Intelligent self-service card issuing digital terminal and terminal card issuing machine system thereof

Abstract

The invention discloses an intelligent self-service card issuing digital terminal and a terminal card issuing machine system thereof, the intelligent self-service card issuing digital terminal comprises a background cloud computing center, the background cloud computing center is in communication connection with a terminal card issuing machine and a payment machine through a communication module, and the terminal card issuing machine and the payment machine are both electrically connected with a screen display unit; a terminal card sender system comprises a control module, the control module is electrically connected with a data processor, the data processor is in communication connection with an information database through a communication module, and the control module is electrically connected with a function management unit, a data storage unit, a calculation model unit and a voltage regulation module. And the data processor is electrically connected with a data encryption unit. According to the intelligent self-service card issuing digital terminal, self-service card issuing and payment are adopted, and the terminal is provided with a visual intercom; when a problem is encountered, a key is pressed to communicate with background customer service; the defects that efficiency is low and a large amount of labor is occupied are overcome, data query of a highway system is facilitated, and data information is encrypted.

Description

Technical Field

[0001] The present invention relates to the technical field of self-service terminals, and in particular to an intelligent self-service card issuing digital terminal and a terminal card issuing machine system thereof. Background Art

[0002] With the intelligent upgrade of toll stations, unmanned intelligent self-service card issuing terminals are gradually being used more widely.

[0003] For example, the Chinese patent with the authorization announcement number CN107274501A discloses a self-service payment and card collection machine, which includes a device housing and an operation panel, a self-service payment module, a self-service card issuance module, an alarm and help module, and a core control module. The core control module receives information from the self-service payment module, the self-service card issuance module, and the alarm and help module in real time and uploads it to the industrial computer. At the same time, it transmits the instructions issued by the host computer to the self-service payment module, the self-service card issuance module, and the alarm and help module to coordinate the normal operation of the entire device and ensure the continuity of the payment and card issuance process. The invention connects two different payment software operating systems in series through a core controller, and can ensure the information security of each charging software. It effectively integrates the advantages of self-service payment machines and card issuance machines in real applications.

[0004] Another example is the Chinese patent with the existing publication number CN206178891U, which discloses an intelligent and fast card issuing system for a high-speed entrance, including a first capture coil, a second capture coil, a first card issuing coil and a second card issuing coil which are sequentially arranged on the lane and connected to the controller, and also includes a capture machine, a self-service card swiping machine and a card issuing module which are sequentially separately arranged on the safety island and connected to the controller. The self-service card swiping machine is provided with an OBU reader / writer identifier and an ETC card swiping panel which are both connected to the controller, and the card issuing module is an automatic card issuing machine and / or a manual card swiping kiosk; the self-service card swiping machine is also provided with an indicator light and a voice prompt system which are connected to the controller.

[0005] The above-mentioned patents have some advantages, but also some disadvantages, such as: it is impossible to conduct question-and-answer training for toll collection services, it is impossible to provide dynamic demonstrations, the user experience is poor, and it is not convenient to integrate information of the entire highway system and it is not convenient to encrypt and manage data information. Summary of the invention

[0006] In view of the problems mentioned in the background technology, the purpose of the present invention is to provide an intelligent self-service card issuance digital terminal and a terminal card issuance machine system thereof to solve the problems mentioned in the background technology.

[0007] The above technical objectives of the present invention are achieved through the following technical solutions:

[0008] An intelligent self-service card issuance digital terminal includes a background cloud computing center, which uses a GPT large model to train common problems in charging services. The background cloud computing center is connected to a terminal card issuing machine and a payment machine through a communication module. The terminal card issuing machine and the payment machine are electrically connected to a screen display unit for displaying an AI digital person. When a user presses an intercom button through the terminal card issuing machine and the payment machine, the AI ​​digital person sends the question back to the background cloud computing center, the GPT large model synthesizes a reply, and the AI ​​digital person answers the user after synthesizing voice; the screen display unit on the terminal card issuing machine and the payment machine demonstrates relevant operations for special situation processing, including how to handle insufficient ETC balance.

[0009] Preferably, the terminal card issuing machine is provided with an information push module, which integrates a card issuance message push subunit, a complaint message push subunit, a transaction information push subunit, a card inventory warning push subunit, and a platform important announcement push subunit.

[0010] Preferably, the terminal card issuing machine and the payment machine are respectively provided with a face recognition module, the face recognition module includes an OCR recognition subunit, a real-name authentication subunit and a portrait comparison subunit, and the portrait comparison subunit is connected to a live data input subunit and a live data input subunit.

[0011] Preferably, the terminal card issuing machine and the payment machine are respectively provided with a bank consumption record query module and a report form receiving module, and the report form receiving module includes a report form applying subunit and a report form printing subunit.

[0012] Preferably, the report printing subunit is connected to a coupon printing subunit, and the terminal card issuing machine and the payment machine are connected to a fingerprint reader and a card reader respectively.

[0013] Preferably, the terminal card issuing machine and the payment machine are provided with an ID card filing module, and the ID card filing module includes an ID card filing sub-unit, a guardian ID card auxiliary filing sub-unit, a face recognition auxiliary filing sub-unit and a hand-filled ID card number filing sub-unit, and the ID card filing sub-unit, the guardian ID card auxiliary filing sub-unit, the face recognition auxiliary filing sub-unit and the hand-filled ID card number filing sub-unit are respectively connected to the information recognition sub-unit.

[0014] Preferably, the terminal card issuing machine and the payment machine are connected to a real-time monitoring device for system consumable resources, and the real-time monitoring device for system consumable resources is used to monitor the number of cards stored in the terminal card issuing machine and the payment machine. The real-time monitoring device for system consumable resources is connected to an early warning device, and the early warning device includes an intelligent voice reminder sub-unit.

[0015] Preferably, the terminal card issuing machine is connected to a receipt printer and a UnionPay card reader, the terminal card issuing machine is also connected to a camera and a banknote identifier, and the terminal card issuing machine is also connected to an RFID card reader; the terminal card issuing machine adopts a CB / S architecture, and the CB / S architecture adopts a C / S architecture with an embedded B / S architecture; the terminal card issuing machine is connected to a high-speed scanner, a password keyboard, an electromagnetic pen, a banknote module and a UnionPay card module.

[0016] A terminal card issuing machine system includes a control module, the control module is electrically connected to a data processor, the data processor is used to calculate and process data information received and sent by the terminal card issuing machine to improve the accuracy and security of the data information, the data processor includes an acquisition unit for receiving data information, a gain unit for amplifying data information, an AD conversion unit for analog-to-digital conversion of data information, and a filtering unit for filtering out clutter from data information, the data processor is communicatively connected to an information database through a communication module, and all toll records of highways are integrated through the information database to facilitate querying the time records of vehicles entering and exiting highways and the distance traveled by vehicles, the data processor is electrically connected to a system driver, and the system driver is electrically connected to a screen display unit, and the screen is controlled by the system driver The screen display unit is driven to operate so that the screen display unit can display various data information. The control module is electrically connected with a function management unit, a data storage unit, a calculation model unit and a voltage regulating module. The voltage regulating module is used to power the control module. The voltage regulating module includes a step-down circuit for reducing the voltage, a conversion circuit for converting AC voltage into DC voltage, a filter circuit for filtering AC voltage in DC voltage, and a voltage stabilizing circuit for stable voltage output. The function management unit includes a face recognition module and an information push module. The data storage unit is used to store data information. The data storage unit includes a ROM memory, a RAM memory and a buffer. The data processor is electrically connected with a data encryption unit. The data encryption unit is used to encrypt data information, received and sent information.

[0017] Preferably, the calculation model unit is used to perform calculation processing based on the information database and the data information obtained by the function management unit, so as to facilitate the calculation processing of vehicle query, transaction information, OCR recognition, face recognition, real-name authentication and portrait comparison at the highway intersection;

[0018] The AI ​​intelligent algorithm adopted by the computing model unit is determined by the neural network input neuron information and the corresponding weight matrix W of the AI ​​intelligent algorithm. T X t, X is a vector, W is a weight matrix, and W is used to transform X into another vector;

[0019] The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1 Convert to another vector;

[0020] Mainly the neuron h at the current moment t , integrate the inputs of the above two parts, activate and generate the output of the hidden layer neurons at the current moment, and the integration process is vector addition: W T X t +U T S t-1 ;

[0021] Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 );

[0022] Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment:

[0023] O t =g(V T S t );

[0024] The forward formula is as follows:

[0025] S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 ));

[0026] In the entire neural network, there are three weight matrices in total. The first matrix is ​​W, and the dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron value, and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where P represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N);

[0027] The data encryption unit includes an asymmetric encryption system and a symmetric encryption system, wherein the symmetric encryption in the symmetric encryption system adopts the AES algorithm, and the asymmetric encryption adopts the DSA algorithm;

[0028] The AES algorithm:

[0029] Suppose the AES decryption function is D, then P = D (K, C), where C is the ciphertext, K is the key, and P is the plaintext. The ciphertext C and the key K are input as parameters of the decryption function, and the decryption function will output the plaintext P;

[0030] Suppose the AES encryption function is E, then C = E(K, P), where P is plain text, K is the key, and C is the cipher text. The plain text P and the key K are input as parameters of the encryption function, and the encryption function E will output the cipher text C.

[0031] The signing process of the DSA algorithm:

[0032] Generate a random number k whose value satisfies 0 <k<q;

[0033] Calculate r = powm (g, k, p) mod q, whose value satisfies r>0;

[0034] Calculate s = (k^(-1)(SHA(M)+x*r))modq, whose value satisfies s>0;

[0035] The DSA algorithm verifies the signature process:

[0036] (r, s, M) is used to represent the signature result obtained by the verifier in some way;

[0037] In order to verify whether the signature of (r, s, M) is indeed signed by the sender, the verifier needs to have (g, p, q, y). The verification process is as follows:

[0038] Calculate w = s^(-1) mod q

[0039] Calculate u1 = (SHA(M)*w) mod q

[0040] Calculate u2 = (r*w) mod q

[0041] Calculate \(v = (((g^{u1})*(y^{u2}))\bmod p)\bmod q = ((g^{u1\bmod p})*(y^{u2\bmod p})\bmod p)\bmod q = (\text{powm}(g, u1, p)*\text{powm}(y, u2, p)\bmod p)\bmod q\)

[0042] If \(v\) is equal to \(r\), then the verification passes; otherwise, the verification fails.

[0043] Parameter definitions of the DSA algorithm:

[0044] \(p\): A prime modulus, whose value satisfies \(2^{L - 1}<p<2^L\), where \(L\) is a multiple of 64 and \(512\leq L\leq1024\).

[0045] \(q\): A prime factor of \((p - 1)\), whose value satisfies \(2^{159}<q<2^{160}\), that is, the length of \(q\) is 160 bits.

[0046] \(g\): \(g=\text{powm}(h, (p - 1) / q, p)\), where \(h\) is any integer satisfying \(1 < h < p - 1\), so \(\text{powm}(h, (p - 1) / q, p)>1\).

[0047] \(x\): The private key, \(x\) is a randomly or pseudo-randomly generated integer, whose value satisfies \(0 < x < q\).

[0048] \(y\): The public key, \(y = \text{powm}(g, x, p)\).

[0049] In summary, the present invention mainly has the following beneficial effects:

[0050] This intelligent self-service card-issuing digital terminal adopts self-service card-issuing and payment, and the terminal is equipped with visual intercom; when encountering problems, after pressing the button, it communicates with the background customer service; it solves the disadvantages of low efficiency and occupying a large amount of labor; the background cloud computing center in the present invention uses the GPT large model for training on charging business questions and answers; the terminal adopts digital human + dynamic demonstration to improve the user experience; it saves artificial customer service resources.

[0051] When the terminal card-issuing machine of the present invention is in use, it queries the data information in the information database through the communication module, so that the management information of the entire highway can be easily queried, and it is convenient for each exit and entrance of the entire highway system to query information. And through the calculation model unit, various data information is calculated, which is convenient for calculating and processing various information, effectively improving the data calculation of the highway system, being able to fully calculate various fees and vehicle information, and through the data encryption unit, various data information is encrypted, improving the security of the data information, preventing data leakage or the highway system from being attacked. Brief Description of the Drawings

[0052] Figure 1It is one of the system block diagrams of the present invention;

[0053] Figure 2 This is the second system block diagram of the present invention

[0054] Figure 3 It is a schematic diagram of the terminal card issuing machine system of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] refer to Figure 1 and Figure 2 , an intelligent self-service card issuance digital terminal, including a background cloud computing center, the background cloud computing center uses the GPT large model to train common problems of charging services, the background cloud computing center is connected to the terminal card issuing machine and the payment machine through a communication module, the terminal card issuing machine and the payment machine are electrically connected to a screen display unit for displaying an AI digital person, when the user presses the intercom button through the terminal card issuing machine and the payment machine, the AI ​​digital person sends the question back to the background cloud computing center, the GPT large model synthesizes the reply and the AI ​​digital person synthesizes the voice to answer the user; the screen display unit on the terminal card issuing machine and the payment machine demonstrates the relevant operations of special situation processing, including how to deal with insufficient ETC balance.

[0057] Among them, the terminal card issuing machine is provided with an information push module, which integrates the card issuing message push subunit, the complaint message push subunit, the transaction information push subunit, the card inventory warning push subunit, and the platform important announcement push subunit. It can realize the one-stop government service functions such as unmanned self-service guidance service, service guide query, self-service form filling, file printing, processing process query, processing result query, etc.

[0058] Among them, the terminal card issuing machine and the payment machine are respectively provided with a face recognition module, and the face recognition module includes an OCR recognition subunit, a real-name authentication subunit and a portrait comparison subunit, and the portrait comparison subunit is connected to a live data input subunit and a live data input subunit.

[0059] The terminal card issuing machine and the payment machine are respectively provided with a bank consumption record query module and a report form receiving module, and the report form receiving module includes a report form applying subunit and a report form printing subunit.

[0060] The report printing subunit is connected to the coupon printing subunit, and the terminal card issuing machine and the payment machine are connected to a fingerprint reader and a card reader respectively.

[0061] Among them, the terminal card issuing machine and the payment machine are provided with an ID card filing module, and the ID card filing module includes an ID card filing sub-unit, a guardian ID card auxiliary filing sub-unit, a face recognition auxiliary filing sub-unit and a hand-filled ID card number filing sub-unit. The ID card filing sub-unit, the guardian ID card auxiliary filing sub-unit, the face recognition auxiliary filing sub-unit and the hand-filled ID card number filing sub-unit are respectively connected to the information recognition sub-unit.

[0062] Among them, the terminal card issuing machine and the payment machine are connected with a real-time monitoring device for system consumable resources, and the real-time monitoring device for system consumable resources is used to monitor the number of cards stored in the terminal card issuing machine and the payment machine. The real-time monitoring device for system consumable resources is connected with an early warning device, and the early warning device includes an intelligent voice reminder sub-unit.

[0063] Among them, the terminal card issuing machine is connected to a receipt printer and a UnionPay card reader, the terminal card issuing machine is also connected to a camera and a banknote identifier, and the terminal card issuing machine is also connected to an RFID card reader; the terminal card issuing machine adopts a CB / S architecture, and the CB / S architecture adopts a C / S architecture with an embedded B / S architecture; the terminal card issuing machine is connected to a high-speed scanner, a password keyboard, an electromagnetic pen, a banknote module and a UnionPay card module.

[0064] Among them, this intelligent self-service card issuance digital terminal adopts self-service card issuance and payment, and the terminal is equipped with video intercom; when encountering problems, communicate with the background customer service after pressing a button; solves the shortcomings of low efficiency and occupying a lot of manpower; the background cloud computing center in the present invention adopts the GPT large model for charging business question and answer training; the terminal adopts digital human + dynamic demonstration to improve user experience; save manual customer service resources.

[0065] refer to Figure 3 , oneA terminal card issuing machine system includes a control module, the control module is electrically connected to a data processor, the data processor is used to calculate and process data information received and sent by the terminal card issuing machine to improve the accuracy and security of the data information, the data processor includes an acquisition unit for receiving data information, a gain unit for amplifying data information, an AD conversion unit for analog-to-digital conversion of data information, and a filtering unit for filtering out clutter from data information, the data processor is connected to an information database through a communication module, and all toll records of highways are integrated through the information database to facilitate querying the time records of vehicles entering and exiting highways and the distance traveled by vehicles, the data processor is electrically connected to a system driver, and the system driver is electrically connected to a screen display unit, and the screen is displayed through the system driver The display unit is driven to operate so that the screen display unit can display various data information. The control module is electrically connected with a function management unit, a data storage unit, a calculation model unit and a voltage regulating module. The voltage regulating module is used to power the control module. The voltage regulating module includes a step-down circuit for reducing the voltage, a conversion circuit for converting AC voltage into DC voltage, a filter circuit for filtering AC voltage in DC voltage, and a voltage stabilizing circuit for stable voltage output. The function management unit includes a face recognition module and an information push module. The data storage unit is used to store data information. The data storage unit includes a ROM memory, a RAM memory and a buffer. The data processor is electrically connected with a data encryption unit, and the data encryption unit is used to encrypt data information, received and sent information.

[0066] The computing model unit is used to perform computing and processing based on the information database and the data information obtained by the function management unit, so as to facilitate the computing and processing of vehicle query, transaction information, OCR recognition, face recognition, real-name authentication and portrait comparison at the highway intersection;

[0067] The AI ​​intelligent algorithm adopted by the computing model unit is determined by the neural network input neuron information and the corresponding weight matrix W of the AI ​​intelligent algorithm. T X t , X is a vector, W is a weight matrix, and W is used to transform X into another vector;

[0068] The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1Convert to another vector;

[0069] Mainly the neuron h at the current moment t , integrate the inputs of the above two parts, activate and generate the output of the hidden layer neurons at the current moment, and the integration process is vector addition: W T X t +U T S t-1 ;

[0070] Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 );

[0071] Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment:

[0072] O t =g(V T S t );

[0073] The forward formula is as follows:

[0074] S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 ));

[0075] In the entire neural network, there are three weight matrices in total. The first matrix is ​​W, and the dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron value, and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where P represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N);

[0076] The data encryption unit includes an asymmetric encryption system and a symmetric encryption system, wherein the symmetric encryption in the symmetric encryption system adopts the AES algorithm, and the asymmetric encryption adopts the DSA algorithm;

[0077] The AES algorithm:

[0078] Let the AES decryption function be D, then P = D(K, C), where C is the ciphertext, K is the key, and P is the plaintext. Input the ciphertext C and the key K as the parameters of the decryption function, and the decryption function will output the plaintext P;

[0079] Let the AES encryption function be E, then C = E(K, P), where P is the plaintext, K is the key, and C is the ciphertext. Input the plaintext P and the key K as the parameters of the encryption function, and the encryption function E will output the ciphertext C;

[0080] The signature process of the DSA algorithm:

[0081] Generate a random number k, whose value satisfies 0 < k < q;

[0082] Calculate r = powm(g, k, p) mod q, whose value satisfies r > 0;

[0083] Calculate s = (k^(-1)(SHA(M) + x * r)) mod q, whose value satisfies s > 0;

[0084] The signature verification process of the DSA algorithm:

[0085] Use (r, s, M) to represent the signature result obtained by the verifier through some means;

[0086] To verify whether the signature of (r, s, M) is indeed signed by the sender, the verifier needs (g, p, q, y), and the verification process is as follows:

[0087] Calculate w = s^(-1) mod q

[0088] Calculate u1 = (SHA(M) * w) mod q

[0089] Calculate u2 = (r * w) mod q

[0090] Calculate v = (((g^u1) * (y^u2)) mod p) mod q = ((g^u1 mod p) * (y^u2 mod p) mod p) mod q = (powm(g, u1, p) * powm(y, u2, p) mod p) mod q

[0091] If v is equal to r, the verification passes, otherwise the verification fails;

[0092] The parameter definition of the DSA algorithm:

[0093] p: A prime modulus, whose value satisfies: 2^(L - 1) < p < 2^L, where L is a multiple of 64 and satisfies 512 ≤ L ≤ 1024,

[0094] q: A prime factor of (p - 1), whose value satisfies 2^159 < q < 2^160, that is, q is 160 bits long.

[0095] g: g = powm(h, (p - 1) / q, p), where h is any integer satisfying 1 < h < p - 1, so that powm(h, (p - 1) / q, p) > 1.

[0096] x: Private key, x is a randomly or pseudo-randomly generated integer, whose value satisfies 0 < x < q.

[0097] y: Public key, y = powm(g, x, p).

[0098] Among them, the communication module queries the data information in the information database, making the management information of the entire highway easy to query, so that each exit and entrance of the entire highway system can query the information. And through the calculation model unit, various data information is calculated, which is convenient for calculating and processing various information, effectively improving the data calculation of the highway system, and being able to fully calculate various fees and vehicle information. Also, through the data encryption unit, various data information is encrypted, improving the security of the data information, preventing data leakage or the highway system from being attacked.

[0099] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent self-service card issuance digital terminal, characterized by: It includes a backend cloud computing center, which uses the GPT large model to train common problems in charging services. The backend cloud computing center is connected to the terminal card issuing machine and the payment machine through a communication module. The terminal card issuing machine and the payment machine are electrically connected to a screen display unit for displaying an AI digital human. When the user presses the intercom button through the terminal card issuing machine and the payment machine, the AI ​​digital human sends the question back to the backend cloud computing center, the GPT large model synthesizes the reply and the AI ​​digital human answers the user after synthesizing the voice; the screen display unit on the terminal card issuing machine and the payment machine demonstrates relevant operations for special situation handling, including how to deal with insufficient ETC balance.

2. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine is provided with an information push module, which integrates a card issuance message push subunit, a complaint message push subunit, a transaction information push subunit, a card inventory warning push subunit, and a platform important announcement push subunit.

3. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine and the payment machine are respectively provided with a face recognition module, which includes an OCR recognition subunit, a real-name authentication subunit and a portrait comparison subunit, and the portrait comparison subunit is connected to a live data input subunit and a live data input subunit.

4. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine and the payment machine are respectively provided with a bank consumption record query module and a report form receiving module, and the report form receiving module includes a report form applying subunit and a report form printing subunit.

5. The intelligent self-service card issuance digital terminal according to claim 4, characterized in that: The report printing subunit is connected to the coupon printing subunit, and the terminal card issuing machine and the payment machine are respectively connected to a fingerprint reader and a card reader.

6. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine and the payment machine are provided with an ID card filing module, which includes an ID card filing sub-unit, a guardian ID card auxiliary filing sub-unit, a face recognition auxiliary filing sub-unit and a hand-filled ID card number filing sub-unit. The ID card filing sub-unit, the guardian ID card auxiliary filing sub-unit, the face recognition auxiliary filing sub-unit and the hand-filled ID card number filing sub-unit are respectively connected to the information recognition sub-unit.

7. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine and the payment machine are connected to a real-time monitoring device for system consumable resources, which is used to monitor the number of cards stored in the terminal card issuing machine and the payment machine. The real-time monitoring device for system consumable resources is connected to an early warning device, which includes an intelligent voice reminder sub-unit.

8. The intelligent self-service card issuance digital terminal according to claim 1, characterized in that: The terminal card issuing machine is connected to a receipt printer and a UnionPay card reader, and is also connected to a camera and a banknote identifier, and is also connected to an RFID card reader; the terminal card issuing machine adopts a CB / S architecture, and the CB / S architecture adopts a C / S architecture with an embedded B / S architecture; the terminal card issuing machine is connected to a high-speed scanner, a password keyboard, an electromagnetic pen, a banknote module and a UnionPay card module.

9. A terminal card issuing machine system, characterized in that: The invention comprises a control module, the control module is electrically connected to a data processor, the data processor is used to calculate and process the data information received and sent by the terminal card issuing machine, so as to improve the accuracy and security of the data information, the data processor comprises an acquisition unit for receiving the data information, a gain unit for amplifying the data information, an AD conversion unit for performing analog-to-digital conversion on the data information, and a filtering unit for filtering out clutter on the data information, the data processor is communicatively connected to an information database through a communication module, and all toll records of the expressway are integrated through the information database, so as to facilitate the query of the time record of the vehicle entering and exiting the expressway and the vehicle's travel distance, the data processor is electrically connected to a system driver, and the system driver is electrically connected to a screen display unit, and the screen display unit is controlled by the system driver The driving operation is carried out to facilitate the screen display unit to display various data information. The control module is electrically connected with a function management unit, a data storage unit, a calculation model unit and a voltage regulating module. The voltage regulating module is used to power the control module. The voltage regulating module includes a step-down circuit for reducing the voltage, a conversion circuit for converting AC voltage into DC voltage, a filter circuit for filtering AC voltage in DC voltage, and a voltage stabilizing circuit with stable voltage output. The function management unit includes a face recognition module and an information push module. The data storage unit is used to store data information. The data storage unit includes a ROM memory, a RAM memory and a buffer. The data processor is electrically connected with a data encryption unit. The data encryption unit is used to encrypt data information, received and sent information.

10. A terminal card issuing machine system according to claim 9, characterized in that: The computing model unit is used to perform computing processing based on the information database and the data information obtained by the function management unit, so as to facilitate the computing processing of vehicle query, transaction information, OCR recognition, face recognition, real-name authentication and portrait comparison at the highway intersection; The AI ​​intelligent algorithm adopted by the computing model unit is determined by the neural network input neuron information and the corresponding weight matrix W of the AI ​​intelligent algorithm. T X t , X is a vector, W is a weight matrix, and W is used to transform X into another vector; The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1 Convert to another vector; Mainly the neuron h at the current moment t , integrate the inputs of the above two parts, activate and generate the output of the hidden layer neurons at the current moment, and the integration process is vector addition: W T X t +U T S t-1 ; Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 ); Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment: O t =g(V T S t ); The forward formula is as follows: S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 )); In the entire neural network, there are three weight matrices in total. The first matrix is ​​W, and the dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron value, and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where P represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N); The data encryption unit includes an asymmetric encryption system and a symmetric encryption system, wherein the symmetric encryption in the symmetric encryption system adopts the AES algorithm, and the asymmetric encryption adopts the DSA algorithm; The AES algorithm: Suppose the AES decryption function is D, then P = D (K, C), where C is the ciphertext, K is the key, and P is the plaintext. The ciphertext C and the key K are input as parameters of the decryption function, and the decryption function will output the plaintext P; Let the AES encryption function be E, then C = E(K, P), where P is the plaintext, K is the key, and C is the ciphertext. When the plaintext P and the key K are input as the parameters of the encryption function, the encryption function E will output the ciphertext C; The signature process of the DSA algorithm: Generate a random number k whose value satisfies 0 < k < q; Calculate r = powm(g, k, p) mod q, whose value satisfies r > 0; Calculate s = (k^(-1)(SHA(M) + x * r)) mod q, whose value satisfies s > 0; The signature verification process of the DSA algorithm: Use (r, s, M) to represent the signature result obtained by the verifier through some means; To verify whether the signature of (r, s, M) is indeed signed by the sender, the verifier needs (g, p, q, y). The verification process is as follows: Calculate w = s^(-1) mod q Calculate u1 = (SHA(M) * w) mod q Calculate u2 = (r * w) mod q Calculate v = (((g^u1) * (y^u2)) mod p) mod q = ((g^u1 mod p) * (y^u2 mod p) mod p) mod q = (powm(g, u1, p) * powm(y, u2, p) mod p) mod q If v is equal to r, the verification passes; otherwise, the verification fails; The parameter definition of the DSA algorithm: p: A prime modulus whose value satisfies: 2^(L - 1) < p < 2^L, where L is a multiple of 64 and satisfies 512 ≤ L ≤ 1024, q: A prime factor of (p - 1) whose value satisfies 2^159 < q < 2^160, that is, q is 160 bits long, g: g = powm(h, (p - 1) / q, p), where h is any integer that satisfies 1 < h < p - 1, so that powm(h, (p - 1) / q, p) > 1, x: The private key, x is a randomly or pseudo-randomly generated integer whose value satisfies 0 < x < q, y: The public key, y = powm(g, x, p).

Images