A method and device for adjusting data allocation permissions based on video facial expressions

Abstract

The application relates to a data allocation permission adjustment method and device based on video expression actions, an electronic device and a computer readable medium. The method comprises the following steps: obtaining initial data allocation permission and access information of a target; determining video text content through the access information; establishing a real-time video connection with the target, and displaying the video text content according to the video connection to generate video data; identifying the expression actions of a user in the video data to determine a corresponding permission adjustment coefficient; and adjusting the data allocation permission of the user according to the initial permission and the permission adjustment coefficient. The data allocation permission adjustment method and device based on video expression actions, the electronic device and the computer readable medium can identify micro expressions and micro actions of a user, check the security level of the user from multiple angles, quickly and accurately adjust the access permission of the user, and ensure system safety, data safety and transaction safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer information processing, in particular, to a data allocation permission adjustment method and device based on video expression actions, an electronic device and a computer readable medium. BACKGROUND

[0002] Data security refers to protecting digital information from unauthorized access, damage or theft throughout its entire life cycle. This concept covers all aspects of information security, from the physical security of hardware and storage devices to management and access control, as well as the logical security of software applications. With the development of the information society, many companies provide access services for data resources, in order to facilitate user use, data resources running users in the specified range of data resources for change, transfer, off-site storage and use, etc.

[0003] For data resource providers, data resource security can be improved from software and hardware aspects. However, the data resource provider has limited ways to verify the user of the data resource. In the prior art, the verification method for the user is basically limited to checking the basic information submitted by the user, or verifying the authenticity of the user through a third party. How to reasonably allocate permissions for users and improve the accuracy of user permission allocation while meeting the data security requirements is a problem faced today.

[0004] Therefore, a new data allocation permission adjustment method and device based on video expression actions, an electronic device and a computer readable medium are needed.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present application, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] Therefore, the present application provides a data allocation permission adjustment method and device based on video expression actions, an electronic device and a computer readable medium, which can identify micro expressions and micro actions of users to assess the security level of users from multiple angles, thereby quickly and accurately adjusting the access permissions of users and ensuring system security, data security and transaction security.

[0007] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0008] According to an aspect of the present application, a data allocation permission adjustment method based on video expression action is provided, which comprises: obtaining initial data allocation permission and access information of a target; determining video text content through the access information; establishing a real-time video connection with the target and displaying the video text content according to the video connection to generate video data; identifying the expression action of a user in the video data to determine a corresponding permission adjustment coefficient; and adjusting the data allocation permission of the user according to the initial permission and the permission adjustment coefficient.

[0009] Optionally, determining the video text content through the access information comprises: extracting basic information from the access information to generate check text content; extracting feature information from the access information to generate communication text content; and generating the video text content containing multiple item contents according to the check text content and the communication text content.

[0010] Optionally, displaying the video text content according to the video connection to generate video data comprises: extracting item contents one by one from the multiple item contents in the video text content; displaying the item contents on a user terminal during the video connection; and generating the video data according to the answer content of the user.

[0011] Optionally, obtaining the initial data allocation permission and the access information of the target comprises: determining the corresponding initial data allocation permission of the user according to the user information of the user.

[0012] Optionally, identifying the expression action of the user in the video data to determine the corresponding permission adjustment coefficient comprises: inputting the video data into an expression action recognition model to generate an expression action recognition result; and determining the permission adjustment coefficient of the user according to the expression action recognition result.

[0013] Optionally, the method further comprises: obtaining historical video data of a historical user; determining sample labels for the historical video data; and training a neural network model through the historical video data with sample labels to generate the expression action recognition model.

[0014] Optionally, determining sample labels for the historical video data comprises: determining expression action labels for the historical video data; determining positive sample labels or negative sample labels for the historical video data according to subsequent behavior data of the historical user; and generating multi-dimensional sample labels through the expression action labels, the positive sample labels or the negative sample labels.

[0015] Optionally, determining the permission adjustment coefficient of the user according to the expression action recognition result comprises: generating an expression score, an action score, and an expression action score according to the expression action recognition result; and determining the permission adjustment coefficient of the user according to the expression score, the action score, and the expression action score.

[0016] Optionally, generating an expression score, an action score, and an expression action score according to the expression action recognition result comprises: extracting an expression recognition category and a corresponding expression quantity from the expression action recognition result to generate the expression score; extracting an action recognition category and a corresponding action quantity from the expression action recognition result to generate the action score; and generating the expression action score from a category and a corresponding quantity of expressions and actions that appear simultaneously in the expression action recognition result.

[0017] According to an aspect of the present application, a device for adjusting data distribution permission based on video expression action is provided, which comprises: an initial module configured to obtain initial permission of data distribution and access information of a target; a content module configured to determine video text content through the access information; a data module configured to establish real-time video connection with the target and display the video text content to generate video data according to the video connection; a coefficient module configured to identify expression action of a user in the video data to determine a corresponding permission adjustment coefficient; and an adjustment module configured to adjust data distribution permission of the user according to the initial permission and the permission adjustment coefficient.

[0018] According to an aspect of the present application, an electronic device is provided, which comprises: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0019] According to an aspect of the present application, a computer readable medium is provided, which stores a computer program, and the program is executed by a processor to implement the method as described above.

[0020] According to the data assignment permission adjustment method and device based on video expression action, the data assignment initial permission and access information of a target are acquired, the video text content is determined through the access information, a real-time video connection is established with the target, the video text content is displayed according to the video connection to generate video data, the expression action of a user in the video data is recognized to determine a corresponding permission adjustment coefficient, and the data assignment permission of the user is adjusted according to the initial permission and the permission adjustment coefficient. In this way, the micro-expression and micro-action of the user can be recognized, the security level of the user can be examined from multiple angles, the access permission of the user can be quickly and accurately adjusted, and system security, data security and transaction security can be ensured.

[0021] It should be understood that the foregoing general description and the following detailed description are only examples and are not restrictive of the application. BRIEF DESCRIPTION OF DRAWINGS

[0022] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0023] Figure 1 FIG. 1 is a system block diagram of a data assignment permission adjustment method and device based on video expression action according to an example embodiment.

[0024] Figure 2 FIG. 2 is a flowchart of a data assignment permission adjustment method based on video expression action according to an example embodiment.

[0025] Figure 3 FIG. 3 is a flowchart of a data assignment permission adjustment method based on video expression action according to another example embodiment.

[0026] Figure 4 FIG. 4 is a flowchart of a data assignment permission adjustment method based on video expression action according to another example embodiment.

[0027] Figure 5 FIG. 5 is a block diagram of a data assignment permission adjustment device based on video expression action according to an example embodiment.

[0028] Figure 6 FIG. 6 is a block diagram of an electronic device according to an example embodiment. DETAILED DESCRIPTION

[0029] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the several views.

[0030] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the

[0031] The block diagrams in the drawings show only the functionality of the embodiments and do not imply that the embodiments will take the form discussed in connection therewith. As illustrated in the drawings, the enclosed blocks can be functional blocks that can be implemented in software or with hardware such as a processor of a mobile terminal or similar device.

[0032] The flow diagrams depicted herein are examples of sequences of operations that can be performed. Such sequences can be embodied in software or code modules executed by a processor that are not necessarily limited to any specific

[0033] It should be understood that although the terms first, second, third, etc. can be used herein to describe various components, these components should not be limited by these terms. These terms are used only to distinguish one component from another. Thus, a first component discussed below could be termed a second component without departing from the teachings of the present disclosure. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0034] Those skilled in the art will understand that the modules or flowcharts depicted in the accompanying drawings are only schematic and that the modules or flowcharts in the drawings do not necessarily correspond to the actual implementation of the application. They have therefore not been drawn on scale. In the drawings, the size of the modules or flowcharts can be exaggerated and can not in particular correspond to the dimensions of a real implementation. The detailed description only explains certain embodiments. Other embodiments can be derived from the application by making simple technical modifications, which should not be considered as limiting the scope of the application.

[0035] In the present application, the data allocation right refers to the access right of any available resource class data, such as material class data resource, information class data resource, and time class data resource, wherein the information class data resource includes computing resource and various types of data resource, and the data resource includes various special data in various fields.

[0036] Figure 1 is a system block diagram of a method and device for adjusting data allocation authority based on video facial expression actions according to an exemplary embodiment.

[0037] As shown in Figure 1 , the system architecture 10 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a communication link medium between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0038] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as Internet service type applications, shopping type applications, web browser applications, instant messaging tools, email clients, social platform software, etc.

[0039] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc.

[0040] The server 105 can be a server that provides various services, such as a background management server that provides support for Internet data service type websites browsed by users using the terminal devices 101, 102, 103. The background management server can analyze and process received user data, and feed back the processing results (such as data allocation authority) to the administrators of the Internet service website and / or the terminal devices 101, 102, 103.

[0041] The server 105 may, for example, obtain initial data allocation authority and access information of a target; the server 105 may, for example, determine video text content through the access information; the server 105 may, for example, establish a real-time video connection with the target and display the video text content according to the video connection to generate video data; the server 105 may, for example, identify facial expression actions of a user in the video data to determine a corresponding authority adjustment coefficient; the server 105 may, for example, adjust the data allocation authority of the user according to the initial authority and the authority adjustment coefficient.

[0042] The server 105 may, for example, also obtain historical video data of historical users; the server 105 may, for example, also determine sample labels for the historical video data; the server 105 may, for example, also train a neural network model through historical video data with sample labels to generate the facial expression action identification model.

[0043] Server 105 can be a single physical server, or it can consist of multiple servers. It should be noted that the data allocation permission adjustment method based on video facial expressions provided in this embodiment can be executed by server 105. Correspondingly, the data allocation permission adjustment device based on video facial expressions can be located in server 105. The web page provided to users for browsing the internet data service platform is generally located in terminal devices 101, 102, and 103.

[0044] Figure 2 This is a flowchart illustrating a data allocation permission adjustment method based on video facial expressions and actions, according to an exemplary embodiment. The data allocation permission adjustment method 20 based on video facial expressions and actions includes at least steps S202 to S210.

[0045] like Figure 2 As shown, in S202, the initial data allocation permissions and access information of the target are obtained. When the user is a historical user, the user's current permissions can be directly obtained as the initial data allocation permissions. When the user is a newly joined user, the corresponding initial data allocation permissions can be determined based on the user's user information. For example, the initial data allocation permissions can be the data usage permissions configured by the system automatically recognizing the user's account level when the user registers for the first time, i.e., which data the user can use or access. Alternatively, the initial data allocation permissions can be the data allocation permissions after the user has been registered for a period of time or has obtained an authentication or permission level.

[0046] In this embodiment, the target can be a user, who can be an individual user or an enterprise user. The access information may include basic information authorized by the user, such as business account information, the user's terminal device identification information, and the user's geographical location. The access information may also include behavioral information, such as the user's page operation data, the user's business access duration, and the user's business access frequency. The specific content of the user information can be determined according to the actual application scenario and is not limited here.

[0047] In one embodiment, access information can be input into a pre-trained user risk model to generate a user risk score. The user's risk security level can then be determined based on this score, and the risk security level corresponds to initial access permissions. Generally, a higher risk score corresponds to a lower user risk security level, and vice versa. Therefore, a higher risk security level corresponds to greater initial access permissions, with specific values ​​adjustable based on the actual scenario.

[0048] The user risk model can include a user behavior risk model, a user access risk model, a user data use risk model, a user credit risk model, a user transaction risk model, a third-party credit risk model, and the like.

[0049] In S204, the video text content is determined based on the access information. For example, basic information is extracted from the access information to generate a check text content; feature information is extracted from the access information to generate a communication text content; and the video text content including a plurality of item contents is generated based on the check text content and the communication text content.

[0050] In the embodiments of the present application, in order to improve the accuracy of determining the data allocation authority, the method provided by the present application can construct a video text content template corresponding to each business type based on sample data of each business type obtained from a plurality of data acquisition paths. In the embodiments of the present application, based on the sample data associated with different business types, a video text content template suitable for generating risk decision rules corresponding to each business type can be constructed. Alternatively, based on the sample data associated with different business types, a total video text content template can be constructed, and each actual business scenario selects and uses according to its own content.

[0051] In a specific embodiment, the check text content can be generated according to the content of the access information filled in by the user, and the check text content can include basic information such as user name, age, address, work, and hometown.

[0052] In a specific application, the check text content can be used to check the access information filled in by the user, and a check item can be generated according to each check content, for example, the following three check items can be generated corresponding to the user information:

[0053] User name: XX;

[0054] User age: XX;

[0055] User address: X province X city XX street XX community.

[0056] In another specific embodiment, feature information can be extracted from the access information filled in by the user, for example, enterprise operation information can be extracted from the user information to generate enterprise operation type feature information, fixed asset information can be extracted from the access information to generate fixed asset type feature information, and other feature information such as spouse income and working years can be extracted to generate corresponding feature information. According to the feature information, a communication text template can be called to generate a communication text content.

[0057] In another specific application, the communication text content can be used for side checking of the user's access information. Based on the user's filled-in information about the enterprise operation, news content of other enterprises in the same industry can be extracted to generate communication content for chatting with the user, so as to verify the user's access information from the side according to the user's feedback in the later stage.

[0058] For example, based on the fixed asset class characteristic information, the following three check items can be generated, which can be chat topics:

[0059] The current selling price range of the property;

[0060] The environment around the property;

[0061] The traffic situation around the property.

[0062] The video text content is generated by checking the items corresponding to the text content and the communication text content.

[0063] In S206, a real-time video connection is established with the target, and the video text content is displayed according to the video connection to generate video data. The user can be scheduled for a video communication, and the whole process of the video can be recorded under the authorization of the user during the video communication.

[0064] In one embodiment, the item content can be extracted one by one from the item content in the video text content; the item content is displayed on the user terminal during the video connection; and the video data is generated according to the user's answer content.

[0065] For example, the multiple items in the video text content can be displayed on the user terminal respectively for the user to reply. More specifically, the items in the video text content can be randomly displayed on the user terminal in a random arrangement. Each time an item is displayed, real-time speech recognition can also be performed to determine whether the user has completed the reply content.

[0066] In one embodiment, a voice robot can also be introduced to have in-depth communication with the user on certain chat content during the video communication. For example, for the user's fixed asset class content, information such as house prices and traffic around the property can be obtained in advance. During the user's reply to this question, in-depth discussion can be carried out according to the user's reply information.

[0067] In S208, the expression action of the user in the video data is recognized to determine the corresponding permission adjustment coefficient. The video data can be input into an expression action recognition model to generate an expression action recognition result; and the permission adjustment coefficient of the user is determined according to the expression action recognition result.

[0068] The specific details of "determining the user's permission adjustment coefficient based on the facial expression recognition results" will be provided later. Figure 4 The corresponding embodiments are described in detail.

[0069] In S210, the user's data allocation permissions are adjusted based on the initial permissions and the permission adjustment coefficient. The adjusted permissions can be calculated based on the adjustment coefficient and the initial permissions; the adjusted permissions may be greater or less than the initial permissions. A reminder message can also be generated to notify the user after the permission adjustment.

[0070] According to the data allocation permission adjustment method based on video facial expressions and actions in this application, the method involves: obtaining the target's initial data allocation permission and access information; determining the video text content based on the access information; establishing a real-time video connection with the target and displaying the video text content based on the video connection to generate video data; identifying the user's facial expressions and actions in the video data to determine their corresponding permission adjustment coefficients; and adjusting the user's data allocation permission based on the initial permission and the permission adjustment coefficients. This method can identify the user's micro-expressions and micro-actions to assess the user's security level from multiple perspectives, thereby quickly and accurately adjusting the user's access permissions and ensuring system security, data security, and transaction security.

[0071] It should be clearly understood that this application describes how specific examples are formed and used, but the principles of this application are not limited to any details of these examples. Rather, based on the teachings of the disclosure of this application, these principles can be applied to many other embodiments.

[0072] Figure 3 This is a flowchart illustrating a data allocation permission adjustment method based on video facial expressions and actions, according to another exemplary embodiment. Figure 3 The process shown in step 30 is a detailed description of "generating an facial expression and motion recognition model".

[0073] like Figure 3 As shown in step S302, historical video data of historical users is obtained.

[0074] In S304, sample labels are determined for the historical video data.

[0075] In one embodiment, for example, facial expression tags can be determined for the historical video data; multiple action or facial expression tags can be predefined, and the action or facial expression tags can be user facial expressions or actions commonly used in fraud cases.

[0076] For example, action tags could be scratching the head, shaking the leg, fidgeting, etc.; facial expression tags could be avoiding eye contact, being nervous, being angry, etc.

[0077] In one embodiment, positive or negative sample labels can be determined for the historical video data based on the subsequent behavior data of historical users; whether a user has positive or negative data usage habits can be comprehensively determined by whether the user uses good data access channels, data storage methods, and data transmission habits.

[0078] For example, if a historical user accesses data via a public network and stores it using Baidu Cloud or a third-party chat application, their behavior can be identified as a negative data usage habit, corresponding to a negative sample label. If the historical user habitually encrypts data transmissions, their behavior can be identified as a positive data usage habit, and they can be assigned a positive sample label. Of course, other labeling methods are also possible. For instance, using ordinary chat software to transmit data can indicate a negative data usage habit, while using an intranet for data transmission can indicate a positive data usage habit, and so on.

[0079] Multi-dimensional sample labels are generated using the facial expression tags, the positive sample labels, or the negative sample labels.

[0080] In S306, the neural network model is trained using historical video data with sample labels to generate the facial expression recognition model.

[0081] For example, for sample data, an initial neural network model is constructed. Labeled video data from the sample data is input into the initial neural network model to obtain predicted labels. These predicted labels are compared with the corresponding real labels to determine if they match. The number of predicted labels matching the real labels is counted, and the percentage of such predicted labels in the total number of predicted labels is calculated. If this percentage is greater than or equal to a preset percentage, the initial neural network model converges, resulting in a trained facial expression recognition model. If the percentage is less than the preset percentage, the parameters in the initial neural network model are adjusted, and the adjusted initial neural network model is used to re-predict the predicted labels for each historical user until the percentage is greater than or equal to the preset percentage. The method for adjusting the parameters in the adjusted model can employ stochastic gradient descent, gradient descent algorithms, or normal equations.

[0082] If the number of times the parameters of the initial neural network model are adjusted exceeds the preset number, the model used to build the initial neural network model can be replaced to improve the model training efficiency.

[0083] Figure 4 This is a flowchart illustrating a data allocation permission adjustment method based on video facial expressions and actions, according to another exemplary embodiment. Figure 4 The process shown in step 40 is...Figure 2 Detailed description of S208 in the flow shown.

[0084] As shown in S402, the video data is input into the expression action recognition model to generate an expression action recognition result. Figure 4

[0085] In S404, an expression score, an action score, and an expression action score are generated according to the expression action recognition result.

[0086] In one embodiment, the expression recognition categories and the corresponding number of expressions can be extracted from the expression action recognition result to generate the expression score; in one embodiment, the action recognition categories and the corresponding number of actions can also be extracted from the expression action recognition result to generate the action score; and in one embodiment, the categories and the corresponding number of expressions and actions that appear simultaneously in the expression action recognition result can also be used to generate the expression action score.

[0087] In a specific application, the expression action recognition result corresponding to the positive sample label of the historical user can be extracted, and the average number of expressions, actions, and expression actions under different statistical categories determined according to the expression action recognition result corresponding to the positive sample label is used as the positive sample average. The expression action recognition result corresponding to the negative sample label of the historical user can also be extracted, and the average number of expressions, actions, and expression actions under different statistical categories determined according to the expression action recognition result corresponding to the negative sample label is used as the negative sample average.

[0088] In one embodiment, the data in the expression action recognition result of the current user can be sorted, and the number of expressions, actions, and expression actions under different statistical categories can be sorted respectively, and then compared with the positive sample average and the negative sample average to generate the score.

[0089] For example, the expression score of the current user can be calculated as follows:

[0090]

[0091] wherein P a is the label score, P a + is the positive expression score, is the negative label score; is the number of labels corresponding to the i-th positive expression category, is the weight corresponding to the i-th positive expression category, A i + is the average value of the historical user corresponding to the i-th positive expression category.​

[0092] The action score and the expression action score can be calculated according to the above public content, and different weight values can be set, which are not limited in the present application.

[0093] In S406, the permission adjustment coefficient of the user is determined according to the expression score, the action score and the expression action score. The expression score, the action score and the expression action score are summarized to generate the overall video score of the user. When the video score is greater than 1, the data allocation permission of the user can be improved. When the video score is less than 1, the data allocation permission of the user can be reduced. Different adjustment ranges can also be set, and the adjustment can be different according to the actual score of the user.

[0094] Those skilled in the art can understand that all or part of the steps of the above embodiments are implemented as computer programs executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present application are executed. The program can be stored in a computer readable storage medium, which can be a read-only memory, a magnetic disk or an optical disk, etc.

[0095] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not for limiting purposes. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of the processes. In addition, it is also easy to understand that the processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0096] The following is a device embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0097] Figure 5 is a block diagram of a data allocation permission adjustment device based on video expression action according to an exemplary embodiment. As shown in Figure 5 The data allocation permission adjustment device based on video expression action 50 includes an initial module 502, a content module 504, a data module 506, a coefficient module 508 and an adjustment module 510.

[0098] The initial module 502 is used to obtain the data allocation initial permission and access information of the target; the initial module 502 is also used to determine the corresponding data allocation initial permission of the user according to the user information of the user.

[0099] The content module 504 is configured to determine the video text content according to the access information, and further configured to extract basic information from the access information to generate a check text content, extract feature information from the access information to generate a communication text content, and generate the video text content containing a plurality of item contents according to the check text content and the communication text content.

[0100] The data module 506 is configured to establish a real-time video connection with the target, display the video text content according to the video connection to generate video data, further configured to extract the item contents from the video text content one by one, display the item contents on a user terminal during the video connection, and generate the video data according to the answer content of the user.

[0101] The coefficient module 508 is configured to identify the expression action of the user in the video data to determine the corresponding permission adjustment coefficient, further configured to input the video data into an expression action recognition model to generate an expression action recognition result, and determine the permission adjustment coefficient of the user according to the expression action recognition result.

[0102] The adjustment module 510 is configured to adjust the data allocation permission of the user according to the initial permission and the permission adjustment coefficient.

[0103] The data allocation permission adjustment device based on video expression action according to the present application, by obtaining the data allocation initial permission and the access information of the target, determining the video text content according to the access information, establishing a real-time video connection with the target, displaying the video text content according to the video connection to generate video data, identifying the expression action of the user in the video data to determine the corresponding permission adjustment coefficient, and adjusting the data allocation permission of the user according to the initial permission and the permission adjustment coefficient, can identify the micro-expression and micro-action of the user, examine the security level of the user from multiple angles, quickly and accurately adjust the access permission of the user, and ensure the system security, data security and transaction security.

[0104] As shown in Figure 6 The present application provides an electronic device, which comprises a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140.

[0105] The memory 1130 is used for storing a computer program.

[0106] The processor 1110 is configured to implement the method of adjusting the data distribution permission based on the facial expression and action of the video in any of the above embodiments when executing the program stored in the memory 1130.

[0107] The electronic device provided by the embodiment of the present application is configured to obtain the initial permission of data distribution and access information of a target by the processor 1110 executing the program stored in the memory 1130; determine the video text content by the access information; establish a real-time video connection with the target, and display the video text content to generate video data according to the video connection; identify the facial expression and action of the user in the video data to determine the corresponding permission adjustment coefficient; and adjust the data distribution permission of the user according to the initial permission and the permission adjustment coefficient.

[0108] The communication bus 1140 mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0109] The communication interface 1120 is configured to communicate between the above-mentioned electronic device and other devices.

[0110] The memory 1130 can include a Random Access Memory (RAM), and can also include a non-volatile memory, for example, at least one disk memory 1130. Optionally, the memory 1130 can also be at least one storage device located away from the aforementioned processor 1110.

[0111] The processor 1110 described above can be a general processor 1110, including a central processing unit 1110 (CPU), a network processing unit 1110 (NP), etc.; or can be a digital signal processor 1110 (DSP), an application specific integrated circuit 1110 (ASIC), a field-programmable gate array 1110 (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0112] The computer readable storage medium stores one or more programs, which can be executed by one or more processors 1110 to implement the method for adjusting the data distribution permission based on the video expression action according to any of the above embodiments.

[0113] In the above embodiments, the implementation can be achieved wholly or partially by software, hardware, firmware or any combination thereof. When implemented by software, the implementation can be achieved wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function according to the embodiments of the present application is wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available media sets. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD) or a semiconductor medium (such as a solid state disk (SSD)) and the like.

[0114] The exemplary embodiments of the present application are specifically shown and described above. It should be understood that the present application is not limited to the detailed structure, arrangement or implementation method described herein; on the contrary, the present application is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the appended claims.

Claims

1. A method for adjusting data allocation permissions based on video facial expressions and actions, characterized in that, include: Obtain the target's data and assign initial permissions and access information; Basic information is extracted from the access information to generate verification text content; Feature information is extracted from the access information to generate communication text content, wherein the communication text content is used to indirectly verify the user's access information. Based on the business information filled in by the user, news content of other companies in the same industry is extracted to generate the communication text content to indirectly verify the user's access information. Generate video text content containing multiple entries based on the verification text content and the communication text content; A real-time video connection is established with the target, and the video text content is displayed based on the video connection. Real-time speech recognition is performed to determine whether the user has completed the response. Video communication is recorded to generate video data. The video data is input into the facial expression and motion recognition model to generate facial expression and motion recognition results; Based on the facial expression and action recognition results, generate facial expression scores, action scores, and facial expression and action scores; The formula for calculating facial expression scores is as follows: Among them, P a Rate the expressions, P a + Rate positive expressions. Rate negative facial expressions; a i + Let i be the number of tags corresponding to the i-th positive emoji category. Let A be the weight corresponding to the i-th positive expression category. i + This represents the average number of emojis used by historical users corresponding to the i-th positive emoji category. The user's permission adjustment coefficient is determined based on the facial expression score, the action score, and the facial expression and action score. The user's data allocation permissions are adjusted based on the initial permissions and the permission adjustment coefficient.

2. The method as described in claim 1, characterized in that, Displaying the video text content based on the video link to generate video data includes: Extract the content of each item from the multiple items in the video text content one by one; The content of the entry is displayed on the user terminal during the video connection process; The video data is generated based on the user's response.

3. The method as described in claim 1, characterized in that, Obtain the target's data, assign initial permissions and access information, including: Determine the initial data permissions assigned to the user based on their user information.

4. The method as described in claim 1, characterized in that, Also includes: Obtain historical video data from historical users; Determine sample labels for the historical video data; The facial expression recognition model is generated by training a neural network model with historical video data bearing sample labels.

5. The method as described in claim 4, characterized in that, Determining sample labels for the historical video data includes: Determine facial expression and action tags for the historical video data; Determine positive or negative sample labels for the historical video data based on the subsequent behavior data of historical users; Multi-dimensional sample labels are generated using the facial expression tags, the positive sample labels, or the negative sample labels.

6. The method as described in claim 1, characterized in that, Based on the facial expression and action recognition results, an expression score, an action score, and an expression-action score are generated, including: The facial expression recognition results are used to extract the facial expression categories and their corresponding number of expressions to generate the facial expression score. The action recognition results are used to extract the action recognition type and its corresponding number of actions to generate the action score; The facial expression and action score is generated from the types and quantities of facial expressions and actions that appear simultaneously in the facial expression and action recognition results.

7. A data allocation and permission adjustment device based on video facial expressions and actions, characterized in that, include: The initial module is used to acquire the target's data and assign initial permissions and access information; The content module is used to extract basic information from the access information to generate verification text content; Feature information is extracted from the access information to generate communication text content, wherein the communication text content is used to indirectly verify the user's access information. Based on the business information filled in by the user, news content of other companies in the same industry is extracted to generate the communication text content to indirectly verify the user's access information. Video text content containing multiple entries is generated based on the verification text content and the communication text content. The data module is used to establish a real-time video connection with the target, display the video text content according to the video connection, and perform real-time speech recognition to determine whether the user has completed the response. It also records the video communication process to generate video data. The coefficient module is used to input the video data into the facial expression and motion recognition model to generate facial expression and motion recognition results; based on the facial expression and motion recognition results, it generates an expression score, a motion score, and an expression-motion score; the formula for calculating the expression score is as follows: Among them, P a Rate the expressions, P a + Rate positive expressions. Rate negative facial expressions; a i + Let i be the number of tags corresponding to the i-th positive emoji category. Let A be the weight corresponding to the i-th positive expression category. i + The average number of expressions used by historical users corresponding to the i-th positive expression category; the user's permission adjustment coefficient is determined based on the expression score, the action score, and the expression-action score; The adjustment module is used to adjust the user's data allocation permissions based on the initial permissions and the permission adjustment coefficient.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images