Interface interaction methods, devices, equipment, media and products

Abstract

This document relates to a user interface interaction method, apparatus, device, medium, and product. The method includes: displaying a first interface; wherein the first interface presents a first assessment task and a first assessment result corresponding to the first assessment task, the first assessment task indicating that at least one first assessment workflow is used to assess a first assessment object; in response to a first trigger operation on a second assessment workflow, displaying the workflow information of the second assessment workflow and the second assessment result corresponding to the second assessment workflow in a visual format; wherein the second assessment workflow is any one of the at least one first assessment workflow. This document can meet users' needs for efficiently and clearly obtaining assessment-related information, effectively improving the user experience.

Description

Technical Field

[0001] This article relates to the field of computer technology, and in particular to an interface interaction method, device, equipment, medium and product. Background Technology

[0002] With the continuous development of computer technology and the popularization of smart terminals, more and more applications support user interface interaction, providing diverse functions through the interface. In order to ensure the reliability of specified objects such as network models, it is currently necessary to evaluate these specified objects in order to promptly identify and optimize them. However, the current interface interaction methods related to evaluation tasks are difficult to meet user needs. Summary of the Invention

[0003] To address, or at least partially address, the aforementioned technical problems, this document provides an interface interaction method, apparatus, device, medium, and product.

[0004] Firstly, this paper provides a user interface interaction method, the method comprising: displaying a first interface; wherein the first interface presents a first assessment task and a first assessment result corresponding to the first assessment task, the first assessment task being used to instruct: to assess a first assessment object using at least one first assessment workflow; in response to a first trigger operation on a second assessment workflow, displaying the workflow information of the second assessment workflow in a visual form, and displaying the second assessment result corresponding to the second assessment workflow; wherein the second assessment workflow is any one of the at least one first assessment workflow.

[0005] Secondly, this paper also provides an interface interaction device, including: an interface display module for displaying a first interface; wherein the first interface presents a first assessment task and a first assessment result corresponding to the first assessment task, the first assessment task being used to instruct: to use at least one first assessment workflow to assess the first assessment object; and an information display module for responding to a first trigger operation on a second assessment workflow, displaying the workflow information of the second assessment workflow in a visual form, and displaying the second assessment result corresponding to the second assessment workflow; wherein the second assessment workflow is any one of the at least one first assessment workflow.

[0006] Thirdly, this document also provides an electronic device, comprising: a storage device storing a computer program thereon; and a processing device for executing the computer program in the storage device to implement the interface interaction method provided herein.

[0007] Fourthly, this document also provides a computer-readable storage medium storing a computer program for executing the interface interaction method provided herein.

[0008] Fifthly, this document also provides a computer program product, including a computer program that, when executed by a processor, implements the interface interaction method provided herein.

[0009] The technical solution provided in this paper can display a first interface, which presents a first evaluation task and a first evaluation result corresponding to the first evaluation task. The first evaluation task is used to indicate: to evaluate the first evaluation object using at least one first evaluation workflow; in response to a first trigger operation on the second evaluation workflow, the workflow information of the second evaluation workflow and the second evaluation result corresponding to the second evaluation workflow are displayed in a visual form; wherein, the second evaluation workflow is any one of at least one first evaluation workflow. The above method presents the assessment tasks and corresponding assessment results on the interface, allowing users to clearly understand the assessment workflow and assessment objects used in the assessment tasks. Furthermore, users can trigger any assessment workflow used by the assessment task as needed. The workflow information of the triggered workflow is then displayed to the user in a visual format, along with the corresponding assessment results. This facilitates users' intuitive and efficient understanding of the relevant information about the assessment workflow used in the assessment task. Compared to methods that only present the final assessment results of the assessment task on the interface, the method provided in this paper can meet users' needs for efficiently and clearly obtaining assessment-related information, effectively improving the user experience.

[0010] It should be understood that the descriptions in this section are not intended to identify key or essential features of the embodiments herein, nor are they intended to limit the scope of this document. Other features of this document will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this description and, together with the description, serve to explain the principles herein.

[0012] To more clearly illustrate the technical solutions in this document or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0013] Figure 1 This is a schematic diagram illustrating one application scenario provided in this article; Figure 2A flowchart illustrating one of the interface interaction methods provided in this paper; Figure 3 This is a schematic diagram of the interface interaction provided in this article; Figure 4 This is a schematic diagram of an interface provided for this article; Figure 5 This is a schematic diagram of an interface provided for this article; Figure 6 This is a schematic diagram of an interface provided for this article; Figure 7 This paper provides a schematic diagram of the structure of an interface interaction device. Figure 8 This is a schematic diagram of the structure of an electronic device provided in this article. Detailed Implementation

[0014] To better understand the objectives, features, and advantages outlined above, the solutions described herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0015] It is understood that before using the technical solutions disclosed in the embodiments of this article, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this article in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0016] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as electronic devices, applications, servers, or storage media, that perform the operations described herein, based on the prompt message.

[0017] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0018] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation method described in this article. Other methods that comply with relevant laws and regulations may also be applied to the implementation method described in this article.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of this document, but other practices may also be adopted in ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments described herein, and not all of them.

[0020] First, to facilitate understanding of the application scenario of this paper, for example, this paper proposes the following: Figure 1 The diagram illustrates an application scenario, primarily showing the terminal device and the server. This paper does not limit the implementation of the terminal device; it can be any type of mobile terminal, fixed terminal, or portable terminal, including but not limited to mobile phones, tablets, laptops, desktop computers, and wearable devices. The terminal device can run applications that support user interface interaction, displaying the user interface on the device screen. In some scenarios, users can operate the terminal device and interact with the interface presented on it. For example, a user can trigger the terminal device to display a desired interface and interact based on the elements presented on the interface. The terminal device can respond to the user's actions, including but not limited to: displaying a first interface; wherein the first interface presents a first evaluation task and a corresponding first evaluation result, the first evaluation task indicating: using at least one first evaluation workflow to evaluate a first evaluation object; responding to a first trigger operation on a second evaluation workflow, displaying the workflow information of the second evaluation workflow in a visual form, and displaying the corresponding second evaluation result; wherein the second evaluation workflow is any one of at least one first evaluation workflow.

[0021] This paper does not restrict the implementation method of the server. For example, the server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, security services, content delivery networks, or big data. The server can include, for example, computing systems / servers, such as mainframes, edge computing nodes, and computing devices in a cloud environment. In some cases, the server can provide background services for the terminal device. A communication connection can be established between the server and the terminal device, which can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth connections, mobile network connections, Universal Serial Bus connections, and Wi-Fi connections; this paper is not limited in this respect. In some scenarios, the terminal device can independently execute the interface interaction method. In other scenarios, the terminal device may need the server to provide auxiliary services during the execution of the interface interaction method. For example, the terminal device can use the server to perform evaluation tasks and obtain the evaluation results generated by the server.

[0022] It should be understood that the above are all exemplary descriptions and should not be regarded as limiting the application scenarios of the interface interaction methods provided in this article.

[0023] This paper does not restrict the application scenarios of the interface interaction method. It can be applied to any scenario where an evaluation task needs to be performed. For example, the interface interaction method can be applied to security evaluation scenarios involving generative models, where the evaluation task is used to evaluate the security of generative models.

[0024] Figure 2 This is a flowchart illustrating a user interface interaction method provided in this paper. This method can be executed by a user interface interaction device, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. For example... Figure 2 As shown, the method mainly includes the following steps 202 to 204: Step 202: Display the first interface; wherein, the first interface presents the first assessment task and the first assessment result corresponding to the first assessment task, and the first assessment task is used to indicate: to use at least one first assessment workflow to assess the first assessment object.

[0025] This paper does not impose restrictions on the evaluation objects and evaluation workflows. Specific settings can be flexibly configured based on the business scenarios of the interface interaction methods. For example, the first evaluation object includes generative models, such as a single model or an intelligent agent. The first evaluation workflow is any workflow among multiple preset workflows. Each preset workflow corresponds to an evaluation logic, and each preset workflow contains at least one evaluation node. Each evaluation node is used to indicate the execution of at least one evaluation step, and multiple evaluation nodes have an execution order relationship. An evaluation workflow can also be understood as an evaluation script used to evaluate a specified type of object. In practical applications, the evaluation workflow can be flexibly configured according to the type of evaluation object and the evaluation scenario. In some cases, the first evaluation task presented on the first interface is represented in the form of task information. The task information includes object information of the first evaluation object and workflow identification information of the first evaluation workflow. The workflow identification information can be represented by, for example, the script name or evaluation logic name corresponding to the workflow, to facilitate user understanding. In addition, this paper does not restrict the form of the evaluation results. In some cases, the evaluation results can be used to measure the evaluation performance of the first evaluation subject. The evaluation results can be represented in the form of result scores or result types.

[0026] Step 204: In response to the first trigger operation on the second assessment workflow, the workflow information of the second assessment workflow and the second assessment result corresponding to the second assessment workflow are displayed in a visual form; wherein, the second assessment workflow is any one of at least one first assessment workflow.

[0027] Users can trigger a second assessment workflow they want to learn more about from at least one first assessment workflow indicated by the first assessment task, as needed. This article does not restrict the first triggering operation, including but not limited to the tap operation. The first assessment workflow triggered by the first triggering operation is the second assessment workflow. The second assessment result is the assessment result corresponding to the second assessment workflow. The first assessment result includes the assessment results corresponding to all first assessment workflows. Therefore, it can also be regarded that the second assessment result is a part of the first assessment result.

[0028] Traditional methods mostly provide users with assessment results directly, but the assessment process is often opaque or only described in text. To help users clearly and efficiently understand the assessment process, this paper proposes a visual approach to display workflow information that users are interested in. This paper does not restrict the display location of the workflow information. In some cases, the workflow information of the second assessment workflow, as well as the corresponding second assessment result, can be displayed visually on the first interface. For example, in response to a first trigger operation on the second assessment workflow, a canvas is displayed on the first interface. The workflow information of the second assessment workflow is displayed visually on the canvas, and the second assessment result corresponding to the second assessment workflow replaces the first assessment result of the first assessment task. This is just an example; in practical applications, the workflow information and second assessment result of the second assessment workflow can also be displayed through pop-ups or through an interface different from the first interface, without limitation. Furthermore, this article does not limit the form of visualization. For example, the form of visualization includes directed graphs. For instance, the nodes of the evaluation workflow can be used to intuitively present the various evaluation nodes through the nodes of the directed graph, and the data flow can be clearly presented through the lines of the directed graph, reducing the cognitive burden on users and improving the efficiency of users obtaining information.

[0029] The above method presents the assessment tasks and corresponding assessment results on the interface, allowing users to clearly understand the assessment workflow and assessment objects used in the assessment tasks. Furthermore, users can trigger any assessment workflow used by the assessment task as needed. The workflow information of the triggered workflow is then displayed to the user in a visual format, along with the corresponding assessment results. This facilitates users' intuitive and efficient understanding of the relevant information about the assessment workflow used in the assessment task. Compared to methods that only present the final assessment results of the assessment task on the interface, the method provided in this paper can meet users' needs for efficiently and clearly obtaining assessment-related information, effectively improving the user experience.

[0030] In some cases, the first evaluation object includes a generative model, and the first evaluation workflow is any of several preset workflows. These preset workflows are based on preset model attack paths. That is, in this paper, corresponding workflows can be set based on multiple model attack paths. The model attack path indicates the sequential attack steps taken against the generative model. Considering that in some scenarios, attackers may take a series of progressive and coordinated attack steps against the generative model to achieve specific goals, in order to improve the security and reliability of the generative model, this paper will directly set up workflows based on model attack paths to simulate attacks on the generative model. This allows for the assessment of the current risks of the generative model based on the evaluation results, enabling timely identification and optimization of problems based on the evaluation results.

[0031] In some cases, the first assessment result includes at least one of the following: the first risk measurement result corresponding to each first assessment workflow, the second risk measurement result corresponding to each first assessment workflow, and the third risk measurement result corresponding to all first assessment workflows.

[0032] Among them, the first risk measurement result is used to measure the assessment performance of the first assessment object under each first risk category. This assessment performance can be measured by the result score or by the result type. In practical applications, multiple result types can be set in different levels according to the performance, such as the type that has been compromised, the type that has risks, and the type that has not been compromised.

[0033] The aforementioned first risk category is determined based on the model attack path of the first evaluation workflow. Specifically, the first risk category of the first evaluation workflow can be selected from multiple preset risk categories based on its corresponding model attack path. It is understandable that simulated attack paths typically exploit vulnerabilities to attack generative models; their essence can be viewed as vulnerability exploitation chains. Each model attack path corresponds to one or more risk categories. The method of dividing risk categories and the granularity of the categories can be flexibly set according to needs. For example, they can be divided into broad categories such as content security risk, model security risk, unauthorized access risk, and decision-making risk. For a particular category, it can be further refined. For example, content security risk can be further divided into information leakage risk and data pollution risk, and model security risk can be further divided into model backdoor implantation risk and weight leakage risk. It should be noted that the above is only a simple, exemplary method of division and should not be considered a limitation. In practical applications, risk categories can be flexibly set and divided.

[0034] Each first assessment workflow corresponds to one or more first risk categories. The first risk categories corresponding to different first assessment workflows may be partially the same or all different. For each first assessment workflow, its corresponding first risk measurement result is used to indicate the assessment performance of the first assessment object under each corresponding first risk category. The assessment performance can be represented by result score, result type, etc. Assuming that the first assessment workflow involves risks 1 to 4, taking the assessment performance represented by result type as an example, the first risk measurement result can be used to indicate: the assessment performance of the first assessment object in risks 1 and 2 is the "already compromised" type, the assessment performance of the first assessment object in risk 3 is the "risk present" type, and the assessment performance of the first assessment object in risk 4 is the "not compromised" type.

[0035] The second risk measurement result is generated based on the first risk measurement results corresponding to each of the first risk categories. For each first assessment workflow, if there are multiple corresponding first risk categories, the second risk measurement result corresponding to the first assessment workflow can be generated by comprehensively considering the assessment performance of the first assessment object under each of the multiple first risk categories corresponding to the first assessment workflow. For example, the assessment performance and reference information of the first assessment object under each of the multiple first risk categories corresponding to the first assessment workflow can be obtained. The reference information includes severity and / or confidence. Then, the weight corresponding to the assessment performance of each first risk category can be obtained. This weight can be determined based on the reference information and / or preset values, etc. Then, the weighted processing is performed based on the assessment performance and weight of the first assessment object under each of the multiple first risk categories corresponding to the first assessment workflow to obtain the second risk measurement result of the first assessment object in the first assessment workflow.

[0036] The third risk measurement result is generated based on at least one of the following: the first risk measurement result corresponding to each of the first assessment workflows, and the second risk measurement result corresponding to each of the first assessment workflows. In some examples, the third risk measurement result can be obtained by statistically analyzing the first risk measurement results corresponding to each of the first assessment workflows. In some specific examples, the third risk measurement result can be obtained by statistically analyzing the same assessment performance in all the first risk measurement results, so that users can intuitively understand the overall performance of the first assessment object. For example, assuming that the first assessment object is assessed using the first assessment workflow 1 and the first assessment workflow 2, the first risk measurement result corresponding to the first assessment workflow 1 indicates that the first assessment object has 5 risk categories corresponding to the assessment performance as a compromised type, 2 risk categories corresponding to the assessment performance as a non-compromised type, and 7 risk categories corresponding to the assessment performance as a risky type under the first assessment workflow 1. The first risk measurement result corresponding to the first assessment workflow 2 indicates that the first assessment object has 3 risk categories corresponding to the assessment performance as a compromised type, 3 risk categories corresponding to the assessment performance as a non-compromised type, and 5 risk categories corresponding to the assessment performance as a risky type under the first assessment workflow 1. Then, the third risk measurement result can be used to indicate that the first assessment object has 8 risk categories corresponding to the assessment performance as a compromised type, 5 risk categories corresponding to the assessment performance as a non-compromised type, and 12 risk categories corresponding to the assessment performance as a risky type. In other examples, a third risk measurement result can be obtained based on the second risk measurement results corresponding to each of the first assessment workflows. For instance, the weights corresponding to the first assessment workflows can be obtained, and the second risk measurement results corresponding to each of the first assessment workflows can be weighted to obtain the third risk measurement result. Alternatively, the second risk measurement results corresponding to each of the first assessment workflows can be statistically analyzed. For example, the second risk measurement results can be represented by result scores or result types. Taking the result types as "collapsed," "risky," and "not collapsed" as an example, the third risk measurement result can be used to indicate the total number of first assessment workflows corresponding to each result type. Furthermore, the third risk measurement result can also simultaneously include results generated based on the first risk measurement results corresponding to each of the first assessment workflows, as well as results generated based on the second risk measurement results corresponding to each of the first assessment workflows. The specific settings can be flexibly configured and are not limited here.

[0037] The first interface can be more than just displaying the assessment object, assessment workflow, and corresponding assessment results for the first assessment task. In some cases, it can also display a report generation control, which generates an assessment report for the first assessment task when triggered. In other cases, the first interface can also display a list of results for each first assessment workflow, including assessment results, confidence level, severity, generation time, and handling recommendations for each risk category, allowing users to gain a clearer and more detailed understanding of the assessment status of the first assessment object. In some cases, the first interface can also display data filtering controls and / or data download controls. The data filtering controls are used to filter data in the result list based on user-input filtering conditions, and the data download controls are used to download all data in the result list or the data selected by the user. Through these methods, users can not only clearly obtain assessment-related information from the first interface but also filter or download the required data as needed, effectively improving the user experience.

[0038] For ease of understanding, see [link to relevant documentation]. Figure 3 The diagram shown illustrates an interaction process based on interface 300, which can be the first interface. Figure 3 As shown, interface 300 clearly displays assessment task information, specifically comprising three areas: area 310 represents the comprehensive assessment result corresponding to assessment task 1; area 320 represents the result list of assessment task 1; and area 330 represents all assessment logic used in assessment task 1. For ease of understanding, [the following text is missing from the original] Figure 3 The evaluation logic is used to represent the aforementioned evaluation workflow, and the evaluation workflow is identified by the evaluation logic name. Specifically, area 310 shows the summary information of all evaluation results, including the third risk measurement result 311, which can be obtained by statistics based on all the first risk measurement results 323. In addition, it also shows the statistical values ​​of various preset severity levels, which can be regarded as part of the evaluation results or as reference information for the evaluation results.

[0039] Area 320 illustrates the results list, which contains assessment-related information for the evaluated object under each risk category corresponding to the assessment logic. This includes the first risk measurement result 323, as well as reference information such as severity and confidence level. In some examples, the result type is related to severity and can be determined based on the severity level. Furthermore, the result categories also include the generation time and treatment recommendations, allowing users to clearly understand the detailed assessment information of the evaluated object. Area 320 also illustrates data filtering controls 321 and data download controls 322. Users can quickly select the assessment information of interest using data filtering controls 321, such as by entering the risk name or setting filter conditions in advanced options. Users can also download data from the results list using data download controls 322 for subsequent analysis and processing.

[0040] In area 330, all the assessment logics used in assessment task 1 are clearly shown, and the second risk measurement result 331 corresponding to each assessment logic is shown. For example, the second risk measurement result 331 corresponding to each assessment logic is obtained based on the first risk measurement result 323 under each risk corresponding to that assessment logic. In addition, area 330 further shows the tool control 332 corresponding to each of the assessment logics used in assessment task 1. For example, in response to the trigger operation of the tool control corresponding to a certain assessment logic, the tool or service used by that assessment logic is further displayed.

[0041] In addition, a report generation control 301 can be set on the first interface. In response to the triggering of the report generation control, an assessment report corresponding to assessment task 1 is generated. The assessment report can include all the data presented on the first interface, as well as the analysis results based on the data presented on the first interface, etc. There are no restrictions here.

[0042] In response to the triggering operation of evaluation logic 1, the interface switches to displaying relevant information about evaluation logic 1. Specifically, area 340 presents the workflow information of evaluation logic 1 in the form of a directed graph on the canvas, allowing users to intuitively understand the specific details of the workflow. Additionally, the results list also changes accordingly, switching from the results list corresponding to all evaluation logics to the results list 350 corresponding to evaluation logic 1. Furthermore, it can display additional key information 333 of evaluation logic 1, including but not limited to information such as consumed computing resources, enabling users to accurately determine the specific evaluation steps, risk details, and consumed computing resources corresponding to a single evaluation logic.

[0043] In some cases, the first assessment result includes at least one of the following: the first risk measurement result corresponding to each first assessment workflow, the second risk measurement result corresponding to each first assessment workflow, and the third risk measurement result common to all first assessment workflows; for details, please refer to the aforementioned relevant content, which will not be repeated here. Based on this, the interface interaction method provided in this paper also includes: in response to the fifth trigger operation on the second risk category, displaying detailed assessment performance information of the first assessment object under the second risk category; wherein, the second risk category is any first risk category, and the assessment details information includes at least one of the following: the first risk measurement result, risk optimization suggestions, and risk association information; the risk association information includes risk behavior information corresponding to the first assessment object, which is related to the second risk category and can be used to achieve evidence tracing.

[0044] The fifth triggering operation mentioned above can be a touch operation, etc. It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another, and should not be considered as specifying a sequence. Users can trigger any risk category in the results list according to their needs. The first risk category of the triggered point becomes the second risk category. At this time, the assessment details of the first assessment object under the second risk category can be further displayed, such as... Figure 4 This is a schematic diagram of an interface, illustrating interface 400. Interface 400 can be the same as interface 300, the difference being that it overlays an area 410 for displaying assessment details. Area 410 can be implemented through additional pages or information panels. Area 410 illustrates the basic information 411 corresponding to the risk, including but not limited to the risk name, the first risk measurement result of the assessment object under this risk, severity, confidence level, logical name, and generation time. Area 410 also illustrates risk optimization suggestions 412 and risk association information 413. For example, risk optimization suggestions may include operational suggestions for relevant personnel, model improvement suggestions, etc., to reduce the probability of the model subsequently encountering such risks or to reduce the adverse effects of such risks. Risk association information can be the dialogue content between the assessment object and the user, which can accurately recreate the object's behavior when the assessment object encounters this risk.

[0045] The above methods allow users to clearly understand the detailed information of the assessed object under any risk category, as well as optimization suggestions and information on the object's behavior related to that risk category. Compared to simply providing users with assessment results, this method better meets users' needs for detailed information and improves the user experience.

[0046] In some cases, step 204 above, which uses visualization to display the workflow information of the second evaluation workflow, includes: displaying the evaluation nodes included in the second evaluation workflow and the execution order of the evaluation nodes through a directed graph, where the evaluation nodes correspond to the graph nodes in the directed graph. For easier understanding, please also refer to... Figure 3 Example of a directed graph within region 340. In some cases, graph nodes present at least one of the following information: the node identifier of the evaluation node, the evaluation purpose of the evaluation node, the execution steps of the evaluation node, and the service configuration information used by the evaluation node. For example, the evaluation purpose can be used to indicate the considerations corresponding to the evaluation node, such as whether the evaluation model has a certain risk. An evaluation node may need to execute one or more evaluation steps, so the execution step information can also be presented to the user through the node. When executing the evaluation steps corresponding to the evaluation node, one or more basic service configurations may be involved, such as email service, web service, etc. The service configuration information can include the service identifier corresponding to the evaluation node, service function description, service configuration parameters, etc., so that the user can clearly understand the service used by the evaluation node. In the above method, the relevant information of the evaluation node can be clearly presented through the graph nodes of the directed graph, and the execution order between the evaluation nodes can be clearly presented through the connections of the directed graph. This visualization presentation method has strong intuitiveness and helps to improve the efficiency of users' information acquisition. In some cases, step 202 above, i.e., the step of displaying the first interface, includes: displaying a second interface; the second interface presents a list of assessment tasks, which includes at least one established assessment task and task information for the established assessment task; in response to a second trigger operation on the first assessment task, the first interface is displayed; the first assessment task is any one of the established assessment tasks, and the second trigger operation includes, but is not limited to, a touch operation. In the above method, the assessment task list presented on the second interface can be used for global risk management. It can clearly present all established assessment tasks and their corresponding task information, making it convenient for users to understand the existing assessment tasks from a global perspective. In addition, users can further select the assessment tasks they are interested in, thereby jumping to the first interface to display the details of the assessment task.

[0047] For example, the task information of an established assessment task includes: the assessment workflow identifier corresponding to the established assessment task, the assessment object identifier, the current execution status, and the third assessment result. The third assessment result contains at least one measurement result, and different measurement results correspond to different display methods. A measurement result can also contain multiple sub-results, such as statistical values ​​corresponding to multiple result types. Different types of sub-results contained in the same measurement result also correspond to different display methods, so that users can efficiently distinguish assessment results with different meanings through the display method. In some cases, the third assessment result is the assessment result corresponding to the established assessment task, and its form is consistent with the first assessment result; in other cases, the third assessment result is only a part of the results in the first assessment result. For example, see Figure 5 The diagram illustrates an interface 500, which can be the first interface. It presents an assessment task list 510 and a task filtering control 520. The assessment task list 510 includes the task name, assessment object identifier, assessment logic, task status, assessment result, creation time, and supported operations for each established assessment task. The assessment workflow identifier is represented by the assessment logic in the list. The current execution status of the established assessment tasks is represented by the task status in the list, including but not limited to processing, exception, unprocessed, paused, terminated, and completed. The assessment results in the list are represented using the aforementioned third risk measurement result. For example, it presents the statistical values ​​511 corresponding to the three result types for the assessment object under the assessment task. Each of the three result types can be considered a sub-result under the third risk measurement result, and different result types are distinguished by color, facilitating users to quickly identify high-priority risks.

[0048] In some cases, the interface interaction method provided in this paper also includes: responding to a task information update message for an established assessment task, and updating the task information of the established assessment task based on the task information update message. Through the above method, real-time updates of the task list can be achieved, such as real-time updates of the task status and assessment results of each established assessment task, ensuring that the second interface used to display the assessment task list can accurately present the task information of each established assessment task in real time.

[0049] To enhance the convenience of task creation for users, the interface interaction method provided in this paper, in some cases, further includes: responding to a third trigger operation on the task creation control, obtaining the second assessment workflow and the second assessment object corresponding to the task to be created; wherein, the task creation control is a control set in either the second or third interface, with the third interface differing from the second interface; creating the task to be assessed based on the second assessment workflow and the second assessment object; and adding the task to be assessed to the assessment task list. In practical applications, task creation controls can be set in both the second and third interfaces, providing users with at least two paths to create tasks, allowing them to quickly trigger task creation regardless of which interface they are currently viewing.

[0050] Such as, Figure 5 As shown, a task creation control 501 is also provided on the second interface, which displays the task list. This allows users to quickly trigger the control and create new tasks based on their understanding of currently created task information; similarly, see... Figure 6 The diagram illustrates an interface, specifically interface 600. Interface 600 can be the third interface mentioned above, which is a details interface for a specific assessment workflow. This third interface also includes a task creation control 601. Users can directly trigger the task creation control 601 to create assessment tasks based on the details of a specific assessment workflow. The difference between creating tasks through the second or third interface lies in the following: Creating tasks through the second or third interface... Figure 5 The second interface shown illustrates task creation. Users need to explicitly input the assessment target and assessment workflow corresponding to the task to be created. This can be achieved through methods such as... Figure 6 The third interface shown allows users to create tasks by simply entering the assessment object corresponding to the task to be created. The assessment workflow corresponding to the task to be created will default to the assessment workflow shown on the third interface, which means the assessment logic shown on the third interface will be used by default.

[0051] In some cases, the interface interaction method provided in this paper further includes: displaying a third interface in response to a fourth trigger operation on the third assessment workflow; wherein the third assessment workflow is any workflow among multiple preset assessment workflows; on the third interface, the workflow information of the third assessment workflow and the task information of associated assessment tasks are presented in a visual form, and the associated assessment tasks are assessment tasks that adopt the third assessment workflow. In practical applications, the fourth interface can display a list of assessment workflows (also known as a list of assessment logics), which includes multiple preset assessment workflows, that is, multiple assessment logics. Users can execute a fourth trigger operation on any one of the multiple preset assessment workflows. The fourth trigger operation includes, but is not limited to, touch operations, etc. The preset assessment workflow that is triggered is referred to here as the third assessment workflow. The third interface is then displayed, and the workflow information of the assessment workflow is displayed in a visual form through the third interface. The visualization method includes, but is not limited to, a directed graph method. For example, the visualization display method of the workflow information of the third assessment workflow can be consistent with the visualization display method of the workflow information of the second assessment workflow mentioned above.

[0052] For better understanding, please continue to refer to [link / reference]. Figure 6 Interface 600 is used to present detailed information about assessment logic 1, which is the triggered third assessment workflow. Interface 600 displays areas 610, 620, and 630. Area 610, triggered by the service details control 602, displays the service configuration information used by assessment logic 1. Examples may include a service introduction, the service's current configuration status (configured or unconfigured), configuration information settings controls, and required / optional field prompts. Specifically, each assessment logic can correspond to multiple services, some of which require configuration by relevant assessment personnel. Furthermore, area 610 can be collapsed by triggering the service details control 602, no longer displaying the basic services on interface 600; this can be configured by the user as needed. Area 620 is used to display the assessment nodes and corresponding node information of assessment logic 1 in a directed graph format. Area 630 can be used to display the task information of the associated assessment tasks corresponding to assessment logic 1, allowing users to view the specific details of the associated assessment tasks. For example, if a related assessment task in region 630 is triggered, it can also redirect to display something like... Figure 3 The interface shown displays detailed information about the associated assessment task.

[0053] In summary, the interface interaction methods presented in this paper can fully meet users' needs for efficiently and clearly obtaining evaluation-related information from multiple aspects, including interface content display and interface interaction. This can effectively improve user experience and can be well applied to various evaluation scenarios such as model safety evaluation.

[0054] Corresponding to the aforementioned interface interaction method, this paper further provides an interface interaction device. Figure 7 This is a schematic diagram of a user interface interaction device provided in this paper. This device can be implemented by software and / or hardware, and is generally integrated into electronic devices, such as... Figure 7 As shown, the interface interaction device includes: The interface display module 702 is used to display the first interface; wherein, the first interface presents the first assessment task and the first assessment result corresponding to the first assessment task, and the first assessment task is used to indicate: to use at least one first assessment workflow to assess the first assessment object; The information display module 704 is used to respond to the first trigger operation of the second evaluation workflow, and to display the workflow information of the second evaluation workflow and the second evaluation result corresponding to the second evaluation workflow in a visual form; wherein, the second evaluation workflow is any one of at least one first evaluation workflow.

[0055] The aforementioned device can present the assessment task and corresponding assessment results on the interface, so that users can clearly understand the assessment workflow and assessment object used in the assessment task. Moreover, users can trigger any assessment workflow used in the assessment task as needed. The workflow information of the triggered workflow is displayed to the user in a visual form, and the assessment results corresponding to the triggered workflow are also displayed to the user. This makes it easy for users to intuitively and efficiently understand the relevant information of the assessment workflow used in the assessment task. Compared with devices that only present the final assessment results of the assessment task on the interface, the aforementioned device provided in this paper can meet the user's need to obtain assessment-related information efficiently and clearly, and can effectively improve the user experience.

[0056] In some cases, the interface display module 702 is specifically used to: display a second interface; the second interface presents a list of assessment tasks, the list of assessment tasks includes at least one established assessment task and task information of the established assessment task; in response to a second trigger operation on the first assessment task, display a first interface; the first assessment task is any one of the established assessment tasks.

[0057] In some cases, the device further includes a task creation module, used to obtain a second evaluation workflow and a second evaluation object corresponding to the task to be created in response to a third trigger operation on the task creation control; wherein the task creation control is a control set by the second interface or the third interface, and the third interface is different from the second interface; based on the second evaluation workflow and the second evaluation object, a task to be evaluated is created; and the task to be evaluated is added to the evaluation task list.

[0058] In some cases, the device further includes a workflow display module for displaying the third interface in response to a fourth trigger operation on the third assessment workflow; wherein the third assessment workflow is any workflow among a plurality of preset assessment workflows; on the third interface, the workflow information of the third assessment workflow and the task information of associated assessment tasks are presented in a visual form, wherein the associated assessment tasks are assessment tasks that adopt the third assessment workflow.

[0059] In some cases, the device further includes a task update module, which updates the task information of the established evaluation task based on the task information update message received from the established evaluation task.

[0060] In some cases, the task information of the established assessment task includes: the assessment workflow identifier, assessment object identifier, current execution status, and third assessment result corresponding to the established assessment task. The third assessment result includes at least one measurement result, and different measurement results correspond to different display methods.

[0061] In some cases, the information display module 704 is specifically used to: display the evaluation nodes included in the second evaluation workflow and the execution order corresponding to the evaluation nodes through a directed graph, wherein the evaluation nodes have a corresponding relationship with the graph nodes in the directed graph.

[0062] In some cases, the graph node presents at least one of the following information: the node identifier of the evaluation node, the evaluation purpose of the evaluation node, the execution step information of the evaluation node, and the service configuration information used by the evaluation node.

[0063] In some cases, the first evaluation object includes a generative model, and the first evaluation workflow is any one of a plurality of preset workflows, the preset workflows being set based on preset model attack paths.

[0064] In some cases, the first assessment result includes at least one of the following: a first risk measurement result corresponding to each of the first assessment workflows, a second risk measurement result corresponding to each of the first assessment workflows, and a third risk measurement result commonly corresponding to all the first assessment workflows. The first risk measurement result is used to measure the evaluation performance of the first evaluation object under each first risk category, and the first risk category is determined based on the model attack path of the first evaluation workflow. The second risk measurement result is generated based on the first risk measurement results corresponding to each of the first risk categories; The third risk measurement result is generated based on at least one of the following: the first risk measurement result corresponding to each of the first assessment workflows, and the second risk measurement result corresponding to each of the first assessment workflows.

[0065] In some cases, the device further includes a details display module, used to display assessment details information of the first assessment object under the second risk category in response to a fifth trigger operation on the second risk category; wherein the second risk category is any one of the first risk categories, and the assessment details information includes at least one of the following: a first risk measurement result, risk optimization suggestions, and risk association information; the risk association information includes risk behavior information corresponding to the first assessment object, and the risk behavior information is related to the second risk category.

[0066] The interface interaction device provided herein can execute the interface interaction method provided in any embodiment herein, and has the corresponding functional modules and beneficial effects of the execution method.

[0067] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device embodiments can be referred to the corresponding process in the method embodiments, and will not be repeated here.

[0068] This document provides an electronic device, comprising: a storage device storing a computer program thereon; and a processing device for executing the computer program in the storage device to implement the steps of any of the interface interaction methods described herein. The beneficial effects that can be achieved include, but are not limited to, meeting the user's need to efficiently and clearly obtain assessment-related information and effectively improving the user experience.

[0069] The following is for reference. Figure 8 This diagram illustrates the structure of an electronic device 800 suitable for implementing the present invention. The terminal devices described herein may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital televisions and desktop computers. Figure 8 The electronic device shown is merely an example and should not impose any limitations on the functionality and scope of this article.

[0070] like Figure 8As shown, the electronic device 800 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory 802 or a program loaded from a storage device 808 into a random access memory 803. The random access memory 803 also stores various programs and data required for the operation of the electronic device 800. The processing unit 801, the read-only memory 802, and the random access memory 803 are interconnected via a bus 804. An input / output interface 805 is also connected to the bus 804.

[0071] Typically, the following devices can be connected to the input / output interface 805: input devices 806 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 807 including, for example, a liquid crystal display, speaker, vibrator, etc.; storage devices 808 including, for example, magnetic tape, hard disk, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 800 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0072] In particular, according to embodiments herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments herein include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 809, or installed from storage device 808, or installed from read-only memory 802. When the computer program is executed by processing device 801, it performs the functions defined in the methods herein.

[0073] Furthermore, the embodiments described herein may also be computer-readable storage media storing a computer program that, when executed by a processor, implements any of the interface interaction methods described herein, and the beneficial effects that can be achieved include, but are not limited to: meeting the user's need to efficiently and clearly obtain evaluation-related information, and effectively improving the user experience.

[0074] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0075] In addition to the methods, devices, and media described above, the embodiments herein may also be computer program products, which include computer programs that, when executed by a processor, implement any of the interface interaction methods described herein. The beneficial effects that can be achieved include, but are not limited to, meeting the user's need to efficiently and clearly obtain evaluation-related information and effectively improving the user experience.

[0076] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations described herein. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0077] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those 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 invention. Therefore, the present invention is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A user interface interaction method, comprising: The first interface is displayed; wherein, the first interface presents a first assessment task and a first assessment result corresponding to the first assessment task, and the first assessment task is used to indicate: to use at least one first assessment workflow to assess the first assessment object; In response to a first trigger operation on the second assessment workflow, the workflow information of the second assessment workflow and the second assessment result corresponding to the second assessment workflow are displayed in a visual form; wherein, the second assessment workflow is any one of the at least one first assessment workflow.

2. The method according to claim 1, wherein displaying the first interface includes: The second interface is displayed; the second interface presents a list of assessment tasks, which includes at least one established assessment task and the task information of the established assessment task; In response to a second trigger operation on the first assessment task, a first interface is displayed; the first assessment task is any one of the established assessment tasks.

3. The method according to claim 2, further comprising: In response to a third trigger operation on the task creation control, the second assessment workflow and the second assessment object corresponding to the task to be created are obtained; wherein, the task creation control is a control set by the second interface or the third interface, and the third interface is different from the second interface; Based on the second assessment workflow and the second assessment object, create the assessment task; Add the task to be evaluated to the evaluation task list.

4. The method according to claim 3, further comprising: In response to a fourth trigger operation on the third assessment workflow, the third interface is displayed; wherein, the third assessment workflow is any workflow among a plurality of preset assessment workflows; On the third interface, the workflow information of the third assessment workflow is presented in a visual form, as well as the task information of the associated assessment tasks, which are assessment tasks that adopt the third assessment workflow.

5. The method according to claim 2, further comprising: In response to receiving the task information update message for the established assessment task, the task information of the established assessment task is updated based on the task information update message.

6. The method according to claim 5, wherein the task information of the established assessment task includes: The established assessment task includes the assessment workflow identifier, assessment object identifier, current execution status, and third assessment result. The third assessment result includes at least one measurement result, and different measurement results correspond to different display methods.

7. The method according to claim 1, wherein displaying the workflow information of the second evaluation workflow in a visual format includes: The second evaluation workflow is illustrated by a directed graph, which shows the evaluation nodes and their corresponding execution order. The evaluation nodes correspond to the graph nodes in the directed graph.

8. The method according to claim 7, wherein the graph node presents at least one of the following information: the node identifier of the evaluation node, the evaluation purpose of the evaluation node, the execution step information of the evaluation node, and the service configuration information adopted by the evaluation node.

9. The method according to any one of claims 1 to 8, wherein the first evaluation object includes a generative model, the first evaluation workflow is any workflow among a plurality of preset workflows, and the preset workflow is set based on a preset model attack path.

10. The method according to claim 9, wherein the first evaluation result includes at least one of the following: a first risk measurement result corresponding to each of the first evaluation workflows, a second risk measurement result corresponding to each of the first evaluation workflows, and a third risk measurement result commonly corresponding to all the first evaluation workflows; The first risk measurement result is used to measure the evaluation performance of the first evaluation object under each first risk category, and the first risk category is determined based on the model attack path of the first evaluation workflow. The second risk measurement result is generated based on the first risk measurement results corresponding to each of the first risk categories; The third risk measurement result is generated based on at least one of the following: the first risk measurement result corresponding to each of the first assessment workflows, and the second risk measurement result corresponding to each of the first assessment workflows.

11. The method according to claim 10, further comprising: In response to the fifth trigger operation for the second risk category, display the assessment details of the first assessment object under the second risk category; Wherein, the second risk category is any one of the first risk categories, and the assessment details information includes at least one of the following: first risk measurement result, risk optimization suggestions, and risk association information; the risk association information includes risk behavior information corresponding to the first assessment object, and the risk behavior information is related to the second risk category.

12. A user interface interaction device, comprising: The interface display module is used to display a first interface; wherein, the first interface presents a first assessment task and a first assessment result corresponding to the first assessment task, and the first assessment task is used to indicate: to use at least one first assessment workflow to assess the first assessment object; The information display module is used to respond to the first trigger operation of the second assessment workflow, and to display the workflow information of the second assessment workflow and the second assessment result corresponding to the second assessment workflow in a visual form; wherein, the second assessment workflow is any one of the at least one first assessment workflow.

13. An electronic device, the electronic device comprising: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the interface interaction method according to any one of claims 1-11.

14. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the interface interaction method of any one of claims 1-11.

15. A computer program product comprising a computer program that, when executed by a processor, implements the interface interaction method of any one of claims 1-11.

Images