Intelligent Testing Method Based on Chip Algorithm and Drone Interface

Abstract

The present application discloses an intelligent testing method based on a chip algorithm and a drone interface, including: in response to a testing request, encrypting interface data obtained from the interface of a chip under test using a pre-configured chip algorithm to obtain encrypted data; sending the encrypted data to a testing device for the testing device to perform intelligent testing; the chip algorithm is configured to: extract a first feature matrix from the interface data; reconstruct the time-domain information in the first feature matrix to form a second feature matrix; decompose the second feature matrix to obtain K third feature matrices; map the reconstructed information in each third feature matrix to the time domain to form a fourth feature matrix; determine the encrypted data based on the K fourth feature matrices, which can encrypt the interface data of the chip under test to improve the security of data transmission between the drone and the testing device, thereby achieving accurate testing of the drone interface and ensuring the stability and reliability of the drone system.

Description

Technical Field

[0001] This application relates to the field of testing technologies, and particularly to an intelligent testing method based on a chip algorithm and a drone interface. Background Art

[0002] With the increase in the endurance of drones, the flight time of drones in the air is getting longer. During the long-term flight of drones, it is necessary to conduct interface tests on them. Otherwise, when the interfaces of drones malfunction, it is likely to affect the normal operation of drones and pose potential safety hazards.

[0003] However, due to the limitations in volume and weight, it is difficult to configure high-computing-power chips in drones to provide services for testing. Interface data can be transmitted to test equipment on the ground for testing to obtain more accurate and reliable test results. However, during the data transmission process, if the transmitted data is intercepted and successfully parsed, it is very easy to affect the data security of drones. Moreover, the interceptor can generate fake data based on the parsed data to provide to the test equipment to deceive the test equipment, resulting in the inability to adjust the operation of drones in a timely manner. Summary of the Invention

[0004] To solve the above technical problems, an embodiment of this application proposes an intelligent testing method based on a chip algorithm and a drone interface.

[0005] An embodiment of this application provides an intelligent testing method based on a chip algorithm and a drone interface. The drone to be tested has a main control chip and a chip to be tested. The method is executed by the main control chip and includes:

[0006] In response to a test request, use a pre-configured chip algorithm to encrypt the interface data obtained from the interface of the chip to be tested to obtain encrypted data;

[0007] Send the encrypted data to the test equipment for the test equipment to perform intelligent testing;

[0008] Wherein, the chip algorithm is configured to:

[0009] Extract a first feature matrix from the interface data;

[0010] Reconstruct the time-domain information in the first feature matrix to form a second feature matrix;

[0011] Decompose the second feature matrix to obtain K third feature matrices, where K is greater than 1;

[0012] Map the information reconstructed in each third feature matrix to the time domain to form a corresponding fourth feature matrix;

[0013] Determine the encrypted data based on K fourth feature matrices.

[0014] Optionally, the reconstructing the time-domain information in the first feature matrix to form a second feature matrix includes:

[0015] Add noise to the time-domain information in the first feature matrix to obtain a fifth feature matrix;

[0016] Map the time-domain information with added noise in the fifth feature matrix to the frequency domain to form a second feature matrix.

[0017] Optionally, the construction method of the noise includes:

[0018] Determine a preset first noise seed;

[0019] Generate a second noise seed based on the time-domain information in the first feature matrix and the first noise seed;

[0020] Perform vector quantization mapping on the second noise seed to construct the noise.

[0021] Optionally, the first noise seed is noise data in the time domain, and the generating a second noise seed based on the time-domain information in the first feature matrix and the first noise seed includes:

[0022] Perform transformation processing on the time-domain information in the first feature matrix to obtain a time-domain latent space feature vector;

[0023] Perform the transformation processing on the first noise seed to obtain a noise latent space feature vector;

[0024] Obtain the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector.

[0025] Optionally, the time-domain latent space feature vector has M elements, the noise latent space feature vector has N elements, both N and M are positive integers, and N < M. The obtaining the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector includes:

[0026] Replace N elements at specified positions in the M elements of the time-domain latent space feature vector with the N elements of the noise latent space feature vector;

[0027] Perform an inverse transformation matching the transformation processing on the time-domain latent space feature vector after replacement to obtain the second noise seed.

[0028] Optionally, the transformation process is implemented by any of the following:

[0029] Autoencoder;

[0030] Variational autoencoder;

[0031] Wavelet transform.

[0032] Optionally, sending the encrypted data to the test device includes:

[0033] Sending a connection request to the test device, where the connection request is used to request the establishment of a dedicated data channel between the main control chip and the test device, and the dedicated data channel is configured for the main control chip to unidirectionally transmit data to the test device;

[0034] Determining that the dedicated data channel is successfully established, and sending the encrypted data to the test device via the dedicated data channel.

[0035] Optionally, the encrypted data is the K fourth feature matrices, and the bandwidth of the dedicated data channel is determined by the data volume of the fourth feature matrix with the largest data volume among the K fourth feature matrices. Sending the encrypted data to the test device via the dedicated data channel includes:

[0036] Sending the K fourth feature matrices to the test device one by one via the dedicated data channel.

[0037] Optionally, extracting the first feature matrix from the interface data includes:

[0038] Preprocessing the interface data;

[0039] Parsing the timestamp in the preprocessed interface data;

[0040] Extracting the first feature matrix from the preprocessed interface data based on the timestamp.

[0041] Optionally, extracting the first feature matrix from the preprocessed interface data based on the timestamp includes:

[0042] Dividing the preprocessed interface data into multiple time window data according to the timestamp at set time intervals;

[0043] Determining the data features corresponding to each time window data;

[0044] Taking the data features corresponding to the multiple time window data as the respective elements in the first feature matrix to construct the first feature matrix.

[0045] In summary, the embodiments of the present application have at least the following beneficial effects:

[0046] By adopting the embodiments of the present application, in response to a test request, the interface data obtained from the interface of the chip under test is encrypted by using a pre-configured chip algorithm to obtain encrypted data; the encrypted data is sent to a test device for the test device to perform intelligent testing; wherein, the chip algorithm is configured to: extract a first feature matrix from the interface data; reconstruct the time-domain information in the first feature matrix to form a second feature matrix; decompose the second feature matrix to obtain K third feature matrices, where K is greater than 1; map the information reconstructed in each third feature matrix to the time domain to form a corresponding fourth feature matrix; based on the K fourth feature matrices, determine the encrypted data, which can encrypt the interface data of the chip under test to improve the security of data transmission between the unmanned aerial vehicle and the test device, and further achieve accurate testing of the unmanned aerial vehicle interface, ensuring the stability and reliability of the unmanned aerial vehicle system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic flowchart of an intelligent testing method based on a chip algorithm and an unmanned aerial vehicle interface provided by an embodiment of the present application;

[0048] Figure 2 is a schematic flowchart of a chip algorithm provided by an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of an intelligent testing device based on a chip algorithm and an unmanned aerial vehicle interface provided by an embodiment of the present application;

[0050] Figure 4 is a schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present application belong to the protection scope of the present application.

[0052] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more. In the description of the present application, the term "comprising" and its variants are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially according to". The term "an embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments".

[0053] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0054] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present application have the same meanings as those commonly understood by those skilled in the technical field to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0055] See Figure 1 , which shows a schematic flowchart of an intelligent test method based on a chip algorithm and a drone interface provided by an embodiment of the present application. The drone to be tested has a main control chip and a chip to be tested. The method is executed by the main control chip and the method includes steps S101 - S102, specifically as follows:

[0056] S101, in response to a test request, use a pre-configured chip algorithm to encrypt the interface data obtained from the interface of the chip to be tested, and obtain encrypted data;

[0057] It should be noted that the test request in this embodiment may be a request initiated by the main control chip when it detects an abnormality in the interface data of the chip to be tested obtained, or a request periodically sent by the test device to the main control chip.

[0058] S102. Send the encrypted data to the test device for the test device to perform intelligent testing;

[0059] In one example, the intelligent testing may refer to the process of using artificial intelligence and machine learning technologies to automate and optimize testing. This testing method aims to improve the efficiency, accuracy, and coverage of testing while reducing manual intervention and errors. For example, a trained interface test model can be pre-deployed in the test device. The interface test model can be trained using a general model training method based on historical test data. In this embodiment, the encrypted data sent to the test device can, on the one hand, be decrypted by the test device using a decryption algorithm, and the decrypted data can be input into the interface test model for testing; on the other hand, the interface test model can be correspondingly configured so that the interface test model first decrypts the encrypted data using the decryption algorithm and then performs testing based on the decrypted data. Among them, the decryption algorithm can be an algorithm that matches the chip algorithm, for example, it can be the inverse operation processing of the chip algorithm.

[0060] Among them, referring to Figure 2 , a schematic flowchart of the chip algorithm provided by the embodiment of the present application is shown. The chip algorithm is configured to include steps S201 - S205:

[0061] S201. Extract a first feature matrix from the interface data;

[0062] In one example, step S201 may include: dividing the interface data into blocks, calculating the eigenvalue of each divided data block, and constructing a first feature matrix based on all eigenvalues.

[0063] S202. Reconstruct the time-domain information in the first feature matrix to form a second feature matrix;

[0064] In one example, step S202 may include: converting the time-domain information in the first feature matrix to a target domain to form a second feature matrix, where the target domain is not the time domain and may include the frequency domain. When the target domain is the frequency domain, the time-domain information in the first feature matrix can be converted to the frequency domain through Fourier transform.

[0065] S203. Decompose the second feature matrix to obtain K third feature matrices, where K > 1;

[0066] In one example, step S203 may include: decomposing the second feature matrix into K third feature matrices, where the dimension of each third feature matrix is equal to that of the second feature matrix, and each third feature matrix has a part of the data in the second feature matrix, and this part of the data can be represented by the element values at the corresponding positions in the second feature matrix.

[0067] S204, mapping the information reconstructed in each third feature matrix to the time domain to form a corresponding fourth feature matrix;

[0068] In one example, the information reconstructed can be mapped to the time domain in a manner corresponding to the reconstruction. For example, when the reconstruction is to convert the time-domain information in the first feature matrix to the frequency domain through Fourier transform, the information reconstructed refers to the frequency-domain information converted from the time-domain information in the first feature matrix in the third feature matrix. At this time, the manner corresponding to the reconstruction can be inverse Fourier transform.

[0069] It should be noted that there may be information reconstructed in any of the third feature matrices in this embodiment. For the third feature matrix without the reconstructed information, it is not mapped, and the third feature matrix is directly used as the corresponding fourth feature matrix.

[0070] S205, determining the encrypted data based on the K fourth feature matrices.

[0071] In one example, step S205 may include: directly forming the encrypted data from the K fourth feature matrices.

[0072] In an alternative embodiment, the reconstructing the time-domain information in the first feature matrix to form a second feature matrix includes:

[0073] Adding noise to the time-domain information in the first feature matrix to obtain a fifth feature matrix;

[0074] Mapping the time-domain information with the added noise in the fifth feature matrix to the frequency domain to form a second feature matrix.

[0075] In one example, the added noise can be preset time-domain noise, which is respectively pre-stored in the unmanned aerial vehicle and the test equipment, so that it can be used for encryption in the unmanned aerial vehicle and for decryption in the test equipment.

[0076] In one example, the time-domain information with the added noise in the fifth feature matrix can be mapped to the frequency domain through Fourier transform.

[0077] In an alternative embodiment, the construction method of the noise includes:

[0078] Determine a preset first noise seed;

[0079] Generate a second noise seed based on the time-domain information in the first feature matrix and the first noise seed;

[0080] Perform vector quantization mapping on the second noise seed to construct the noise.

[0081] It should be noted that the vector quantization mapping in this embodiment is a data compression and feature extraction technology. Vector quantization realizes data compression and feature extraction by mapping high-dimensional data to a low-dimensional discrete space (codebook), making the data volume of the noise smaller for subsequent data transmission.

[0082] In one example, the preset first noise seed may be the preset time-domain noise in the above embodiment. Thus, in this embodiment, by further processing the preset time-domain noise, the finally generated noise can carry both the information of the preset time-domain noise and the time-domain information in the first feature matrix, improving the security of encryption.

[0083] In an alternative implementation, the first noise seed is noise data in the time domain. The generating of the second noise seed based on the time-domain information in the first feature matrix and the first noise seed includes:

[0084] Perform transformation processing on the time-domain information in the first feature matrix to obtain a time-domain latent space feature vector;

[0085] Perform the transformation processing on the first noise seed to obtain a noise latent space feature vector;

[0086] Obtain the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector.

[0087] It should be noted that the latent space generally refers to a low-dimensional, abstract representation space, where each point corresponds to a latent representation of the original data. Since the latent space usually has a lower dimension than the original data space, it helps to reduce the complexity of the data. And by mapping high-dimensional data to the latent space, the high-level features and internal structure of the data can be captured. Applying it to this embodiment can obtain low-dimensional latent space feature vectors, making the data volume of the second noise seed smaller, and further making the data volume of the noise smaller for subsequent data transmission.

[0088] In an alternative embodiment, the time-domain latent space feature vector has M elements, and the noise latent space feature vector has N elements, where both N and M are positive integers and N < M. Obtaining the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector includes:

[0089] Replacing N elements at specified positions among the M elements of the time-domain latent space feature vector with the N elements of the noise latent space feature vector;

[0090] Performing an inverse transformation matching the transformation process on the time-domain latent space feature vector after replacement to obtain the second noise seed.

[0091] It should be noted that among the N elements at the specified positions among the M elements of the time-domain latent space feature vector in this embodiment, the specified positions can be several positions respectively pre-configured in both the unmanned aerial vehicle and the test equipment for the encryption and decryption of both parties. Among them, one position can correspond to at least one of the N elements of the noise latent space feature vector, and each position is used to integrate the information possessed by the respective elements corresponding to it.

[0092] In an alternative embodiment, the transformation process is implemented by any one of the following:

[0093] Autoencoder;

[0094] Variational autoencoder;

[0095] Wavelet transform.

[0096] In an example, the simplified autoencoder and the simplified variational autoencoder are both simplified encoder networks. Since only encryption (i.e., the encoding process) needs to be implemented on the unmanned aerial vehicle side, the decoder networks contained in the autoencoder and the variational autoencoder can be removed respectively, and the encoder networks corresponding to the autoencoder and the variational autoencoder are pruned respectively, so that the pruned encoder networks are simplified encoder networks, which are convenient for running by the low-computing-power main control chip of the unmanned aerial vehicle.

[0097] In an alternative embodiment, sending the encrypted data to the test equipment includes:

[0098] Sending a connection request to the test equipment, where the connection request is used to request to establish a dedicated data channel between the main control chip and the test equipment, and the dedicated data channel is configured for the main control chip to unidirectionally transmit data to the test equipment;

[0099] Determining that the dedicated data channel is successfully established, and sending the encrypted data to the test equipment via the dedicated data channel.

[0100] In this embodiment, by establishing a dedicated data channel, it is possible to prevent an interceptor from transmitting forged data to the test device for deception. In addition, since the dedicated data channel can only be used for the main control chip to unidirectionally transmit data to the test device, there is no need to worry about other personnel using the data transmission process of the data used for testing to send control signals to the unmanned aerial vehicle to hijack the unmanned aerial vehicle.

[0101] In an alternative embodiment, the encrypted data is the K fourth feature matrices, and the bandwidth of the dedicated data channel is determined by the data volume of the fourth feature matrix with the largest data volume among the K fourth feature matrices. Sending the encrypted data to the test device via the dedicated data channel includes:

[0102] Via the dedicated data channel, the K fourth feature matrices are sent to the test device one by one.

[0103] In an example, the bandwidth of the dedicated data channel can be configured according to the data volume of the fourth feature matrix with the largest data volume, so that the dedicated data channel can transmit the fourth feature matrix with the largest data volume to the test device within a set time. In this embodiment, a dedicated data channel with a smaller bandwidth can be used to transmit each of the fourth feature matrices to the test device one by one, so as to reduce the impact of the test on the normal operation of the unmanned aerial vehicle.

[0104] In an alternative embodiment, extracting the first feature matrix from the interface data includes:

[0105] Preprocessing the interface data;

[0106] Parsing the time stamp in the preprocessed interface data;

[0107] Based on the time stamp, extracting the first feature matrix from the preprocessed interface data.

[0108] In an alternative embodiment, the extracting the first feature matrix from the preprocessed interface data based on the time stamp includes:

[0109] Dividing the preprocessed interface data into multiple time window data according to the time stamp at set time intervals;

[0110] Determining the data characteristics corresponding to each time window data;

[0111] Taking the data characteristics corresponding to the multiple time window data as the respective elements in the first feature matrix to construct the first feature matrix.

[0112] It should be noted that the set time interval in this embodiment can be pre-configured separately in both the drone and the test equipment to facilitate encryption / decryption between the two parties.

[0113] Correspondingly, an embodiment of the present application further provides an intelligent test device based on a chip algorithm and a drone interface, which can implement all processes of the intelligent test method based on the chip algorithm and the drone interface provided in the above embodiment.

[0114] See Figure 3 , which shows a schematic structural diagram of the intelligent test device based on the chip algorithm and the drone interface provided in the embodiment of the present application. The drone to be tested has a main control chip and a chip to be tested. The intelligent test device based on the chip algorithm and the drone interface is deployed on the main control chip. The device includes:

[0115] An encryption module 301, configured to, in response to a test request, use a pre-configured chip algorithm to encrypt the interface data obtained from the interface of the chip to be tested to obtain encrypted data;

[0116] A data sending module 302, configured to send the encrypted data to a test device for the test device to perform intelligent testing;

[0117] Among them, the chip algorithm is configured as:

[0118] Extract a first feature matrix from the interface data;

[0119] Reconstruct the time-domain information in the first feature matrix to form a second feature matrix;

[0120] Decompose the second feature matrix to obtain K third feature matrices, where K is greater than 1;

[0121] Map the information reconstructed in each third feature matrix to the time domain to form a corresponding fourth feature matrix;

[0122] Determine the encrypted data based on the K fourth feature matrices.

[0123] In an alternative embodiment, the reconstructing the time-domain information in the first feature matrix to form a second feature matrix includes:

[0124] Add noise to the time-domain information in the first feature matrix to obtain a fifth feature matrix;

[0125] Map the time-domain information with the added noise in the fifth feature matrix to the frequency domain to form a second feature matrix.

[0126] In an alternative embodiment, the construction method of the noise includes:

[0127] Determine a preset first noise seed;

[0128] Generate a second noise seed based on the time-domain information in the first feature matrix and the first noise seed;

[0129] Perform vector quantization mapping on the second noise seed to construct the noise.

[0130] In an alternative embodiment, the first noise seed is noise data in the time domain, and the generating the second noise seed based on the time-domain information in the first feature matrix and the first noise seed includes:

[0131] Perform a transformation process on the time-domain information in the first feature matrix to obtain a time-domain latent space feature vector;

[0132] Perform the transformation process on the first noise seed to obtain a noise latent space feature vector;

[0133] Obtain the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector.

[0134] In an alternative embodiment, the time-domain latent space feature vector has M elements, the noise latent space feature vector has N elements, both N and M are positive integers, and N < M. The obtaining the second noise seed based on the time-domain latent space feature vector and the noise latent space feature vector includes:

[0135] Replace N elements at specified positions in the M elements of the time-domain latent space feature vector with the N elements of the noise latent space feature vector;

[0136] Perform an inverse transformation matching the transformation process on the time-domain latent space feature vector after replacement to obtain the second noise seed.

[0137] In an alternative embodiment, the transformation process is implemented by any one of the following:

[0138] Autoencoder;

[0139] Variational autoencoder;

[0140] Wavelet transform.

[0141] In an alternative embodiment, the sending the encrypted data to the test device includes:

[0142] Send a connection request to the test device, where the connection request is used to request the establishment of a dedicated data channel between the main control chip and the test device, and the dedicated data channel is configured to unidirectionally transmit data from the main control chip to the test device;

[0143] Determine that the dedicated data channel is successfully established, and send the encrypted data to the test device via the dedicated data channel.

[0144] In an alternative embodiment, the encrypted data is the K fourth feature matrices, and the bandwidth of the dedicated data channel is determined by the data volume of the fourth feature matrix with the largest data volume among the K fourth feature matrices. Sending the encrypted data to the test device via the dedicated data channel includes:

[0145] Via the dedicated data channel, send the K fourth feature matrices to the test device one by one.

[0146] In an alternative embodiment, extracting the first feature matrix from the interface data includes:

[0147] Preprocess the interface data;

[0148] Parse the timestamp in the preprocessed interface data;

[0149] Based on the timestamp, extract the first feature matrix from the preprocessed interface data.

[0150] In an alternative embodiment, the extracting the first feature matrix from the preprocessed interface data based on the timestamp includes:

[0151] At a set time interval, divide the preprocessed interface data into multiple time window data according to the timestamp;

[0152] Determine the data features corresponding to each time window data;

[0153] Respectively use the data features corresponding to the multiple time window data as the respective elements in the first feature matrix to construct the first feature matrix.

[0154] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the intelligent testing method based on the chip algorithm and the UAV interface described in any one of the above are implemented.

[0155] The embodiments of the present application further provide a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the intelligent testing method based on the chip algorithm and the drone interface described in any one of the above.

[0156] See Figure 4 , the embodiments of the present application further provide a computer device, including a processor 401, a memory 402, and a computer program stored in the memory 402 and configured to be executed by the processor 401. When the processor 401 executes the computer program, the steps of the intelligent testing method based on the chip algorithm and the drone interface described in any one of the above are implemented.

[0157] The computer device of this embodiment includes: a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401, such as an intelligent testing program based on the chip algorithm and the drone interface. When the processor 401 executes the computer program, the steps in each of the above embodiments of the intelligent testing method based on the chip algorithm and the drone interface are implemented, such as Figure 1 the steps S101 - 102 shown.

[0158] Exemplarily, the computer program may be divided into one or more modules / units. The one or more modules / units are stored in the memory 402 and executed by the processor 401 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the computer device.

[0159] The computer device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art can understand that the schematic diagram is only an example of the computer device, and does not constitute a limitation on the computer device. It may include more or fewer components than shown, or combine some components, or different components. For example, the computer device may further include input / output devices, network access devices, a bus, etc.

[0160] The processor 401 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor 401 may also be any conventional processor, etc. The processor 401 is the control center of the computer device, and connects various parts of the entire computer device through various interfaces and lines.

[0161] The memory 402 can be used to store the computer programs and / or modules. The processor 401 realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 402, and by calling the data stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0162] Among them, if the modules / units integrated in the computer device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 401, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0163] In summary, the embodiments of this application have at least the following beneficial effects:

[0164] By adopting the embodiments of this application, in response to a test request, using a pre-configured chip algorithm, encrypt the interface data obtained from the interface of the chip under test to obtain encrypted data; send the encrypted data to the test device for the test device to perform intelligent testing; wherein, the chip algorithm is configured to: extract a first feature matrix from the interface data; reconstruct the time-domain information in the first feature matrix to form a second feature matrix; decompose the second feature matrix to obtain K third feature matrices, where K is greater than 1; map the information reconstructed in each third feature matrix to the time domain to form a corresponding fourth feature matrix; based on the K fourth feature matrices, determine the encrypted data, which can encrypt the interface data of the chip under test to improve the security of data transmission between the drone and the test device, and further achieve accurate testing of the drone interface, ensuring the stability and reliability of the drone system.

[0165] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary hardware platform. Of course, it can also be implemented entirely through hardware. Based on such an understanding, all or part of the technical solution of this application that contributes to the background technology can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0166] The above is the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art of this technology, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements are also regarded as the protection scope of this application.

Claims

1. An intelligent testing method based on chip algorithm and drone interface, characterized in that: The unmanned aerial vehicle to be tested has a main control chip and a chip to be tested, and the method is executed by the main control chip and includes: In response to a test request, using a pre-configured chip algorithm, encrypting the interface data obtained from the interface of the chip to be tested to obtain encrypted data; Sending the encrypted data to a test device so that the test device can perform intelligent testing; Wherein, the chip algorithm is configured as follows: extracting a first feature matrix from the interface data; Reconstructing the time domain information in the first characteristic matrix to form a second characteristic matrix; Decomposing the second characteristic matrix to obtain K third characteristic matrices, where K is greater than 1; Mapping the information reconstructed in each third characteristic matrix to the time domain to form a corresponding fourth characteristic matrix; Determining the encrypted data based on the K fourth characteristic matrices includes: forming the encrypted data from the K fourth characteristic matrices; The step of reconstructing the time domain information in the first characteristic matrix to form a second characteristic matrix includes: Adding noise to the time domain information in the first characteristic matrix to obtain a fifth characteristic matrix; The time domain information after adding the noise in the fifth characteristic matrix is ​​mapped to the frequency domain to form a second characteristic matrix.

2. The method according to claim 1, characterized in that The noise is constructed in a manner including: Determining a preset first noise seed; Generate a second noise seed based on the time domain information in the first feature matrix and the first noise seed; Vector quantization mapping is performed on the second noise seed to construct the noise.

3. The method according to claim 2, characterized in that The first noise seed is noise data in the time domain, and the generating the second noise seed based on the time domain information in the first feature matrix and the first noise seed includes: Transforming the time domain information in the first feature matrix to obtain a time domain latent space feature vector; Performing the transformation process on the first noise seed to obtain a noise latent space feature vector; The second noise seed is obtained based on the time-domain latent space feature vector and the noise latent space feature vector.

4. The method according to claim 3, characterized in that The time domain latent space feature vector has M elements, the noise latent space feature vector has N elements, N and M are both positive integers, and N<M, and the second noise seed is obtained based on the time domain latent space feature vector and the noise latent space feature vector, including: Replace the N elements of the noise latent space feature vector with the N elements of the specified positions of the M elements of the time domain latent space feature vector; The replaced time-domain latent space feature vector is subjected to an inverse transformation matching the transformation process to obtain the second noise seed.

5. The method according to claim 3, characterized in that The transformation process is implemented by any of the following: Autoencoders; Variational Autoencoder; Wavelet transform.

6. The method according to claim 1, characterized in that The sending the encrypted data to the test device comprises: Sending a connection request to the test device, wherein the connection request is used to request to establish a dedicated data channel between the main control chip and the test device, and the dedicated data channel is constructed so that the main control chip can unidirectionally transmit data to the test device; It is determined that the dedicated data channel is successfully established, and the encrypted data is sent to the test device via the dedicated data channel.

7. The method according to claim 6, characterized in that The encrypted data is the K fourth characteristic matrices, the bandwidth of the dedicated data channel is determined by the amount of data of the fourth characteristic matrix with the largest amount of data among the K fourth characteristic matrices, and sending the encrypted data to the test device via the dedicated data channel includes: The K fourth characteristic matrices are sent one by one to the test device via the dedicated data channel.

8. The method according to claim 1, characterized in that The step of extracting a first characteristic matrix from the interface data comprises: Preprocessing the interface data; Parse the timestamp in the preprocessed interface data; Based on the timestamp, a first feature matrix is ​​extracted from the preprocessed interface data.

9. The method according to claim 8, characterized in that The step of extracting a first feature matrix from the preprocessed interface data based on the timestamp includes: At a set time interval, dividing the pre-processed interface data into a plurality of time window data according to the timestamp; Determine the data features corresponding to each time window data; The data features corresponding to the multiple time window data are respectively used as elements in the first feature matrix to construct the first feature matrix.

Images