Crime record-free proof automatic processing method and system based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based crime record-free proof automatic processing method and system, and belongs to the technical field of data processing. Crime record-free request data transmitted by an applicant is acquired, and network flow characteristics are acquired in real time in the access process of the applicant; the crime record-free request data and the network flow characteristics are comprehensively processed through artificial intelligence to obtain a crime record-free request result, and finally, the crime record-free request result is encrypted by adopting an encryption algorithm to obtain a crime record-free certificate automatic processing result, so that the crime record-free certificate automatic processing result is obtained. And the crime-free record certificate automatic processing result is returned to the applicant, so that the crime-free record acquisition efficiency can be effectively improved, the error problem caused by manual auditing is avoided, and the data access security can be effectively ensured.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to an artificial intelligence-based automatic processing method and system for a certificate of no criminal record. Background Art

[0002] Currently, the processing of criminal record certificates relies primarily on manual review, which is inefficient and prone to errors. Therefore, how to use artificial intelligence technology to automatically process criminal record certificates and improve processing efficiency and accuracy has become a pressing issue. Summary of the Invention

[0003] The present invention provides an artificial intelligence-based automatic processing method and system for a certificate of no criminal record, which is used to solve the problem that the processing of a certificate of no criminal record in the prior art mainly relies on manual review, which is inefficient and prone to errors.

[0004] In one aspect, the present invention provides an artificial intelligence-based method for automatically processing a criminal record certificate, comprising: Obtain criminal record clearance request data transmitted by applicants and collect network traffic characteristics in real time during the applicants’ access process; Comprehensively processing the criminal record request data and the network traffic characteristics through artificial intelligence to obtain a criminal record request result; The result of the criminal record certificate request is encrypted using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and the automatic processing result of the criminal record certificate is returned to the applicant.

[0005] In a possible implementation, the criminal record request data includes: the applicant's real-time facial image, ID number, and name.

[0006] In one possible implementation, the clean criminal record request data and the network traffic characteristics are comprehensively processed by artificial intelligence to obtain a clean criminal record request result, including: Identifying the network traffic characteristics using a pre-deployed first artificial intelligence model to determine a network security identification result; wherein the network security identification result is that the current network access process is secure or the current network access process is unsafe; When the network security identification result indicates that the current network access process is unsafe, the applicant's current criminal record certificate request result is determined to be an abnormal request, and the automatic processing flow of the criminal record certificate is terminated; When the network security identification result indicates that the current network access process is secure, a pre-deployed second artificial intelligence model is used to perform facial recognition on the real-time facial image in the criminal record clearance request data to determine a facial recognition result; wherein the facial recognition result includes facial recognition passing or facial recognition failing; When the face recognition result is that the face recognition fails, a clean criminal record request result is generated as face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate ends; When the face recognition result is that the face recognition is passed, the identity information corresponding to the real-time face image of the applicant is retrieved from the database; Performing secondary verification based on the identity information corresponding to the real-time facial image of the applicant using the ID card number and name in the criminal record request data to obtain a secondary verification result; wherein the secondary verification result includes secondary verification pass or secondary verification fail; When the secondary verification result is a secondary verification failure, a clean criminal record request result is generated as a face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate is terminated; When the secondary verification result is that the secondary verification is successful, the corresponding criminal record is retrieved from the database to obtain the target criminal record, and the target criminal record is used as the criminal record request result.

[0007] In one possible implementation, when the applicant's current criminal record request result is an abnormal request, the following further includes: The access of the applicant is controlled by using a pre-set access restriction policy to manage the security of the access process.

[0008] In a possible implementation, the first artificial intelligence model is configured as a convolutional neural network model; and the second artificial intelligence model is configured as a comprehensive model of a convolutional neural network model and a BP neural network model.

[0009] In one possible implementation, the method for pre-deploying the first artificial intelligence model and the second artificial intelligence model includes: Using an intelligent optimization algorithm to train the hyperparameters of the first artificial intelligence model and the second artificial intelligence model to determine the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model; Deploy the first artificial intelligence model and the second artificial intelligence model according to the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model.

[0010] In one possible implementation, an encryption algorithm is used to encrypt the result of the criminal record certificate request to obtain an automatic processing result of the criminal record certificate, and the automatic processing result of the criminal record certificate is returned to the applicant, including: Preprocessing the real-time facial image of the applicant in the criminal record clean record request data to obtain the real-time facial image after preprocessing; Using a pre-deployed second artificial intelligence model to perform a feature extraction operation on the pre-processed real-time facial image to obtain the applicant's current corresponding temporary encrypted features; Based on the temporary encryption feature currently corresponding to the applicant, a symmetric encryption key corresponding to the symmetric encryption algorithm is generated, and the result of the criminal record clearance request is encrypted using the symmetric encryption key to obtain an automatic processing result of the criminal record clearance certificate; The automatic processing result of the criminal record certificate is returned to the applicant.

[0011] In one possible implementation, preprocessing the real-time facial image of the applicant in the criminal record clearance request data to obtain the preprocessed real-time facial image includes: Grayscale and normalize the real-time facial image of the applicant in the criminal record clean record request data to obtain a pre-processed real-time facial image.

[0012] In one possible implementation, a symmetric encryption key corresponding to a symmetric encryption algorithm is generated based on the applicant's current temporary encryption feature, and the symmetric encryption key is used to encrypt the result of the criminal record clean record request to obtain an automatic processing result of the criminal record clean record certificate, including: Performing a hash operation on the temporary encryption feature currently corresponding to the applicant to obtain a hash operation result, and generating a symmetric encryption key corresponding to the symmetric encryption algorithm based on the encryption public key disclosed by the applicant and the hash operation result; Based on the symmetric encryption key corresponding to the symmetric encryption algorithm, the symmetric encryption algorithm is used to encrypt the result of the criminal record clean record request to obtain an automatic processing result of the criminal record clean record certificate.

[0013] On the other hand, the present invention provides an artificial intelligence-based automatic processing system for a certificate of no criminal record, comprising: a data acquisition module, a data comprehensive processing module, and a data encryption feedback module; The data collection module is used to obtain the criminal record request data transmitted by the applicant and to collect network traffic characteristics in real time during the applicant's visit; The data comprehensive processing module is used to comprehensively process the criminal record request data and the network traffic characteristics through artificial intelligence to obtain a criminal record request result; The data encryption feedback module is used to encrypt the result of the criminal record certificate request using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and return the automatic processing result of the criminal record certificate to the applicant.

[0014] The present invention provides an artificial intelligence-based automatic processing method and system for a certificate of clean record. The method obtains criminal record request data transmitted by an applicant and collects network traffic characteristics in real time during the applicant's access process. The method then uses artificial intelligence to comprehensively process the criminal record request data and the network traffic characteristics to obtain a criminal record request result. Finally, the criminal record request result is encrypted using an encryption algorithm to obtain an automatic processing result of the certificate of clean record. The automatic processing result of the certificate of clean record is returned to the applicant. This method can not only effectively improve the efficiency of obtaining criminal records and avoid errors caused by manual review, but also effectively ensure data access security. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0016] Figure 1 A flowchart of an artificial intelligence-based automatic processing method for a certificate of no criminal record is provided in an embodiment of the present invention.

[0017] Figure 2 A schematic diagram of an artificial intelligence-based automatic processing system for criminal record certificates provided in an embodiment of the present invention.

[0018] Among them, 201 is a data acquisition module, 202 is a data comprehensive processing module, and 203 is a data encryption feedback module.

[0019] The above drawings illustrate specific embodiments of the present invention, which will be described in more detail below. These drawings and the accompanying description are not intended to limit the scope of the present invention in any way, but rather to illustrate the concept of the present invention to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0020] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0021] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the applicant's real-time facial image, ID number, name and other criminal record request data described below in this embodiment, as well as data such as network traffic collected in real time during the applicant's visit, are all legally obtained after authorization by the applicant.

[0022] like Figure 1 As shown, an embodiment of the present invention provides an artificial intelligence-based automatic processing method for a certificate of no criminal record, comprising: S101. Obtaining the criminal record clean record request data transmitted by the applicant and collecting network traffic characteristics in real time during the applicant's access process; Criminal record request data is used to identify applicants. By verifying this information, the applicant's criminal record can be confirmed. Network traffic signatures, on the other hand, are network security-related features of the applicant's access process. By identifying these features, access security can be guaranteed and database intrusions can be prevented.

[0023] After an individual submits an application online, the data is transmitted through the internet. Data exchange and security between these networks comply with relevant national and agency regulations. Once the individual's application record is uploaded to the relevant agency's network, the "PUIPA Criminal Record Certificate Automatic Processing Machine" automatically verifies the application's jurisdiction based on the application information and compares it with the National Criminal Record Certificate System. If a person is found to have no criminal record, a report is issued with an electronic signature after a secondary review. If not, the application is rejected, or personnel from the relevant agency intervene to assess the situation.

[0024] S102. Comprehensively process the clean criminal record request data and the network traffic characteristics through artificial intelligence to obtain a clean criminal record request result; The network traffic characteristics can be identified by artificial intelligence, and the criminal record request data will only be processed when the network security is identified. Then, the data in the criminal record request data can be identified by artificial intelligence. After successful identification, the corresponding criminal record in the database can be scheduled or generated to obtain the criminal record request result, which can effectively improve the efficiency of obtaining criminal records and avoid errors caused by human review.

[0025] S103: Encrypt the result of the request for a clean criminal record using an encryption algorithm to obtain an automatic processing result of the clean criminal record certificate, and return the automatic processing result of the clean criminal record certificate to the applicant.

[0026] By encrypting the result of the criminal record request using an encryption algorithm, the security of the criminal record can be effectively improved.

[0027] In a possible implementation, the criminal record request data includes: the applicant's real-time facial image, ID number, and name.

[0028] It is worth noting that, in addition to the aforementioned criminal record request data, other application-related data can also be used as criminal record request data to achieve the same or similar effect. For example, the applicant's fingerprint data can be collected as criminal record request data.

[0029] In one possible implementation, the clean criminal record request data and the network traffic characteristics are comprehensively processed by artificial intelligence to obtain a clean criminal record request result, including: S1021. Identify the network traffic characteristics using a pre-deployed first artificial intelligence model to determine a network security identification result; wherein the network security identification result is that the current network access process is secure or the current network access process is insecure; S1022. When the network security identification result indicates that the current network access process is unsafe, the applicant's current request for a clear criminal record is determined to be an abnormal request, and the automatic processing flow for the clear criminal record certificate is terminated. The embodiments of the present invention can effectively ensure the security of the database by identifying network security, obtaining network security identification results, and controlling the data access process according to the network security identification results.

[0030] S1023. When the network security identification result indicates that the current network access process is secure, performing facial recognition on the real-time facial image in the criminal record clearance request data using a pre-deployed second artificial intelligence model to determine a facial recognition result; wherein the facial recognition result includes facial recognition passing or facial recognition failing. S1024. When the face recognition result is face recognition failure, a clean criminal record request result is generated as face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate is terminated; S1025. When the face recognition result is passed, the identity information corresponding to the real-time face image of the applicant is retrieved from the database; After a pre-set period, a criminal record can be generated based on data in the judicial database (for example, by identifying keywords to determine whether a crime has occurred). This record and the corresponding identity information are stored in a database, facilitating subsequent identification and scheduling, and improving data processing efficiency. It is worth noting that if a person has a criminal record, their information is not stored in the database, reducing data processing volume and improving the efficiency of criminal record processing.

[0031] S1026. Perform secondary verification based on the identity information corresponding to the real-time facial image of the applicant using the ID card number and name in the criminal record request data to obtain a secondary verification result; wherein the secondary verification result includes secondary verification pass or secondary verification fail; S1027. When the secondary verification result is a secondary verification failure, a clean criminal record request result is generated as a face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate is terminated; S1028. When the secondary verification result is that the secondary verification is successful, the corresponding criminal record is retrieved from the database to obtain a target criminal record, and the target criminal record is used as the criminal record request result.

[0032] When the facial recognition result is passed, it proves that the applicant's criminal record has been stored in the database, and the identity information entered can be verified. After the identity information verification is passed, the corresponding target criminal record can be dispatched, thereby achieving rapid review and dispatch.

[0033] In one possible implementation, when the applicant's current criminal record request result is an abnormal request, the following further includes: The access of the applicant is controlled by using a pre-set access restriction policy to manage the security of the access process.

[0034] For example, you can set up a system to block access to an applicant's account for a period of time or permanently block it to ensure database security. Applicants' accounts can only be registered using ID card and face recognition to ensure account uniqueness.

[0035] In a possible implementation, the first artificial intelligence model is configured as a convolutional neural network model; and the second artificial intelligence model is configured as a comprehensive model of a convolutional neural network model and a BP neural network model.

[0036] It is worth noting that the first and second artificial intelligence models described above are merely examples provided in the embodiments of the present invention, and other neural network models may also be used to construct the second artificial intelligence model. For example, the second artificial intelligence model may also be constructed using only a convolutional neural network.

[0037] In one possible implementation, the method for pre-deploying the first artificial intelligence model and the second artificial intelligence model includes: Using an intelligent optimization algorithm to train the hyperparameters of the first artificial intelligence model and the second artificial intelligence model to determine the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model; Deploy the first artificial intelligence model and the second artificial intelligence model according to the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model.

[0038] The first artificial intelligence model can be trained using the KDD Cup 99 dataset, while the second artificial intelligence model can be trained using facial data corresponding to existing people in the database.

[0039] Using an intelligent optimization algorithm to train the hyperparameters of the first artificial intelligence model and the second artificial intelligence model to determine the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model, including: A1. Use the first artificial intelligence model or the second artificial intelligence model as the target artificial intelligence model, and initialize the hyperparameters of the target artificial intelligence model as follows:

[0040] in, Indicates the i Individuals, and i =1, is a randomly generated individual, Indicates the i +1 individual, represents the remainder function, represents pi, and sin represents the sine function; Each hyperparameter has an upper and lower limit, so the hyperparameter can be randomly initialized between the corresponding upper and lower limits, encoded into a vector, and randomly generated individuals can be obtained.

[0041] By using the above initialization strategy, the present invention can make the initial solutions more evenly distributed in the solution space, and can effectively improve the algorithm training speed and global optimization capability.

[0042] A2. Obtain the loss function value corresponding to each individual, and determine the individual with the smallest loss function value as the optimal individual, and determine the individual with the second smallest loss function value as the first optimal individual and the second optimal individual; Among them, the loss function can be obtained through the cross entropy loss function value.

[0043] A3. Based on the loss function value corresponding to each individual, all individuals are divided into the first target individual, the second target individual, and the third target individual in ascending order of the loss function value; The ratio between the first target individual, the second target individual and the third target individual is set to 2:6:2. At the same time, in order to enable integer division, the total number of individuals should be set to an integer multiple of 10.

[0044] A4. Search for the first target individual. The first target individual after the search is obtained as:

[0045]

[0046] in, Indicates the t During the training m first target individuals, m=1,2,…,M, M represents the total number of first target individuals, Indicates the t -1 training session m The first target individual, Indicates the m The first target individual after the search, represents a variable search coefficient, represents the exponential function with the natural constant e as the base, represents the first random number between (0,1), represents the maximum number of training times, represents the second random number between (0,1), Represents the first constant term between (0,1), which can be set to 0.5; represents the third random number between (0,1), represents the first randomly generated individual, and Each dimension of the hyperparameter is passed through generate, Represents a random number between [-1,1], Indicates the maximum value of the variable search coefficient, which can be set to 0.9; Indicates the minimum value of the variable search coefficient, which can be set to 0.5; By searching for the first target individual, the present invention enables the first target individual with a better position to have a wider search range or to search based on the historical position, which can effectively jump out of the local optimum and improve the training speed of the algorithm.

[0047] Optionally, an annealing simulation algorithm may be introduced to control the search process of the first target individual to ensure the convergence efficiency of the algorithm.

[0048] A5. Search for a second target individual based on the optimal individual, and obtain the second target individual after the search as:

[0049] in, Indicates the t During the training n The second target individual, Indicates the n The second target individual after the search, n =1,2,…,N, N represents the total number of second target individuals, represents the first target individual that is randomly matched to the second target individual, represents the first learning factor, , represents the first interaction coefficient and is set between (0,1), represents the fifth random number between (0,1), represents the second learning factor, , represents the second interaction coefficient and is set between (0,1). represents the sixth random number between (0,1), represents the second randomly generated individual, and Each dimension of the hyperparameter is passed through generate, Represents the seventh random number between (-1,1), Represents the second target individual With the first target individual The Euclidean distance between represents the optimal individual; The embodiment of the present invention can perform comprehensive learning on the second target individual by searching for the second target individual, and perform adaptive learning in combination with its own position information, which can effectively realize neighborhood search, improve the algorithm's search accuracy and the ability to search for a better solution.

[0050] A6. Search for a third target individual based on the optimal individual, the first optimal individual, and the second optimal individual. The third target individual obtained after the search is:

[0051]

[0052]

[0053]

[0054]

[0055] in, Indicates the t During the training k A third target individual, Indicates the k The third target individual after the search, k =1,2,…,K, K represents the total number of the third target individuals, represents the first optimal individual, represents the second best individual, represents the search step length, represents the first weighting factor, represents the second weighting factor, represents the third weighting factor, represents the eighth random number between (0,1), Represents the second constant term between (0,1), which can be set to 0.5; represents the ninth random number between (0,1), Indicates the third target individual The corresponding position evaluation factor, position evaluation factor = 1 / (loss function value + 0.0001), The worst individual, represents the position evaluation factor corresponding to the worst individual, Indicates the h weighting factors, and h =1, 2, 3 represent the weighting factors corresponding to the best individual, the first best individual, and the second best individual, respectively. represents the influence parameter corresponding to the optimal individual, It represents the influence parameter corresponding to the first optimal individual, It represents the influence parameter corresponding to the second best individual, Indicates the h influence parameters, and h =1, 2, 3 represent the influence parameters of the best individual, the first best individual, and the second best individual, respectively. represents the position evaluation factor corresponding to the optimal individual, represents the position evaluation factor corresponding to the first optimal individual, represents the position evaluation factor corresponding to the second best individual, | | represents taking the absolute value of each element; The embodiment of the present invention searches for the third target individual, so that the third target individual can be searched in a closed and better area, or searched in the worst position, which is more conducive to searching for the optimal solution and improving the algorithm training speed.

[0056] A7. Determine whether the current number of training times is greater than or equal to the preset maximum number of training times. If so, re-determine the optimal individual based on the first target individual after the search, the second target individual after the search, and the third target individual after the search, and use the hyperparameters in the re-determined optimal individual as the final hyperparameters of the target artificial intelligence model. Otherwise, return to step A2.

[0057] Optionally, out-of-bounds handling and / or greedy strategies may be implemented to ensure the effectiveness of the algorithm.

[0058] The training algorithm provided by the embodiment of the present invention can effectively improve the training speed and training effect of the algorithm, find the global optimal solution, and ensure that the first artificial intelligence model and the second artificial intelligence model can accurately complete their respective data recognition tasks.

[0059] In one possible implementation, an encryption algorithm is used to encrypt the result of the criminal record certificate request to obtain an automatic processing result of the criminal record certificate, and the automatic processing result of the criminal record certificate is returned to the applicant, including: Preprocessing the real-time facial image of the applicant in the criminal record clean record request data to obtain the real-time facial image after preprocessing; A pre-deployed second artificial intelligence model is used to perform feature extraction operations on the real-time facial image after preprocessing to obtain the applicant's current corresponding temporary encryption features; for example, the data output by the fully connected layer of the convolutional neural network in the second artificial intelligence model can be used as temporary encryption features.

[0060] Based on the temporary encryption feature currently corresponding to the applicant, a symmetric encryption key corresponding to the symmetric encryption algorithm is generated, and the result of the criminal record clearance request is encrypted using the symmetric encryption key to obtain an automatic processing result of the criminal record clearance certificate; The automatic processing result of the criminal record certificate is returned to the applicant.

[0061] In one possible implementation, preprocessing the real-time facial image of the applicant in the criminal record clearance request data to obtain the preprocessed real-time facial image includes: Grayscale and normalize the real-time facial image of the applicant in the criminal record clean record request data to obtain a pre-processed real-time facial image.

[0062] In one possible implementation, a symmetric encryption key corresponding to a symmetric encryption algorithm is generated based on the applicant's current temporary encryption feature, and the symmetric encryption key is used to encrypt the result of the criminal record clean record request to obtain an automatic processing result of the criminal record clean record certificate, including: Performing a hash operation on the temporary encryption feature currently corresponding to the applicant to obtain a hash operation result, and generating a symmetric encryption key corresponding to the symmetric encryption algorithm based on the encryption public key disclosed by the applicant and the hash operation result; After performing a hash operation on the temporary encryption feature currently corresponding to the applicant, the temporary encryption feature can be converted into a hash operation result with a fixed number of bits (such as 128 or 256 bits). It is worth noting here that the temporary encryption feature needs to be converted into the input form of the hash operation.

[0063] After obtaining the hash operation result, the hash operation result can be XORed with the applicant's public encryption key to obtain the XORed public encryption key. Since the length of the public key is generally greater than the key length of the symmetric encryption algorithm, based on the key length requirement of the symmetric encryption algorithm, the XORed public encryption key can be randomly intercepted with data of a corresponding length to obtain the symmetric encryption key corresponding to the symmetric encryption algorithm. It is worth noting that if the length of the hash operation result is shorter than the length of the encryption public key, the hash operation result is repeatedly permuted until the length of the encryption public key is met.

[0064] The encrypted public key can be the data made public by the applicant, and the applicant himself stores the encrypted private key to achieve data decryption.

[0065] Based on the symmetric encryption key corresponding to the symmetric encryption algorithm, the symmetric encryption algorithm is used to encrypt the result of the criminal record clean record request to obtain an automatic processing result of the criminal record clean record certificate.

[0066] After the result of the criminal record request is encrypted using a symmetric encryption algorithm, the symmetric encryption key may be transmitted to the applicant using an encryption public key, so that the applicant may decrypt the data using the symmetric encryption key.

[0067] The embodiment of the present invention generates a symmetric encryption key using the real-time facial image of the applicant in the criminal record request data, which can effectively generate a unique temporary key, effectively ensure the security of each data transmission process, and combine symmetric encryption algorithms with asymmetric encryption algorithms for encrypted transmission, greatly improving data encryption efficiency and ensuring the efficiency of the entire process.

[0068] The present invention provides an artificial intelligence-based automatic processing method for a criminal record certificate. The method obtains criminal record request data transmitted by an applicant and collects network traffic characteristics in real time during the applicant's access process. The method then uses artificial intelligence to comprehensively process the criminal record request data and the network traffic characteristics to obtain a criminal record request result. Finally, the method uses an encryption algorithm to encrypt the criminal record request result to obtain an automatic processing result of the criminal record certificate. The method then returns the automatic processing result of the criminal record certificate to the applicant. This method can not only effectively improve the efficiency of obtaining criminal records and avoid errors caused by manual review, but also effectively ensure data access security.

[0069] like Figure 2 As shown, the embodiment of the present invention provides an automatic processing system for a certificate of no criminal record based on artificial intelligence, comprising: a data acquisition module 201, a data comprehensive processing module 202, and a data encryption feedback module 203; The data collection module 201 is used to obtain the criminal record request data transmitted by the applicant and to collect network traffic characteristics in real time during the applicant's access process; The data comprehensive processing module 202 is used to comprehensively process the criminal record clean record request data and the network traffic characteristics through artificial intelligence to obtain a criminal record clean record request result; The data encryption feedback module 203 is used to encrypt the result of the criminal record certificate request using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and return the automatic processing result of the criminal record certificate to the applicant.

[0070] Figure 2 The artificial intelligence-based automatic processing system for criminal record certificates shown can implement the above-mentioned method and technical solution. Its principles and beneficial effects are similar and will not be repeated here.

[0071] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0075] Those skilled in the art will understand that all or part of the steps in implementing the above facts and methods can be completed by instructing relevant hardware through a program, and the program involved or the program can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: the corresponding method steps are then brought out, and the storage medium can be ROM / RAM, a disk, an optical disk, etc.

[0076] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An artificial intelligence-based automatic processing method for a certificate of no criminal record, characterized in that: include: Obtain criminal record clearance request data transmitted by applicants and collect network traffic characteristics in real time during the applicants’ access process; Comprehensively processing the criminal record request data and the network traffic characteristics through artificial intelligence to obtain a criminal record request result; The result of the criminal record certificate request is encrypted using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and the automatic processing result of the criminal record certificate is returned to the applicant.

2. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 1, characterized in that: The criminal record request data includes: the applicant's real-time facial image, ID number and name.

3. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 2, characterized in that: The criminal record request data and the network traffic characteristics are comprehensively processed by artificial intelligence to obtain a criminal record request result, including: Identifying the network traffic characteristics using a pre-deployed first artificial intelligence model to determine a network security identification result; wherein the network security identification result is that the current network access process is secure or the current network access process is unsafe; When the network security identification result indicates that the current network access process is unsafe, the applicant's current criminal record certificate request result is determined to be an abnormal request, and the automatic processing flow of the criminal record certificate is terminated; When the network security identification result indicates that the current network access process is secure, a pre-deployed second artificial intelligence model is used to perform facial recognition on the real-time facial image in the criminal record clearance request data to determine a facial recognition result; wherein the facial recognition result includes facial recognition passing or facial recognition failing; When the face recognition result is that the face recognition fails, a clean criminal record request result is generated as face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate ends; When the face recognition result is that the face recognition is passed, the identity information corresponding to the real-time face image of the applicant is retrieved from the database; Performing secondary verification based on the identity information corresponding to the real-time facial image of the applicant using the ID card number and name in the criminal record request data to obtain a secondary verification result; wherein the secondary verification result includes secondary verification pass or secondary verification fail; When the secondary verification result is a secondary verification failure, a clean criminal record request result is generated as a face authentication failure, and the clean criminal record request result is directly transmitted to the applicant, and the automatic processing flow of the clean criminal record certificate is terminated; When the secondary verification result is that the secondary verification is successful, the corresponding criminal record is retrieved from the database to obtain the target criminal record, and the target criminal record is used as the criminal record request result.

4. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 3, characterized in that: When the applicant's current criminal record request result is an abnormal request, it also includes: The access of the applicant is controlled by using a pre-set access restriction policy to manage the security of the access process.

5. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 4, characterized in that: The first artificial intelligence model is set to: a convolutional neural network model; the second artificial intelligence model is set to: a comprehensive model of a convolutional neural network model and a BP neural network model.

6. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 5, characterized in that: The method for pre-deploying the first artificial intelligence model and the second artificial intelligence model includes: Using an intelligent optimization algorithm to train the hyperparameters of the first artificial intelligence model and the second artificial intelligence model to determine the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model; Deploy the first artificial intelligence model and the second artificial intelligence model according to the final hyperparameters corresponding to the first artificial intelligence model and the second artificial intelligence model.

7. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 6, characterized in that: The result of the criminal record certificate request is encrypted using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and the automatic processing result of the criminal record certificate is returned to the applicant, including: Preprocessing the real-time facial image of the applicant in the criminal record clean record request data to obtain the real-time facial image after preprocessing; Using a pre-deployed second artificial intelligence model to perform a feature extraction operation on the pre-processed real-time facial image to obtain the applicant's current corresponding temporary encrypted features; Based on the temporary encryption feature currently corresponding to the applicant, a symmetric encryption key corresponding to the symmetric encryption algorithm is generated, and the result of the criminal record clearance request is encrypted using the symmetric encryption key to obtain an automatic processing result of the criminal record clearance certificate; The automatic processing result of the criminal record certificate is returned to the applicant.

8. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 1, characterized in that: Preprocessing the real-time facial image of the applicant in the criminal record clean record request data to obtain the preprocessed real-time facial image includes: Grayscale and normalize the real-time facial image of the applicant in the criminal record clean record request data to obtain a pre-processed real-time facial image.

9. The method for automatically processing a criminal record certificate based on artificial intelligence according to claim 8, characterized in that: Based on the temporary encryption feature currently corresponding to the applicant, a symmetric encryption key corresponding to the symmetric encryption algorithm is generated, and the result of the criminal record certificate request is encrypted using the symmetric encryption key to obtain the automatic processing result of the criminal record certificate, including: Performing a hash operation on the temporary encryption feature currently corresponding to the applicant to obtain a hash operation result, and generating a symmetric encryption key corresponding to the symmetric encryption algorithm based on the encryption public key disclosed by the applicant and the hash operation result; Based on the symmetric encryption key corresponding to the symmetric encryption algorithm, the symmetric encryption algorithm is used to encrypt the result of the criminal record clean record request to obtain an automatic processing result of the criminal record clean record certificate.

10. An artificial intelligence-based automatic processing system for criminal record certificates, characterized in that: include: Data acquisition module, data comprehensive processing module and data encryption feedback module; The data collection module is used to obtain the criminal record request data transmitted by the applicant and to collect network traffic characteristics in real time during the applicant's visit; The data comprehensive processing module is used to comprehensively process the criminal record request data and the network traffic characteristics through artificial intelligence to obtain a criminal record request result; The data encryption feedback module is used to encrypt the result of the criminal record certificate request using an encryption algorithm to obtain an automatic processing result of the criminal record certificate, and return the automatic processing result of the criminal record certificate to the applicant.

Images