阅读说明：本技术 用于生成用户特定反馈的系统和方法 (System and method for generating user-specific feedback ) 是由 P·B·J·希金斯 孙雯 于 2020-05-20 设计创作，主要内容包括：本发明提供用于为用户生成基于用户的反馈的系统。系统包括用户传感器和反馈管理单元,用户传感器适于获取用户数据。反馈管理单元适于获得用户档案,用户档案包括：用户目标；以及与用户已经在追求用户目标的时间量有关的用户经验水平。进一步地,反馈管理单元适于基于所获取的用户数据来生成情绪预测,并且基于用户经验水平和情绪预测来选择反馈类型和反馈效价。反馈管理单元然后基于所选择的反馈类型和反馈效价生成反馈。系统还包括适于向用户提供所生成的反馈的用户接口。(The present invention provides a system for generating user-based feedback for a user. The system comprises a user sensor adapted to obtain user data and a feedback management unit. The feedback management unit is adapted to obtain a user profile, the user profile comprising: a user target; and a user experience level related to the amount of time the user has been pursuing the user goal. Further, the feedback management unit is adapted to generate an emotion prediction based on the acquired user data, and to select the type of feedback and the valence of the feedback based on the user experience level and the emotion prediction. The feedback management unit then generates feedback based on the selected feedback type and feedback titer. The system further comprises a user interface adapted to provide the generated feedback to the user.)

1. A system (100) for generating user-based feedback for a user, the system comprising:

a user sensor (110) adapted to acquire user data;

a feedback management unit (130), wherein the feedback management unit is adapted to:

obtaining a user profile, the user profile comprising:

a user target; and

a user experience level related to an amount of time the user has been pursuing the user goal;

generating an emotion prediction based on the obtained user data;

selecting a feedback type and a feedback titer based on the user experience level and the mood prediction; and

generating feedback based on the selected feedback type and feedback titer; and

a user interface (140) adapted to provide the generated feedback to the user.

2. The system (100) according to claim 1, wherein the user sensor is adapted to sense one or more of:

a movement mode;

physical activity;

galvanic skin response;

heart rate; and

user interaction with the system.

3. The system (100) according to any one of claims 1 to 2, wherein the user profile further comprises historical user data.

4. A system (100) according to claim 3, wherein the feedback management unit (130) is adapted to generate an emotion prediction comprising comparing the obtained user data with the historical user data.

5. The system (100) according to any of claims 1 to 4, wherein the user profile further comprises a target performance related to achieving the user goal, and wherein the feedback management unit (130) is further adapted to select the feedback type and the feedback titer based on the target performance.

6. The system (100) according to any of claims 1 to 5, wherein the user profile further comprises a user self-assessment relating to a user's perception of user performance towards the user target, and wherein the feedback management unit (130) is further adapted to select a feedback type and a feedback valence based on the user self-assessment.

7. The system (100) according to any one of claims 1 to 6, wherein the feedback type includes one or more of:

verifying the feedback; and

and (4) information feedback.

8. The system (100) according to any one of claims 1 to 7, wherein the feedback titer includes one or more of:

positive feedback; and

negative feedback.

9. The system (100) according to any one of claims 1 to 8, wherein the user sensor (110) and the user interface (140) are located within a smart device of the user.

10. The system (100) of claim 9, wherein the smart device comprises one or more of:

a smart phone; and

provided is a smart watch.

11. A computer-implemented method (400) for generating user-specific feedback for a user, the method comprising:

obtaining (410) user data;

obtaining (420) a user profile, the user profile comprising:

a user target; and

a user experience level related to an amount of time the user has been pursuing the user goal;

generating (430) an emotion prediction based on the obtained user data;

selecting (440) a feedback type and a feedback titer based on the user experience level and the mood prediction;

generating (450) feedback based on the selected feedback type and feedback titer; and

providing (460) the generated feedback to the user.

12. The method (400) of claim 11, wherein the user profile further includes a target performance, and wherein selecting the feedback type and the feedback titer is further based on the target performance.

13. The method (400) of any of claims 11-12, wherein the user profile further comprises a user self-assessment, and wherein selecting the feedback type and the feedback titer is further based on the user self-assessment.

14. The method (400) of any of claims 11-13, wherein the method further comprises: updating the user profile based on the user data and the selected feedback type and feedback titer.

15. A computer program comprising computer program code means adapted to perform the method of any of claims 11 to 14 when said computer program is run on a computer.

Technical Field

The present invention relates to the field of generating user specific feedback, and more particularly to the field of automatically generating and providing user specific feedback.

Background

Setting goals and receiving feedback that the goals are implemented are fundamental techniques to implement behavior changes and are often implemented as functions in mobile health applications. The heart of lifestyle behavior modification is three interrelated technologies: self-monitoring of behavior; setting a target; and receiving feedback regarding the performance of achieving the goal. The nature and timing of the feedback, as well as the potential emotional state of the user, may affect how the user responds to the feedback.

In these techniques, periodic feedback on preset goals is considered the basis for user-directed behavior changes, as it helps to maintain power and motivate continuous efforts toward the ultimate goal without direct input from the healthcare provider. However, it is often overlooked that feedback may be more or less effective depending on various factors when it is received.

Therefore, there is a need for a means of generating and providing user-specific feedback to a user in a manner that optimizes the likelihood of success for the user to achieve their goals.

Disclosure of Invention

The invention is defined by the claims.

According to an example of an aspect of the present invention there is provided a system for generating user-based feedback for a user, the system comprising:

a user sensor adapted to acquire user data;

a feedback management unit, wherein the feedback management unit is adapted to:

obtaining a user profile, the user profile comprising:

a user target; and

a user experience level related to an amount of time that the user has been pursuing the user goal;

generating an emotion prediction based on the acquired user data;

selecting a feedback type and a feedback titer based on the user experience level and the mood prediction; and

generating feedback based on the selected feedback type and feedback titer; and

a user interface adapted to provide the generated feedback to a user.

The present invention provides a method of generating user-specific feedback based on the mood of the user and the length of time they have been pursuing a goal.

It is well known that the mood of a user can affect their acceptance of a given form of feedback. Furthermore, the time they have pursued the goal can also affect the reception and effectiveness of a given type of feedback.

By tailoring the feedback type and valence based on the user's mood and goal phase, feedback can be generated that may best impact the user's motivation to pursue the goal.

The combination of the mood of the user and the length of time the user has been pursuing the goal provides a more accurate assessment of the type of feedback and the best opportunity to provide feedback that is most beneficial to the user.

In one embodiment, the user sensor is adapted to sense one or more of:

a movement mode;

physical activity;

galvanic skin response;

heart rate; and

user interaction with the system.

In this way, many different sensor outputs may be used to assess the mood of the user.

In one embodiment, the user profile further comprises historical user data.

By providing historical user data, the performance of a user over a period of time may be evaluated.

In a further embodiment, the feedback management unit is adapted to generate an emotion prediction, which comprises comparing the obtained user data with historical user data.

In this way, the current data may be compared to historical user data to generate a more informed decision about the user's current mood.

In one arrangement, the user profile further comprises a target performance related to the achievement of the user target, and wherein the feedback management unit is further adapted to select the feedback type and the feedback titer based on the target performance.

In this way, the user can select appropriate feedback in consideration of the achievement degree of the goal.

In an embodiment, the user profile further comprises a user self-assessment relating to the user's perception of their performance towards the user target, and wherein the feedback management unit is further adapted to select the type of feedback and the feedback titer is further based on the user self-assessment.

In this way, the user's perception of his own performance may be taken into account when selecting the appropriate feedback.

In one embodiment, the feedback types include one or more of:

verifying the feedback; and

and (4) information feedback.

In this way, the amount of detail in the feedback can be adjusted according to the user's acceptance.

In one embodiment, the feedback titer includes one or more of:

positive feedback; and

negative feedback.

Thus, the tone of the feedback can be adjusted according to the acceptance degree of the user.

In one embodiment, the user sensor and user interface are located within the user's smart device.

In this way, the system may be integrated into a single smart device.

In further embodiments, the smart device includes one or more of the following:

a smart phone; and

provided is a smart watch.

According to an example of an aspect of the present invention, there is provided a computer-implemented method for generating user-specific feedback for a user, the method comprising:

obtaining user data;

obtaining a user profile, the user profile comprising:

a user target; and

a user experience level related to an amount of time that the user has been pursuing the user goal;

generating an emotion prediction based on the acquired user data;

selecting a feedback type and a feedback titer based on the user experience level and the mood prediction;

generating feedback based on the selected feedback type and feedback titer; and

the generated feedback is provided to the user.

In one embodiment, the user profile further comprises a target performance, and wherein selecting the feedback type and the feedback titer is further based on the target performance.

In one embodiment, the user profile further comprises a user self-assessment, and wherein selecting the feedback type and the feedback titer is further based on the user self-assessment.

In one embodiment, the method further comprises updating the user profile based on the user data and the selected feedback type and feedback titer.

In this way, the user profile may be continuously updated based on the most recent feedback provided to the user.

According to an example of an aspect of the present invention, there is provided a computer program comprising computer program code means adapted to perform the above-mentioned method when said computer program is run on a computer.

These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiment(s) described hereinafter.

Drawings

For a better understanding of the present invention, and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

FIG. 1 illustrates a system for generating user-based feedback for a user;

fig. 2 shows a schematic diagram of a feedback management unit;

FIG. 3 shows a schematic diagram of an exemplary state and phase detector; and

FIG. 4 illustrates a method of generating user-based feedback for a user.

Detailed Description

The present invention will be described with reference to the accompanying drawings.

It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the devices, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, systems, and methods of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings. It should be understood that these drawings are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the figures to indicate the same or similar parts.

The present invention provides a system for generating user-based feedback for a user. The system comprises a user sensor adapted to obtain user data and a feedback management unit. The feedback management unit is adapted to obtain a user profile, the user profile comprising: a user target; and a user experience level related to the amount of time the user has been pursuing the user goal. Further, the feedback management unit is adapted to generate an emotion prediction based on the acquired user data, and to select the type of feedback and the valence of the feedback based on the user experience level and the emotion prediction. The feedback management unit then generates feedback based on the selected feedback type and feedback titer. The system further comprises a user interface adapted to provide the generated feedback to the user.

FIG. 1 illustrates a system 100 for generating user-based feedback for a user.

The system 100 includes a user sensor 110, the user sensor 110 being adapted to acquire user data, which may include one or more of: motion patterns, for example, acquired by an accelerometer; physical activity; galvanic skin responses, for example, acquired through electrodes in contact with the user's skin; heart rate, for example, acquired using a heart rate monitor; and user interaction with the system. The user interactions may include, for example, user data aggregated from multiple calls made by the user, the user's social network activity level, the usage activity level of a given application, the total screen time, and so forth. These metrics may be used to assess the mood of the user. The user sensors 110 may be located within a user's smart device (such as a smart phone and/or a smart watch). The user sensor may also be located in any suitable device that the user carries with him.

The acquired user data may be communicated from the user sensors to the processing unit 120, and the processing unit 120 may be a local processing unit or a remote processing unit. The local processing unit may be a processor located within the same device as the user sensor, such as a smart phone. The remote processing unit may be a cloud processing resource that communicates with the user sensor over a wired/wireless link. In the example shown in fig. 1, processing unit 120 is a remote processing unit, and more specifically a cloud processing resource.

The processing unit 120 may aggregate the user data in the memory unit 125, which may then be provided to the feedback management unit 130 and/or the user interface 140.

In other words, the system 100 operates using sensors from a smartphone or sensors from a variety of wearable technologies capable of tracking user data related to, for example, physical activity, motion, physiological functions, and social interactions. The system may operate and/or be used within existing mobile or electronic wellness applications that provide feedback to users regarding their progress in achieving a goal. Further, the system may utilize existing connectivity platforms and access to the cloud, for example, via WLAN or 4G connections. In the system 100 shown in fig. 1, user data from the user sensors 110 is aggregated on a cloud server and managed for analysis.

The system 100 further comprises a feedback management unit 130, the feedback management unit 130 being configured to analyze the user data and select an appropriate feedback to provide to the user.

The feedback management unit 130 is adapted to obtain a user profile comprising user goals and a user experience level related to the amount of time the user has been pursuing the user goals. The user profile may also include historical user data, i.e., user data captured over a period of time. The user goal may be, for example, a diet goal or an exercise goal.

In other words, the user profile may be maintained and continuously updated with objectively obtained user start date data relating to the date the user began pursuing the user objective. In addition, the user profile may include subjective information about user self-performance, which may be obtained by the user using a digital visual analog scale (dVAS), and user response performance, which may also be captured using dVAS.

In one example, a user starting the system and recording three consecutive days of usage may be the starting time for the user to pursue the user's goals.

The user's past success in the program may also be logged using historical user data. In this case, the rules may be used to continuously update the user's profile (e.g., weekly) and prompt completion of the dVAS to maintain an updated record of user self-performance and user reaction performance. Thus, based on the following dimensions: program time (days); self-potency (score between 0-100); and response efficacy (score between 0-100), each user may be provided with a continuously updated profile, and the feedback type and feedback titer may be customized according to the continuously updated profile.

The feedback management unit is further adapted to generate an emotion prediction based on the acquired user data.

For example, system 100 may utilize a mobile phone or fitness watch sensor as user sensor 110 to generate user data that is processed as a quantitative assessment of mood. User data such as the following may be analyzed to assess the mood of the user: a movement mode; physical activity; galvanic skin response; heart rate; and user interaction with the system (e.g., typing dynamics, frequency and duration of telephone conversations, frequency and duration of messaging, social media usage, frequency of application usage, etc.).

Some combination of various types of user data may be utilized based on the availability of sensors and the willingness of users to share related data, and reduced to a single quantitative variable. The emotional predictions may be continuously evaluated, and records of past and current emotional states may be generated and maintained.

Generating the emotional predictions may include: the obtained user data is compared with historical user data to correlate trends in the user data with user emotions, thereby improving the accuracy of emotion prediction.

Finally, the feedback management unit 130 selects a feedback type and a feedback titer based on the user experience level and the emotion prediction, and generates feedback to provide to the user based on the selected feedback type and feedback titer.

The feedback type may include verification feedback and/or informational feedback, and the feedback titer may include positive feedback and/or negative feedback.

In some cases, the user profile further comprises a target performance related to the achievement of the user target, and wherein the feedback management unit is further adapted to select the feedback type and the feedback titer based on the target performance. Furthermore, the user profile may comprise a user self-assessment relating to the user's perception of their performance towards the user target, and wherein the feedback management unit is further adapted to select the type of feedback and the feedback titer is further based on the user self-assessment.

From the feedback valence, positive feedback emphasizes the success of the user over the failure of the user. Conversely, negative feedback highlights unsuccessful results more than successful ones. In the most basic theory of motivation, positive feedback will result in positive emotions/effects, while negative feedback will result in negative emotions/effects. In fact, the psychological processing of positive and negative feedback is performed using different cognitive mechanisms. Positive feedback is processed by reinforcement learning; and the process of negative feedback occurs through cognitive information processing.

By extension, if the user is already in a negative mood, negative feedback should not be provided, as it is not well accepted, not adequately handled, and may even worsen the user's mood. Nevertheless, it is important to note that in many cases it is essential to provide negative feedback.

Positive feedback is important when users begin to pursue new targets. In other words, positive feedback should be more popular than negative feedback when the user first begins to pursue a new target. Positive feedback can improve outcome expectation (response efficacy) and self-efficacy, while also increasing user confidence.

However, in some cases, positive feedback may be problematic because it may encourage a sense of self-satisfaction, a sense of partial target achievement, and a sense of relaxation effort. On the other hand, negative feedback may decrease the confidence of the user, especially in the case where self-efficiency and response efficiency are low. However, negative feedback helps encourage users at a higher stage of target pursuit and summation capability to increase efforts at key stages where behavior change maintenance is critical to target success.

In addition to the effects of positive and negative feedback, the user experience level (i.e., the amount of time the user has been pursuing the user's goals) also affects the degree of reception of feedback. The user experience level may be categorized according to whether the user is highlighted towards the goal or balanced towards the goal.

The highlighted user is often in an early stage of pursuing a new goal. The highlighted user tends to focus on the target and take action consistent with the target. These actions often complement each other in terms of user goals, for example, a user seeking dietary goals no longer eats fried food and drinks sugar-containing beverages on weekends. The user will publicly express a commitment to the diet objective with high expectations and confidence of success. Each action taken further confirms the user's commitment to achieve the goal. According to the cross-theoretical model/change phase model, they are between the preparation phase and the early action phase.

In contrast, users in balance are often in a more advanced stage, i.e., early excitement and motivation to achieve a goal may have declined, and eventually the goal is not in their mind. The user may re-recognize the necessity to achieve the goal, but consider each step as a process to achieve the goal. In this case, the user will typically go deep into the program and step towards the goal, for example, a user seeking a diet goal may choose to eat salad at monday lunch because they know that they have eaten fried breakfast on sunday.

In the balance category, if the previous action is inconsistent with the target, the user is more likely to follow the target-consistent operation. According to the cross-theoretical model, these users will be in the middle and late action and maintenance phases.

In view of the feedback titer and the user experience level, the feedback management unit may determine the following. The reaction to positive feedback may be an increase in motivation and effort given when highlighting, as it enhances the sensory commitment to the target. The reaction to positive feedback may be a decrease in the power and effort given at the equilibrium time, as this indicates sufficient progress and effort. The reaction to negative feedback may be a decrease in power and effort when highlighting, as it may diminish the promise of the target. The reaction to negative feedback may be to give a boost in power and effort at equilibrium time, as it indicates an under-progression.

In summary, positive feedback may be more useful when a user is actively building commitments to goals; however, negative feedback may be more useful when an individual needs increased effort to actively pursue a daily goal (balance). Indeed, negative feedback processing may be critical when user data highlights a gap between the target and the current performance and the user needs to take action to close this gap.

In other words, the user's sense of promise may change over time. It goes without saying that users actively establish their commitments (highlighting) at the beginning of pursuit of the goal, but may also reestablish the commitments later during the procedure when a significantly new goal has been set. Thus, users are less likely to evaluate their commitments and as they become more experienced in pursuing goals, they are more likely to balance detailed progress monitoring. In fact, users who are more experienced in a given task are more likely to seek negative feedback, while those who are less experienced are more likely to seek positive feedback.

As described above, providing feedback may change an individual's mood. Further, the indication that the user is in a positive or negative mood may be a mechanism by which feedback management unit 130 may provide feedback to drive motivation and effort. In addition, mood prediction may provide target progress information.

However, the potential mood of the user when giving feedback (independent of the feedback itself) may affect the handling and the way of action of the feedback. Emotions can be viewed as a self-regulating resource of management information. Furthermore, whether the user attributes their current positive or negative mood to the actual feedback given has a significant impact on whether the feedback has a necessary impact on the effort to achieve the goal. In the period when individuals seek to improve their commitment to goals (highlighting), the potential positive impact in giving positive feedback may further increase the motivation to achieve goals. Furthermore, if feedback is provided to a user who is highlighted when in a negative mood, the goal-directed effort may be suboptimally affected.

Furthermore, the importance of negative feedback is crucial for a user who is balancing, and if this negative feedback is given at a potentially positive mood, the user (who has more cognitive resources) will be better able to process the information contained in the negative feedback and be more likely to take sufficient action on the negative feedback provided. Thus, by taking into account the mood of the user and their level of experience, the time and valence of the feedback can be adjusted to optimize the user's response and effort to achieve the goal. Furthermore, since emotions are not simple binary states and there is a continuous emotional state between very bad emotions and very good emotions, a continuous quantitative representation of emotions can be provided to enhance the accuracy of the feedback management unit.

In addition to the valence (positive or negative) of feedback, the type of feedback also has a significant impact on power and effort. Feedback types can be divided into two broad categories: confirmatory or verification feedback; and informational feedback. Confirmatory feedback is simply an indication of whether a person is on the right track, i.e. it provides minimal information and is useful in the early stages of pursuing goals and when the cognitive load is high (e.g. during negative emotional times).

In contrast, informational feedback is much more detailed and may provide information about, for example, the size of the performance gap, the reason why the individual has not achieved target behavior, and even how corrective action is taken. The informational feedback is useful for higher-level users seeking goals (balance). However, informative feedback may carry a considerable cognitive burden. To ensure that highly detailed informative feedback is adequately handled, management may feedback at a relatively cognitively easy time when more cognitive resources are available. Such times are often associated with a general positive mood.

Furthermore, the presence of positive emotions predicts that the interest in negative information of the user will increase and supports more thorough processing of the negative information if the negative information is deemed useful for the user's goal.

Additionally, the feedback management unit may adjust the feedback to take into account the user's sense of self-performance. The user's self-effectiveness, or the belief (confidence) in their ability to achieve a goal, may be considered in the context of feedback type and valence. Users with low self-potency will benefit more from positive feedback than those with already high self-potency. Thus, it is possible to determine the potency of the feedback based on knowledge of self-potency.

The efficacy of the reaction, i.e. whether the feedback information is considered useful, may have an impact on the choice of feedback titer. When negative feedback is provided during a positive impact, it gets better processed when the information is deemed useful. The user may provide an indication of the perceived usefulness of certain feedback aspects to select the type and valence of the feedback for future use.

The system 100 further comprises a user interface 140, the user interface 140 being adapted to provide the generated feedback to the user. The user interface may be located within a user's smart device (such as a smart phone and/or a smart watch). The user interface may be located in the same device as the user sensor. The user interface may include an application for processing user interactions, such as an application for collecting user self-performance or reaction performance ratings.

Fig. 2 shows a schematic representation of the feedback management unit 130.

The feedback management unit 130 may comprise an emotion predictor unit 210, the emotion predictor unit 210 being adapted to receive user data from the user sensor 110 (and also historical user data from the memory unit 125) and to generate an emotion prediction for the user. The user data may include various data types as described above.

As described in one or more of the following: likamwa R, Liu Y, Lane ND, Zhong l.moodsope: building a Mobile Sensor from Smartphone Usage Patterns; MobisSys' 13, June 25-28,2013, Taipei, Taiwan; stutz T, et al, smartphone Based Stress Prediction; ricci et al (Eds.): UMAP2015, LNCS 9146, pp.240-251, DOI 10.1007/978-3-319-; and Cao B, Zheng L, Zhang C, et al, DeepMood: Modeling mobile phone typing dynamics for motion detection.Association for Computing Machinery 2017.https:// doi.org/10.1145/3097983.3098086, mood predictions may be generated using user data.

The feedback management unit 130 may be configured to perform a continuous analysis of the emotion prediction using user data from the user sensors 110 and/or mobile device usage to determine the current emotional state of the user. Emotion predictor unit 210 may convert the results of a given emotion algorithm to generate semi-quantitative variables for emotion, which may be used to provide a more accurate prediction of emotion over simple positive or negative binary states. For example, emotions can be classified according to a continuum from very negative to very positive: -3 (very negative), -2, -1, 0 (neutral), +1, +2, +3 (very positive). Initially, this may be performed using basic heuristic algorithms, but may also be determined and dynamically updated using machine learning algorithms.

Further, the feedback management unit 130 may comprise a phase and state detection module 220, the phase and state detection module 220 being adapted to obtain a user profile 225 (and may also receive historical user data from the memory unit 125) to determine the user experience level. The operation of the phase and state detection module 220 is further discussed below with reference to FIG. 3.

As described above, the user experience level may be used to select the feedback type and the feedback titer through the feedback selection unit 230. The user emotion prediction may then be combined with the selected feedback type and feedback valence as input to the feedback trigger unit 240. The feedback selection unit may use the user experience level to change the wording and/or appearance of the feedback provided to the user.

The feedback trigger unit 240 may prepare using the most recently updated feedback type and valence data from the feedback selection unit 230 daily or at any other suitable interval. When the appropriate emotional state of the selected feedback type and feedback valence is received, a feedback release may be triggered and the feedback presented to the user, as determined by emotion predictor unit 210.

In other words, the feedback trigger unit 240 receives input from the emotion predictor unit and from the feedback selection unit. The personalized feedback message created in the feedback selector unit is only sent to the user if the right conditions are fulfilled depending on the user's level of emotion and experience. The feedback trigger unit may continuously analyze the user's prediction of emotion while also evaluating historical patterns of recent emotion predictions to ensure accurate emotion detection. This may be performed, for example, by evaluating recent data patterns using basic outlier detection methods, such as the Grubbs test method. If a given mood data set is determined to be an outlier, it may be excluded from the historical user data. Classical bayesian prediction or similar methods that take into account historical user data can be used to determine the probability that the emotion prediction is correct based on past emotion history. The most likely emotional state may be selected based on the maximum probability value obtained from a series of such predictions.

Fig. 3 shows a schematic diagram of an exemplary state and phase detector 220 of feedback module 130.

The state and phase detector 220 may operate according to the following rule set; however, after aggregation of a large amount of user data, the rules may be managed by a machine learning algorithm trained using available user data.

The state and phase detector 220 shown in FIG. 3 takes into account the amount of time the user has been pursuing the user goal 310 and the success of the user pursuing the goal 320 to generate a measure of the phase of the user's progress toward the goal (novice: N)₁；N₂(ii) a Or N₃Or the expert: e₁；E₂(ii) a Or E₃) And self-efficacy 330 (F)_{1. 2 or 3}) And reaction efficiency 340 (R)_{1. 2 or 3}). The state and phase detector 220 shown in fig. 3 is adapted to generate a tertile number (3 parts) from the continuous variables obtained from the user profile, which tertile number may correspond to early, medium or late stages of novice and expert categories as well as high, medium, low self-potency and response potency.

Data relating to the length of time that the user pursues the goal may be analyzed first. These data can be obtained directly from the user profile. Four temporal levels in the program are used to assign users to one of four categories: n is a radical of₁、N₂、N₃Or an expert. In the example shown in fig. 3, if the time is less than three days ((iii))<3d) Then the user is not assigned a category. If the time is between 3 and 7 days (3-7d), the user is assigned a first novice category. If the time is between seven and twenty-one days (7-21d), the user is assigned a second novice category. If the time is between twenty-one and twenty-eight days (21-28d), the user is assigned a third novice category. If the time for the user to pursue the target exceeds 28 days (>28d) They may be assigned to expert categories. It is noted thatIn the example shown in fig. 3, the time taken to pursue the goal is not used to assign the user to a specific expert category, but is used as an indicator that the user is no longer a novice.

Data relating to the user's success in pursuing goals may be used to refine the assignment of expert categories. For example, if the performance is poor (P), even at 28 days, the individual may be designated N₃And remain in the novice category for selection of feedback type and valence.

Depending on the degree of success, the user may be designated as E if the objective pursuit experience exceeds 28 days₁(intermediate (M) expression), E₂(good (G) Performance) or E₃(very good (VG) performance).

After the user is assigned to one of the novice or expert categories, self-efficacy data 330 may be used to change from low (F)₁) In (F)₂) Or high (F)₃) The user's level of self-efficacy is determined. It will be understood that although only for N₃The category illustrates this stage, but this step may be implemented for any novice or expert category. The user's self-efficacy score may be obtained by providing a prompt to the user, such as through a user interface using the dVAS, to provide feedback regarding how they perceive their progress toward a goal.

Finally, the user may be assigned R₁、R₂Or R₃(low, medium and high, respectively) reaction performance level 340. Again, it will be understood that although this stage is for F only₂Categories are shown, but this step can be implemented for any self-efficacy category of any novice or expert category. The user's reaction efficacy score may be obtained by providing a prompt to the user (e.g., through a user interface) to provide feedback regarding how they perceive their progress toward the goal.

The user's self-efficacy and response efficacy scores may be obtained through a user interface via an electronic visual analog scale (eVAS) or dVAS, which may quantitatively collect user-perceived self-efficacy and response efficacy data, e.g., in response to a number of questions. Each of the self-potency and response potency scores may have three or fewer such questions, and these questions may be selected by an expert in the target area according to established criteria. The questions may be customized according to the implementation of the system.

Thus, the user, and more particularly the experience level of the user, may be scored across three dimensions to derive the best choice of feedback titer and feedback type. In the example shown in FIG. 3, there may be 54 different user profiles. For example, if the user's score is E₁F₃R₂Then the user is an early expert (with moderate success in achieving the goal after more than 28 days) with a high self-efficacy score and a moderate level response efficacy score. In this case, the user may be provided with informative feedback with negative valence while attempting to enhance the reaction efficacy at a lower level using reaction efficacy boost.

For having low self-potency (F)₁) And/or low reaction efficiency (R)₁) Additional boost may be provided by feedback. For example, the boost may take the form of encouraging information, intended to enhance user confidence. The implementation of the lifting may vary depending on the implementation of the system.

The following are examples of how the above-described system may be implemented.

The above-described system may be incorporated into a weight loss application (e.g., on a user's smart phone or other smart device) as an add-on module, or may be included within a native application framework.

The user may be prompted to connect the application to available sensors within the smartphone and/or within the fitness tracker (or smart watch) or any of a variety of such devices. The system may be configured to synchronize with the target setting and feedback functions of existing applications.

The phase and state detection module may collect user engagement data (such as active time when pursuing a goal) as well as success data from existing tracking and/or monitoring functions of the application. These data can be used to maintain a continuous assessment of the user phase. Additionally, at predetermined time intervals (such as once every two weeks, but may be adjusted), after the automatic prompt is provided via the push notification, the user's status (self-efficacy and reactive efficacy scores) may be evaluated using the eVAS questionnaire method and completed by manual input by the user.

These data may then be sent to a feedback type and valence selector module of the feedback management unit, which uses a set of rules such as those described above to select the appropriate feedback content for the current stage and state of the user.

In addition to the phase and state detection module, the emotion predictor unit may also use user sensor inputs and algorithms to record a continuous assessment of the user's emotional state over time. These emotional state data may then be periodically sent to the feedback trigger module.

The feedback trigger module may provide feedback to the user when the selected feedback type and valence and the coinciding emotional state satisfy the trigger criteria.

For example, users who have recently begun (novice) to use a weight loss application or weight management program will typically receive verification-type feedback with a clear positive valence only when they establish their own positive mood for commitment to weight targets (to encourage reinforcement learning). This approach can enhance motivation and drive continued weight loss efforts.

Over time and with good records in achieving early goals and metrics, users may be upgraded to the expert stage. In this regard, the feedback type may contain a large amount of information, with varying degrees of detail based on the user's level of expertise (1, 2, or 3). The feedback may have a negative valence to better motivate the user at this stage. Since feedback has a negative valence, it should be delivered in positive mood, so that cognitive resources are available to properly process information, and ensure that the required gap and details of action are fully internalized, and motivation is enhanced.

This is achieved by controlling the trigger to provide the correct type of feedback based on the mood prediction of the user.

Fig. 4 illustrates a method 400 for generating user-specific feedback for a user.

The method begins by obtaining 410 user data, for example, via a user sensor located in a user's smart device, and obtaining 420 a user profile that includes a user goal and a user experience level related to an amount of time the user has been pursuing the user goal.

An emotion prediction is then generated 430 based on the acquired user data, and a feedback type and feedback titer are selected 440 based on the target phase and emotion prediction.

Feedback is generated 450 based on the selected feedback type and feedback titer, and the generated feedback is provided 460 to the user.

Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. If a computer program is discussed above, it may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the internet or other wired or wireless telecommunication systems. If the term "adapted" is used in the claims or the description, it is to be noted that the term "adapted" is intended to be equivalent to the term "configured to". Any reference signs in the claims shall not be construed as limiting the scope.