Audio recording evidence generation and verification method and system, electronic device and storage medium

Abstract

The application discloses a kind of generation and verification method, system, electronic equipment and storage medium of recording evidence, which comprises the following steps: obtaining original audio data from recording device;Original audio data is processed to embed digital watermark in original audio data, and target audio data is obtained;According to target audio data, generate main evidence file and secondary evidence file;According to main evidence file, evidence publicity is carried out;According to secondary evidence file, whether main evidence file is legal is verified.The present application can generate main evidence and secondary evidence according to audio data embedded with digital watermark, carry out evidence publicity through main evidence, and verify the legality of audio data through digital watermark, thereby improving the reliability of main evidence;When main evidence is questioned or may be copied, forged, tampered, secondary evidence can be used to verify main evidence to determine whether main evidence is legal, thereby improving the legality and reliability of recording evidence.

Description

Technical Field

[0001] This invention relates to the field of audio processing technology, and in particular to a method, system, electronic device, and storage medium for generating and verifying audio recording evidence. Background Technology

[0002] As is well known, audio data collected by recording devices such as voice recorders and tape recorders is often used as judicial evidence and even plays a decisive role in some cases. Therefore, the authenticity and legality of audio data are very important.

[0003] However, with the development of computer and related technologies, the forgery, copying, and alteration of audio have become increasingly easy, making it impossible to guarantee the authenticity of recording data. This greatly reduces the legality and reliability of recording data, and consequently, the legality and reliability of judicial evidence. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this invention is to propose a method for generating and verifying audio recording evidence. This method can generate primary evidence and secondary evidence based on audio data embedded with digital watermarks. The primary evidence is made public, and the legality of the audio data can be verified through the digital watermark, thereby improving the reliability of the primary evidence. When the primary evidence is questioned or may be forged or tampered with, the secondary evidence can be used to verify the primary evidence to determine whether the primary evidence is legal. Thus, the legality and reliability of audio recording evidence can be improved.

[0006] Therefore, the second objective of this invention is to provide a system for generating and verifying audio recording evidence.

[0007] Therefore, a third objective of the present invention is to provide an electronic device.

[0008] Therefore, a fourth object of the present invention is to provide a computer-readable storage medium.

[0009] To achieve the above objectives, a first aspect of the present invention discloses a method for generating and verifying audio recording evidence, comprising the following steps: obtaining raw audio data from a recording device; processing the raw audio data to embed a digital watermark into the raw audio data to obtain target audio data; generating a main evidence file and a secondary evidence file based on the target audio data; publicizing the evidence based on the main evidence file; and verifying the legality of the main evidence file based on the secondary evidence file.

[0010] According to the method for generating and verifying audio recording evidence according to embodiments of the present invention, original audio data is acquired, processed, and a digital watermark is embedded in the original audio data to obtain target audio data; a main evidence file and a secondary evidence file are generated based on the target audio data; the main evidence file is publicly disclosed; and the legality of the main evidence file is verified based on the secondary evidence file. Thus, this method can generate main and secondary evidence based on audio data with embedded digital watermarks, publicly disclose the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or altered, the secondary evidence can be used to verify the main evidence to determine its legality, thereby improving the legality and reliability of the audio recording evidence.

[0011] In addition, the method for generating and verifying audio evidence according to the above embodiments of the present invention may also include the following additional technical features:

[0012] In some examples, before obtaining the raw audio data from the recording device, the method further includes: verifying the legitimacy of the recording device; and obtaining the raw audio data after successful verification.

[0013] In some examples, verifying the legitimacy of the recording device includes: verifying the recording device based on its device ID, wherein the device ID is generated by the recording device based on a device certificate uniquely corresponding to the recording device.

[0014] In some examples, the device ID is configured as a 128-bit AES key stored in the OTP register of the recording device.

[0015] In some examples, the recording device includes a secure storage unit that is encrypted with the AES key, and the data stored in the secure storage unit can only be accessed on the recording device and only in a preset mode.

[0016] In some examples, after verifying the legitimacy of the recording device, the process further includes: the recording device generating an evidence key in a secure environment, the evidence key comprising an evidence private key and an evidence public key; storing the evidence private key in the secure storage unit; generating a registration ID based on the evidence public key and storing it in the recording device; encrypting the evidence public key and the device ID with the device certificate and registering them with a certification authority, so that the certification authority can check the legitimacy of the device certificate, and after confirming the legitimacy of the device certificate, registering the device ID, registration ID, and evidence public key in a database, generating a registration receipt, and sending the registration receipt to the recording device; the recording device recording the received registration receipt in the database and deleting the evidence public key to complete the registration of the recording device.

[0017] In some examples, the method further includes: if the recording device does not receive the registration receipt within a preset time, it shall re-register so that the certification authority may resend the registration receipt until the recording device receives the registration receipt.

[0018] In some examples, the method further includes: when the recording device is initialized, retaining the previously recorded registration receipt; when re-registering after initialization, the certification authority compares the retained registration receipt with the registration receipt in the database, and when the registration is confirmed to be valid, marks the corresponding registration ID before initialization as outdated.

[0019] In some examples, processing the original audio data includes: generating digital watermark information, the digital watermark information including recording time information corresponding to the original audio data; encrypting the digital watermark information according to the RSA key in the digital watermark information to obtain encrypted digital watermark information; encoding the encrypted digital watermark information to obtain the digital watermark; and embedding the digital watermark into the original audio data to obtain the target audio data.

[0020] In some examples, embedding the digital watermark into the original audio data includes: performing frame segmentation on the original audio data to extract a first audio synchronization reference point with the watermark; dividing the original audio data into multiple first synchronization units based on the first audio synchronization reference point; dividing each first synchronization unit into multiple first audio segments, and performing a fast Fourier transform on each first audio segment to obtain a corresponding first low-frequency spectrum; and embedding the digital watermark into the first low-frequency spectrum to obtain the target audio data.

[0021] In some examples, the process of generating the master evidence file includes: calculating the data size of the target audio data and the corresponding first hash value; generating a globally unique identifier corresponding to the target audio data; filling the content of the target audio data into a preset first file data structure according to the data size of the target audio data, the first hash value, and the globally unique identifier, wherein the first file data structure contains a first evidence header; signing the first evidence header with the RSA key, and saving it to obtain the master evidence file.

[0022] In some examples, the process of generating the secondary evidence file includes: encrypting the digital watermark using the RSA key to obtain an encrypted digital watermark; calculating the data size of the encrypted digital watermark and its corresponding second hash value; obtaining the globally unique identifier; filling the content of the encrypted digital watermark into a preset second file data structure based on the globally unique identifier, the data size of the encrypted digital watermark, and its corresponding second hash value, wherein the second file data structure includes a second evidence header; signing the second evidence header using the RSA key; and saving the signed evidence file to obtain the secondary evidence file.

[0023] In some examples, the evidence disclosure based on the master evidence file includes: extracting a second audio synchronization reference point with a watermark from the master evidence file; dividing the audio in the master evidence file into multiple second synchronization units based on the second audio synchronization reference point; dividing each second synchronization unit into multiple second audio segments, and performing a Fast Fourier Transform on each second audio segment to obtain a corresponding second low-frequency spectrum; extracting a binary watermark from the second low-frequency spectrum, and decoding and decrypting the binary watermark using a public key corresponding to the RSA key to obtain the corresponding current watermark information; comparing the current watermark information with the digital watermark information to determine whether the original audio data is legitimate.

[0024] In some examples, verifying the legitimacy of the primary evidence file based on the secondary evidence file includes: decrypting the secondary evidence file using the public key corresponding to the RSA key to obtain the second evidence header and digital watermark information; and comparing the second evidence header and the digital watermark information with the primary evidence file to determine whether the primary evidence file is legitimate.

[0025] To achieve the above objectives, a second aspect of the present invention discloses a system for generating and verifying audio recording evidence, comprising: an acquisition module for acquiring raw audio data from a recording device; a processing module for processing the raw audio data to embed a digital watermark into the raw audio data to obtain target audio data; a generation module for generating a main evidence file and a secondary evidence file based on the target audio data; a public disclosure module for publicizing the evidence based on the main evidence file; and a verification module for verifying the legality of the main evidence file based on the secondary evidence file.

[0026] According to the audio recording evidence generation and verification system of the present invention, the system acquires original audio data, processes the original audio data to embed a digital watermark into the original audio data, and obtains target audio data; generates a main evidence file and a secondary evidence file based on the target audio data; discloses the evidence based on the main evidence file; and verifies the legality of the main evidence file based on the secondary evidence file. Thus, the system can generate main and secondary evidence based on audio data with embedded digital watermarks, disclose the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or tampered with, the secondary evidence can be used to verify the main evidence to determine its legality, thereby improving the legality and reliability of the audio recording evidence.

[0027] To achieve the above objectives, a third aspect of the present invention discloses an electronic device, including a system for generating and verifying audio evidence as described in the second aspect of the present invention; or, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the method for generating and verifying audio evidence as described in the first aspect of the present invention.

[0028] According to an embodiment of the present invention, an electronic device acquires original audio data, processes the original audio data to embed a digital watermark into the original audio data, and obtains target audio data; generates a primary evidence file and a secondary evidence file based on the target audio data; discloses the evidence based on the primary evidence file; and verifies the legality of the primary evidence file based on the secondary evidence file. Thus, the electronic device can generate primary and secondary evidence based on audio data embedded with a digital watermark, disclose the evidence through the primary evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the primary evidence. When the primary evidence is questioned or may be forged or altered, the secondary evidence can be used to verify the primary evidence to determine its legality, thereby improving the legality and reliability of the recorded evidence.

[0029] To achieve the above objectives, a fourth aspect of the present invention discloses a computer-readable storage medium storing a program that, when executed by a processor, implements the method for generating and verifying audio evidence as described in the first aspect of the present invention.

[0030] According to an embodiment of the present invention, a computer-readable storage medium storing a program thereon, when executed by a processor, can acquire original audio data, process the original audio data to embed a digital watermark into the original audio data, and obtain target audio data; generate a main evidence file and a secondary evidence file based on the target audio data; publicize the evidence based on the main evidence file; and verify the legality of the main evidence file based on the secondary evidence file. Thus, it is possible to generate main evidence and secondary evidence based on audio data with embedded digital watermarks, publicize the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or tampered with, the main evidence can be verified through the secondary evidence to determine its legality, thereby improving the legality and reliability of the recorded evidence.

[0031] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0032] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0033] Figure 1 This is a flowchart of a method for generating and verifying audio evidence according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram illustrating the process of verifying the legality of a recording device according to an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram illustrating the device certificate generation process of a recording device according to an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of the registration process of a recording device according to an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram of the process of embedding a digital watermark according to an embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram illustrating the process of extracting digital watermark information according to an embodiment of the present invention;

[0039] Figure 7This is a schematic diagram of the data structure of the master evidence file according to an embodiment of the present invention;

[0040] Figure 8 This is a schematic diagram of the data structure of a supplementary evidence document according to an embodiment of the present invention;

[0041] Figure 9 This is a structural block diagram of a system for generating and verifying audio evidence according to an embodiment of the present invention. Detailed Implementation

[0042] The embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. The embodiments of the present invention are described in detail below.

[0043] The following is for reference. Figures 1-9 This invention describes a method, system, electronic device, and storage medium for generating and verifying audio recording evidence according to embodiments of the present invention.

[0044] Figure 1 This is a flowchart of a method for generating and verifying audio recording evidence according to an embodiment of the present invention. Figure 1 As shown, the method for generating and verifying this audio evidence includes the following steps:

[0045] Step S1: Obtain raw audio data from the recording device.

[0046] In a specific embodiment, the recording device is a device that collects and records voice data, such as, but not limited to, a voice recorder, a recorder, a mobile phone with recording function, a tablet computer, etc. The recording device can record raw audio data, such as dialogue between people, and store it in the corresponding storage space. Thus, when needed, the raw audio data collected by the recording device can be retrieved.

[0047] Step S2: Process the original audio data to embed the digital watermark into the original audio data to obtain the target audio data.

[0048] Specifically, this involves processing the acquired raw audio data, such as embedding a digital watermark into the raw audio data through encryption and encoding, to obtain the target audio data. In other words, the target audio data is the raw audio data that has undergone a series of processing steps, resulting in audio data with a digital watermark.

[0049] Step S3: Generate the main evidence file and the secondary evidence file based on the target audio data.

[0050] Step S4: Publicize the evidence based on the main evidence document.

[0051] Step S5: Verify the legality of the main evidence document based on the supplementary evidence document.

[0052] Specifically, the target audio data can generate two types of evidence files: a primary evidence file and a secondary evidence file. On one hand, the primary evidence file allows for public disclosure to verify the authenticity of the original audio data, thereby enhancing the legality and reliability of the recording evidence. For example, the primary evidence file allows for direct playback of the audio, querying information such as the recording time, authenticating the primary evidence file, and identifying the recording device corresponding to the original audio data. When the original audio data is suspected of being forged, copied, or tampered with, the primary evidence file is submitted to an authentication agency. The agency can use a public key to extract all information from the primary evidence file, such as the encrypted and encoded digital watermark in the audio, which can then be decoded and decrypted to obtain the original watermark data. Based on the extracted data, the agency determines the authenticity and legality of the original audio data and can generate an authentication report, which is then made public to relevant personnel, thus proving the authenticity and legality of the recording evidence. On the other hand, the secondary evidence file verifies the legality of the primary evidence file. For example, when the authenticity of the primary evidence document is questioned, such as if someone copies or tampers with it, the primary evidence document can be verified through secondary evidence documents to determine its authenticity and legality. For instance, the device holder can use a public key to decrypt the secondary evidence document and obtain the original watermark data. If someone copies or tampers with the data in the primary evidence document, the data parsed from the secondary evidence document can be compared with the corresponding data in the primary evidence document to determine its authenticity and legality. When there are multiple primary evidence documents, the accurate and authentic primary evidence document can be determined by identifying which one contains the original audio data, thereby improving the accuracy and legality of the primary evidence document and ultimately enhancing the legality and reliability of the recorded evidence.

[0053] Therefore, the above-described method for generating and verifying audio evidence involves acquiring original audio data, processing the original audio data to embed a digital watermark into the original audio data, obtaining target audio data, generating a main evidence file and a secondary evidence file based on the target audio data, publicizing the evidence based on the main evidence file, and verifying the legality of the main evidence file based on the secondary evidence file. Thus, this method can generate main and secondary evidence based on audio data embedded with a digital watermark, publicize the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. Furthermore, when the main evidence is questioned or may be forged or altered, the secondary evidence can be used to verify the main evidence to determine its legality, thereby improving the legality and reliability of the audio evidence.

[0054] In one embodiment of the present invention, before obtaining the original audio data from the recording device, the method further includes: verifying the legitimacy of the recording device; and obtaining the original audio data after the verification is passed.

[0055] Specifically, with the development of computer-related technologies, it has become easier to forge, copy, or tamper with recording devices. Therefore, in this embodiment of the invention, a verification mechanism for the legitimacy of recording devices is established to ensure the legitimacy and security of the recording devices themselves. Specifically, in this embodiment of the invention, the legitimacy of the recording device is verified before obtaining the original audio data from the recording device. This involves the distribution, production, and storage of the recording device legitimacy certificate, and can solve problems such as the initialization of the recording device legitimacy certificate. After the recording device's legitimacy verification is passed, the original audio data is obtained, thereby improving the security, legitimacy, and reliability of the recording device, and further enhancing the security, authenticity, and reliability of the original audio data.

[0056] In one embodiment of the present invention, verifying the legitimacy of the recording device includes: verifying the recording device based on the device ID of the recording device, wherein the device ID is generated by the recording device based on a device certificate uniquely corresponding to the recording device.

[0057] In one embodiment of the invention, the device ID is configured as a 128-bit AES key stored in the OTP register of the recording device.

[0058] Specifically, combined Figure 2 As shown, the process of generating a device certificate includes, for example, the following: After obtaining authorization from a certification authority, the device manufacturer receives a manufacturer certificate. Based on the manufacturer certificate, a product certificate can be generated for the recording devices to be manufactured, and a unique device certificate is generated for each recording device using the product certificate. Within the recording device, the device can generate a unique RSA key pair as an evidence key and register the evidence public key with the certification authority. It can be understood that the RSA key pair includes an RSA private key and an RSA public key corresponding to the RSA private key.

[0059] Each recording device includes an OTP (One-Time Programmable) register, which stores its unique device ID, i.e., a 128-bit AES (Advanced Encryption Standard) key. This AES key is used for secure storage. This AES key is unique to each recording device and is written to it after random initialization by the recording device itself.

[0060] It should be noted that the AES key in the OTP register can only be accessed by the CPU (Central Processing Unit) in secure mode. It is randomly generated and written into the OTP register during the production of the recording device in secure mode.

[0061] In one embodiment of the present invention, the recording device includes a secure storage unit, which is encrypted using an AES key. Data stored in the secure storage unit is accessible only on the recording device and only in a preset mode. The preset mode is, for example, a secure mode, where the data stored in the secure storage unit is accessible only on the recording device and only in a secure environment.

[0062] In specific embodiments, the secure storage unit is located in a non-volatile storage area, including MMC (MultiMedia Card), NAND (NAND flash memory), or hard disk. The secure storage unit has the following two characteristics: 1. Data stored in the secure storage unit can only be deciphered in plaintext mode by the CPU; 2. Data stored in the secure storage unit cannot be decrypted by the other recording device after being copied to it. To achieve these two characteristics, in this embodiment of the invention, the secure storage unit uses an AES key in the chip's OTP register for encryption. The AES key can only be accessed in the CPU's secure mode, therefore, data can only be decrypted in the CPU's secure mode to obtain plaintext. Furthermore, the AES key is uniquely associated with each recording device. Therefore, data stored in the secure storage unit cannot be decrypted using the AES key on the other recording device's SOC (System on Chip). This prevents the recording device from being copied, tampered with, or forged, thereby improving the security and reliability of the recording device and enhancing the authenticity and legality of the recorded data.

[0063] In another embodiment, the secure storage unit is also used to store the recording device's device certificate, evidence private key (i.e., RSA private key), and registration receipt, etc.

[0064] As a specific embodiment, combined with Figure 2 and Figure 3This paper describes the authorization and distribution process of device certificates for recording equipment. Specifically, the certification authority authorizes equipment manufacturers to produce recording equipment. Each manufacturer needs to obtain a manufacturer certificate, which they create and send to the certification authority. The certification authority then returns a manufacturer certificate. Once the manufacturer has the manufacturer certificate, it can use it to generate a product certificate for each product. Then, using the product certificate, it generates a unique device certificate for each recording device. This device certificate is embedded in the corresponding recording device when the product leaves the factory. The recording device uses its device certificate to generate a 128-byte AES key, i.e., the device ID, as its unique identifier.

[0065] In one embodiment of the present invention, after verifying the legality of the recording device, the process further includes: a registration process for the recording device. Figure 4 The registration process for recording equipment is as follows:

[0066] 1. In a secure environment, the recording device generates an evidence key, which includes a private evidence key and a public evidence key. Specifically, the evidence key is, for example, an RSA-2048 random key pair. An RSA-2048 random key pair is an asymmetric key pair, containing a private key and a public key—that is, an evidence private key and an evidence public key. In other words, each recording device has a unique set of paired RSA-2048 keys used to encrypt data. The private key is stored on the device and used to encrypt the evidence data to generate evidence data; the public key is stored in the cloud, such as by a certification authority, and can be used to verify data when necessary. The private key is stored on the device and must be accessible only in a secure environment. Before being written into the device environment, the private key is protected by a unique DUK (device unique key), also known as the device ID. This DUK is an AES-128 key that is written into the OTP of the recording device's SoC when the recording device is generated. This DUK itself is also protected by AES embedded in the chip and is not in plaintext, thereby improving security.

[0067] 2. Store the evidence private key in a secure storage unit.

[0068] 3. A registration ID is generated based on the evidence public key and stored in the recording device. Specifically, the recording device uses the evidence public key to generate a 32-byte message digest, which is the registration ID, and is stored in the recording device. It is understood that every subsequent recording evidence must include the registration ID information. The evidence public key is deleted from the local machine after the recording device has successfully registered.

[0069] 4. After encrypting the evidence public key and device ID with the device certificate, the device is registered with the certification authority. This allows the certification authority to verify the validity of the device certificate. Upon confirming the validity of the device certificate, the certification authority registers the device ID, registration ID, and evidence public key in a database, such as a secure storage unit, and generates a registration receipt, which is then sent to the recording device. Specifically, the recording device encrypts the evidence public key and device ID with the public key from the device certificate and registers them with the certification authority. Upon receiving the device registration, the certification authority verifies the validity of the device certificate and then registers the device ID, registration ID, and evidence public key in its database to complete the recording device registration. After registration, the certification authority generates a random 128-byte receipt and sends it to the recording device as the registration receipt.

[0070] 5. The recording device records the received registration receipt in the database and deletes the evidence public key to complete the registration of the recording device. Specifically, after receiving the registration receipt, the recording device records the registration receipt in a secure storage environment, i.e., the database, and deletes the evidence public key from the recording device. This completes the registration of the recording device.

[0071] In one embodiment of the present invention, after the registration of the recording device is completed, the method further includes: if the recording device does not receive a registration receipt within a preset time, it shall re-register so that the certification authority resends the registration receipt until the recording device receives the registration receipt. Specifically, if the recording device does not receive a registration receipt within a specified time, the recording device may re-register, and the certification authority shall reissue the registration receipt until the recording device successfully receives the registration receipt.

[0072] In one embodiment of the present invention, after the registration of the recording device is completed, the method further includes: when the recording device is initialized, retaining the registration receipt of the last recorded session; when re-registering after initialization, the certification authority compares the retained registration receipt with the registration receipt in the database, and when it confirms that the current registration is legal, marks the corresponding registration ID before initialization as outdated.

[0073] Specifically, when the recording device is initialized, such as when it is restored to factory settings, the previous registration receipt is retained; that is, the previous registration receipt is not cleared. After initialization (such as after a factory reset), the user needs to repeat the registration process. During re-registration, the previous registration receipt is required. That is, the certification authority searches its database based on the retained previous registration receipt, compares it with the existing registration receipts, and if the current registration is confirmed to be valid, marks the original registration ID (the one from before initialization) as outdated, but retains the record for future authentication purposes.

[0074] As a specific embodiment, the following provides an exemplary description of the legality verification process for recording devices in conjunction with specific application scenarios.

[0075] In a specific embodiment, it is understood that although equipment manufacturers possess product certificates and can write the same certificate into different recording devices, each recording device generates its own corresponding evidence key pair. Therefore, during the registration process, the recording device registers its evidence public key with the certification authority. Since the device registration process occurs after the recording device leaves the factory, this evidence key pair is randomly unique, and the equipment manufacturer cannot obtain it. This ensures that each recording device is unique, and the equipment manufacturer cannot copy an identical recording device. This effectively prevents the equipment manufacturer from stealing or copying the recording device, ensuring that the recording device cannot be copied or forged by the equipment manufacturer, thereby improving the security and legality of the recording device, and consequently, the security and legality of the recorded data. If the certification authority discovers recording devices with the same device ID registered with different evidence public keys, it can initiate an inquiry into the equipment manufacturer and, if necessary, revoke its product certificate.

[0076] In a specific implementation, it is understood that before a device manufacturer produces the equipment, a certification body must first conduct a qualification review of the manufacturer, authorize the manufacturer, and issue a product certificate. The manufacturer then generates a certificate for each recording device. Third parties outside the manufacturer cannot obtain product certificates and therefore cannot produce recording devices with insecure software. Furthermore, because the authorization of device certificates uses a hierarchical authorization method, it is possible to trace the manufacturer back to the manufacturer. If a manufacturer is found to have security issues, its product certificate can be revoked. This makes the manufacturer's responsibility traceable, thereby incentivizing them to ensure the security of their recording devices and preventing them from using third parties to counterfeit recording devices and create recording devices with uncontrolled software, thus improving the security and legality of the recording devices.

[0077] In specific embodiments, it is understood that the certification authority only possesses the public key of the recording device, while to forge the recording device, one must possess its private key. In the embodiments of the present invention, only the recording device possesses its private key; therefore, the certification authority cannot forge the recording device. This effectively prevents certification authorities from forging and copying the recording device, thereby improving the security and legitimacy of the recording device.

[0078] In other words, the process of verifying the legality of the recording device in the embodiments of the present invention specifically involves the distribution, production, and storage of a legality certificate for the recording device. When the recording device records the original audio data, it can record the recording time and other related information of the recording device, and bind this information to prevent the recording device from being copied, tampered with, or forged. This can improve the security and legality of the recording device, and thus improve the security and reliability of the recording data.

[0079] In some embodiments, the recording device is equipped with RTC (Real-Time Clock) hardware. Before the recording device starts working, the RTC performs network time synchronization, and when the RTC is reset, network time synchronization is performed again. Additionally, the recording device can be configured to restrict users from manually setting the time. This ensures the authenticity and legitimacy of the time information used when recording audio data.

[0080] In other embodiments, before each audio data collection by the recording device, the collection time is registered with the certification authority. The certification authority registers the collection time and generates a unique number for this collection. This unique number is then sent to the recording device. In this way, time authentication can be completed for each recording device when collecting audio data, ensuring the authenticity and legality of the time information when the recording device records audio data.

[0081] In one embodiment of the present invention, the process of processing the original audio data includes: generating digital watermark information, wherein the digital watermark information includes recording time information corresponding to the original audio data, and it is understood that the recording time information is generated synchronously by the recording device when acquiring the original audio data; encrypting the digital watermark information according to the RSA key in the digital watermark information to obtain encrypted digital watermark information, thereby improving the security of the watermark digital information; encoding the encrypted digital watermark information to obtain a digital watermark, thereby further improving the security of the digital watermark information; and embedding the digital watermark into the original audio data to obtain target audio data. It is understood that the target audio data is the audio data obtained after embedding the digital watermark into the original audio data, wherein the digital watermark is the watermark data obtained after encrypting and encoding the digital watermark information.

[0082] Specifically, combined Figure 5As shown, the process begins with generating a digital watermark, which contains the recording time information of the original audio data. The generated digital watermark is then preprocessed, for example, by encrypting it using the RSA key within the watermark. The encrypted watermark is then encoded to obtain a binary encoded watermark, i.e., the digital watermark itself. This binary encoded watermark is then embedded into the original audio data using a watermark embedding algorithm to obtain the target audio data. It is understood that the RSA key in the digital watermark corresponds to the RSA private key in the recording device. The watermark embedding algorithm described above can be any existing watermark embedding algorithm, as long as it can embed the digital watermark into the audio data; no restrictions are placed here.

[0083] In one embodiment of the present invention, combined with Figure 5 As shown, the process of embedding a digital watermark into the original audio data includes: performing frame segmentation on the original audio data to extract the first audio synchronization reference point with the watermark; dividing the original audio data into multiple first synchronization units according to the first audio synchronization reference point; dividing each first synchronization unit into multiple first audio segments, and performing a fast Fourier transform on each first audio segment to obtain the corresponding first low-frequency spectrum; embedding the digital watermark into the first low-frequency spectrum to obtain the target audio data. Specifically, the pre-set digital watermark information is encrypted using an RSA key, and the encrypted watermark is encoded to obtain more secure binary watermark data, i.e., the digital watermark. The digital watermark is then embedded into the original audio data. This process includes: performing frame segmentation on the original audio data, such as performing non-overlapping equal-length frame segmentation, and extracting the watermark synchronization reference point, i.e., the first audio synchronization reference point; dividing the original audio data into several synchronization units, i.e., multiple first synchronization units, based on the watermark synchronization reference point; further dividing each first synchronization unit into several audio segments, i.e., multiple first audio segments; and performing FFT (Fast Fourier Transform) on each first audio segment to obtain the corresponding first low-frequency spectrum. The binary watermark data is then embedded into the first low-frequency spectrum to obtain the corresponding target audio data.

[0084] In one embodiment of the present invention, the process of generating a master evidence file includes: calculating the data size of the target audio data and the corresponding first hash value; generating a GUID (Globally Unique Identifier) ​​corresponding to the target audio data to identify the uniqueness of the file; filling the content of the target audio data into a preset first file data structure according to the data size of the target audio data, the first hash value, and the globally unique identifier, wherein the first file data structure contains a first evidence header; signing the first evidence header with an RSA key, and saving it to obtain the master evidence file. That is to say, the generated master evidence file contains at least recording time information, hash value, and other information, as well as the original audio data.

[0085] In a specific embodiment, the format of the master evidence file is as follows: Figure 7 As shown, it includes an evidence header, i.e., the first evidence header, and the original audio data with a watermark, i.e., the target audio data, and other related data. Specifically, for the main evidence file, the size and hash value of the target audio data are first calculated, and a unique GUID is generated to identify the file's uniqueness. The relevant content of the main evidence file, such as the GUID, magic text, version, DUK, RUK (Ramdom Unique Key), recording time information, audio data offset position, audio data size (e.g., audio data length), audio data hash value, offset positions of other related data, lengths of other related data, hash values ​​of other related data, reserved data, and evidence signature, are then filled into the various fields of the main evidence file data structure, i.e., the first file data structure. Specifically, this can be filled into the various fields of the evidence header of the main evidence file. The evidence header of the main evidence file is signed using an RSA key, and after saving, an independent file is obtained, i.e., the main evidence file, for example, denoted as example.audio.

[0086] In one embodiment of the present invention, the process of generating a secondary evidence file includes: encrypting the digital watermark using an RSA key to obtain an encrypted digital watermark; calculating the data size of the encrypted digital watermark and its corresponding second hash value; obtaining a globally unique identifier, i.e., the GUID corresponding to the primary evidence file during its generation, since the primary and secondary evidence files are one-to-one correspondences, the same GUID is used. Based on the globally unique identifier, the data size of the encrypted digital watermark, and the corresponding second hash value, the content of the encrypted digital watermark is filled into a preset second file data structure, wherein the second file data structure includes a second evidence header; the second evidence header is signed using an RSA key and saved to obtain the secondary evidence file. That is to say, the generated secondary evidence file contains at least recording time information, hash value, and the encrypted digital watermark. The secondary evidence file mainly serves as a backup of the encrypted digital watermark and is stored in the recording device.

[0087] In a specific embodiment, the format of the supplementary evidence document is as follows: Figure 8 As shown, it includes an evidence header, i.e., the second evidence header, and an encrypted digital watermark. Specifically, for the secondary evidence file, the encrypted digital watermark is first obtained, its size and hash value are calculated, and the GUID corresponding to the primary evidence file is obtained to identify the file's uniqueness. The relevant content of the secondary evidence file, such as the GUID, magic letter, version, DUK, RUK, recording time information, the offset position of the encrypted digital watermark, the size of the encrypted digital watermark (e.g., the length of the encrypted digital watermark), the hash value of the encrypted digital watermark, reserved data, and evidence signature, are then filled into the various fields of the secondary evidence file data structure, i.e., the second file data structure. Specifically, this can be filled into the various fields of the evidence header of the secondary evidence file. The evidence header of the secondary evidence file is signed using an RSA key, i.e., the private key of the recording device. After saving, an independent file is obtained, i.e., the secondary evidence file, for example, denoted as example.dat.

[0088] In one embodiment of the present invention, combined with Figure 6As shown, the process of publicizing evidence based on the master evidence file includes: extracting the second audio synchronization reference point with watermark from the master evidence file; dividing the audio in the master evidence file into multiple second synchronization units based on the second audio synchronization reference point; dividing each second synchronization unit into multiple second audio segments, and performing a fast Fourier transform on each second audio segment to obtain the corresponding second low-frequency spectrum; extracting the binary watermark from the second low-frequency spectrum, and decoding and decrypting the binary watermark using the public key corresponding to the RSA key to obtain the corresponding current watermark information; comparing the current watermark information with the digital watermark information to determine whether the original audio data is legitimate. Specifically, this involves extracting the watermarked audio synchronization reference point, i.e., the second audio synchronization reference point. Based on this reference point, the audio is divided into multiple second synchronization units, and each unit is further divided into several audio segments. An FFT is performed on each segment to obtain the corresponding second low-frequency spectrum. A binary watermark is extracted from the low-frequency spectrum of each segment, and then decoded and decrypted using an RSA public key to obtain the corresponding watermark data. This data is then compared with the pre-defined watermark data to confirm whether the audio has been tampered with. For example, it is determined whether the decoded and decrypted watermark data matches the pre-defined watermark data. If they match, the audio in the main evidence file has not been tampered with; otherwise, it is considered that the audio in the main evidence file has been tampered with. The pre-defined watermark data can be, for example, a digital watermark embedded in the original audio data, i.e., a digital watermark obtained after encryption and encoding of the digital watermark information.

[0089] In one embodiment of the present invention, verifying the legitimacy of the primary evidence file based on the secondary evidence file includes: decrypting the secondary evidence file using the public key corresponding to the RSA key to obtain a second evidence header and digital watermark information; comparing the second evidence header and digital watermark information with the primary evidence file to determine whether the primary evidence file is legitimate. For example, when the audio in the primary evidence file is suspected of being forged, i.e., when the legitimacy of the primary evidence file is questioned, the primary evidence file can be submitted to an authentication agency for authentication. The authentication agency can use the RSA public key to extract all information in the primary evidence file, such as extracting the encrypted and encoded digital watermark from the audio, then decoding and decrypting it to obtain the original watermark data, i.e., the digital watermark information. Based on the extracted relevant data, the agency determines whether the audio file is legitimate and generates an authentication report which is then made public to relevant personnel. This verifies the authenticity and legitimacy of the audio data in the primary evidence file. Furthermore, the device holder can use the RSA public key to decode and decrypt the secondary evidence file to obtain the header information and original watermark information, i.e., digital watermark information. If someone copies the data in the main evidence file, the corresponding data in the secondary evidence file can be used to judge the main evidence file, thereby determining which one is the original audio data, thus providing further evidence and improving the security and reliability of the recording evidence.

[0090] In other words, after the recording device records the raw audio data through its microphone, the raw audio data undergoes a series of processing steps, including adding a digital watermark, generating evidentiary data, encrypting the evidentiary data, and finally generating the main evidence file and the supplementary evidence file. The main evidence file can be used for evidence disclosure, while the supplementary evidence file can assist in verifying the legality of the main evidence file in situations where there is a dispute over its submission, thereby providing further evidence.

[0091] To facilitate a better understanding of the main evidence document formula and the auxiliary evidence document process for verifying the main evidence document in the above embodiments of the present invention, the following specific embodiments are described in conjunction with specific scenarios.

[0092] In some embodiments, when there is only one version of the master evidence document, if someone questions the master evidence document, the master evidence document can simply be submitted to an certification body for certification, and the certification body's certification report will be the final result.

[0093] In other embodiments, when there are two versions of the master evidence file, one of which is obtained by tampering with the original master evidence file, such as by removing certain key information from the audio, the hash value of the audio data in the tampered master evidence file will not correspond to the hash value of the evidence header of the master evidence file; and the watermark information extracted from the audio will also be missing. Therefore, submitting the two master evidence files to an authentication agency for authentication can determine the authenticity of the two master evidence files and issue authentication reports for the two master evidence files.

[0094] In some embodiments, when there are two versions of the master evidence file, one of which is obtained by the forger using a legitimate recording device to transcribe the original audio data, this forged master evidence file is also legitimate from the perspective of the certification authority. Therefore, the certification authority cannot distinguish between the authenticity of the two versions. However, the transcribed audio will still have the digital watermark information of the original audio. The digital watermark information has the characteristic of preventing transcription. Therefore, the holder of the recording device can extract the digital watermark information of the audio from the secondary evidence file. Thus, two digital watermark information can be extracted from the forged audio. By comparing the extracted digital watermark information with the digital watermark information of the secondary evidence file, if the digital watermark information of the other recording device can be obtained from one audio file, it means that the audio file is transcribed. Audio with only one digital watermark information is obviously more credible than audio with multiple digital watermark information. Thus, it is possible to determine and identify the genuine and legitimate recording evidence as well as the forged, copied, or tampered recording evidence.

[0095] Therefore, the recording evidence generation and verification method of this invention provides a recording evidence generation and legality verification mechanism, which can ensure the authenticity and legality of audio data, prevent audio data from being forged, copied, or tampered with, and provide a safe and reliable recording evidence verification environment. Simultaneously, the process of verifying the legality of the recording device also involves the distribution, production, and storage of a recording device legality certificate. When the recording device records original audio data, it can record the recording time and other related information of the recording device, binding this information to prevent the recording device from being copied, tampered with, or forged. This improves the security and legality of the recording device, and consequently enhances the security and reliability of the recording data.

[0096] In specific embodiments, the methods of the present invention can be applied to many fields and scenarios such as recording devices such as voice recorders, notary systems, and public security evidence collection systems, and have strong applicability and a wide range of applications.

[0097] According to the method for generating and verifying audio recording evidence according to embodiments of the present invention, original audio data is acquired, processed, and a digital watermark is embedded in the original audio data to obtain target audio data; a main evidence file and a secondary evidence file are generated based on the target audio data; the main evidence file is publicly disclosed; and the legality of the main evidence file is verified based on the secondary evidence file. Thus, this method can generate main and secondary evidence based on audio data with embedded digital watermarks, publicly disclose the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or altered, the secondary evidence can be used to verify the main evidence to determine its legality, thereby improving the legality and reliability of the audio recording evidence.

[0098] A further embodiment of the present invention proposes a system for generating and verifying audio recording evidence.

[0099] Figure 9 This is a structural block diagram of a system for generating and verifying audio evidence according to an embodiment of the present invention. Figure 9 As shown, the audio recording evidence generation and verification system 100 includes: an acquisition module 110, a processing module 120, a generation module 130, a public display module 140, and a verification module 150.

[0100] Specifically, the acquisition module 110 is used to acquire raw audio data from the recording device.

[0101] In a specific embodiment, the recording device is a device that collects and records voice data, such as, but not limited to, a voice recorder, a recorder, a mobile phone with recording function, a tablet computer, etc. The recording device can record raw audio data, such as dialogue between people, and store it in the corresponding storage space. Thus, when needed, the raw audio data collected by the recording device can be retrieved.

[0102] The processing module 120 is used to process the original audio data to embed the digital watermark into the original audio data to obtain the target audio data.

[0103] Specifically, this involves processing the acquired raw audio data, such as embedding a digital watermark into the raw audio data through encryption and encoding, to obtain the target audio data. In other words, the target audio data is the raw audio data that has undergone a series of processing steps, resulting in audio data with a digital watermark.

[0104] The generation module 130 is used to generate the main evidence file and the secondary evidence file based on the target audio data.

[0105] The public disclosure module 140 is used to disclose evidence based on the main evidence document.

[0106] The verification module 150 is used to verify the legality of the main evidence document based on the secondary evidence document.

[0107] Specifically, the target audio data can generate two types of evidence files: a primary evidence file and a secondary evidence file. On one hand, the primary evidence file allows for public disclosure to verify the authenticity of the original audio data, thereby enhancing the legality and reliability of the recording evidence. For example, the primary evidence file allows for direct playback of the audio, querying information such as the recording time, authenticating the primary evidence file, and identifying the recording device corresponding to the original audio data. When the original audio data is suspected of being forged, copied, or tampered with, the primary evidence file is submitted to an authentication agency. The agency can use a public key to extract all information from the primary evidence file, such as extracting the encrypted and encoded digital watermark from the audio, decoding and decrypting it to obtain the original watermark data, and determining the authenticity and legality of the original audio data based on the extracted data. An authentication report can then be generated and made public to relevant personnel, thus proving the authenticity and legality of the recording evidence. On the other hand, the secondary evidence file verifies the legality of the primary evidence file. For example, when the authenticity of the primary evidence document is questioned, such as if someone copies or tampers with it, the primary evidence document can be verified through secondary evidence documents to determine its authenticity and legality. For instance, the device holder can use a public key to decrypt the secondary evidence document and obtain the original watermark data. If someone copies or tampers with the data in the primary evidence document, the data parsed from the secondary evidence document can be compared with the corresponding data in the primary evidence document to determine its authenticity and legality. When there are multiple primary evidence documents, the accurate and authentic primary evidence document can be determined by identifying which one contains the original audio data, thereby improving the accuracy and legality of the primary evidence document and ultimately enhancing the legality and reliability of the recorded evidence.

[0108] Therefore, the aforementioned audio evidence generation and verification system 100 acquires the original audio data, processes the original audio data to embed a digital watermark into the original audio data, and obtains the target audio data; it generates a main evidence file and a secondary evidence file based on the target audio data, discloses the evidence based on the main evidence file, and verifies the legality of the main evidence file based on the secondary evidence file. Thus, the system can generate main evidence and secondary evidence based on audio data with embedded digital watermarks, disclose the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence; when the main evidence is questioned or may be forged or tampered with, the main evidence can be verified through the secondary evidence to determine whether the main evidence is legal, thereby improving the legality and reliability of the audio evidence.

[0109] In one embodiment of the present invention, before acquiring the original audio data from the recording device, the acquisition module 110 is further configured to: verify the legitimacy of the recording device; and acquire the original audio data after the verification is passed. Specifically, verifying the legitimacy of the recording device before acquiring the original audio data involves the distribution, production, and storage of the recording device legitimacy certificate, and can solve problems such as the initialization of the recording device legitimacy certificate; after the recording device legitimacy verification is passed, the original audio data is acquired, thereby improving the security, legitimacy, and reliability of the recording device, and further improving the security, authenticity, and reliability of the original audio data.

[0110] In one embodiment of the present invention, the process of obtaining the module 110 to verify the legitimacy of the recording device includes: verifying the recording device according to the device ID of the recording device, wherein the device ID is generated by the recording device based on the device certificate uniquely corresponding to the recording device.

[0111] In one embodiment of the invention, the device ID is configured as a 128-bit AES key stored in the OTP register of the recording device.

[0112] In one embodiment of the present invention, the recording device includes a secure storage unit, which is encrypted using an AES key. Data stored in the secure storage unit is accessible only on the recording device and only in a preset mode. The preset mode is, for example, a secure mode, where the data stored in the secure storage unit is accessible only on the recording device and only in a secure environment.

[0113] In one embodiment of the present invention, the recording device needs to be registered before use. Specifically, this includes: the recording device generating an evidence key in a secure environment, the evidence key comprising a private evidence key and a public evidence key; storing the private evidence key in a secure storage unit; generating a registration ID based on the public evidence key and storing it in the recording device; encrypting the public evidence key and the device ID with a device certificate and registering them with a certification authority so that the certification authority can verify the legality of the device certificate, and after confirming the legality of the device certificate, registering the device ID, registration ID, and public evidence key in a database, generating a registration receipt, and sending the registration receipt to the recording device; the recording device recording the received registration receipt in the database and deleting the public evidence key to complete the registration of the recording device.

[0114] In one embodiment of the present invention, after the recording device completes registration, if the recording device does not receive a registration receipt within a preset time, it shall re-register so that the certification authority resends the registration receipt until the recording device receives the registration receipt. Specifically, if the recording device does not receive a registration receipt within the specified time, the recording device may re-register, and the certification authority shall reissue the registration receipt until the recording device successfully receives the registration receipt.

[0115] In one embodiment of the present invention, after the recording device is registered, if the recording device is initialized, the previously recorded registration receipt is retained. When re-registering after initialization, the certification authority compares the retained registration receipt with the registration receipts in the database. If the current registration is confirmed to be valid, the registration ID corresponding to the one before initialization is marked as expired. Specifically, when the recording device is initialized, such as when the recording device is restored to factory settings, the previously recorded registration receipt is retained; that is, the previous registration receipt is not cleared. After initialization (such as after a factory reset), the user needs to repeat the registration process. During re-registration, the previous registration receipt is required. That is, the certification authority searches the database based on the retained previous registration receipt and compares it with the registration receipts in the database. If the current registration is confirmed to be valid, the registration ID corresponding to the one before initialization, i.e., the original registration ID, is marked as expired, but the record is still retained for subsequent authentication evidence.

[0116] In other words, the process of verifying the legality of the recording device in the embodiments of the present invention specifically involves the distribution, production, and storage of a legality certificate for the recording device. When the recording device records the original audio data, it can record the recording time and other related information of the recording device, and bind this information to prevent the recording device from being copied, tampered with, or forged. This can improve the security and legality of the recording device, and thus improve the security and reliability of the recording data.

[0117] In one embodiment of the present invention, the processing module 120 processes the original audio data, including: generating digital watermark information, the digital watermark information including recording time information corresponding to the original audio data; encrypting the digital watermark information according to the RSA key in the digital watermark information to obtain encrypted digital watermark information; encoding the encrypted digital watermark information to obtain a digital watermark; and embedding the digital watermark into the original audio data to obtain target audio data.

[0118] In one embodiment of the present invention, the process by which the processing module 120 embeds a digital watermark into the original audio data includes: performing frame-segmentation processing on the original audio data to extract a first audio synchronization reference point with a watermark; dividing the original audio data into multiple first synchronization units according to the first audio synchronization reference point; dividing each first synchronization unit into multiple first audio segments, and performing a fast Fourier transform on each first audio segment to obtain a corresponding first low-frequency spectrum; and embedding the digital watermark into the first low-frequency spectrum to obtain the target audio data.

[0119] In one embodiment of the present invention, the process of generating the master evidence file by the generation module 130 includes: calculating the data size of the target audio data and the corresponding first hash value; generating a globally unique identifier corresponding to the target audio data; filling the content of the target audio data into a preset first file data structure according to the data size of the target audio data, the first hash value and the globally unique identifier, wherein the first file data structure contains a first evidence header; signing the first evidence header with an RSA key, and saving it to obtain the master evidence file.

[0120] In one embodiment of the present invention, the process of generating a secondary evidence file by the generation module 130 includes: encrypting a digital watermark using an RSA key to obtain an encrypted digital watermark; calculating the data size of the encrypted digital watermark and its corresponding second hash value; obtaining a globally unique identifier; and filling the content of the encrypted digital watermark into a preset second file data structure based on the globally unique identifier, the data size of the encrypted digital watermark, and its corresponding second hash value, wherein the second file data structure includes a second evidence header; signing the second evidence header using an RSA key; and saving the signed document to obtain the secondary evidence file.

[0121] In one embodiment of the present invention, the process of the disclosure module 140 disclosing evidence based on the master evidence file includes: extracting a second audio synchronization reference point with a watermark from the master evidence file; dividing the audio in the master evidence file into multiple second synchronization units based on the second audio synchronization reference point; dividing each second synchronization unit into multiple second audio segments, and performing a fast Fourier transform on each second audio segment to obtain the corresponding second low-frequency spectrum; extracting a binary watermark from the second low-frequency spectrum, and decoding and decrypting the binary watermark using a public key corresponding to the RSA key to obtain the corresponding current watermark information; and comparing the current watermark information with the digital watermark information to determine whether the original audio data is legal.

[0122] In one embodiment of the present invention, the verification module 150 verifies the legality of the main evidence file based on the secondary evidence file, including: decrypting the secondary evidence file using the public key corresponding to the RSA key to obtain the second evidence header and digital watermark information; and comparing the second evidence header and digital watermark information with the main evidence file to determine whether the main evidence file is legal.

[0123] In specific embodiments, the audio evidence generation and verification system 100 can be applied to many fields and scenarios such as audio recording devices such as voice recorders, notary systems, and public security evidence collection systems.

[0124] It should be noted that the specific implementation of the audio recording evidence generation and verification system 100 in this embodiment of the invention is similar to the specific implementation of the audio recording evidence generation and verification method in this embodiment of the invention. For details, please refer to the description in the method section. To reduce redundancy, it will not be repeated here.

[0125] According to the audio recording evidence generation and verification system of the present invention, the system acquires original audio data, processes the original audio data to embed a digital watermark into the original audio data, and obtains target audio data; generates a main evidence file and a secondary evidence file based on the target audio data; discloses the evidence based on the main evidence file; and verifies the legality of the main evidence file based on the secondary evidence file. Thus, the system can generate main and secondary evidence based on audio data with embedded digital watermarks, disclose the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or tampered with, the secondary evidence can be used to verify the main evidence to determine its legality, thereby improving the legality and reliability of the audio recording evidence.

[0126] A further embodiment of the present invention provides an electronic device comprising the audio recording evidence generation and verification system described in any of the above embodiments of the present invention; or, the electronic device comprises: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the audio recording evidence generation and verification method as described in any of the above embodiments of the present invention.

[0127] In specific embodiments, the electronic device is, for example, a recording device or other electronic device capable of acquiring audio data. This electronic device can be applied in many fields and scenarios, such as notarization systems and public security evidence collection systems.

[0128] It should be noted that the specific implementation of the electronic device in this embodiment of the invention in generating and verifying audio evidence is similar to the specific implementation of the audio evidence generation and verification system or method in this embodiment of the invention. For details, please refer to the description in the device or method section. To reduce redundancy, it will not be repeated here.

[0129] According to an embodiment of the present invention, an electronic device acquires original audio data, processes the original audio data to embed a digital watermark into the original audio data, and obtains target audio data; generates a primary evidence file and a secondary evidence file based on the target audio data; discloses the evidence based on the primary evidence file; and verifies the legality of the primary evidence file based on the secondary evidence file. Thus, the electronic device can generate primary and secondary evidence based on audio data embedded with a digital watermark, disclose the evidence through the primary evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the primary evidence. When the primary evidence is questioned or may be forged or altered, the secondary evidence can be used to verify the primary evidence to determine its legality, thereby improving the legality and reliability of the recorded evidence.

[0130] Furthermore, other configurations and functions of the electronic devices according to the above embodiments of the present invention are known to those skilled in the art, and will not be described in detail to reduce redundancy.

[0131] A further embodiment of the present invention provides a computer-readable storage medium storing a program that, when executed by a processor, implements the method for generating and verifying audio evidence as described in any of the above embodiments of the present invention.

[0132] According to an embodiment of the present invention, a computer-readable storage medium storing a program thereon, when executed by a processor, can acquire original audio data, process the original audio data to embed a digital watermark into the original audio data, and obtain target audio data; generate a main evidence file and a secondary evidence file based on the target audio data; publicize the evidence based on the main evidence file; and verify the legality of the main evidence file based on the secondary evidence file. Thus, it is possible to generate main evidence and secondary evidence based on audio data with embedded digital watermarks, publicize the evidence through the main evidence, and verify the legality of the audio data through the digital watermark, thereby improving the reliability of the main evidence. When the main evidence is questioned or may be forged or tampered with, the main evidence can be verified through the secondary evidence to determine its legality, thereby improving the legality and reliability of the recorded evidence.

[0133] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0134] In the description of this invention, "a plurality of" means two or more.

[0135] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0136] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for generating and verifying audio recording evidence, characterized in that, For use in recording devices, the method for generating and verifying recorded evidence includes the following steps: Obtain raw audio data from the recording device; The original audio data is processed to embed a digital watermark into the original audio data to obtain the target audio data; Generate a primary evidence file and a secondary evidence file based on the target audio data; The evidence will be made public based on the aforementioned main evidence document; Verify the legality of the main evidence document based on the supplementary evidence document; The generation of the secondary evidence file includes: The digital watermark is encrypted using an RSA key to obtain the encrypted digital watermark; Calculate the data size of the encrypted digital watermark and its corresponding second hash value; Obtain a globally unique identifier. Based on the globally unique identifier, the data size of the encrypted digital watermark, and the corresponding second hash value, fill the content of the encrypted digital watermark into a preset second file data structure. The second file data structure includes a second evidence header, and the filled content includes the globally unique identifier, magic word, version, DUK, RUK, recording time information, the offset position of the encrypted digital watermark, the size of the encrypted digital watermark, the hash value of the encrypted digital watermark, reserved data, and evidence signature. The second evidence header is signed using an RSA key and then saved to obtain the secondary evidence file.

2. The method for generating and verifying audio evidence according to claim 1, characterized in that, Before acquiring the raw audio data from the recording device, the method further includes: The legality of the recording device shall be verified; After successful verification, the original audio data is obtained.

3. The method for generating and verifying audio recording evidence according to claim 2, characterized in that, The verification of the legality of the recording device includes: The recording device is verified based on its device ID, which is generated by the recording device based on a device certificate that uniquely corresponds to the recording device.

4. The method for generating and verifying audio recording evidence according to claim 3, characterized in that, The device ID is configured as a 128-bit AES key stored in the OTP register of the recording device.

5. The method for generating and verifying audio evidence according to claim 4, characterized in that, The recording device includes a secure storage unit, which is encrypted using the AES key. The data stored in the secure storage unit can only be accessed on the recording device and only in a preset mode.

6. The method for generating and verifying audio evidence according to claim 5, characterized in that, After verifying the legality of the recording device, the method further includes: The recording device generates an evidence key in a secure environment, the evidence key containing a private evidence key and a public evidence key; The private key for the evidence is stored in the secure storage unit; A registration ID is generated based on the evidence public key and stored in the recording device; The evidence public key and the device ID are encrypted with the device certificate and registered with the certification authority so that the certification authority can check the legality of the device certificate. After confirming the legality of the device certificate, the certification authority registers the device ID, registration ID and the evidence public key in the database, generates a registration receipt, and sends the registration receipt to the recording device. The recording device records the received registration receipt into the database and deletes the evidence public key to complete the registration of the recording device.

7. The method for generating and verifying audio recording evidence according to claim 6, characterized in that, Also includes: If the recording device does not receive the registration receipt within a preset time, it will re-register so that the certification authority can resend the registration receipt until the recording device receives the registration receipt.

8. The method for generating and verifying audio evidence according to claim 7, characterized in that, Also includes: When the recording device is initialized, the previously recorded registration receipt is retained; When re-registering after initialization, the certification authority compares the retained registration receipt with the registration receipt in the database. If the registration is confirmed to be valid, the corresponding registration ID before initialization is marked as expired.

9. The method for generating and verifying audio recording evidence according to claim 1, characterized in that, The processing of the original audio data includes: A digital watermark information is generated, the digital watermark information including the recording time information corresponding to the original audio data; The digital watermark information is encrypted using the RSA key in the digital watermark information to obtain the encrypted digital watermark information. The encrypted digital watermark information is encoded to obtain the digital watermark; The digital watermark is embedded into the original audio data to obtain the target audio data.

10. The method for generating and verifying audio recording evidence according to claim 9, characterized in that, The step of embedding the digital watermark into the original audio data includes: The original audio data is processed by frame segmentation to extract the first audio synchronization reference point with watermark; The original audio data is divided into multiple first synchronization units based on the first audio synchronization reference point; Each of the first synchronization units is divided into multiple first audio segments, and a fast Fourier transform is performed on each of the first audio segments to obtain the corresponding first low-frequency spectrum. The digital watermark is embedded into the first low-frequency spectrum to obtain the target audio data.

11. The method for generating and verifying audio recording evidence according to claim 9 or 10, characterized in that, The process of generating the master evidence file includes: Calculate the data size of the target audio data and the corresponding first hash value; Generate a globally unique identifier corresponding to the target audio data; Based on the data size of the target audio data, the first hash value, and the globally unique identifier, the content of the target audio data is filled into a preset first file data structure, wherein the first file data structure contains a first evidence header; The first evidence header is signed using the RSA key and then saved to obtain the master evidence file.

12. The method for generating and verifying audio recording evidence according to claim 11, characterized in that, The process of publicizing evidence based on the master evidence document includes: Extract the watermarked second audio synchronization reference point from the main evidence file; The audio in the main evidence file is divided into multiple second synchronization units based on the second audio synchronization reference point; Each second synchronization unit is divided into multiple second audio segments, and a fast Fourier transform is performed on each second audio segment to obtain the corresponding second low-frequency spectrum; Extract the binary watermark from the second low-frequency spectrum, and decode and decrypt the binary watermark using the public key corresponding to the RSA key to obtain the corresponding current watermark information; The current watermark information is compared with the digital watermark information to determine whether the original audio data is legitimate.

13. The method for generating and verifying audio recording evidence according to claim 12, characterized in that, The step of verifying the legality of the main evidence document based on the secondary evidence document includes: The secondary evidence file is decrypted using the public key corresponding to the RSA key to obtain the second evidence header and digital watermark information; The second evidence header and the digital watermark information are compared with the main evidence file to determine whether the main evidence file is legitimate.

14. A system for generating and verifying audio recording evidence, characterized in that, For recording devices, the system for generating and verifying recorded evidence includes: The acquisition module is used to acquire raw audio data from the recording device; The processing module is used to process the original audio data to embed the digital watermark into the original audio data to obtain the target audio data; The generation module is used to generate a main evidence file and a secondary evidence file based on the target audio data; The public disclosure module is used to publicly disclose evidence based on the main evidence file; The verification module is used to verify whether the main evidence file is legal based on the secondary evidence file; The generation module generates the secondary evidence file by including: The digital watermark is encrypted using an RSA key to obtain the encrypted digital watermark; Calculate the data size of the encrypted digital watermark and its corresponding second hash value; Obtain a globally unique identifier. Based on the globally unique identifier, the data size of the encrypted digital watermark, and the corresponding second hash value, fill the content of the encrypted digital watermark into a preset second file data structure. The second file data structure includes a second evidence header, and the filled content includes the globally unique identifier, magic word, version, DUK, RUK, recording time information, the offset position of the encrypted digital watermark, the size of the encrypted digital watermark, the hash value of the encrypted digital watermark, reserved data, and evidence signature. The second evidence header is signed using an RSA key and then saved to obtain the secondary evidence file.

15. An electronic device, characterized in that, include: The system for generating and verifying audio evidence as described in claim 14; or A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the method for generating and verifying audio evidence as described in any one of claims 1-13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method for generating and verifying audio evidence as described in any one of claims 1-13.

Images