A task difficulty measurement method and system in a multitask environment

Abstract

The present application relates to a kind of task difficulty measurement method and system under multi-task environment, first, the complex task under multi-task environment is decomposed, obtain multiple subtasks.Then, according to subtask difficulty quantification model, the task difficulty value of each subtask is calculated;According to the three-dimensional attribute of subtask, the correlation coefficient between any two subtasks is determined;According to the task processing curve of subtask in the set time, determine the concurrent task in complex task and concurrent duration;According to the task difficulty of the subtask included in concurrent task, the correlation coefficient between the subtask included in concurrent task and the concurrent duration of concurrent task, determine the difficulty increment of concurrent task.Finally, according to the task difficulty value of each subtask and the difficulty increment of each concurrent task, determine the difficulty of complex task.The present application is suitable for the difficulty quantification of various complex tasks, fills the deficiency in the field of human-computer interaction in the quantitative aspect of task factor.

Description

Technical Field

[0001] This invention relates to the field of human-computer interaction safety, and in particular to a method and system for measuring task difficulty in a multi-task environment. Background Technology

[0002] With the rapid development of technology and the increasing complexity of operating systems, operators face significantly greater cognitive pressure. In fields such as heavy industry, mine safety, and air traffic control, operators are required to handle multiple different types of tasks simultaneously, thus significantly increasing the difficulty of these tasks. In multi-tasking environments, measuring the difficulty (task complexity) of operator participation in tasks can help optimize operator tasks and select multi-task coordination strategies in engineering practice. Therefore, quantifying the task complexity or difficulty of complex tasks involving multiple tasks is of great significance. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for measuring task difficulty in a multi-tasking environment with a wide range of applications.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for measuring task difficulty in a multi-tasking environment includes the following steps:

[0006] Step 1: Decompose the complex task in the multi-task environment to obtain multiple meta-tasks; the meta-task is the smallest task unit of the complex task.

[0007] Step 2: Calculate the task difficulty value for each of the meta-tasks based on the meta-task difficulty quantification model;

[0008] Step 3: Determine the correlation coefficient between any two meta-tasks based on the three-dimensional attributes of the meta-tasks; the three-dimensional attributes are the response attributes, resource attributes, and information interaction attributes of the meta-tasks; the correlation coefficient is calculated based on the number of cell overlaps of the three-dimensional attributes of any two meta-tasks within the three-dimensional attribute model of the meta-tasks; the three-dimensional attribute model of the meta-tasks uses the three-dimensional attributes as the three dimensions of space, dividing the cube into eight cells;

[0009] Step 4: Based on the task processing curve of the meta-task within a set time period, determine the concurrent tasks and concurrent durations in the complex task; the task processing curve is a curve showing the execution status of the meta-task changing over time; the concurrent task consists of multiple meta-tasks that need to be executed simultaneously within the same time period, and the concurrent duration is the duration of the concurrent task.

[0010] Step 5: for each of the concurrent tasks, determining a difficulty increment value of the concurrent task according to the task difficulty values of the sub-tasks included in the concurrent task, the correlation coefficients between the sub-tasks included in the concurrent task, and the concurrent duration of the concurrent task;

[0011] Step 6: determining the difficulty of the complex task according to the task difficulty values of each of the sub-tasks and the difficulty increment values of each of the concurrent tasks.

[0012] Optionally, before Step 2, the method further comprises: according to the response mode of the sub-tasks, classifying the sub-tasks into continuous sub-tasks and discrete sub-tasks.

[0013] Optionally, the sub-task difficulty quantification model comprises a continuous sub-task calculation module and a discrete sub-task calculation module.

[0014] The continuous sub-task calculation module is configured to calculate the task difficulty value of the continuous sub-task.

[0015] The discrete sub-task calculation module is configured to calculate the task difficulty value of the discrete sub-task.

[0016] Optionally, the calculation formula of the sub-task difficulty quantification model is as follows:

[0017]

[0018] wherein, Id(i) is the task difficulty value of the sub-task, A(i) is the action intensity of the continuous sub-task; W s (i) is the action intensity noise of the continuous sub-task; μ is a correction factor; ΔT i is the duration to be responded by the discrete sub-task; j(i) is the stimulus quantity of the discrete sub-task; for continuous task is the continuous sub-task; forDiscrete task is the discrete sub-task.

[0019] Optionally, the task processing curve comprises the process of the sub-task from generation to response one or more times.

[0020] Optionally, the response attribute, resource attribute, and information interaction attribute of the sub-task are as follows:

[0021] The response attribute comprises timely response and continuous response.

[0022] The resource attribute comprises visual resource and auditory resource.

[0023] The information interaction attribute comprises input information and output information.

[0024] Optionally, Step 5 specifically comprises:

[0025] According to Calculate the difficulty increment of concurrent tasks ΔId(Task, i, j), wherein, is the task difficulty value of the normalized meta task i, is the task difficulty value of the normalized meta task j, c ij is the correlation coefficient between the meta task i and the meta task j, t ijk is the concurrent duration of the kth concurrency of the meta task i and the meta task j within Δt, and Δt is a set time length.

[0026] Optionally, the step 6 specifically includes:

[0027] According to Calculate the difficulty of the complex task Id(Task), wherein, is the task difficulty value of the normalized ith meta task, and ΔId(Task, i, j) is the difficulty increment of concurrent tasks.

[0028] Optionally, the meta task includes a monitoring task, a tracking task, a communication task, and a resource management task.

[0029] The application further provides a task difficulty measurement system in a multitasking environment, comprising:

[0030] A target task acquisition module is configured to acquire a target task, wherein the target task is a complex task in a multitasking environment.

[0031] A task disassembling module is configured to disassemble the complex task in the multitasking environment to obtain a plurality of meta tasks, wherein the meta task is the smallest task unit of the complex task.

[0032] A meta task difficulty calculation module is configured to calculate the task difficulty value of each meta task according to a meta task difficulty quantification model.

[0033] A correlation coefficient calculation module is configured to determine the correlation coefficient between any two meta tasks according to the three-dimensional attributes of the meta tasks, wherein the three-dimensional attributes are the response attribute, the resource attribute, and the information interaction attribute of the meta task, the correlation coefficient is calculated according to the unit overlap number of the three-dimensional attributes of the any two meta tasks in a meta task three-dimensional attribute model, and the meta task three-dimensional attribute model divides a cube into eight units with the three-dimensional attributes as the three dimensions of space.

[0034] The concurrent task acquisition module is configured to determine concurrent tasks in the complex task and a concurrent duration according to a task processing curve of the meta task within a set time; the task processing curve is a curve of the execution of the meta task over time; the concurrent task is composed of a plurality of meta tasks that need to be executed simultaneously within the same time period, and the concurrent duration is a duration of the concurrent task;

[0035] The task difficulty increment module is configured to determine a difficulty increment of each concurrent task according to a task difficulty of the meta task included in the concurrent task, a correlation coefficient between the meta tasks included in the concurrent task, and the concurrent duration of the concurrent task.

[0036] The task difficulty calculation module is configured to determine the difficulty of the complex task according to the task difficulty value of each meta task and the difficulty increment of each concurrent task.

[0037] According to the embodiments of the present application, the following technical effects are achieved: the task difficulty measurement method and system in a multi-task environment provided by the present application first decomposes a complex task in a multi-task environment into a plurality of meta tasks; then, a task difficulty value of each meta task is calculated according to a meta task difficulty quantization model; a correlation coefficient between any two meta tasks is determined according to three-dimensional attributes of the meta tasks; then, concurrent tasks in the complex task and a concurrent duration are determined according to a task processing curve of the meta task within a set time; for each concurrent task, a difficulty increment of the concurrent task is determined according to a task difficulty of the meta task included in the concurrent task, a correlation coefficient between the meta tasks included in the concurrent task, and the concurrent duration of the concurrent task; finally, the difficulty of the complex task is determined according to the task difficulty value of each meta task and the difficulty increment of each concurrent task. The present application decomposes a complex task into the smallest task unit, quantizes the difficulty of the smallest task unit, and measures the difficulty increment between the smallest task units, and calculates the task difficulty of the complex task through the task difficulty value of the meta task and the difficulty increment of the concurrent task. The present application is suitable for difficulty quantization of various complex tasks, and fills the gap in the field of human-computer interaction in terms of task factor quantization. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0039] Figure 1 The present application provides a task difficulty measurement method in a multi-task environment.

[0040] Figure 2 A three-dimensional attribute model of a meta task in a human-computer interaction process is provided in the present application.

[0041] Figure 3 A task profile schematic diagram is provided in the present application.

[0042] Figure 4 Detailed schematic diagrams of two complex tasks in an embodiment provided in the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present application.

[0044] As the operating system is becoming more and more complex, the cognitive pressure of an operator is increasing. For example, when the operator is facing a complex task such as a simulated flight, the operator is required to be responsible for multiple types of tasks in the same time period, and the difficulty of the task is significantly increased. To solve this problem, the present application provides a task difficulty measurement method and system in a multi-task environment.

[0045] In order to make the above-mentioned objects, features and advantages of the present application more apparent, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0046] The present application provides a task difficulty measurement method in a multi-task environment, comprising the following steps:

[0047] Step 1: decompose a complex task in a multi-task environment to obtain a plurality of meta tasks; the meta task is the smallest task unit of the complex task.

[0048] Step 2: calculate the task difficulty value of each meta task according to a meta task difficulty quantification model.

[0049] Step 3: determine the correlation coefficient between any two meta tasks according to the three-dimensional attributes of the meta tasks; the three-dimensional attributes are response attributes, resource attributes and information interaction attributes of the meta tasks; the correlation coefficient is calculated according to the number of unit overlaps of the three-dimensional attributes of the any two meta tasks in a meta task three-dimensional attribute model; the meta task three-dimensional attribute model takes three-dimensional attributes as three dimensions of space, and divides a cube into eight units.

[0050] Step 4: determining concurrent tasks in the complex task and concurrent duration according to a task processing curve of the meta task within a set time; the task processing curve is a curve of execution of the meta task changing with time; the concurrent task is composed of multiple meta tasks that need to be executed simultaneously in the same time period, and the concurrent duration is the duration of the concurrent task.

[0051] Step 5: for each concurrent task, determining a difficulty increment of the concurrent task according to a task difficulty of the meta task included in the concurrent task, a correlation coefficient between the meta tasks included in the concurrent task, and the concurrent duration of the concurrent task.

[0052] Step 6: determining the difficulty of the complex task according to the task difficulty value of each meta task and the difficulty increment of each concurrent task.

[0053] In this embodiment, the complex task of flight simulation is taken as an example to decompose the complex task in a multi-task environment to obtain multiple meta tasks; the meta task is the smallest task unit of the complex task, which can be specifically as follows:

[0054] When decomposing the complex task of flight simulation, the complex task is decomposed into the smallest task unit, i.e., the meta task, according to the operation manual, sorting historical operation records, and abstracting each smallest task unit. It should be noted that each meta task obtained by decomposition is required to be as simple and reasonable as possible, and at the same time, the set of meta tasks can simulate the actual complex task, which can be consulted and summarized from relevant books and documents.

[0055] As shown in the following table, Table 1 shows each type of meta task obtained by decomposing the complex task of flight simulation and its description.

[0056] Table 1

[0057]

[0058] Among them, according to the above decomposed meta task, the meta task is divided into continuous meta task and discrete meta task according to the response mode of the meta task. For example: the tracking task needs to continuously track the target moving by the operating rod, so that the target always remains within the specified space range, i.e., the operator needs to continuously respond to the operating rod, i.e., this type of task is called a continuous task; the monitoring task, the communication task and the resource management task are tasks that suddenly appear in the task process, which have the characteristics of uncertainty and discontinuity in task time, i.e., this type of task is called a discrete task.

[0059] In some embodiments, the task difficulty value of each meta task is calculated according to a meta task difficulty quantification model, which can be specifically as follows:

[0060] For most tasks that operators face in human-computer interaction, the information demand value of different sub-tasks determines the difficulty of operators to perceive all the information of the tasks, that is, the information demand value of a sub-task represents the difficulty of the sub-task. For different sub-tasks, there are discrete tasks and continuous tasks, and the information demand value of different sub-tasks needs to be measured according to different methods, and then the difficulty of the sub-tasks is measured, therefore, the difficulty quantification model of sub-tasks includes a continuous sub-task calculation module and a discrete sub-task calculation module.

[0061] For continuous tasks, the difficulty index I d represents the logarithmic relationship between the task action amplitude A and the action tolerance range W s , and is used to measure the average minimum information value required for a specified task action, and the specific formula is as follows:

[0062]

[0063] However, in human-computer interaction, the action amplitude and tolerance range of some tasks are not easy to measure, especially for tasks with discrete response requirements, for example, the monitoring task in Table 1, the response action is completed in a very short time, and the operation amplitude and the allowed tolerance range cannot be accurately measured, and the information demand value of the response action cannot be represented. Therefore, for such tasks, other task characteristics are needed to measure the information demand value.

[0064] That is, for discrete tasks, the second type of difficulty index I reflects the stimulus information entropy of the task in unit response time, Compared with I d , the second type of difficulty index I

[0065]

[0066] where Hs is the information content in the stimulus set, j is the total number of stimuli, and ΔT is the duration of the task response.

[0067] Further, I d and I can be widely applied to task setting and difficulty quantification in human-computer interaction experiments, however, I d and I are not balanced on the same numerical scale.

[0068] To solve this problem, the present application proposes a correction method between different difficulty indexes, assuming that a complex task Task is composed of m continuous tasks and n-m discrete tasks, for two types of meta-tasks, as shown in formula (4) and formula (5), the reciprocal of the task response rate and the correlation coefficient between the task difficulty I d is obtained by a linear regression equation, and the correction factor μ is represented as the ratio of the two coefficients. Wherein, the response rate RR is defined as: the ratio of the number of successful responses to the number of tasks within the task time Δt under the specified response criterion, i represents the meta-task Task i . The correction factor μ reflects the difference between the slope a and a * , as shown in formula (8), in order to ensure the numerical consistency of the information processing ability of the task personnel on the two types of difficulty indexes, for discrete tasks, the second type of task difficulty index is corrected to Wherein, formula (3)-(8) are as follows:

[0069] Task={Task1, Task2, …, Task m , Task m+1 , …, Task n} (m < n) (3)

[0070]

[0071]

[0072]

[0073] RR(i)=I d (i)·a, (i=1, 2, …, m) (7)

[0074]

[0075] Based on the above formula, the calculation formula of the meta-task difficulty quantification model is as follows:

[0076]

[0077] Wherein, Id(i) is the task difficulty value of the meta-task, A(i) is the action intensity of the continuous meta-task; W s (i) is the action intensity noise of the continuous meta-task; μ is the correction factor; ΔT i is the duration of the discrete meta-task to be responded; j(i) is the stimulus quantity of the discrete meta-task; for continuous task is a continuous meta-task; forDiscrete task is a discrete meta-task.

[0078] Specifically, according to the above quantitative method, the task difficulty values of four types of meta-tasks in the complex task of simulated flight are obtained, as shown in Table 2.

[0079] Table 2

[0080]

[0081] In some embodiments, the difficulty of multi-task not only considers the difficulty of meta-task, but also considers the difficulty increment caused by resource competition between meta-tasks. The key to measuring this difficulty increment lies in how to measure the strength of the resource competition relationship between meta-tasks. The present application determines the basic difficulty attributes of complex tasks, thereby establishing a three-dimensional attribute model of meta-tasks, and measuring the strength of the resource competition relationship between meta-tasks through this model, and then measuring the difficulty increment caused by concurrent tasks. The specific steps can be as follows:

[0082] In practical applications, the correlation coefficient between any two meta-tasks is determined according to the three-dimensional attributes of the meta-tasks, wherein the three-dimensional attributes of the meta-tasks include response attributes, resource attributes and information interaction attributes. By taking the three attributes as three groups of basic difficulty attributes of the meta-tasks, the type of any meta-task can be determined, and the resource competition relationship between the meta-tasks can be explored.

[0083] Specifically, according to the different response modes required by the meta-tasks, the response attributes of the meta-tasks are divided into timely response and continuous response. Since the two different response requirements have different interference levels for concurrent tasks, the influence levels of the two different response requirements on the task difficulty are also different.

[0084] Specifically, according to the different resource attributes required by the meta-tasks, the resource attributes of the meta-tasks are divided into visual resources and auditory resources, for example, the monitoring task is visual, and the communication task is auditory.

[0085] Specifically, according to the different information interaction modes between the meta-tasks and the personnel, the information interaction attributes of the meta-tasks are divided into input information and output information, wherein the completion of the task is composed of two parts: the perception of the task environment information by the operator and the information feedback of the task environment. These two parts are defined as the information input process and the information output process of the operator. For specific meta-tasks, the information input and information output parts have primary and secondary roles in a completion cycle of the meta-task. In the embodiments, the meta-task with the information input process as the main part is defined as an input-type task, and the meta-task with the information output process as the main part is defined as an output-type task.

[0086] Based on the above three-dimensional attributes of the meta-tasks, the present application proposes a three-dimensional attribute model of meta-tasks in the human-computer interaction process, as shown in Figure 2As shown, three groups of task basic difficulty attributes are embodied in three dimensions of space, thereby dividing the cube into eight basic cells, and each cell represents a basic attribute unit of a meta task. Through the model, any meta task is divided into one or more cells in the cube according to its difficulty attributes in three dimensions. Meanwhile, in multi-task processing, for any two meta tasks, the greater the number of cell overlaps between the two, the stronger the resource competition relationship between the two, and the greater the value-added to the task difficulty. Therefore, the measurement rule of the strength of the resource competition relationship between meta tasks is determined, and the meta task Task i The correlation coefficient c j of the meta task Task ij is defined as the resource competition strength between the two meta tasks, and the correlation coefficient c ij is positively correlated with the number of cell overlaps p ij between the two meta tasks. If a complex task is composed of n meta tasks, the correlation coefficient matrix A can be obtained from the correlation coefficient between any two meta tasks, as shown in formula (10), and the matrix A represents the resource competition pressure between meta tasks in multi-task processing.

[0087]

[0088] Specifically, for the complex task of simulating flight in the embodiment of the application, the attribute classification of the four types of meta tasks is shown in Table 3, and according to the above rule, the correlation coefficient matrix A between meta tasks is shown in formula (11).

[0089] Table 3

[0090]

[0091]

[0092] Wherein, A represents the correlation coefficient matrix between meta tasks.

[0093] In some embodiments, the difficulty of multi-task depends on the difficulty of meta tasks and the difficulty value-added brought by multi-task processing, and concurrent tasks (i.e., the operator is required to complete two meta tasks at the same time) are a classic multi-task processing scenario and a key factor affecting task difficulty. Measuring the difficulty value-added brought by concurrent tasks is crucial to measuring task difficulty in a multi-task environment. For each concurrent task, according to the task difficulty of the meta tasks included in the concurrent task, the correlation coefficient between the meta tasks included in the concurrent task, and the concurrent duration of the concurrent task, the difficulty value-added of the concurrent task is determined, and the specific steps can be as follows:

[0094] Specifically, in multi-task processing, each start to end of any meta task defines a task event, and all task events of n types of meta tasks in a given time period Δt are integrated on the same task profile, and the task profile is as followsFigure 3 As shown, the meta task Task i is obtained from the task profile j The concurrent duration t ij .

[0095] The difficulty quantification method of the meta task proposed by step S1, wherein the difficulty of the n meta tasks is respectively Id(1), …, Id(n). In order to eliminate the influence of different dimensions of the indicators in the task difficulty calculation formula, the meta task difficulty is normalized to solve the comparability between the task difficulty values, and the process is shown in formula (12).

[0096]

[0097] The resource competition pressure brought by the concurrent tasks increases the overall task difficulty. It is assumed that the task difficulty increment brought by Task i and Task j is ΔId(Task, i, j), which is determined by the meta task difficulty value, the correlation coefficient c ij between the meta tasks, and the concurrent duration t ij of the meta tasks, as shown in formula (13), wherein, is the normalized task difficulty of Task i , c ij is the correlation coefficient between Task i and Task j , and t ijk is the duration of the kth concurrency of Task i and Task j within Δt, and Δt is the length of the given time period.

[0098]

[0099] Specifically, according to the above method, the concurrent task difficulty increment of Task1 and Task2 in the embodiment is obtained by statistical calculation, as shown in Table 4, and the specific composition of the two complex tasks is shown in Table 5. Figure 4

[0100] Table 4

[0101]

[0102]

[0103] In some embodiments, the difficulty of the complex task is determined according to the task difficulty value of each meta task and the difficulty increment of each concurrent task, which can be specifically as follows: ​

[0104] The difficulty Id (Task) of the complex task is calculated according to the difficulty measurement values of various meta-tasks and the difficulty increment values caused by concurrent tasks in the complex task, wherein the difficulty Id (Task) of the complex task is determined by the task difficulty values of all n meta-tasks and the difficulty increment values of all concurrent tasks, as shown in formula (14).

[0105]

[0106] Specifically, according to the statistical calculation of the above formula, the task difficulty of Task1 and Task2 in the embodiment is obtained, as shown in Table 5.

[0107] Table 5

[0108]

[0109] Further, according to the correlation coefficient matrix A between meta-tasks obtained above, formula (15) can be obtained from the matrix A, wherein a ij is a matrix element.

[0110]

[0111] It can be observed that the resource preemption pressure between concurrent tasks caused by the monitoring meta-task is the largest, and the monitoring meta-task is regarded as a safety-critical meta-task.

[0112] The application further provides a task difficulty measurement system in a multi-task environment, comprising:

[0113] A target task acquisition module is configured to acquire a target task, wherein the target task is a complex task in a multi-task environment.

[0114] A task disassembly module is configured to disassemble the complex task in the multi-task environment to obtain a plurality of meta-tasks, wherein the meta-task is the smallest task unit of the complex task.

[0115] A meta-task difficulty calculation module is configured to calculate the task difficulty value of each meta-task according to a meta-task difficulty quantification model.

[0116] A correlation coefficient calculation module is configured to determine the correlation coefficient between any two meta-tasks according to the three-dimensional attributes of the meta-tasks, wherein the three-dimensional attributes are the response attribute, the resource attribute and the information interaction attribute of the meta-task, the correlation coefficient is calculated according to the number of unit overlaps of the three-dimensional attributes of the any two meta-tasks in a meta-task three-dimensional attribute model, and the meta-task three-dimensional attribute model divides a cube into eight units with the three-dimensional attributes as the three dimensions of space.

[0117] The concurrent task acquisition module is configured to determine concurrent tasks in the complex task and a concurrent duration according to a task processing curve of the meta task within a set time; the task processing curve is a curve of the execution of the meta task over time; the concurrent task is composed of multiple meta tasks that need to be executed simultaneously within the same time period, and the concurrent duration is a duration of the concurrent task.

[0118] The task difficulty value increment module is configured to determine a difficulty value increment of each concurrent task according to a task difficulty of a meta task included in the concurrent task, a correlation coefficient between the meta tasks included in the concurrent task, and the concurrent duration of the concurrent task.

[0119] The task difficulty calculation module is configured to determine a difficulty of the complex task according to a task difficulty value of each meta task and the difficulty value increment of each concurrent task.

[0120] In summary, the present application has the following advantages: the present application comprehensively understands various operation tasks of operators according to an operation manual and related operation records in the industry, and then can decompose actual complex tasks into minimum task units (meta tasks). In combination with information theory, the meta tasks obtained by decomposition are quantified in difficulty, the basic difficulty attributes of the complex task are determined, and a meta task three-dimensional attribute model is established. The strength of the resource competition relationship between the meta tasks is measured by the model, the calculation rule of the strength of the competition relationship is determined, the difficulty value increment caused by concurrent tasks is measured, and thus the task difficulty value of the complex task can be obtained. The method completes the difficulty measurement of the complex task from the perspective of information demand in a multi-task environment, and provides help for task optimization of operators and selection of multi-task coordination strategies. The method is also applicable to difficulty measurement of complex operation tasks in other fields.

[0121] In the specification, each embodiment focuses on the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the system disclosed by the embodiments, since it corresponds to the method disclosed by the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0122] The principles and implementation modes of the present application are described by using specific examples in the present application, and the above embodiment description is only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for measuring task difficulty in a multi-task environment in the field of human-computer interaction, characterized in that, The method comprises the following steps: Step 1: decompose a complex task of simulated flight in a multitasking environment to obtain a plurality of subtasks; the subtask is a minimum task unit of the complex task of simulated flight; the subtask is any at least one of a monitoring task, a tracking task, a communication task and a resource management task; the monitoring task comprises monitoring an abnormal situation; the abnormal situation is a red light that can be turned on, a green light that can be turned off or a wave bar that can be stopped; the tracking task is to continuously track a constantly moving target through a joystick so that the target always remains within a specified spatial range; the communication task comprises responding to a call within a specified time when a tower call arrives; the resource management task comprises controlling the opening or closing of a valve so that the fuel value is within a reasonable interval, and responding to valve damage; Step 2: calculate a task difficulty value of each subtask according to a subtask difficulty quantification model; Step 3: determine a correlation coefficient between any two subtasks according to three-dimensional attributes of the subtasks; the three-dimensional attributes are response attributes, resource attributes and information interaction attributes of the subtasks; the correlation coefficient is calculated according to the number of unit overlaps of the three-dimensional attributes of any two subtasks in a subtask three-dimensional attribute model; the subtask three-dimensional attribute model divides a cube into eight units with the three-dimensional attributes as the three dimensions of space; Step 4: determine concurrent tasks in the complex task of simulated flight and concurrent durations according to a task processing curve of the subtasks within a specified time; the task processing curve is a curve of the execution of the subtasks over time; the concurrent task is composed of a plurality of subtasks that need to be executed simultaneously within the same time period, and the concurrent duration is the duration of the concurrent task; Step 5: for each concurrent task, determine a difficulty increment of the concurrent task according to the task difficulty values of the subtasks included in the concurrent task, the correlation coefficients between the subtasks included in the concurrent task and the concurrent duration of the concurrent task; Step 6: determine the difficulty of the complex task of simulated flight according to the task difficulty values of each subtask and the difficulty increments of each concurrent task; The calculation formula of the subtask difficulty quantification model is as follows: wherein Id(i) is the task difficulty value of the elementary task, A(i) is the action intensity of the continuous elementary task; W s (i) is the action intensity noise of the continuous elementary task; μ is the correction factor; ΔT i is the duration to be responded of the discrete elementary task; j(i) is the stimulus quantity of the discrete elementary task; for continuous task is the continuous elementary task; forDiscrete task is the discrete elementary task. 2.The method of claim 1, wherein, Before step 2, the method further comprises dividing the subtasks into continuous subtasks and discrete subtasks according to response modes of the subtasks. 3.The method of claim 2, wherein, The subtask difficulty quantification model comprises a continuous subtask calculation module and a discrete subtask calculation module; The continuous subtask calculation module is used to calculate the task difficulty values of the continuous subtasks; The discrete subtask calculation module is used to calculate the task difficulty values of the discrete subtasks. 4.The method of claim 1, wherein, The task processing curve comprises the process of the subtasks from generation to response one or more times. 5.The method of claim 1, wherein, The response attributes, resource attributes and information interaction attributes of the subtasks are as follows: The response attributes comprise timely response and continuous response; The resource attributes comprise visual resources and auditory resources; The information interaction attributes comprise input information and output information. 6.The method of claim 1, wherein, Step 5 specifically comprises: According to Calculate the difficulty increment value ΔId(Task, i, j) of concurrent tasks, wherein, is the task difficulty value of the normalized meta task i, is the task difficulty value of the normalized meta task j, c ij is the correlation coefficient between meta task i and meta task j, t ijk is the concurrent duration of the kth concurrency of meta task i and meta task j within Δt, and Δt is the set time length. 7.The method of claim 1, wherein, The step 6 specifically comprises: According to calculating the difficulty Id of the complex task (Task), wherein, Id(Task) is the difficulty value of the meta task i after standardization processing, and ΔId(Task,i,j) is the difficulty increment value of the concurrent task. 8.The method of claim 1, wherein, The meta-tasks include monitoring tasks, tracking tasks, communication tasks and resource management tasks.

9. A system for measuring task difficulty in a multi-task environment in the field of human-computer interaction, for implementing the method for measuring task difficulty in a multi-task environment in the field of human-computer interaction according to any one of claims 1-8, characterized in that, Comprise: A target task acquisition module, configured to acquire a target task, the target task being a complex task in a multi-task environment; A task disassembling module, configured to disassemble a complex simulation flight task in a multi-task environment to obtain a plurality of meta-tasks, the meta-task being a minimum task unit of the complex simulation flight task; A meta-task difficulty calculation module, configured to calculate a task difficulty value of each meta-task according to a meta-task difficulty quantification model; A correlation coefficient calculation module, configured to determine a correlation coefficient between any two meta-tasks according to three-dimensional attributes of the meta-tasks, the three-dimensional attributes being response attributes, resource attributes and information interaction attributes of the meta-tasks, the correlation coefficient being calculated according to a unit overlap number of the three-dimensional attributes of the any two meta-tasks in a meta-task three-dimensional attribute model, the meta-task three-dimensional attribute model dividing a cube into eight units with the three-dimensional attributes as three dimensions of space; A concurrent task acquisition module, configured to determine a concurrent task and a concurrent duration in the complex simulation flight task according to a task processing curve of the meta-tasks within a set time, the task processing curve being a curve of execution of the meta-tasks changing with time, the concurrent task being composed of a plurality of meta-tasks that need to be executed simultaneously in the same time period, and the concurrent duration being a duration of the concurrent task; A task difficulty increment module, configured to determine a difficulty increment of each concurrent task according to a task difficulty of the meta-tasks included in the concurrent task, a correlation coefficient between the meta-tasks included in the concurrent task, and a concurrent duration of the concurrent task; A task difficulty calculation module, configured to determine a difficulty of the complex simulation flight task according to the task difficulty value of each meta-task and the difficulty increment of each concurrent task.

Images