Information identification method and system, vehicle, electronic device, and storage medium

Abstract

An information identification method, an information identification system, a vehicle capable of implementing the information identification method, an electronic device, and a computer-readable storage medium. The information identification method applied to a first device comprises: playing back target audio; acquiring a first ambient sound file which is collected by the first device and comprises the target audio; receiving a second ambient sound file, wherein the second ambient sound file is obtained by collecting a second ambient sound by a second device; and on the basis of the first ambient sound file and the second ambient sound file, determining whether to perform an unlocking operation. By adding similarity analysis for sound information in physical environments of two end devices, the method can improve the security of keyless entry and reduce the risk of attacks on automobiles, and complex hardware does not need to be added, so that the deployment cost is low.

Description

Information identification method, system, vehicle, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 27, 2023, with application number 202311603967.4 and invention name “Information Identification Method, System, Vehicle, Electronic Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of automotive technology, and in particular to an information identification method, system, vehicle, electronic device, and storage medium. Background Art

[0003] With the rapid development of the automotive industry, more intelligent functions and a better car experience are provided to users. Keyless entry systems allow users to easily unlock their vehicles without carrying physical keys, which is convenient and fast, improving the user experience.

[0004] In the prior art, in the keyless vehicle unlocking scenario, there is a possibility of attack. The attacker can illegally unlock the user's vehicle without the user's knowledge by simulating reasonable keyless unlocking conditions, thereby causing property loss.

[0005] Public content

[0006] In view of the above problems, embodiments of the present application provide an information identification method, system, vehicle, electronic device and storage medium that overcome the above problems or at least partially solve the above problems.

[0007] In a first aspect, an embodiment of the present application provides an information identification method, applied to a first device, comprising:

[0008] Play the target audio;

[0009] Obtaining a first ambient sound file including the target audio, collected by the first device;

[0010] receiving a second ambient sound file, where the second ambient sound file is obtained by collecting the second ambient sound by the second device; and

[0011] Determine whether to perform an unlocking operation according to the first ambient sound file and the second ambient sound file.

[0012] In a second aspect, an embodiment of the present application provides an information identification system, including:

[0013] a first device and a second device communicatively connected to the first device;

[0014] The first device is used to: play target audio and obtain a first ambient sound file including the target audio collected by the first device;

[0015] The second device is used to: collect the second ambient sound to generate a second ambient sound file;

[0016] The first device is further configured to receive the second ambient sound file, and determine whether to perform an unlocking operation based on the first ambient sound file and the second ambient sound file.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0018] memory for storing computer programs; and

[0019] The processor is configured to implement the steps of the information identification method described in the first aspect when executing the program stored in the memory.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the information identification method described in the first aspect above.

[0021] In a fifth aspect, an embodiment of the present application provides a vehicle, which includes the electronic device described in the third aspect above.

[0022] In an embodiment of the present application, after the first device plays the target audio, the first device collects the ambient sound to obtain a first ambient sound file including the target audio, and the second device collects the ambient sound to generate a second ambient sound file. The first device receives the second ambient sound file and determines whether to perform an unlocking operation based on the audio similarity between the first ambient sound file and the second ambient sound file. By analyzing the similarity of sound information in the physical environment of the two-end devices, it is possible to identify whether there is an attack, thereby improving the security of keyless entry and reducing the risk of the car being attacked, without adding complex hardware and with low deployment costs.

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments.

[0025] FIG1 is a schematic diagram showing an information identification method provided in an embodiment of the present application.

[0026] FIG2 shows a flowchart of similarity detection provided by an embodiment of the present application.

[0027] FIG3 shows an overall implementation flow chart of the information identification method provided in an embodiment of the present application.

[0028] FIG4 shows one of the schematic diagrams of the information identification system provided in an embodiment of the present application.

[0029] FIG5 shows a second schematic diagram of the information identification system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0032] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0033] At present, in order to realize the keyless entry function in the keyless entry scenario, the distance between the user's smart device and the vehicle can be detected. When the distance between the two meets the conditions, the vehicle is controlled to perform the unlocking action to realize keyless unlocking control of the vehicle. However, the keyless entry system that only measures the distance based on the received signal strength indication (RSSI) value cannot prevent broadcast relay attacks and poses a security risk. The broadcast relay attack is to deploy a relay device between the user's smart device and the vehicle to forward the communication data over a long distance, thereby simulating reasonable keyless unlocking conditions. The user's vehicle can be illegally unlocked without the user's knowledge, and the user may suffer property loss. In order to prevent the keyless entry function from being attacked by broadcast relays, the following enhanced keyless entry methods are currently commonly used:

[0034] 1. Verify signal strength and direction. This method improves security to a certain extent. However, after a relay attack, the signal strength and direction may be the same as the original signal, thus rendering the relay attack defense ineffective and posing a security issue.

[0035] 2. Obtain the Global Positioning System (GPS) location information of the smart terminal and the vehicle to calculate the distance between them and compare it with the distance calculated by calculating the RSSI value. This method improves security to a certain extent, but due to the addition of a GPS locator, it can only be used when both the vehicle and the smart terminal are connected to the network, making this solution less applicable.

[0036] 3. Add a manual gesture verification process; this method improves the security of the system to a certain extent, but it will reduce the convenience of using the solution and the user experience will be poor.

[0037] It can be seen that the existing processing methods for preventing broadcast relay attacks have problems such as insufficient security, insufficient applicability or reduced convenience.

[0038] To address the above issues, an embodiment of the present application provides an information recognition method that improves the security of the keyless entry system and reduces the risk of the car being attacked by increasing the similarity analysis of sound information in the physical environment of the vehicle and the smart terminal.

[0039] The following describes an information identification method provided in an embodiment of the present application. The method is applied to a first device, as shown in FIG1 , and includes the following steps:

[0040] Step 101: Play the target audio.

[0041] The first device of the embodiment of the present application is a vehicle, and a communication connection is established between the first device and the second device. The second device is a mobile smart device, including but not limited to a smart phone, a smart wearable product, and the smart wearable product can be a smart watch, a smart bracelet, etc. The communication between the first device and the second device can be network communication, Bluetooth communication, NFC (Near Field Communication, short-range wireless communication) communication, infrared communication, etc. By adopting Bluetooth communication, NFC communication or infrared communication, the interaction between the first device and the second device can be achieved without the need for a network environment, without being connected to the Internet, and is not affected by the environment, and has high applicability.

[0042] The first device adds sound information to its physical environment by playing target audio. The target audio can be pre-stored audio on the first device or generated by the first device before playback. The target audio must be played for a certain duration to avoid situations where it cannot be captured due to a short duration. The target audio must also be played at a volume greater than a set threshold to prevent it from being covered by other sounds.

[0043] Step 102: Obtain a first ambient sound file including the target audio collected by the first device.

[0044] After playing the target audio, the first device collects audio information from the environment in which it is located. Because the target audio needs to last for a certain period of time, the first device collects audio information from the current environment. Therefore, the collected audio information includes the target audio. Based on the collected audio information, the first device obtains a first ambient sound file that includes the target audio.

[0045] The target audio may correspond to a default duration, and the target audio may be any type of audio, which is not specifically limited here.

[0046] Step 103: Receive a second ambient sound file, where the second ambient sound file is obtained by collecting the second ambient sound by the second device.

[0047] After the first device plays the target audio, the second device communicating with the first device collects audio information of the environment in which it is located, obtains a second ambient sound, generates a second ambient sound file based on the second ambient sound, and the first device receives the second ambient sound file generated by the second device.

[0048] The first device may send a collection instruction to the second device to instruct it to collect the ambient sound, and the second device may collect the ambient sound based on the received collection instruction to obtain a second ambient sound file.

[0049] If the first device and the second device are within a reasonable communication distance, a relay attack cannot be carried out. At this time, the first device and the second device interact directly, and the first device directly receives the second ambient sound file sent by the second device. If the distance between the first device and the second device is far and there is a relay attack, the effective communication distance between the first device and the second device will be extended. At this time, the first device and the second device are not within a reasonable communication distance, and the second ambient sound file received by the first device is the forwarded second ambient sound file. For example, if the effective communication distance between the first device and the second device is 10 meters, and the distance between the first device and the second device is 100 meters and there is a relay attack, the first device and the second device are not within a reasonable communication distance, and the signal received by the first device is the signal forwarded by the relay device.

[0050] Step 104: Determine whether to perform an unlocking operation based on the first ambient sound file and the second ambient sound file.

[0051] After obtaining the first and second ambient sound files, the first device determines whether to perform an unlock operation based on the similarity between the first and second ambient sound files. If the unlock operation is determined to be necessary, the keyless unlock process continues, successfully unlocking the vehicle and enabling keyless entry. If the unlock operation is determined not to be necessary, the vehicle is determined to be under attack and the keyless unlock process is terminated.

[0052] In the above-mentioned implementation scheme of the present application, after the first device plays the target audio, the first device collects the ambient sound to obtain a first ambient sound file including the target audio, and the second device collects the ambient sound to generate a second ambient sound file. The first device receives the second ambient sound file and determines whether to perform an unlocking operation based on the audio similarity between the first ambient sound file and the second ambient sound file. By analyzing the similarity of the sound information in the physical environment of the two-end devices, it is possible to identify whether there is an attack, thereby improving the security of keyless entry and reducing the risk of the car being attacked, without adding complex hardware and with low deployment costs.

[0053] In an optional embodiment of the present application, when playing the target audio, the first device plays the target audio that is randomly generated and has a unique identifier.

[0054] The target audio played by the first device has a unique identifier and cannot be played repeatedly. The first device randomly generates the target audio before playing it. To prevent the target audio from being reused, the first device can delete the target audio after playing it. Since the target audio cannot be played repeatedly, the problem of replay attacks after being recorded can be avoided.

[0055] By playing unique target audio that is allowed to be played once, it is possible to avoid attacks such as replay after being recorded, thus ensuring the safety of the vehicle.

[0056] As another optional embodiment, before playing the target audio, the first device receives a first distance signal sent by the second device; calculates the distance between the first device and the second device based on the received signal strength indicator RSSI value corresponding to the first distance signal; when the calculated distance is less than or equal to the preset distance, plays the target audio; when the calculated distance is greater than the preset distance, receives a second distance signal sent by the second device; wherein the preset distance is the maximum distance for keyless unlocking.

[0057] The first device receives the first distance signal sent by the second device. For example, a Bluetooth connection is established between the first device and the second device, and the first device receives the first distance signal sent by the second device based on the Bluetooth connection.

[0058] Due to the deployment of relay devices, the first distance signal (such as a Bluetooth signal) received by the first device may not be sent directly by the second device, but may also be forwarded by a relay device. After receiving the first distance signal, the first device calculates the distance between itself and the second device based on the first distance signal.

[0059] Signal strength and distance have a linear relationship. The first device can calculate the distance based on the RSSI value corresponding to the first distance signal. If a relay device is present, the calculated distance is not the actual distance between the first and second devices. If no relay device is present, the first distance signal is sent directly by the second device, and the calculated distance is the actual distance between the first and second devices.

[0060] The first device cannot determine whether the first distance signal is sent directly by the second device. When the calculated distance is less than or equal to the preset distance (which meets the safety distance for keyless unlocking), it outputs the target audio to verify whether the keyless entry function has been attacked based on the target audio. When the calculated distance is greater than the preset distance, it can continue to receive the second distance signal sent by the second device.

[0061] The target audio can be randomly generated and played by the first device when the calculated distance is less than or equal to a preset distance. Alternatively, the target audio can be pre-generated, randomly generated, and non-repeating audio segments, with one segment randomly selected as the target audio. Playing the randomly generated audio as the target audio allows the use of unique, randomly generated audio as auxiliary distance determination information, preventing attacks that could be replayed after recording, and ensuring security.

[0062] Since the first distance signal can be sent by the second device or forwarded by the relay device, after the first device determines that the restriction conditions for keyless unlocking are met based on the first distance signal, it can continue to analyze the ambient audio to evaluate whether the distance obtained through the first distance signal is true and accurate, thereby identifying whether there is a relay attack.

[0063] When it is determined that the restriction condition of keyless unlocking is met based on the calculated distance, target audio is output, and the ambient sound of the first device and the second device is analyzed based on the target audio to verify whether the calculated distance is the actual distance between the first device and the second device, thereby identifying whether a relay attack exists.

[0064] The following describes a process of establishing communication between the first device and the second device by taking Bluetooth-based communication between the first device and the second device as an example.

[0065] The first device periodically sends a Bluetooth beacon message;

[0066] When receiving the authentication connection sent by the second device, security authentication is performed on the second device, and a Bluetooth communication connection is established with the second device after the security authentication passes.

[0067] The first device can periodically send out Bluetooth beacon messages and wait for the authentication connection of the second device. When the first device receives the authentication connection sent by the second device, it performs security authentication on the second device and establishes a Bluetooth communication connection with the second device after the security authentication is passed. After the Bluetooth communication connection is established, data interaction can be performed between the second device and the first device. In order to ensure that the Bluetooth communication is in a good state, the transmission power and antenna performance parameters of the Bluetooth modules of the first device and the second device can be adjusted. For the second device, it can perform security authentication on the first device and establish a Bluetooth communication connection between the two after the security authentication of the second device and the first device are both passed.

[0068] By performing security authentication on the first device and the second device, the reliability of the Bluetooth communication connection can be guaranteed; by adjusting parameters of the Bluetooth module, the communication status of the Bluetooth communication can be guaranteed.

[0069] The following describes the process of determining whether to perform an unlock operation based on the first ambient sound file and the second ambient sound file. When determining whether to perform an unlock operation based on the first ambient sound file and the second ambient sound file, the process includes:

[0070] When the similarity between the first ambient sound file and the second ambient sound file is greater than or equal to a preset threshold, determining to perform an unlocking operation;

[0071] When the similarity between the first ambient sound file and the second ambient sound file is less than the preset threshold, it is determined that an attack has occurred and the unlocking operation is not performed.

[0072] After obtaining the first and second ambient sound files, the system detects the similarity between the first and second ambient sound files and compares the similarity with a preset threshold. If the similarity is greater than or equal to the preset threshold, it indicates that the first and second devices are within a reasonable communication distance, and the first device can perform an unlock operation. If the similarity is less than the preset threshold, it can be determined that an attack has occurred, and the first device does not perform the unlock operation.

[0073] In the case where the second ambient sound file is the real ambient sound collected by the second device from the environment in which it is located,

[0074] If the similarity between the first ambient sound file and the second ambient sound file is less than a preset threshold, it can be determined that the first device and the second device are not within a reasonable communication distance, the first distance signal and the second ambient sound file received by the first device are forwarded by the relay device, and a relay attack exists in the keyless unlocking scenario, so the first device does not perform the unlocking operation.

[0075] For another situation, the target audio in the embodiment of the present application is unique and is allowed to be played once. When the distance between the first device and the second device is not within a reasonable communication distance, the first device plays audio 1. In this case, the second environmental sound file sent by the second device does not include audio 1, or the second environmental sound file sent by the second device includes audio 1, but because the two devices are in different environments, the other environmental sounds collected by the second device that are different from audio 1 are different from those of the first device. When the first device plays audio 2, the first device collects the first environmental sound file including audio 2, and the second device sends the second environmental sound file including audio 1 (obtained by recording audio 1). Since the second environmental sound file including audio 1 sent by the second device has a low similarity to the first environmental sound file including audio 2 collected by the first device, and the second environmental sound file including audio 1 sent by the second device has a high similarity to the first environmental sound file including audio 1 collected by the first device before (both include audio 1), it can be determined that a replay attack exists.

[0076] If it is determined that an attack has occurred by comparing the similarity with the preset threshold, the first device will disconnect the communication connection with the second device and terminate the keyless unlocking process to ensure the security of the unlocking; if it is determined that there is no attack by comparing the similarity with the preset threshold, the remaining keyless unlocking processes will continue to be executed until the vehicle is successfully unlocked, so as to ensure that the second device can achieve keyless unlocking when it is located near the first device.

[0077] It should be noted that when determining whether to perform the unlocking operation based on the first ambient sound file and the second ambient sound file, the similarity deviation of the first ambient sound file and the second ambient sound file can also be obtained. When the similarity deviation between the two is small, such as less than or equal to a set deviation threshold, it can be determined to perform the unlocking operation. Correspondingly, if the similarity deviation between the two is large, such as greater than a set deviation threshold, it can be determined not to perform the unlocking operation.

[0078] Among them, when judging the similarity between the first ambient sound file and the second ambient sound file, it is necessary to obtain the first voiceprint data corresponding to the first ambient sound file and the second voiceprint data corresponding to the second ambient sound file, and then judge whether the similarity between the first voiceprint data and the second voiceprint data is greater than or equal to the preset threshold.

[0079] When obtaining the first voiceprint data and the second voiceprint data, the first ambient sound file is divided into M audio intervals, and the second ambient sound file is divided into N audio intervals, where M and N are integers greater than or equal to 1 respectively; the eigenvalues ​​corresponding to each audio interval are determined respectively; the first voiceprint data is generated according to the M eigenvalues ​​corresponding to the M audio intervals, and the second voiceprint data is generated according to the N eigenvalues ​​corresponding to the N audio intervals.

[0080] When obtaining the first voiceprint data corresponding to the first ambient sound file, the first ambient sound file is divided into M audio regions. Since the value of M is greater than or equal to 1, at least one audio region corresponding to the first ambient sound file can be obtained through the region division. For each of the M audio regions, a feature value corresponding to each audio region is determined to obtain M feature values ​​corresponding to the first ambient sound file. The first voiceprint data corresponding to the first ambient sound file is then determined based on the M feature values.

[0081] When obtaining the second voiceprint data corresponding to the second ambient sound file, the second ambient sound file is divided into N audio regions. Since the value of N is greater than or equal to 1, at least one audio region corresponding to the second ambient sound file can be obtained through the region division. For each of the N audio regions, a feature value corresponding to each audio region is determined to obtain N feature values ​​corresponding to the second ambient sound file. The second voiceprint data corresponding to the second ambient sound file is then determined based on the N feature values.

[0082] Optionally, when determining the eigenvalues ​​corresponding to each audio interval, Fourier transform can be performed on the audio data corresponding to each audio interval to obtain frequency domain information; and the sound signal eigenvalue corresponding to the maximum frequency in the frequency domain information is set as the eigenvalue corresponding to the audio interval.

[0083] For each audio interval, when determining its corresponding eigenvalue, a Fourier transform is performed on the audio data corresponding to the audio interval to obtain the corresponding frequency domain information of the audio data. The horizontal axis of the frequency domain information corresponds to the frequency, and the vertical axis represents the sound eigenvalue corresponding to the frequency signal. After obtaining the frequency domain information based on the transform, the sound signal eigenvalue corresponding to the maximum frequency is set as the eigenvalue corresponding to the audio interval, thereby determining the eigenvalue corresponding to the audio interval based on the corresponding frequency domain information.

[0084] Optionally, when generating the first voiceprint data according to the M characteristic values ​​corresponding to the M audio intervals and generating the second voiceprint data according to the N characteristic values ​​corresponding to the N audio intervals, the method includes:

[0085] Arrange the M eigenvalues ​​corresponding to the M audio intervals in a preset order to obtain the first voiceprint data; arrange the N eigenvalues ​​corresponding to the N audio intervals in a preset order to obtain the second voiceprint data; the preset order is the time order, and the value of M is equal to N.

[0086] After obtaining the M characteristic values ​​corresponding to the first ambient sound file, the M characteristic values ​​corresponding to the first ambient sound file can be arranged according to the time arrangement order corresponding to the M audio intervals of the first ambient sound file to determine the first voiceprint data; after obtaining the N characteristic values ​​corresponding to the second ambient sound file, the N characteristic values ​​corresponding to the second ambient sound file can be arranged according to the time arrangement order corresponding to the N audio intervals of the second ambient sound file to determine the second voiceprint data.

[0087] In this embodiment, the durations corresponding to the first ambient sound file and the second ambient sound file can be the same. When dividing the audio intervals, the first ambient sound file and the second ambient sound file adopt the same division strategy, that is, the value of M is equal to N, the durations corresponding to the N audio intervals can be equal, or each audio interval corresponds to a duration, or other situations; the duration of each audio interval corresponding to the first ambient sound file corresponds one-to-one to the duration of each audio interval corresponding to the second ambient sound file, which can ensure that the voiceprint data is compared based on the same number of characteristic values.

[0088] When judging whether the similarity between the first voiceprint data and the second voiceprint data is greater than or equal to a preset threshold, the similarity comparison result is obtained based on at least one of the Euclidean distance, mutual correlation and cosine similarity of the first voiceprint data and the second voiceprint data; when the similarity comparison result indicates that the first voiceprint data and the second voiceprint data are similar, it is determined that the similarity between the first voiceprint data and the second voiceprint data is greater than or equal to the preset threshold.

[0089] After obtaining the first voiceprint data and the second voiceprint data, at least one of Euclidean distance, mutual correlation and cosine similarity can be calculated based on the first voiceprint data and the second voiceprint data, and a similarity comparison result can be obtained based on the calculation result.

[0090] Among them, the larger the Euclidean distance, the smaller the similarity, the larger the mutual correlation, the greater the similarity, and the larger the cosine similarity, the more similar; after determining the similarity comparison result based on at least one of the Euclidean distance, mutual correlation and cosine similarity, it can be determined whether the first voiceprint data and the second voiceprint data are similar. When the similarity comparison result indicates that the first voiceprint data and the second voiceprint data are similar, it is determined that the similarity between the two is greater than or equal to a preset threshold.

[0091] When the similarity comparison result includes two of the Euclidean distance, cross-correlation and cosine similarity, the first voiceprint data and the second voiceprint data can be determined to be similar when the two items respectively meet the corresponding conditions, such as when the Euclidean distance is less than a set distance value and the cosine similarity is greater than a set value, the first voiceprint data and the second voiceprint data are determined to be similar; when the similarity comparison result includes the Euclidean distance, cross-correlation and cosine similarity, the first voiceprint data and the second voiceprint data can be determined to be similar when at least two items respectively meet the corresponding conditions.

[0092] In the above implementation process, M eigenvalues ​​corresponding to the first ambient sound file and N eigenvalues ​​corresponding to the second ambient sound file are obtained by performing interval division. The first voiceprint data can be generated based on the M eigenvalues ​​and the second voiceprint data can be generated based on the N eigenvalues. The similarity between the first voiceprint data and the second voiceprint data is compared in at least one dimension, and the similarity between the first ambient sound file and the second ambient sound file can be determined based on the comparison result of at least one dimension.

[0093] The following describes a process of detecting the similarity between the first ambient sound file and the second ambient sound file through a specific implementation process, as shown in FIG2 , including:

[0094] Step 201: Divide the first ambient sound file collected by the first device into M audio intervals, and divide the second ambient sound file audio collected by the second device into N audio intervals, where M equals N.

[0095] Step 202: For each audio interval, perform Fourier transform on the audio data corresponding to the audio area to obtain frequency domain information, and set the sound signal eigenvalue corresponding to the maximum frequency in the frequency domain information as the eigenvalue corresponding to the audio interval.

[0096] Step 203: Arrange the M characteristic values ​​corresponding to the first ambient sound file in chronological order to obtain first voiceprint data; and arrange the N characteristic values ​​corresponding to the second ambient sound file in chronological order to obtain second voiceprint data.

[0097] Step 204: Obtain a similarity comparison result based on at least one of the Euclidean distance, the mutual correlation, and the cosine similarity between the first voiceprint data and the second voiceprint data.

[0098] The above process can better perform feature extraction by performing interval division; after obtaining the first voiceprint data and the second voiceprint data through feature extraction and feature value arrangement, similarity comparison is performed based on at least one of Euclidean distance, mutual correlation and cosine similarity, which can achieve similarity comparison in at least one dimension.

[0099] As an optional embodiment, after playing the target audio, the first device and the second device collect ambient sound in the same period of time to obtain a first ambient sound file and a second ambient sound file.

[0100] After playing the target audio, the first device collects ambient sound to obtain a first ambient sound file. Simultaneously, the second device collects ambient sound to obtain a second ambient sound file. Before collecting ambient sound, the first device may send a collection instruction to the second device, instructing both devices to collect ambient sound simultaneously, such that the first and second devices collect ambient sound at the same time after playing the target audio.

[0101] The collection instruction can carry a collection time to indicate when the second device should collect audio from the environment. The first device can send a collection instruction before playing the target audio so that the second device can collect audio from the environment immediately after the target audio is played. For the first device, the first device can also collect audio from the environment according to the collection instruction. Since both the first and second devices collect audio based on the collection instruction, it is guaranteed that the first and second ambient sound files corresponding to the same time period are obtained.

[0102] If the collection instruction only carries the collection time, the collection can be stopped after the default collection duration; the collection instruction can also carry the collection time and end time, or carry the collection time and collection duration to ensure that the first device and the second device collect ambient sound at the same time period.

[0103] The above describes various embodiments of the information identification method. The following describes the overall process of the information identification method through a specific example, as shown in FIG3 , including:

[0104] Step 301: A first device establishes a Bluetooth communication connection with a second device.

[0105] Step 302: The first device receives a Bluetooth signal and calculates a first distance between the first device and the second device based on an RSSI value corresponding to the Bluetooth signal.

[0106] Step 303 : The first device determines whether the first distance is less than or equal to the keyless unlocking safety distance. If so, execute step 304 ; otherwise, return to step 302 .

[0107] Step 304: The first device plays a randomly generated target audio that is unique and only allowed to be played once.

[0108] Step 305: The first device and the second device simultaneously collect audio of the surrounding environment to obtain a first ambient sound file and a second ambient sound file, and the first device receives the second ambient sound file.

[0109] Step 306 : The first device detects whether the similarity between the first ambient sound file and the second ambient sound file is greater than or equal to a preset threshold. If so, step 307 is executed; otherwise, step 308 is executed.

[0110] Step 307: Continue to execute the keyless unlocking process until the vehicle is successfully unlocked.

[0111] Step 308: Disconnect the Bluetooth communication connection with the second device and terminate the keyless unlocking.

[0112] The above implementation process can introduce environmental sound perception to strengthen the verification of whether the keyless entry function is subject to relay attacks, thereby preventing relay attacks to a large extent, and improving the security of keyless entry while maintaining ease of use; in the process of mutual authentication between the first device and the second device, a randomly generated and unique sound is selected as auxiliary distance judgment information, which can avoid replay attacks after being recorded and ensure system security.

[0113] The above is the overall implementation process of the information identification method provided in the embodiment of the present application. After the first device plays the target audio, the first device collects the ambient sound to obtain a first ambient sound file including the target audio. The second device collects the ambient sound to generate a second ambient sound file. The first device receives the second ambient sound file and determines whether to perform the unlocking operation based on the audio similarity between the first and second ambient sound files. By analyzing the similarity of the sound information in the physical environment of the two-end devices, it can identify whether there is an attack, thereby improving the security of keyless entry and reducing the risk of the car being attacked. This solution does not require the addition of complex hardware and has low deployment costs. In addition, this solution does not need to work in a networked state and has high applicability.

[0114] By obtaining the similarity between the first ambient sound file and the second ambient sound file, comparing the similarity with a preset threshold, and detecting whether the actual distance between the first device and the second device meets the unlocking condition based on the comparison, the accuracy and reliability of RSSI ranging can be evaluated by increasing the perception of ambient sound information, thereby reducing the risk of relay attacks on the keyless entry function; by playing a unique target audio that allows single playback, it can avoid attacks such as replay after recording and ensure security.

[0115] By performing interval division to obtain M eigenvalues ​​corresponding to the first ambient sound file and N eigenvalues ​​corresponding to the second ambient sound file, generating first voiceprint data based on the M eigenvalues ​​and generating second voiceprint data based on the N eigenvalues, and comparing the similarity of the first voiceprint data and the second voiceprint data in at least one dimension, it is possible to determine the similarity of the first ambient sound file and the second ambient sound file based on the comparison result of at least one dimension.

[0116] This embodiment of the present application provides an information identification system, as shown in FIG4 , including:

[0117] A first device 10 and a second device 20 communicatively connected to the first device 10;

[0118] The first device 10 is configured to: play the target audio and obtain a first ambient sound file including the target audio collected by the first device 10;

[0119] The second device 20 is used to collect the second ambient sound and generate a second ambient sound file;

[0120] The first device 10 is further configured to receive a second ambient sound file, and determine whether to perform an unlocking operation based on the first ambient sound file and the second ambient sound file.

[0121] The first device 10 adds sound information to the physical environment by playing the target audio. After playing the target audio, the first device 10 collects audio information from the environment and obtains a first ambient sound file that includes the target audio. After the first device 10 plays the target audio, the second device 20 in communication with the first device 10 collects audio information from the environment and obtains a second ambient sound. The second ambient sound file is generated based on the second ambient sound, and the first device 10 receives the second ambient sound file generated by the second device 20.

[0122] The first device 10 can send a collection instruction to the second device 20 to collect ambient sound. The second device 20 collects the ambient sound based on the received collection instruction and obtains a second ambient sound file. The first device 10 and the second device 20 collect ambient sound during the same time period to obtain audio information in different environments during the same time period.

[0123] After obtaining the first and second ambient sound files, the first device 10 determines whether to perform an unlocking operation based on the similarity between the first and second ambient sound files. If the unlocking operation is determined to be necessary, the keyless unlocking process continues, successfully unlocking the vehicle and enabling keyless entry. If the unlocking operation is determined not to be necessary, the vehicle is determined to be under attack and the keyless unlocking process is terminated.

[0124] The first device 10 is a vehicle, and the second device 20 is a mobile smart device, including but not limited to a smart phone and a smart wearable product. The smart wearable product may be a smart watch, a smart bracelet, etc.

[0125] Optionally, as shown in FIG5 , the first device 10 includes a first communication module 11 , a speaker 12 , a first microphone 13 , a judge 14 , and an electronic control unit ECU 15 ; the second device 20 includes a second communication module 21 and a second microphone 22 ;

[0126] The first communication module 11 establishes a connection with the second communication module 21 , the second communication module 21 is connected to the second microphone 22 , and the first communication module 11 , the speaker 12 , the first microphone 13 and the determiner 14 are respectively connected to the ECU 15 .

[0127] Among them, the speaker 12 is used to play the target audio that is randomly generated and uniquely identified; before the speaker 12 plays the target audio, the first communication module 11 receives the first distance signal sent by the second communication module 21, and calculates the distance between the first communication module 11 and the second device 20 based on the RSSI value corresponding to the first distance signal. When the calculated distance is less than or equal to the preset distance, the ECU 15 controls the speaker 12 to play the target audio. When the calculated distance is greater than the preset distance, the first communication module 11 continues to wait for receiving the second distance signal sent by the second communication module 21; the preset distance is the maximum distance for keyless unlocking.

[0128] The first communication module 11 and the second communication module 21 can be a Bluetooth module, a network module, an NCF module, or other types of communication modules. This embodiment is described using a Bluetooth module as an example. The first communication module 11 receives the first distance signal sent by the second communication module 21 and calculates the distance between the first device 10 and the second device 20 based on the RSSI value corresponding to the first distance signal. After obtaining the distance through calculation, it detects whether the calculated distance is less than or equal to the preset distance. If it is less than or equal to the preset distance, the ECU 15 is notified, and the ECU 15 controls the speaker 12 to play the target audio. If the calculated distance is greater than the preset distance, the system can continue to wait for the second distance signal sent by the second communication module 21.

[0129] After the speaker 12 plays the target audio, the ECU 15 controls the first microphone 13 to collect ambient sound and controls the first communication module 11 to send a collection instruction to the second communication module 21. The collection instruction can also be sent to the second communication module 21 before the target audio is played. The second communication module 21 sends the collection instruction to the second microphone 22, and the second microphone 22 collects the ambient sound based on the collection instruction. The collection instruction can carry the collection time and end time, or the collection time and collection duration, so that the second microphone 22 can collect audio of the corresponding duration of the environment after the target audio is played. It can also carry only the collection time, in which case the microphone collects ambient sound for the default duration.

[0130] It should be noted that when ECU15 controls the first microphone 13 to collect ambient sound, the first microphone 13 needs to obtain the collection time and collection duration; the collection time and end time of the ambient sound collected by the first microphone 13 are the same as the collection time and end time of the ambient sound collected by the second microphone 22, so it can be ensured that the first ambient sound file and the second ambient sound file corresponding to the same time period are obtained.

[0131] Optionally, after obtaining the second ambient sound file, the second microphone 22 sends it to the second communication module 21, the second communication module 21 sends it to the first communication module 11, and the first communication module 11 sends the second ambient sound file to the judge 14 through the ECU 15; after obtaining the first ambient sound file, the first microphone 13 sends it to the judge 14 through the ECU 15; at this point, the judge 14 obtains the first ambient sound file and the second ambient sound file.

[0132] After obtaining the first ambient sound file and the second ambient sound file, the judge 14 determines whether to perform the unlocking operation based on the similarity between the first ambient sound file and the second ambient sound file; if the similarity between the first ambient sound file and the second ambient sound file is greater than or equal to a preset threshold, the judge 14 notifies the ECU 15, and the ECU 15 performs the unlocking operation; if the similarity between the first ambient sound file and the second ambient sound file is less than the preset threshold, it is determined that an attack has occurred, and the ECU 15 does not perform the unlocking operation.

[0133] When determining whether the similarity between the first ambient sound file and the second ambient sound file is greater than or equal to a preset threshold, the determiner 14 determines whether the similarity between the first voiceprint data corresponding to the first ambient sound file and the second voiceprint data corresponding to the second ambient sound file is greater than or equal to the preset threshold.

[0134] That is, before the determiner 14 performs the determination, it is necessary to obtain the first voiceprint data and the second voiceprint data. When obtaining the voiceprint data, the determiner 14 is configured to divide the first ambient sound file into M audio intervals and the second ambient sound file into N audio intervals, where M and N are integers greater than or equal to 1, respectively, determine the feature value corresponding to each audio interval, and then generate the first voiceprint data based on the M feature values ​​corresponding to the M audio intervals and generate the second voiceprint data based on the N feature values ​​corresponding to the N audio intervals.

[0135] When determining the characteristic value corresponding to each audio interval, the judge 14 is used to: for each audio interval, perform Fourier transform on the audio data corresponding to the audio interval to obtain frequency domain information; and set the sound signal characteristic value corresponding to the maximum frequency in the frequency domain information as the characteristic value corresponding to the audio interval.

[0136] When generating the first voiceprint data according to the M characteristic values ​​corresponding to the M audio intervals and generating the second voiceprint data according to the N characteristic values ​​corresponding to the N audio intervals, the judge 14 is used to: arrange the M characteristic values ​​corresponding to the M audio intervals in a preset order to obtain the first voiceprint data; arrange the N characteristic values ​​corresponding to the N audio intervals in a preset order to obtain the second voiceprint data; wherein the preset order is the time order, and the value of M is equal to N.

[0137] The detailed process of obtaining the first voiceprint data and the second voiceprint data can be found in the introduction of the method side, which will not be elaborated here.

[0138] After obtaining the first voiceprint data and the second voiceprint data, the judge 14 obtains a similarity comparison result based on at least one of the Euclidean distance, mutual correlation and cosine similarity of the first voiceprint data and the second voiceprint data; when the similarity comparison result indicates that the first voiceprint data and the second voiceprint data are similar, it is determined that the similarity between the first voiceprint data and the second voiceprint data is greater than or equal to a preset threshold.

[0139] By comparing the similarity of the first voiceprint data and the second voiceprint data in at least one dimension, the similarity between the first ambient sound file and the second ambient sound file can be determined based on the comparison results in at least one dimension. The detailed process of performing the voiceprint data similarity comparison can be found in the description of the method side and will not be elaborated here.

[0140] The information recognition system provided in the embodiment of the present application strengthens the verification of whether the keyless entry function is subject to relay attacks by introducing ambient sound perception, which can prevent relay attacks to a large extent, and improve the security of keyless entry while maintaining ease of use; in the process of mutual authentication between the first device and the second device, a randomly generated and unique sound is selected as auxiliary distance judgment information, which can avoid replay attacks after being recorded and ensure system security; and the system only needs to add an ambient sound sensor, with low deployment cost, and does not need to work in an Internet state, and has high applicability.

[0141] As for the above-mentioned information identification system embodiment, since it is basically similar to the information identification method embodiment, the relevant parts can be referred to the partial description of the method embodiment.

[0142] An embodiment of the present application also provides an electronic device, including a processor and a memory, wherein the processor and the memory communicate with each other via a communication bus. The memory is used to store computer programs. When the processor is used to execute the program stored in the memory, the following steps are implemented: playing target audio; obtaining a first ambient sound file including the target audio collected by the first device; receiving a second ambient sound file, wherein the second ambient sound file is obtained by collecting the second ambient sound by the second device; determining whether to perform an unlocking operation based on the first ambient sound file and the second ambient sound file. The processor can also implement other steps in the above-mentioned information recognition method, which will not be repeated here.

[0143] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0144] The communication interface is used for communication between the above terminal and other devices.

[0145] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0146] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0147] In another embodiment provided by the present application, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the information identification method described in the above embodiment.

[0148] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the information identification method described in the above embodiment.

[0149] An embodiment of the present application also provides a vehicle, comprising the above-mentioned electronic device.

[0150] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0151] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0152] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0153] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the scope of protection of the present application.

Claims

1. An information identification method, applied to a first device, characterized in that: include: Play the target audio; Acquire a first ambient sound file including the target audio collected by the first device; receiving a second ambient sound file, where the second ambient sound file is obtained by collecting the second ambient sound by the second device; and Determine whether to perform an unlocking operation according to the first ambient sound file and the second ambient sound file.

2. The method according to claim 1, characterized in that The playing target audio includes: Play the target audio that is randomly generated and has a unique identifier.

3. The method according to claim 1 or 2, characterized in that: Before playing the target audio, the method further includes: Receive a first distance signal sent by the second device.

4. The method according to claim 3, characterized in that Also includes: Calculating the distance between the second device and the first distance signal according to the received signal strength indicator RSSI value corresponding to the first distance signal; When the calculated distance is less than or equal to the preset distance, playing the target audio; as well as When the calculated distance is greater than the preset distance, receiving a second distance signal sent by the second device; The preset distance is the maximum distance for keyless unlocking.

5. The method according to any one of claims 1 to 4, characterized in that: The determining whether to perform an unlocking operation according to the first ambient sound file and the second ambient sound file includes: If the similarity between the first ambient sound file and the second ambient sound file is greater than or equal to a preset threshold, determining to perform an unlocking operation; and When the similarity between the first ambient sound file and the second ambient sound file is less than the preset threshold, it is determined that an attack exists and the unlocking operation is not performed.

6. The method according to claim 5, characterized in that The method further comprises: It is determined whether the similarity between the first voiceprint data corresponding to the first ambient sound file and the second voiceprint data corresponding to the second ambient sound file is greater than or equal to the preset threshold.

7. The method according to claim 6, characterized in that The determining whether the similarity between the first voiceprint data corresponding to the first ambient sound file and the second voiceprint data corresponding to the second ambient sound file is greater than or equal to the preset threshold comprises: acquiring a similarity comparison result based on at least one of the Euclidean distance, the mutual correlation and the cosine similarity of the first voiceprint data and the second voiceprint data; and When the similarity comparison result indicates that the first voiceprint data and the second voiceprint data are similar, it is determined that the similarity between the first voiceprint data and the second voiceprint data is greater than or equal to the preset threshold.

8. The method according to claim 7, characterized in that The method further comprises: Divide the first ambient sound file into M audio intervals, and divide the second ambient sound file into N audio intervals, where M and N are integers greater than or equal to 1; Determine the eigenvalue corresponding to each audio interval respectively; and The first voiceprint data is generated according to the M characteristic values ​​corresponding to the M audio intervals, and the second voiceprint data is generated according to the N characteristic values ​​corresponding to the N audio intervals.

9. The method according to claim 8, characterized in that The step of respectively determining the characteristic value corresponding to each audio interval includes: For each audio interval, performing Fourier transform on the audio data corresponding to the audio interval to obtain frequency domain information; and The sound signal characteristic value corresponding to the maximum frequency in the frequency domain information is set as the characteristic value corresponding to the audio interval.

10. The method according to claim 8 or 9, characterized in that: The generating the first voiceprint data according to the M characteristic values ​​corresponding to the M audio intervals and the generating the second voiceprint data according to the N characteristic values ​​corresponding to the N audio intervals include: Arrange the M characteristic values ​​corresponding to the M audio intervals in a preset order to obtain the first voiceprint data; and Arrange the N characteristic values ​​corresponding to the N audio intervals in a preset order to obtain the second voiceprint data; The preset order is a time order, and the value of M is equal to N.

11. The method according to any one of claims 1 to 10, characterized in that: After playing the target audio, the first device and the second device collect ambient sound in the same period of time to obtain the first ambient sound file and the second ambient sound file.

12. The method according to any one of claims 1 to 10, characterized in that: The first device is a vehicle, and the second device is at least one of a mobile phone and a smart wearable product.

13. An information recognition system, characterized in that: include: A first device (10) and a second device (20) communicatively connected to the first device; The first device is used to: play target audio, and obtain a first ambient sound file including the target audio collected by the first device; The second device is used to: collect the second ambient sound to generate a second ambient sound file; The first device is further used to: receive the second ambient sound file, and determine whether to perform an unlocking operation according to the first ambient sound file and the second ambient sound file.

14. An electronic device, characterized in that: include: Memory, used to store computer programs; as well as A processor, for implementing the steps of the information identification method as claimed in any one of claims 1 to 12 when executing a program stored in a memory.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the information identification method according to any one of claims 1 to 12 are implemented.

16. A vehicle, characterized in that: The vehicle includes the electronic device as claimed in claim 14.

Images