Supply chain authorization authentication method and device based on finger-pressing signature and medium

Abstract

The invention relates to the technical field of identity authentication, and relates to a supply chain authorization authentication method and device based on finger-pressing signature, and a medium, and the method comprises the steps: carrying out the data framing of finger-pressing signature data of a supply chain person, and obtaining a finger-pressing signature sequence; performing fingerprint extraction and definition screening on the finger pressure signature sequence to obtain a standard fingerprint image, and performing texture feature extraction on the standard fingerprint image to obtain finger pressure fingerprint features; performing force feature extraction and inter-frame feature extraction on the shiatsu signature sequence to obtain a shiatsu force feature; carrying out key point positioning and motion analysis operation on the shiatsu signature sequence to obtain shiatsu motion features; and performing feature screening fusion on the finger pressure fingerprint feature, the finger pressure degree feature and the finger pressure motion feature to obtain a standard finger pressure feature, and performing supply chain authorization authentication on the standard finger pressure feature by using a pre-acquired real finger pressure feature to obtain an authentication result. According to the invention, the accuracy of authorization authentication can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of identity authentication, and in particular to a supply chain authorization authentication method, device and medium based on finger pressure signature. Background Art

[0002] The supply chain finance platform is a financial service platform that aims to provide financing, settlement, risk management and other services to all participants in the supply chain to promote the smooth operation of the supply chain and the flow of funds. When authenticating and transferring electronic bond certificates on the supply chain finance platform, the managers of the supply chain finance platform and the owners of the bond certificates often need to authorize the operations.

[0003] Most existing real-name authentication methods are based on electronic signatures, that is, signing a name on an electronic document through a capacitive pen or other media to achieve authorization. However, in actual applications, the signatures of authentication methods based on electronic signatures have a certain possibility of forgery, and the security factor is not high, which may lead to low accuracy in supply chain authorization authentication. Summary of the invention

[0004] The present invention provides a supply chain authorization authentication method, device and medium based on finger pressure signature, the main purpose of which is to solve the problem of low accuracy when performing supply chain authorization authentication.

[0005] To achieve the above object, the present invention provides a supply chain authorization and authentication method based on finger pressure signature, comprising:

[0006] Using a preset pressure sensing electronic screen to obtain finger pressure signature data of supply chain personnel, performing data framing and format conversion on the finger pressure signature data to obtain a finger pressure signature sequence;

[0007] Performing fingerprint extraction and clarity screening on the finger pressure signature sequence to obtain a standard fingerprint image, and performing texture feature extraction on the standard fingerprint image to obtain a finger pressure fingerprint feature;

[0008] Extracting force features and performing inter-frame feature analysis on the finger pressure signature sequence to obtain finger pressure force features;

[0009] Performing key point positioning and motion analysis operations on the finger pressure signature sequence to obtain finger pressure motion features;

[0010] The finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature are subjected to feature screening and fusion to obtain a standard finger pressure feature, and the supply chain authorization authentication is performed on the standard finger pressure feature using the real finger pressure feature acquired in advance to obtain an authentication result.

[0011] Optionally, the step of performing data framing and format conversion on the finger pressure signature data to obtain a finger pressure signature sequence includes:

[0012] Performing element traversal analysis on the finger pressure signature data to obtain analyzed finger pressure data;

[0013] Performing time-series frame division on the analyzed finger pressure data to obtain a finger pressure data group sequence;

[0014] Selecting finger pressure data groups in the finger pressure data group sequence one by one as target finger pressure data groups, performing force coordinate mapping on the target finger pressure data groups, and obtaining a target finger pressure signature;

[0015] The target finger pressure signatures corresponding to all the target finger pressure data sets in the finger pressure data set sequence are collected into a finger pressure data set sequence.

[0016] Optionally, the extracting fingerprints and screening the clarity of the finger pressure signature sequence to obtain a standard fingerprint image includes:

[0017] Selecting finger pressure signatures in the finger pressure signature sequence one by one as target finger pressure signatures, performing gray value mapping on the target finger pressure signatures, and obtaining a target fingerprint image;

[0018] The image clarity of the target fingerprint image is calculated using the following image clarity quality formula:

[0019]

[0020] Wherein, T refers to the image definition, M is the pixel length of the target fingerprint image, N is the pixel width of the target fingerprint image, m is the pixel horizontal index, n is the pixel vertical index, r refers to the preset sampling frame length, G is the grayscale symbol, G (m,n) Refers to the grayscale value of the pixel with coordinate point (m,n) in the target fingerprint image;

[0021] Gathering the image clarity of all target finger pressure signatures in the finger pressure signature sequence into a clarity sequence;

[0022] Performing extreme value screening on the definition sequence to obtain standard definition;

[0023] The target fingerprint image corresponding to the standard definition is used as a standard fingerprint image.

[0024] Optionally, extracting texture features from the standard fingerprint image to obtain finger pressure fingerprint features includes:

[0025] Performing texture filtering on the standard fingerprint image to obtain global fingerprint features;

[0026] Evenly dividing the standard fingerprint image into blocks to obtain a fingerprint block group;

[0027] Extracting local binary features from the fingerprint block group to obtain binary local features;

[0028] Performing texture key point detection on the standard fingerprint image to obtain fingerprint key points;

[0029] Extracting a key local image from the fingerprint block group according to the fingerprint key point;

[0030] Performing texture filtering on the key local image to obtain local fingerprint features;

[0031] A fully connected fusion operation is performed on the global fingerprint feature, the binary local feature and the local fingerprint feature to obtain a finger pressure fingerprint feature.

[0032] Optionally, the extracting force features and performing inter-frame feature analysis on the finger pressure signature sequence to obtain the finger pressure force features includes:

[0033] Calculating the average pressure of the finger pressure signature sequence to obtain an average pressure feature sequence;

[0034] Performing extreme pressure screening on the finger pressure signature sequence to obtain an extreme pressure feature sequence;

[0035] Performing a multi-level downsampling operation on the finger pressure signature sequence to obtain a pressure distribution feature sequence;

[0036] Performing global pooling and full-connection fusion operations on the average pressure feature sequence, the extreme pressure feature sequence, and the pressure distribution feature sequence to obtain a multi-dimensional pressure feature sequence;

[0037] Inter-frame feature analysis is performed on the multi-dimensional pressure feature sequence to obtain the pressure intensity feature.

[0038] Optionally, performing inter-frame feature analysis on the multi-dimensional pressure feature sequence to obtain the pressure intensity feature includes:

[0039] Performing a time-series Fourier transform on the multi-dimensional pressure feature sequence to obtain a pressure sequence frequency domain;

[0040] Extracting frequency domain features of the pressure sequence in the frequency domain to obtain frequency domain pressure features;

[0041] Performing time series convolution on the multi-dimensional pressure feature sequence to obtain a time series pressure feature;

[0042] Performing self-attention feature encoding on the multi-dimensional pressure feature sequence to obtain an attention pressure feature;

[0043] The frequency domain pressure feature, the time series pressure feature and the attention pressure feature are globally pooled and fully connected to obtain a finger pressure intensity feature.

[0044] Optionally, performing key point positioning and motion analysis operations on the finger pressure signature sequence to obtain finger pressure motion features includes:

[0045] Selecting finger pressure signatures in the finger pressure signature sequence one by one as target finger pressure signatures, performing texture key point detection on the target finger pressure signature sequence to obtain target key points;

[0046] The target pressure center of gravity is calculated using the following pressure center of gravity formula to obtain the target pressure center of gravity;

[0047]

[0048] Wherein, x is the horizontal coordinate of the target pressure center of gravity, y is the vertical coordinate of the target pressure center of gravity, a is the horizontal index of the pixel, b is the vertical index of the pixel, A is the length of the target finger pressure signature, B is the width of the target finger pressure signature, P (a,b) is the force value at the position with coordinates (a, b) in the target finger pressure signature;

[0049] Collecting the target key points of all target finger pressure signatures in the finger pressure signature sequence into a key point sequence, and collecting the target pressure gravity centers of all target finger pressure signatures in the finger pressure signature sequence into a pressure gravity center sequence;

[0050] Performing trajectory fitting and motion feature extraction on the key point sequence to obtain key point motion features;

[0051] Performing trajectory fitting and motion feature extraction on the pressure center of gravity sequence to obtain the center of gravity point motion features;

[0052] A feature fusion operation is performed on the key point motion feature and the center of gravity point motion feature to obtain a finger pressure motion feature.

[0053] Optionally, the performing feature screening and fusion on the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature to obtain a standard finger pressure feature includes:

[0054] Performing mean normalization and matrix operations on the finger pressure fingerprint features to obtain a fingerprint feature matrix;

[0055] Performing mean normalization and matrix operations on the finger pressure force characteristics to obtain a force feature matrix;

[0056] Performing mean normalization and matrix operations on the finger pressure motion features to obtain a motion feature matrix;

[0057] Perform matrix concatenation and covariance matrix calculation on the fingerprint feature matrix, the force feature matrix, and the motion feature matrix to obtain a finger pressure covariance matrix;

[0058] Performing eigenvalue decomposition on the finger pressure covariance matrix to obtain a finger pressure eigenvector group and a finger pressure eigenvalue group;

[0059] Performing principal component screening on the finger pressure feature vector group according to the finger pressure feature value group to obtain a screened finger pressure feature vector group;

[0060] The screened finger pressure feature vector group is subjected to dimensionality reduction projection to obtain standard finger pressure features.

[0061] Optionally, the using of the pre-acquired real acupressure feature to perform supply chain authorization authentication on the standard acupressure feature to obtain an authentication result includes:

[0062] Calculating the characteristic distance between the real finger pressure feature and the standard finger pressure feature by using a cosine distance algorithm;

[0063] Determining whether the characteristic distance is less than a preset distance threshold;

[0064] If so, determining that authentication is successful is the authentication result;

[0065] If not, authentication failure is determined as the authentication result.

[0066] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein:

[0067] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned supply chain authorization and authentication method based on finger pressure signature.

[0068] In order to solve the above problem, the present invention also provides a computer-readable storage medium storing a computer program, which implements the above supply chain authorization and authentication method based on finger pressure signature when executed by a processor.

[0069] The embodiment of the present invention can display the finger pressure signature data in a graphical manner by performing data framing and format conversion on the finger pressure signature data, thereby facilitating authentication analysis of the finger pressure signature data using machine vision technology; by performing fingerprint extraction and clarity screening on the finger pressure signature sequence, the details of texture features can be improved; by performing texture feature extraction on the standard fingerprint image, the texture features of the fingerprint can be extracted in layers and grades, thereby extracting the detail features of the finger pressure fingerprint features; by performing force feature extraction and inter-frame feature analysis on the finger pressure signature sequence, the features of the relationship between the force of the finger pressure signature data and time can be extracted, thereby extracting the user's force habits when signing with finger pressure.

[0070] By performing key point positioning and motion analysis operations on the finger pressure signature sequence, the motion state of the user when performing finger pressure signature can be feature extracted by combining the position change relationship of the pressure center of gravity and the position change relationship of the fingerprint control key point. By performing feature screening and fusion and authorization authentication on the finger pressure fingerprint feature, the finger pressure force feature and the finger pressure motion feature, key features of the various features of the finger pressure signature data can be screened out for fusion, thereby improving the accuracy of authorization authentication. Therefore, the supply chain authorization authentication method, device and medium based on finger pressure signature proposed by the present invention can solve the problem of low accuracy when performing supply chain authorization authentication. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A schematic diagram of a flow chart of a supply chain authorization and authentication method based on finger pressure signature provided in one embodiment of the present invention;

[0072] Figure 2 A schematic diagram of a process for extracting a finger pressure signature sequence according to an embodiment of the present invention;

[0073] Figure 3 A schematic diagram of a process for extracting finger pressure characteristics according to an embodiment of the present invention;

[0074] Figure 4 A functional module diagram of a supply chain authorization and authentication system based on finger pressure signature provided by an embodiment of the present invention;

[0075] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0076] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0077] The embodiment of the present application provides a supply chain authorization and authentication method based on finger pressure signature. The execution subject of the supply chain authorization and authentication method based on finger pressure signature includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the supply chain authorization and authentication method based on finger pressure signature can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0078] Reference Figure 1 FIG. 1 is a flow chart of a supply chain authorization and authentication method based on finger pressure signature provided by an embodiment of the present invention. In this embodiment, the supply chain authorization and authentication method based on finger pressure signature includes:

[0079] S1. Using a preset pressure sensing electronic screen to obtain finger pressure signature data of supply chain personnel, performing data framing and format conversion on the finger pressure signature data to obtain a finger pressure signature sequence.

[0080] Specifically, the supply chain personnel refers to the supply chain platform management personnel. When performing operations such as authentication and transfer of electronic bond certificates of the supply chain platform, the operations need to be authorized by the management personnel of the supply chain platform. The finger pressure signature data is the fingerprint pressure data for the authorization process.

[0081] In detail, the pressure sensing electronic screen is an electronic display screen with a built-in pressure sensor, which can detect the amount of pressure applied by the user to various locations on the screen. It can detect the user's touch pressure through the built-in pressure sensor and convert this information into digital signals.

[0082] In the embodiment of the present invention, each finger pressure signature in the finger pressure signature sequence is the signature data of each frame in the finger pressure signature data, and the signature data records information such as the position and pressure of the finger on the pressure sensing electronic screen.

[0083] In the embodiment of the present invention, referring to Figure 2 As shown, the finger pressure signature data is framed and format converted to obtain a finger pressure signature sequence, including:

[0084] S21, performing element traversal analysis on the finger pressure signature data to obtain analyzed finger pressure data;

[0085] S22, performing time-series frame division on the analyzed finger pressure data to obtain a finger pressure data group sequence;

[0086] S23, selecting the finger pressure data groups in the finger pressure data group sequence one by one as the target finger pressure data group, performing force coordinate mapping on the target finger pressure data group, and obtaining the target finger pressure signature;

[0087] S24, collecting the target finger pressure signatures corresponding to all the target finger pressure data sets in the finger pressure data set sequence into a finger pressure data set sequence.

[0088] In detail, the element traversal parsing refers to parsing each data element in the finger pressure signature data in a traversal manner, for example, using the xml.etree.ElementTree method, and the time series framing refers to grouping according to the timestamps of each data in the parsed finger pressure data, grouping the parsed finger pressure data with the same timestamp into a finger pressure data group, and arranging all the finger pressure data groups into a finger pressure data group sequence in time series order.

[0089] Specifically, the force coordinate mapping refers to mapping each acupressure data in the target acupressure data group according to the coordinate position to obtain a force map, and using the force map mapped by all the acupressure data in the target acupressure data group as the target acupressure signature.

[0090] In the embodiment of the present invention, by performing data framing and format conversion on the finger pressure signature data, the finger pressure signature data can be displayed graphically, thereby facilitating authentication analysis of the finger pressure signature data using machine vision technology.

[0091] S2. Perform fingerprint extraction and clarity screening on the finger pressure signature sequence to obtain a standard fingerprint image, and perform texture feature extraction on the standard fingerprint image to obtain a finger pressure fingerprint feature.

[0092] In detail, the standard fingerprint image refers to the fingerprint image with the highest definition in the finger pressure signature sequence. By screening the definition of the standard fingerprint image, the accuracy of fingerprint texture feature matching can be improved.

[0093] In the embodiment of the present invention, the step of extracting fingerprints and screening the finger pressure signature sequence for clarity to obtain a standard fingerprint image includes:

[0094] Selecting finger pressure signatures in the finger pressure signature sequence one by one as target finger pressure signatures, performing gray value mapping on the target finger pressure signatures, and obtaining a target fingerprint image;

[0095] The image clarity of the target fingerprint image is calculated using the following image clarity quality formula:

[0096]

[0097] Wherein, T refers to the image definition, M is the pixel length of the target fingerprint image, N is the pixel width of the target fingerprint image, m is the pixel horizontal index, n is the pixel vertical index, r refers to the preset sampling frame length, G is the grayscale symbol, G (m,n) Refers to the grayscale value of the pixel with coordinate point (m,n) in the target fingerprint image;

[0098] Aggregating the image clarity of all target finger pressure signatures in the finger pressure signature sequence into a clarity sequence;

[0099] Performing extreme value screening on the definition sequence to obtain standard definition;

[0100] The target fingerprint image corresponding to the standard definition is used as a standard fingerprint image.

[0101] In detail, the grayscale value mapping refers to mapping the force value of each coordinate in the target finger pressure signature to a preset grayscale interval to obtain a grayscale image. The image clarity of the target fingerprint image is calculated by using the image clarity quality formula. The overall clarity of the target fingerprint image can be judged according to the amplitude value of the grayscale change in each area of ​​the target fingerprint image, thereby improving the accuracy of the clarity calculation.

[0102] In detail, the step of extracting texture features from the standard fingerprint image to obtain the finger pressure fingerprint features includes:

[0103] Performing texture filtering on the standard fingerprint image to obtain global fingerprint features;

[0104] Evenly dividing the standard fingerprint image into blocks to obtain a fingerprint block group;

[0105] Extracting local binary features from the fingerprint block group to obtain binary local features;

[0106] Performing texture key point detection on the standard fingerprint image to obtain fingerprint key points;

[0107] Extracting a key local image from the fingerprint block group according to the fingerprint key point;

[0108] Performing texture filtering on the key local image to obtain local fingerprint features;

[0109] A fully connected fusion operation is performed on the global fingerprint feature, the binary local feature and the local fingerprint feature to obtain a finger pressure fingerprint feature.

[0110] In detail, the texture filtering refers to filtering the standard fingerprint image using a directional texture filter or a frequency texture filter, and the uniform blocking refers to blocking the annotated fingerprint-resistant image according to a preset size.

[0111] Specifically, the local binary feature extraction refers to extracting the features corresponding to the fingerprint block group using the local binary pattern (Local Binary Patterns, LBP for short) method, the texture key point detection method can be SIFT algorithm or SURF algorithm, and the key local image refers to the fingerprint block in the fingerprint block group that contains the fingerprint key point.

[0112] In the embodiment of the present invention, by performing fingerprint extraction and clarity screening on the finger pressure signature sequence, the details of the texture features can be improved, and by performing texture feature extraction on the standard fingerprint image, the texture features of the fingerprint can be extracted in layers and grades, thereby extracting the detailed features of the finger pressure fingerprint features, thereby improving the accuracy of fingerprint comparison.

[0113] S3, extracting force features and performing inter-frame feature analysis on the finger pressure signature sequence to obtain finger pressure force features.

[0114] In detail, the finger pressure force feature is a dynamic feature that reflects the relationship between the force feature corresponding to the finger pressure signature sequence and time changes.

[0115] In the embodiment of the present invention, referring to Figure 3 As shown, the force feature extraction and inter-frame feature analysis of the finger pressure signature sequence are performed to obtain the finger pressure force feature, including:

[0116] S31, calculating the average pressure of the finger pressure signature sequence to obtain an average pressure feature sequence;

[0117] S32, performing extreme pressure screening on the finger pressure signature sequence to obtain an extreme pressure feature sequence;

[0118] S33, performing a multi-level downsampling operation on the finger pressure signature sequence to obtain a pressure distribution feature sequence;

[0119] S34, performing global pooling and full-connection fusion operations on the average pressure feature sequence, the extreme pressure feature sequence, and the pressure distribution feature sequence to obtain a multi-dimensional pressure feature sequence;

[0120] S35, performing inter-frame feature analysis on the multi-dimensional pressure feature sequence to obtain pressure intensity features.

[0121] In detail, the average pressure calculation refers to calculating the average of the pressure strengths at different positions in each finger pressure signature in the finger pressure signature sequence, and the extreme pressure screening refers to screening out the maximum value of the pressure in each finger pressure signature.

[0122] In detail, the inter-frame feature analysis of the multi-dimensional pressure feature sequence to obtain the pressure intensity feature includes:

[0123] Performing a time-series Fourier transform on the multi-dimensional pressure feature sequence to obtain a pressure sequence frequency domain;

[0124] Extracting frequency domain features of the pressure sequence in the frequency domain to obtain frequency domain pressure features;

[0125] Performing time series convolution on the multi-dimensional pressure feature sequence to obtain a time series pressure feature;

[0126] Performing self-attention feature encoding on the multi-dimensional pressure feature sequence to obtain an attention pressure feature;

[0127] The frequency domain pressure feature, the time series pressure feature and the attention pressure feature are globally pooled and fully connected to obtain a finger pressure intensity feature.

[0128] In detail, the frequency domain feature extraction refers to extracting the spectral energy, main frequency distribution, frequency center and frequency bandwidth of the pressure sequence frequency domain, and the time series convolution refers to extracting features of the multidimensional pressure feature sequence using a cyclic time series neural network.

[0129] In an embodiment of the present invention, by performing force feature extraction and inter-frame feature analysis on the finger pressure signature sequence, the characteristics of the relationship between the force of the finger pressure signature data and time can be extracted, thereby extracting the user's force habits when signing with finger pressure, and improving the accuracy of authorization authentication.

[0130] S4. Perform key point positioning and motion analysis operations on the finger pressure signature sequence to obtain finger pressure motion features.

[0131] In detail, the finger pressure motion feature is a feature related to the motion direction and motion speed of the user when performing finger pressure signing.

[0132] In the embodiment of the present invention, the key point positioning and motion analysis operations are performed on the finger pressure signature sequence to obtain the finger pressure motion features, including:

[0133] Selecting finger pressure signatures in the finger pressure signature sequence one by one as target finger pressure signatures, performing texture key point detection on the target finger pressure signature sequence to obtain target key points;

[0134] The target pressure center of gravity is calculated using the following pressure center of gravity formula to obtain the target pressure center of gravity;

[0135]

[0136] Wherein, x is the horizontal coordinate of the target pressure center of gravity, y is the vertical coordinate of the target pressure center of gravity, a is the horizontal index of the pixel, b is the vertical index of the pixel, A is the length of the target finger pressure signature, B is the width of the target finger pressure signature, P (a,b) is the force value at the position with coordinates (a, b) in the target finger pressure signature;

[0137] Collecting the target key points of all target finger pressure signatures in the finger pressure signature sequence into a key point sequence, and collecting the target pressure gravity centers of all target finger pressure signatures in the finger pressure signature sequence into a pressure gravity center sequence;

[0138] Performing trajectory fitting and motion feature extraction on the key point sequence to obtain key point motion features;

[0139] Performing trajectory fitting and motion feature extraction on the pressure center of gravity sequence to obtain the center of gravity point motion features;

[0140] A feature fusion operation is performed on the key point motion feature and the center of gravity point motion feature to obtain a finger pressure motion feature.

[0141] In detail, the pressure center of gravity formula can calculate the center of gravity of pressure according to each finger pressure signature with the pressure intensity and distribution position, thereby providing a more accurate relationship of pressure changes.

[0142] Specifically, the trajectory fitting method can be a polynomial fitting method or a spline curve fitting method, and the motion feature extraction refers to calculating the speed and acceleration and other features of the key point sequence and the pressure center of gravity sequence, and performing feature fusion on the speed and acceleration features and the curve obtained by trajectory fitting.

[0143] In an embodiment of the present invention, by performing key point positioning and motion analysis operations on the finger pressure signature sequence, the motion state of the user when performing finger pressure signing can be feature extracted in combination with the position change relationship of the pressure center of gravity and the position change relationship of the fingerprint control key points, thereby improving the accuracy of subsequent authorization authentication.

[0144] S5. Perform feature screening and fusion on the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature to obtain a standard finger pressure feature, and use the real finger pressure feature obtained in advance to perform supply chain authorization authentication on the standard finger pressure feature to obtain an authentication result.

[0145] In the embodiment of the present invention, the feature screening and fusion of the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature to obtain the standard finger pressure feature includes:

[0146] Performing mean normalization and matrix operations on the finger pressure fingerprint features to obtain a fingerprint feature matrix;

[0147] Performing mean normalization and matrix operations on the finger pressure force characteristics to obtain a force feature matrix;

[0148] Performing mean normalization and matrix operations on the finger pressure motion features to obtain a motion feature matrix;

[0149] Perform matrix concatenation and covariance matrix calculation on the fingerprint feature matrix, the force feature matrix, and the motion feature matrix to obtain a finger pressure covariance matrix;

[0150] Performing eigenvalue decomposition on the finger pressure covariance matrix to obtain a finger pressure eigenvector group and a finger pressure eigenvalue group;

[0151] Performing principal component screening on the finger pressure feature vector group according to the finger pressure feature value group to obtain a screened finger pressure feature vector group;

[0152] The screened finger pressure feature vector group is subjected to dimensionality reduction projection to obtain standard finger pressure features.

[0153] In detail, the mean normalization refers to the mean of each characteristic element in the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure motion feature being zero and the standard deviation being one. The mean normalization can be performed using the Z-score normalization method or the Min-Max normalization method. The matrix operation refers to constructing a characteristic matrix using each characteristic element as a matrix element.

[0154] Specifically, the principal component screening refers to selecting the finger pressure feature vectors corresponding to several finger pressure feature values ​​with larger values ​​in the finger pressure feature value group as the screening finger pressure feature vectors to form the screening finger pressure feature vector group, and the dimensionality reduction projection method refers to multiplying the feature matrix formed by the screening finger pressure feature vector group by the fingerprint feature matrix, the force feature matrix and the motion feature matrix to obtain the feature matrix after matrix splicing.

[0155] Specifically, the real finger pressure feature refers to the finger pressure signature data of a real person that is input in advance and processed using the same processing method as the standard finger pressure feature.

[0156] In detail, the use of the pre-acquired real finger pressure feature to perform supply chain authorization authentication on the standard finger pressure feature to obtain the authentication result includes:

[0157] Calculating the characteristic distance between the real finger pressure feature and the standard finger pressure feature by using a cosine distance algorithm;

[0158] Determining whether the characteristic distance is less than a preset distance threshold;

[0159] If so, determining that authentication is successful is the authentication result;

[0160] If not, authentication failure is determined as the authentication result.

[0161] In detail, the successful authentication refers to determining that the finger pressure signature data corresponding to the standard finger pressure feature is the authentic signature data of the manager, that is, determining that the identity of the supply chain personnel is authentic; the failed authentication refers to determining that the finger pressure signature data corresponding to the standard finger pressure feature is not the authentic signature data of the manager, that is, determining that the identity of the supply chain personnel is false.

[0162] In the embodiment of the present invention, by performing feature screening and fusion as well as authorization authentication on the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature, key features of the various features of the finger pressure signature data can be screened out for fusion, thereby improving the accuracy of authorization authentication.

[0163] The embodiment of the present invention can display the finger pressure signature data in a graphical manner by performing data framing and format conversion on the finger pressure signature data, thereby facilitating authentication analysis of the finger pressure signature data using machine vision technology; by performing fingerprint extraction and clarity screening on the finger pressure signature sequence, the details of texture features can be improved; by performing texture feature extraction on the standard fingerprint image, the texture features of the fingerprint can be extracted in layers and grades, thereby extracting the detail features of the finger pressure fingerprint features; by performing force feature extraction and inter-frame feature analysis on the finger pressure signature sequence, the features of the relationship between the force of the finger pressure signature data and time can be extracted, thereby extracting the user's force habits when signing with finger pressure.

[0164] By performing key point positioning and motion analysis operations on the finger pressure signature sequence, the motion state of the user when performing finger pressure signature can be feature extracted by combining the position change relationship of the pressure center of gravity and the position change relationship of the fingerprint control key point. By performing feature screening and fusion and authorization authentication on the finger pressure fingerprint feature, the finger pressure force feature and the finger pressure motion feature, key features of the various features of the finger pressure signature data can be screened out for fusion, thereby improving the accuracy of authorization authentication. Therefore, the supply chain authorization authentication method based on finger pressure signature proposed by the present invention can solve the problem of low accuracy when performing supply chain authorization authentication.

[0165] like Figure 4, which is a functional module diagram of a supply chain authorization and authentication system based on finger pressure signature provided by an embodiment of the present invention.

[0166] The supply chain authorization and authentication system 100 based on finger pressure signature of the present invention can be installed in an electronic device. According to the functions to be implemented, the supply chain authorization and authentication system 100 based on finger pressure signature can include a format conversion module 101, a texture extraction module 102, a force extraction module 103, a motion extraction module 104 and an authorization and authentication module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, which are stored in the memory of the electronic device.

[0167] In this embodiment, the functions of each module / unit are as follows:

[0168] The format conversion module 101 is used to obtain finger pressure signature data of supply chain personnel using a preset pressure sensing electronic screen, perform data framing and format conversion on the finger pressure signature data, and obtain a finger pressure signature sequence;

[0169] The texture extraction module 102 is used to perform fingerprint extraction and clarity screening on the finger pressure signature sequence to obtain a standard fingerprint image, and perform texture feature extraction on the standard fingerprint image to obtain a finger pressure fingerprint feature;

[0170] The force extraction module 103 is used to extract force features and perform inter-frame feature analysis on the finger pressure signature sequence to obtain finger pressure force features;

[0171] The motion extraction module 104 is used to perform key point positioning and motion analysis operations on the finger pressure signature sequence to obtain finger pressure motion features;

[0172] The authorization authentication module 105 is used to perform feature screening and fusion on the finger pressure fingerprint feature, the finger pressure strength feature and the finger pressure movement feature to obtain a standard finger pressure feature, and use the pre-acquired real finger pressure feature to perform supply chain authorization authentication on the standard finger pressure feature to obtain an authentication result.

[0173] In detail, each module described in the supply chain authorization and authentication system 100 based on finger pressure signature in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The supply chain authorization and authentication method based on finger pressure signature described in the present invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0174] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0175] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0177] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0178] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0179] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system embodiment can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A supply chain authorization and authentication method based on finger pressure signature, characterized in that: The method comprises: Using a preset pressure sensing electronic screen to obtain finger pressure signature data of supply chain personnel, performing data framing and format conversion on the finger pressure signature data to obtain a finger pressure signature sequence; Performing fingerprint extraction and clarity screening on the finger pressure signature sequence to obtain a standard fingerprint image, and performing texture feature extraction on the standard fingerprint image to obtain a finger pressure fingerprint feature; Extracting force features and performing inter-frame feature analysis on the finger pressure signature sequence to obtain finger pressure force features; Performing key point positioning and motion analysis operations on the finger pressure signature sequence to obtain finger pressure motion features; The finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure movement feature are subjected to feature screening and fusion to obtain a standard finger pressure feature, and the supply chain authorization authentication is performed on the standard finger pressure feature using the real finger pressure feature acquired in advance to obtain an authentication result.

2. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The step of performing data framing and format conversion on the finger pressure signature data to obtain a finger pressure signature sequence includes: Performing element traversal analysis on the finger pressure signature data to obtain analyzed finger pressure data; Performing time-series frame division on the analyzed finger pressure data to obtain a finger pressure data group sequence; Selecting finger pressure data groups in the finger pressure data group sequence one by one as target finger pressure data groups, performing force coordinate mapping on the target finger pressure data groups, and obtaining a target finger pressure signature; The target finger pressure signatures corresponding to all the target finger pressure data sets in the finger pressure data set sequence are collected into a finger pressure data set sequence.

3. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The step of extracting texture features from the standard fingerprint image to obtain finger pressure fingerprint features includes: Performing texture filtering on the standard fingerprint image to obtain global fingerprint features; Evenly dividing the standard fingerprint image into blocks to obtain a fingerprint block group; Extracting local binary features from the fingerprint block group to obtain binary local features; Performing texture key point detection on the standard fingerprint image to obtain fingerprint key points; Extracting a key local image from the fingerprint block group according to the fingerprint key point; Performing texture filtering on the key local image to obtain local fingerprint features; A fully connected fusion operation is performed on the global fingerprint feature, the binary local feature and the local fingerprint feature to obtain a finger pressure fingerprint feature.

4. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The extracting force features and performing inter-frame feature analysis on the finger pressure signature sequence to obtain the finger pressure force features includes: Calculating the average pressure of the finger pressure signature sequence to obtain an average pressure feature sequence; Performing extreme pressure screening on the finger pressure signature sequence to obtain an extreme pressure feature sequence; Performing a multi-level downsampling operation on the finger pressure signature sequence to obtain a pressure distribution feature sequence; Performing global pooling and full-connection fusion operations on the average pressure feature sequence, the extreme pressure feature sequence, and the pressure distribution feature sequence to obtain a multi-dimensional pressure feature sequence; Inter-frame feature analysis is performed on the multi-dimensional pressure feature sequence to obtain the pressure intensity feature.

5. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 4, characterized in that: The performing inter-frame feature analysis on the multi-dimensional pressure feature sequence to obtain the pressure intensity feature includes: Performing a time-series Fourier transform on the multi-dimensional pressure feature sequence to obtain a pressure sequence frequency domain; Extracting frequency domain features of the pressure sequence in the frequency domain to obtain frequency domain pressure features; Performing time series convolution on the multi-dimensional pressure feature sequence to obtain a time series pressure feature; Performing self-attention feature encoding on the multi-dimensional pressure feature sequence to obtain an attention pressure feature; The frequency domain pressure feature, the time series pressure feature and the attention pressure feature are globally pooled and fully connected to obtain a finger pressure intensity feature.

6. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The key point positioning and motion analysis operations are performed on the finger pressure signature sequence to obtain the finger pressure motion features, including: Selecting finger pressure signatures in the finger pressure signature sequence one by one as target finger pressure signatures, performing texture key point detection on the target finger pressure signature sequence to obtain target key points; The target pressure center of gravity is calculated using the following pressure center of gravity formula to obtain the target pressure center of gravity; Wherein, x is the horizontal coordinate of the target pressure center of gravity, y is the vertical coordinate of the target pressure center of gravity, a is the horizontal index of the pixel, b is the vertical index of the pixel, A is the length of the target finger pressure signature, B is the width of the target finger pressure signature, P (a,b) is the force value at the position with coordinates (a, b) in the target finger pressure signature; Collecting the target key points of all target finger pressure signatures in the finger pressure signature sequence into a key point sequence, and collecting the target pressure gravity centers of all target finger pressure signatures in the finger pressure signature sequence into a pressure gravity center sequence; Performing trajectory fitting and motion feature extraction on the key point sequence to obtain key point motion features; Performing trajectory fitting and motion feature extraction on the pressure center of gravity sequence to obtain the center of gravity point motion features; A feature fusion operation is performed on the key point motion feature and the center of gravity point motion feature to obtain a finger pressure motion feature.

7. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The step of performing feature screening and fusion on the finger pressure fingerprint feature, the finger pressure intensity feature and the finger pressure motion feature to obtain a standard finger pressure feature includes: Performing mean normalization and matrix operations on the finger pressure fingerprint features to obtain a fingerprint feature matrix; Performing mean normalization and matrix operations on the finger pressure force characteristics to obtain a force feature matrix; Performing mean normalization and matrix operations on the finger pressure motion features to obtain a motion feature matrix; Perform matrix concatenation and covariance matrix calculation on the fingerprint feature matrix, the force feature matrix, and the motion feature matrix to obtain a finger pressure covariance matrix; Performing eigenvalue decomposition on the finger pressure covariance matrix to obtain a finger pressure eigenvector group and a finger pressure eigenvalue group; Performing principal component screening on the finger pressure feature vector group according to the finger pressure feature value group to obtain a screened finger pressure feature vector group; The screened finger pressure feature vector group is subjected to dimensionality reduction projection to obtain standard finger pressure features.

8. The supply chain authorization and authentication method based on finger pressure signature as claimed in claim 1, characterized in that: The method of using the real finger pressure feature acquired in advance to perform supply chain authorization authentication on the standard finger pressure feature to obtain the authentication result includes: Calculating the characteristic distance between the real finger pressure feature and the standard finger pressure feature by using a cosine distance algorithm; Determining whether the characteristic distance is less than a preset distance threshold; If so, determining that authentication is successful is the authentication result; If not, authentication failure is determined as the authentication result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the supply chain authorization and authentication method based on finger pressure signature as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the supply chain authorization and authentication method based on finger pressure signature as claimed in any one of claims 1 to 8 is implemented.

Images