Information management system and method for cloud platform

Abstract

According to the information management system and method for the cloud platform, an identity card and license file of an enterprise legal person is added, and identity information of the enterprise legal person is recognized; performing face information recognition on the enterprise legal person, and verifying the face information of the enterprise legal person; adding an enterprise business license, identifying business license information of the enterprise business license, comparing industrial and commercial business information, and verifying authenticity of the business license information; the enterprise user carries out secondary confirmation on the identity information of the enterprise legal person and the business license information of the enterprise business license; the enterprise user selects a business data type needing to be authorized and an institution needing to be authorized; an online authorization file is signed by the enterprise user. Therefore, the real identity of the enterprise legal person can be ensured, and the security and credibility of the information management system are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent information management technology, and more specifically, to an information management system and method for a cloud platform. Background Art

[0002] With the rise and development of cloud platforms, more and more enterprises choose to store and process their business data in the cloud. On the cloud platform, enterprise users can enjoy efficient and convenient information management services, but at the same time, they also face challenges in information security and privacy protection. In order to ensure the information security and privacy rights of enterprise users, it is necessary to effectively verify and manage the identities and authorizations of enterprise users.

[0003] However, there is currently a lack of a unified, standard, and trustworthy information management system and method on cloud platforms, resulting in some problems for enterprise users when using cloud platforms. For example, enterprise users need to provide different proof and authorization documents to different institutions, increasing the workload and cost of enterprise users; enterprise users cannot effectively control the scope of use and permissions of their business data, which may lead to the abuse or theft of business data, etc.

[0004] Therefore, an optimized information management system and method for a cloud platform are expected. Summary of the Invention

[0005] To solve the above technical problems, this application is proposed. Embodiments of this application provide an information management system and method for a cloud platform, which add the identity certificate file of the enterprise legal person to identify the identity information of the enterprise legal person; perform face information recognition on the enterprise legal person and verify the face information of the enterprise legal person; add the business license of the enterprise to identify the business license information of the business license, compare the industrial and commercial business information, and verify the authenticity of the business license information; have the enterprise user perform a secondary confirmation on the identity information of the enterprise legal person and the business license information of the business license; have the enterprise user select the types of business data to be authorized and the institutions to be authorized; and have the enterprise user sign an online authorization document. In this way, the true identity of the enterprise legal person can be ensured, and the security and credibility of the information management system can be improved.

[0006] In a first aspect, an information management method for a cloud platform is provided, which includes:

[0007] Add the identity certificate file of the enterprise legal person to identify the identity information of the enterprise legal person;

[0008] Perform face information recognition on the enterprise legal person and verify the face information of the enterprise legal person;

[0009] Add the business license of the enterprise, identify the business license information of the enterprise business license, compare the industrial and commercial business information, and verify the authenticity of the business license information;

[0010] The enterprise user shall conduct a secondary confirmation on the identity information of the enterprise legal person and the business license information of the enterprise business license;

[0011] The enterprise user shall select the types of business data to be authorized and the institutions to be authorized;

[0012] The enterprise user shall sign an online authorization document.

[0013] In the above information management method for the cloud platform, for the enterprise legal person, face information recognition is performed and the face information of the enterprise legal person is verified, including: obtaining the verification face image of the enterprise legal person; obtaining the sequence of real-time face acquisition images of the enterprise legal person collected by multiple cameras; extracting the face features of the verification face image and the sequence of real-time face acquisition images to obtain the verification face feature vector and the sequence of acquisition face feature vectors; and determining whether the verification passes based on the semantic difference of face features between the verification face feature vector and the sequence of acquisition face feature vectors.

[0014] In the above information management method for the cloud platform, extracting the face features of the verification face image and the sequence of real-time face acquisition images to obtain the verification face feature vector and the sequence of acquisition face feature vectors includes: using a deep learning network model to perform feature extraction on the verification face image and the sequence of real-time face acquisition images to obtain the verification face feature vector and the sequence of acquisition face feature vectors.

[0015] In the above information management method for the cloud platform, the deep learning network model is a face feature extractor based on a convolutional neural network model.

[0016] In the above information management method for the cloud platform, using a deep learning network model to perform feature extraction on the verification face image and the sequence of real-time face acquisition images to obtain the verification face feature vector and the sequence of acquisition face feature vectors includes: passing the verification face image through the face feature extractor based on the convolutional neural network model to obtain the verification face feature vector; passing the sequence of real-time face acquisition images through the face feature extractor based on the convolutional neural network model to obtain the sequence of acquisition face feature vectors.

[0017] In the above information management method for a cloud platform, determining whether the verification passes based on the semantic difference in facial features between the verified facial feature vector and the sequence of the collected facial feature vectors includes: passing the sequence of the collected facial feature vectors through a feature clustering module based on essential features to obtain an essential semantic facial feature vector of the collected face; performing clustering optimization on the essential semantic facial feature vector of the collected face to obtain an optimized essential semantic facial feature vector of the collected face; calculating a facial semantic feature similarity metric coefficient between the verified facial feature vector and the optimized essential semantic facial feature vector of the collected face; and determining whether the verification passes based on a comparison between the facial semantic feature similarity metric coefficient and a predetermined threshold.

[0018] In the above information management method for a cloud platform, passing the sequence of the collected facial feature vectors through a feature clustering module based on essential features to obtain an essential semantic facial feature vector of the collected face includes: processing the sequence of the collected facial feature vectors with the following feature clustering formula to obtain the essential semantic facial feature vector of the collected face; where the feature clustering formula is:

[0019]

[0020]

[0021] where is the th collected facial feature vector in the sequence of the collected facial feature vectors, is the th collected facial feature vector in the sequence of the collected facial feature vectors, represents the 1-norm of the feature vector, is the length of the sequence of the collected facial feature vectors minus one, is the representation of the sequence of the collected facial feature vectors, represents the semantic feature difference coefficient, represents the natural exponential function operation, represents the total number of the semantic feature difference coefficients, is the essential semantic facial feature vector of the collected face.

[0022] In the above information management method for a cloud platform, performing clustering optimization on the essential semantic facial feature vector of the collected face to obtain an optimized essential semantic facial feature vector of the collected face includes: clustering each eigenvalue of the essential semantic facial feature vector of the collected face; and performing optimization based on the within-class and between-class characteristics of the clusters to obtain the optimized essential semantic facial feature vector of the collected face.

[0023] In the above information management method for a cloud platform, calculating the face semantic feature similarity metric coefficient between the verified face feature vector and the optimized acquired face essential semantic feature vector includes: calculating the face semantic feature similarity metric coefficient between the verified face feature vector and the optimized acquired face essential semantic feature vector using the following semantic feature similarity metric formula; wherein, the semantic feature similarity metric formula is:

[0024]

[0025] Wherein, is the verified face feature vector, is the optimized acquired face essential semantic feature vector, is the dimension of the verified face feature vector, is the face semantic feature similarity metric coefficient, represents the logarithmic function operation with base 2.

[0026] In a second aspect, there is provided an information management system for a cloud platform, which includes:

[0027] An identity information recognition module, configured to add the ID certificate file of the enterprise legal person and recognize the identity information of the enterprise legal person;

[0028] A face information verification module, configured to perform face information recognition on the enterprise legal person and verify the face information of the enterprise legal person;

[0029] A business license information verification module, configured to add the enterprise business license, recognize the business license information of the enterprise business license, compare the industrial and commercial business information, and verify the authenticity of the business license information;

[0030] A secondary confirmation module, configured to perform secondary confirmation on the identity information of the enterprise legal person and the business license information of the enterprise business license by the enterprise user;

[0031] An authorization selection module, configured to allow the enterprise user to select the types of business data to be authorized and the institutions to be authorized;

[0032] An online authorization file signing module, configured to allow the enterprise user to sign an online authorization file.

[0033] Compared with the prior art, the information management system and method for a cloud platform in the present application add the identity certificate file of the corporate legal person, identify the identity information of the corporate legal person; perform face information recognition on the corporate legal person and verify the face information of the corporate legal person; add the business license of the enterprise, identify the business license information of the business license of the enterprise, compare the industrial and commercial business information, and verify the authenticity of the business license information; have the enterprise user perform secondary confirmation on the identity information of the corporate legal person and the business license information of the business license of the enterprise; have the enterprise user select the types of business data to be authorized and the institutions to be authorized; and have the enterprise user sign an online authorization document. In this way, the true identity of the corporate legal person can be ensured, and the security and credibility of the information management system can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following descriptions are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 It is a flowchart of an information management method for a cloud platform according to an embodiment of the present application.

[0036] Figure 2 It is a schematic structural diagram of an information management method for a cloud platform according to an embodiment of the present application.

[0037] Figure 3 It is a block diagram of an information management system for a cloud platform according to an embodiment of the present application.

[0038] Figure 4 It is a schematic diagram of a scenario of an information management method for a cloud platform according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0040] Unless otherwise specified, all technical and scientific terms used in the embodiments of the present application have the same meaning as commonly understood by those of ordinary skill in the technical field of the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the scope of the present application.

[0041] In the description of the embodiments of the present application, it should be noted that unless otherwise specified and defined, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection, or the connection inside two components. It can be directly connected, or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meaning of the above terms can be understood according to specific circumstances.

[0042] It should be noted that the terms "first / second / third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged in a specific order or sequence when permitted. It should be understood that the objects distinguished by "first / second / third" can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here.

[0043] Currently, there is a lack of a unified, standard, and trustworthy information management system and method on the cloud platform, which brings a series of problems to enterprise users when using the cloud platform. First of all, enterprise users need to provide different certification and authorization documents to different institutions, which increases the workload and cost of enterprise users. Secondly, enterprise users cannot effectively control the scope of use and permissions of their business data, which may lead to problems such as the abuse or theft of business data.

[0044] On the current cloud platform, due to the lack of a unified information management system and method, enterprise users need to frequently provide different certification and authorization documents to different institutions. This situation not only increases the workload of enterprise users, but also results in additional time and financial costs. If there is a unified and trustworthy information management system, enterprise users can manage their information and authorizations on the cloud platform more efficiently, thereby reducing unnecessary repetitive work and costs.

[0045] In addition, due to the lack of a unified and standard data management method, enterprise users cannot effectively control the scope of use and permissions of their business data, which may lead to the abuse or theft of business data, bringing potential risks and losses to the enterprise. Therefore, establishing a unified, standard, and trustworthy information management system and method is crucial for protecting enterprise data security.

[0046] To solve these problems, the cloud platform can consider introducing an authentication and authorization system based on blockchain technology. Blockchain technology can provide a decentralized and tamper-proof authentication and authorization mechanism, thereby helping enterprise users manage their information and permissions on the cloud platform more effectively. In addition, it is also crucial to formulate unified data management standards and methods to ensure that enterprise users can effectively control the scope of use and permissions of their business data. The cloud platform can help enterprise users manage their information and permissions more efficiently, thereby reducing the workload and risks and improving the overall security and efficiency.

[0047] Figure 1 The flowchart of the information management method for a cloud platform according to an embodiment of the present application. As Figure 1 shown, the information management method for a cloud platform includes: S110, adding the identity certificate file of the legal person of the enterprise and identifying the identity information of the legal person of the enterprise; S120, performing face information recognition on the legal person of the enterprise and verifying the face information of the legal person of the enterprise; S130, adding the business license of the enterprise, identifying the business license information of the business license of the enterprise, comparing the industrial and commercial business information, and verifying the authenticity of the business license information; S140, having the enterprise user perform a secondary confirmation on the identity information of the legal person of the enterprise and the business license information of the business license of the enterprise; S150, having the enterprise user select the types of business data to be authorized and the institutions to be authorized; S160, having the enterprise user sign an online authorization document.

[0048] Among them, in order to prevent identity theft and fraud, it is necessary to perform face information recognition on the legal person of the enterprise and verify its face information to ensure the true identity of the legal person of the enterprise and improve the security and credibility of the information management system. In the prior art, face information recognition of the legal person of the enterprise is usually performed by comparing the photo on the identity certificate file with the face photo taken in real time to determine whether they are the same person. The problem with this method is that the face photo taken may be affected by factors such as light, angle, and expression, resulting in misjudgment or missed judgment. Therefore, an optimized solution is expected.

[0049] To address the above technical problems, the technical concept of the present application is: using image processing technology based on deep learning to jointly analyze the sequence of the face image for verification and the real-time face acquisition image, mine the face features expressed by each, and establish a similarity correlation relationship between the two, thereby realizing the recognition and verification of the face information of the legal person of the enterprise based on this similarity correlation relationship.

[0050] Figure 2 The schematic diagram of the architecture of the information management method for a cloud platform according to an embodiment of the present application. As Figure 2As shown, face information of the legal person of the enterprise is identified, and the face information of the legal person of the enterprise is verified, including: First, obtain the verification face image of the legal person of the enterprise; Then, obtain the sequence of real-time face capture images of the legal person of the enterprise collected by multiple cameras; Next, extract the face features of the verification face image and the sequence of real-time face capture images to obtain the verification face feature vector and the sequence of captured face feature vectors; Finally, determine whether the verification passes based on the semantic difference of face features between the verification face feature vector and the sequence of captured face feature vectors.

[0051] First, obtain the verification face image of the legal person of the enterprise to ensure that the obtained face image is legal and authorized. By using the face image, it can be ensured that the image used is legal and trustworthy, which helps to improve the reliability of the entire verification process. Then, obtain the sequence of real-time face capture images of the legal person of the enterprise collected by multiple cameras, and ensure that the positions and angles of the cameras can fully cover all aspects of the face to obtain comprehensive face information. The sequence of real-time face images collected by multiple cameras can provide more dimensional face information, which helps to improve the accuracy and robustness of face recognition. Next, extract the face features of the verification face image and the sequence of real-time face capture images to obtain the verification face feature vector and the sequence of captured face feature vectors, and ensure the accuracy and stability of the face feature extraction algorithm to obtain reliable face feature vectors. By extracting the face feature vectors, the face information can be transformed into more representative and comparable numerical features, providing a reliable data basis for subsequent face feature comparison. Finally, determine whether the verification passes based on the semantic difference of face features between the verification face feature vector and the sequence of captured face feature vectors, and ensure that the comparison algorithm between the face feature vectors can accurately evaluate the semantic difference of face features for effective verification. By comparing the semantic differences of the face feature vectors, it can be more accurately judged whether the verification passes, thereby improving the accuracy and security of face verification.

[0052] Based on this, in the technical solution of this application, the process of identifying the face information of the legal person of the enterprise and verifying the encoding of the face information of the legal person of the enterprise includes: First, obtain the verification face image of the legal person of the enterprise; and obtain the sequence of real-time face capture images of the legal person of the enterprise collected by multiple cameras. Here, obtaining the verification face image of the legal person of the enterprise is to obtain the face image of the legal person of the enterprise. The verification face image refers to the face image obtained for verifying the authenticity of the identity of the legal person of the enterprise. In the information management system, by comparing the obtained verification face image with the real-time face photo provided by the legal person of the enterprise, it can be determined whether they are the same person. It is worth mentioning that in the process of obtaining the verification face image of the legal person of the enterprise, legal authorization or permission needs to be obtained in order to be able to access and use the face image data. In this way, using the verified face image as a reference can improve the accuracy and credibility of face information recognition and verification. At the same time, obtaining the sequence of real-time face capture images of the legal person of the enterprise collected by multiple cameras is to obtain face images from multiple angles and perspectives, so as to increase the verification and confirmation of the authenticity of the identity of the legal person of the enterprise. It should be understood that different cameras can capture face images from different angles and perspectives, and can more comprehensively capture the facial features of the legal person of the enterprise. This can reduce the recognition error caused by the camera angle and improve the accuracy of face information recognition and verification.

[0053] Then, pass the verification face image through a face feature extractor based on a convolutional neural network model to obtain a verification face feature vector; at the same time, pass the sequence of real-time face capture images through the face feature extractor based on the convolutional neural network model to obtain a sequence of captured face feature vectors. Here, considering that the Convolutional Neural Network (CNN) model has excellent performance in image processing and feature extraction. Specifically, CNN can automatically learn the features in the image, so as to be able to extract the key features in the face image, such as facial contours, eyes, nose, etc. These features play an important role in face recognition. In this way, through the face feature extractor based on the convolutional neural network model, discriminative face features are extracted from the verification face image and the sequence of real-time face capture images, so as to transform the image into a vector representation with higher dimension and richer expression ability for accurate and reliable face recognition and identity verification.

[0054] In a specific embodiment of this application, extracting the face features of the verification face image and the sequence of real-time face capture images to obtain a verification face feature vector and a sequence of captured face feature vectors includes: using a deep learning network model to perform feature extraction on the verification face image and the sequence of real-time face capture images to obtain the verification face feature vector and the sequence of captured face feature vectors.

[0055] Among them, the deep learning network model is a face feature extractor based on a convolutional neural network model.

[0056] Furthermore, using the deep learning network model to extract features from the sequence of the verification face image and the real-time face acquisition images to obtain the sequence of the verification face feature vectors and the acquisition face feature vectors includes: passing the verification face image through the face feature extractor based on the convolutional neural network model to obtain the verification face feature vector; passing the sequence of the real-time face acquisition images through the face feature extractor based on the convolutional neural network model to obtain the sequence of the acquisition face feature vectors.

[0057] In an embodiment of the present application, determining whether the verification passes based on the semantic difference of face features between the sequence of the verification face feature vectors and the sequence of the acquisition face feature vectors includes: passing the sequence of the acquisition face feature vectors through a feature clustering module based on essential features to obtain the acquisition face essential semantic feature vectors; performing clustering optimization on the acquisition face essential semantic feature vectors to obtain the optimized acquisition face essential semantic feature vectors; calculating the face semantic feature similarity metric coefficient between the verification face feature vector and the optimized acquisition face essential semantic feature vectors; determining whether the verification passes based on the comparison between the face semantic feature similarity metric coefficient and a predetermined threshold.

[0058] Considering that the sequence of the real-time face acquisition images of the corporate legal person collected by multiple cameras provides face information of the corporate legal person from multiple angles and perspectives, but at the same time brings a large amount of redundancy, and these redundancies will affect subsequent analysis and processing. Therefore, in the technical solution of the present application, passing the sequence of the acquisition face feature vectors through a feature clustering module based on essential features to capture the core face features and essential semantic expressions in the sequence of the acquisition face feature vectors, thereby obtaining the acquisition face essential semantic feature vectors. Specifically, the feature clustering module based on essential features can automatically select and emphasize important regions in the face feature distribution, while weakening or ignoring those redundant features. This can reduce the influence of redundant information and noise existing in the sequence of the real-time face acquisition images and gather more important and useful semantic information together.

[0059] In a specific embodiment of the present application, passing the sequence of the acquisition face feature vectors through a feature clustering module based on essential features to obtain the acquisition face essential semantic feature vectors includes: processing the sequence of the acquisition face feature vectors with the following feature clustering formula to obtain the acquisition face essential semantic feature vectors; where the feature clustering formula is:

[0060]

[0061]

[0062] Among them, is the th face feature vector collected in the sequence of collecting face feature vectors, is the th face feature vector collected in the sequence of collecting face feature vectors, represents the 1-norm of the feature vector, is one less than the length of the sequence of collecting face feature vectors, is the representation of the sequence of collecting face feature vectors, represents the semantic feature difference coefficient, represents the natural exponential function operation, represents the total number of the semantic feature difference coefficients, is the essential semantic feature vector of the collected face.

[0063] In particular, in the technical solution of this application, each face feature vector collected in the sequence of collecting face feature vectors respectively represents the image semantic features of multi-angle face collection images of the enterprise legal person to be verified. Considering that each real-time face collection image of the enterprise legal person in the sequence of real-time face collection images of the enterprise legal person is taken from different angles of the enterprise legal person to be verified, this makes there be an obvious difference in the pixel distribution of the image source domain among each real-time face collection image of the enterprise legal person in the sequence of real-time face collection images of the enterprise legal person, that is, there is an inconsistency in the image semantic distribution among each face feature vector collected in the sequence of collecting face feature vectors.

[0064] Thus, when passing the sequence of collecting face feature vectors through the feature clustering module based on the essential features to obtain the essential semantic feature vector of the collected face, considering that due to the inconsistency in the image semantic feature distribution of each face feature vector collected, the significance of its respective feature distribution information based on the image semantic feature distribution will also be affected, that is, the essential semantic feature vector of the collected face has local feature distribution discreteness as a whole of the feature distribution, thereby affecting the calculation accuracy of the face semantic feature similarity measurement coefficient between the essential semantic feature vector of the collected face and the face feature vector to be verified.

[0065] Based on this, the present application performs clustering optimization on the collected human face essential semantic feature vectors to obtain optimized collected human face essential semantic feature vectors. That is, first, clustering is performed on each eigenvalue of the collected human face essential semantic feature vectors, for example, clustering based on the distance between eigenvalues, and then optimization is performed based on the within-class and between-class characteristics of the clustered features to obtain the optimized collected human face essential semantic feature vectors.

[0066] In a specific embodiment of the present application, optimization is performed based on the within-class and between-class characteristics of the clustered features to obtain the optimized collected human face essential semantic feature vectors, including: optimizing based on the within-class and between-class characteristics of the clustered features with the following clustering optimization formula to obtain the optimized collected human face essential semantic feature vectors; wherein, the clustering optimization formula is:

[0067]

[0068] Wherein, are the respective eigenvalues of the collected human face essential semantic feature vectors, is the number of feature sets corresponding to the collected human face essential semantic feature vectors, is the number of clustering features, is the natural constant, represents the clustering feature set, are the respective eigenvalues of the optimized collected human face essential semantic feature vectors.

[0069] Specifically, by using the within-class and between-class features of the collected human face essential semantic feature vectors as different instance roles to perform class instance description based on the clustering proportion distribution, and introducing the clustering response history based on the within-class and between-class dynamic contexts, a global perspective that maintains coordination between the within-class distribution and the between-class distribution of the overall features of the collected human face essential semantic feature vectors is achieved, so that the optimized feature clustering operation for the collected human face essential semantic feature vectors can maintain a coherent and consistent response for the within-class and between-class features, thereby improving the feature distribution convergence of the collected human face essential semantic feature vectors as a whole feature distribution. In this way, the calculation accuracy of the face semantic feature similarity measurement coefficient between the collected human face essential semantic feature vectors and the verification human face feature vectors is improved.

[0070] Subsequently, calculate the face semantic feature similarity metric coefficient between the verified face feature vector and the optimized acquired face essential semantic feature vector; and determine whether the verification passes based on the comparison between the face semantic feature similarity metric coefficient and a predetermined threshold. That is, by calculating the face semantic feature similarity metric coefficient, measure the similarity between the face features in the verification information expressed by the verified face feature vector and the real-time face features expressed by the acquired face essential semantic feature vector, so as to perform face recognition and identity verification based on this similarity. In the actual application process of this application, by adjusting the predetermined threshold, the strictness of the verification can be flexibly controlled. In this way, the sensitivity of the verification can be adjusted according to specific application scenarios and requirements.

[0071] In a specific embodiment of this application, calculating the face semantic feature similarity metric coefficient between the verified face feature vector and the optimized acquired face essential semantic feature vector includes: calculating the face semantic feature similarity metric coefficient between the verified face feature vector and the optimized acquired face essential semantic feature vector using the following semantic feature similarity metric formula; wherein, the semantic feature similarity metric formula is:

[0072]

[0073] Wherein, is the verified face feature vector, is the optimized acquired face essential semantic feature vector, is the dimension of the verified face feature vector, is the face semantic feature similarity metric coefficient, represents the logarithmic function operation with base 2.

[0074] In summary, the information management method for a cloud platform based on the embodiments of this application is elucidated. It uses image processing technology based on deep learning to jointly analyze the sequences of verified face images and real-time face acquisition images, mine the face features expressed by each of them, and establish a similarity correlation relationship between the two, so as to realize the recognition and verification of the face information of enterprise legal persons based on this similarity correlation relationship.

[0075] In an embodiment of this application, an intelligent management cloud platform is provided, and its product specifications include hardware specifications and software specifications. Among them, the hardware specifications are shown in Table 1 below, and the software specifications are shown in Table 2 below:

[0076] Table 1 Hardware Specifications

[0077] Serial number Configuration CN8060 CN8061 1 Power supply 220V 220V 2 CPU i7 i7 3 Motherboard Seavo:SV1-H312A Seavo: SV4-H11A6 4 Memory 16G 16G 5 System disk Solid state drive 256G Solid state drive 256G 6 Storage disk Standard configuration 1T Standard configuration 1T 7 Expansion disk Not supported Supported (7 pieces) 8 Display screen LCD screen 7-inch color liquid crystal touch screen 9 Chassis 2U 4U 10 Serial port (COM) 1 piece 2 pieces

[0078] Table 2 Software Specifications

[0079] Serial number Configuration CN8060 CN8061 1 System Linux-Ubuntu16.04 Linux-Ubuntu16.04 2 Database PG database PG database 3 Number of customers 2000 5000 4 Video device 500 devices / 1000 channels 1500 devices / 3000 channels 5 Concurrency D1 video concurrency 100 channels D1 video concurrency 200 channels 6 Number of alarm messages 2000W 2000W

[0080] In one embodiment of the present application, Figure 3 is a block diagram of an information management system for a cloud platform according to an embodiment of the present application. As Figure 3 shown, the information management system 200 for a cloud platform according to an embodiment of the present application includes: an identity information recognition module 210, configured to add an identity certificate file of an enterprise legal person and recognize the identity information of the enterprise legal person; a face information verification module 220, configured to perform face information recognition on the enterprise legal person and verify the face information of the enterprise legal person; a business license information verification module 230, configured to add an enterprise business license, recognize the business license information of the enterprise business license, compare the industrial and commercial business information, and verify the authenticity of the business license information; a secondary confirmation module 240, configured to perform secondary confirmation on the identity information of the enterprise legal person and the business license information of the enterprise business license by an enterprise user; an authorization selection module 250, configured to allow the enterprise user to select the types of business data to be authorized and the institutions to be authorized; and an online authorization document signing module 260, configured to allow the enterprise user to sign an online authorization document.

[0081] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above information management system for a cloud platform have been described in detail in the description of the information management method for a cloud platform with reference to Figure 1 to Figure 2 above, and therefore, the repeated description thereof will be omitted.

[0082] As described above, the information management system 200 for a cloud platform according to an embodiment of the present application can be implemented in various terminal devices, such as a server for information management of a cloud platform, etc. In one example, the information management system 200 for a cloud platform according to an embodiment of the present application can be integrated into a terminal device as a software module and / or a hardware module. For example, the information management system 200 for a cloud platform can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the information management system 200 for a cloud platform can also be one of many hardware modules of the terminal device.

[0083] Alternatively, in another example, the information management system 200 for a cloud platform and the terminal device can also be separate devices, and the information management system 200 for a cloud platform can be connected to the terminal device through a wired and / or wireless network and transmit interaction information in accordance with a predefined data format.

[0084] Figure 4 is a scenario schematic diagram of an information management method for a cloud platform according to an embodiment of the present application. AsFigure 4 As shown, in this application scenario, first, obtain the verified face image of the enterprise legal person (for example, C1 as illustrated in Figure 4 ); and obtain the sequence of real-time face capture images of the enterprise legal person collected by multiple cameras (for example, C2 as illustrated in Figure 4 ); then, input the obtained verified face image and the sequence of real-time face capture images into a server (for example, S as illustrated in Figure 4 ) that deploys an information management algorithm for the cloud platform, where the server can process the verified face image and the sequence of real-time face capture images based on the information management algorithm for the cloud platform to determine whether the verification passes.

[0085] It should also be noted that in the devices, equipment, and methods of this application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of this application.

[0086] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0087] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article, or terminal device comprising the element.

[0088] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

Claims

1. An information management method for a cloud platform, characterized in that: include: Add the ID card document of the corporate legal person to identify the identity information of the corporate legal person; Performing facial information recognition on the corporate legal person and verifying the facial information of the corporate legal person; Add the business license of the enterprise, identify the business license information of the business license of the enterprise, compare the industrial and commercial business information, and verify the authenticity of the business license information; The corporate user conducts a second confirmation of the identity information of the corporate legal person and the business license information of the corporate business license; The enterprise user selects the type of business data that needs to be authorized and the institution that needs to be authorized; The online authorization document is signed by the enterprise user.

2. The information management method for a cloud platform according to claim 1, characterized in that: Performing facial information recognition on the corporate legal person and verifying the facial information of the corporate legal person includes: Obtain the verification face image of the corporate legal person; Acquire a sequence of real-time facial images of the corporate legal person captured by multiple cameras; Extracting facial features of the sequence of the verification facial image and the real-time facial acquisition image to obtain a sequence of a verification facial feature vector and an acquisition facial feature vector; Based on the facial feature semantic differences between the verification facial feature vector and the sequence of collected facial feature vectors, it is determined whether the verification is passed.

3. The information management method for a cloud platform according to claim 2, characterized in that: Extracting facial features of the sequence of the verification facial image and the real-time facial acquisition image to obtain a sequence of a verification facial feature vector and an acquisition facial feature vector, comprising: A deep learning network model is used to perform feature extraction on the sequence of the verification face image and the real-time face acquisition image to obtain a sequence of the verification face feature vector and the acquisition face feature vector.

4. The information management method for a cloud platform according to claim 3, characterized in that: The deep learning network model is a face feature extractor based on a convolutional neural network model.

5. The information management method for a cloud platform according to claim 4, characterized in that: Using a deep learning network model to extract features from the sequence of the verification face image and the real-time face acquisition image to obtain a sequence of the verification face feature vector and the acquisition face feature vector, comprising: Passing the verification face image through the face feature extractor based on the convolutional neural network model to obtain the verification face feature vector; The sequence of real-time face collection images is passed through the face feature extractor based on the convolutional neural network model to obtain the sequence of collected face feature vectors.

6. The information management method for a cloud platform according to claim 5, characterized in that: Determining whether verification is passed based on the semantic difference of facial features between the verification facial feature vector and the sequence of collected facial feature vectors includes: Passing the sequence of collected face feature vectors through a feature clustering module based on essential features to obtain an essential semantic feature vector of the collected face; Performing clustering optimization on the collected face essential semantic feature vector to obtain an optimized collected face essential semantic feature vector; Calculate the facial semantic feature similarity measurement coefficient between the verified facial feature vector and the optimized collected facial essential semantic feature vector; Based on the comparison between the facial semantic feature similarity measurement coefficient and a predetermined threshold, it is determined whether the verification is passed.

7. The information management method for a cloud platform according to claim 6, characterized in that: The sequence of collected face feature vectors is passed through a feature clustering module based on essential features to obtain an essential semantic feature vector of the collected face, including: The sequence of the collected face feature vectors is processed using the following feature clustering formula to obtain the essential semantic feature vector of the collected face; wherein the feature clustering formula is: in, is the first in the sequence of collecting facial feature vectors Collect facial feature vectors, is the first in the sequence of collecting facial feature vectors Collect facial feature vectors, represents the 1-norm of the eigenvector, is the length of the sequence of collected facial feature vectors minus one, is a representation of the sequence of collected facial feature vectors, represents the semantic feature difference coefficient, represents the natural exponential function operation, represents the total number of difference coefficients of the semantic features, The method is to collect the essential semantic feature vector of the face.

8. The information management method for a cloud platform according to claim 7, characterized in that: Clustering and optimizing the collected face essential semantic feature vector to obtain an optimized collected face essential semantic feature vector includes: Clustering each eigenvalue of the collected face essential semantic feature vector; Based on the clustered feature in-class and out-of-class representations, optimization is performed to obtain the optimized essential semantic feature vector of the collected face.

9. The information management method for a cloud platform according to claim 8, characterized in that: Calculating the facial semantic feature similarity measurement coefficient of the verified facial feature vector and the optimized collected facial essential semantic feature vector, including: The facial semantic feature similarity measurement coefficient of the verification facial feature vector and the optimized acquired facial essential semantic feature vector is calculated using the following semantic feature similarity measurement formula; wherein the semantic feature similarity measurement formula is: in, is the verification face feature vector, The optimized essential semantic feature vector of the face is collected. is the dimension of the verification face feature vector, is the similarity measurement coefficient of the facial semantic features, Represents the logarithmic function operation with base 2.

10. An information management system for a cloud platform, characterized in that: include: An identity information recognition module is used to add the identity card and license documents of the corporate legal person to identify the identity information of the corporate legal person; A face information verification module, used to perform face information recognition on the corporate legal person and verify the face information of the corporate legal person; A business license information verification module is used to add a business license of an enterprise, identify the business license information of the business license of the enterprise, compare the industrial and commercial business information, and verify the authenticity of the business license information; A secondary confirmation module, used for the enterprise user to conduct secondary confirmation of the identity information of the enterprise legal person and the business license information of the enterprise business license; An authorization selection module, used for the enterprise user to select the type of business data that needs to be authorized and the institution that needs to be authorized; The online authorization document signing module is used for the enterprise user to sign the online authorization document.

Images