[0070] Specifically, after the intelligent central control system is started, it enters a standby state and waits for voice commands from the user. When a voice command is detected, the intelligent central control system receives the voice signal through a microphone.

[0071] The second detection unit 20 is used to detect the voice change feature of the voice signal to determine whether the current user has performed a voice change operation.

[0072] Specifically, when the intelligent central control system performs voice change detection, it can detect the voice change features in the voice signal through machine learning algorithms and identify whether there is forgery or voice change.

[0073] The execution unit 30 is used to execute a multiple verification mechanism to obtain a verification result when the current user performs the voice change operation. The verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user. The multiple verification mechanism is a measure to perform user identity authentication in multiple ways.

[0074] Specifically, if a voice change operation is detected, a multiple verification mechanism will be activated to send a verification request to the mobile phone of a user with pre-stored permissions, or require the current user to perform a specific voice verification method to ensure the safety of the operation. This multiple verification mechanism increases the security level of the system and prevents illegal operations by unauthorized users.

[0075] The adjustment unit 40 is used to adjust the device state to the initial state when the verification result is that the current user is the non-authorized user and has executed the voice command. The device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0076] Specifically, for erroneous operations that have been performed, the intelligent central control system will correct them and restore the equipment to the correct state.

[0077] In this embodiment, the first detection unit is used to detect the voice command issued by the current user in real time to obtain a voice signal; the second detection unit is used to detect the voice change feature of the above voice signal to determine whether the above current user has a voice change operation; the execution unit is used to execute a multiple verification mechanism when the above current user has the above voice change operation to obtain a verification result, the above verification result is that the above current user is a pre-stored authorized user or the above current user is an unauthorized user, and the above multiple verification mechanism is a measure to verify the user's identity in multiple ways; the adjustment unit is used to adjust the device state to the initial state when the above verification result is that the above current user is the above unauthorized user and the above voice command has been executed. The above device state is the state of the device after the above voice command has been executed, and the above initial state is the state of the above device before the above voice command is executed. The present application uses voice change detection and multiple verification mechanisms to comprehensively identify whether it is an unauthorized user, and corrects or closes the voice command issued by the unauthorized user, etc., to ensure that the central control system is in the correct state and improve security. The present application solves the problem that the system security is reduced by identifying the voice change operation but not effectively preventing the voice change operation in the prior art.

[0078] In order to improve the accuracy of speech recognition so as to effectively execute the user's command, in an optional implementation manner, the device further includes:

[0079] The input-output unit is used to detect the voice command issued by the current user in real time, and after obtaining the voice signal, input the above voice signal into the voice recognition model, so as to use the above voice recognition model to analyze and transform the above voice signal, and output the corresponding text command. The above voice recognition model is a convergent model obtained by training a predetermined model using multiple groups of training data, and each group of the above training data includes a sample voice signal and a sample text command corresponding to the above sample voice signal.

[0080] In the above embodiment, if Figure 3As shown, after receiving the voice signal, voice recognition is performed, and the user's voice signal is converted into text instructions in real time using a voice recognition model. The voice recognition model is a deep learning model, such as RNN (recurrent neural network) or Transformer training. Text instructions provide the system with a structured and standardized way to parse and execute commands, which is more direct and efficient than directly processing voice signals, thereby executing user commands more safely and effectively. In addition, text instructions can also be sent to users with pre-stored permissions, who can reconfirm whether the instructions are correct, thereby improving the accuracy of voice recognition.

[0081] In order to accurately identify whether there is forgery or voice change, in an optional implementation, the device further includes: an extraction unit, which is used to perform voiceprint analysis on the voice signal to extract the voiceprint feature of the current user before detecting the voice change feature of the voice signal to determine whether the current user has a voice change operation; a matching unit, which is used to match the voiceprint feature with the voiceprint feature of the pre-stored authorized user to obtain a matching result, wherein the matching result is a successful match or a failed match.

[0082] The second detection unit includes: an input module, when the above-mentioned matching result is the above-mentioned matching failure, inputting the above-mentioned voice signal into the voice change detection model to perform voice change detection and obtain the voice change feature, the above-mentioned voice change detection model is a convergence model obtained by training a first predetermined model with multiple groups of first training data, and the above-mentioned first training data includes a sample voice signal and the above-mentioned voice change feature corresponding to the above-mentioned sample voice signal; a first comparison module, comparing the above-mentioned voice change feature with the preset user feature to obtain the voice change detection result, the above-mentioned voice change detection result is that the above-mentioned current user has the above-mentioned voice change operation or the above-mentioned current user does not have the above-mentioned voice change operation.

[0083] In the above embodiment, the system performs voiceprint analysis on the received voice signal and uses voiceprint recognition technology to extract the user's voiceprint features, and compares them with the voiceprint features of pre-stored authorized users through feature matching algorithms (such as MFCC, Mel Frequency Cepstral Coefficients). Because voiceprint recognition has high accuracy and uniqueness, it can effectively distinguish different users. The voiceprint features are extracted and compared with the pre-stored authorized user voiceprint database to determine whether the voice command comes from the authorized user. In the case where the matching result is a match failure, that is, if the voiceprint recognition fails to determine the user's identity, the system further performs voice change detection, and at the same time, the text command can be sent to the pre-stored authorized user. Through the machine learning algorithm, the system can detect the voice change features in the voice signal and identify whether there is forgery or voice change. A deep learning model combining convolutional neural network (CNN) and recurrent neural network (RNN) can be used to train the system to recognize the voice change features in the voice signal. These models can learn the subtle differences in voice change and help the system identify forged voices.

[0084] In order to protect the property and information security of the user, in an optional implementation manner, the device further includes:

[0085] The control unit is used to match the above-mentioned voiceprint features with the voiceprint features of the pre-stored authorized user, and after obtaining the matching result, if the above-mentioned matching result is that the above-mentioned match is successful, control the execution of the above-mentioned voice instruction.

[0086] In the above embodiment, if the above voiceprint features successfully match the voiceprint features of the pre-stored authorized user, it can be said that the user who currently issues the voice command is the pre-stored authorized user in the smart central control system, and the voice command can be executed. By confirming that the voice command is indeed from the authorized user, the system can prevent unauthorized users (such as visitors or imitators) from illegally operating smart home devices through voice changing technology, thereby protecting the user's property and information security.

[0087] In order to enhance the reliability of the intelligent central control system, in an optional implementation manner, the device further includes:

[0088] The early warning unit is used to execute a multiple verification mechanism in the presence of the above-mentioned voice change operation. After obtaining the verification result, if the above-mentioned verification result is that the above-mentioned current user is the above-mentioned non-authorized user and the above-mentioned voice instruction has not been executed, the above-mentioned voice instruction will not be executed, and an early warning message will be sent to the above-mentioned pre-stored authorized user. The above-mentioned early warning message is used to remind the above-mentioned pre-stored authorized user that the above-mentioned non-authorized user is performing a voice operation.

[0089] In the above embodiment, if it is finally confirmed that the voice command comes from a visitor or unauthorized user, the system will refuse to execute the voice command and send a warning to the pre-authorized user. This can be achieved through SMS, application push notification or email.

[0090] In addition, the intelligent central control system will record the detailed information of the illegal operation, including time, location, and attempted instructions, so that authorized users and security personnel can analyze it. The intelligent central control system can also preset some automatic response measures, such as automatically locking the system or shutting down certain functions when an unauthorized user attempts to operate until the authorized user verifies it. The smart home system can provide timely feedback and response mechanisms while ensuring user safety, thereby enhancing the security and reliability of the entire system.

[0091] In order to effectively identify illegal voice change operations, in an optional implementation, the execution unit includes:

[0092] A first sending module sends a first verification request to the pre-stored permission user, and sends a second verification request to the current user, wherein the first verification request at least includes a verification code verification and the text instruction verification, and the second verification is at least a specific voice verification;

[0093] A second sending module receives first response information of the first verification request and second response information of the second verification request, wherein the first response information is information obtained in response to the first verification request, and the second response information is information obtained in response to the second verification request;

[0094] A verification module, verifying the first response information and the second response information;

[0095] A first determination module, when the verification of the first response information and the verification of the second response information are passed, determines that the verification result is that the current user is the pre-stored permission user;

[0096] The second determination module determines that the verification result is that the current user is a non-authorized user when the verification of the first response information fails and / or the verification of the second response information fails.

[0097] In the above embodiment, after detecting signs of voice change or unauthorized user, the intelligent central control system will start a multiple verification mechanism, such as sending a verification request to the authorized user's mobile phone, or requiring a specific voice verification. After detecting a voice command, the intelligent central control system will perform preliminary voice recognition and voiceprint analysis. If the voiceprint analysis fails to determine the user's identity, or detects a possible voice change operation, the system will enter the multiple verification stage. The intelligent central control system will send a first verification request to the pre-stored authorized user (i.e., a user who has registered and has operation authority). This request includes at least two parts: the intelligent central control system generates a random verification code and sends it to the pre-stored authorized user through SMS, email or application push. The pre-stored authorized user needs to enter this verification code within a certain period of time to complete the verification. The intelligent central control system includes the previously converted text instruction in the first verification request, requiring the pre-stored authorized user to confirm whether this is the instruction they issued. At the same time, the intelligent central control system will also send a second verification request to the current user who issued the voice command. This request at least includes: the intelligent central control system requires the current user to say a specific phrase or answer to the question to verify his identity. This specific voice verification content should be pre-set and only known to the real authorized user. The intelligent central control system waits for and receives response information from the pre-stored authorized user, which is a reply to the first verification request, including a verification code and a confirmation of the text instruction. At the same time, the intelligent central control system also receives response information from the current user, which is a reply to the second verification request, that is, a recording of a specific voice. The intelligent central control system verifies the received first response information and second response information: checks whether the verification code is correct and whether the text instruction is confirmed by the authorized user. Through voice recognition technology, compare the specific voice spoken by the current user with the pre-stored authorized user voice sample to confirm whether they match. If the verification of the first response information and the second response information passes, the intelligent central control system will confirm that the current user is a pre-stored authorized user and execute the corresponding voice instruction. If any of the first response information or the second response information fails to pass the verification, the intelligent central control system will determine that the current user is a non-authorized user. In this case, the system will refuse to execute the instruction and send a warning notification to the authorized user, and may take further security measures, such as temporarily locking the system or requiring stricter verification. The smart central control system can effectively prevent illegal voice-changing operations and ensure that only truly authorized users can control smart home devices, thereby improving the security and reliability of the smart central control system.

[0098] In order to effectively prevent illegal operations, in an optional implementation manner, the adjustment unit includes:

[0099] The recognition module performs voiceprint recognition on historical voice signals within a historical time period to obtain historical voiceprint features;

[0100] A second comparison module compares the historical voiceprint features with the voiceprint features of the current user to obtain a comparison result, wherein the comparison result is that the historical voiceprint features are consistent with the voiceprint features of the current user or the historical voiceprint features are inconsistent with the voiceprint features of the current user;

[0101] The adjustment module, when the comparison result is that the historical voiceprint feature is consistent with the voiceprint feature of the current user, cancels all historical voice commands executed in the historical time period and adjusts the device state to the initial state. The historical voice command is the voice command corresponding to the historical voice signal.

[0102] In the above embodiment, after identifying the existence of voice change operation, the intelligent central control system will review and analyze the voice signals collected in the historical time period. These voice signals are records left by previous users when interacting with the intelligent central control system. The intelligent central control system will use voiceprint recognition technology to extract voiceprint features from these historical voice signals. Voiceprint recognition technology is based on the uniqueness of each person's voice and identifies the identity of the speaker by analyzing the physical characteristics of the voice (such as pitch, timbre, rhythm, etc.). Once the system extracts voiceprint features from the historical voice signals, it compares these features with the voiceprint features of the current user. The purpose of the comparison is to determine whether the voiceprint features of the current user are consistent with the voiceprint features in the historical records. If the comparison result shows that the voiceprint features of the current user are consistent with the historical voiceprint features, the system will consider that the current user is an unauthorized user and has issued multiple voice commands for voice control. The system will revoke these commands and adjust the device status back to the initial state. In layman's terms, for the erroneous operations that have been executed, the previously implemented commands with similar voiceprints within a period of time will be rolled back and restored to the initial state of the device. This prevents any unauthorized changes or operations from affecting the system. The smart central control system can effectively identify and prevent illegal operations, ensuring that only authorized users can control smart home devices, thereby improving the security of the entire system.

[0103] The above-mentioned device for preventing abnormal voice-changing voice control includes a processor and a memory. The above-mentioned first detection unit, the second detection unit and the execution unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in any combination.

[0104] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of identifying the voice change operation but not effectively preventing the voice change operation, which leads to reduced system security, in the prior art is solved by adjusting the kernel parameters.

[0105] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0106] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the method for preventing abnormal voice change control.

[0107] Specifically, the method for preventing abnormal voice-changing voice control includes:

[0108] Step S201, real-time detection of the voice command issued by the current user to obtain a voice signal;

[0109] Step S202, detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation;

[0110] Step S203, when the current user has performed the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways;

[0111] Step S204, when the verification result is that the current user is the non-authorized user and has executed the voice command, adjust the device state to the initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0112] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for preventing abnormal voice change voice control is executed when the program is running.

[0113] Specifically, the method for preventing abnormal voice-changing voice control includes:

[0114] Step S201, real-time detection of the voice command issued by the current user to obtain a voice signal;

[0115] Step S202, detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation;

[0116] Step S203, when the current user has performed the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways;

[0117] Step S204, when the verification result is that the current user is the non-authorized user and has executed the voice command, adjust the device state to the initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0118] An embodiment of the present invention provides an intelligent central control system, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are implemented:

[0119] Step S201, real-time detection of the voice command issued by the current user to obtain a voice signal;

[0120] Step S202, detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation;

[0121] Step S203, when the current user has performed the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways;

[0122] Step S204, when the verification result is that the current user is the non-authorized user and has executed the voice command, adjust the device state to the initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0123] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0124] Step S201, real-time detection of the voice command issued by the current user to obtain a voice signal;

[0125] Step S202, detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation;

[0126] Step S203, when the current user has performed the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways;

[0127] Step S204, when the verification result is that the current user is the non-authorized user and has executed the voice command, adjust the device state to the initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

[0128] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0129] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0130] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0134] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0135] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0137] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0138] 1) The method for preventing abnormal voice-changing voice control of the present application, first, detect the voice command issued by the current user in real time to obtain a voice signal; then, detect the voice-changing features of the voice signal to determine whether the current user has a voice-changing operation; then, if the current user has the voice-changing operation, execute a multiple verification mechanism to obtain a verification result, the verification result is that the current user is a pre-stored authorized user or the current user is an unauthorized user, the multiple verification mechanism is a measure for user identity verification in multiple ways; finally, if the verification result is that the current user is an unauthorized user and has executed the voice command, adjust the device state to the initial state, the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed. The present application uses voice-changing detection and multiple verification mechanisms to comprehensively identify whether it is an unauthorized user, and corrects or closes the voice command issued by the unauthorized user, etc., to ensure that the central control system is in the correct state and improve security. The present application solves the problem that the system security is reduced by identifying the voice-changing operation but not effectively preventing the voice-changing operation in the prior art.

[0139] 2) The device for preventing abnormal voice-changing voice control of the present application comprises a first detection unit for real-time detection of the voice command issued by the current user to obtain a voice signal; a second detection unit for detecting the voice-changing characteristics of the voice signal to determine whether the current user has a voice-changing operation; an execution unit for executing a multiple verification mechanism to obtain a verification result when the current user has a voice-changing operation, wherein the verification result is that the current user is a pre-stored authorized user or the current user is an unauthorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways; an adjustment unit for adjusting the device state to an initial state when the verification result is that the current user is an unauthorized user and has executed the voice command, wherein the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command has been executed. The present application uses voice-changing detection and multiple verification mechanisms to comprehensively identify whether the user is an unauthorized user, and corrects or closes the voice command issued by the unauthorized user, to ensure that the central control system is in the correct state and improve security. The present application solves the problem in the prior art that the voice change operation is recognized but the voice change operation is not effectively prevented, resulting in reduced system security.

[0140] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for preventing abnormal voice-changing voice control, characterized in that: include: Detect the voice command issued by the current user in real time and obtain the voice signal; Detecting the voice change feature of the voice signal to determine whether the current user has a voice change operation; In the case where the current user has the voice change operation, a multiple verification mechanism is executed to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways; When the verification result is that the current user is the unauthorized user and has executed the voice command, the device state is adjusted to an initial state, where the device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

2. The method according to claim 1, characterized in that After real-time detection of the voice command issued by the current user and obtaining the voice signal, the method further includes: The speech signal is input into a speech recognition model, and the speech signal is analyzed and transformed by the speech recognition model to output corresponding text instructions. The speech recognition model is a convergent model obtained by training a predetermined model using multiple sets of training data, and each set of training data includes a sample speech signal and a sample text instruction corresponding to the sample speech signal.

3. The method according to claim 1, characterized in that: Before detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation, the method further includes: performing voiceprint analysis on the voice signal to extract the voiceprint feature of the current user; matching the voiceprint feature with the voiceprint feature of a pre-stored authorized user to obtain a matching result, wherein the matching result is a matching success or a matching failure. Detecting the voice change feature of the voice signal to determine whether the current user has performed a voice change operation, including: when the matching result is the matching failure, inputting the voice signal into a voice change detection model to perform voice change detection to obtain a voice change feature, the voice change detection model is a convergent model obtained by training a first predetermined model using multiple groups of first training data, the first training data including a sample voice signal and the voice change feature corresponding to the sample voice signal; comparing the voice change feature with a preset user feature to obtain a voice change detection result, the voice change detection result is that the current user has performed the voice change operation or the current user does not perform the voice change operation.

4. The method according to claim 3, characterized in that After matching the voiceprint feature with the voiceprint feature of the pre-stored authorized user to obtain a matching result, the method further includes: When the matching result is that the match is successful, control is performed to execute the voice instruction.

5. The method according to claim 1, characterized in that: In the case where the voice change operation occurs, a multiple verification mechanism is executed, and after obtaining a verification result, the method further includes: When the verification result is that the current user is the unauthorized user and has not executed the voice command, the voice command is not executed, and an early warning message is sent to the pre-stored authorized user, wherein the early warning message is used to remind the pre-stored authorized user that the unauthorized user is performing voice operations.

6. The method according to claim 2, characterized in that In the case of the voice change operation, multiple verification mechanisms are executed to obtain verification results, including: Sending a first verification request to the pre-stored permission user, and sending a second verification request to the current user, wherein the first verification request at least includes a verification code verification and the text instruction verification, and the second verification is at least a specific voice verification; receiving first response information of the first verification request and second response information of the second verification request, wherein the first response information is information obtained in response to the first verification request, and the second response information is information obtained in response to the second verification request; verifying the first response information and the second response information; In the case where the verification of the first response information passes and the verification of the second response information passes, determining that the verification result is that the current user is the pre-stored permission user; In a case where the verification of the first response information fails and / or the verification of the second response information fails, it is determined that the verification result is that the current user is a non-authorized user.

7. The method according to claim 3, characterized in that When the verification result is that the current user is the unauthorized user and has executed the voice command, adjusting the device state to an initial state includes: Perform voiceprint recognition on historical voice signals within a historical time period to obtain historical voiceprint features; Performing feature comparison between the historical voiceprint feature and the voiceprint feature of the current user to obtain a comparison result, wherein the comparison result is that the historical voiceprint feature is consistent with the voiceprint feature of the current user or the historical voiceprint feature is inconsistent with the voiceprint feature of the current user; When the comparison result shows that the historical voiceprint feature is consistent with the voiceprint feature of the current user, all historical voice commands executed in the historical time period are revoked, and the device state is adjusted to the initial state. The historical voice command is the voice command corresponding to the historical voice signal.

8. A device for preventing voice-changing voice control, characterized in that: The device comprises: The first detection unit is used to detect the voice command issued by the current user in real time to obtain a voice signal; A second detection unit, used to detect the voice change feature of the voice signal to determine whether the current user has performed a voice change operation; an execution unit, configured to execute a multiple verification mechanism, if the current user has performed the voice change operation, to obtain a verification result, wherein the verification result is that the current user is a pre-stored authorized user or the current user is a non-authorized user, and the multiple verification mechanism is a measure for user identity verification in multiple ways; An adjustment unit is used to adjust the device state to an initial state when the verification result is that the current user is the unauthorized user and has executed the voice command. The device state is the state of the device after the voice command has been executed, and the initial state is the state of the device before the voice command is executed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. An intelligent central control system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images