Management controller, voice command transmission system, and voice command transmission method

Abstract

The application provides a management controller, a voice instruction transmission system and a voice instruction transmission method, and applies to the technical field of servers.The management controller comprises: an integrated circuit built-in audio bus controller, which is used for obtaining voice instruction data through an integrated circuit built-in audio bus interface, extracting a check code from the voice instruction data, and checking a voice instruction in the voice instruction data by using the check code; a direct execution memory, which is used for storing the checked voice instruction; and a voice recognition and conversion module connected with the direct execution memory, which is used for reading the voice instruction from the direct execution memory, converting the voice instruction into an executable management controller control instruction, writing the executable management controller control instruction into the direct execution memory, and executing the executable management controller control instruction. In this way, the convenience of executing the management controller instruction is improved.

Description

Technical Field

[0001] This invention relates to the field of server technology, and in particular to management controllers, voice command transmission systems, and voice command transmission methods. Background Technology

[0002] The management controller is an embedded management system used to monitor the operation of servers. Currently, operators usually issue commands to the management controller through a terminal interface to control the server. However, issuing commands through the terminal interface requires operators to perform a series of manual operations on the terminal interface, which is not very convenient.

[0003] It is evident that improving the ease of execution of management controller commands is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a management controller, a voice command transmission system, and a voice command transmission method, which can improve the convenience of command execution by the management controller. The specific solution is as follows:

[0005] In a first aspect, the present invention provides a management controller, comprising:

[0006] An integrated circuit with a built-in audio bus controller is used to acquire voice command data through the integrated circuit's built-in audio bus interface, extract a check code from the voice command data, and use the check code to verify the voice commands in the voice command data.

[0007] Direct execution memory is used to store verified voice commands;

[0008] The speech recognition and conversion module connected to the direct execution memory is used to read speech commands from the direct execution memory, convert the speech commands into executable management controller control commands, and write the executable management controller control commands into the direct execution memory so as to execute the executable management controller control commands.

[0009] Optionally, the speech recognition and conversion module is further used for:

[0010] Record the storage address of the voice command in the direct execution memory;

[0011] Accordingly, writing the executable management controller control instructions into the direct execution memory includes:

[0012] Based on the storage address, the executable management controller control instructions are written into the direct execution memory, overwriting the voice instructions.

[0013] Optionally, the integrated circuit's built-in audio bus controller further includes a decryption module for:

[0014] The voice command data is decrypted to obtain the decrypted voice command data;

[0015] Accordingly, a verification code is extracted from the voice command data, and the voice commands in the voice command data are verified using the verification code, including:

[0016] The verification code is extracted from the decrypted voice command data, and the verification code is used to verify the voice commands in the voice command data.

[0017] Optionally, a command execution module may also be included, for:

[0018] The executable management controller control instructions are read from the direct execution memory and executed.

[0019] Optionally, a two-wire serial bus connected to the audio codec is also included for:

[0020] The audio codec is configured to process signals collected by the microphone and transmit voice command data to the integrated circuit's built-in audio bus controller.

[0021] Optionally, the speech recognition and conversion module is specifically used for:

[0022] A speech-to-text conversion network model is used to convert speech commands into executable management controller control commands. The training process of the speech-to-text conversion network model includes:

[0023] Obtain an initial voice dataset, wherein the initial voice data in the initial voice dataset consists of management controller voice commands recorded for different personnel;

[0024] The initial speech data in the initial speech dataset is processed using a preset processing strategy to obtain processed speech data. The preset processing strategy includes one or more of the following: pitch modulation, tone modulation, and background noise modulation.

[0025] Add label information to the processed speech data to obtain a training sample set, wherein the label information is the executable management controller control instruction corresponding to the processed speech data;

[0026] The deep learning network model is trained using the training sample set. During the training process, the training loss is calculated using the output of the deep learning network model and the label information of the processed input speech data. The deep learning network model is then updated based on the training loss to obtain the updated deep learning network model. When the training termination condition is met, the updated deep learning network model is determined as the speech conversion network model.

[0027] Secondly, the present invention discloses a management controller voice command transmission system, comprising the aforementioned management controller, an audio codec connected to the integrated circuit's built-in audio bus controller, and a microphone connected to the audio codec; wherein,

[0028] The microphone is used to collect voice commands;

[0029] The audio encoder is used to convert the voice commands output by the microphone into a format corresponding to the integrated circuit built-in audio bus, so as to transmit them to the integrated circuit built-in audio bus controller through the integrated circuit built-in audio bus interface.

[0030] Thirdly, the present invention discloses a method for transmitting voice commands to a management controller, comprising:

[0031] Using an integrated circuit built-in audio bus controller, voice command data is acquired through the integrated circuit built-in audio bus interface, and a verification code is extracted from the voice command data. The verification code is then used to verify the voice commands in the voice command data.

[0032] Store the verified voice commands into the direct execution memory;

[0033] Voice commands are read from the direct execution memory and converted into executable management controller control commands. The executable management controller control commands are then written into the direct execution memory to execute the executable management controller control commands.

[0034] Fourthly, the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the aforementioned management controller voice command transmission method.

[0035] Fifthly, the present invention discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the aforementioned management controller voice command transmission method.

[0036] As can be seen from the above scheme, the present invention provides a management controller, including: an integrated circuit built-in audio bus controller, used to acquire voice command data through the integrated circuit built-in audio bus interface, extract a check code from the voice command data, and use the check code to verify the voice commands in the voice command data; a direct execution memory, used to store the verified voice commands; and a voice recognition and conversion module connected to the direct execution memory, used to read the voice commands from the direct execution memory, convert the voice commands into executable management controller control commands, and write the executable management controller control commands into the direct execution memory to execute the executable management controller control commands.

[0037] As can be seen, the beneficial effects of this invention are as follows: The integrated circuit-embedded audio bus controller of the management controller acquires voice command data through the integrated circuit-embedded audio bus interface, extracts a checksum from the voice command data to verify the voice command, and stores the verified voice command in the direct execution memory. The voice recognition and conversion module connected to the direct execution memory reads the voice command from the direct execution memory, converts it into executable management controller control commands, stores it back in the direct execution memory, and waits for the executable management controller control commands to be executed. In this way, by setting up an integrated circuit-embedded audio bus controller, a direct execution memory, and a voice recognition and conversion module in the management controller, the transmission, verification, and conversion of voice commands are realized to obtain executable management controller control commands, which are then executed. This enables voice control based on the management controller, ensures data integrity and accuracy, and thus improves the convenience of management controller command execution.

[0038] Accordingly, the management controller voice command transmission system, management controller voice command transmission method, computer-readable storage medium, and computer program product provided by the present invention also have the above-mentioned technical effects. Attached Figure Description

[0039] To more clearly illustrate the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A schematic diagram of a management controller structure provided in an embodiment of the present invention;

[0041] Figure 2 A circuit connection diagram of a management controller voice command transmission system provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of I2S signal transmission with added CRC provided in an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of a direct execution memory storage provided in an embodiment of the present invention;

[0044] Figure 5 A flowchart of a voice command transmission method for a management controller provided in an embodiment of the present invention;

[0045] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the present invention.

[0047] The terms "comprising" and "having," and any variations thereof, in the specification and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may include steps or units not listed.

[0048] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] Next, a management controller provided by an embodiment of the present invention will be described in detail. Figure 1 A management controller is provided as an embodiment of the present invention, the management controller comprising:

[0050] The integrated circuit built-in audio bus controller 11 is used to acquire voice command data through the integrated circuit built-in audio bus interface, extract a verification code from the voice command data, and use the verification code to verify the voice command in the voice command data;

[0051] Direct execution memory 12 is used to store verified voice commands;

[0052] The speech recognition and conversion module 13, which is connected to the direct execution memory, is used to read speech commands from the direct execution memory, convert the speech commands into executable management controller control commands, and write the executable management controller control commands into the direct execution memory so as to execute the executable management controller control commands.

[0053] The management controller can be one of the following: BMC (Baseboard Management Controller), Integrated Light-Out (iLO) system, Integrated Dell Remote Access Control (IDRAC) card, or processing chip.

[0054] In an optional implementation, the checksum can be a cyclic redundancy check (CRUD). In this embodiment, the checksum can be extracted from the voice command data, calculated based on a preset polynomial, and then compared with the checksum extracted from the voice command data. If they match, the checksum passes; otherwise, it fails. The checksum extracted from the voice command data is the checksum calculated by the voice command data sender based on the preset polynomial. The integrated circuit's built-in audio bus controller 11 can also be used to store the verified voice commands into a direct execution memory.

[0055] In an optional implementation, the integrated circuit's built-in audio bus controller further includes a decryption module, configured to: decrypt the voice command data to obtain decrypted voice command data; correspondingly, extract a verification code from the voice command data, and use the verification code to verify the voice commands in the voice command data, including: extracting a verification code from the decrypted voice command data, and using the verification code to verify the voice commands in the voice command data.

[0056] That is, in this embodiment of the invention, the decryption module can also be implemented in the integrated circuit's built-in audio bus controller. Encrypting the encrypted voice command data, i.e., encrypting the voice command data during transmission, further enhances data security.

[0057] Among them, executable management controller control instructions are management controller control instructions that can be executed by the processor, that is, instructions that can be executed by the processor to remotely manage and monitor the server hardware. For example, executable management controller control instructions can be executable baseboard management controller control instructions.

[0058] The flash memory (i.e., flash storage) in the direct execution memory 12 is divided into multiple sectors according to a preset sector size, such as 4KB. Each sector can serve as an independent storage unit for data reading, writing, and erasing operations. Multiple fixed-size sectors can store a single voice command or an executable management controller control command. Dividing the XIP flash memory into 4KB sectors provides greater flexibility and reliability, meeting the needs of different application scenarios. Furthermore, an end marker can be added to the executable management controller control command to ensure that the complete executable management controller control command is read.

[0059] In an optional implementation, the voice recognition and conversion module 13 is further configured to: record the storage address of the voice instruction in the direct execution memory; correspondingly, writing the executable management controller control instruction into the direct execution memory includes: writing the executable management controller control instruction into the direct execution memory based on the storage address, overwriting the voice instruction.

[0060] In this embodiment of the invention, the voice command can be deleted from the direct execution memory based on its storage address in the direct execution memory, and the converted executable management controller control command can be written into the location corresponding to that storage address in the direct execution memory.

[0061] In an optional implementation, the speech recognition and conversion module is specifically used to: convert speech commands into executable management controller control commands using a speech conversion network model, wherein the training process of the speech conversion network model includes: acquiring an initial speech dataset, wherein the initial speech data in the initial speech dataset consists of management controller speech commands recorded for different personnel; processing the initial speech data in the initial speech dataset using a preset processing strategy to obtain processed speech data, wherein the preset processing strategy includes one or more processing strategies such as tone modulation, tone modulation, and background sound modulation; adding label information to the processed speech data to obtain a training sample set, wherein the label information consists of executable management controller control commands corresponding to the processed speech data; training a deep learning network model using the training sample set, wherein during the training process, the training loss is calculated using the output results of the deep learning network model and the label information of the input processed speech data, and the deep learning network model is updated based on the training loss to obtain an updated deep learning network model; when the training termination condition is met, the currently updated deep learning network model is determined as the speech conversion network model.

[0062] In this embodiment of the invention, the recorded voice commands for the management controller can include device information management commands, server status monitoring management commands, remote control management commands, maintenance management commands, and visual console interface commands. Device information management commands can include commands to obtain server information: queries and records detailed server information, including model, manufacturer, production date, production and technical information of each component, chassis information, motherboard information, etc. Commands to obtain BMC information: queries information about the BMC itself, such as server hostname, IP address, BMC firmware version, etc. Server status monitoring management commands can include commands to detect the health status of various server components (such as CPU, memory, hard drive, fan, chassis, etc.) such as temperature and voltage, and fan speed adjustment commands to adjust fan speed in real time based on temperature data collection points to ensure the server does not overheat and to control overall power consumption within a reasonable range. Remote control management commands can include: remote power on / off: sending commands through the BMC to remotely power on or off the server. Remote restart: sending restart commands through the BMC when necessary to restore normal server operation. Remote firmware update: uploading and installing new firmware versions through the BMC to fix known issues or improve performance. Remote System Installation: With network connectivity between the remote PC and the BMC management port, an operating system ISO image from the PC's hard drive can be directly used for installation. Maintenance and management commands can include: Log Management Commands: Query, download, or clear BMC log files for troubleshooting or performance analysis. User Management Commands: Add, delete, or modify BMC user accounts and permissions. BIOS Management Commands: Access and modify BIOS settings through the BMC, such as boot order and hardware configuration. Alarm Management Commands: View, confirm, or clear alarm information generated by the BMC. Visual Console Interface Commands can include: Login to the BMC Web Interface Command: Log in to the BMC Web interface using the IP address configured on the BMC within the local area network for visual management. View Device List Command: View the usage status of all devices in the device list interface. View Device Details Command: View detailed information for individual devices in the device details interface, such as CPU usage, hardware temperature, memory usage, network transmit / receive rate, disk usage, and IP address.

[0063] Furthermore, the management controller also includes a command execution module for:

[0064] The executable management controller control instructions are read from the direct execution memory and executed.

[0065] Furthermore, the management controller also includes a two-wire serial bus connected to the audio codec, used for: configuring the audio codec to process signals acquired by the microphone and transmitting voice command data to the integrated circuit's built-in audio bus controller. That is, the two-wire serial bus initializes and configures the audio codec to process signals acquired by the microphone and transmit voice command data to the integrated circuit's built-in audio bus controller. The audio codec may also include an encryption module for encrypting the voice command data.

[0066] As can be seen, the beneficial effects of this invention are as follows: The integrated circuit-embedded audio bus controller of the management controller acquires voice command data through the integrated circuit-embedded audio bus interface, extracts a checksum from the voice command data to verify the voice command, and stores the verified voice command in the direct execution memory. The voice recognition and conversion module connected to the direct execution memory reads the voice command from the direct execution memory, converts it into executable management controller control commands, stores it back in the direct execution memory, and waits for the executable management controller control commands to be executed. In this way, by setting up an integrated circuit-embedded audio bus controller, a direct execution memory, and a voice recognition and conversion module in the management controller, the transmission, verification, and conversion of voice commands are realized to obtain executable management controller control commands, which are then executed. This enables voice control based on the management controller, ensures data integrity and accuracy, and thus improves the convenience of management controller command execution.

[0067] Furthermore, this invention discloses a management controller voice command transmission system, including the management controller disclosed in the foregoing embodiments, an audio codec connected to the integrated circuit built-in audio bus controller, and a microphone connected to the audio codec; wherein, the microphone is used to collect voice commands; the audio encoder is used to convert the voice commands output by the microphone into a format corresponding to the integrated circuit built-in audio bus, so as to transmit them to the integrated circuit built-in audio bus controller through the integrated circuit built-in audio bus interface.

[0068] See Figure 2 As shown, Figure 2This is a circuit connection diagram of a voice command transmission system for a management controller provided in an embodiment of the present invention. Taking BMC as an example, other management controllers mentioned above can be used. In this embodiment, the accuracy of the data is ensured by adding CRC checksum to I2S data transmission; the integrity of the data is further guaranteed by adding encryption / decryption modules to the CODEC module (i.e., audio codec) and the I2S controller (i.e., integrated circuit built-in audio bus controller); an XIP module (i.e., direct execution memory) is added to the BMC, which can be a Nor Flash of type XIP, shortening the instruction execution time; a voice recognition and conversion module is added to the BMC to realize the execution of BMC commands via voice control. I2S (Inter-IC Sound, integrated circuit built-in audio bus) is a serial interface standard used for digital audio transmission to solve the problem of transmitting audio data between integrated circuits. The I2S protocol defines the transmission format, timing, and control signals of audio data. In operation, audio acquisition and output, and communication between the AD and the main chip are all conducted through I2S. I2S is a digital audio interface that can realize the transmission of voice signals, while CODEC is a codec chip used for audio data conversion, realizing the mutual conversion between analog and digital signals. The CODEC is initialized and configured using I2C (i.e., a two-wire serial bus). XIP (eXecute In Place) means that the CPU directly reads program code from memory and executes it, without having to load it into RAM. Application programs can run directly in flash memory, eliminating the need to load code into system RAM. The command execution module can be a hardware module, or it can be implemented in software, where the software retrieves instructions from the XIP and executes them sequentially. Figure 2 All modules involved are hardware modules.

[0069] like Figure 2 As shown, the microphone is connected to the CODEC module to transmit voice commands. The CODEC module converts the input analog signal into a storable digital signal. Simultaneously, the CODEC integrates a hardware encryption module to encrypt the converted digital signal. The encrypted signal is then transmitted to the I2S controller via the I2S interface. The hardware decryption module integrated in the I2S controller decrypts the encrypted signal to obtain the correct voice command, which is directly stored in the field-executable NOR flash memory. The voice recognition and conversion model retrieves the voice signal from the XIP memory, processes it, and obtains an executable command for the BMC. This command overwrites the stored voice command. Subsequently, the BMC sequentially retrieves executable commands from the XIP memory, realizing remote voice command control of the BMC. This embodiment of the invention mainly includes I2S signal transmission, a hardware encryption / decryption module, an XIP storage module, and a voice recognition and conversion module.

[0070] The I2S signal transmission involves three transmission lines: the SCK serial clock signal; the WS channel selection signal, also called LRCK, used to switch between left and right channel data; and the SD serial data signal, which is the actual audio data. During I2S data transmission, left alignment is selected, and a CRC checksum is placed in the last 8 bits of the data transmission. When the I2S controller receives the decrypted audio signal, it uses the CRC checksum to verify the accuracy of the signal transmission. Further details can be found in [link to documentation]. Figure 3 As shown, Figure 3 This is a schematic diagram of I2S signal transmission with added CRC provided in an embodiment of the present invention.

[0071] This invention provides a hardware encryption / decryption module, which can be an SM2 implementation using a hardware-based language. In the SM2 public-key encryption algorithm, the sender encrypts the message into ciphertext using the receiver's public key, and the receiver decrypts the received ciphertext using their private key to restore the original message. The key consists of a public key and a private key. The public key can be given to others and can be made public within a certain scope, while the private key must be kept secret. The public key can be calculated from the private key; however, calculating the private key from the public key is extremely difficult and currently impossible. SM2 is an elliptic curve public-key cryptography algorithm, an asymmetric encryption algorithm based on ECC. Because this algorithm is based on ECC, its signature speed and key generation speed are faster than RSA. 256-bit ECC (SM2 uses a type of 256-bit ECC) has higher security strength than 2048-bit RSA, but its computation speed is faster. The SM2 encryption and decryption process is a logical calculation flow. In this embodiment of the invention, the different calculation formulas involved can be implemented using the hardware description language Verilog. The logical calculation is achieved by calling the registers of different modules according to the logical calculation flow. The encryption and decryption modules are implemented in hardware, and the final encryption and decryption calculations are performed by configuring registers (the registers can be read and written). The system can implement a random number generator, an elliptic point / curve point calculation module, a point-to-character conversion module, a KDF key derivation function module, a bit string / string concatenation function module, a bit string XOR operation module, a hash operation module, and an output module. The encryption process may include:

[0072] A1: Use a random number generator to generate random numbers. Implemented using a random number generator;

[0073] A2: Calculate the points of the elliptic curve This converts the data type of C1 to a bit string; G is a base point of an elliptic curve, and its order is a prime number. This is achieved through the elliptic curve point calculation module and the point-to-character conversion module.

[0074] A3: Calculate points on the elliptic curve If S is a point at infinity, an error will be reported and the program will exit. It is a public key, and the cofactor of the order n of G is h; it is implemented through the elliptic point and curve point calculation module;

[0075] A4: Calculate points on the elliptic curve The data types of coordinates x2 and y2 are converted into bit strings; this is achieved through the elliptic point and curve point calculation module and the point-to-character conversion module.

[0076] A5: Calculation If t is a string of all zeros, then return A1; KDF(): key derivation function; x∥y: concatenation of x and y; integer klen represents the bit length of the key data to be obtained; KDF key derivation function module and bit string / string concatenation function module are implemented;

[0077] A6: Calculation M: The message to be encrypted; implemented using the bitwise XOR operation module of the bit string.

[0078] A7: Calculation Hash(): A cryptographic hash function. Implemented using the hash operation module.

[0079] A8: Output ciphertext This is achieved through the output module.

[0080] Based on the encryption and decryption algorithm flows, the specific modules that need to be implemented in hardware were determined. The calculation formulas involved in the decryption algorithm are the same as those in the encryption algorithm, therefore the hardware modules that need to be implemented are also the same as those in the encryption algorithm.

[0081] Further, see Figure 4 As shown, Figure 4 This is a schematic diagram of a direct execution memory (XIP) provided in an embodiment of the present invention. The XIP storage module uses XIP flash. XIP, or eXecute In Place, means that the CPU directly reads program code from memory for execution without having to load it into RAM. Application programs can run directly in the flash memory without having to load the code into system RAM. The XIP flash is divided into 4KB sectors. The voice signal received by the I2S controller is directly stored in the XIP flash sectors (multiple fixed-size sectors can store one instruction). The voice recognition module obtains input from the fixed-size sector blocks, processes it through the network model, and obtains BMC instruction information. These output instructions overwrite the voice signal in the corresponding sector. Simultaneously, the interrupt triggers the command execution module to process the BMC instructions (i.e., execute the management controller control instructions).

[0082] The speech recognition and conversion module can use network models for speech recognition, including but not limited to DNN-HMM, Attention-based RNN, and Transformer. The training corpus is built in-house, consisting of specified BMC commands recorded by several different people within the company. After recording, the commands are modulated with pitch, timbre, and background noise to generate tens of thousands of samples as input to the network model. The speech recognition features are specified BMC keywords. The network model outputs the specified BMC commands.

[0083] It should be noted that the I2S transmission protocol lacks data verification. If directly used for transmitting BMC commands, data loss and interference may occur, leading to errors in the final BMC command execution. Furthermore, after receiving data from the I2S interface, DMA (Direct Memory Access) is often used to move the data from the FIFO to memory before processing. This process makes command processing susceptible to the size of the FIFO. The BMC voice command transmission system based on I2S proposed in this invention achieves correct voice signal transmission by modifying the I2S signal transmission (adding CRC checksum); further ensures correct voice command transmission through encryption / decryption hardware modules, avoiding interference from transmission channels and electromagnetic radiation; enables rapid voice signal recognition and processing through an XIP storage module, while BMC commands overwrite the voice signal, avoiding wasted storage space; and ensures the accuracy of BMC command recognition by constructing input feature parameters, output targets, and training corpora for the network model. By customizing I2S signal transmission and integrating SM2 encryption / decryption hardware modules, the correct transmission of voice signals is achieved; the conversion of voice commands into BMC executable commands is accelerated through the XIP module; and the correct BMC execution commands are obtained by constructing a network model to train corpora and feature parameters.

[0084] This invention provides a voice command transmission system integrating a CODEC, I2S controller, XIP storage module, voice recognition network module, interrupt mechanism, and BMC instruction execution module. While the embodiments of this invention are described above, the above descriptions and definitions are merely for facilitating understanding of the embodiments of this invention and are not intended to limit the invention. Any modifications and variations made without departing from the spirit and scope of this invention are within the protection scope of this invention.

[0085] This invention expands the application scenarios of BMC by integrating a voice receiving module and a voice recognition and conversion module into the BMC. The voice receiving module may include an integrated circuit with a built-in audio bus controller. Operators can transmit voice signals to the BMC via a microphone, and voice recognition technology converts audio commands into executable commands for the BMC.

[0086] Further, see Figure 5 As shown, a method for transmitting voice commands to a management controller includes:

[0087] Step S11: Using the integrated circuit built-in audio bus controller, acquire voice command data through the integrated circuit built-in audio bus interface, extract the verification code from the voice command data, and use the verification code to verify the voice commands in the voice command data.

[0088] The embodiments of the present invention can implement the management controller voice command transmission method based on the management controller and management controller voice command transmission system disclosed in the foregoing embodiments.

[0089] In an optional implementation, the integrated circuit's built-in audio bus controller further includes a decryption module. In this embodiment of the invention, the decryption module can be used to decrypt the voice command data to obtain decrypted voice command data. Correspondingly, a verification code is extracted from the voice command data, and the verification code is used to verify the voice commands in the voice command data, including: extracting the verification code from the decrypted voice command data, and using the verification code to verify the voice commands in the voice command data.

[0090] Step S12: Store the verified voice commands into the direct execution memory.

[0091] Step S13: Read the voice command from the direct execution memory, convert the voice command into an executable management controller control command, and write the executable management controller control command into the direct execution memory so as to execute the executable management controller control command.

[0092] In this embodiment of the invention, a voice recognition and conversion module can be used to read voice commands from the direct execution memory, convert the voice commands into executable management controller control commands, and write the executable management controller control commands into the direct execution memory.

[0093] Furthermore, the storage address of the recorded voice instruction in the direct execution memory can also be used; correspondingly, writing the executable management controller control instruction into the direct execution memory includes: writing the executable management controller control instruction into the direct execution memory based on the storage address, overwriting the voice instruction.

[0094] Furthermore, embodiments of the present invention can also read executable management controller control instructions from the direct execution memory and execute the executable management controller control instructions.

[0095] Furthermore, embodiments of the present invention can also utilize a two-wire serial bus connected to the audio codec to configure the audio codec, so as to process the signal collected by the microphone through the audio codec and transmit the voice command data to the integrated circuit built-in audio bus controller.

[0096] In an optional implementation, a speech conversion network model can be used to convert speech commands into executable management controller control commands, wherein the training process of the speech conversion network model includes:

[0097] An initial speech dataset is obtained, wherein the initial speech data in the initial speech dataset consists of management controller voice commands recorded for different personnel; the initial speech data in the initial speech dataset is processed using a preset processing strategy to obtain processed speech data, wherein the preset processing strategy includes one or more of tone modulation, tone modulation, and background noise modulation; label information is added to the processed speech data to obtain a training sample set, wherein the label information is the executable management controller control command corresponding to the processed speech data; a deep learning network model is trained using the training sample set. During the training process, the training loss is calculated using the output of the deep learning network model and the label information of the input processed speech data, and the deep learning network model is updated based on the training loss to obtain an updated deep learning network model. When the training termination condition is met, the currently updated deep learning network model is determined as the speech conversion network model.

[0098] Figure 6 A structural diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 6 As shown, the electronic device includes: a memory 60 for storing computer programs;

[0099] The processor 61 is used to implement the steps of the voice command transmission method for the management controller as described in the above embodiment when executing a computer program.

[0100] The electronic devices provided in this embodiment may include servers, etc.

[0101] The processor 61 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 61 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 61 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 61 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 61 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0102] The memory 60 may include one or more computer-readable storage media, which may be non-transitory. The memory 60 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 60 is used to store at least the following computer program 601, which, after being loaded and executed by the processor 61, is capable of implementing the relevant steps of the management controller voice command transmission method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 60 may also include an operating system 602 and data 603, and the storage method may be temporary storage or permanent storage. The operating system 602 may include Windows, Unix, Linux, etc. The data 603 may include, but is not limited to, training data.

[0103] In some embodiments, the electronic device may further include a display screen 62, an input / output interface 63, a communication interface 64, a power supply 65, and a communication bus 66.

[0104] Those skilled in the art will understand that Figure 6 The structures shown do not constitute a limitation on electronic devices and may include more or fewer components than those shown.

[0105] It is understood that if the voice command transmission method for the management controller in the above embodiments is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the current technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, magnetic disk, or optical disk, and other media capable of storing program code.

[0106] Based on this, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described management controller voice command transmission method.

[0107] This invention discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the management controller voice command transmission method disclosed in the foregoing embodiments.

[0108] The foregoing has provided a detailed description of a management controller, a voice command transmission system, and a voice command transmission method provided by embodiments of the present invention. The various embodiments are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0109] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0110] The above provides a detailed description of the management controller, voice command transmission system, and voice command transmission method provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and core ideas of this invention. It should be noted that those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this invention.

Claims

1. A management controller, characterized in that, include: An integrated circuit with a built-in audio bus controller is used to acquire voice command data through the integrated circuit's built-in audio bus interface, extract a check code from the voice command data, and use the check code to verify the voice commands in the voice command data. Direct execution memory is used to store verified voice commands; The speech recognition and conversion module connected to the direct execution memory is used to read speech commands from the direct execution memory, convert the speech commands into executable management controller control commands, and write the executable management controller control commands into the direct execution memory so as to execute the executable management controller control commands; The management controller further includes a command execution module, configured to: read executable management controller control instructions from the direct execution memory, and execute the executable management controller control instructions; The speech recognition and conversion module is further configured to: record the storage address of the speech instruction in the direct execution memory; correspondingly, the step of writing the executable management controller control instruction into the direct execution memory includes: writing the executable management controller control instruction into the direct execution memory based on the storage address, overwriting the speech instruction, and executing the steps of reading the executable management controller control instruction from the direct execution memory and executing the executable management controller control instruction by triggering the command execution module through an interrupt.

2. The management controller according to claim 1, characterized in that, The integrated circuit's built-in audio bus controller also includes a decryption module for: The voice command data is decrypted to obtain the decrypted voice command data; Accordingly, a verification code is extracted from the voice command data, and the voice commands in the voice command data are verified using the verification code, including: The verification code is extracted from the decrypted voice command data, and the verification code is used to verify the voice commands in the voice command data.

3. The management controller according to claim 1, characterized in that, It also includes a two-wire serial bus for connecting to the audio codec, used for: The audio codec is configured to process signals collected by the microphone and transmit voice command data to the integrated circuit's built-in audio bus controller.

4. The management controller according to any one of claims 1 to 3, characterized in that, The speech recognition and conversion module is specifically used for: A speech-to-text conversion network model is used to convert speech commands into executable management controller control commands. The training process of the speech-to-text conversion network model includes: Obtain an initial voice dataset, wherein the initial voice data in the initial voice dataset consists of management controller voice commands recorded for different personnel; The initial speech data in the initial speech dataset is processed using a preset processing strategy to obtain processed speech data. The preset processing strategy includes one or more of the following: pitch modulation, tone modulation, and background noise modulation. Add label information to the processed speech data to obtain a training sample set, wherein the label information is the executable management controller control instruction corresponding to the processed speech data; The deep learning network model is trained using the training sample set. During the training process, the training loss is calculated using the output of the deep learning network model and the label information of the processed input speech data. The deep learning network model is then updated based on the training loss to obtain the updated deep learning network model. When the training termination condition is met, the updated deep learning network model is determined as the speech conversion network model.

5. A voice command transmission system for a management controller, characterized in that, Includes a management controller as described in any one of claims 1 to 4, an audio codec connected to the integrated circuit's built-in audio bus controller, and a microphone connected to the audio codec; wherein, The microphone is used to collect voice commands; The audio codec is used to convert the voice commands output by the microphone into a format corresponding to the integrated circuit's built-in audio bus, so as to transmit them to the integrated circuit's built-in audio bus controller through the integrated circuit's built-in audio bus interface.

6. A method for transmitting voice commands to a management controller, characterized in that, include: Using an integrated circuit built-in audio bus controller, voice command data is acquired through the integrated circuit built-in audio bus interface, and a verification code is extracted from the voice command data. The verification code is then used to verify the voice commands in the voice command data. Store the verified voice commands into the direct execution memory; The system reads voice commands from the direct execution memory, converts the voice commands into executable management controller control commands, and writes the executable management controller control commands into the direct execution memory to execute the executable management controller control commands. The storage address of the voice command in the direct execution memory is recorded. Based on the storage address, the executable management controller control instructions are written into the direct execution memory, overwriting the voice instructions. The interrupt-triggered command execution module then executes the steps of reading the executable management controller control instructions from the direct execution memory and executing the executable management controller control instructions.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the voice command transmission method for the management controller as described in claim 6.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the voice command transmission method for the management controller as described in claim 6.

Images