A sound password transmission verification method and device, electronic equipment and storage medium

Abstract

The embodiment of the application discloses a kind of sound password transmission verification method, device, electronic equipment and storage medium, and the sound password information obtained by receiving microphone device is transmitted to edge server;Sound password information is at least one layer of self-encoding processing of self-encoder by edge server, and sound data is obtained;Sound data is sent to receiving end by satellite navigation positioning system, to carry out sound password verification for second sound data by receiving end;Control instruction or warning information sent by the verification result based on sound password verification of receiving end is received by satellite navigation positioning system;When receiving control instruction, the corresponding permission is opened according to control instruction;When receiving warning information, send early warning signal to safety early warning terminal equipment, it can solve the technical problem that the confidentiality and security of identity verification information transmission is low, improve the confidentiality and security of identity verification information transmission.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of identity verification, and particularly relate to a sound password transmission verification method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Identity verification (i.e., "identity authentication" or "identity identification") is a process of verifying whether the real identity of a user is consistent with his external identity, so as to determine whether the user information is reliable, prevent illegal users from impersonating other legitimate users to obtain a series of related permissions, and ensure the security and legal interests of the user information. There are many methods of identity verification, which can be basically divided into: identity verification based on shared key, identity verification based on biological characteristics, and identity verification based on public key encryption algorithm. Among them, the identity verification based on biological characteristics includes fingerprint identity verification, voice identity verification, iris identity verification, and sound password identity verification.

[0003] In some places with high confidentiality, identity verification must be performed before entering. However, the general identity verification control center is not set locally (within the scope of the place), and therefore the corresponding identity verification information needs to be transmitted to the corresponding remote identity verification control center to perform identity verification. At present, identity verification information is generally sent to the corresponding remote identity verification control center through an operator network signal or a wired network. This method has a high dependence on the operator network signal or the wired network. Generally, places with high confidentiality do not set up a wired network to contact the outside world (remote identity verification control center), and shield the operator network signal to contact the outside world (remote identity verification control center). Only within a predetermined range in the corresponding place can the wired network and the operator network signal be used to improve confidentiality.

[0004] Therefore, the existing identity verification information transmission method is not suitable for use in places with high confidentiality. The existing identity verification information transmission method has low confidentiality and security. SUMMARY

[0005] Embodiments of the present application provide a sound password transmission verification method, device, electronic equipment and storage medium, which can solve the technical problem of low confidentiality and security of identity verification information transmission, and improve the confidentiality and security of identity verification information transmission.

[0006] In a first aspect, embodiments of the present application provide a sound password transmission verification method applied to a sending end, comprising:

[0007] receiving sound password information obtained by a microphone device, and transmitting the sound password information to an edge server;

[0008] The edge server performs self-encoding processing on the voice password information through at least one layer of self-encoder to obtain voice data, wherein the voice data is data meeting a preset data capacity condition;

[0009] The voice data is sent to a receiving end through a satellite navigation positioning system, so that the receiving end performs voice password verification on the second voice data;

[0010] The satellite navigation positioning system receives a control instruction or warning information sent by the receiving end based on a verification result of the voice password verification;

[0011] When the control instruction is received, the corresponding permission is opened according to the control instruction;

[0012] When the warning information is received, a pre-warning signal is sent to a safety pre-warning terminal device.

[0013] Further, the edge server performs self-encoding processing on the voice password information through at least one layer of self-encoder to obtain voice data, comprising:

[0014] The edge server pre-processes the voice password information to obtain first voice data;

[0015] The edge server performs self-encoding processing on the first voice data through at least one layer of self-encoder to obtain second voice data, wherein the second voice data is data meeting a preset data capacity condition.

[0016] Further, the edge server pre-processes the voice password information to obtain first voice data, comprising:

[0017] The edge server performs feature extraction processing on the voice password information to generate Doppler spectrogram features;

[0018] The edge server performs noise reduction processing on the Doppler spectrogram features to obtain the first voice data.

[0019] Further, the preset data capacity condition is that the data capacity meets a short message transceiving capacity;

[0020] The edge server performs self-encoding processing on the first voice data through at least one layer of self-encoder to obtain second voice data, comprising:

[0021] The edge server performs self-encoding processing on the first voice data through a first layer of self-encoder to obtain first self-encoding data;

[0022] The first self-encoding data is subjected to voice feature extraction processing to obtain voice feature data;

[0023] match, by the edge server, the data volume of the sound feature data with the preset data volume condition, to determine whether the sound feature data meets the preset data volume condition;

[0024] If the sound feature data meets the preset data volume condition, the sound feature data is determined as the second sound data.

[0025] If the sound feature data does not meet the preset data volume condition, the first auto-encoding data is subjected to auto-encoding processing and sound feature extraction processing of a next layer of auto-encoder until second sound data meeting the preset data volume condition is obtained, and the second sound data is sound feature data.

[0026] Further, after the auto-encoding processing of the first sound data by the edge server through at least one layer of auto-encoder to obtain second sound data, the method further comprises:

[0027] The second sound data is subjected to classification label processing by the edge server, and the second sound data after the classification label processing is output.

[0028] Further, the satellite navigation positioning system is a Beidou satellite navigation positioning system.

[0029] The sound data is transmitted to the receiving end through the satellite navigation positioning system, comprising:

[0030] The sound data is transmitted to a ground central station through the Beidou satellite navigation positioning system, so that the ground central station verifies the identity legality of the sound data.

[0031] If the ground central station verifies that the identity of the sound data is legal, the ground central station transmits the sound data to the receiving end through the Beidou navigation positioning system.

[0032] If the ground central station verifies that the identity of the sound data is not legal, the transmitting end receives alarm information transmitted by the ground central station through the Beidou navigation positioning system.

[0033] In a second aspect, the embodiments of the present application provide a sound password transmission verification method, applied to a receiving end, comprising:

[0034] The sound data is received through the Beidou satellite navigation positioning system.

[0035] A corresponding pre-stored sound key is determined according to the classification label of the sound data.

[0036] The sound feature of the sound data is subjected to similarity matching with the sound feature of the pre-stored sound key.

[0037] When the similarity is greater than or equal to the preset value, a control instruction is sent to the sending end through the Beidou satellite navigation positioning system;

[0038] When the similarity is less than the preset value, a warning information is sent to the sending end through the Beidou satellite navigation positioning system.

[0039] In a third aspect, an embodiment of the present application provides a sound password transmission verification device, applied to a sending end, comprising:

[0040] A sound acquisition module is configured to receive sound password information acquired by a microphone device and transmit the sound password information to an edge server;

[0041] An edge service module is configured to perform self-encoding processing on the sound password information through the edge server to obtain sound data, the sound data being data meeting a preset data capacity condition;

[0042] A sending module is configured to send the sound data to a receiving end through a satellite navigation positioning system for sound password verification of the receiving end on second sound data;

[0043] A receiving module is configured to receive a control instruction or a warning information sent by the receiving end based on a verification result of the sound password verification through a satellite navigation positioning system;

[0044] A control module is configured to start a corresponding permission according to the control instruction when the control instruction is received;

[0045] An alarm module is configured to send a pre-warning signal to a security terminal when the warning information is received.

[0046] Further, the edge service module is further configured to perform preprocessing on the sound password information through the edge server to obtain first sound data;

[0047] The edge service module is further configured to perform self-encoding processing on the first sound data through the edge server to obtain second sound data, the second sound data being data meeting a preset data capacity condition.

[0048] Further, the edge service module is further configured to perform feature extraction processing on the sound password information through the edge server to generate Doppler spectrogram features;

[0049] The edge service module is further configured to perform noise reduction processing on the Doppler spectrogram features through the edge server to obtain the first sound data.

[0050] Further, the preset data capacity condition is that the data capacity meets a short message transmission capacity.

[0051] The edge service module is further configured to perform self-encoding processing on the first sound data by the first layer of self-encoders through the edge server to obtain first self-encoding data.

[0052] The first self-encoding data is subjected to sound feature extraction processing to obtain sound feature data.

[0053] The data capacity of the sound feature data is matched with the preset data capacity condition through the edge server to determine whether the sound feature data meets the preset data capacity condition.

[0054] If the sound feature data meets the preset data capacity condition, the sound feature data is obtained as the second sound data.

[0055] If the sound feature data does not meet the preset data capacity condition, the first self-encoding data is subjected to self-encoding processing and sound feature extraction processing of the next layer of self-encoders until the second sound data meeting the preset data capacity condition is obtained, and the second sound data is sound feature data.

[0056] Further, the edge service module is further configured to perform classification label processing on the second sound data through the edge server, and output the second sound data after classification label processing.

[0057] Further, the satellite navigation positioning system is a Beidou satellite navigation positioning system.

[0058] The sending module is further configured to send the sound data to a ground center station through the Beidou satellite navigation positioning system, so that the ground center station verifies the identity legality of the sound data.

[0059] If the ground center station verifies the identity legality of the sound data, the ground center station sends the sound data to a receiving end through the Beidou navigation positioning system.

[0060] If the ground center station verifies that the identity of the sound data is not legal, the receiving end receives alarm information sent by the ground center station through the Beidou navigation positioning system.

[0061] In a fourth aspect, an embodiment of the present application provides a sound password transmission verification device, comprising:

[0062] a memory and one or more processors;

[0063] The memory is configured to store one or more programs.

[0064] When the one or more programs are executed by the one or more processors, the one or more processors implement the voice password transmission verification method as described in the first aspect.

[0065] In a fifth aspect, the embodiments of the present application provide a storage medium storing computer executable instructions for executing the voice password transmission verification method as described in the first aspect when executed by a computer processor.

[0066] The embodiments of the present application obtain voice data satisfying a preset data capacity condition by performing self-encoding processing of the voice password information obtained by the microphone device through at least one layer of self-encoder, send the obtained voice data to the receiving end through the satellite navigation positioning system, and receive the control instruction or alarm information fed back by the corresponding receiving end based on the voice password verification result of the voice data through the satellite navigation positioning system. When the control instruction is received, the corresponding permission is opened according to the control instruction, and when the alarm information is received, a warning signal is sent to the security warning terminal device. By using the above technical means, the voice password information can be sent to the remote receiving end through the satellite navigation positioning system by performing self-encoding processing of the obtained voice password information through at least one layer of self-encoder to obtain voice data satisfying the preset data capacity condition required by the satellite navigation positioning system short message sending, so that the dependence on the data transmission wired network and the operator network signal is reduced, and the confidentiality and security of the voice password information transmission are improved. In addition, by receiving the control instruction or alarm information fed back by the corresponding receiving end through the satellite navigation positioning system, the use of wired network and operator network signal is also avoided, and the confidentiality and security of data transmission and reception are further improved. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 is a flowchart of a voice password transmission verification method provided by the embodiments of the present application;

[0068] Figure 2 is a data transmission schematic diagram provided by the embodiments of the present application;

[0069] Figure 3 is a self-encoding processing schematic diagram provided by the embodiments of the present application;

[0070] Figure 4 is a flowchart of another voice password transmission verification method provided by the embodiments of the present application;

[0071] Figure 5 is a flowchart of another voice password transmission verification method provided by the embodiments of the present application;

[0072] Figure 6This is a schematic diagram of the structure of a voice password transmission verification device provided in an embodiment of this application;

[0073] Figure 7 This is a schematic diagram of the structure of a voice password transmission verification device provided in an embodiment of this application. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0075] The voice password transmission verification method, apparatus, electronic device, and storage medium provided in this application are designed for locations requiring high confidentiality, where voice password transmission via wired networks and carrier network signals is not possible. By performing at least one layer of self-encoding processing on the acquired voice password information, attributing it to voice data that meets the preset data capacity requirements for short message transmission by the satellite navigation and positioning system, the voice password information can be transmitted to a remote receiving end via the satellite navigation and positioning system. This reduces reliance on wired and carrier network signals, improving the confidentiality and security of voice password transmission. Furthermore, the system receives control commands or alarm information from the corresponding receiving end via the satellite navigation and positioning system, further avoiding the use of wired and carrier network signals and enhancing the confidentiality and security of data transmission and reception. This contrasts with traditional voice password transmission methods, which typically rely heavily on carrier network signals and wired networks, generally transmitting the corresponding voice password information to a remote receiving end (authentication control center) via carrier network signals or wired networks. In locations requiring high security, wired networks are typically not used to connect to the outside world (the receiving end), and carrier network signals are blocked. Wired networks and carrier network signals are only used within a predetermined area of ​​the location to enhance security. Therefore, traditional voice password transmission methods offer low security and are unsuitable for such high-security locations. Based on this, the voice password transmission verification method described in this application is provided to address the technical problem of low security and confidentiality in existing voice password information transmission methods, making it suitable for high-security locations.

[0076] Figure 1 A flowchart of a voice password transmission verification method provided in this application embodiment is given. The voice password transmission verification method provided in this embodiment can be executed by a voice password transmission verification device, which can be implemented by software and / or hardware. The voice password transmission verification device can be composed of two or more physical entities, or it can be composed of a single physical entity. Generally, the voice password transmission verification device can be a terminal device, such as a computer device.

[0077] The following description uses a computer device as the main body for executing the voice password transmission verification method. Figure 1 This is a flowchart of a voice password transmission verification method provided in an embodiment of this application. Figure 2 This is a schematic diagram of data transmission provided in an embodiment of this application, with reference to... Figure 1 and Figure 2 This voice password transmission verification method, applied to the sending end 10, specifically includes:

[0078] S101. Receive the voice password information acquired by the microphone device and transmit the voice password information to the edge server.

[0079] A microphone device can be understood as an energy conversion device that converts sound signals into electrical signals. Sound information can be captured through a microphone device. In highly secure locations, identity verification is required for entry or granting certain permissions. Voice password verification is one such method. Voice password verification involves using a voice recording device to convert the vocabulary of a user's speech into computer-readable data, repeatedly measuring and recording changes in the sound waveform, and then converting this data into a saved sound template. This template is compared with a pre-stored sound key to verify the user's identity and the match of the speech content. For voice password verification to enter a location or grant certain permissions, the first step is to obtain the voice password information of the user requiring authentication. A microphone device 11 is configured at the entrance of the location or in the authentication area where certain permissions are granted to capture the user's voice password information. The captured voice password information is received by the microphone device 11 and transmitted to the edge server 14 for processing.

[0080] For example, suppose the voice password is "Open Sesame" used to open the access control system. The user needs to record the "Open Sesame" voice message beforehand, which is then processed to obtain a pre-stored voice key. This pre-stored voice key information includes the user's voice characteristics and corresponding voice content information. When the user needs to open the access control system, they need to say the "Open Sesame" voice password. The server backend compares this voice password with the pre-stored voice key. Only after confirming the user's legitimacy can the access control system be opened.

[0081] In general, locations with high security requirements do not have wired networks connecting them to the outside world (receiving end 20), and they also shield operator network signals that connect them to the outside world (receiving end 20). Wired networks and operator network signals are only used within a predetermined area of ​​the corresponding location to enhance security. An edge computing system and a 5G communication system that can only communicate within the location's area are constructed in these high-security locations. The edge computing system is the sender of voice password information, including a message sending device (which can be a device integrated with a microphone), a microphone device 11, and an edge server 14, etc. The remote control center is the corresponding receiving end 20, which is used to verify the voice password information. The microphone device 11 obtains the corresponding user's voice password information and forwards it to the 5G base station 13 via the wireless router 12 (5GPCE) within the location. The 5G base station 13 then transmits the voice password information to the edge server 14 deployed within the high-security location for further processing.

[0082] For example, in the Taklamakan Desert, a classified unit discovered an oil field. To further explore, the unit established a camp, a highly secure location for security reasons. An edge computing system and a 5G communication system, capable of communication only within the camp, were built within the camp area. This edge computing system, acting as the sender of voice password information, includes message sending devices, a microphone device 11, and an edge server 14. The microphone device 11 collects voice password information from personnel and forwards it to a 5G base station 13 via a wireless router 12 (5GPCE) within the site. The 5G base station 13 then transmits the voice password information to the edge server 14 deployed within the camp for further processing.

[0083] For example, assuming the access control voice password for user A is "Open Sesame", user A says "Open Sesame" into the microphone device 11 corresponding to the access control. The microphone device 11 captures the voice password information and sends it to the edge server 14. After the edge server 14 processes the voice password information, it sends the processed voice password information to the receiving end 20 through the corresponding short message sending device, so that the receiving end 20 can authenticate the voice password information, verify whether it is user A's voice, and verify whether the voice password content is correct.

[0084] S102. The voice password information is processed by the edge server through at least one layer of autoencoder to obtain voice data, wherein the voice data is data that meets the preset data capacity conditions.

[0085] Edge server 14 can be understood as possessing data computing, networking, storage, and application capabilities. It receives sensing data and requests transmitted from edge devices, analyzes the data, and returns the results to the edge devices for control. When edge server 14 receives voice password information, it preprocesses the information. This preprocessing involves feature extraction to generate Doppler spectrogram features, followed by noise reduction to obtain first voice data. Edge server 14 then performs at least one layer of autoencoder processing on the first voice data to obtain second voice data. This second voice data meets preset data capacity requirements. Feature extraction of the voice password information allows for direct comparison of voice features for authentication. The autoencoder process compresses the voice data to meet the corresponding data capacity requirements for transmission.

[0086] In one embodiment, the voice password information is processed by an edge server 14 to extract features, generating Doppler spectrogram features. The Doppler spectrogram features are then denoised to obtain first voice data. The first voice data is then processed by the edge server 14 using at least one layer of autoencoder to obtain first autoencoded data. Voice feature extraction is then performed on the first autoencoded data by the edge server 14 to obtain voice feature data. The data capacity of this voice feature data is matched against a preset data capacity condition to determine if it meets the condition. If the data capacity of the voice feature data meets the preset condition, the obtained voice feature data is the corresponding second voice data. If the data capacity of the voice feature data does not meet the preset condition, the first autoencoded data undergoes further autoencoder processing and voice feature processing until the corresponding second voice data whose data capacity meets the preset condition is obtained.

[0087] In one embodiment, since wired networks and carrier networks are not used to communicate with the receiving end 20 in locations requiring high security, this application proposes a method for sending voice password information to the receiving end 20 via a satellite navigation and positioning system. Because sending information via a satellite navigation and positioning system requires meeting certain data capacity requirements, a preset data capacity condition is necessary. The voice password information needs to be processed so that the processed voice data meets the preset data capacity condition before it can be sent to the receiving end 20 via satellite navigation and positioning information.

[0088] For example, there are currently four major global satellite navigation and positioning systems: China's BeiDou Navigation Satellite System, Europe's Galileo Navigation Satellite System, Russia's GLONASS Navigation Satellite System, and the United States' GPS Navigation Satellite System. This embodiment uses the BeiDou Navigation Satellite System as an example. The BeiDou Navigation Satellite System can provide five major services: basic navigation service, international search and rescue service, regional precise point positioning service, regional satellite-based augmentation service, and short message communication service. The short message communication service is a unique feature of the BeiDou Navigation Satellite System. In China and surrounding areas, the short message communication service can provide a single message capacity of 1000 Chinese characters or 14000 bits. In other regions globally, it can provide a single message capacity of 40 Chinese characters or 560 bits. Providing a single message capacity of 1000 Chinese characters or 14000 bits in China and surrounding areas greatly expands the service range of the BeiDou short message communication service. Therefore, when using the BeiDou satellite navigation and positioning system 15 to send voice command information to the receiving end 20 in the form of short messages, it is necessary to preset the data capacity condition to be less than 14,000 bits.

[0089] Figure 3 This is a schematic diagram of a self-encoding process provided in an embodiment of this application, with reference to... Figure 3S1021. Generate Doppler spectrogram features. The edge server 14 performs feature extraction processing on the voice password information to generate Doppler spectrogram features. S1022. Noise reduction processing. The edge server 14 performs noise reduction processing on the Doppler spectrogram features to obtain the first sound data. S1023. Autoencoder. The first sound data is input into the autoencoder to obtain the first layer of autoencoded data. S1024. Feature extraction. Sound feature extraction processing is performed on the first autoencoded data to obtain sound feature data. S1025. Determine if the sound feature data is less than 14000 bits. The data capacity of the sound feature data is compared with 14000 bits to determine if the sound feature data meets the preset data capacity condition of less than 14000 bits. If the data capacity of the sound feature data meets the preset data capacity condition of less than 14000 bits, the sound feature data is output. If the data capacity of the sound feature data does not meet the preset data capacity condition, the first autoencoded data is processed by the next layer of autoencoder for autoencoding and sound feature processing until sound feature data with a corresponding data capacity that meets the preset data capacity condition of less than 14000 bits is obtained. S1026, Output Features. Output sound feature data with a data capacity that meets the preset data capacity condition of less than 14000 bits. This sound feature data is the second sound data. S1027, LR Classifier. The output sound feature data is classified using an LR classifier. S1028, Classification Label. The sound feature data after classification by the LR classifier is labeled, and the sound feature data with the corresponding classification label (second sound data) is output. S1029, Calculate and Output the Second Sound Data. The above-mentioned automatic iterative reduction of the voice feature data to below 14,000 bits, combined with the short message service for transmission of the tags obtained by the classifier, overcomes the problem of data capacity mismatch when transmitting voice data in the BeiDou satellite navigation and positioning system. This allows the BeiDou satellite navigation and positioning system to fully utilize its strong security and wide coverage, greatly expanding the scope of BeiDou's application.

[0090] S103. The sound data is sent to the receiving end through the satellite navigation and positioning system so that the receiving end can verify the second sound data with a voice password.

[0091] Currently, there are four major global satellite navigation and positioning systems: China's BeiDou Navigation Satellite System, Europe's Galileo Navigation Satellite System, Russia's GLONASS Navigation Satellite System, and the United States' GPS Navigation Satellite System. This embodiment uses the BeiDou Navigation Satellite System as an example. The BeiDou Navigation Satellite System provides five main services: basic navigation service, international search and rescue service, regional precise point positioning service, regional satellite-based augmentation service, and short message communication service. The short message communication service is a unique feature of the BeiDou Navigation Satellite System. In China and surrounding areas, the short message communication service can provide a single message capacity of 1000 Chinese characters or 14000 bits. In other regions globally, it can provide a single message capacity of 40 Chinese characters or 560 bits. Providing a single message capacity of 1000 Chinese characters or 14000 bits in China and surrounding areas significantly expands the service range of the BeiDou short message communication service. After the voice password information is processed by the edge server 14 in step S102, second voice data with a data capacity of less than 14,000 bits, which meets the requirements for short message transmission by the BeiDou Navigation Satellite System, is obtained. The sending end sends the second voice data to the receiving end 20 through the BeiDou Navigation Satellite System 15, so that the receiving end 20 can verify the voice password using the second voice data.

[0092] For example, in a highly secure location, the edge server 14 processes the voice password information to obtain second voice data with a data capacity of less than 14,000 bits, which meets the requirements for short message transmission by the BeiDou Navigation Satellite System. This data is then forwarded to the wireless router 12 (5GPCE) within the location via the 5G base station 13, and transmitted to the short message transmission device via the wireless router 12 (5GPCE). The short message transmission device then transmits the second voice data to the receiving end 20 via the BeiDou Navigation Satellite System 15 using the short message communication service.

[0093] During the transmission of the second voice data to the receiving end 20 via the BeiDou Navigation Satellite System 15 using short message communication service, to verify the user's identity, the second voice data is first transmitted to the ground control station 16 via the BeiDou Navigation Satellite System 15 for identity verification. If the ground control station 16 verifies the identity of the second voice data is legitimate, it then transmits the second voice data to the receiving end 20 via the BeiDou Navigation Satellite System. If the ground control station 16 verifies the identity of the voice data is illegitimate, the sending end receives an alarm message sent by the ground control station 16 via the BeiDou Navigation Satellite System. This identity verification verifies whether the sender of the second voice data is a legitimate user, preventing the transmission of voice data from illegitimate users to the receiving end 20, thereby reducing the probability of the receiving end 20 being compromised by unauthorized information and causing a security incident.

[0094] The transmission of voice data via the BeiDou satellite navigation and positioning system 15 is suitable for locations where there is no wired network connection to the outside world (receiving end 20) or where the operator network signal is blocked from connection to the outside world (receiving end 20). It is only used within a preset range in the corresponding location and in locations with a high degree of confidentiality for wired network and operator network signals, thereby improving the security and confidentiality of voice password information transmission.

[0095] S104. Receive control commands or warning messages sent by the receiving end based on the verification result of the voice password verification via the satellite navigation and positioning system.

[0096] After the receiving end 20 verifies the received second sound data using a voice password, it generates a verification result. If the verification result is successful, a control command is generated and fed back to the sending end via the satellite navigation and positioning system. If the verification result is unsuccessful, an alarm message is generated and fed back to the sending end via the satellite positioning and navigation system. The sending end receives the corresponding control command or alarm message sent by the receiving end 20 based on the verification result of the voice password verification via the satellite navigation and positioning system.

[0097] S105. Upon receiving the control command, enable the corresponding permissions according to the control command.

[0098] When the sending end receives a control command, it proves that the user who issued the voice command has been successfully authenticated, and then grants the corresponding permissions according to the control command, such as opening the door.

[0099] S106. Upon receiving the warning information, a warning signal is sent to the safety warning terminal device.

[0100] When the sending end receives an alarm message, it proves that the user who issued the voice password has failed to authenticate. Based on the alarm message, it generates an early warning signal and sends the early warning signal to the security early warning terminal device, such as issuing a "password error" voice alarm.

[0101] Figure 4 This is a flowchart of another voice password transmission verification method provided in the embodiments of this application. Referring to the figure, see below. Figure 4 The voice password transmission verification method, applied to the receiving end 20, specifically includes:

[0102] S201: Receives audio data via the BeiDou satellite navigation and positioning system.

[0103] The receiving end can be understood as a control center for centralized management. Only after the control center verifies the identity can certain permissions for the corresponding location be granted. Generally, locations with high security levels do not have wired networks connecting them to the outside world (receiving end 20), and they block operator network signals for communication with the outside world (receiving end 20). Wired networks and operator network signals are only used within a preset area of ​​the corresponding location to improve security. Edge computing systems and 5G communication systems that can only communicate within the location's area are built in these high-security locations. The corresponding control center is located remotely. For example, in the aforementioned camp transmitter in the Taklamakan Desert, the corresponding control center (receiving end 20) might be located in Beijing or Shanghai. For instance, if voice password authentication is required to enter a certain area within the camp, the camp transmitter will send the processed voice password information and corresponding voice data to the corresponding remote receiving end 20 via the BeiDou satellite navigation and positioning system 15.

[0104] The receiver 20 receives sound data generated by the transmitter based on the user's voice password information captured by the microphone device 11 through the BeiDou satellite positioning system. The BeiDou satellite navigation and positioning system 15 is used for transmitting and receiving the sound data corresponding to the voice password. This is suitable for locations with high security requirements where there is no wired network or operator network signal for external communication, thus improving the security and confidentiality of voice password information transmission.

[0105] S202. Determine the corresponding pre-stored key sound based on the classification label of the sound data.

[0106] The pre-stored sound key can be understood as using a sound recording device to convert the vocabulary content of a user's pre-recorded speech into computer-readable data, repeatedly measuring and recording changes in the sound waveform, and then converting and saving it as a sound template to generate the pre-stored key sound. The sound data sent by the transmitting end is sound data that has undergone label classification processing using an LR classifier. A mapping relationship between corresponding labels and corresponding pre-stored key sounds is pre-set. Therefore, the receiving end 20 can determine the corresponding pre-stored key sound based on the classification labels of the received sound data.

[0107] S203. Perform similarity matching between the sound features of the sound data and the sound features of the pre-stored key sound.

[0108] The system performs a similarity match between the sound features in the sound data and the sound features of pre-stored key sounds in the database. This sound feature matching can verify the identity of the user who issued the voice password.

[0109] S204. When the similarity is greater than or equal to a preset value, a control command is sent to the sending end through the BeiDou satellite navigation and positioning system.

[0110] The preset value can be set according to the actual situation, for example, set to 80%. Then, when the similarity between the sound features of the sound data received from the sending end and the sound features of the pre-stored key sound is greater than or equal to 80%, the authentication is successful, and the corresponding control command is generated. The control command is sent to the corresponding sending end through the Beidou satellite navigation and positioning system 15, so that the sending end can open the corresponding permissions according to the control command.

[0111] S205. When the similarity is less than the preset value, a warning message is sent to the sending end through the Beidou satellite navigation and positioning system.

[0112] The preset value can be set according to the actual situation, for example, set to 80%. Then, when the similarity between the sound features of the sound data received from the sending end and the sound features of the pre-stored key sound is less than 80%, the authentication fails, and the corresponding alarm information is generated. The alarm information is sent to the corresponding sending end through the Beidou satellite navigation and positioning system 15, so that the sending end can make the corresponding alarm prompt based on the alarm information.

[0113] Figure 5 This is a flowchart of another voice password transmission verification method provided in the embodiments of this application, referred to... Figure 5The voice password transmission method includes: S301, when the microphone device at the transmitting end captures voice password information, it sends the voice password information to the wireless router (5GCPE). S302, the wireless router (5GCPE) transmits the voice password information to the 5G base station. S303, the 5G base station transmits the data to an edge server deployed at the edge. This edge server is a voice processing server. S304, the edge server processes the voice password information to generate Doppler spectral features. S305, the edge server performs noise reduction processing on the Doppler spectral features. S306, the voice feature data of less than 14,000 bits is extracted through autoencoder encoding and sent to the BeiDou satellite (GEO satellite) via a BeiDou short message sending device. S307, the BeiDou satellite (GEO satellite) sends the voice data feature data to the ground control center (MCC). S308, after the ground control center (MCC) determines that the sending method is legitimate, it broadcasts the information to the short message receiving end via the BeiDou satellite (GEO satellite). S309. The short message receiver receives the voice feature data sent by the sender and compares it with the voice feature data pre-stored in the database. S310. If the similarity is greater than or equal to 80%, the receiver sends a pass command to the short message sender; otherwise, the receiver sends an alarm command to the short message sender.

[0114] In one embodiment, an classified unit discovered an oil field in the Taklamakan Desert. To further explore, the unit established a highly secure camp. An edge computing system and a 5G communication system, allowing communication only within the camp, were built within the camp area. This edge computing system, acting as the sender of voice password information, includes message sending equipment, microphone equipment, and an edge server. A secure area was designated within the camp, and personnel were prohibited from carrying any electronic devices. Voice data was collected from personnel using microphone equipment, and corresponding voice feature data was extracted using the aforementioned implementation method. This extracted voice feature data was then sent from the camp's sender to the remote headquarters control center (receiving end) via the short message service of the BeiDou Navigation Satellite System. The headquarters control center compared the received voice feature data with pre-stored voice features in its database. If the comparison was successful (similarity greater than or equal to a threshold), the headquarters control center (receiving end) returned an authorization signal to the camp via the short message system. If the comparison failed (similarity less than the threshold), the headquarters control center (receiving end) sent a warning signal to the camp security center via the short message system.

[0115] The above-described method involves performing at least one layer of autoencoder processing on the voice password information acquired by the microphone device to obtain voice data that meets preset data capacity requirements. This voice data is then transmitted to the receiving end via a satellite navigation and positioning system. The receiving end then receives control commands or alarm messages based on the voice password verification results from the voice data. Upon receiving a control command, the corresponding permissions are granted; upon receiving an alarm message, a warning signal is sent to the security warning terminal device. This technique allows for the transmission of voice password information to a remote receiving end via satellite navigation and positioning, reducing reliance on wired networks and carrier network signals, and improving the confidentiality and security of voice password transmission. Furthermore, receiving control commands or alarm messages from the receiving end via satellite navigation and positioning system also avoids the use of wired networks and carrier network signals, further enhancing the confidentiality and security of data transmission.

[0116] Based on the above embodiments, Figure 6 This is a schematic diagram of a voice password transmission verification device provided in an embodiment of this application. (Reference) Figure 6 The voice password transmission verification device provided in this embodiment is specifically applied to the sending end and includes: a voice acquisition module 21, an edge service module 22, a sending module 23, a receiving module 24, a control module 25, and an alarm module 26.

[0117] The sound acquisition module 21 is used to receive the sound password information acquired by the microphone device and transmit the sound password information to the edge server.

[0118] Edge service module 22 is used to perform at least one layer of autoencoder processing on the voice password information through the edge server to obtain voice data, wherein the voice data is data that meets the preset data capacity conditions;

[0119] The sending module 23 is used to send the sound data to the receiving end through the satellite navigation and positioning system so that the receiving end can verify the second sound data with a voice password.

[0120] The receiving module 24 is used to receive control commands or warning messages sent by the receiving end based on the verification result of the voice password verification through the satellite navigation and positioning system;

[0121] Control module 25 is used to enable corresponding permissions according to the control command when the control command is received;

[0122] The alarm module 26 is used to send a warning signal to the security terminal when the warning information is received.

[0123] Furthermore, the edge service module 22 is also used to preprocess the voice password information through the edge server to obtain first voice data;

[0124] The first audio data is processed by the edge server through at least one layer of autoencoder to obtain the second audio data, which is data that meets the preset data capacity conditions.

[0125] Furthermore, the edge service module 22 is also used to perform feature extraction processing on the voice password information through the edge server to generate Doppler spectrogram features;

[0126] The edge server performs noise reduction processing on the Doppler spectrogram features to obtain the first sound data.

[0127] Furthermore, the preset data capacity condition is that the data capacity meets the short message transmission and reception capacity;

[0128] The edge service module 22 is further configured to perform a first-layer autoencoder self-encoding process on the first sound data through the edge server to obtain the first autoencoded data;

[0129] The first autoencoded data is subjected to sound feature extraction processing to obtain sound feature data;

[0130] The edge server matches the data capacity of the sound feature data with the preset data capacity condition to determine whether the sound feature data meets the preset data capacity condition.

[0131] If the sound feature data meets the preset data capacity condition, then the sound feature data is obtained as the second sound data;

[0132] If the sound feature data does not meet the preset data capacity condition, the first autoencoder data will undergo autoencoding processing and sound feature extraction processing at the next layer autoencoder until a second sound data that meets the preset data capacity condition is obtained. The second sound data is the sound feature data.

[0133] Furthermore, the edge service module 22 is also used to perform classification label processing on the second sound data through the edge server, and output the second sound data with corresponding classification labels.

[0134] Furthermore, the satellite navigation and positioning system is the BeiDou satellite navigation and positioning system;

[0135] The sending module 23 is also used to send the sound data to the ground center station through the Beidou satellite navigation and positioning system, so that the ground center station can verify the identity and legality of the sound data;

[0136] If the ground center station verifies that the identity of the voice data is legitimate, the ground center station will send the voice data to the receiving end through the BeiDou navigation and positioning system;

[0137] If the ground center station verifies that the identity of the sound data is invalid, the sending end receives an alarm message sent by the ground center station through the BeiDou navigation and positioning system.

[0138] The above-described method involves performing at least one layer of autoencoder processing on the voice password information acquired by the microphone device to obtain voice data that meets preset data capacity requirements. This voice data is then transmitted to the receiving end via a satellite navigation and positioning system. The receiving end then receives control commands or alarm messages based on the voice password verification results from the voice data. Upon receiving a control command, the corresponding permissions are granted; upon receiving an alarm message, a warning signal is sent to the security warning terminal device. This technique allows for the transmission of voice password information to a remote receiving end via satellite navigation and positioning, reducing reliance on wired networks and carrier network signals, and improving the confidentiality and security of voice password transmission. Furthermore, receiving control commands or alarm messages from the receiving end via satellite navigation and positioning system also avoids the use of wired networks and carrier network signals, further enhancing the confidentiality and security of data transmission.

[0139] The voice password transmission verification device provided in this application embodiment can be used to execute the voice password transmission verification method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0140] This application provides a voice password transmission verification device, referring to... Figure 7 The voice password transmission verification device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors and the number of memories in the voice password transmission verification device can be one or more. The processor, memory, communication module, input device, and output device of the voice password transmission verification device can be connected via a bus or other means.

[0141] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the voice password transmission verification method described in any embodiment of this application (e.g., the voice acquisition module, edge service module, sending module, receiving module, control module 25, and alarm module 26 in the voice password transmission verification device). The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0142] The communication module 33 is used for data transmission.

[0143] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory, thereby realizing the above-mentioned voice password transmission verification method.

[0144] Input device 34 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 35 may include display devices such as a display screen.

[0145] The voice password transmission verification device provided above can be used to execute the voice password transmission verification method provided in the above embodiments, and has corresponding functions and beneficial effects.

[0146] This application embodiment also provides a storage medium for storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a voice password transmission verification method. This voice password transmission verification method includes: receiving voice password information acquired by a microphone device and transmitting the voice password information to an edge server; performing at least one layer of autoencoder processing on the voice password information through the edge server to obtain voice data, wherein the voice data meets a preset data capacity condition; sending the voice data to a receiving end via a satellite navigation and positioning system for the receiving end to perform voice password verification on the second voice data; receiving a control command or warning message sent by the receiving end based on the verification result of the voice password verification via the satellite navigation and positioning system; upon receiving the control command, enabling the corresponding permissions according to the control command; and upon receiving the warning message, sending a warning signal to a security warning terminal device.

[0147] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a first computer system in which the program is executed, or may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0148] Of course, the storage medium for storing computer-executable instructions provided in the embodiments of this application is not limited to the voice password transmission verification method described above, but can also perform related operations in the voice password transmission verification method provided in any embodiment of this application.

[0149] The voice password transmission verification device, storage medium, and voice password transmission verification equipment provided in the above embodiments can execute the voice password transmission verification method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the voice password transmission verification method provided in any embodiment of this application.

[0150] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A voice password transmission verification method, applied at the sending end, characterized in that, include: Receive voice password information acquired by the microphone device and transmit the voice password information to the edge server; The edge server performs at least one layer of autoencoder processing on the voice password information to obtain second voice data. The second voice data is data that meets a preset data capacity condition, which is that the data capacity meets the short message transmission and reception capacity. The second sound data is sent to the receiving end through a satellite navigation and positioning system so that the receiving end can verify the second sound data with a voice password. The satellite navigation and positioning system is the Beidou satellite navigation and positioning system. The receiver receives control commands or warning messages sent by the receiving end based on the verification result of the voice password verification through the satellite navigation and positioning system. The receiving end is used to determine the corresponding pre-stored voice key according to the classification label of the second voice data. The similarity of the sound features of the second sound data with the sound features of the pre-stored sound key is performed; when the similarity is greater than or equal to a preset value, a control command is sent to the sending end through the BeiDou satellite navigation and positioning system; when the similarity is less than the preset value, a warning message is sent to the sending end through the BeiDou satellite navigation and positioning system. Upon receiving the control command, the corresponding permissions are granted according to the control command. Upon receiving the warning information, a warning signal is sent to the safety warning terminal device; The step of performing at least one layer of autoencoder processing on the voice password information through the edge server to obtain the second voice data includes: The edge server preprocesses the voice password information to obtain the first voice data; The first audio data is processed by the edge server through at least one layer of autoencoder to obtain the second audio data, which is data that meets the preset data capacity condition. The step of preprocessing the voice password information through the edge server to obtain the first voice data includes: The edge server performs feature extraction processing on the voice password information to generate Doppler spectrogram features. The edge server performs noise reduction processing on the Doppler spectrogram features to obtain the first sound data.

2. The method according to claim 1, characterized in that, The step of performing at least one layer of autoencoder processing on the first audio data via an edge server to obtain the second audio data includes: The first audio data is processed by the edge server using a first-layer autoencoder to obtain first autoencoded data. The first autoencoded data is subjected to sound feature extraction processing to obtain sound feature data; The edge server matches the data capacity of the sound feature data with the preset data capacity condition to determine whether the sound feature data meets the preset data capacity condition. If the sound feature data meets the preset data capacity condition, then the sound feature data is obtained as the second sound data; If the sound feature data does not meet the preset data capacity condition, the first autoencoder data will undergo autoencoding processing and sound feature extraction processing at the next layer autoencoder until a second sound data that meets the preset data capacity condition is obtained. The second sound data is the sound feature data.

3. The method according to claim 2, characterized in that, After performing at least one layer of autoencoder processing on the first audio data via the edge server to obtain the second audio data, the method further includes: The edge server performs classification and labeling processing on the second sound data, and outputs the second sound data with corresponding classification labels.

4. The method according to claim 1, characterized in that, The step of sending the second sound data to the receiving end via a satellite navigation and positioning system includes: The second voice data is transmitted to the ground center station via the BeiDou satellite navigation and positioning system so that the ground center station can verify the identity and legality of the second voice data; If the ground center station verifies that the identity of the second voice data is legitimate, the ground center station will send the second voice data to the receiving end through the BeiDou satellite navigation and positioning system; If the ground control station verifies that the identity of the second voice data is invalid, the sending end receives an alarm message sent by the ground control station through the BeiDou satellite navigation and positioning system.

5. A voice password transmission verification method, applied at a receiving end, characterized in that, include: The second audio data is received through the BeiDou satellite navigation and positioning system. The second audio data is obtained by the microphone device of the transmitting end, and the audio password information is transmitted to the edge server. The edge server performs at least one layer of autoencoder processing on the voice password information to obtain the second voice data, which is data that meets the preset data capacity condition, whereby the data capacity meets the short message transmission and reception capacity. Determine the corresponding pre-stored audio key based on the classification label of the second audio data; The sound features of the second sound data are matched with the sound features of the pre-stored sound key for similarity. When the similarity is greater than or equal to a preset value, a control command is sent to the sending end through the BeiDou satellite navigation and positioning system; When the similarity is less than a preset value, a warning message is sent to the sending end through the BeiDou satellite navigation and positioning system; The second audio data is obtained by performing at least one layer of autoencoder processing on the audio password information through the edge server, including: The edge server preprocesses the voice password information to obtain the first voice data; The first audio data is processed by the edge server through at least one layer of autoencoder to obtain the second audio data, which is data that meets the preset data capacity condition. The step of preprocessing the voice password information through the edge server to obtain the first voice data includes: The edge server performs feature extraction processing on the voice password information to generate Doppler spectrogram features. The edge server performs noise reduction processing on the Doppler spectrogram features to obtain the first sound data.

6. A voice password transmission verification device, applied at the sending end, characterized in that, include: The sound acquisition module is used to receive voice password information acquired by the microphone device and transmit the voice password information to the edge server; The edge service module is used to perform at least one layer of autoencoder processing on the voice password information through the edge server to obtain second voice data. The second voice data is data that meets a preset data capacity condition, wherein the preset data capacity condition is that the data capacity meets the short message transmission and reception capacity. The sending module is used to send the second sound data to the receiving end through a satellite navigation and positioning system, so that the receiving end can verify the second sound data with a voice password. The satellite navigation and positioning system is the Beidou satellite navigation and positioning system. The receiving module is used to receive control commands or warning messages sent by the receiving end based on the verification result of the voice password verification through the satellite navigation and positioning system. The receiving end is used to determine the corresponding pre-stored voice key according to the classification label of the second voice data. The similarity of the sound features of the second sound data with the sound features of the pre-stored sound key is performed; when the similarity is greater than or equal to a preset value, a control command is sent to the sending end through the BeiDou satellite navigation and positioning system; when the similarity is less than the preset value, a warning message is sent to the sending end through the BeiDou satellite navigation and positioning system. The control module is used to enable the corresponding permissions according to the control command when it receives the control command; The alarm module is used to send a warning signal to the security terminal device when the warning information is received; The step of performing at least one layer of autoencoder processing on the voice password information through the edge server to obtain the second voice data includes: The edge server preprocesses the voice password information to obtain the first voice data; The first audio data is processed by the edge server through at least one layer of autoencoder to obtain the second audio data, which is data that meets the preset data capacity condition. The step of preprocessing the voice password information through the edge server to obtain the first voice data includes: The edge server performs feature extraction processing on the voice password information to generate Doppler spectrogram features. The edge server performs noise reduction processing on the Doppler spectrogram features to obtain the first sound data.

7. A voice password transmission verification device, characterized in that, include: Memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a processor, are used to perform the method as described in any one of claims 1-5.

Images