Recommended authentication methods, devices, equipment and storage media

Abstract

The present invention provides a method, device, equipment and storage medium for recommending authentication methods. The method includes: when a user handles a business, first, the user's static state information is obtained, and the user's dynamic state information is extracted from historical video data; wherein the static state information is used to characterize the user's physical state; the dynamic state information includes the user's image features and voiceprint features; then, the user's static state information and dynamic state information are processed using an intelligent recommendation model to obtain the arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users. In this solution, by pre-building an intelligent recommendation model, when a customer handles a business, the intelligent recommendation model is used to recommend an authentication method based on the customer's state, so as to achieve the purpose of providing an authentication method based on the customer's state and improving the customer experience.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, equipment and storage medium for recommending an authentication method. Background Art

[0002] At present, customers mostly go to bank branches to handle banking business, and then conduct business or transactions at the counter of the branch under the guidance of customer service. When customers use counter transactions at bank branches, they mostly complete business handling and transactions by confirming the information on the screen, clicking the confirmation button on the touch screen and signing. However, for customers with different physical and mental conditions, the authentication method of counter transactions is too single. Since it is difficult to provide more suitable authentication methods for different customers, it is easy to cause trouble to customers and poor customer experience.

[0003] It can be seen that there is an urgent need for a recommendation method for authentication methods to provide authentication methods based on customer status and improve customer experience. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method, apparatus, device and storage medium for recommending an authentication method, so as to provide an authentication method based on the customer status and improve the customer experience.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] The first aspect of the present application provides a method for recommending an authentication method, including:

[0007] When a user handles a service, the static state information of the user is obtained, and the dynamic state information of the user is extracted from the historical video data; wherein the static state information is used to characterize the physical state of the user; and the dynamic state information includes the image features and voiceprint features of the user;

[0008] The static state information and dynamic state information of the user are processed by an intelligent recommendation model to obtain arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users.

[0009] Optionally, the training method of the intelligent recommendation model includes:

[0010] Obtaining static state information and dynamic state information of the sample user; wherein the static state information of the sample user is used to characterize the physical state of the sample user; the dynamic state information of the sample user includes image features and voiceprint features of the sample user;

[0011] Obtaining a training set of authentication methods; wherein the training set includes multiple authentication methods with labels, and the labels are used to describe the sorting positions of the authentication methods in the training set;

[0012] The neural network model is trained using the static state information and dynamic state information of the sample users and the training set of the authentication method to obtain the intelligent recommendation model.

[0013] Optionally, extracting the dynamic state information of the user from the historical video data includes:

[0014] Extracting the image information and voice information of the user's historical business transactions from the historical video data;

[0015] The image features of the user are extracted from the image information of the user's historical business handling, and the voiceprint features of the user are extracted from the voice information of the user's historical business handling.

[0016] Optionally, the multiple authentication methods include: electronic signature, face recognition, voiceprint recognition, and button confirmation.

[0017] Optionally, after the intelligent recommendation model is used to process the static state information and the dynamic state information of the user to obtain the arrangement results of the multiple authentication methods, the method further includes:

[0018] According to the click feedback information of the user in the arrangement result of the multiple authentication methods, the selection of the multiple authentication methods is recorded to obtain the number of times each authentication method is adopted;

[0019] According to the number of times each authentication method is adopted, a layer of weight is added to the score of each authentication method in the intelligent recommendation model, and the recommendation order of the multiple authentication methods in the intelligent recommendation model is adjusted.

[0020] A second aspect of the present application provides a device for recommending an authentication method, including:

[0021] A first acquisition unit is used to acquire static state information of the user when the user handles a service, and extract dynamic state information of the user from historical video data; wherein the static state information is used to characterize the physical state of the user; and the dynamic state information includes image features and voiceprint features of the user;

[0022] A processing unit is used to process the static state information and dynamic state information of the user using an intelligent recommendation model to obtain arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users.

[0023] Optionally, also include:

[0024] A second acquisition unit is used to acquire static state information and dynamic state information of the sample user; wherein the static state information of the sample user is used to characterize the physical state of the sample user; and the dynamic state information of the sample user includes image features and voiceprint features of the sample user;

[0025] A third acquisition unit is used to acquire a training set of authentication methods; wherein the training set includes multiple authentication methods with labels, and the labels are used to describe the sorting position of the authentication methods in the training set;

[0026] A training unit is used to train the neural network model using the static state information and dynamic state information of the sample user and the training set of the authentication method to obtain the intelligent recommendation model.

[0027] Optionally, when the first acquisition unit executes the step of extracting the dynamic state information of the user from the historical video data, it is specifically used to:

[0028] Extracting the image information and voice information of the user's historical business transactions from the historical video data;

[0029] The image features of the user are extracted from the image information of the user's historical business handling, and the voiceprint features of the user are extracted from the voice information of the user's historical business handling.

[0030] Optionally, the multiple authentication methods in the processing unit include: electronic signature, face recognition, voiceprint recognition, and button confirmation.

[0031] Optionally, also include:

[0032] A recording unit, used to record the selection of multiple authentication methods according to the click feedback information of the user in the arrangement results of multiple authentication methods, and obtain the number of times each authentication method is adopted;

[0033] The adjustment unit is used to add a layer of weight to the score of each authentication method in the intelligent recommendation model according to the number of times each authentication method is adopted, and adjust the recommendation order of multiple authentication methods in the intelligent recommendation model.

[0034] A third aspect of the present application provides an electronic device, including:

[0035] one or more processors;

[0036] a storage device having one or more programs stored thereon;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the recommended method of any authentication method provided in the first aspect of the present application.

[0038] A fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for recommending any of the authentication methods provided in the first aspect of the present application is implemented.

[0039] It can be seen from the above technical scheme that in a method for recommending an authentication method provided in an embodiment of the present application, a neural network model is trained based on the static state information and dynamic state information of sample users and a training set of authentication methods to obtain an intelligent recommendation model. In this way, when a user handles a business, the present scheme first obtains the static state information of the user and extracts the dynamic state information of the user from historical video data, wherein the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. Then, the intelligent recommendation model is used to process the user's static state information and dynamic state information to obtain the arrangement results of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A flowchart of a recommended method for an authentication method provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of a training method for an intelligent recommendation model provided in an embodiment of the present application;

[0043] Figure 3 A flowchart of another authentication method recommended by an embodiment of the present application;

[0044] Figure 4 A flowchart of a recommended method for another authentication method provided in an embodiment of the present application;

[0045] Figure 5 A structural block diagram of a recommended device for an authentication method provided in an embodiment of the present application;

[0046] Figure 6A schematic diagram of an electronic device for executing a recommended method for authentication provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0049] As can be seen from the background technology, when customers use counter transactions at bank branches, they mostly complete business processing and transactions by confirming the information on the screen, clicking the confirmation button on the touch screen and signing. However, for customers with different physical and psychological conditions, the authentication method of counter transactions is too single. Since it is difficult to provide more suitable authentication methods for different customers, it is easy to cause trouble to customers and poor customer experience.

[0050] Therefore, this solution first obtains the user's static state information when the user handles a business, and extracts the user's dynamic state information from historical video data, where the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. The intelligent recommendation model is then used to process the user's static state information and dynamic state information to obtain the arrangement results of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience.

[0051] See also Figure 1 , a recommended method of authentication method disclosed in an embodiment of the present application includes the following steps:

[0052] S101. When a user handles a service, static status information of the user is obtained, and dynamic status information of the user is extracted from historical video data.

[0053] The static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features.

[0054] In the specific implementation of step S101, when the user handles a business, the user's customer information and physical condition are obtained, and the user's image information and voice information are obtained from the video recording of the business handling to extract the user's image features and voiceprint features.

[0055] It should be noted that the static status information also includes the user's age, gender, job and region, and the user's physical status includes the user's health status, hand health, eye health and oral health.

[0056] S102: Using an intelligent recommendation model to process the user's static state information and dynamic state information, and obtain arrangement results of multiple authentication methods.

[0057] Among them, the intelligent recommendation model is obtained by training the neural network model based on the static state information and dynamic state information of sample users.

[0058] In step S102, multiple authentication methods are available, including: electronic signature, face recognition, voiceprint recognition, and button confirmation, and the authentication method is used to authenticate the identity of the user currently handling the business.

[0059] In the specific implementation of step S102, the user's customer information, physical condition, image information and voice information are input into the intelligent recommendation model. After the intelligent recommendation model processes the input data, the ranking results of the multiple authentication methods are obtained and displayed on the interface.

[0060] Specifically, the arrangement results after scoring of multiple authentication methods can be an order of arrangement from high to low scores. For example, when the scoring range is 0 to 10 points, the electronic signature score is 8 points, the face recognition score is 9 points, the voiceprint recognition score is 6 points, and the button confirmation score is 7 points. Then the arrangement results from high to low according to the scores are face recognition, electronic signature, voiceprint recognition, and button confirmation.

[0061] It should be noted that the interface may be an interface of a human-computer interaction device, and the human-computer interaction device may be set by a technician, including but not limited to a PC, a PAD, and a mobile phone.

[0062] In a method for recommending an authentication method provided in an embodiment of the present application, a neural network model is trained based on static state information and dynamic state information of sample users and a training set of authentication methods to obtain an intelligent recommendation model. In this way, when a user handles a business, the present solution first obtains the user's static state information and extracts the user's dynamic state information from historical video data, wherein the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. The intelligent recommendation model is then used to process the user's static state information and dynamic state information to obtain an arrangement result of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience.

[0063] Based on the recommendation method of an authentication method disclosed in the above embodiment of the present application, a pre-built intelligent recommendation model is involved when executing step S102. Figure 2 As shown, a training method for an intelligent recommendation model disclosed in an embodiment of the present application includes the following steps:

[0064] S201. Obtain static status information and dynamic status information of sample users.

[0065] The static state information of the sample user is used to characterize the physical state of the sample user, and the dynamic state information of the sample user includes the image features and voiceprint features of the sample user.

[0066] In the process of implementing step S201, the customer information and physical condition of the sample user are collected, that is, the age, gender, job, region, health status, hand health, eye health, oral health of the sample user saved in the database, and the image information and voice information of the sample user in the process of handling business are obtained from the historical business handling video, and the image features and voiceprint features therein are extracted.

[0067] It should be noted that there can be multiple sample users.

[0068] S202: Obtain a training set of the authentication method.

[0069] The training set includes multiple authentication methods with labels, and the labels are used to describe the ranking positions of the authentication methods in the training set.

[0070] In the specific process of implementing step S202, a plurality of authentication methods that have been manually marked are obtained, that is, a plurality of authentication methods that have been manually sorted and have labels indicating sorting positions.

[0071] For example, the label for the electronic signature position is 2, the label for the face recognition position is 1, the label for the voiceprint recognition position is 4, and the label for the button confirmation position is 3. The sorting results after manual labeling are face recognition, electronic signature, button confirmation, and voiceprint recognition.

[0072] S203: Train the neural network model using the static state information and dynamic state information of the sample users and the training set of the authentication method to obtain an intelligent recommendation model.

[0073] In the specific implementation process of step S203, a multi-layer deep neural network model is first constructed, and then the customer information, physical condition, image features, voiceprint features, and multiple authentication methods with labels of the sample user are input, and then iterative training is performed through the back propagation algorithm to finally obtain an intelligent recommendation model.

[0074] It should be noted that the back propagation algorithm is a learning algorithm suitable for multi-layer neural networks.

[0075] This solution first obtains the user's static state information when the user handles a business, and extracts the user's dynamic state information from historical video data, where the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. The intelligent recommendation model is then used to process the user's static state information and dynamic state information to obtain the arrangement results of multiple authentication methods, so as to provide authentication methods based on customer status and improve customer experience.

[0076] See also Figure 3 Another recommended method for authentication disclosed in the embodiment of the present application includes the following steps:

[0077] S301. When a user handles a service, obtain the user's static status information.

[0078] In the specific implementation of step S301, when the user handles the business, the user's age, gender, job, region, health status, hand health, eye health, oral health, etc. stored in the database are obtained.

[0079] S302: Extract the image information and voice information of the user's historical business transactions from the historical video data.

[0080] In the specific implementation of step S302, firstly, the video recording of the historical business handling is obtained from the video data stored in the database, and then the image information and voice information of the user in the process of handling the business are intercepted according to the user information.

[0081] S303: extracting the image features of the user from the image information of the user's historical business handling, and extracting the voiceprint features of the user from the voice information of the user's historical business handling.

[0082] In the specific implementation of step S303, the image features of the user, which may be the facial features of the user, are extracted from the image information of the user during the business process, and the voiceprint features of the user are extracted from the voice information of the user during the business process.

[0083] Among them, image features can be used for face recognition, and voiceprint features can be used for voiceprint recognition.

[0084] S304: Use the intelligent recommendation model to process the user's static state information and dynamic state information to obtain arrangement results of multiple authentication methods.

[0085] The execution principle and process of the above step S304 are the same as Figure 1 The execution principle and process of step S102 disclosed in are the same, which can be referred to and will not be repeated here.

[0086] In a method for recommending an authentication method provided in an embodiment of the present application, a neural network model is trained based on static state information and dynamic state information of sample users and a training set of authentication methods to obtain an intelligent recommendation model. In this way, when a user handles a business, the present solution first obtains the user's static state information and extracts the user's dynamic state information from historical video data, wherein the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. The intelligent recommendation model is then used to process the user's static state information and dynamic state information to obtain an arrangement result of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience.

[0087] See also Figure 4 , a recommended method of authentication method disclosed in an embodiment of the present application includes the following steps:

[0088] S401. When a user handles a service, the user's static state information is obtained, and the user's dynamic state information is extracted from historical video data.

[0089] S402: Using the intelligent recommendation model to process the user's static state information and dynamic state information, and obtain arrangement results of multiple authentication methods.

[0090] S403: According to the click feedback information of the user in the arrangement results of the multiple authentication methods, the selection conditions of the multiple authentication methods are recorded to obtain the number of times each authentication method is adopted.

[0091] In the specific implementation process of step S403, after the user selects an authentication method, first obtain the user's click feedback information in the arrangement results of multiple authentication methods, then extract and record the user's selection of the authentication method in the click feedback information, and finally obtain the corresponding number of times each authentication method is adopted.

[0092] S404. According to the number of times each authentication method is adopted, a weight is added to the score of each authentication method in the intelligent recommendation model, and the recommendation order of multiple authentication methods in the intelligent recommendation model is adjusted.

[0093] In the process of implementing step S404, a layer of weight is added to the recommendation score of each authentication method obtained in the intelligent recommendation model according to the recorded number of times each authentication method is adopted. The more times each authentication method is adopted, the higher the weight. Based on the recommendation score after the weight is increased, the recommendation order of multiple authentication methods in the intelligent recommendation model is adjusted to continuously optimize the intelligent recommendation model.

[0094] It should be noted that the intelligent recommendation model can also be iteratively optimized by continuously acquiring the user's static state information and historical dynamic state information.

[0095] The execution principle and process of the above steps S401 and S402 are the same as Figure 1 The execution principle and process of step S101 and step S102 disclosed in are the same, which can be referred to and will not be repeated here.

[0096] In a method for recommending an authentication method provided in an embodiment of the present application, a neural network model is trained based on static state information and dynamic state information of sample users and a training set of authentication methods to obtain an intelligent recommendation model. In this way, when a user handles a business, the present solution first obtains the user's static state information and extracts the user's dynamic state information from historical video data, wherein the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. The intelligent recommendation model is then used to process the user's static state information and dynamic state information to obtain an arrangement result of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience.

[0097] Corresponding to the method for recommending an authentication method provided in the above-mentioned embodiment of the present application, the embodiment of the present application also provides a device for recommending an authentication method.

[0098] See also Figure 5 The recommended device for the authentication method disclosed in the embodiment of the present application includes:

[0099] The first acquisition unit 501 is used to acquire the static state information of the user when the user handles the service, and extract the dynamic state information of the user from the historical video data; wherein the static state information is used to represent the user's physical state; the dynamic state information includes the user's image features and voiceprint features;

[0100] The processing unit 502 is used to process the user's static state information and dynamic state information using an intelligent recommendation model to obtain arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users.

[0101] Optionally, the recommended authentication method also includes:

[0102] The second acquisition unit 503 is used to acquire static state information and dynamic state information of the sample user; wherein the static state information of the sample user is used to characterize the physical state of the sample user; the dynamic state information of the sample user includes image features and voiceprint features of the sample user;

[0103] The third acquisition unit 504 is used to acquire a training set of authentication methods; wherein the training set includes multiple authentication methods with labels, and the labels are used to describe the ranking position of the authentication methods in the training set;

[0104] The training unit 505 is used to train the neural network model using the static state information and dynamic state information of the sample users and the training set of the authentication method to obtain an intelligent recommendation model.

[0105] Optionally, when the first acquisition unit 501 extracts the user's dynamic state information from the historical video data, it is specifically used to:

[0106] From the historical video data, extract the image information and voice information of the user's historical business transactions;

[0107] The image features of the user are extracted from the image information of the user's historical business transactions, and the voiceprint features of the user are extracted from the voice information of the user's historical business transactions.

[0108] Optionally, the multiple authentication methods in the processing unit 502 include: electronic signature, face recognition, voiceprint recognition, and button confirmation.

[0109] Optionally, the recommended authentication method also includes:

[0110] The recording unit 506 is used to record the selection of multiple authentication methods according to the click feedback information of the user in the arrangement results of multiple authentication methods, and obtain the number of times each authentication method is adopted;

[0111] The adjustment unit 507 is used to add a layer of weight to the score of each authentication method in the intelligent recommendation model according to the number of times each authentication method is adopted, and adjust the recommendation order of multiple authentication methods in the intelligent recommendation model.

[0112] It should be noted that the specific principles and execution processes of each module in the recommended device for the authentication method disclosed in the above embodiment of the present application are similar to those in the above embodiment. Figures 1 to 4 The principles and execution processes of the corresponding parts in the recommended method of the authentication method disclosed in the embodiment of the present application are the same. Please refer to the corresponding parts in the recommended method of the authentication method disclosed in the above embodiment of the present application, and no further details will be given here.

[0113] In a device for recommending an authentication method provided in an embodiment of the present application, a neural network model is trained by a training unit 505 based on static state information and dynamic state information of a sample user and a training set of authentication methods to obtain an intelligent recommendation model. In this way, when a user handles a business, the present solution first obtains the static state information of the user through a first acquisition unit 501, and extracts the dynamic state information of the user from historical video data, wherein the static state information is used to characterize the user's physical state, and the dynamic state information includes the user's image features and voiceprint features. Then, the processing unit 502 uses the intelligent recommendation model to process the static state information and dynamic state information of the user to obtain the arrangement results of multiple authentication methods, so as to achieve the purpose of providing authentication methods based on customer status and improving customer experience.

[0114] Another embodiment of the present application further provides an electronic device, such as Figure 6 As shown, including:

[0115] Processor 601 and storage device 602;

[0116] Wherein, the storage device 602 is used to store computer programs;

[0117] The processor 601 is used to execute the computer program. When the program is executed, it is specifically used to implement the present application as follows: Figures 1 to 4 The illustrated embodiment discloses a recommended method of authentication.

[0118] Another embodiment of the present application further provides a computer storage medium for storing a computer program. When the computer program is executed, it is specifically used to implement the present application as follows: Figures 1 to 4 The illustrated embodiment discloses a recommended method of authentication.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0120] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0121] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for recommending an authentication method, characterized in that: include: When a user handles counter services, the static state information of the user is obtained, and the dynamic state information of the user is extracted from the historical video data; wherein the static state information is used to characterize the physical state of the user, and the physical state of the user includes: the health state of the user, the health state of the hands, the health state of the eyes, and the health state of the mouth; the dynamic state information includes the image features and voiceprint features of the user; Using an intelligent recommendation model to process the static state information and dynamic state information of the user to obtain arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users; After the intelligent recommendation model is used to process the static state information and the dynamic state information of the user to obtain the arrangement results of the multiple authentication methods, the method further includes: According to the click feedback information of the user in the arrangement result of the multiple authentication methods, the selection of the multiple authentication methods is recorded to obtain the number of times each authentication method is adopted; According to the number of times each authentication method is adopted, a layer of weight is added to the score of each authentication method in the intelligent recommendation model, and the recommendation order of the multiple authentication methods in the intelligent recommendation model is adjusted.

2. The recommendation method according to claim 1, characterized in that: The training method of the intelligent recommendation model includes: Obtaining static state information and dynamic state information of the sample user; wherein the static state information of the sample user is used to characterize the physical state of the sample user; the dynamic state information of the sample user includes image features and voiceprint features of the sample user; Obtaining a training set of authentication methods; wherein the training set includes multiple authentication methods with labels, and the labels are used to describe the sorting positions of the authentication methods in the training set; The neural network model is trained using the static state information and dynamic state information of the sample users and the training set of the authentication method to obtain the intelligent recommendation model.

3. The recommendation method according to claim 1, characterized in that: The extracting the dynamic state information of the user from the historical video data includes: Extracting the image information and voice information of the user's historical business transactions from the historical video data; The image features of the user are extracted from the image information of the user's historical business handling, and the voiceprint features of the user are extracted from the voice information of the user's historical business handling.

4. The recommendation method according to claim 1, characterized in that: The multiple authentication methods include: electronic signature, face recognition, voiceprint recognition, and button confirmation.

5. A device for recommending an authentication method, characterized in that: include: The first acquisition unit is used to acquire the static state information of the user when the user handles counter services, and extract the dynamic state information of the user from the historical video data; wherein the static state information is used to characterize the physical state of the user, and the physical state of the user includes: the health state of the user, the health state of the hands, the health state of the eyes, and the health state of the mouth; the dynamic state information includes the image features and voiceprint features of the user; A processing unit, used to process the static state information and dynamic state information of the user using an intelligent recommendation model to obtain arrangement results of multiple authentication methods; wherein the intelligent recommendation model is obtained by training a neural network model based on the static state information and dynamic state information of sample users; The device is also used for: According to the click feedback information of the user in the arrangement result of the multiple authentication methods, the selection of the multiple authentication methods is recorded to obtain the number of times each authentication method is adopted; According to the number of times each authentication method is adopted, a layer of weight is added to the score of each authentication method in the intelligent recommendation model, and the recommendation order of the multiple authentication methods in the intelligent recommendation model is adjusted.

6. The recommendation device according to claim 5, characterized in that: Also includes: A second acquisition unit is used to acquire static state information and dynamic state information of the sample user; wherein the static state information of the sample user is used to characterize the physical state of the sample user; and the dynamic state information of the sample user includes image features and voiceprint features of the sample user; A third acquisition unit is used to acquire a training set of authentication methods; wherein the training set includes multiple authentication methods with labels, and the labels are used to describe the sorting position of the authentication methods in the training set; A training unit is used to train the neural network model using the static state information and dynamic state information of the sample user and the training set of the authentication method to obtain the intelligent recommendation model.

7. The device according to claim 5, when the first acquisition unit executes the step of extracting the dynamic state information of the user from the historical video data, is specifically configured to: Extracting the image information and voice information of the user's historical business transactions from the historical video data; The image features of the user are extracted from the image information of the user's historical business handling, and the voiceprint features of the user are extracted from the voice information of the user's historical business handling.

8. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 4.

9. A computer storage medium, characterized in that A computer program is stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images