CN112015242B - Intelligent reward method and system with active triggering - Google Patents
Intelligent reward method and system with active triggering Download PDFInfo
- Publication number
- CN112015242B CN112015242B CN202011177469.4A CN202011177469A CN112015242B CN 112015242 B CN112015242 B CN 112015242B CN 202011177469 A CN202011177469 A CN 202011177469A CN 112015242 B CN112015242 B CN 112015242B
- Authority
- CN
- China
- Prior art keywords
- time
- reward
- read
- preset
- write
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/163—Wearable computers, e.g. on a belt
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
Abstract
The invention provides an active triggering intelligent reward method and system, wherein the method comprises the following steps: monitoring the reading and writing postures of a user wearing the smart watch in real time; recording the read-write posture, and determining the compliant read-write time of the read-write posture; acquiring matched compliance scores based on compliance read-write time; according to a reward mechanism preset by parents at the parental level and in combination with compliance scores, actively triggering to acquire reward information and pushing the reward information to a smart watch for displaying. The reading and writing postures are obtained through supervision, and the compliance time is determined, so that corresponding rewards are actively triggered and obtained, and the enthusiasm and interestingness of using the intelligent watch are improved.
Description
Technical Field
The invention relates to the technical field of intelligent supervision, in particular to an actively triggered intelligent reward method and system.
Background
The intelligent child watch is a novel wearable device, combines the latest IT technology with the traditional watch function, and has the advantages of convenience in carrying, easiness in use, rich functions and the like. Therefore, the intelligent child watch is widely applied to supervision of students, but if the students are simply supervised by the intelligent child watch, such as supervision of reading and writing postures, the students can feel tired in the past, and in order to avoid the phenomenon that the intelligent child watch is used as an appliance for supervising children and the phenomenon that the children conflict and use products tiredly, the invention provides an actively-triggered intelligent reward method and system.
Disclosure of Invention
The invention provides an actively triggered intelligent reward method and system, which are used for actively triggering and obtaining corresponding reward by monitoring and obtaining read-write postures and determining compliance time, so that the enthusiasm and the interestingness of using an intelligent watch are improved.
The invention provides an actively triggered intelligent reward method, which comprises the following steps:
monitoring the reading and writing postures of a user wearing the smart watch in real time;
recording the read-write gesture, and determining the compliant read-write time of the read-write gesture;
acquiring matched compliance scores based on the compliance read-write time;
according to a reward mechanism preset by parents at the chief's end and in combination with the compliance score, actively triggering and acquiring reward information, and pushing the reward information to the intelligent watch for displaying.
In one possible way of realisation,
the step of monitoring the reading and writing postures of the user wearing the smart watch in real time comprises the following steps:
monitoring the read-write attitude image and the read-write attitude information of the user at each time point based on the timestamp;
performing space splitting on the read-write attitude image at each time point, dividing the read-write attitude image into a plurality of subspaces, and determining the current state of the target part of the user corresponding to each subspace;
determining point information at each time point based on the read-write attitude information, splitting the point information, and acquiring current information of a target part of the user;
and performing fusion processing on the current state and the current information of the same time point and the same target part, determining the read-write gesture of the corresponding target part, and acquiring the read-write gesture of the user.
In one possible way of realisation,
recording the read-write gesture, and determining the compliant read-write time of the read-write gesture comprises the following steps:
judging whether the recorded read-write gesture meets preset constraint conditions at each time point;
if yes, judging that the reading and writing posture is qualified, and acquiring corresponding compliance reading and writing time;
otherwise, performing first calibration on the corresponding first time point meeting the preset constraint condition, and performing second calibration on the remaining time point serving as a second time point;
determining the effective time accumulated sum of a first time point for carrying out first calibration and determining the ineffective time accumulated sum of a second time point for carrying out second calibration;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is larger than a first preset ratio, judging that the reading and writing posture is qualified, and taking the effective time accumulated sum as the compliant reading and writing time;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is smaller than a second preset ratio, judging that the reading and writing posture is unqualified, and defaulting the corresponding compliance reading and writing time to be zero, wherein the first preset ratio is larger than the second preset ratio;
if the ratio of the effective time accumulated sum to the ineffective time accumulated sum is larger than or equal to a second preset ratio and smaller than or equal to a first preset ratio, extracting a random time period of a first time point for first calibration, and determining whether the hand gesture of the user changes in the random time period;
if the change occurs, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time;
if not, monitoring whether the eye posture of the user is always in an eye closing state within the random time period;
if so, judging that a false gesture exists, if the ratio of the difference value of the effective time accumulation and the time sum of different random time periods to the invalid time accumulation sum is greater than or equal to a second preset ratio, taking the corresponding difference value as the compliance read-write time, and if not, defaulting the corresponding compliance read-write time to be zero;
otherwise, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time.
In one possible way of realisation,
based on the compliance read-write time, the step of obtaining the matched compliance score comprises the following steps:
acquiring the total duration of the compliance read-write time within a preset time;
matching and obtaining a compliance score related to the total duration based on a time score matching database.
In one possible way of realisation,
according to a reward mechanism preset by a parent at the keeper end and in combination with the compliance score, the step of actively triggering and acquiring reward information comprises the following steps:
acquiring a preset reward mechanism, and converting the compliance score based on the reward mechanism to acquire a trigger instruction;
and acquiring corresponding reward information based on the trigger instruction.
In one possible implementation manner, the method further includes:
pushing prizes to be awarded to the smart watch, and meanwhile, obtaining implementation conditions of each prize to be awarded, wherein the implementation conditions are related to the compliance reading and writing time and a reward mechanism set by a captain terminal;
receiving a prize to be awarded selected by the user based on the smart watch, and comparing preset read-write time of corresponding realization conditions with current compliance read-write time of the user;
meanwhile, obtaining the starting reward time and the ending reward time of the prize to be rewarded corresponding to the realization condition;
pushing a task list to the smart watch according to the comparison result, the starting reward time and the ending reward time, wherein the task list comprises a plurality of execution modes;
meanwhile, based on the execution method, the time for the user to obtain the prize to be awarded is estimated, and the execution method and the corresponding estimated time are pushed to the smart watch to be displayed;
and meanwhile, the execution mode selected by the user is also obtained, and reminding information is sent to the intelligent watch according to the corresponding reminding rule.
In a possible implementation manner, the step of determining whether the recorded read-write gesture satisfies a preset constraint condition at each time point includes:
acquiring the current pose of the user at the same time point from a plurality of orientation captures based on a preset monitoring component;
constructing pose matrixes in different directions based on the current pose;
based on a component database, extracting correction parameters related to the monitoring component, carrying out orientation splitting processing on the correction parameters to obtain correction subsets in corresponding orientations, and constructing correction vectors based on the correction subsets;
and based on the correction vector, correcting the corresponding pose matrix, wherein the correcting step comprises the following steps:
determining a first weight value of the correction vector, and determining a second weight value of each row vector in the corresponding pose matrix;
the correction vector corrects each row vector in the corresponding pose matrix based on the first weight value and the second weight value;
identifying the pose matrix after the correction processing based on a preset pose identification model, and determining whether each row of vectors and the whole matrix in the pose matrix after the correction processing are qualified or not according to an identification processing result;
if the user is in compliance, judging that the current pose of the user meets a preset constraint condition;
otherwise, extracting a difference vector based on the pose matrix after correction, constructing a difference matrix, calculating a characteristic value of each row of vectors in the difference matrix, and inputting the characteristic value into the pose identification model;
if all the characteristic values are qualified, judging that the current pose of the user meets a preset constraint condition;
and if not, judging that the current pose of the user does not meet the preset constraint condition, and simultaneously extracting the current pose image corresponding to the row vector of the characteristic value related to unqualified identification, and transmitting and displaying the current pose image.
In a possible implementation manner, in a process of actively triggering and acquiring reward information according to a reward mechanism preset by a parent at a parental side and in combination with the compliance score, the method further includes:
optimizing and adjusting a reward mechanism preset by parents of the keeper, wherein the method comprises the following steps:
acquiring each mechanism index of the reward mechanism, and determining an index weight value of each mechanism index;
acquiring various feedback indexes of the user of the smart watch bound with the parent end to the reward mechanism;
acquiring historical behavior information of the user, preprocessing the historical behavior information, and calculating matching values of the preprocessing result and various feedback indexes according to the preprocessing result and the following formula;
wherein the content of the first and second substances,
the matching value of the preprocessing result and the ith feedback index is shown, and the value range of i is [1, n ]](ii) a n1 represents the total number of behavior classifications of the corresponding preprocessing results after the historical behavior information is preprocessed;
a behavior weight value representing the jth class of behavior;
a behavior valid value representing a jth class behavior;
an index effective value representing the ith feedback index;
the adjustment factor related to the ith feedback index is represented, and the value range is [0.01,0.26 ]](ii) a m1 represents the total number of behavior gesture actions contained in the j-th class of behaviors;
representing an action effective value corresponding to the k-th action posture action;
represents the maximum action effective value;
representing a minimum action effective value;
comparing the obtained matching value with a corresponding preset value, screening the corresponding feedback index when the matching value is greater than or equal to the preset value, otherwise, judging whether the corresponding feedback index is rejected or not based on the determined index weight value of each mechanism index;
and optimizing the reward mechanism based on the judgment result and according to all the screened feedback indexes to obtain a new reward mechanism, and actively triggering to obtain reward information according to the new reward mechanism and in combination with the compliance score.
In one possible implementation manner, the method further includes:
the smart watch initiatively defaults all users wearing the smart watch in a preset distance range to mutually add friends based on an NFC communication technology;
or when the approaching distance between the users wearing the smart watch is smaller than or equal to a preset boundary value, automatically adding friends through an NFC communication technology.
The invention provides an actively triggered intelligent reward system, which comprises:
the monitoring module is used for monitoring the reading and writing postures of a user wearing the intelligent watch in real time;
the recording module is used for recording the reading and writing posture and determining the compliant reading and writing time of the reading and writing posture;
the obtaining module is used for obtaining matched compliance scores based on the compliance reading and writing time;
and the trigger module is used for actively triggering and acquiring reward information according to a reward mechanism preset by parents at the head of the household and combining the compliance score, and pushing the reward information to the intelligent watch for displaying.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart illustrating an actively triggered intelligent reward method according to an embodiment of the present invention;
FIG. 2 is a block diagram of an actively triggered smart bonus system in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an actively triggered intelligent reward method, as shown in fig. 1, comprising:
step 1: monitoring the reading and writing postures of a user wearing the smart watch in real time;
step 2: recording the read-write gesture, and determining the compliant read-write time of the read-write gesture;
and step 3: acquiring matched compliance scores based on the compliance read-write time;
and 4, step 4: according to a reward mechanism preset by parents at the chief's end and in combination with the compliance score, actively triggering and acquiring reward information, and pushing the reward information to the intelligent watch for displaying.
The beneficial effects of the above technical scheme are: the method and the device are used for actively triggering and obtaining the corresponding reward by monitoring and obtaining the read-write gesture and determining the compliance time, so that the enthusiasm and the interestingness of using the intelligent watch are improved.
The invention provides an actively triggered intelligent reward method, which comprises the following steps of monitoring the reading and writing postures of a user wearing an intelligent watch in real time:
monitoring the read-write attitude image and the read-write attitude information of the user at each time point based on the timestamp;
performing space splitting on the read-write attitude image at each time point, dividing the read-write attitude image into a plurality of subspaces, and determining the current state of the target part of the user corresponding to each subspace;
determining point information at each time point based on the read-write attitude information, splitting the point information, and acquiring current information of a target part of the user;
and performing fusion processing on the current state and the current information of the same time point and the same target part, determining the read-write gesture of the corresponding target part, and acquiring the read-write gesture of the user.
In this embodiment, the reading and writing posture image may be acquired by a camera, and the spatial splitting is performed to split the reading and writing posture image into limb movements to determine the current state of the user;
in this embodiment, the acquisition of the read-write attitude information may be performed by acquiring through a gyroscope and a displacement sensor, and the information splitting is performed to verify the current state of the target portion corresponding to the acquired same time point.
The beneficial effects of the above technical scheme are: by acquiring the information of the two at the same time point and fusing the information of the two, the accuracy of determining the read-write posture is improved, and a data basis is provided for subsequent awards.
The invention provides an actively triggered intelligent reward method, which comprises the following steps of recording the read-write gesture and determining the compliant read-write time of the read-write gesture:
judging whether the recorded read-write gesture meets preset constraint conditions at each time point;
if yes, judging that the reading and writing posture is qualified, and acquiring corresponding compliance reading and writing time;
otherwise, performing first calibration on the corresponding first time point meeting the preset constraint condition, and performing second calibration on the remaining time point serving as a second time point;
determining the effective time accumulated sum of a first time point for carrying out first calibration and determining the ineffective time accumulated sum of a second time point for carrying out second calibration;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is larger than a first preset ratio, judging that the reading and writing posture is qualified, and taking the effective time accumulated sum as the compliant reading and writing time;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is smaller than a second preset ratio, judging that the reading and writing posture is unqualified, and defaulting the corresponding compliance reading and writing time to be zero, wherein the first preset ratio is larger than the second preset ratio;
if the ratio of the effective time accumulated sum to the ineffective time accumulated sum is larger than or equal to a second preset ratio and smaller than or equal to a first preset ratio, extracting a random time period of a first time point for first calibration, and determining whether the hand gesture of the user changes in the random time period;
if the change occurs, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time;
if not, monitoring whether the eye posture of the user is always in an eye closing state within the random time period;
if so, judging that a false gesture exists, if the ratio of the difference value of the effective time accumulation and the time sum of different random time periods to the invalid time accumulation sum is greater than or equal to a second preset ratio, taking the corresponding difference value as the compliance read-write time, and if not, defaulting the corresponding compliance read-write time to be zero;
otherwise, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time.
In this embodiment, the predetermined constraint conditions include, for example, the head is more than 30CM away from the desk, the waist and the head are approximately perpendicular to the desk, the left hand is placed flat on the desk, and the right hand is in a writing or flat state.
In this embodiment, the first calibration and the second calibration may be highlight calibration or the like.
In this embodiment, the first preset ratio is, for example, a value greater than 1.5, the second preset ratio is, for example, a value greater than 1, and the second preset value is smaller than the first preset value.
In this embodiment, the random time period may be 3-5S;
in this embodiment, the hand gesture is, for example, that the user is in a writing state or the like;
in this embodiment, the eye posture is monitored to avoid a pseudo sleep posture of the user during reading and writing, that is, the reading and writing posture is standard, but the user is in a sleep state.
The beneficial effects of the above technical scheme are: the first calibration and the second calibration are used for obtaining the valid time and the invalid time, the ratio of the first calibration to the second calibration is used for determining the reading and writing time of the compliance, the ratio of the first calibration to the second calibration is specifically analyzed, and then the accurate determination of the reading and writing time of the compliance is further improved by combining the specific analysis with the pseudo posture.
The invention provides an actively triggered intelligent reward method, which comprises the following steps of obtaining matched compliance scores based on compliance read-write time:
acquiring the total duration of the compliance read-write time within a preset time;
matching and obtaining a compliance score related to the total duration based on a time score matching database.
In this embodiment, since the reward mechanisms set by different parents are different, a time score matching database needs to be set to match and obtain the corresponding compliance score.
The beneficial effects of the above technical scheme are: the corresponding compliance score can be conveniently matched and obtained, and the pertinence and the effectiveness of the reward are improved.
The invention provides an actively triggered intelligent reward method, which actively triggers and acquires reward information according to a reward mechanism preset by a parent at a household end and in combination with a compliance score, and comprises the following steps:
acquiring a preset reward mechanism, and converting the compliance score based on the reward mechanism to acquire a trigger instruction;
and acquiring corresponding reward information based on the trigger instruction.
In this embodiment, for example, children K0-K6 (toddler to elementary 6 years) who may obtain a corresponding match score at compliant read-write times during school;
the corresponding reward information is other reward information such as stationery, toys and the like;
in this embodiment, the predetermined reward mechanism, for example, the parents at the parental side set different step rewards for the children according to the number of compliant days. If the continuous compliance reading and writing is carried out for 1 day, 3 days, 7 days and 30 days, different step rewards can be obtained respectively;
a step reward scheme can also be set according to the time length of the compliance reading and writing hours, for example, different step rewards are obtained by continuously performing the compliance reading and writing for 3 hours, 15 hours, 30 hours and 100 hours;
meanwhile, the reward can also be the title number of 'yearly healthy sunshine juvenile' issued by departments such as schools, classes, education and the like;
or the combination of the above reward means;
meanwhile, the bonus condition for the existence of the bonus mechanism may be set to: after the statistical scores of the child compliance reading and writing duration meet the corresponding conditions, the materials such as stationery, toys and the like can be donated for the children in the poor mountain areas.
The prize related to the reward information can be obtained from an online shop of stationery, toys and other articles opened on the platform by an external merchant, or can be obtained from an online shopping mall of stationery, stationery and other articles which run on the platform.
In this embodiment, after the compliance reading and writing data score of the child is converted into the equivalent prize, the parent can pay for the prize through the parent, and the platform is express-delivered to the parent.
The beneficial effects of the above technical scheme are: by setting up a reward mechanism by parents at the head of the family, the enthusiasm of the read-write posture compliance of the children can be pertinently improved, and the reward randomness is improved.
The invention provides an actively triggered intelligent reward method, which further comprises the following steps:
pushing prizes to be awarded to the smart watch, and meanwhile, obtaining implementation conditions of each prize to be awarded, wherein the implementation conditions are related to the compliance reading and writing time and a reward mechanism set by a captain terminal;
receiving a prize to be awarded selected by the user based on the smart watch, and comparing preset read-write time of corresponding realization conditions with current compliance read-write time of the user;
meanwhile, obtaining the starting reward time and the ending reward time of the prize to be rewarded corresponding to the realization condition;
pushing a task list to the smart watch according to the comparison result, the starting reward time and the ending reward time, wherein the task list comprises a plurality of execution modes;
meanwhile, based on the execution method, the time for the user to obtain the prize to be awarded is estimated, and the execution method and the corresponding estimated time are pushed to the smart watch to be displayed;
and meanwhile, the execution mode selected by the user is also obtained, and reminding information is sent to the intelligent watch according to the corresponding reminding rule.
In this embodiment, the execution mode includes at least one mode that can obtain the prize required by the user.
The beneficial effects of the above technical scheme are: through the mode of independently propelling movement, the user of being convenient for selects the prize that needs, improves user's enthusiasm, and through a plurality of execution modes of propelling movement, the user of being convenient for selects, and guarantees that the user can effectual execution, improves the efficiency of obtaining the prize, through sending the information of reminding, is convenient for remind the user, obtains the progress of prize.
The invention provides an actively triggered intelligent reward method, which comprises the following steps of judging whether the recorded read-write gesture meets preset constraint conditions at each time point:
acquiring the current pose of the user at the same time point from a plurality of orientation captures based on a preset monitoring component;
constructing pose matrixes in different directions based on the current pose;
based on a component database, extracting correction parameters related to the monitoring component, carrying out orientation splitting processing on the correction parameters to obtain correction subsets in corresponding orientations, and constructing correction vectors based on the correction subsets;
and based on the correction vector, correcting the corresponding pose matrix, wherein the correcting step comprises the following steps:
determining a first weight value of the correction vector, and determining a second weight value of each row vector in the corresponding pose matrix;
the correction vector corrects each row vector in the corresponding pose matrix based on the first weight value and the second weight value;
identifying the pose matrix after the correction processing based on a preset pose identification model, and determining whether each row of vectors and the whole matrix in the pose matrix after the correction processing are qualified or not according to an identification processing result;
if the user is in compliance, judging that the current pose of the user meets a preset constraint condition;
otherwise, extracting a difference vector based on the pose matrix after correction, constructing a difference matrix, calculating a characteristic value of each row of vectors in the difference matrix, and inputting the characteristic value into the pose identification model;
if all the characteristic values are qualified, judging that the current pose of the user meets a preset constraint condition;
and if not, judging that the current pose of the user does not meet the preset constraint condition, and simultaneously extracting the current pose image corresponding to the row vector of the characteristic value related to unqualified identification, and transmitting and displaying the current pose image.
In this embodiment, the monitoring component may be implemented as any one or a combination of a camera, a laser radar, a millimeter wave radar, and the like.
In this embodiment, the modified parameters are parameters related to the operation of the monitoring assembly itself, and include parameters corresponding to different orientations.
In the embodiment, whether the pose matrix is qualified or not is judged by identifying each row vector and the whole matrix in the pose matrix after correction, and when the pose matrix is qualified in the first identification, the constraint condition can be considered to be met.
In this embodiment, whether the constraint condition is satisfied is determined finely by extracting the feature value of each row of vectors in the disparity vector and performing discrimination again.
The beneficial effects of the above technical scheme are: the current pose of the same time point is captured from a plurality of directions, effective judgment of the current learned pose is facilitated, error influence caused by a device is eliminated by acquiring a correction vector of a monitoring assembly, whether constraint conditions are met or not is facilitated to judge by identifying a pose matrix after correction, and validity of whether the constraint conditions are met or not is further improved by extracting a difference vector and identifying corresponding characteristic values, so that the current pose is facilitated to be effectively judged, and validity of actively triggering and obtaining reward information is indirectly improved.
The invention provides an actively triggered intelligent reward method, which actively triggers the process of obtaining reward information according to a reward mechanism preset by a parent at a household end and in combination with the compliance score, and further comprises the following steps:
optimizing and adjusting a reward mechanism preset by parents of the keeper, wherein the method comprises the following steps:
acquiring each mechanism index of the reward mechanism, and determining an index weight value of each mechanism index;
acquiring various feedback indexes of the user of the smart watch bound with the parent end to the reward mechanism;
acquiring historical behavior information of the user, preprocessing the historical behavior information, and calculating matching values of the preprocessing result and various feedback indexes according to the preprocessing result and the following formula;
wherein the content of the first and second substances,
the matching value of the preprocessing result and the ith feedback index is shown, and the value range of i is [1, n ]](ii) a n1 represents the total number of behavior classifications of the corresponding preprocessing results after the historical behavior information is preprocessed;
a behavior weight value representing the jth class of behavior;
a behavior valid value representing a jth class behavior;
an index effective value representing the ith feedback index;
the adjustment factor related to the ith feedback index is represented, and the value range is [0.01,0.26 ]](ii) a m1 represents the total number of behavior gesture actions contained in the j-th class of behaviors;
represents the k-th actionAn action effective value corresponding to the gesture action;
represents the maximum action effective value;
representing a minimum action effective value;
comparing the obtained matching value with a corresponding preset value, screening the corresponding feedback index when the matching value is greater than or equal to the preset value, otherwise, judging whether the corresponding feedback index is rejected or not based on the determined index weight value of each mechanism index;
and optimizing the reward mechanism based on the judgment result and according to all the screened feedback indexes to obtain a new reward mechanism, and actively triggering to obtain reward information according to the new reward mechanism and in combination with the compliance score.
In this embodiment, the feedback index is related to the normal reading and writing information of the user, and the historical behavior information is also related to the normal learning information of the user.
In this embodiment, the preprocessing may be a cluster analysis of historical behavior information.
The preset value in this embodiment is preset.
The beneficial effects of the above technical scheme are: the method comprises the steps of calculating a matching value of a feedback index according to a formula by obtaining the feedback index and historical behavior information of a user, then comparing the matching value with a preset value to screen the feedback index, judging whether the feedback index is removed or not based on an index weighted value, and finally optimizing a reward mechanism level according to a judgment result and the screened feedback index, so that the accuracy and the efficiency of actively triggering and obtaining reward information are improved, and the enthusiasm of the user is facilitated.
The invention provides an actively triggered intelligent reward method, which further comprises the following steps:
the smart watch initiatively defaults all users wearing the smart watch in a preset distance range to mutually add friends based on an NFC communication technology;
or when the approaching distance between the users wearing the smart watch is smaller than or equal to a preset boundary value, automatically adding friends through an NFC communication technology.
In this embodiment, based on the social relationship between college students, the system may actively add all users using the eye-protecting posture-correcting child smart watch within a preset distance range as friends by actively searching each other and taking the class as a unit based on the NFC near-field communication technology.
Similarly, the user can enable the two intelligent watch terminals to approach to the preset value, and friends are automatically added through NFC communication.
The beneficial effects of the above technical scheme are: the smart watch is actively used for searching through NFC, the system actively and automatically adds the smart watch to be friends, complex operation of adding friends to a narrow screen is omitted in social scenes of classes and acquaintances, and user experience is effectively improved.
The present invention provides an actively triggered intelligent reward system, as shown in fig. 2, including:
the monitoring module is used for monitoring the reading and writing postures of a user wearing the intelligent watch in real time;
the recording module is used for recording the reading and writing posture and determining the compliant reading and writing time of the reading and writing posture;
the obtaining module is used for obtaining matched compliance scores based on the compliance reading and writing time;
and the trigger module is used for actively triggering and acquiring reward information according to a reward mechanism preset by parents at the head of the household and combining the compliance score, and pushing the reward information to the intelligent watch for displaying.
Based on this intelligent bonus system, still include:
acquiring compliance scores of all users wearing the intelligent watch in a target area;
and performing PK and evaluation on the compliance scores of all users in the corresponding region results by performing region division on the target region, and pushing the evaluation results every day, every week, every month, every school period and every year.
The regional result may be a division result in units of country, province, city, county, street, school, class, and the like.
The beneficial effects of the above technical scheme are: the method and the device are used for actively triggering and obtaining the corresponding reward by monitoring and obtaining the read-write gesture and determining the compliance time, so that the enthusiasm and the interestingness of using the intelligent watch are improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. An actively triggered smart rewards method, comprising:
monitoring the reading and writing postures of a user wearing the smart watch in real time;
recording the read-write gesture, and determining the compliant read-write time of the read-write gesture;
acquiring matched compliance scores based on the compliance read-write time;
actively triggering and acquiring reward information according to a reward mechanism preset by a parent at the parental level and in combination with the compliance score, and pushing the reward information to the smart watch for displaying;
the step of monitoring the reading and writing postures of the user wearing the smart watch in real time comprises the following steps:
monitoring the read-write attitude image and the read-write attitude information of the user at each time point based on the timestamp;
performing space splitting on the read-write attitude image at each time point, dividing the read-write attitude image into a plurality of subspaces, and determining the current state of the target part of the user corresponding to each subspace;
determining point information at each time point based on the read-write attitude information, splitting the point information, and acquiring current information of a target part of the user;
and performing fusion processing on the current state and the current information of the same time point and the same target part, determining the read-write gesture of the corresponding target part, and acquiring the read-write gesture of the user.
2. The smart rewards method of claim 1, wherein the step of recording the read-write gesture and determining a compliant read-write time for the read-write gesture comprises:
judging whether the recorded read-write gesture meets preset constraint conditions at each time point;
if yes, judging that the reading and writing posture is qualified, and acquiring corresponding compliance reading and writing time;
otherwise, performing first calibration on the corresponding first time point meeting the preset constraint condition, and performing second calibration on the remaining time point serving as a second time point;
determining the effective time accumulated sum of a first time point for carrying out first calibration and determining the ineffective time accumulated sum of a second time point for carrying out second calibration;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is larger than a first preset ratio, judging that the reading and writing posture is qualified, and taking the effective time accumulated sum as the compliant reading and writing time;
if the ratio of the effective time accumulated sum to the invalid time accumulated sum is smaller than a second preset ratio, judging that the reading and writing posture is unqualified, and defaulting the corresponding compliance reading and writing time to be zero, wherein the first preset ratio is larger than the second preset ratio;
if the ratio of the effective time accumulated sum to the ineffective time accumulated sum is larger than or equal to a second preset ratio and smaller than or equal to a first preset ratio, extracting a random time period of a first time point for first calibration, and determining whether the hand gesture of the user changes in the random time period;
if the change occurs, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time;
if not, monitoring whether the eye posture of the user is always in an eye closing state within the random time period;
if so, judging that a false gesture exists, if the ratio of the difference value of the effective time accumulation and the time sum of different random time periods to the invalid time accumulation sum is greater than or equal to a second preset ratio, taking the corresponding difference value as the compliance read-write time, and if not, defaulting the corresponding compliance read-write time to be zero;
otherwise, judging that no false gesture exists, and taking the accumulated sum of the effective time as the compliant reading and writing time.
3. The smart rewards method of claim 1, wherein the step of obtaining a matching compliance score based on the compliance read-write time comprises:
acquiring the total duration of the compliance read-write time within a preset time;
matching and obtaining a compliance score related to the total duration based on a time score matching database.
4. The intelligent reward method of claim 1, wherein the step of actively triggering to obtain reward information according to a reward mechanism preset by a parent at the parental side and in combination with the compliance score comprises:
acquiring a preset reward mechanism, and converting the compliance score based on the reward mechanism to acquire a trigger instruction;
and acquiring corresponding reward information based on the trigger instruction.
5. The smart rewards method of claim 1, further comprising:
pushing prizes to be awarded to the smart watch, and meanwhile, obtaining implementation conditions of each prize to be awarded, wherein the implementation conditions are related to the compliance reading and writing time and a reward mechanism set by a captain terminal;
receiving a prize to be awarded selected by the user based on the smart watch, and comparing preset read-write time of corresponding realization conditions with current compliance read-write time of the user;
meanwhile, obtaining the starting reward time and the ending reward time of the prize to be rewarded corresponding to the realization condition;
pushing a task list to the smart watch according to the comparison result, the starting reward time and the ending reward time, wherein the task list comprises a plurality of execution modes;
meanwhile, based on the execution method, the time for the user to obtain the prize to be awarded is estimated, and the execution method and the corresponding estimated time are pushed to the smart watch to be displayed;
and meanwhile, the execution mode selected by the user is also obtained, and reminding information is sent to the intelligent watch according to the corresponding reminding rule.
6. The smart rewarding method of claim 2, wherein the step of determining whether the recorded read-write gestures satisfy a predetermined constraint at each time point comprises:
acquiring the current pose of the user at the same time point from a plurality of orientation captures based on a preset monitoring component;
constructing pose matrixes in different directions based on the current pose;
based on a component database, extracting correction parameters related to the monitoring component, carrying out orientation splitting processing on the correction parameters to obtain correction subsets in corresponding orientations, and constructing correction vectors based on the correction subsets;
and based on the correction vector, correcting the corresponding pose matrix, wherein the correcting step comprises the following steps:
determining a first weight value of the correction vector, and determining a second weight value of each row vector in the corresponding pose matrix;
the correction vector corrects each row vector in the corresponding pose matrix based on the first weight value and the second weight value;
identifying the pose matrix after the correction processing based on a preset pose identification model, and determining whether each row of vectors and the whole matrix in the pose matrix after the correction processing are qualified or not according to an identification processing result;
if the current pose of the user is qualified, judging that the current pose of the user meets a preset constraint condition;
otherwise, extracting a difference vector based on the pose matrix after correction, constructing a difference matrix, calculating a characteristic value of each row of vectors in the difference matrix, and inputting the characteristic value into the pose identification model;
if all the characteristic values are qualified, judging that the current pose of the user meets a preset constraint condition;
and if not, judging that the current pose of the user does not meet the preset constraint condition, and simultaneously extracting the current pose image corresponding to the row vector of the characteristic value related to unqualified identification, and transmitting and displaying the current pose image.
7. The intelligent reward method according to claim 1, wherein in the process of actively triggering to obtain reward information according to a reward mechanism preset by a parent at the parental side and in combination with the compliance score, the method further comprises:
optimizing and adjusting a reward mechanism preset by parents of the keeper, wherein the method comprises the following steps:
acquiring each mechanism index of the reward mechanism, and determining an index weight value of each mechanism index;
acquiring various feedback indexes of the user of the smart watch bound with the parent end to the reward mechanism;
acquiring historical behavior information of the user, preprocessing the historical behavior information, and calculating matching values of the preprocessing result and various feedback indexes according to the preprocessing result and the following formula;
wherein the content of the first and second substances,
the matching value of the preprocessing result and the ith feedback index is shown, and the value range of i is [1, n ]](ii) a n1 represents the total number of behavior classifications of the corresponding preprocessing results after the historical behavior information is preprocessed;
a behavior weight value representing a jth class of behavior;
a behavior valid value representing a jth class behavior;
an index effective value representing the ith feedback index;
the adjustment factor related to the ith feedback index is represented, and the value range is [0.01,0.26 ]](ii) a m1 represents the total number of behavior gesture actions contained in the j-th class of behaviors;
representing an action effective value corresponding to the k-th action posture action;
represents the maximum action effective value;
representing a minimum action effective value;
comparing the obtained matching value with a corresponding preset value, screening the corresponding feedback index when the matching value is greater than or equal to the preset value, otherwise, judging whether the corresponding feedback index is rejected or not based on the determined index weight value of each mechanism index;
and optimizing the reward mechanism based on the judgment result and according to all the screened feedback indexes to obtain a new reward mechanism, and actively triggering to obtain reward information according to the new reward mechanism and in combination with the compliance score.
8. The smart rewards method of claim 1, further comprising:
the smart watch initiatively defaults all users wearing the smart watch in a preset distance range to mutually add friends based on an NFC communication technology;
or when the approaching distance between the users wearing the smart watch is smaller than or equal to a preset boundary value, automatically adding friends through an NFC communication technology.
9. An actively triggered smart rewards system, comprising:
the monitoring module is used for monitoring the reading and writing postures of a user wearing the intelligent watch in real time;
the recording module is used for recording the reading and writing posture and determining the compliant reading and writing time of the reading and writing posture;
the obtaining module is used for obtaining matched compliance scores based on the compliance reading and writing time;
and the trigger module is used for actively triggering and acquiring reward information according to a reward mechanism preset by parents at the head of the household and combining the compliance score, and pushing the reward information to the intelligent watch for displaying.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011618557.3A CN112764463B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011177469.4A CN112015242B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011614896.4A CN112698688B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011177469.4A CN112015242B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011614896.4A Division CN112698688B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011618557.3A Division CN112764463B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112015242A CN112015242A (en) | 2020-12-01 |
| CN112015242B true CN112015242B (en) | 2021-02-02 |
Family
ID=73528395
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011177469.4A Active CN112015242B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011614896.4A Active CN112698688B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011618557.3A Active CN112764463B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011614896.4A Active CN112698688B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
| CN202011618557.3A Active CN112764463B (en) | 2020-10-29 | 2020-10-29 | Intelligent reward method and system with active triggering |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN112015242B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012005A (en) * | 2021-04-15 | 2021-06-22 | 四川写正智能科技有限公司 | Method for improving platform flow stability and user activity |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079103A (en) * | 2007-06-14 | 2007-11-28 | 上海交通大学 | Human face posture identification method based on sparse Bayesian regression |
| CN110148092A (en) * | 2019-04-16 | 2019-08-20 | 无锡海鸿信息技术有限公司 | The analysis method of teenager's sitting posture based on machine vision and emotional state |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030046702A1 (en) * | 2001-09-03 | 2003-03-06 | Gen Sasaki | Program server and a receiver |
| CN103473688A (en) * | 2012-06-06 | 2013-12-25 | 飞彩科技有限公司 | Reward method based on consumer access and system thereof |
| US20140272847A1 (en) * | 2013-03-14 | 2014-09-18 | Edulock, Inc. | Method and system for integrated reward system for education related applications |
| US20140278895A1 (en) * | 2013-03-12 | 2014-09-18 | Edulock, Inc. | System and method for instruction based access to electronic computing devices |
| CN104867281A (en) * | 2015-05-11 | 2015-08-26 | 广东小天才科技有限公司 | Method and device for detecting user's sitting posture |
| CN105931436A (en) * | 2016-06-03 | 2016-09-07 | 深圳市中幼国际教育科技有限公司 | Children' writing posture correction device |
| US20190139438A1 (en) * | 2017-11-09 | 2019-05-09 | General Electric Company | System and method for guiding social interactions |
| JP2019158862A (en) * | 2018-03-12 | 2019-09-19 | パナソニックＩｐマネジメント株式会社 | Tracking device and tracking method |
| JP7267681B2 (en) * | 2018-03-30 | 2023-05-02 | 株式会社バンダイナムコエンターテインメント | REMOTE CONTROL SYSTEM, PROGRAM AND REMOTE CONTROL METHOD |
| CN111240481B (en) * | 2020-01-10 | 2021-02-09 | 鄢家厚 | Read-write distance identification method based on smart watch |
| CN111415389B (en) * | 2020-03-18 | 2023-08-29 | 清华大学 | Label-free six-dimensional object posture prediction method and device based on reinforcement learning |
| CN111415281A (en) * | 2020-03-24 | 2020-07-14 | 合肥星空物联信息科技有限公司 | Child habit formation method based on sitting posture detection |
| CN111416991B (en) * | 2020-04-28 | 2022-08-05 | Oppo（重庆）智能科技有限公司 | Special effect processing method and apparatus, and storage medium |
-
2020
- 2020-10-29 CN CN202011177469.4A patent/CN112015242B/en active Active
- 2020-10-29 CN CN202011614896.4A patent/CN112698688B/en active Active
- 2020-10-29 CN CN202011618557.3A patent/CN112764463B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079103A (en) * | 2007-06-14 | 2007-11-28 | 上海交通大学 | Human face posture identification method based on sparse Bayesian regression |
| CN110148092A (en) * | 2019-04-16 | 2019-08-20 | 无锡海鸿信息技术有限公司 | The analysis method of teenager's sitting posture based on machine vision and emotional state |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012005A (en) * | 2021-04-15 | 2021-06-22 | 四川写正智能科技有限公司 | Method for improving platform flow stability and user activity |
| CN113012005B (en) * | 2021-04-15 | 2023-07-18 | 四川写正智能科技有限公司 | Method for improving platform flow stability and user activity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112698688A (en) | 2021-04-23 |
| CN112698688B (en) | 2022-10-21 |
| CN112764463A (en) | 2021-05-07 |
| CN112015242A (en) | 2020-12-01 |
| CN112764463B (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11659050B2 (en) | Discovering signature of electronic social networks | |
| Russo | Eye fixations can save the world: A critical evaluation and a comparison between eye fixations and other information processing methodologies. | |
| Murphy | Machine learning: a probabilistic perspective | |
| Lan et al. | Behavior-Based Latent Variable Model for Learner Engagement. | |
| Peterson et al. | Effects of physical attractiveness on political beliefs | |
| CN112015242B (en) | Intelligent reward method and system with active triggering | |
| KR101612782B1 (en) | System and method to manage user reading | |
| Lalor et al. | py-irt: A scalable item response theory library for python | |
| US20070094172A1 (en) | Neural network based rating system | |
| Yang et al. | PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection | |
| Rathi et al. | Analysis of user’s learning styles and academic emotions through web usage mining | |
| Dai et al. | Longitudinal data collection to follow social network and language development dynamics at preschool | |
| Simmons et al. | Large language models as subpopulation representative models: A review | |
| Liu et al. | A Policy-Graph Approach to Explain Reinforcement Learning Agents: A Novel Policy-Graph Approach with Natural Language and Counterfactual Abstractions for Explaining Reinforcement Learning Agents | |
| CN114721572A (en) | Visual display method, device, medium, equipment and system for dream | |
| Corrigan | An investigation into machine learning solutions involving time series across different problem domains | |
| Sinha et al. | An Educational based Intelligent Student Stress Prediction using ML | |
| Moussawi et al. | Using Machine Learning to Enhance" Students' Assessment" Moodle Application | |
| Marathe et al. | Heterogeneous systems for information-variable environments (hive) | |
| KR101680241B1 (en) | Method for predicting human personality based on data regarding human position having specific data type | |
| Bydžovská | Towards Prediction and Recommendation in Higher Education | |
| Teng | Essays in applied microeconomics | |
| CN112115908B (en) | Social ability assessment method and device | |
| Goindani | Social reinforcement learning | |
| Williams | A data mining approach to rapidly learning traveler activity patterns for mobile applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |