System and method for classifying user tasks as system 1 tasks or system 2 tasks

Abstract

To provide a system and a method.SOLUTION: A system and a method are disclosed for determining whether a user should adopt system 1 type thinking or system 2 type thinking when the user engages in a task. The system and method include: determining one or more characteristics of the task on the basis of the information on the task received from a data base for storing the information on the task; determining one or more characteristics of the user on the task; determining the state of the user on the basis of one or more physiological sensors configured so as to detect one or more features of the user; and determining that the user adopts system 1 type thinking or system 2 type thinking when the user engages in the tank on the basis of the one or more determined characteristics of the task, the one or more determined characteristics of the user, and the determined state of the user.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] This specification generally relates to a system and method for determining whether a user adopts System 1 type thinking or System 2 type thinking when engaging in a task.

Background Art

[0002] Research on human logical thinking suggests that most of human logical thinking ability can be approximated by a dual - process model that distinguishes between rapid and automatic intuition and slower, deliberative analytical processing. These two are typically referred to as System 1 type thinking and System 2 type thinking respectively. Generally, System 2 type thinking has advantages regarding recognition in terms of accuracy and generalizability, and System 1 type thinking has advantages regarding speed and recognition processing cost in terms of working memory and attention. Distinguishing between System 1 type thinking and System 2 type thinking makes it possible to adjust a human - interaction system to communicate with users in a more effective way.

[0003] Therefore, there is a need for a system and method for determining whether a user adopts System 1 type thinking or System 2 type thinking when engaging in a task.

Summary of the Invention

[0004] In an embodiment, a method is disclosed for a user to determine whether to adopt System 1 type thinking or System 2 type thinking when engaging in a task. The method includes determining one or more characteristics of the task based on information about the task received from a database storing information about the task, determining one or more characteristics of the user with respect to the task, determining the state of the user based on one or more physiological sensors configured to sense one or more characteristics of the user, and based on the determined one or more characteristics of the task, the determined one or more characteristics of the user, and the determined state of the user, determining that the user will adopt System 1 type thinking or System 2 type thinking when engaging in the task.

[0005] In some embodiments, a system is disclosed for a user to determine whether to adopt System 1 type thinking or System 2 type thinking when engaging in a task. The system includes one or more physiological sensors configured to sense one or more characteristics of the user and an electronic control unit communicatively coupled to the one or more physiological sensors. The electronic control unit determines one or more characteristics of the task based on information about the task received from a database storing information about the task, determines one or more characteristics of the user with respect to the task, determines the state of the user based on one or more characteristics of the user sensed by the one or more physiological sensors, and is configured to determine that the user will adopt System 1 type thinking or System 2 type thinking when engaging in the task based on the determined one or more characteristics of the task, the determined one or more characteristics of the user, and the determined state of the user.

[0006] In some embodiments, a system is disclosed for predicting whether a user will employ System 1 type thinking or System 2 type thinking when engaging in a task. The system includes one or more physiological sensors configured to sense one or more characteristics of the user, and an electronic control unit communicatively coupled to the one or more physiological sensors. The electronic control unit implements a machine learning model and receives, as inputs to the machine learning model, one or more characteristics of the task, one or more characteristics of the user with respect to the task, and a user state based on one or more characteristics of the user sensed by the one or more physiological sensors. The machine learning model is configured to predict that when the user engages in the task, the user will employ System 1 type thinking or System 2 type thinking based on the one or more characteristics of the task, the one or more characteristics of the user, and the user state.

[0007] These and additional features provided by the embodiments described herein will be fully understood in conjunction with the drawings and by considering the following detailed description.

Brief Description of the Drawings

[0008] The embodiments described in the drawings are exemplary in nature and are not intended to limit the subject matter defined by the claims. The following detailed description of the exemplary embodiments can be understood when read in conjunction with the following drawings in which similar structures are denoted by similar reference numerals.

[0009]

Figure 1

[0010]

Figure 2

[0011]

Figure 3

[0012]

Figure 4

[0013]

Figure 5

Best Mode for Carrying Out the Invention

[0014] The embodiments described herein relate to a system and method for determining whether a user adopts System 1 type thinking or System 2 type thinking when engaging in a task. System 1 type thinking is a thinking process in which a user utilizes automatic, intuitive, and unconscious thinking. That is, System 1 type thinking generally requires little energy or attention. However, when a user adopts System 1 type thinking, the response may tend to be biased because analytical and logical thinking is rarely or not at all adopted. Additionally, System 1 type thinking continuously creates impressions, intuitions, and judgments based on daily routine tasks. That is, when faced with a decision, a person automatically adopts System 1 type thinking. Therefore, System 1 type thinking is highly influential and can provide guidance for most daily decisions. However, unlike System 1 type thinking, System 2 type thinking requires energy and attention to fully consider choices and information. System 2 type thinking excludes automatic instincts and preconceptions in order to make information-based and / or logically considered choices. That is, System 2 type thinking is a time-consuming, controlled, analytical thinking method dominated by logical thinking. Furthermore, System 2 type thinking typically occurs when a user faces a new situation or when the user is consciously making an effort to engage in the details of a task.

[0015] However, when a user engages in a task, the determination of whether the user adopts System 1 type thinking or System 2 type thinking is not based solely on the particularity of the task itself. As described in more detail herein, the determination includes the particularity of the user performing a particular task. For example, a less experienced user may be likely to utilize System 2 type thinking for a particular task, while an experienced user performing the same task may be likely to utilize System 1 type thinking.

[0016] This embodiment discloses a system and method configured to collect and analyze information from at least three special categories to determine whether a user uses or attempts to use System 1 type thinking or System 2 type thinking for a special task. The three factors include the characteristics of the task, the characteristics of the user, and the state of the user. As described in more detail herein, the analysis of information related to the three factors is performed by an arithmetic processing unit such as an electronic control unit. The electronic control unit is configured to receive sensor data from one or more sensors, along with information from one or more data storage devices such as a database related to one or more of the three factors. The electronic control unit analyzes the data and information using one or more algorithms and / or machine learning models as described in more detail herein.

[0017] In some embodiments, the systems and methods described herein can be implemented to enhance or improve the interaction and / or communication between a system that deploys a task, such as a navigation system of a vehicle configured to provide navigation information, and a user. For example, as described in more detail herein, when it is determined that the user has adopted either System 1 type thinking or System 2 type thinking, a vehicle system such as a navigation system, or a system based on other vehicles or non-vehicles, can be configured to adopt an interaction and / or communication system and method that matches the type of thinking the user has adopted for the task.

[0018] These systems and methods are described in more detail below with reference to the drawings in which like numerals indicate like structures.

[0019] Referring now to FIG. 1, there is shown a system 100 for determining whether a user will employ System 1 type thinking or System 2 type thinking when the user engages in a task. System 100 includes an electronic control unit 130. The electronic control unit 130 includes a processor 132 and a memory component 134. System 100 also includes a communication bus 120, one or more input devices 136, one or more cameras 138, an eye tracking system 140, a lighting device 141, one or more physiological sensors 142, a speaker 144, a steering wheel system 146, a display 148, a data storage component 150, and / or network interface hardware 170. System 100 is communicatively coupled to a network 180 by network interface hardware 170. The components of System 100 are communicatively coupled to each other via communication bus 120.

[0020] It is understood that the embodiments shown and described herein are not limited to the components or arrangements shown and described with respect to FIG. 1, which is merely an example for illustration purposes. The various components of System 100 and their interactions are described in detail herein.

[0021] The communication bus 120 can be formed from any medium capable of transmitting signals, such as, for example, conductive wires, conductive traces, optical waveguides, etc. The communication bus 120 can also refer to electromagnetic radiation and the space through which their corresponding electromagnetic waves pass. Additionally, the communication bus 120 can be formed from a combination of media capable of transmitting signals. In one embodiment, the communication bus 120 comprises a combination of conductive traces, conductive wires, connectors, and buses that cooperate to permit the transmission of electrical data signals to components such as processor 132, memory, sensors, input devices, output devices, and communication devices. Thus, the communication bus 120 can comprise a bus. Additionally, it is noted that the term "signal" means a waveform (e.g., electrical, optical, magnetic, mechanical, or electromagnetic) that can propagate through a medium, such as DC, AC, sine wave, triangular wave, rectangular wave, vibration, etc. The communication bus 120 communicatively couples the various components of the system 100. As used herein, the term "communicatively coupled" means that the coupled components can exchange signals with each other, such as, for example, electrical signals via a conductive medium, electromagnetic signals via air, optical signals via an optical waveguide, etc.

[0022] The electronic control unit 130 can be any device, or any combination of components, that includes a processor 132 and a memory component 134. The processor 132 of the system 100 can be any device that can execute a set of machine-readable instructions stored in the memory component 134. Thus, the processor 132 can be an electric controller, an integrated circuit, a microchip, a field programmable gate array, a computer, or any other arithmetic processing device. The processor 132 is communicatively coupled to the other components of the system 100 by a communication bus 120. Thus, the communication bus 120 can communicatively couple any number of processors 132 to each other and enable the components coupled to the communication bus 120 to operate in a distributed arithmetic processing environment. Specifically, each of the components can act as a node that can send and / or receive data. The embodiment shown in FIG. 1 includes a single processor 132, but other embodiments can include one or more processors 132.

[0023] The memory component 134 of the system 100 is coupled to the communication bus 120 and communicatively coupled to the processor 132. The memory component 134 can be a non-transitory computer-readable memory implemented as, for example, RAM, ROM, flash memory, a hard drive, or any non-transitory memory device capable of storing machine-readable instructions that can be accessed by and executed by the processor 132. The set of machine-readable instructions can be machine language directly executable by the processor 132, or any programming language of any generation (e.g., 1GL, 2GL, 3GL, 4GL, or 5GL), such as assembly language, object-oriented programming (OOP), scripting language, microcode, etc., that can be compiled or assembled into machine-readable instructions and stored in the memory component 134, and can include logic or algorithms described in the programming language. Alternatively, the set of machine-readable instructions can be described in a hardware description language (HDL), such as logic implemented via any of a field-programmable gate array (FPGA) configuration, or an application-specific integrated circuit (ASIC), or their equivalents. Thus, the functions described herein can be implemented in any conventional computer programming language, as pre-programmed hardware elements, or as a combination of hardware and software components. Although the system 100 shown in FIG. 1 includes a single memory component 134, other embodiments can include one or more memory components 134.

[0024] System 100 includes one or more input devices 136. The one or more input devices 136 can be any device configured to enable a user to input information into the system. For example, the one or more input devices 136 can include a keyboard, a mouse, a stylus, a scanner, a gesture camera, a microphone, and the like. System 100 can also include one or more cameras 138. The one or more cameras 138 can be communicably coupled to the communication bus 120 and the processor 132. The one or more cameras 138 can be any device having an array of sensing devices (e.g., pixels) capable of detecting radiation in the ultraviolet wavelength band, the visible light wavelength band, or the infrared wavelength band. The one or more cameras 138 can have any resolution. The one or more cameras 138 can be, for example, an omnidirectional camera or a panoramic camera. In some embodiments, one or more optical components, such as mirrors, fish-eye lenses, or any other type of lens, can be optically coupled to each of the one or more cameras 138. The one or more cameras 138 can capture image data or video data of the vehicle's environment.

[0025] In some embodiments, system 100 can be implemented in vehicle 110 (FIG. 3) to enhance the driver's interaction and / or communication with one or more vehicle systems. For example, as described in more detail herein, when it is determined that the user is employing System 1 type thinking or System 2 type thinking, the vehicle system or other systems can be configured to employ interaction and / or communication systems and methods that are consistent with the type of thinking the user is employing for the task. For example, the one or more cameras 138 can be implemented by system 100 to image events occurring in the environment around the driver to provide information regarding the user's state and / or the characteristics of the task.

[0026] System 100 can include an eye tracking system 140 for tracking the eye movements and / or fixation state of a subject. The eye tracking system 140 can include one or more cameras 138 positioned to view one or more eyes of the subject and / or an array of infrared light detectors. The eye tracking system 140 can also include an illumination device 141, which may be an infrared or near-infrared light emitter, or can be communicatively coupled to the illumination device 141. The illumination device 141 can emit infrared or near-infrared light, which can reflect from portions of the eyes that create a profile that is more easily detectable than the reflection of visible light from the eyes for eye tracking purposes. In some embodiments, the eye tracking system 140 can also be configured to determine the pupil dilation or constriction of the user's eyes.

[0027] The eye tracking system 140 can be spatially oriented in the environment and can generate a fixation direction vector. One of various coordinate systems, such as a user coordinate system (UCS), can be implemented. For example, the UCS has its origin at the center of the front face of the fixation tracker. With the origin defined at the center of the front face (e.g., the eye tracking camera lens) of the eye tracking system 140, the fixation direction vector can be defined with respect to the position of the origin. Further, when spatially orienting the eye tracking system 140 in the environment, all other objects, including the one or more cameras 138, can be localized with respect to the position of the origin of the eye tracking system 140. In some embodiments, the origin of the coordinate system can be defined at a position on the subject, e.g., at a point between the subject's eyes. Regardless of the position of the origin with respect to the coordinate system, a calibration process can be employed by the eye tracking system 140 to calibrate the coordinate system for collecting eye tracking data, pupil dilation data, and / or eye movement information that can be used to determine the user's state, task characteristics, and / or user characteristics.

[0028] Referring further to FIG. 1, system 100 can further include one or more physiological sensors 142. The one or more physiological sensors 142 can be communicatively coupled to communication bus 120 and electronic control unit 130. The one or more physiological sensors 142 can be any device capable of monitoring and capturing the physiological state of a human body, such as the driver's stress level through monitoring the electrical activity of the heart, skin conductance, respiration, etc. The one or more physiological sensors 142 include sensors configured to measure events related to the human body, such as heart rate changes, activity related to the electrical properties of the skin (EDA), muscle tension, cardiac output, etc. The one or more physiological sensors 142 can monitor electroencephalogram (EEG) brain waves, skin conductance response (SCR), activity related to the electrical properties of the skin through galvanic skin response (GSR), heart rate (HR), beats per minute (BPM), heart rate variability (HRV) and other cardiovascular criteria, vasomotor activity, muscle activity through electromyogram (EMG), changes in pupil diameter associated with thought and emotion through pupillometry (e.g., pupillometry data), eye movements recorded via electrooculogram (EOG) and gaze direction methods, and cardiac mechanics recorded via impedance cardiography or other physiological means.

[0029] The physiological sensor 142 can generate physiological response data that can be used to train or evolve the neural network 400 to determine the user's state. The physiological response data of the subject can indicate the user's state. For example, the physiological sensor 142 can detect user characteristics indicating the user's stress level, fatigue level, and / or health status. In some examples, the physiological response data can indicate whether the user is engaged in multiple tasks or whether the user is concentrating on a particular task. For example, physiological response data indicating a rapid heartbeat, dilated pupils, rapid eye movement, and / or the presence of sweat can indicate that the user has an elevated stress level. As another example, physiological response data indicating slow eye movement and / or the presence of a change in eye color or a change in the area around the eyes can indicate that the user is fatigued. Further, physiological response data regarding the user's body temperature, blood oxygen level, heart rate (e.g., active or resting heart rate), blood pressure, respiratory rate, oxygen saturation level, etc. indicates the user's health status.

[0030] The system 100 can also include a speaker 144. The speaker 144 (e.g., an audio output device) is coupled to the communication bus 120 and communicatively coupled to the electronic control unit 130. The speaker 144 converts audio message data as a signal from the processor 132 of the electronic control unit 130 into mechanical vibrations that generate sound. For example, the speaker 144 can provide information to the user in an audible form. The audible information can be used independently of or in combination with visual images, text data, etc. However, it should be understood that in other embodiments, the system 100 may not include the speaker 144.

[0031] The steering wheel system 146 is coupled to the communication bus 120 and communicatively coupled to the electronic control unit 130. The steering wheel system 146 can include a plurality of sensors such as a physiological sensor 142 located on the steering wheel. Additionally, the steering wheel system 146 can include a motor or component for providing haptic feedback to the driver. For example, the steering wheel system 146 can be configured to provide vibrations of varying intensity through the steering wheel as a means of communicating with the driver or sending an alert to the driver.

[0032] The system 100 can include a display 148 for presenting information to the user in a visible form. The display 148 can be a heads-up display system, a navigation display, a smartphone or computing device, a television, or the like. The display 148 can include any medium capable of transmitting an optical output such as, for example, a cathode ray tube, a light emitting diode, a liquid crystal display, a plasma display, or the like. The display 148 can also include one or more input devices. The one or more input devices can be any device capable of converting user contact, such as a button, a switch, a knob, a microphone, or the like, into a data signal that can be transmitted over the communication bus 120. In some embodiments, the one or more input devices include a power button, a volume button, a start button, a scroll button, or the like. The one or more input devices can be provided to enable the user to interact with the display 148 to operate, select, set preferences, and perform other functions described herein. In some embodiments, the input device includes a pressure sensor, a touch sensing area, a pressure sensing piece, or the like.

[0033] The data storage component 150 communicatively coupled to the system 100 may be a volatile and / or non-volatile digital storage component, and thus, may include random access memory (including SRAM, DRAM, and / or other types of random access memory), flash memory, registers, compact discs (CDs), digital versatile discs (DVDs), and / or other types of storage components. The data storage component 150 may be locally resident to the system 100 and / or may be remote from the system 100 and may be configured to store one or more data such as one or more characteristics 152 of one or more tasks, one or more characteristics 154 of one or more users, and the like.

[0034] One or more characteristics 152 of one or more tasks can include characteristics such as the type of task. The type of task can include, for example, an incidental task, a routine task, a project, a reactive task, a problem-solving task, a decision-execution task, a planning task, a collaborative or independent task, a creative task, and the like. Each type of task can be classified as a task that includes System 1 type thinking or System 2 type thinking. However, the type of task alone may not be able to indicate the type of thinking employed by the user. Other characteristics such as the typical length of time taken to complete the task, the number of steps involved in completing the task, whether any of the senses such as vision, hearing, taste, or touch are involved in completing the task, and / or whether the task involves the processing of words, written information, sounds, and / or images, etc., can be considered in determining whether one or more characteristics of the task indicate that the user is engaged in a task that employs System 1 or System 2 type thinking. For example, tasks with few steps, tasks that can be completed in a short time period, and tasks that involve the processing of visual and / or audible information, etc., generally tend to cause the user to engage in System 1 type thinking. On the other hand, for example, tasks with more steps, tasks that take several minutes or hours to complete, and tasks that involve the processing of words and / or written information, etc., generally tend to cause the user to engage in System 2 type thinking. Therefore, by analyzing one or more characteristics of the task, the system and method can determine whether the characteristics of the task indicate a task that includes System 1 type thinking or System 2 type thinking. As described in more detail herein, based on one or more characteristics of the task, the determination that a user is employing System 1 type thinking or System 2 type thinking for a particular task can be a binary determination (e.g., System 1 type thinking or System 2 type thinking), or a prediction defined by the likelihood that the user is employing System 1 type thinking or System 2 type thinking.

[0035] One or more characteristics 154 of one or more users can include characteristics such as the experience level of the user performing the task, the number of times the user has completed a special task or a similar task in the past, the amount of time the user spent when previously engaged in solving the same or a similar task, whether the user is proficient in a particular set of skills related to one or more characteristics of the task, the frequency with which the user interacted with a special task, etc. One or more characteristics 154 of one or more users can be stored as a user profile in the data storage component 150 and / or the memory component 134 of the electronic control unit 130. The user profile can be developed based on past interactions of the user with the system when the user completed tasks. For example, from previous interactions, the system can learn how the user solves tasks, whether the user can complete tasks in a timely or efficient manner, etc. In some embodiments, the user profile can be developed independently of past interactions with tasks. For example, the system can prompt the user to complete surveys, questions, or simple recognition tasks that collect information directly provided by the user, such as the user's education level or skills, requests to evaluate the user's set of skills, requests to obtain the user's satisfaction level for a particular type of task through a rating process, etc. The process of collecting information about the user can, for example, be combined with monitoring the user's physiological state to determine whether the user feels stressed when faced with a special category of tasks or topics. Such information can, in part, indicate information about the type of thinking the user employs when handling special tasks.

[0036] For example, an experienced user in solving or completing a particular task may not exhibit an elevated stress level, unlike a user who is dealing with the particular task for the first time. Further, an experienced user with respect to a particular task is more likely to utilize System 1 type thinking, as opposed to a user who is dealing with the particular task for the first time, who is more likely to use System 2 type thinking. As described in more detail herein, based on one or more characteristics of one or more users, the determination that a user has adopted System 1 type thinking or System 2 type thinking with respect to a particular task can be a binary decision (i.e., either System 1 type thinking or System 2 type thinking), or a prediction defined by the likelihood that the user has adopted System 1 type thinking or System 2 type thinking.

[0037] Referring further to FIG. 1, system 100 can also include network interface hardware 170 communicatively coupled to electronic control unit 130 via communication bus 120. Network interface hardware 170 can include wired or wireless networking hardware such as a modem, a LAN port, a Wi-Fi card, a WiMax card, mobile communication hardware, and / or other hardware for communicating with network 180 and / or other devices and systems. For example, system 100 can be communicatively coupled to network 180 by network interface hardware 170.

[0038] Referring now to FIG. 2, an information flow diagram 200 is shown for determining whether a user adopts System 1 type thinking or System 2 type thinking when engaging in a task. The information flow diagram 200 illustrates sources of information available to analysis modules 210-240 implemented by the electronic control unit 130. The system and method can be implemented using an electronic control unit 130 (FIG. 1) that includes one or more processors 132 (FIG. 1). The electronic control unit 130 receives information regarding task characteristics, user characteristics, and user state. The electronic control unit 130 can be in communication with one or more input devices to provide information regarding task characteristics, user characteristics, and user state.

[0039] The input device may be one or more sensors such as cameras 138, one or more physiological sensors 142A - 142I, or other types of sensors that can provide information about the user's state. For example, regarding the user's state, the sensors can detect the user's stress level (e.g., based on a fast heartbeat, dilated pupils, rapid eye movement, presence of sweat, etc.), fatigue level (e.g., based on eye movement, presence of eye bags under the eyes, etc.), health state (e.g., based on body temperature, blood oxygen level, heartbeat, blood pressure, etc.), and whether the user is performing multiple tasks. FIG. 2 shows various types of physiological sensors 142A - 142I. As non - limiting examples, the physiological sensors 142A - 142I can include an electrocardiogram sensor 142A, a body temperature sensor 142B, a heart rate sensor 142C, a pupil dilation sensor 142D (e.g., realized using one or more cameras 138 and / or an eye - tracking system 140), an eye - tracker 142E (e.g., the eye - tracking system 140), a sweating sensor 142F, an oxygen sensor 142G, a blood pressure sensor 142H, or a respiration rate sensor 142I. These are just some examples of physiological sensors 142A - 142I that can be implemented in system 100 to monitor various physiological states of the user. The physiological sensors 142A - 142I can be embedded in a seat or a floor to monitor a user sitting or lying on it, or can be coupled to the user through a wearable device 149 (FIG. 3) configured to monitor the user from a distance when the user is within the detection range of one or more of the physiological sensors 142A - 142I. The physiological sensors 142A - 142I generate electrical signals in response to the states they are configured to monitor and transmit them to the electronic control unit 130 for analysis.

[0040] In addition to the sensors, system 100 can also obtain information including one or more characteristics of a task and one or more characteristics of a user from data storage components 150, input devices such as a display 148 with touch functionality, input devices 136, one or more cameras, etc. The electronic control unit 130 requests and / or receives information regarding one or more characteristics of one or more tasks. Such information can include the type of task the user is currently engaged in, the typical length of time it takes to complete the task, the number of steps involved in completing the task, whether any of the senses such as vision, hearing, taste, or touch are involved in completing the task, and whether the task involves processing such as words, described information, sounds, and / or images.

[0041] Additionally, system 100 obtains information about the user engaged in the task. For example, one or more characteristics 154 of one or more users can include the user's experience level in performing the task, the number of times the user has completed special or similar tasks in the past, the amount of time it took the user when previously engaged in solving the same or similar tasks, whether the user is proficient in a particular set of skills related to one or more characteristics of the task, and the frequency with which the user has interacted with special tasks, etc.

[0042] As shown in FIG. 2, the electronic control unit 130 includes one or more analysis modules (e.g., the user state module 210, the task characteristic module 220, and the user characteristic module 230) that analyze data from at least three special categories (e.g., one or more characteristics of the task, one or more characteristics of the user, and the user's state) to determine whether the user uses or attempts to use system 1 type thinking or system 2 type thinking for a particular task. The electronic control unit 130 analyzes the physiological response data generated by the physiological sensors 142A-142I to determine the user's state. The user's state can cover a wide range. That is, in order to determine the effect that a task has on the user, the user's basic state may be required. For example, a person in poor health may inherently have high blood pressure or a heart rate higher than normal, but these cannot indicate the user's stress level and are rather the result of the user's current health state. Therefore, the user state module 210 adopted by the electronic control unit 130 can be configured to determine the user's health state, and it can be used as the basic state when determining one or more characteristics of the user presented by itself in response to engaging in a task. For example, these characteristics can include the stress level, fatigue level, etc. Based on the determined state of the user based on one or more physiological sensors 142A-142I configured to sense one or more characteristics of the user, the electronic control unit 130 can determine whether the user's state is correlated with someone engaged in system 1 type thinking or system 2 type thinking. As a non-limiting example, generally, the more stressed, fatigued, and in poor health the user is, the more likely the user is to engage in system 1 type thinking. Conversely, when the user is calm, well-rested, and in better health, the user is more likely to engage in system 2 type thinking. A person engaged in multiple tasks is more likely to engage in system 1 type thinking.However, the user's state does not independently indicate the type of thinking the user engages in for a particular task.

[0043] Therefore, the electronic control unit 130 is also configured to collect information regarding the characteristics of the user task and / or the characteristics of the user, one or more sensors (e.g., one or more cameras 138 and / or input devices or input devices 136 such as a display 148 having a touch function), and / or one or more databases (e.g., data storage component 150) storing information regarding the characteristics of the user task and / or the characteristics of the user. The electronic control unit 130 can further be configured with a task characteristic module 220 implemented to analyze one or more characteristics of the task to determine whether the task is inherently a task in which the user may need to implement system 1 type thinking or system 2 type thinking to complete the task. That is, the electronic control unit 130 can receive information regarding a particular task from a database storing information regarding the task. For example, one or more characteristics of the task can include the type of task, the typical length of time taken to complete the task, the number of steps involved in completing the task, which senses (e.g., vision, hearing, taste, touch) are involved in completing the task, and / or whether the task involves processing of words / described information or sounds / images.

[0044] It should also be noted that the electronic control unit 130 can include a process for determining what task the user is currently engaged in. In some embodiments, the electronic control unit 130 determining what task the user is currently engaged in is nothing more than querying the operating state of the system to determine what function is currently being utilized. For example, in the context of a vehicle, the system 100 can be implemented as part of the vehicle to the user interface, and the currently active vehicle system can be a navigation system. Thus, when the relevant system is not currently active, the electronic control unit 130 can determine that the user is currently engaged in vehicle navigation as opposed to currently communicating with another person via phone or exchanging messages via multimedia.

[0045] Referring back to the analysis of one or more characteristics of a task to determine whether the task is inherently a task that requires the user to perform System 1 type thinking or System 2 type thinking to complete the task, the task characteristics module 220 can be preconfigured with a plurality of guiding principles for making a determination or prediction about what type of thinking the user is capable of engaging in with respect to a particular task. As a non-limiting example, generally, tasks that have more steps, take longer to complete, and involve the processing of verbal / described information engage the user in System 2 type thinking. However, tasks that have fewer steps, can be completed more quickly, and involve the processing of visual / audio information generally engage the user in System 1 type thinking. These and other guiding principles for making a determination or prediction about what type of thinking the user is capable of engaging in with respect to a particular task can be predefined in the task characteristics module 220 and implemented by the electronic control unit 130. Similar to what was described with respect to the user's state, one or more characteristics of a task do not independently indicate the type of thinking the user engages in with respect to a particular task.

[0046] Therefore, the electronic control unit 130 can further be configured with a user characteristic module 230 implemented to analyze one or more characteristics of the user to determine whether the task is inherently a task that may require the user to engage in System 1 type thinking or System 2 type thinking to complete the task. That is, the electronic control unit 130 can request and receive information about a particular user from a database storing information about the user. The information can include characteristics such as the user's experience level in performing the task, the number of times the user has completed a particular task or similar tasks in the past, the amount of time taken when the user previously engaged in solving the same or similar tasks, whether the user is proficient in a particular set of skills related to one or more characteristics of the task, and the frequency with which the user has interacted with a particular task, etc. As discussed above, the information can be defined in a user profile generated based on the user's previous experience in completing the task and / or based on the prompted feedback requested by the user's system.

[0047] The user characteristic module 230 provides guiding principles for the electronic control unit 130 to make decisions or at least predictions regarding the type of thinking the user can engage in when performing a particular task. As a non-limiting example, a more experienced user in solving a particular task is more likely to engage in System 1 type thinking, while a less experienced user is more likely to engage in System 2 type thinking when engaging in the System task. The experience level can be defined by the number of times the user has completed this particular task or similar tasks. In addition to the experience level, the amount of time the user previously required to solve the same or similar tasks can also be provided.

[0048] When information is generated and / or collected for each of three factors (e.g., task characteristics, user characteristics, and user state), the electronic control unit 130 combines a determination and / or prediction about the type of thinking the user is currently engaged in based on analysis through each of the analysis modules 210-230. Since none of the factors exclusively indicate the type of thinking the user will adopt when engaged in a particular task, the electronic control unit 130 weights the determinations and implements another module 240 to make a final determination and / or prediction as to whether the user is engaged in System 1 type thinking or System 2 type thinking. As will be discussed in more detail herein, the electronic control unit 130 can utilize one or more machine learning models trained to understand multi-dimensional information and make a determination and / or prediction as to whether the user is engaged in System 1 type thinking or System 2 type thinking for a particular task.

[0049] In some embodiments, after each of the analysis modules 210-230 is implemented, the determination made by the electronic control unit 130 as an output can be a determination having a confidence value. The confidence value indicates how likely it is that the user is engaged in System 1 type thinking or System 2 type thinking based on the information analyzed by that particular module. The confidence value can be a percentage on a scale from 0% to 100%, where 100% indicates the strength in the determination made in response to the analysis performed by the particular module.

[0050] Referring to FIG. 3, an implementation form as an example of system 100 deployed in vehicle 110 is shown for a user to determine whether to rely on system 1 type thinking or system 2 type thinking when engaging in vehicle-based tasks. In some embodiments, physiological sensor 142 is deployed within the vehicle cabin to capture physiological response data of the user 300 (e.g., the driver) when engaging in various tasks. For example, as shown, the eye tracking system 140 can be positioned within vehicle 110 such that a camera or detection device (e.g., 138) is configured to image the driver's eye movement, pupil dilation, head and / or body position. In some embodiments, an illumination device 141, such as an infrared lamp, can direct infrared light towards the driver to improve the detection of eye movement, pupil dilation, head and / or body position. Further, one or more physiological sensors 142 can be configured within vehicle seat 310 to monitor characteristics of user 300 such as, but not limited to, respiration rate, heart rate, body temperature, etc. In some embodiments, one or more physiological sensors 142 can be implemented in a wearable device 149 communicatively coupled to electronic control unit 130. The user can interact with the navigation system to obtain directions to a destination, change the play list of the audio system, engage in vehicle-related tasks such as checking or updating schedules for loading, delivery, or reservations, or other tasks. However, it is understood that the implementation form of system 100 for a user to determine whether to adopt system 1 type thinking or system 2 type thinking when engaging in tasks in vehicle 110 is only one environment in which system 100 can be deployed.

[0051] Referring now to FIG. 4, a diagram is shown as an example of a machine learning model such as neural network 400 for predicting whether a user will adopt System 1 type thinking or System 2 type thinking when the user is engaged in a task. In particular, FIG. 4 shows a machine learning model of the type of neural network 400. However, it should be understood that the electronic control unit 130 can implement various types of machine learning models to predict or determine whether a user will adopt System 1 type thinking or System 2 type thinking when the user is engaged in a task. As used herein, a "machine learning model" is one or more mathematical models configured to find patterns in data and apply the determined patterns to a new data set to make predictions. Different approaches, also referred to as categories of machine learning, are also realized depending on the nature of the problem to be solved and the type and amount of data. Categories of machine learning models include, for example, supervised learning, unsupervised learning, reinforcement learning, deep learning, or combinations thereof.

[0052] Referring to a machine learning model of the type of neural network 400, for example, the neural network 400 can include one or more layers 405, 410, 415, 420 having one or more nodes 401 connected by node connections 402. The one or more layers 405, 410, 415, 420 can include an input layer 405, one or more hidden layers 410, 415, and an output layer 420. The input layer 405 represents the unprocessed information supplied to the neural network 400. For example, one or more characteristics 152 of one or more tasks, one or more characteristics 154 of one or more users, sensor data from one or more cameras 138, the eye tracking system 140, and / or physiological response data from one or more physiological sensors 142 can be input to the neural network 400 in the input layer 405. The neural network 400 processes the received unprocessed information in the input layer 405 through the nodes 401 and the node connections 402. The one or more hidden layers 410, 415 execute arithmetic processing actions depending on the inputs from the input layer 405 and the weights for the node connections 402. In other words, the hidden layers 410, 415 execute arithmetic processing and transfer the information from the input layer 405 to the output layer 420 through their associated nodes 401 and node connections 402.

[0053] Generally, when the neural network 400 is learning, the neural network 400 is identifying and determining patterns within the unprocessed information received at the input layer 405. In response, one or more parameters, such as the weights associated with the node connections 402 between nodes 401, can be adjusted through a process known as back-propagation. Although there are various processes through which learning can occur, it should be understood that two common learning processes include associative mapping and regularity detection. Associative mapping is a learning process in which the neural network 400 learns to generate a special pattern on a set of inputs whenever another special pattern is applied to the set of inputs. Regularity detection is a learning process in which the neural network 400 learns to respond to special characteristics of the input patterns. In associative mapping, the neural network 400 stores relationships between patterns, whereas in regularity detection, the response of each unit has a special "meaning". This type of learning mechanism can be used for feature discovery and knowledge representation.

[0054] The neural network has knowledge contained in the values of the node connection weights. Modifying the knowledge stored in the network as a function of experience means a learning rule for changing the values of the weights. Information is stored in the weight matrix W of the neural network 400. Learning is the determination of the weights. Depending on how learning is carried out, two main categories of neural networks are distinguished. 1) Fixed networks where the weights cannot be changed (i.e., dW / dt = 0), and 2) Adaptive networks where the network can change its own weights (i.e., dW / dt ≠ 0). In fixed networks, the weights are deductively fixed according to the problem to be solved.

[0055] To train a neural network 400 for performing a task, adjustments are made to the weights so that the error between the desired output and the actual output is reduced. This process may require the neural network 400 to compute an error weight derivative (EW). In other words, in this process, when each weight is increased or decreased slightly, it is necessary to calculate how each error changes. The error backpropagation algorithm is one method used to determine the EW.

[0056] The algorithm first calculates the EW by computing an error activation derivative (EA), that is, the rate at which the error changes when the activation level of a unit is changed. For the output units, the EA is simply the difference between the actual output and the desired output. To calculate the EA for a hidden unit in the layer immediately preceding the output layer, first, all the weights between the hidden unit and the output units connected to the hidden unit are identified. Then, those weights are multiplied by the EA of their output units and the products are added. This sum is equal to the EA for the selected hidden unit. After calculating all the EAs for the hidden layer immediately preceding the output layer, moving layer by layer in the direction opposite to the direction in which the activation propagates through the neural network 400 (hence, "backpropagation"), the EAs for the other layers can be calculated in a similar manner. Once the EA is calculated for a unit, it is straightforward to calculate the EW for each incoming connection to the unit. The EW is the product of the EA and the activation through the incoming connection. It should be understood that this is only one way in which the neural network 400 is trained to perform a task.

[0057] Referring further to FIG. 4, neural network 400 can include one or more hidden layers 410, 415 that feed into one or more nodes 401 of output layer 420. Depending on the particular output that neural network 400 is configured to generate, there can be one or more output layers 420. For example, neural network 400 can be trained to output a prediction 430 as to whether a user engages in System 1 type thinking or System 2 type thinking when the user performs a particular task. Additionally, neural network 400 can also generate a confidence value 440 indicating how likely it is that the user is employing System 1 type thinking or System 2 type thinking. Further, known conditions 450 can be determined by neural network 400 in training and can be used as feedback for further training neural network 400.

[0058] Looking at FIG. 5, a flowchart 500 is shown as an example for determining whether a user adopts System 1 type thinking or System 2 type thinking when the user engages in a task. In other words, flowchart 500 shows an example of a method implemented by electronic control unit 130 for determining, or at least predicting, whether a user engages in System 1 type thinking or System 2 type thinking when the user completes a particular task. Flowchart 500 is just one way implemented by a system for determining, or at least predicting, whether a user engages in System 1 type thinking or System 2 type thinking when the user completes a particular task. Other ways of implementing the analysis of the three factors (e.g., user state, task characteristics, and user characteristics) as described herein can be implemented without departing from the scope of the present disclosure.

[0059] In block 502, the electronic control unit 130 identifies the task being performed by the user. As discussed above, the determination can be made based on the current operation of a system that interacts with the user, such as the operation of a navigation system by user 300 (e.g., the driver) of vehicle 110. However, in some embodiments, the image data collected by one or more cameras 138 can be analyzed to determine what task the user is performing. For example, one or more cameras 138 can identify a cooking task through image data of a user interacting with cooking utensils and stirring a ball. Additionally, in block 502, the electronic control unit 130 can obtain information through the image data as to whether the user is performing multiple tasks or is focused on a particular task.

[0060] In block 504, the electronic control unit 130 can query a database (e.g., data storage component 150) having one or more characteristics 152 of one or more tasks for characteristics regarding the identified task (e.g., the particular task the user is engaged in). As a result, the electronic control unit 130 determines one or more characteristics for the identified task based on the information received from the database. In some embodiments, in block 504, the electronic control unit 130 can further analyze one or more characteristics for the identified task to determine, based on the one or more characteristics, whether the task is a task that the user can engage in system 1 type thinking or system 2 type thinking, for example, as described with reference to task characteristic module 220.

[0061] In block 506, the electronic control unit 130 can query a database (e.g., data storage component 150) having one or more characteristics 154 of one or more users regarding the characteristics of the user who will execute the identified task. As a result, the electronic control unit 130 determines one or more characteristics of the user based on the information received from the database. These characteristics can relate to the user's expertise or experience in engaging in and / or completing a particular task. In some embodiments, in block 506, the electronic control unit 130 can further analyze one or more characteristics of the user to determine, based on the one or more characteristics, whether the user is likely to engage in system 1 type thinking or system 2 type thinking to complete the task, for example, as described with reference to the user characteristics module 230.

[0062] In block 508, the electronic control unit 130 receives one or more signals from one or more sensors, including, for example, one or more cameras 138, an eye tracking system 140, a physiological sensor 142, etc. The electronic control unit 130 analyzes a signal that can include physiological response data of the user who is engaged in executing the identified task. Determinations about stress level, fatigue level, etc. are made by the electronic control unit 130 through the analysis of one or more signals from one or more sensors. Through the analysis of one or more physiological sensors 142 configured to sense one or more characteristics of the user, the electronic control unit 130 determines the state of the user. In some embodiments, in block 508, the electronic control unit 130 determines, based on the state of the user, whether the user is engaged in system 1 type thinking or system 2 type thinking to complete the task, for example, as described with reference to the user characteristics module 230.

[0063] In block 510, the electronic control unit 130 summarizes the decisions made through the analysis performed in blocks 504-508 and makes a determination, or at least a prediction, with a level of confidence as to whether the user will employ System 1 type thinking or System 2 type thinking when the user engages in a task. The determination can be made by weighting three factors (e.g., one or more determined characteristics of the task, one or more determined characteristics of the user, and the determined state of the user). In some embodiments, the electronic control unit 130 can assign a greater weight to one factor than to the other factors based on the determined confidence level for the factor. That is, if one factor more clearly indicates System 1 type thinking or System 2 type thinking, that factor is given a greater weight when combining all three of these factors in making the determination that the user is employing System 1 type thinking or System 2 type thinking when the user engages in the task.

[0064] The functional blocks and / or flowchart elements described herein can be converted into machine-readable instructions. By way of non-limiting example, the machine-readable instructions can be described using any suitable programming protocol such as (i) descriptive statements to be parsed (e.g., such as hypertext markup language, extensible markup language, etc.), (ii) assembly language, (iii) object code generated from source code by a compiler, (iv) source code described using syntax from any appropriate programming language for execution by an interpreter, (v) source code for compilation and execution by a just-in-time compiler. Alternatively, the machine-readable instructions can be described in a hardware description language (HDL) such as logic implemented via any of a field programmable gate array (FPGA) configuration or an application specific integrated circuit (ASIC) or their equivalents. Accordingly, the functions described herein can be implemented in any conventional computer programming language, as pre-programmed hardware elements, or as a combination of hardware and software components.

[0065] It should be understood that the embodiments described herein are directed to a system and method for a user to determine whether to employ System 1 type thinking or System 2 type thinking based on three factors when engaging in a task. In some embodiments, the system and method can utilize an electronic control unit and / or a neural network to receive, analyze, and make a determination or prediction regarding whether a user is engaging in System 1 type thinking or System 2 type thinking when performing a particular task. For example, a method for determining whether a user will employ System 1 type thinking or System 2 type thinking when engaging in a task can include determining one or more characteristics of the task based on information about the task received from a database storing information about the task, determining one or more characteristics of the user with respect to the task, determining the state of the user based on one or more physiological sensors configured to sense one or more characteristics of the user, and determining that the user will employ System 1 type thinking or System 2 type thinking when engaging in the task based on the determined one or more characteristics of the task, the determined one or more characteristics of the user, and the determined state of the user.

[0066] The terms "substantially" and "about" are used herein to refer to the inherent degree of uncertainty that can be considered to result from any quantitative comparison, value, measurement, or other representation. These terms can also be used herein to represent the degree to which a quantitative representation may deviate from a specified reference without resulting in a change in the basic function of the subject matter.

[0067] Although specific embodiments have been illustrated and described herein, it should be understood that various other changes and modifications can be made without departing from the spirit and scope of the claimed subject matter. Further, while various aspects of the claimed subject matter have been described herein, such aspects need not be utilized in combination. Accordingly, the appended claims are intended to cover all such changes and modifications that are within the scope of the claimed subject matter.

Claims

1. A method for determining whether to employ System 1 type thinking or System 2 type thinking when a user engages in a task, comprising: determining one or more characteristics of the task based on information about the task received from a database storing information about the task; determining one or more characteristics of the user with respect to the task; determining the state of the user based on one or more physiological sensors configured to sense one or more characteristics of the user; determining whether the user will employ System 1 type thinking or System 2 type thinking when engaging in the task based on the determined one or more characteristics of the task, the determined one or more characteristics of the user, and the determined state of the user.

2. The method of claim 1, wherein the state of the user includes at least one of the user's stress level, fatigue level, or health condition.

3. The method of claim 2, wherein the stress level is defined by at least one of the user's heart rate, pupil dilation, eye movement, or sweating.

4. The method of claim 3, wherein an elevated level of stress indicates that the user will employ System 1 type thinking for the task.

5. The method of claim 2, wherein the fatigue level is defined by at least one of the user's eye movement or discoloration of the eyes or around the eyes.

6. The method of claim 2, wherein an elevated level of fatigue indicates that the user will employ System 1 type thinking for the task.

7. The method of claim 1, wherein the one or more characteristics of the user include the user's level of experience with respect to the task.

8. The method of claim 7, wherein when it is determined that the user has a high level of experience with respect to the task, the state of the user indicates that the user will employ System 1 type thinking for the task.

9. The method of claim 7, wherein when one or more of the characteristics of the task indicate that the task includes at least one of visual information, audible information, or a limited number of steps, the user is determined to adopt System 1 type thinking.

10. A system for predicting whether a user will adopt System 1 type thinking or System 2 type thinking when engaging in a task, one or more physiological sensors configured to sense one or more characteristics of the user, comprising an electronic control unit communicatively coupled to the one or more physiological sensors, the electronic control unit implementing a machine learning model, receiving, as inputs to the machine learning model, one or more characteristics of the task, one or more characteristics of the user related to the task, and the state of the user based on the one or more characteristics of the user sensed by the one or more physiological sensors, characterized in that the machine learning model is configured to predict whether the user will adopt System 1 type thinking or System 2 type thinking when engaging in the task, based on the one or more characteristics of the task, the one or more characteristics of the user, and the state of the user.

11. The system of claim 10, wherein the electronic control unit is further configured to determine a confidence level corresponding to the prediction of whether the user will adopt System 1 type thinking or System 2 type thinking when engaging in the task.

Images