Service processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a business processing method and device, a storage medium and electronic equipment, and relates to the technical field of block chains. The method comprises the steps that when it is detected that a to-be-detected object handles a financial service, facial features of the to-be-detected object are collected, and current facial feature information is obtained; according to the target information of the to-be-detected object, obtaining pre-stored target facial feature information of a target object from the block chain; judging whether the to-be-detected object is a target object or not according to the current facial feature information and the target facial feature information; and if the to-be-detected object is not the target object, acquiring expression features of the to-be-detected object to obtain current expression feature information, and determining a processing result of the financial service according to the current expression feature information and the target expression feature information. Through application of the method and the device, the problem that the effect of handling financial business for a user by adopting a face recognition technology is poorer due to poorer face recognition effect in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of blockchain technology, and more specifically, to a business processing method and device, a storage medium, and an electronic device. Background Art

[0002] At present, the application of face recognition technology is very extensive. In terms of banking business, many bank ATMs (Automated Teller Machines) have introduced face recognition functions. Customers do not need to carry physical bank cards or enter passwords. They can complete withdrawal or deposit operations through facial recognition. This function is particularly popular among the elderly because it simplifies the operation process and reduces the difficulty of operation. Some banks also use face recognition technology in counter business to verify customer identity and ensure the authenticity and security of business handling. However, in the existing face recognition process, face recognition is easily blocked by light, which affects the judgment and recognition of the face, resulting in the inability to recognize the face. It takes multiple recognitions to get a judgment. In an environment with insufficient light or too strong light, the accuracy of face recognition will also drop significantly. In addition, facial obstructions will also affect the effect of face recognition, resulting in inaccurate recognition or recognition failure, reducing the efficiency and accuracy of recognition, which will lead to poor results in using face recognition technology to handle financial services for users.

[0003] Currently, no effective solution has been proposed to address the problem that the effect of face recognition in related technologies is poor, resulting in poor results in using face recognition technology to handle financial services for users. Summary of the invention

[0004] The main purpose of this application is to provide a business processing method and device, storage medium and electronic device to solve the problem that the face recognition effect in the related technology is poor, resulting in poor effect of using face recognition technology to handle financial services for users.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for processing a business is provided. The method includes: when it is detected that the object to be detected is handling financial business, the facial features of the object to be detected are collected to obtain the current facial feature information; according to the target information of the object to be detected, the target facial feature information of the target object pre-stored is obtained from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, the account information provided by the object to be detected; according to the current facial feature information and the target facial feature information, it is judged whether the object to be detected is the target object; if the object to be detected is not the target object, the expression features of the object to be detected are collected to obtain the current expression feature information, and according to the current expression feature information and the target expression feature information, the processing result of the financial business is determined, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether the financial business is allowed to be handled for the object to be detected.

[0006] Furthermore, before obtaining pre-stored target facial feature information of the target object from the blockchain based on the target information of the object to be detected, the method also includes: obtaining facial image data of the target object, and extracting feature information of the facial image data of the target object to obtain the target facial feature information; and storing the target facial feature information in the blockchain.

[0007] Furthermore, judging whether the object to be detected is the target object based on the current facial feature information and the target facial feature information includes: converting the current facial feature information into a feature vector to obtain a first feature vector; converting the target facial feature information into a feature vector to obtain a second feature vector; calculating the distance information between the first feature vector and the second feature vector to obtain a target distance; judging whether the object to be detected is the target object based on the target distance.

[0008] Further, based on the target distance, determining whether the object to be detected is the target object includes: determining whether the target distance is greater than a preset distance; if the target distance is not greater than the preset distance, determining that the object to be detected is the target object; if the target distance is greater than the preset distance, determining that the object to be detected is not the target object.

[0009] Furthermore, determining the processing result of the financial service based on the current expression feature information and the target expression feature information includes: judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information; if the object to be detected is not the target object, outputting a prohibition instruction to indicate that the financial service is prohibited from being processed for the object to be detected; if the object to be detected is the target object, outputting a processing instruction to indicate that the financial service is processed for the object to be detected.

[0010] Furthermore, judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information includes: calculating the similarity between the current expression feature information and the target expression feature information to obtain a target similarity; judging whether the target similarity is greater than a preset similarity; if the target similarity is not greater than the preset similarity, determining that the object to be detected is the target object; if the target similarity is greater than the preset similarity, determining that the object to be detected is not the target object.

[0011] Furthermore, when it is detected that the object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information, including: when it is detected that the object to be detected is handling financial business, facial image data of the object to be detected is acquired, and the facial image data of the object to be detected is pre-processed to obtain processed facial image data; feature extraction processing is performed on the processed facial image data to obtain the current facial feature information.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a business processing device is provided. The device includes: a first acquisition unit, which is used to collect facial features of the object to be detected when it is detected that the object to be detected is handling financial business, and obtain current facial feature information; a first acquisition unit, which is used to obtain the target facial feature information of the target object pre-stored from the blockchain according to the target information of the object to be detected, wherein the target information is at least one of the following: the name of the object to be detected, the account information provided by the object to be detected; a first judgment unit, which is used to judge whether the object to be detected is the target object according to the current facial feature information and the target facial feature information; a first processing unit, which is used to collect the expression features of the object to be detected if the object to be detected is not the target object, obtain the current expression feature information, and determine the processing result of the financial business according to the current expression feature information and the target expression feature information, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether the financial business is allowed to be handled for the object to be detected.

[0013] Furthermore, the device also includes: a second processing unit, used to obtain facial image data of the target object and extract feature information of the facial image data of the target object to obtain the target facial feature information before obtaining the target facial feature information of the target object pre-stored in the blockchain based on the target information of the object to be detected; and a first storage unit, used to store the target facial feature information in the blockchain.

[0014] Furthermore, the first judgment unit includes: a first conversion module, used to convert the current facial feature information into a feature vector to obtain a first feature vector; a second conversion module, used to convert the target facial feature information into a feature vector to obtain a second feature vector; a first calculation module, used to calculate the distance information between the first feature vector and the second feature vector to obtain a target distance; and a first judgment module, used to judge whether the object to be detected is the target object based on the target distance.

[0015] Furthermore, the first judgment module includes: a first judgment submodule, used to judge whether the target distance is greater than a preset distance; a first determination submodule, used to determine that the object to be detected is the target object if the target distance is not greater than the preset distance; and a second determination submodule, used to determine that the object to be detected is not the target object if the target distance is greater than the preset distance.

[0016] Furthermore, the first processing unit includes: a second judgment module, used to judge whether the object to be detected is the target object based on the current expression feature information and the target expression feature information; a first processing module, used to output a prohibition instruction if the object to be detected is not the target object, to indicate that the financial business is prohibited for the object to be detected; and a second processing module, used to output a processing instruction if the object to be detected is the target object, to indicate that the financial business is handled for the object to be detected.

[0017] Furthermore, the second judgment module includes: a first calculation submodule, used to calculate the similarity between the current expression feature information and the target expression feature information to obtain the target similarity; a second judgment submodule, used to determine whether the target similarity is greater than a preset similarity; a third determination submodule, used to determine that the object to be detected is the target object if the target similarity is not greater than the preset similarity; and a fourth determination submodule, used to determine that the object to be detected is not the target object if the target similarity is greater than the preset similarity.

[0018] Furthermore, the first acquisition unit includes: a third processing module, which is used to obtain facial image data of the object to be detected when it is detected that the object to be detected is handling financial business, and pre-process the facial image data of the object to be detected to obtain processed facial image data; a fourth processing module, which is used to perform feature extraction processing on the processed facial image data to obtain the current facial feature information.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein the program executes any one of the above-mentioned service processing methods.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, which includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned service processing methods.

[0021] Through the present application, the following steps are adopted: when it is detected that the object to be detected is handling financial business, the facial features of the object to be detected are collected to obtain current facial feature information; according to the target information of the object to be detected, the target facial feature information of the target object pre-stored is obtained from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, the account information provided by the object to be detected; according to the current facial feature information and the target facial feature information, it is judged whether the object to be detected is the target object; if the object to be detected is not the target object, the expression features of the object to be detected are collected to obtain current expression feature information, and according to the current expression feature information and the target expression feature information, the processing result of the financial business is determined, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial business for the object to be detected, which solves the problem that the effect of face recognition in the related technology is poor, resulting in poor effect of using face recognition technology to handle financial business for users. By adding facial expression recognition to traditional facial recognition, a double verification mechanism is formed, and the entered facial expression features and facial features are stored on the blockchain. The facial feature information and facial expression feature information stored on the blockchain are extremely secure and cannot be tampered with, which can effectively protect the user's data security. Through the double verification method, the efficiency of recognition can be improved, the number of recognition errors can be reduced, and suspicious persons can be discovered in a timely manner, thereby improving the effect of handling financial services for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 is a flowchart of a method for processing a service provided in an embodiment of the present application;

[0024] Figure 2 It is a flowchart of a bank branch face recognition method based on blockchain provided in an embodiment of the present application;

[0025] Figure 3 is a flowchart of the facial recognition steps in an embodiment of the present application;

[0026] Figure 4 is a flow chart of the expression feature recognition steps in an embodiment of the present application;

[0027] Figure 5 is a schematic diagram of a face recognition device provided according to an embodiment of the present application;

[0028] Figure 6 is a schematic diagram of a service processing device provided according to an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0034] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0035] Blockchain is a decentralized distributed ledger technology that is tamper-proof, secure and reliable. It combines multiple technologies such as distributed storage, peer-to-peer transmission, consensus mechanism and cryptography.

[0036] Face recognition technology is a biometric technology based on facial feature information. It uses computer technology of analysis and comparison to identify faces. Face recognition technology refers to computer technology that uses facial visual feature information to identify identity. It extracts and analyzes facial features in face images or video streams to achieve individual identity recognition.

[0037] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flowchart of a method for processing a service provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0038] Step S101, when it is detected that the subject to be detected is handling financial business, facial features of the subject to be detected are collected to obtain current facial feature information.

[0039] For example, when a user (corresponding to the object to be detected mentioned above) is handling a business (corresponding to the financial business mentioned above), the user places his face in front of the recognition system so that the recognition system can capture the facial features of the user (corresponding to the object to be detected mentioned above). Then the recognition system can obtain the facial feature information of the user (corresponding to the object to be detected mentioned above) (corresponding to the current facial feature information mentioned above).

[0040] Step S102, based on the target information of the object to be detected, obtain the target facial feature information of the target object pre-stored from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, and the account information provided by the object to be detected.

[0041] For example, the recognition system can obtain pre-stored user facial feature information (corresponding to the above-mentioned target facial feature information) from the blockchain based on the name and / or account information of the user (corresponding to the above-mentioned object to be detected).

[0042] Step S103, judging whether the object to be detected is the target object according to the current facial feature information and the target facial feature information.

[0043] For example, the recognition system compares the captured facial feature information (corresponding to the above-mentioned object to be detected) of the user (corresponding to the above-mentioned object to be detected) with the user facial feature information (corresponding to the above-mentioned target facial feature information) pre-stored in the blockchain to determine whether the user (corresponding to the above-mentioned object to be detected) and the target object are the same person.

[0044] Step S104: if the object to be detected is not the target object, the facial expression features of the object to be detected are collected to obtain current facial expression feature information, and the processing result of the financial service is determined based on the current facial expression feature information and the target facial expression feature information, wherein the target facial expression feature information is the facial expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial services for the object to be detected.

[0045] For example, if it is determined that the user (corresponding to the above-mentioned object to be detected) and the target object are not the same person, the recognition system prompts the user (corresponding to the above-mentioned object to be detected) to make an expression feature, and again compares the expression feature information of the user (corresponding to the above-mentioned object to be detected) (corresponding to the above-mentioned current expression feature information) with the user expression feature information pre-stored in the blockchain (corresponding to the above-mentioned target expression feature information). The expression features are combined with the facial features to further confirm the face. If they are consistent, it is determined to be the correct user, and at this time, financial services can be directly handled for the user (corresponding to the above-mentioned object to be detected); if they are inconsistent, it is determined to be an incorrect user, and at this time, financial services cannot be directly handled for the user (corresponding to the above-mentioned object to be detected).

[0046] For example, if it is determined that the user (corresponding to the above-mentioned object to be detected) and the target object are the same person, there is no need to compare the facial expression features. The user (corresponding to the above-mentioned object to be detected) can be directly determined to be the correct user, and financial services can be directly handled for the user (corresponding to the above-mentioned object to be detected).

[0047] Through the above steps S101 to S104, by adding the recognition of expression features on the basis of traditional facial recognition, a double verification mechanism is formed, and the entered expression features and facial features are stored on the blockchain. The facial feature information and expression feature information stored on the blockchain are extremely secure and cannot be tampered with, which can effectively protect the user's data security. Through the double verification method, the recognition efficiency can be improved, the recognition errors can be reduced, and suspicious persons can be discovered in time, thereby improving the effect of handling financial services for users.

[0048] Optionally, in the business processing method provided in the embodiment of the present application, when it is detected that the object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information, including: when it is detected that the object to be detected is handling financial business, facial image data of the object to be detected is obtained, and the facial image data of the object to be detected is pre-processed to obtain processed facial image data; feature extraction processing is performed on the processed facial image data to obtain current facial feature information.

[0049] For example, when handling business, the user (corresponding to the object to be detected mentioned above) places his face in front of the recognition system, so that the recognition system can capture the facial image data of the user (corresponding to the object to be detected mentioned above), pre-process the captured facial image data, and extract the features to obtain the facial feature information of the user (corresponding to the object to be detected mentioned above) (corresponding to the current facial feature information mentioned above).

[0050] Through the above solution, the user's facial feature information can be obtained quickly and accurately.

[0051] Optionally, in the service processing method provided in the embodiment of the present application, before obtaining pre-stored target facial feature information of the target object from the blockchain based on the target information of the object to be detected, the method further includes: obtaining facial image data of the target object, and extracting feature information of the facial image data of the target object to obtain target facial feature information; and storing the target facial feature information in the blockchain.

[0052] For example, when a user (corresponding to the target object mentioned above) enters his face in a bank branch, he can make a set of facial features, enter facial feature information (corresponding to the target facial feature information mentioned above) and the current facial feature information, and store it in the blockchain. Moreover, facial features can include angry expressions, happy expressions, sad expressions, etc., where users can randomly make corresponding expressions according to their own preferences and enter and store them in the blockchain in the recognition system.

[0053] Through the above scheme, the user's facial feature information and expression feature information can be conveniently stored in the blockchain, thereby ensuring the security of user data.

[0054] Optionally, in the service processing method provided in the embodiment of the present application, judging whether the object to be detected is the target object based on the current facial feature information and the target facial feature information includes: converting the current facial feature information into a feature vector to obtain a first feature vector; converting the target facial feature information into a feature vector to obtain a second feature vector; calculating the distance information between the first feature vector and the second feature vector to obtain the target distance; judging whether the object to be detected is the target object based on the target distance.

[0055] For example, the extracted facial features (corresponding to the current facial feature information mentioned above) can be converted into feature vectors (corresponding to the first feature vector mentioned above) based on a convolutional neural network method, and the user facial feature information pre-stored in the blockchain (corresponding to the target facial feature information mentioned above) can be converted into feature vectors (corresponding to the second feature vector mentioned above), and then the distance between the two sets of feature vectors (corresponding to the first feature vector and the second feature vector mentioned above) can be calculated to obtain the target distance mentioned above, and based on the distance between the two sets of feature vectors (corresponding to the first feature vector and the second feature vector mentioned above) (corresponding to the target distance mentioned above), it can be judged whether the user (corresponding to the object to be detected mentioned above) and the target object are the same person.

[0056] Through the above scheme, it is possible to quickly and accurately determine whether the object to be detected and the target object are the same person based on the distance between the feature vectors.

[0057] Optionally, in the service processing method provided in the embodiment of the present application, judging whether the object to be detected is a target object based on the target distance includes: judging whether the target distance is greater than a preset distance; if the target distance is not greater than the preset distance, determining that the object to be detected is a target object; if the target distance is greater than the preset distance, determining that the object to be detected is not a target object.

[0058] For example, the preset distance may be 3. If the distance between the two sets of feature vectors (corresponding to the first feature vector and the second feature vector) obtained by calculation (corresponding to the target distance) is 2, it can be determined that the user (corresponding to the object to be detected) and the target object are the same person. If the distance between the two sets of feature vectors (corresponding to the first feature vector and the second feature vector) obtained by calculation (corresponding to the target distance) is 5, it can be determined that the user (corresponding to the object to be detected) and the target object may be the same person, and further confirmation is required.

[0059] In summary, by judging whether the distance between the feature vectors is greater than the preset distance, it is possible to quickly and accurately determine whether the object to be detected and the target object are the same person.

[0060] Optionally, in the business processing method provided in the embodiment of the present application, judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information includes: calculating the similarity between the current expression feature information and the target expression feature information to obtain the target similarity; judging whether the target similarity is greater than a preset similarity; if the target similarity is not greater than the preset similarity, determining that the object to be detected is the target object; if the target similarity is greater than the preset similarity, determining that the object to be detected is not the target object.

[0061] For example, a threshold value of the degree of facial similarity (corresponding to the above-mentioned preset similarity) can be obtained based on big data, wherein the similarity (corresponding to the above-mentioned target similarity) between the expression feature information of the user (corresponding to the above-mentioned object to be detected) (corresponding to the above-mentioned current expression feature information) and the user expression feature information pre-stored in the blockchain (corresponding to the above-mentioned target expression feature information) obtained by calculation is compared with the obtained threshold value (corresponding to the above-mentioned preset similarity). If the similarity (corresponding to the above-mentioned target similarity) between the expression feature information of the user (corresponding to the above-mentioned object to be detected) (corresponding to the above-mentioned current expression feature information) and the user expression feature information pre-stored in the blockchain (corresponding to the above-mentioned target expression feature information) is not greater than the threshold value (corresponding to the above-mentioned preset similarity), it is determined to be similar; if the similarity (corresponding to the above-mentioned target similarity) between the expression feature information of the user (corresponding to the above-mentioned object to be detected) (corresponding to the above-mentioned current expression feature information) and the user expression feature information pre-stored in the blockchain (corresponding to the above-mentioned target expression feature information) is greater than the threshold value (corresponding to the above-mentioned preset similarity), it is determined to be dissimilar.

[0062] Through the above scheme, whether the object to be detected and the target object are similar can be quickly and accurately determined according to the similarity between the expression features.

[0063] Optionally, in the business processing method provided in the embodiment of the present application, determining the processing result of the financial business based on the current expression feature information and the target expression feature information includes: judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information; if the object to be detected is not the target object, outputting a prohibition instruction to indicate that financial business is prohibited for the object to be detected; if the object to be detected is the target object, outputting a processing instruction to indicate that financial business is processed for the object to be detected.

[0064] For example, the facial features to be confirmed are deeply judged in combination with the expression features, and the recognition system provides feedback to the user based on the judgment result. If it is verified that the user (corresponding to the above-mentioned object to be detected) and the target object are not the same person, the system prohibits the user (corresponding to the above-mentioned object to be detected) from handling financial services, and requires the user (corresponding to the above-mentioned object to be detected) to try again or take other identity authentication measures; if it is verified that the user (corresponding to the above-mentioned object to be detected) and the target object are the same person, the system can handle financial services for the user (corresponding to the above-mentioned object to be detected).

[0065] Through the above scheme, financial services can be handled quickly and accurately for users based on the verification results.

[0066] For example, Figure 2 is a flowchart of a bank branch face recognition method based on blockchain provided in an embodiment of the present application, such as Figure 2 As shown, a bank branch face recognition method based on blockchain, the recognition steps include:

[0067] When a user enters his / her face at a bank branch, he / she makes a set of facial features, and the facial feature information he / she enters and the facial feature information he / she currently makes are stored in the blockchain;

[0068] When the user authenticates, he / she places his / her face in front of the recognition system, which captures the user's facial features and uploads the data to the recognition system.

[0069] The recognition system determines whether the user's face is consistent with the user's facial feature information pre-stored in the blockchain. If the comparison is consistent, it is determined to be a confirmed face. If the comparison is inconsistent, the current face is determined to be a face to be confirmed, and further recognition is performed;

[0070] The recognition system prompts the user to make expression features and then compares them again. The expression features are combined with facial features to further confirm the face. If they match, the user is identified as the correct user. If they do not match, the user is identified as the wrong user.

[0071] After determining that the user is the wrong user, the identification system sends instructions to the background and transmits information to the customer service staff. The customer service staff will immediately determine whether the user is a suspicious person and perform manual business operations for the user.

[0072] This embodiment forms a dynamic double verification mechanism by adding expression features on the basis of traditional facial recognition. This mechanism is more difficult to forge because even if the facial image is copied, the expression features are difficult to completely imitate, thereby greatly improving the security of identity verification. The recorded facial image is stored on the blockchain, and the facial feature information and expression feature information are extremely secure and cannot be tampered with. Once the information is entered, it cannot be maliciously modified or deleted, further ensuring the security of user data. Due to the double verification of facial and expression features, the recognition system can confirm the user's identity more quickly, reducing the trouble of repeated attempts due to verification failures. After the verification is successful, the bank can provide more personalized services based on the user's facial and expression feature data. When the recognition system determines that it is a wrong user, it can immediately send instructions to the background to notify the customer service staff. The customer service staff can quickly intervene to determine whether it is a suspicious person, so as to take timely measures to prevent the occurrence of suspicious behavior. Through fast and accurate identity verification, users can enter the business processing process more quickly, reducing the waiting time in queues at bank branches.

[0073] For example, Figure 3 is a flowchart of the facial recognition steps in the embodiment of the present application, such as Figure 3 As shown, when a user conducts business at a bank branch for the first time, he / she enters the basic information of his / her upper face in advance at the bank branch, and then enters the expression feature information accordingly. The expression features include angry expression, happy expression and sad expression. The user randomly makes corresponding expressions according to his / her own preferences and enters and stores them in the blockchain in the recognition system.

[0074] When handling business, the user places the face in front of the recognition system for the recognition system to capture the face, pre-process the image data captured by the face, and extract the features. After the features are extracted, they are compared with the facial image features stored in the blockchain, and the extracted features are converted into feature vectors based on the convolutional neural network method. The distance between the two sets of feature vectors can be used as a measure of similarity. The smaller the distance, the more similar the two sets of feature vectors are, indicating that they are the same person, and the larger the distance, the more different the two sets of feature vectors are, indicating that they are not the same person.

[0075] The similarity distance calculation formula for the two sets of feature vectors x1 and y1 to be calculated is:

[0076]

[0077] Among them, x1 and y1 are two sets of feature vectors, n is the dimension of the vector, Σ represents the sum, which combines the distance differences in two directions into a single value, reflecting the difference between the two points in the overall distance. If the d value of the calculated result is in the range of 1-3, it indicates that the currently recognized face is the same person, and it is confirmed and output. If the d value is out of the range, it indicates that the currently recognized face may be the same person, and it is judged as a suspected user, and the output is a face to be confirmed.

[0078] In this embodiment, the preprocessing of image data, feature extraction and conversion into feature vectors using a convolutional neural network are all existing technologies and will not be elaborated on here. By comparing the collected user facial images with the stored user facial images, the similarity of the two sets of facial images can be determined, and whether the current user's face is consistent can be determined, so that the user's face can be better judged and recognized.

[0079] For example, Figure 4 is a flow chart of the expression feature recognition steps in the embodiment of the present application, such as Figure 4 As shown, when the output is a face to be confirmed, the recognition system displays a prompt to prompt the user to make expression features, upload the expression features made by the current user, pre-process the expression data, and extract the features, wherein the expression features are compared and judged. The expression features include the features of the eyes, the features of the nose, and the features of the mouth. After the comparison and judgment, the similarity value of the expression features is obtained.

[0080] The judgment formula is:

[0081] K=c 眼 +c 鼻 +c 嘴

[0082] Among them, K is the total similarity of the face, c 眼 、c 鼻 With c 嘴 is the similarity value of the eye feature, the feature similarity value of the nose and the similarity value of the mouth, c 眼 、c 鼻 With c 嘴 The calculation formula used is equal, where c 眼 The calculation formula is:

[0083]

[0084] Among them, x1 and y1 are two sets of feature vectors;

[0085] The threshold of face similarity is obtained based on big data, where the calculated K value is compared with the obtained threshold. If it is greater than the threshold, it is judged as dissimilar; if it is less than the threshold, it is judged as similar.

[0086] The facial features to be confirmed are deeply judged in combination with the facial expression features. Based on the judgment results, the recognition system provides feedback to the user. If the verification is successful, the user can continue with the subsequent operations; if the verification fails, the system requires the user to try again or take other identity authentication measures.

[0087] After the identification system determines that the user is the wrong one or fails to successfully match any record in the blockchain, the system triggers the early warning mechanism and sends instructions to the back-end monitoring and management system. After receiving this instruction, the back-end system passes the information to the customer service. The customer service analyzes whether it is a common misidentification situation or suspicious behavior. After determining the current user situation, the customer service staff manually handles the business of the current user.

[0088] In this embodiment, the threshold of face similarity is obtained by searching the network big data to obtain the existing threshold. The feature vector is an important concept in linear algebra. It has a special directionality under linear transformation, that is, the vector will only be scaled after linear transformation, but will not change its direction. In face recognition applications, feature vectors are extracted from the original image data through feature extraction algorithms. These feature vectors can represent the key information of the image and reduce the dimension of the data, making subsequent processing and comparison more efficient. In the face recognition system, the similarity comparison of feature vectors is a key step in determining whether two faces belong to the same person. By calculating the distance between the two feature vectors, the similarity between them is obtained, and the similarity between the two faces is determined according to the preset similarity threshold.

[0089] For example, Figure 5 is a schematic diagram of a face recognition device provided according to an embodiment of the present application, such as Figure 5 As shown, a face recognition device for bank branches based on blockchain, the face recognition device is a recognition system, and the recognition system includes a camera, a blockchain storage unit, an operation screen and an operation host, wherein the camera is fixedly installed on the operation host, the blockchain storage unit is located inside the operation host, and the operation screen is located on the outer surface of the operation host.

[0090] The camera is used to capture the user's facial information and upload the captured facial information to the blockchain storage unit. The operation screen is used for users to operate and handle business, and the operation host is the operating instrument.

[0091] The introduction of the operation screen in this embodiment allows the user to interact with the system intuitively and complete business operations and processing. This graphical interface reduces the user's learning cost and improves operational efficiency. Identity authentication can be completed through facial recognition, which simplifies business processes. The camera is fixedly installed on the operating host, which is convenient for the user to quickly capture facial information. The user only needs to stand in front of the camera and the system can automatically complete the recognition process. The double verification method can improve the efficiency of recognition, reduce recognition errors, and promptly detect suspicious persons, bringing better usage prospects.

[0092] Therefore, in this embodiment, by adding the recognition of expression features, a double verification mechanism is formed, and the entered expression features and facial features are stored on the blockchain. The facial feature information and expression feature information stored on the blockchain are extremely secure and cannot be tampered with, which can effectively protect the user's data security. Through the double verification method, the efficiency of recognition can be improved, the number of recognition errors can be reduced, and suspicious persons can be discovered in a timely manner, bringing better usage prospects.

[0093] In summary, the business processing method provided by the embodiment of the present application is as follows: when it is detected that the object to be detected is handling financial business, the facial features of the object to be detected are collected to obtain current facial feature information; based on the target information of the object to be detected, the target facial feature information of the target object pre-stored is obtained from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, the account information provided by the object to be detected; based on the current facial feature information and the target facial feature information, it is determined whether the object to be detected is the target object; if the object to be detected is not the target object, the expression features of the object to be detected are collected to obtain current expression feature information, and based on the current expression feature information and the target expression feature information, the processing result of the financial business is determined, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial business for the object to be detected, which solves the problem that the effect of face recognition in the related technology is poor, resulting in poor effect of using face recognition technology to handle financial business for users. By adding facial expression recognition to traditional facial recognition, a double verification mechanism is formed, and the entered facial expression features and facial features are stored on the blockchain. The facial feature information and facial expression feature information stored on the blockchain are extremely secure and cannot be tampered with, which can effectively protect the user's data security. Through the double verification method, the efficiency of recognition can be improved, the number of recognition errors can be reduced, and suspicious persons can be discovered in a timely manner, thereby improving the effect of handling financial services for users.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] The embodiment of the present application also provides a service processing device. It should be noted that the service processing device of the embodiment of the present application can be used to execute the service processing method provided by the embodiment of the present application. The service processing device provided by the embodiment of the present application is introduced below.

[0096] Figure 6 Schematic diagram of a service processing device according to an embodiment of the present application. Figure 6 As shown, the device includes: a first collection unit 601, a first acquisition unit 602, a first judgment unit 603 and a first processing unit 604.

[0097] Specifically, the first collection unit 601 is used to collect facial features of the object to be detected and obtain current facial feature information when it is detected that the object to be detected is handling financial business;

[0098] The first acquisition unit 602 is used to acquire the target facial feature information of the target object stored in advance from the blockchain according to the target information of the object to be detected, wherein the target information is at least one of the following: the name of the object to be detected, and the account information provided by the object to be detected;

[0099] The first judgment unit 603 is used to judge whether the object to be detected is a target object according to the current facial feature information and the target facial feature information;

[0100] The first processing unit 604 is used to collect the expression features of the object to be detected if it is not the target object, obtain current expression feature information, and determine the processing result of the financial service based on the current expression feature information and the target expression feature information, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle the financial service for the object to be detected.

[0101] In summary, the service processing device provided by the embodiment of the present application, when the first collection unit 601 detects that the object to be detected is handling financial services, collects the facial features of the object to be detected to obtain current facial feature information; the first acquisition unit 602 obtains the target facial feature information of the target object pre-stored from the blockchain based on the target information of the object to be detected, wherein the target information is at least one of the following: the name of the object to be detected, the account information provided by the object to be detected; the first judgment unit 603 judges whether the object to be detected is the target object based on the current facial feature information and the target facial feature information; if the object to be detected is not the target object, the first processing unit 604 collects the expression features of the object to be detected to obtain the current expression feature information, and determines the processing result of the financial service based on the current expression feature information and the target expression feature information, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial services for the object to be detected, which solves the problem that the effect of face recognition in the related technology is poor, resulting in poor effect of using face recognition technology to handle financial services for users. By adding facial expression recognition to traditional facial recognition, a double verification mechanism is formed, and the entered facial expression features and facial features are stored on the blockchain. The facial feature information and facial expression feature information stored on the blockchain are extremely secure and cannot be tampered with, which can effectively protect the user's data security. Through the double verification method, the efficiency of recognition can be improved, the number of recognition errors can be reduced, and suspicious persons can be discovered in a timely manner, thereby improving the effect of handling financial services for users.

[0102] Optionally, in the service processing device provided in the embodiment of the present application, the device also includes: a second processing unit, used to obtain facial image data of the target object and extract feature information of the facial image data of the target object to obtain target facial feature information before obtaining pre-stored target facial feature information of the target object from the blockchain based on the target information of the object to be detected; and a first storage unit, used to store the target facial feature information in the blockchain.

[0103] Optionally, in the service processing device provided in the embodiment of the present application, the first judgment unit includes: a first conversion module, used to convert current facial feature information into a feature vector to obtain a first feature vector; a second conversion module, used to convert target facial feature information into a feature vector to obtain a second feature vector; a first calculation module, used to calculate the distance information between the first feature vector and the second feature vector to obtain the target distance; and a first judgment module, used to judge whether the object to be detected is the target object based on the target distance.

[0104] Optionally, in the service processing device provided in the embodiment of the present application, the first judgment module includes: a first judgment submodule, used to judge whether the target distance is greater than a preset distance; a first determination submodule, used to determine that the object to be detected is a target object if the target distance is not greater than the preset distance; and a second determination submodule, used to determine that the object to be detected is not a target object if the target distance is greater than the preset distance.

[0105] Optionally, in the business processing device provided in the embodiment of the present application, the first processing unit includes: a second judgment module, used to judge whether the object to be detected is a target object based on current expression feature information and target expression feature information; a first processing module, used to output a prohibition instruction if the object to be detected is not the target object, to indicate that financial services are prohibited for the object to be detected; and a second processing module, used to output a processing instruction if the object to be detected is the target object, to indicate that financial services are handled for the object to be detected.

[0106] Optionally, in the service processing device provided in the embodiment of the present application, the second judgment module includes: a first calculation submodule, used to calculate the similarity between the current expression feature information and the target expression feature information to obtain the target similarity; a second judgment submodule, used to determine whether the target similarity is greater than a preset similarity; a third determination submodule, used to determine that the object to be detected is the target object if the target similarity is not greater than the preset similarity; and a fourth determination submodule, used to determine that the object to be detected is not the target object if the target similarity is greater than the preset similarity.

[0107] Optionally, in the business processing device provided in the embodiment of the present application, the first acquisition unit includes: a third processing module, which is used to obtain facial image data of the object to be detected when it is detected that the object to be detected is handling financial business, and pre-process the facial image data of the object to be detected to obtain processed facial image data; a fourth processing module, which is used to perform feature extraction processing on the processed facial image data to obtain current facial feature information.

[0108] The service processing device includes a processor and a memory. The above-mentioned first collection unit 601, first acquisition unit 602, first judgment unit 603 and first processing unit 604 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0109] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the effect of handling financial services for users can be improved by adjusting kernel parameters.

[0110] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0111] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the service processing method is implemented.

[0112] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the service processing method when running.

[0113] like Figure 7 As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: when it is detected that an object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information; according to target information of the object to be detected, target facial feature information of the target object pre-stored is obtained from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, and the account information provided by the object to be detected; according to the current facial feature information and the target facial feature information, it is determined whether the object to be detected is the target object; if the object to be detected is not the target object, the expression features of the object to be detected are collected to obtain current expression feature information, and according to the current expression feature information and the target expression feature information, the processing result of the financial business is determined, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial business for the object to be detected.

[0114] When the processor executes the program, the following steps are also implemented: before obtaining the target facial feature information of the target object pre-stored from the blockchain based on the target information of the object to be detected, it also includes: obtaining the facial image data of the target object, and extracting the feature information of the facial image data of the target object to obtain the target facial feature information; storing the target facial feature information in the blockchain.

[0115] When the processor executes the program, the following steps are also implemented: judging whether the object to be detected is the target object based on the current facial feature information and the target facial feature information, including: converting the current facial feature information into a feature vector to obtain a first feature vector; converting the target facial feature information into a feature vector to obtain a second feature vector; calculating the distance information between the first feature vector and the second feature vector to obtain the target distance; judging whether the object to be detected is the target object based on the target distance.

[0116] When the processor executes the program, the following steps are also implemented: judging whether the object to be detected is a target object based on the target distance includes: judging whether the target distance is greater than a preset distance; if the target distance is not greater than the preset distance, determining that the object to be detected is a target object; if the target distance is greater than the preset distance, determining that the object to be detected is not a target object.

[0117] When the processor executes the program, the following steps are also implemented: based on the current expression feature information and the target expression feature information, determining the processing result of the financial business includes: based on the current expression feature information and the target expression feature information, judging whether the object to be detected is the target object; if the object to be detected is not the target object, outputting a prohibition instruction to indicate that financial business is prohibited for the object to be detected; if the object to be detected is the target object, outputting a processing instruction to indicate that financial business is processed for the object to be detected.

[0118] When the processor executes the program, the following steps are also implemented: judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information, including: calculating the similarity between the current expression feature information and the target expression feature information to obtain the target similarity; judging whether the target similarity is greater than the preset similarity; if the target similarity is not greater than the preset similarity, determining that the object to be detected is the target object; if the target similarity is greater than the preset similarity, determining that the object to be detected is not the target object.

[0119] When the processor executes the program, the following steps are also implemented: when it is detected that the object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information, including: when it is detected that the object to be detected is handling financial business, facial image data of the object to be detected is obtained, and the facial image data of the object to be detected is pre-processed to obtain processed facial image data; feature extraction processing is performed on the processed facial image data to obtain current facial feature information.

[0120] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0121] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: when it is detected that an object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information; based on the target information of the object to be detected, target facial feature information of the target object pre-stored is obtained from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, and the account information provided by the object to be detected; based on the current facial feature information and the target facial feature information, it is determined whether the object to be detected is the target object; if the object to be detected is not the target object, the expression features of the object to be detected are collected to obtain current expression feature information, and based on the current expression feature information and the target expression feature information, a processing result for the financial business is determined, wherein the target expression feature information is the expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether it is allowed to handle financial business for the object to be detected.

[0122] When executed on a data processing device, it is also suitable for executing a program that is initialized with the following method steps: before obtaining pre-stored target facial feature information of a target object from a blockchain based on target information of the object to be detected, it also includes: obtaining facial image data of the target object, and extracting feature information of the facial image data of the target object to obtain target facial feature information; and storing the target facial feature information in the blockchain.

[0123] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: judging whether the object to be detected is a target object based on current facial feature information and target facial feature information, including: converting the current facial feature information into a feature vector to obtain a first feature vector; converting the target facial feature information into a feature vector to obtain a second feature vector; calculating the distance information between the first feature vector and the second feature vector to obtain a target distance; judging whether the object to be detected is a target object based on the target distance.

[0124] When executed on a data processing device, it is also suitable for executing a program that is initialized with the following method steps: judging whether the object to be detected is a target object based on the target distance includes: judging whether the target distance is greater than a preset distance; if the target distance is not greater than the preset distance, determining that the object to be detected is a target object; if the target distance is greater than the preset distance, determining that the object to be detected is not a target object.

[0125] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: determining the processing result of the financial business based on the current expression feature information and the target expression feature information, including: judging whether the object to be detected is the target object based on the current expression feature information and the target expression feature information; if the object to be detected is not the target object, outputting a prohibition instruction to indicate that financial business is prohibited for the object to be detected; if the object to be detected is the target object, outputting a processing instruction to indicate that financial business is handled for the object to be detected.

[0126] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: judging whether the object to be detected is a target object based on current expression feature information and target expression feature information, including: calculating the similarity between the current expression feature information and the target expression feature information to obtain the target similarity; judging whether the target similarity is greater than a preset similarity; if the target similarity is not greater than the preset similarity, determining that the object to be detected is the target object; if the target similarity is greater than the preset similarity, determining that the object to be detected is not the target object.

[0127] When executed on a data processing device, it is also suitable for executing an initialization program having the following method steps: when it is detected that the object to be detected is handling financial business, facial features of the object to be detected are collected to obtain current facial feature information including: when it is detected that the object to be detected is handling financial business, facial image data of the object to be detected is obtained, and the facial image data of the object to be detected is pre-processed to obtain processed facial image data; feature extraction processing is performed on the processed facial image data to obtain current facial feature information.

[0128] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0129] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, 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 generate 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 flowchart and / or block diagram. 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.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0133] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0134] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0135] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0136] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0137] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for processing a business, characterized in that: include: When it is detected that the subject to be detected is handling financial business, facial features of the subject to be detected are collected to obtain current facial feature information; According to the target information of the object to be detected, obtaining pre-stored target facial feature information of the target object from the blockchain, wherein the target information is at least one of the following: the name of the object to be detected, and the account information provided by the object to be detected; Determining whether the object to be detected is the target object based on the current facial feature information and the target facial feature information; If the object to be detected is not the target object, the facial expression features of the object to be detected are collected to obtain current facial expression feature information, and the processing result of the financial service is determined based on the current facial expression feature information and the target facial expression feature information, wherein the target facial expression feature information is the facial expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether the financial service is allowed to be processed for the object to be detected.

2. The method according to claim 1, characterized in that Before obtaining pre-stored target facial feature information of the target object from the blockchain based on the target information of the object to be detected, the method further includes: Acquiring facial image data of the target object, and extracting feature information of the facial image data of the target object to obtain target facial feature information; The target facial feature information is stored in the blockchain.

3. The method according to claim 1, characterized in that Determining whether the object to be detected is the target object based on the current facial feature information and the target facial feature information includes: Converting the current facial feature information into a feature vector to obtain a first feature vector; Converting the target facial feature information into a feature vector to obtain a second feature vector; Calculating distance information between the first eigenvector and the second eigenvector to obtain a target distance; According to the target distance, it is determined whether the object to be detected is the target object.

4. The method according to claim 3, characterized in that Determining whether the object to be detected is the target object according to the target distance includes: Determining whether the target distance is greater than a preset distance; If the target distance is not greater than the preset distance, determining that the object to be detected is the target object; If the target distance is greater than the preset distance, it is determined that the object to be detected is not the target object.

5. The method according to claim 1, wherein Determining a processing result of the financial service based on the current expression feature information and the target expression feature information includes: Determining whether the object to be detected is the target object based on the current expression feature information and the target expression feature information; If the object to be detected is not the target object, outputting a prohibition instruction to prohibit processing the financial business for the object to be detected; If the object to be detected is the target object, a processing instruction is output to instruct the processing of the financial business for the object to be detected.

6. The method according to claim 5, characterized in that Determining whether the object to be detected is the target object based on the current expression feature information and the target expression feature information includes: Calculating the similarity between the current expression feature information and the target expression feature information to obtain a target similarity; Determining whether the target similarity is greater than a preset similarity; If the target similarity is not greater than the preset similarity, determining that the object to be detected is the target object; If the target similarity is greater than the preset similarity, it is determined that the object to be detected is not the target object.

7. The method according to claim 1, characterized in that When it is detected that the subject to be detected is handling financial business, facial features of the subject to be detected are collected, and current facial feature information obtained includes: When it is detected that the subject to be detected is handling financial business, acquiring facial image data of the subject to be detected, and preprocessing the facial image data of the subject to be detected to obtain processed facial image data; Perform feature extraction processing on the processed facial image data to obtain the current facial feature information.

8. A service processing device, characterized in that: include: The first collection unit is configured to collect facial features of a subject to be detected and obtain current facial feature information when detecting that the subject to be detected is handling financial business; A first acquiring unit is configured to acquire pre-stored target facial feature information of the target object from a blockchain based on the target information of the target object to be detected, wherein the target information is at least one of the following: a name of the target object to be detected, and account information provided by the target object to be detected; a first judging unit, configured to judge whether the object to be detected is the target object based on the current facial feature information and the target facial feature information; The first processing unit is configured to collect facial expression features of the object to be detected if the object to be detected is not the target object, obtain current facial expression feature information, and determine a processing result for the financial service based on the current facial expression feature information and target facial expression feature information, wherein the target facial expression feature information is facial expression feature information of the target object pre-stored in the blockchain, and the processing result indicates whether the financial service is allowed to be processed for the object to be detected.

9. A computer-readable storage medium, characterized in that The storage medium stores a program, wherein the program executes the service processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The system comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the service processing method described in any one of claims 1 to 7.

Images