Mobile office method and system based on 5G network

Abstract

The present invention belongs to the technical field of Internet of Things office. The present invention discloses a mobile office method and system based on a 5G network, including: collecting multimodal data of users; preprocessing the multimodal data of users to obtain multimodal features; performing user verification based on the multimodal features and pre-stored user modal features, and generating a user modal key; using the user modal key as an encryption key to encrypt and share transmission data; greatly improving the security of the system.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things office technology, and more specifically, to a mobile office method and system based on a 5G network. Background Art

[0002] The patent application with the publication number CN118337962A discloses a 5G network data transmission method for a beyond-visual-range remote driving platform, which includes: obtaining images at each acquisition moment during the remote driving process; obtaining a local contrast feature data sequence in the same direction in the neighborhood of each current co-located macroblock; calculating the inter-frame data offset index of each matching block; obtaining a relative feature analysis data sequence of each matching block; calculating the relative inter-frame offset coefficient of each matching block, and combining compression coding technology to complete the 5G network data transmission of the beyond-visual-range remote driving platform; the method analyzes the local area change characteristics between images at adjacent acquisition moments, combines global search and local search, improves the efficiency and accuracy of motion vector calculation in the inter-frame prediction process, and realizes efficient transmission of network data in the beyond-visual-range remote driving platform.

[0003] With the rapid development of science and technology, 5G technology has gradually penetrated into all aspects of our lives, especially in the office field. With its high speed, low latency and large number of connections, 5G technology is leading the innovation of office methods, improving office efficiency and changing our working mode. The high speed and low latency characteristics of 5G technology make remote office and video conferencing possible, breaking the limitations of traditional office mode. With the support of 5G technology, team members in different locations can share and edit files in real time and collaborate efficiently. At the same time, through high-definition video conferencing, you can feel the communication between colleagues more realistically and enhance the cohesion of the team. With the high-speed transmission of 5G network, cloud office becomes a reality. In the cloud office mode, the data and applications required for office are stored in the cloud, and employees can access them anytime and anywhere through any device, which greatly improves the flexibility and efficiency of office. In addition, cloud office can also save a lot of hardware equipment and maintenance costs for enterprises. 5G technology combined with advanced technologies such as artificial intelligence and big data can realize intelligent office methods. At the same time, through big data analysis, enterprises can understand the market and customer needs more accurately and provide strong support for decision-making.

[0004] However, while enjoying the convenience brought by 5G technology, there are also security issues. For example, during data transmission, the high-speed transmission of 5G networks increases the risk of data interception, and the use of insecure networks such as public Wi-Fi increases the possibility of man-in-the-middle attacks. During user authentication, password authentication is easy to be cracked or leaked, a single biometric feature (such as fingerprints) may be forged, and tokens or smart cards are easy to be lost or stolen.

[0005] In view of this, the present invention proposes a mobile office method and system based on 5G network to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a method and system for mobile office based on 5G network;

[0007] The mobile office method based on the 5G network of the present invention includes: collecting multimodal data of the user;

[0008] Preprocess the user's multimodal data to obtain multimodal features;

[0009] Perform user verification based on multimodal features and pre-stored user modal features, and generate a user modal key;

[0010] The user mode key is used as the encryption key to encrypt and share the transmitted data.

[0011] Furthermore, the multimodal data includes: facial image, heart rate data, respiratory rate data and galvanic skin response data.

[0012] Furthermore, the specific method of preprocessing the multimodal data of the user includes:

[0013] Coordinate the facial image and construct the image coordinates with the lower left corner of the facial image as the coordinate origin;

[0014] Extracting facial geometric features of facial images through image coordinates, including: distance between eyes, length and width of eyes, forehead width, mouth width, coordinates of nose tip, mouth corners and eye corners;

[0015] The facial image is equalized by image coordinates, and the specific methods include:

[0016] Perform grayscale statistics on each pixel in the facial image. The formula for grayscale statistics is: Where h(i) represents the number of pixels at gray level i, I(x,y) is the gray value of the facial image at coordinate position (x,y), i represents the gray level, and δ represents the Kronecker delta function;

[0017] For each gray level, the cumulative distribution is calculated using the formula: Where CF(i) represents the cumulative distribution of gray level i;

[0018] Normalize the cumulative distribution of each gray level to obtain the gray level mapping value. The calculation formula for normalization is: where CF norm(i) represents the mapping value of gray level i, CF min represents the minimum non-zero value in the cumulative distribution, and N represents the total number of pixels in the facial image;

[0019] The neighborhood size of each pixel in the facial image is preset to be O×P; O represents the number of pixels on the long side of the neighborhood, and P represents the number of pixels on the wide side of the neighborhood. The local value of each pixel in the facial image is calculated, and the calculation formula of the local value is: Where LB(R) represents the local value of pixel R, M represents the total number of pixels in the neighborhood, a represents the ath pixel in the neighborhood of pixel R, and I(x a ,y a ) is the facial image at coordinate position (x a ,y a ) gray value, x a Represents the horizontal coordinate of the ath pixel in the neighborhood of pixel point R, y a Represents the vertical coordinate of the ath pixel in the neighborhood of pixel point R, I(x R ,y R ) is the facial image at coordinate position (x R ,y R ) gray value, x R Represents the horizontal coordinate of pixel point R, y R represents the vertical coordinate of pixel point R, S is the comparison function, 2 a are binary weights;

[0020] According to the local value of each pixel of the facial image, a pixel local histogram is constructed, and facial texture features are extracted through the pixel local histogram data. The facial texture features include: mean, variance, contrast and energy of the pixel local histogram data;

[0021] Perform frequency conversion on the heart rate data. The frequency conversion formula is:

[0022] Where g represents the scale parameter, e represents the translation parameter, represents complex conjugate, f(t) represents the tth heart rate data in the time domain; analyze the frequency spectrum after frequency transformation, extract variance, skewness, kurtosis, edge points, mutation points and scale coefficient as heart rate features, and similarly obtain respiratory features through respiratory frequency data, and obtain skin features through skin electrical response data.

[0023] Furthermore, the specific method of obtaining the multimodal features includes:

[0024] The facial geometric features, facial texture features, heart rate features, breathing features and skin features are fused through the early fusion method to obtain multimodal features.

[0025] Furthermore, the specific method of performing user verification based on the multimodal features and the pre-stored user modal features includes:

[0026] Each feature in the multimodal feature is vectorized, and the average similarity between the vectorized feature and the corresponding feature in the pre-stored user modal feature is calculated. The calculation formula is: Where sim represents the average similarity, T represents the total number of features in the multimodal feature, and A h Represents the feature vector of the hth feature in the multimodal feature, B h represents the feature vector of the user modal feature corresponding to the hth feature in the multimodal feature, ||A h || represents the eigenvector A h The module of ||B h || represents the feature vector B h Model;

[0027] When the average similarity value is greater than or equal to the preset similarity threshold, the user verification is passed;

[0028] When the average similarity value is less than a preset similarity threshold, the user verification fails, the user is prohibited from accessing, and a user verification failure message is sent to the danger warning terminal.

[0029] Furthermore, the specific method of generating the user modal key includes:

[0030] When the user verification is passed, the similarity between the user modal feature and the corresponding feature in the multimodal feature is calculated according to the cosine similarity formula, the feature with the highest similarity in the multimodal feature is taken as the key feature, the key feature is hashed twice, and the user modal key is obtained.

[0031] Furthermore, the specific steps of encrypting and sharing the transmission data include:

[0032] Step 1: Generate a pseudo-random sequence and a symmetric key based on the user modal key;

[0033] Step 2: Encrypt and share the transmitted data using a pseudo-random sequence and a symmetric key.

[0034] Furthermore, the specific method of generating a pseudo-random sequence and a symmetric key based on a user modal key includes:

[0035] Initialize n quantum bits to state |0>;

[0036] The user modal key is divided into q sub-keys, the value of q is the same as the value of n, and each quantum bit is rotated three times according to the sub-key to obtain the rotated quantum bit. The rotation formula is: LZ c →G(θ c)·L(θ c )·U(θ c )·LZ c ; where θ c represents the rotation angle corresponding to the cth quantum bit, LZ c represents the cth quantum bit, G(θ c ) represents the first revolving door, L(θ c ) represents the second revolving door, U(θ c ) represents the third revolving door;

[0037] The formula for calculating the rotation angle is: θ c =H -1 (MY v )mod2π; where MY v represents the vth subkey, H -1 represents the anti-hash function, and π represents pi;

[0038] The formula for the first rotation operation is: Where τ represents the imaginary unit, G(θ c ) represents the first revolving door;

[0039] The formula for the second rotation operation is: Where L(θ c ) represents the second revolving door;

[0040] The formula for the third rotation operation is: Among them U(θ c ) represents the third revolving door;

[0041] The measurement function of the quantum computing platform is used to measure the rotating quantum bits to obtain a pseudo-random sequence, which is then used through a hash function to generate a symmetric key.

[0042] Furthermore, the specific manner of encrypting and sharing data transmission by using a pseudo-random sequence and a symmetric key includes:

[0043] The transmission data is divided into LEN blocks of data. The value of LEN is consistent with the value of n. Each data block is encrypted using a symmetric encryption algorithm with a symmetric key to obtain a ciphertext block. The encryption formula is: MW η represents the nth ciphertext block, D η represents the nth data block, The encryption key is MY η AES encryption algorithm, MY η represents the nth symmetric key, n represents the data subscript, which is used to determine the nth data; the ciphertext block is enhanced and obfuscated according to the pseudo-random sequence to obtain an enhanced ciphertext block, and the formula for enhanced obfuscation is: in is the enhanced ciphertext block obtained after enhancing the confusion of the nth ciphertext block, Ran η represents the nth pseudo-random sequence; using the symmetric key as the key and the pseudo-random sequence as the value, construct a decryption key-value pair, steganographically write the decryption key-value pair through the LSB steganography algorithm to obtain a secret key-value pair, and splice the secret key-value pair to the end of the corresponding enhanced ciphertext block to obtain a synthetic ciphertext block; initialize the bandwidth of the virtual channel to DK-Size, the delay to YC-Size, and the transmission protocol to HTTPS secure transmission protocol; initialize the network address through the algorithm to minimize address waste; based on the bandwidth, delay, transmission protocol and network address, construct a virtual channel through the tunneling technology method; share and transmit the synthetic ciphertext block through the constructed virtual channel; split the synthetic ciphertext block to obtain an encrypted content block and a decryption key block; the data receiving end decodes the decryption key block through the steganography decoding method to obtain a decryption key-value pair, based on the value of the decryption key-value pair, that is, the pseudo-random sequence, the encrypted content block is reversely enhanced and obfuscated to obtain a ciphertext block, based on the key of the decryption key-value pair, that is, the symmetric key, the ciphertext block is reversely encrypted to obtain a data block, the data blocks are combined in sequence, and the data receiving end obtains the transmitted data.

[0044] The mobile office system based on 5G network of the present invention includes:

[0045] Data collection module: collects multimodal data of users;

[0046] Data processing module: pre-process the user's multimodal data to obtain multimodal features;

[0047] User verification module: performs user verification based on multimodal features and pre-stored user modal features, and generates a user modal key;

[0048] Data encryption sharing module: uses the user modal key as the encryption key to encrypt and share the transmitted data.

[0049] The technical effects and advantages of the mobile office method and system based on 5G network of the present invention are as follows:

[0050] The present invention ensures the multi-level identity authentication and increases the security of the system by collecting multi-modal data; improves the contrast of the image through grayscale statistics and equalization processing, making facial features more obvious and easy to identify; extracts multi-dimensional features through wavelet transform and spectrum analysis, and provides rich physiological feature information; verifies based on multi-modal features and pre-stored user modal features to improve the security of the system; uses user modal keys as encryption keys to increase the unpredictability and security of the encryption system; generates keys through complex quantum state rotation operations, which are highly unpredictable and anti-cracking, greatly enhancing the security of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a schematic diagram of the mobile office method based on 5G network of the present invention;

[0052] Figure 2 This is a schematic diagram of the mobile office system based on 5G network of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1

[0055] See also Figure 1 As shown, the mobile office method based on the 5G network described in this embodiment includes: collecting multimodal data of the user;

[0056] Preprocess the user's multimodal data to obtain multimodal features;

[0057] Perform user verification based on multimodal features and pre-stored user modal features, and generate a user modal key;

[0058] The user modal key is used as the encryption key to encrypt and share the transmitted data;

[0059] The multimodal data includes: facial images, heart rate data, respiratory rate data, and galvanic skin response data, which is the electrical conductance data of the user's skin;

[0060] Multimodal data is data extracted from users in microenvironment changes. During user authentication, the microenvironment control terminal performs micro-fluctuation control on the user's surrounding environment, collects the user's facial image through the camera under microenvironment changes, collects the user's skin conductivity data under microenvironment changes through the skin conductivity sensor, collects the user's heart rate data under microenvironment changes through the heart rate sensor, and collects the user's breathing rate data under microenvironment changes through the breathing sensor;

[0061] The specific methods for preprocessing the user's multimodal data include:

[0062] Coordinate the facial image and construct the image coordinates with the lower left corner of the facial image as the coordinate origin;

[0063] Extracting facial geometric features of facial images through image coordinates, including: distance between eyes, length and width of eyes, forehead width, mouth width, coordinates of nose tip, mouth corners and eye corners;

[0064] The facial image is equalized by image coordinates to increase the contrast of the image and make the facial features more obvious. The specific methods include:

[0065] Perform grayscale statistics on each pixel in the facial image. The formula for grayscale statistics is: Where h(i) represents the number of pixels at gray level i, I(x,y) is the gray value of the facial image at coordinate position (x,y), i represents the gray level, and δ represents the Kronecker delta function;

[0066] The grayscale range is [0,255];

[0067] For each gray level, the cumulative distribution is calculated using the formula: Where CF(i) represents the cumulative distribution of gray level i;

[0068] Normalize the cumulative distribution of each gray level to obtain the gray level mapping value. The calculation formula for normalization is: where CF norm (i) represents the mapping value of gray level i, CF min represents the minimum non-zero value in the cumulative distribution, and N represents the total number of pixels in the facial image;

[0069] The neighborhood size of each pixel in the facial image is preset to be O×P; O represents the number of pixels on the long side of the neighborhood, and P represents the number of pixels on the wide side of the neighborhood. The local value of each pixel in the facial image is calculated, and the calculation formula of the local value is: Where LB(R) represents the local value of pixel R, M represents the total number of pixels in the neighborhood, a represents the ath pixel in the neighborhood of pixel R, and I(x a ,y a ) is the facial image at coordinate position (x a ,y a ) gray value, x a Represents the horizontal coordinate of the ath pixel in the neighborhood of pixel point R, y a Represents the vertical coordinate of the ath pixel in the neighborhood of pixel point R, I(x R ,y R ) is the facial image at coordinate position (x R ,y R ) gray value, x R Represents the horizontal coordinate of pixel point R, y RRepresents the vertical coordinate of pixel R, S is a comparison function, returns 0 or 1, 2 a are binary weights used to form binary numbers;

[0070] According to the local value of each pixel, a local pixel histogram is constructed. The histogram represents the frequency distribution of different binary codes in the image and can be used as a representation of texture features.

[0071] Extracting facial texture features through pixel local histogram data, the facial texture features include: mean, variance, contrast and energy of pixel local histogram data;

[0072] Perform frequency conversion on the heart rate data. The frequency conversion formula is:

[0073] Where g represents the scale parameter, e represents the translation parameter, represents complex conjugate, f(t) represents the tth heart rate data in the time domain; analyze the frequency spectrum after frequency transformation, extract variance, skewness, kurtosis, edge point, mutation point and scale coefficient as heart rate features, and similarly obtain respiratory features through respiratory frequency data, and obtain skin features through skin electrical response data (i.e., the same method as obtaining heart rate features through heart rate data);

[0074] The facial geometric features, facial texture features, heart rate features, breathing features and skin features are fused through the early fusion method to obtain multimodal features;

[0075] The specific method of performing user verification on the multimodal features and the pre-stored user modal features and generating the user modal key includes:

[0076] Each feature in the multimodal feature is vectorized, and the average similarity between the vectorized feature and the corresponding feature in the pre-stored user modal feature is calculated. The calculation formula is: Where sim represents the average similarity, T represents the total number of features in the multimodal feature, and A h Represents the feature vector of the hth feature in the multimodal feature, B h represents the feature vector of the user modal feature corresponding to the hth feature in the multimodal feature, ||A h || represents the eigenvector A h The module of ||B h || represents the feature vector B h Model;

[0077] When the average similarity value is greater than or equal to the preset similarity threshold, the user verification is passed, and the similarity between the user modal feature and the corresponding feature in the multimodal feature is calculated according to the cosine similarity formula. The feature with the highest similarity in the multimodal feature is taken as the key feature, and the key feature is hashed twice to obtain the user modal key;

[0078] Hashing is to transform an input of any length into an output of fixed length through a hash algorithm. This conversion is a compression mapping;

[0079] When the average similarity value is less than the preset similarity threshold, the user verification fails, the user is prohibited from accessing, and the user verification failure information is sent to the danger warning terminal;

[0080] Specific ways to encrypt and share transmitted data include:

[0081] Initialize n qubits to state |0>. In quantum computing, qubits can be represented as quantum states |0> or |1>. Initializing to the |0> state ensures that the qubits start from a known standard state, and the initial state of the qubits is in a superposition state of quantum mechanics, which is difficult to be predicted and stolen by the outside world.

[0082] The user modal key is divided into q sub-keys, the value of q is the same as the value of n, and each quantum bit is rotated three times according to the sub-key to obtain the rotated quantum bit. The rotation formula is: LZ c →G(θ c )·L(θ c )·U(θ c )·LZ c ; where θ c represents the rotation angle corresponding to the cth quantum bit, LZ c represents the cth quantum bit, G(θ c ) represents the first revolving door, L(θ c ) represents the second revolving door, U(θ c ) represents the third revolving door;

[0083] By applying a series of rotation gate operations to quantum bits, the generated quantum state has a high degree of complexity and randomness, which increases the unpredictability of the encryption key. Moreover, since the rotation angle is determined by the hash value of the master key, even if the adversary obtains part of the information, it is difficult to restore the original key, which enhances the anti-cracking ability.

[0084] The formula for calculating the rotation angle is: θ c =H -1 (MY v )mod2π; where MY v represents the vth subkey, H -1 represents the anti-hash function, and π represents pi;

[0085] The formula for the first rotation operation is: Where τ represents the imaginary unit, G(θ c ) represents the first revolving door;

[0086] The formula for the second rotation operation is: Where L(θ c ) represents the second revolving door;

[0087] The formula for the third rotation operation is: Among them U(θ c ) represents the third revolving door;

[0088] The measurement function of the quantum computing platform is used to measure the rotating quantum bits to obtain a pseudo-random sequence, and a symmetric key is generated by using a hash function on the pseudo-random sequence.

[0089] The transmission data is divided into LEN blocks of data. The value of LEN is consistent with the value of n. Each data block is encrypted using a symmetric encryption algorithm with a symmetric key to obtain a ciphertext block. The encryption formula is: MW η represents the nth ciphertext block, D η represents the nth data block, The encryption key is MY η AES encryption algorithm, MY η represents the nth symmetric key, n represents the data subscript, which is used to determine the nth data; the ciphertext block is enhanced and obfuscated according to the pseudo-random sequence to obtain an enhanced ciphertext block, and the formula for enhanced obfuscation is: in is the enhanced ciphertext block obtained after enhancing the confusion of the nth ciphertext block, Ran ηrepresents the nth pseudo-random sequence; using the symmetric key as the key and the pseudo-random sequence as the value, construct a decryption key-value pair, steganographically write the decryption key-value pair through the LSB steganography algorithm to obtain a secret key-value pair, and splice the secret key-value pair to the end of the corresponding enhanced ciphertext block to obtain a synthetic ciphertext block; initialize the bandwidth of the virtual channel to DK-Size, the delay to YC-Size, and the transmission protocol to HTTPS secure transmission protocol; initialize the network address through the algorithm to minimize address waste; based on the bandwidth, delay, transmission protocol and network address, construct a virtual channel through the tunneling technology method; share and transmit the synthetic ciphertext block through the constructed virtual channel; split the synthetic ciphertext block to obtain an encrypted content block and a decryption key block; the data receiving end decodes the decryption key block through the steganography decoding method to obtain a decryption key-value pair, based on the value of the decryption key-value pair, that is, the pseudo-random sequence, the encrypted content block is reversely enhanced and obfuscated to obtain a ciphertext block, based on the key of the decryption key-value pair, that is, the symmetric key, the ciphertext block is reversely encrypted to obtain a data block, the data blocks are combined in sequence, and the data receiving end obtains the transmitted data;

[0090] A virtual channel is a logical communication path created by software or protocol layer on the basis of a physical network; it virtualizes the channel for data sharing and transmission, allowing different data streams to be shared and transmitted through a single physical network while maintaining the isolation and security of the data streams.

[0091] This embodiment ensures the multi-level identity authentication and increases the security of the system by collecting multimodal data; improves the contrast of the image through grayscale statistics and equalization processing, making facial features more obvious and easy to identify; extracts multidimensional features through wavelet transform and spectrum analysis to provide rich physiological feature information; verifies based on multimodal features and pre-stored user modal features to improve the security of the system; uses user modal keys as encryption keys to increase the unpredictability and security of the encryption system; generates keys through complex quantum state rotation operations, which are highly unpredictable and anti-cracking, greatly enhancing the security of data sharing and transmission.

[0092] Example 2

[0093] See also Figure 2 As shown, for the part not described in detail in this embodiment, please refer to the description of Embodiment 1, and a mobile office system based on a 5G network is provided, including:

[0094] Data collection module: collects multimodal data of users;

[0095] Data processing module: pre-process the user's multimodal data to obtain multimodal features;

[0096] User verification module: performs user verification based on multimodal features and pre-stored user modal features, and generates a user modal key;

[0097] Data encryption and sharing module: uses the user modal key as the encryption key to encrypt and share the transmitted data;

[0098] The modules are connected to each other via wired and / or wireless means to achieve data transmission between modules.

[0099] Example 3

[0100] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the mobile office method based on the 5G network provided above is implemented.

[0101] Since the electronic device introduced in this embodiment is an electronic device used to implement the accompanying office method based on the 5G network in the embodiment of the present application, based on the accompanying office method based on the 5G network introduced in the embodiment of the present application, the technical personnel of the field can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as the technical personnel of the field implement the electronic device used in the accompanying office method based on the 5G network in the embodiment of the present application, it belongs to the scope of protection of this application.

[0102] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0103] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A mobile office method based on 5G network, characterized in that: include: Collect multimodal data of users; Preprocess the user's multimodal data to obtain multimodal features; Perform user verification based on multimodal features and pre-stored user modal features, and generate a user modal key; The user modal key is used as the encryption key to encrypt and share the transmitted data; The specific method of generating the user modality key includes: When the user passes the verification, the similarity between the user modal feature and the corresponding feature in the multimodal feature is calculated according to the cosine similarity formula, and the feature with the highest similarity in the multimodal feature is taken as the key feature. The key feature is hashed twice to obtain the user modal key; The specific steps of encrypting and sharing the transmitted data include: Step 1: Generate a pseudo-random sequence and a symmetric key based on the user modal key; Step 2: Encrypt and share the transmitted data using a pseudo-random sequence and a symmetric key; The specific method of generating a pseudo-random sequence and a symmetric key based on a user modal key includes: Initialize n quantum bits to state |0>; The user modal key is divided into q sub-keys, the value of q is the same as the value of n, and each quantum bit is rotated three times according to the sub-key to obtain the rotated quantum bit. The rotation formula is: LZ c →G(θ c )·L(θ c )·U(θ c )·LZ c ; where θ c represents the rotation angle corresponding to the cth quantum bit, LZ c represents the cth quantum bit, G(θ c ) represents the first revolving door, L(θ c ) represents the second revolving door, U(θ c ) represents the third revolving door; The formula for calculating the rotation angle is: θ c =H -1 (MY v )mod2π; where MY v represents the vth subkey, H -1 represents the anti-hash function, and π represents pi; The formula for the first rotation operation is: Where τ represents the imaginary unit, G(θ c ) represents the first revolving door; The formula for the second rotation operation is: Where L(θ c ) represents the second revolving door; The formula for the third rotation operation is: Among them U(θ c ) represents the third revolving door; The measurement function of the quantum computing platform is used to measure the rotating quantum bits to obtain a pseudo-random sequence, and a symmetric key is generated by using a hash function on the pseudo-random sequence. The specific method of encrypting and sharing the transmission data by using a pseudo-random sequence and a symmetric key includes: The transmission data is divided into LEN blocks of data. The value of LEN is consistent with the value of n. Each data block is encrypted using a symmetric encryption algorithm with a symmetric key to obtain a ciphertext block. The encryption formula is: MW η represents the nth ciphertext block, D η represents the nth data block, The encryption key is MY η AES encryption algorithm, MY η represents the nth symmetric key, n represents the data subscript, which is used to determine the nth data; the ciphertext block is enhanced and obfuscated according to the pseudo-random sequence to obtain an enhanced ciphertext block, and the formula for enhanced obfuscation is: in is the enhanced ciphertext block obtained after enhancing the confusion of the nth ciphertext block, Ran η represents the nth pseudo-random sequence; using the symmetric key as the key and the pseudo-random sequence as the value, construct a decryption key-value pair, steganographically write the decryption key-value pair through the LSB steganography algorithm to obtain a secret key-value pair, and splice the secret key-value pair to the end of the corresponding enhanced ciphertext block to obtain a synthetic ciphertext block; initialize the bandwidth of the virtual channel to DK-Size, the delay to YC-Size, and the transmission protocol to HTTPS secure transmission protocol; initialize the network address through the algorithm to minimize address waste; based on the bandwidth, delay, transmission protocol and network address, construct a virtual channel through the tunneling technology method; share and transmit the synthetic ciphertext block through the constructed virtual channel; split the synthetic ciphertext block to obtain an encrypted content block and a decryption key block; the data receiving end decodes the decryption key block through the steganography decoding method to obtain a decryption key-value pair, based on the value of the decryption key-value pair, that is, the pseudo-random sequence, the encrypted content block is reversely enhanced and obfuscated to obtain a ciphertext block, based on the key of the decryption key-value pair, that is, the symmetric key, the ciphertext block is reversely encrypted to obtain a data block, the data blocks are combined in sequence, and the data receiving end obtains the transmitted data.

2. The mobile office method based on 5G network according to claim 1 is characterized in that: The multimodal data includes: facial image, heart rate data, respiratory rate data and skin electrical response data.

3. The mobile office method based on 5G network according to claim 2 is characterized in that: The specific method of preprocessing the multimodal data of the user includes: Coordinate the facial image and construct the image coordinates with the lower left corner of the facial image as the coordinate origin; Extracting facial geometric features of facial images through image coordinates, including: distance between eyes, length and width of eyes, forehead width, mouth width, coordinates of nose tip, mouth corners and eye corners; The facial image is equalized by image coordinates, and the specific methods include: Perform grayscale statistics on each pixel in the facial image. The formula for grayscale statistics is: Where h(i) represents the number of pixels at gray level i, I(x,y) is the gray value of the facial image at coordinate position (x,y), i represents the gray level, and δ represents the Kronecker delta function; For each gray level, the cumulative distribution is calculated using the formula: Where CF(i) represents the cumulative distribution of gray level i; Normalize the cumulative distribution of each gray level to obtain the gray level mapping value. The calculation formula for normalization is: where CF norm (i) represents the mapping value of gray level i, CF min represents the minimum non-zero value in the cumulative distribution, and N represents the total number of pixels in the facial image; The neighborhood size of each pixel in the facial image is preset to be O×P; O represents the number of pixels on the long side of the neighborhood, and P represents the number of pixels on the wide side of the neighborhood. The local value of each pixel in the facial image is calculated, and the calculation formula of the local value is: Where LB(R) represents the local value of pixel R, M represents the total number of pixels in the neighborhood, a represents the ath pixel in the neighborhood of pixel R, and I(x a ,y a ) is the facial image at coordinate position (x a ,y a ) gray value, x a Represents the horizontal coordinate of the ath pixel in the neighborhood of pixel point R, y a Represents the vertical coordinate of the ath pixel in the neighborhood of pixel point R, I(x R ,y R ) is the facial image at coordinate position (x R ,y R ) gray value, x R Represents the horizontal coordinate of pixel point R, y R represents the vertical coordinate of pixel point R, S is the comparison function, 2 a are binary weights; According to the local value of each pixel of the facial image, a pixel local histogram is constructed, and facial texture features are extracted through the pixel local histogram data. The facial texture features include: mean, variance, contrast and energy of the pixel local histogram data; Perform frequency conversion on the heart rate data. The frequency conversion formula is: Where g represents the scale parameter, e represents the translation parameter, represents complex conjugate, f(t) represents the tth heart rate data in the time domain; analyze the frequency spectrum after frequency transformation, extract variance, skewness, kurtosis, edge points, mutation points and scale coefficient as heart rate features, and similarly obtain respiratory features through respiratory frequency data, and obtain skin features through skin electrical response data.

4. The mobile office method based on 5G network according to claim 3 is characterized in that: The multimodal feature acquisition method includes: The facial geometric features, facial texture features, heart rate features, breathing features and skin features are fused through the early fusion method to obtain multimodal features.

5. The mobile office method based on 5G network according to claim 4 is characterized in that: The specific method of performing user verification based on the multimodal features and the pre-stored user modal features includes: Each feature in the multimodal feature is vectorized, and the average similarity between the vectorized feature and the corresponding feature in the pre-stored user modal feature is calculated. The calculation formula is: Where sim represents the average similarity, T represents the total number of features in the multimodal feature, and A h Represents the feature vector of the hth feature in the multimodal feature, B h represents the feature vector of the user modal feature corresponding to the hth feature in the multimodal feature, ||A h || represents the eigenvector A h The module of ||B h || represents the feature vector B h Model; When the average similarity value is greater than or equal to the preset similarity threshold, the user verification is passed; When the average similarity value is less than a preset similarity threshold, the user verification fails, the user is prohibited from accessing, and a user verification failure message is sent to the danger warning terminal.

6. A mobile office system based on a 5G network, which is used to implement the mobile office method based on a 5G network as described in any one of claims 1 to 5, characterized in that: include: Data collection module: collects multimodal data of users; Data processing module: pre-process the user's multimodal data to obtain multimodal features; User verification module: performs user verification based on multimodal features and pre-stored user modal features, and generates a user modal key; Data encryption and sharing module: uses the user modal key as the encryption key to encrypt and share the transmitted data; The specific method of generating the user modality key includes: When the user passes the verification, the similarity between the user modal feature and the corresponding feature in the multimodal feature is calculated according to the cosine similarity formula, and the feature with the highest similarity in the multimodal feature is taken as the key feature. The key feature is hashed twice to obtain the user modal key; The specific steps of encrypting and sharing the transmitted data include: Step 1: Generate a pseudo-random sequence and a symmetric key based on the user modal key; Step 2: Encrypt and share the transmitted data using a pseudo-random sequence and a symmetric key; The specific method of generating a pseudo-random sequence and a symmetric key based on a user modal key includes: Initialize n quantum bits to state |0>; The user modal key is divided into q sub-keys, the value of q is the same as the value of n, and each quantum bit is rotated three times according to the sub-key to obtain the rotated quantum bit. The rotation formula is: LZ c →G(θ c )·L(θ c )·U(θ c )·LZ c ; where θ c represents the rotation angle corresponding to the cth quantum bit, LZ c represents the cth quantum bit, G(θ c ) represents the first revolving door, L(θ c ) represents the second revolving door, U(θ c ) represents the third revolving door; The formula for calculating the rotation angle is: θ c =H -1 (MY v )mod2π; where MY v represents the vth subkey, H -1 represents the anti-hash function, and π represents pi; The formula for the first rotation operation is: Where τ represents the imaginary unit, G(θ c ) represents the first revolving door; The formula for the second rotation operation is: Where L(θ c ) represents the second revolving door; The formula for the third rotation operation is: Among them U(θ c ) represents the third revolving door; The measurement function of the quantum computing platform is used to measure the rotating quantum bits to obtain a pseudo-random sequence, and a symmetric key is generated by using a hash function on the pseudo-random sequence. The specific method of encrypting and sharing the transmission data by using a pseudo-random sequence and a symmetric key includes: The transmission data is divided into LEN blocks of data. The value of LEN is consistent with the value of n. Each data block is encrypted using a symmetric encryption algorithm with a symmetric key to obtain a ciphertext block. The encryption formula is: MW η represents the nth ciphertext block, D η represents the nth data block, Indicates that the encryption key is MY η AES encryption algorithm, MY η represents the nth symmetric key, n represents the data subscript, which is used to determine the nth data; the ciphertext block is enhanced and obfuscated according to the pseudo-random sequence to obtain an enhanced ciphertext block, and the formula for enhanced obfuscation is: in is the enhanced ciphertext block obtained after enhancing the confusion of the nth ciphertext block, Ran η represents the nth pseudo-random sequence; using the symmetric key as the key and the pseudo-random sequence as the value, construct a decryption key-value pair, steganographically write the decryption key-value pair through the LSB steganography algorithm to obtain a secret key-value pair, and splice the secret key-value pair to the end of the corresponding enhanced ciphertext block to obtain a synthetic ciphertext block; initialize the bandwidth of the virtual channel to DK-Size, the delay to YC-Size, and the transmission protocol to HTTPS secure transmission protocol; initialize the network address through the algorithm to minimize address waste; based on the bandwidth, delay, transmission protocol and network address, construct a virtual channel through the tunneling technology method; share and transmit the synthetic ciphertext block through the constructed virtual channel; split the synthetic ciphertext block to obtain an encrypted content block and a decryption key block; the data receiving end decodes the decryption key block through the steganography decoding method to obtain a decryption key-value pair, based on the value of the decryption key-value pair, that is, the pseudo-random sequence, the encrypted content block is reversely enhanced and obfuscated to obtain a ciphertext block, based on the key of the decryption key-value pair, that is, the symmetric key, the ciphertext block is reversely encrypted to obtain a data block, the data blocks are combined in sequence, and the data receiving end obtains the transmitted data.

Images