Search

CN-121542710-B - Method, apparatus, device, storage medium and program product for task intervention

CN121542710BCN 121542710 BCN121542710 BCN 121542710BCN-121542710-B

Abstract

The application provides a method, a device, equipment, a storage medium and a program product for task intervention. The method comprises the steps of obtaining a starting time, an ending time and a current time of a current concentration task, obtaining a physiological state feature sequence of a user, wherein the physiological state feature sequence comprises physiological state features of the user from the starting time to the current time, determining a heart flow state identification result of the user based on the physiological state feature sequence, predicting a cognitive exhaustion time of the user based on the physiological state feature sequence, and adjusting the ending time of the current concentration task according to the heart flow state identification result and the cognitive exhaustion time. The method can flexibly intervene in the learning process of the user.

Inventors

  • LI NA

Assignees

  • 熵基科技股份有限公司

Dates

Publication Date
20260505
Application Date
20260120

Claims (10)

  1. 1. A method of task intervention, the method comprising: responding to a task parameter setting operation aiming at a current focused task, and acquiring a task type and a starting time set by the task parameter setting operation; extracting session data corresponding to each historical focus task belonging to the task type from a session database of a user, wherein the session data of the historical focus task comprises effective focus time of the user in the historical focus task; Determining a time attenuation weight coefficient and a concentration quality weight coefficient for each historical concentration task, determining a comprehensive weight coefficient for each historical concentration task based on the time attenuation weight coefficient and the concentration quality weight coefficient of each historical concentration task, carrying out weighted summation on the effective concentration time length of each historical concentration task by adopting the concentration quality weight coefficient of each historical concentration task to obtain a first prediction value of concentration time length, and carrying out weighted summation on the effective concentration time length of each historical concentration task by adopting the comprehensive weight coefficient of each historical concentration task to obtain a second prediction value; Determining an ending time based on the concentration time prediction value and the starting time; The method comprises the steps of obtaining the starting time, the ending time and the current time, and obtaining a physiological state characteristic sequence of the user, wherein the physiological state characteristic sequence comprises physiological state characteristics of the user from the starting time to the current time, and the physiological state characteristics comprise concentration degree characteristics, blink characteristics and heart rate variation characteristics; Determining a heart flow state recognition result of the user based on the physiological state feature sequence, and predicting a cognitive exhaustion time of the user based on the physiological state feature sequence, wherein the method specifically comprises the steps of determining whether the user currently meets preset heart flow state judgment conditions according to heart rate change features, concentration features and blink features in the physiological state feature sequence, determining that the user is currently in a heart flow state under the condition that the user currently meets the preset heart flow state judgment conditions, inputting the physiological state feature sequence into each pre-trained cognitive state recognition model to obtain a cognitive state index sequence, wherein the cognitive state index sequence comprises each cognitive state index of the user from the starting time to the current time, inputting the cognitive state index sequence into a pre-trained cognitive exhaustion point prediction model, and determining the cognitive exhaustion time of the user based on a fatigue curve of the user through the pre-trained cognitive exhaustion point prediction model; and adjusting the ending time of the current concentration task according to the heart flow state identification result and the cognitive exhaustion time.
  2. 2. The method according to claim 1, wherein said adjusting the end time of the current task of concentration according to the heart flow status recognition result and the cognitive exhaustion time comprises: Extending the ending time under the condition that the heart flow state identification result represents that the user is in the heart flow state currently; Adjusting the end time to be before the cognitive exhaustion time when the heart flow state recognition result indicates that the user is not in the heart flow state currently and the cognitive exhaustion time is earlier than the end time; and if the heart flow state identification result indicates that the user is not in the heart flow state currently and the ending time is earlier than the cognitive exhaustion time, maintaining the ending time unchanged.
  3. 3. The method of claim 1, wherein the cognitive state indicator comprises a concentration indicator, the method further comprising: determining the current distraction time of the user according to the concentration index from the starting time to the current time; determining a current attention intervention strategy for the user according to the current distraction time; And according to the attention intervention strategy, the current attention of the user is intervened.
  4. 4. The method of claim 1, wherein the cognitive state indicator comprises a fatigue indicator, the method further comprising: determining whether the user is in a fatigue state currently according to the fatigue index from the starting moment to the current moment of the user; Determining a rest time length matched with the fatigue index at the current moment based on the fatigue fading curve of the user under the condition that the user is in the fatigue state; and generating rest suggestion prompt information based on the rest time length and pushing the rest suggestion prompt information to the terminal of the user.
  5. 5. The method according to claim 1, wherein the method further comprises: the method comprises the steps of obtaining session data of the user under the condition that the user is focused on a task, wherein the session data at least comprises a time stamp and physiological index data; Based on the session data of the completed concentrated task, extracting a state feature vector of the user in the task completion process of the completed concentrated task; screening out virtual object visualization parameters matched with the state feature vector based on a preset mapping rule; And generating a virtual object corresponding to the completed concentration task based on the virtual object visualization parameters, and displaying the virtual object in a virtual space, wherein the virtual form of the virtual object in the virtual space represents the physiological state level of the user under the completed concentration task.
  6. 6. The method of claim 5, wherein the method further comprises: determining a target virtual object clicked by the virtual object clicking operation in response to the virtual object clicking operation aiming at the virtual space; The method comprises the steps of displaying the form change history of the target virtual object in the virtual space during the execution of a corresponding target concentrating task, generating the form change history based on session data of the target concentrating task, and representing the physiological state level fluctuation condition of the user in the process of executing the target concentrating task.
  7. 7. A focused task intervention device, the device comprising: The personalized duration recommending module is used for responding to the task parameter setting operation aiming at the current focused task and acquiring the task type and the starting time set by the task parameter setting operation; the method comprises the steps of extracting session data corresponding to each historical focus task belonging to a task type from a session database of a user, wherein the session data of the historical focus task comprises effective focus time lengths of the user in the historical focus tasks, determining focus time length predicted values for the current focus tasks based on the session data of the historical focus tasks, specifically comprising the steps of determining time attenuation weight coefficients and focus quality weight coefficients for the historical focus tasks, determining comprehensive weight coefficients for the historical focus tasks based on the time attenuation weight coefficients and focus quality weight coefficients of the historical focus tasks, adopting the focus quality weight coefficients of the historical focus tasks, carrying out weighted summation on the effective focus time lengths of the historical focus tasks to obtain first predicted values, and adopting the comprehensive weight coefficients of the historical focus tasks to carry out weighted summation on the effective focus time lengths of the historical focus tasks to obtain second predicted values; The acquisition module is used for acquiring the starting time, the ending time and the current time and acquiring a physiological state characteristic sequence of the user, wherein the physiological state characteristic sequence comprises physiological state characteristics of the user from the starting time to the current time, and the physiological state characteristics comprise concentration characteristics, blink characteristics and heart rate variation characteristics; The recognition module is used for determining a heart flow state recognition result of the user based on the physiological state feature sequence and predicting the cognitive exhaustion time of the user based on the physiological state feature sequence, and specifically comprises the steps of determining whether the user currently accords with a preset heart flow state judgment condition according to heart rate change features, concentration features and blink features in the physiological state feature sequence; under the condition that the user is determined to be in a current heart flow state under the condition that the current user accords with the preset heart flow state judgment condition, inputting the physiological state characteristic sequence into each pre-trained cognitive state recognition model to obtain a cognitive state index sequence, wherein the cognitive state index sequence comprises each cognitive state index from the starting moment to the current moment of the user; And the intervention module is used for adjusting the ending time of the current concentration task according to the heart flow state identification result and the cognitive exhaustion time.
  8. 8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
  9. 9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
  10. 10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Method, apparatus, device, storage medium and program product for task intervention Technical Field The present application relates to the field of man-machine interaction, and in particular, to a method, an apparatus, a device, a storage medium, and a program product for task intervention. Background With the development of information technology, various digital learning tools, such as tomato work method application, concentration timers, task management software and the like, have been widely applied to individual learning and working processes. The current digital learning tools often assist users in time planning through preset time blocks and task lists, and rely on subjective self-control capability of the users to execute learning and work planning. However, the individual state in the learning process is continuously changed, the tools cannot adaptively adjust the learning and working plans of the user according to the individual state, and the intervention means (such as rest reminding) are often relatively fixed, for example, when the user is in a tired or distracted state, the intervention cannot be performed in time, and when the user is in a highly concentrated 'heart flow' state, the fixed rest reminding can interrupt the efficient learning process of the user. Therefore, the digital learning tool in the conventional art has a problem that it is impossible to flexibly intervene in the learning process of the user. Disclosure of Invention The application aims to at least solve one of the technical defects, and particularly the technical defects that a digital learning tool in the prior art cannot flexibly intervene in a learning process of a user. In a first aspect, the present application provides a method of task-focused intervention, comprising: Acquiring a starting time, an ending time and a current time of a current concentration task, and acquiring a physiological state feature sequence of a user, wherein the physiological state feature sequence comprises physiological state features of the user from the starting time to the current time; Determining a heart flow state recognition result of the user based on the physiological state feature sequence, and predicting a cognitive exhaustion moment of the user based on the physiological state feature sequence; And adjusting the ending time of the current concentration task according to the heart flow state identification result and the cognitive exhaustion time. In one embodiment, adjusting the end time of the current task according to the heart flow state identification result and the cognitive exhaustion time includes: Under the condition that the heart flow state identification result represents that the user is in the heart flow state currently, the ending time is prolonged; when the heart flow state identification result indicates that the user is not in the heart flow state currently and the cognitive exhaustion time is earlier than the end time, adjusting the end time to be before the cognitive exhaustion time; and when the heart flow state identification result indicates that the user is not in the heart flow state currently and the ending time is earlier than the cognitive exhaustion time, maintaining the ending time unchanged. In one embodiment, the physiological state features include a concentration feature, a blink feature, and a heart rate variation feature, and determining the user's heart flow state recognition result based on the sequence of physiological state features includes: determining whether the user currently accords with a preset heart flow state judgment condition according to heart rate variation characteristics, concentration characteristics and blink characteristics in the physiological state characteristic sequence; and under the condition that the user is determined to be in the current heart flow state. In one embodiment, predicting a cognitive exhaustion moment of a user based on a physiological state feature sequence comprises: Inputting the physiological state characteristic sequence into each pre-trained cognitive state recognition model to obtain a cognitive state index sequence, wherein the cognitive state index sequence comprises each cognitive state index from the starting moment to the current moment of a user; And inputting the cognitive state index sequence into a pre-trained cognitive exhaustion point prediction model, and determining the cognitive exhaustion time of the user based on a fatigue curve of the user through the pre-trained cognitive exhaustion point prediction model. In one embodiment, the cognitive state indicator comprises a concentration indicator, the method further comprising: determining the current distraction time of the user according to the concentration index from the starting time to the current time; Determining a current attention intervention strategy for a user according to the current distraction time; according to the attention intervention strategy, the current atte