A blockchain-based console identity recognition method

Abstract

The application discloses a console identity recognition method based on a block chain, relates to the technical field of computer security and man-machine interaction, and realizes non-sensitization and precision of console identity recognition through the fusion of behavior characteristic modeling and the block chain technology; in the multi-person rotation scene, the operator does not need to actively perform biological verification actions, the system continuously captures physical operation actions and graphic interaction logic, converts behavior characteristics into encrypted operation fingerprints and stores the operation fingerprints in a chain, a block chain smart contract compares the time sequence difference between current operation and historical fingerprints in real time, and biological auxiliary verification is triggered only when behavior is abnormal, so that operation interruption caused by gloves, light and other factors in an industrial environment is significantly reduced, a dynamic permission label generation mechanism breaks through the limitation of static authorization, the semantic intention of a control instruction is analyzed, a preset device permission topology graph is combined, a minimum device operation range is automatically delimited, and a label effective period is set according to an instruction risk level.

Description

Technical Field

[0001] This invention relates to the fields of computer security and human-computer interaction technology, and in particular to a blockchain-based console identity recognition method. Background Technology

[0002] In scenarios such as multi-party collaborative meeting scheduling and emergency command, the console often requires multiple people to take turns operating it. For example, in important meetings, the chairperson, translator, and technical support personnel need to quickly take over operating the same console, and industrial dispatch centers have multiple shifts of operators to hand over their duties. Such scenarios require seamless identity switching to avoid meeting interruptions or instruction delays. Current mainstream solutions use biometric recognition, such as facial recognition or fingerprint recognition, to bind the operator's identity, which conforms to the continuous verification principle of zero-trust architecture.

[0003] To meet the need for rapid switching, mainstream solutions mainly adopt two types of technologies: one is rapid identity loading based on environment variables, such as the Azure console binding to the terminal through a preset key, which automatically loads the corresponding user configuration when switching; the other is dynamic biometric detection, which refers to the liveness detection mechanism of Alibaba Cloud's real-person authentication, and periodically triggers face comparison during operation; some systems combine the OIDC protocol to realize cross-session permission synchronization, and update access tokens in real time through a centralized identity provider.

[0004] In practical applications, explicit biometric authentication in existing solutions requires interrupting the operation process. For example, fingerprint recognition requires users to remove their gloves to contact the sensor, causing operational delays in industrial scenarios. In addition, there is a risk of confusion during permission handover. When multiple people switch roles rapidly, centralized identity providers may cause overlapping permissions between operators due to synchronization delays. At the same time, physical conditions limit identity recognition. For example, changes in lighting at the conference console affect the accuracy of facial recognition, or biometric features cannot be collected when operators are wearing protective equipment. These shortcomings are particularly prominent in scenarios such as scheduling and multinational conferences that require highly continuous operations. Summary of the Invention

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] This invention provides a blockchain-based console identity recognition method to solve the problems of interrupted biometric verification, delayed centralized permission synchronization, and physical limitations on recognition accuracy in multi-party rotation scenarios.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] This invention provides a blockchain-based console identity verification method, which includes:

[0009] Step S1: Collect the operator's operational behavior characteristics through the console sensors. The operational behavior characteristics include physical operation action sequences and graphical interface interaction logic sequences.

[0010] Step S2: Encrypt the operation behavior characteristics to generate an operation fingerprint, and write the hash value of the operation fingerprint into the blockchain network;

[0011] Step S3: Capture the console operation flow in real time and extract the current operation behavior features to generate a temporary verification fingerprint;

[0012] Step S4: By using a smart contract deployed on the blockchain, the temporary verification fingerprint is compared with the historical operation fingerprint stored on the chain.

[0013] Step S5: When the smart contract determines that the matching degree is lower than the dynamic threshold, the biometric-assisted verification process is initiated.

[0014] Step S6: After successful verification, a dynamic permission tag is generated. This tag includes the operator's digital identity, the range of operable devices, and the tag's validity period.

[0015] Step S7: Execute control instructions within the permission boundaries defined by the dynamic permission label.

[0016] As a preferred embodiment of the blockchain-based console identity recognition method described in this invention, in step S1, the physical operation action sequence is collected by a non-contact sensor, including gesture spatial trajectory features and knob rotation angular velocity sequence;

[0017] The graphical interface interaction logic sequence includes a multi-window collaborative operation event flow, which consists of window focus switching timing and cross-application data drag-and-drop paths.

[0018] As a preferred embodiment of the blockchain-based console identity recognition method of the present invention, in step S2, the blockchain network adopts a consortium blockchain architecture, and its consensus nodes include console terminals, cloud permission servers and audit terminals.

[0019] Operation fingerprint storage adopts a sharding strategy, with physical operation features sharded and stored on the console terminal node, and logical operation features sharded and stored on the cloud permission server node.

[0020] As a preferred embodiment of the blockchain-based console identity verification method described in this invention, wherein: in step S4, when the smart contract performs the comparison:

[0021] Retrieve the decryption key of the historical operation fingerprint;

[0022] Calculate a measure of the temporal difference between temporary verification fingerprints and historical operation fingerprints;

[0023] Step S5 is activated when the time sequence difference metric exceeds the adaptive threshold.

[0024] In a preferred embodiment of the blockchain-based console identity recognition method described in this invention, in step S4, the calculation method of the time-series difference measure is as follows:

[0025] {P h (t),G h (t)} and {P c (t),G c Linear interpolation of (t)} to a sampling frequency of 100Hz yields discrete sequences of lengths N and M, respectively.

[0026] Construct the local distance matrix:

[0027]

[0028] Among them, D i,j w represents the local distance between row index i and column index j. p P is a 2×2 diagonal matrix of physical feature weights. h (i) is the historical physics operation feature vector, P c (j) is the current physical operation feature vector, ||·||2 is the Euclidean norm, and w g G is a 2×2 diagonal matrix of graphic feature weights. h (i) represents the historical graphical interaction feature vector, G c (j) is the current graphical interaction feature vector, i∈[1,N], j∈[1,M];

[0029] Dynamic programming cumulative distance:

[0030] When i = j = 1, DTW(i,j) = D 1,1 ,

[0031] In other cases, DTW(i,j) = D i,j +min{DTW(i-1,j),DTW(i,j-1),DTW(i-1,j-1)},

[0032] Where DTW(i,j) are the elements of the cumulative distance matrix, D 1,1 Let `min{·}` be the initial local distance, and `min{·}` denotes the operation of selecting the minimum value.

[0033] Normalized variance measure:

[0034]

[0035] Where, Δ TSAs a measure of temporal difference, DTW(N,M) is the bottom right element of the cumulative distance, N is the length of the historical sequence, M is the length of the current sequence, exp(·) is the natural exponential function, α is the time mismatch amplification factor, |NM| is the difference in length between the two sequences, and max(N,M) is the larger of the two sequences.

[0036] Calculate adaptive weights:

[0037] w p =diag(k) s ,k r ),

[0038] w g =diag(k) f ,k d ),

[0039] Among them, w p Let k be the physical feature weight matrix, diag(·) be the diagonal matrix generator, and k be the weight matrix. s k represents the gesture trajectory weighting coefficient. r w is the knob angular velocity weighting coefficient. g Let k be the graphic feature weight matrix. f k is the window focus switching weight coefficient. d The weight coefficient for the data drag path.

[0040] In the formula:

[0041]

[0042] Where, k s ,k r ,k f ,k d σ represents the weight coefficients of each feature. s ,σ r ,σ f ,σ d These represent the historical variances of gesture trajectory, knob angular velocity, window focus switching, and data drag path, respectively; ∈ represents the fine-tuning constant; and is a predefined constant.

[0043] As a preferred embodiment of the blockchain-based console identity recognition method described in this invention, step S5 includes the following biometric-assisted verification process:

[0044] Biometric data is collected via the local security chip in the console.

[0045] Generate biometric zero-knowledge proofs in a trusted execution environment;

[0046] Submit zero-knowledge proofs to the blockchain for on-chain verification.

[0047] In a preferred embodiment of the blockchain-based console identity recognition method described in this invention, step S6, the generation of the dynamic permission tag includes:

[0048] Analyze the semantic intent of the current control command;

[0049] Map the device's operating range according to semantic operational intent;

[0050] The effective duration of the label is set based on the risk level of the instruction.

[0051] As a preferred embodiment of the blockchain-based console identity recognition method described in this invention, the semantic operation intent parsing adopts a pre-trained natural language processing model, and the input sources include voice command text and graphical interface operation logs.

[0052] The mapping of device operation scope is executed based on the device permission topology map stored in the blockchain.

[0053] As a preferred embodiment of the blockchain-based console identity recognition method described in this invention, the semantic operation intent parsing process in step S6 includes:

[0054] Perform dual-source word segmentation and embedding of instructions:

[0055]

[0056] in, Let E be the i-th initial embedding vector, and E be the size |V|×d. e The word vector lookup table matrix, τ i The terms are discrete word units resulting from the fusion of speech transcription and interface logs, where |V| is the vocabulary size, and d is the word set. e For the embedded dimension;

[0057] Perform context encoding:

[0058]

[0059] Where, r i For contextual representation, BiGRU(·) is a bidirectional gated cyclic update operator;

[0060] Calculate the global attention weights:

[0061]

[0062] Where, β i Let L be the attention weight of the i-th element, u be the trainable global query vector, and L be the weight of the i-th element. t The length of the lexical sequence is T, and T represents the transpose. d is the scaling factor. e For the embedded dimension;

[0063] Generate intent vector:

[0064]

[0065] Where v is the semantic intent vector of the current instruction;

[0066] The formula for calculating prototype similarity is:

[0067]

[0068] Among them, s k To operate the prototype p with the kth device k The cosine similarity, ||·|2 is the L2 norm, K is the total number of prototypes, p k This is the prototype vector for the operation of the k-th device.

[0069] Define the intention probability distribution as follows:

[0070]

[0071] Among them, P k Let λ be the probability of the k-th type of intent, and λ be the temperature scaling factor.

[0072] In the formula:

[0073]

[0074] Where λ is the temperature scaling factor, κ risk This is a baseline coefficient set according to the risk level of the instruction. The variance of similarity in the previous time period is denoted as , and ∈ is the fine-tuning constant.

[0075] Intent determination:

[0076]

[0077] Among them, I * The semantic operation intent label is determined.

[0078] As a preferred embodiment of the blockchain-based console identity verification method described in this invention, during the handover of operation permissions:

[0079] Predicting handover time points based on the decay trend of operational behavior feature matching degree;

[0080] Generate a draft of dynamic permission labels for the successor operator at the predicted time point;

[0081] The status of old and new permission tags is updated synchronously through the blockchain consensus mechanism.

[0082] The beneficial effects of this invention are as follows: By integrating behavioral feature modeling with blockchain technology, this invention achieves seamless and accurate console identity recognition. In multi-person shift scenarios, operators do not need to actively perform biometric verification actions. The system continuously captures physical operation actions (such as knob rotation trajectories) and graphical interaction logic (such as window switching paths), converting behavioral features into encrypted operation fingerprints and storing them on the blockchain. The blockchain smart contract compares the temporal differences between the current operation and historical fingerprints in real time, triggering biometric verification only when abnormal behavior occurs, significantly reducing operation interruptions caused by factors such as gloves and lighting in industrial environments.

[0083] The dynamic permission tag generation mechanism overcomes the limitations of static authorization. By parsing the semantic intent of control commands (such as the voice command "adjust the temperature in area A") and combining it with a pre-defined device permission topology, it automatically delineates the minimum operational scope of the devices and sets the tag validity period based on the command's risk level. This design completely eliminates the risk of confusion during permission handover, ensuring strict isolation of control domains for different operators and meeting the auditing requirements of high-security scenarios.

[0084] The permission handover process intelligently predicts behavior decay trends. Based on historical on-chain data, the system predicts the handover time, generates a draft of the successor's permissions in advance, and updates it synchronously via blockchain consensus, achieving a seamless switch between old and new permission states. This mechanism avoids the synchronization delays inherent in centralized identity providers while adapting to the rapid rotation needs in emergency scheduling scenarios.

[0085] This invention further enhances environmental adaptability. Non-contact sensors collect features such as gesture spatial trajectories, avoiding physical contact limitations; the adaptive weighting mechanism in the temporal difference measurement can suppress misjudgments caused by fluctuations in operational rhythm, improving robustness in complex industrial environments. The blockchain sharding storage strategy balances efficiency and security, with physical features stored on local terminal nodes and logical features stored on cloud nodes, ensuring controllability of sensitive data while supporting cross-terminal verification. Attached Figure Description

[0086] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0087] Figure 1 This is a flowchart illustrating the blockchain-based console identity recognition method in Example 1. Detailed Implementation

[0088] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0089] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0090] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0091] Example 1, referring to Figure 1 This embodiment provides a blockchain-based console identity verification method, including the following steps:

[0092] Step S1: Collect the operator's operational behavior characteristics through the console sensors. The operational behavior characteristics include physical operation action sequences and graphical interface interaction logic sequences.

[0093] In step S1, the sequence of physical operation actions is collected by non-contact sensors, including gesture spatial trajectory features and knob rotation angular velocity sequence;

[0094] The graphical user interface interaction logic sequence includes a multi-window collaborative operation event flow, which consists of the window focus switching sequence and cross-application data drag-and-drop path.

[0095] Step S2: Encrypt the operation behavior characteristics to generate an operation fingerprint, and write the hash value of the operation fingerprint into the blockchain network;

[0096] In step S2, the blockchain network adopts a consortium blockchain architecture, and its consensus nodes include a console terminal, a cloud permission server, and an audit terminal.

[0097] Operation fingerprint storage adopts a sharding strategy, with physical operation features sharded and stored on the console terminal node, and logical operation features sharded and stored on the cloud permission server node;

[0098] Step S3: Capture the console operation flow in real time and extract the current operation behavior features to generate a temporary verification fingerprint;

[0099] Step S4: By using a smart contract deployed on the blockchain, the temporary verification fingerprint is compared with the historical operation fingerprint stored on the chain.

[0100] In step S4, when the smart contract performs the comparison:

[0101] Retrieve the decryption key of the historical operation fingerprint;

[0102] Calculate a measure of the temporal difference between temporary verification fingerprints and historical operation fingerprints;

[0103] Step S5 is activated when the time-series difference measure exceeds the adaptive threshold.

[0104] In step S4, the time series difference metric is calculated as follows:

[0105] {P h (t),G h (t)} and {P c (t),G c Linear interpolation of (t)} to a sampling frequency of 100Hz yields discrete sequences of lengths N and M, respectively.

[0106] Construct the local distance matrix:

[0107]

[0108] Among them, D i,j w represents the local distance between row index i and column index j. p P is a 2×2 diagonal matrix of physical feature weights. h (i) is the historical physics operation feature vector, P c (j) is the current physical operation feature vector, ||·||2 is the Euclidean norm, and w g G is a 2×2 diagonal matrix of graphic feature weights. h (i) represents the historical graphical interaction feature vector, G c (j) is the current graphical interaction feature vector, i∈[1,N], j∈[1,M];

[0109] Dynamic programming cumulative distance:

[0110] When i = j = 1, DTW(i,j) = D 1,1 ,

[0111] In other cases, DTW(i,j) = D i,j +min{DTW(i-1,j),DTW(i,j-1),DTW(i-1,j-1)},

[0112] Where DTW(i,j) are the elements of the cumulative distance matrix, D 1,1 Let `min{·}` be the initial local distance, and `min{·}` denotes the operation of selecting the minimum value.

[0113] Normalized variance measure:

[0114]

[0115] Where, Δ TS As a measure of temporal difference, DTW(N,M) is the bottom right element of the cumulative distance, N is the length of the historical sequence, M is the length of the current sequence, exp(·) is the natural exponential function, α is the time mismatch amplification factor, |NM| is the difference in length between the two sequences, and max(N,M) is the larger of the two sequences.

[0116] Calculate adaptive weights:

[0117] w p =diag(k) s ,k r ),

[0118] w g =diag(k) f ,k d ),

[0119] Among them, w p Let k be the physical feature weight matrix, diag(·) be the diagonal matrix generator, and k be the weight matrix. s k represents the gesture trajectory weighting coefficient. r w is the knob angular velocity weighting coefficient. g Let k be the graphic feature weight matrix. f k is the window focus switching weight coefficient. d The weight coefficient for the data drag path.

[0120] In the formula:

[0121]

[0122] Where, k s ,k r ,k f ,k d σ represents the weight coefficients of each feature. s ,σ r ,σ f ,σ d These represent the historical variances of gesture trajectory, knob angular velocity, window focus switching, and data drag path, respectively, with ∈ being the fine-tuning constant 10. -6 ;

[0123] Specifically, the temporal difference measure maps heterogeneous operation trajectories to a unified time axis, suppresses unstable dimensions through variance-driven weights, and the exponential compensation term is sensitive to rhythmic abrupt changes, which can capture anomalies in real time and output stable scales, while maintaining tolerance for normal rhythms.

[0124] Step S5: When the smart contract determines that the matching degree is lower than the dynamic threshold, the biometric-assisted verification process is initiated.

[0125] In step S5, the biometric-assisted verification process includes:

[0126] Biometric data is collected via the local security chip in the console.

[0127] Generate biometric zero-knowledge proofs in a trusted execution environment;

[0128] Submit zero-knowledge proofs to the blockchain for on-chain verification;

[0129] Step S6: After successful verification, a dynamic permission tag is generated. This tag includes the operator's digital identity, the range of operable devices, and the tag's validity period.

[0130] In step S6, the generation of dynamic permission tags includes:

[0131] Analyze the semantic intent of the current control command;

[0132] Map the device's operating range according to semantic operational intent;

[0133] The effective duration of the label is set based on the risk level of the instruction.

[0134] Semantic operation intent parsing uses a pre-trained natural language processing model, with input sources including voice command text and graphical interface operation logs;

[0135] The mapping of device operation scope is executed based on the device permission topology map stored in the blockchain.

[0136] The semantic operation intent parsing process in step S6 includes:

[0137] Perform dual-source word segmentation and embedding of instructions:

[0138]

[0139] in, Let E be the i-th initial embedding vector, and E be the size |V|×d. e The word vector lookup table matrix, τ i The terms are discrete word units resulting from the fusion of speech transcription and interface logs, where |V| is the vocabulary size, and d is the word set. e For the embedded dimension;

[0140] Context encoding (bidirectional gated recurrent unit):

[0141]

[0142] Where, r i For contextual representation, BiGRU(·) is a bidirectional gated cyclic update operator;

[0143] Calculate the global attention weights:

[0144]

[0145] Where, β i Let L be the attention weight of the i-th element, u be the trainable global query vector, and L be the weight of the i-th element. t The length of the lexical sequence is T, and T represents the transpose. d is the scaling factor. e For the embedded dimension;

[0146] Generate intent vector:

[0147]

[0148] Where v is the semantic intent vector of the current instruction;

[0149] The formula for calculating prototype similarity is:

[0150]

[0151] Among them, s k To operate the prototype p with the kth device k The cosine similarity, ||·|2 is the L2 norm, K is the total number of prototypes, p k This is the prototype vector for the operation of the k-th device.

[0152] Define the intention probability distribution as follows:

[0153]

[0154] Among them, P k Let λ be the probability of the k-th type of intent, and λ be the temperature scaling factor.

[0155] In the formula:

[0156]

[0157] Where λ is the temperature scaling factor, κ risk This is a baseline coefficient set according to the risk level of the instruction. The variance of similarity in the previous time period is denoted as , and ∈ is the fine-tuning constant 10. -6 ;

[0158] Intent determination:

[0159]

[0160] Among them, I * The determined semantic operation intent label;

[0161] Specifically, the parsing process maps multi-source instructions to context vectors, then uses global attention to focus on keyword elements, weakening the influence of modifiers and filler items; the combination of cosine similarity and temperature scaling enables the model to output a sharper probability distribution in high-risk instruction scenarios, thus facilitating the subsequent permission generation module's interpretation.

[0162] Step S7: Execute control instructions within the permission boundaries defined by the dynamic permission label;

[0163] During the handover of operational permissions:

[0164] Predicting handover time points based on the decay trend of operational behavior feature matching degree;

[0165] Generate a draft of dynamic permission labels for the successor operator at the predicted time point;

[0166] The status of old and new permission tags is updated synchronously through the blockchain consensus mechanism.

[0167] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A blockchain-based console identity verification method, characterized in that, Includes the following steps: Step S1: Collect the operator's operational behavior characteristics through the console sensors. The operational behavior characteristics include physical operation action sequences and graphical interface interaction logic sequences. Step S2: Encrypt the operation behavior characteristics to generate an operation fingerprint, and write the hash value of the operation fingerprint into the blockchain network; Step S3: Capture the console operation flow in real time and extract the current operation behavior features to generate a temporary verification fingerprint; Step S4: Compare the temporary verification fingerprint with the historical operation fingerprint stored on the blockchain through a smart contract deployed on the blockchain. Step S5: When the smart contract determines that the matching degree is lower than the dynamic threshold, the biometric-assisted verification process is initiated. Step S6: After successful verification, a dynamic permission tag is generated. This tag includes the operator's digital identity, the range of operable devices, and the tag's validity period. Step S7: Execute control instructions within the permission boundaries defined by the dynamic permission label; In step S4, during the smart contract execution comparison, a timing difference metric is calculated. The timing difference metric is calculated as follows: Will and Linear interpolation to a 100Hz sampling frequency yields the lengths. and Discrete sequences; Construct the local distance matrix: ， in, Indicates row index With column index Local distance at that location for Physical feature weight diagonal matrix, This is the feature vector of historical physical operations. This is the current physical operation feature vector. It is the Euclidean norm. for Graphic feature weight diagonal matrix, For historical graphical interaction feature vectors, This is the current graphical interaction feature vector. , ; Dynamic programming cumulative distance: when , , Other situations , in, For the cumulative distance matrix elements, The initial local distance, This indicates the operation of selecting the minimum value; Normalized variance measure: ， in, As a measure of temporal difference, To accumulate distance to the bottom right element, The length of the historical sequence. The current sequence length. It is a natural exponential function. This is the duration mismatch amplification factor. The difference in length between the two sequences. The one with the larger length; Calculate adaptive weights: ， ， in, The physical feature weight matrix, To generate diagonal matrix operators, The gesture trajectory weighting coefficient, This is the knob angular velocity weighting coefficient. The graph feature weight matrix, This is the weighting coefficient for window focus switching. The weight coefficient for the data drag path. In the formula: ， ， ， ， in, These are the weight coefficients for each feature. These are the historical variances of gesture trajectory, knob angular velocity, window focus switching, and data drag path. These are fine-tuning constants, which are predefined constants; Step S6 includes parsing the semantic operational intent of the current control command. The parsing process includes: Perform dual-source word segmentation and embedding of instructions: ， in, For the first An initial embedding vector, For size The word vector lookup table matrix, These are discrete word units resulting from the fusion of speech transcription and interface logs. For vocabulary size, For the embedded dimension; Perform context encoding: ， in, For contextual representation, For bidirectional gated loop update operators; Calculate the global attention weights: ， in, For the first Each attention weight, This is a trainable global query vector. The length of the word sequence. Indicates transpose. Scaling factor For the embedded dimension; Generate intent vector: ， in, This is the semantic intent vector of the current instruction; The formula for calculating prototype similarity is: ， in, In order to be with the first Device operation prototype cosine similarity, It is a norm 2. The total number of prototypes. For the first Each device operation prototype vector; Define the intention probability distribution as follows: ， in, For the first Class intention probability, This is the temperature scaling factor; In the formula: ， in, This is the temperature scaling factor. This is a baseline coefficient set according to the risk level of the instruction. This represents the variance of similarity in the previous time period. This is the fine-tuning constant; Intent determination: ， in, The semantic operation intent label is determined.

2. The blockchain-based console identity verification method as described in claim 1, characterized in that, In step S1, the sequence of physical operation actions is acquired by a non-contact sensor, including gesture spatial trajectory features and knob rotation angular velocity sequence; The graphical interface interaction logic sequence includes a multi-window collaborative operation event flow, which consists of window focus switching timing and cross-application data drag-and-drop paths.

3. The blockchain-based console identity verification method as described in claim 1, characterized in that, In step S2, the blockchain network adopts a consortium blockchain architecture, and its consensus nodes include a console terminal, a cloud permission server, and an audit terminal. Operation fingerprint storage adopts a sharding strategy, with physical operation features sharded and stored on the console terminal node, and logical operation features sharded and stored on the cloud permission server node.

4. The blockchain-based console identity verification method as described in claim 1, characterized in that, In step S4, when the smart contract performs the comparison: Retrieve the decryption key of the historical operation fingerprint; Calculate a measure of the temporal difference between temporary verification fingerprints and historical operation fingerprints; Step S5 is activated when the time-series difference measure exceeds the adaptive threshold.

5. The blockchain-based console identity verification method as described in claim 1, characterized in that, In step S5, the biometric-assisted verification process includes: Biometric data is collected via the local security chip in the console. Generate biometric zero-knowledge proofs in a trusted execution environment; Submit zero-knowledge proofs to the blockchain for on-chain verification.

6. The blockchain-based console identity verification method as described in claim 1, characterized in that, In step S6, the generation of the dynamic permission tag includes: Analyze the semantic intent of the current control command; Map the device's operating range according to semantic operational intent; The effective duration of the label is set based on the risk level of the instruction.

7. The blockchain-based console identity recognition method as described in claim 1, characterized in that, The semantic operation intent parsing uses a pre-trained natural language processing model, and the input sources include voice command text and graphical interface operation logs. The mapping of device operation scope is executed based on the device permission topology map stored in the blockchain.

8. The blockchain-based console identity verification method as described in claim 1, characterized in that, During the handover of operational permissions: Predicting handover time points based on the decay trend of operational behavior feature matching degree; Generate a draft of dynamic permission labels for the successor operator at the predicted time point; The status of old and new permission tags is updated synchronously through the blockchain consensus mechanism.

Images