CN110599748A - Reminding method and reminding device applying same - Google Patents
Reminding method and reminding device applying same Download PDFInfo
- Publication number
- CN110599748A CN110599748A CN201910890147.5A CN201910890147A CN110599748A CN 110599748 A CN110599748 A CN 110599748A CN 201910890147 A CN201910890147 A CN 201910890147A CN 110599748 A CN110599748 A CN 110599748A
- Authority
- CN
- China
- Prior art keywords
- notification
- user
- value
- weight
- behavior
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a reminding method and a reminding device using the same, wherein the reminding method comprises the following steps: the reminding device judges a first current user state, selects a first rule state according to the first current user state, finds out a maximum utility value corresponding to the first rule state, and determines a notification behavior of reminding items. Then, the reminding device judges the second current user state, selects a second rule state which is in accordance with the second current user state, and obtains an adjusting weight according to a relative relation between a report signal and the notification behavior transmitted by the electronic device. And finally, the reminding device obtains an updated utility value according to the adjustment weight and the maximum utility value corresponding to the second rule state, and replaces the maximum utility value corresponding to the first rule state with the updated utility value.
Description
Technical Field
The present invention relates to a reminding method and a reminding device using the same, and more particularly, to a reminding method and a reminding device using the same for determining whether to remind a user according to a current user status.
Background
At present, most reminding devices only consider the time factor. For example, when the current time reaches the set time point of the reminding event set by the user, the reminding device sends out a notification message to remind the user that the set time point is reached. However, the habit of the user is constantly changing, so it is difficult to determine whether to send the notification message according to the time.
Disclosure of Invention
The embodiment of the invention provides a reminding method and a reminding device using the same, which can improve the existing problems.
An embodiment of the invention provides a reminding method. The reminding method is used for judging whether to send out a notice to a user, and the user is provided with a sensor. The reminding method comprises the following steps. A reminding device for judging a first current user state of the user according to a sensing signal transmitted by the sensor; the reminding device selects a first rule state which is consistent with the first current user state from a plurality of rule states; the reminding device determines a first notification behavior to a reminding item according to a first maximum one of a notification utility value and a non-notification utility value corresponding to the first rule state; after a period of time, the reminding device judges a second current user state of the user according to the sensing signal transmitted by the sensor; the reminding device selects a second rule state which is consistent with the second current user state from the rule states; the reminding device obtains an adjusting weight according to a relative relation between a report signal transmitted by an electronic device and the first notification behavior, wherein the report signal is an actual behavior of the user on the reminding item; the reminding device obtains an updated utility value according to the adjustment weight and a second maximum value of the notification utility value and the non-notification utility value corresponding to the second rule state; and replacing the first maximum corresponding to the first rule state with the updated utility value.
Another embodiment of the invention provides a reminder device. The reminding device is used for judging whether to send out a notice to a user, and the user is provided with a sensor. The reminding device comprises a judging unit, a selecting unit, a notification behavior determining unit and a calculating unit. The judging unit is used for judging a first current user state of the user. The selection unit is used for selecting a first rule state corresponding to the first current user state from a plurality of rule states. The notification behavior determination unit is used for determining a first notification behavior of a reminder according to a first maximum one of a notification utility value and a non-notification utility value corresponding to the first rule state. Wherein, the judging unit is further configured to: after a period of time, judging a second current user state of the user according to the sensing signal transmitted by the sensor; the selection unit is further used for: from these rule states, a second rule state is selected that corresponds to the second current user state. The computing unit is used for: obtaining an adjustment weight according to a relative relationship between a report signal transmitted by an electronic device and the first notification behavior, wherein the report signal is an actual behavior of the user on the reminder; obtaining an updated utility value according to a second maximum one of the notification utility value and the non-notification utility value corresponding to the second rule state and the adjustment weight; and replacing the first maximum corresponding to the first rule state with the updated utility value.
In order to better understand the above and other aspects of the present invention, the following detailed description of the embodiments is made with reference to the accompanying drawings, in which:
drawings
FIG. 1 is a schematic diagram of a reminder system according to an embodiment of the invention.
Fig. 2 is a flow chart of a reminding method of the reminding device of fig. 1.
The correspondence of reference numerals to components is as follows:
10: a reminder system; 100: a reminder device; 110: a controller; 120: a judgment unit; 130: a selection unit; 140: a notification behavior decision unit; 150: a calculation unit; 160: a reminder communication unit; 200: a sensor; 300: an electronic device; 305: a body; 310: a sensor; 320: an electronic device communication unit; a: a first notification action; a': a second notification action; r: adjusting the weight; n1: a notification signal; qn(s, a): the first maximum; qn+1(s, a): renewal effectA use value; qY: sending a notification utility value; qN: not sending a notification utility value; ri、R1、R3: a rule state; s: a first rule state; s': a second rule state; s1: sensing a signal; s2: reporting the signal; s110 to S145: a step of; t1: a first time interval; t2: a second time interval; α: a learning rate; γ: a discount coefficient;: the second largest.
Detailed Description
In order to better appreciate the above and other aspects of the present invention, reference will now be made in detail to the embodiments illustrated in the accompanying drawings.
Fig. 1 is a schematic diagram of a reminder system 10 according to an embodiment of the invention. The reminder system 10 includes a reminder device 100, at least one sensor 200, and an electronic device 300. The reminder device 100 can be, for example, a portable electronic device, such as a mobile phone or a notebook computer, or can be other types of electronic devices, such as a desktop computer. The electronic device 300 may be, for example, a medicine tank, a sports apparatus (such as a treadmill), a medical examination apparatus (such as a blood pressure monitor, a weight scale, a blood sugar detector, etc.), or any other electronic device that a user needs to use in his/her range of motion.
As shown in fig. 1, at least one sensor 200 is disposed on the user to sense the position of the user and/or the physiological status of the user. The sensor 200 is, for example, a Global Positioning System (GPS) module, and can sense the location of the user. Alternatively, the sensor 200 is, for example, a physiological signal sensing module, which can sense a physiological state of the user, such as heartbeat and/or blood pressure. Alternatively, the sensor 200 is, for example, an acceleration sensor (G-sensor), which can sense the user's motion, such as the user being in a static state (e.g. lying down or standing up), or in a dynamic state (e.g. walking). In addition, the sensor 200 can be integrated into a wearable device suitable for being worn by a user, such as a bracelet, a watch, an earphone, an earring, a necklace, or a ring. In another embodiment, the sensor 200 and the reminder device 100 can be integrated into a single wearable device.
The reminder device 100 is used to determine whether to notify the user. For example, the reminder device 100 determines the first current user status of the user according to the sensing signal S1 transmitted from the sensor 200. Then, the reminder device 100 selects a first rule state corresponding to the first current user state from the plurality of rule states. Then, the reminding device 100 sends a notification utility value Q according to the first rule stateYAnd no notification utility value QNDetermines a first notification action for a reminder. Then, after a period of time, the reminder device 100 determines the second current user status of the user according to the sensing signal S1 transmitted from the sensor 200. Then, the reminding device 100 selects a second rule state corresponding to a second current user state from the rule states. Then, the reminder device 100 obtains the adjustment weight according to the relative relationship between the report signal S2 sent by the electronic device 300 and the first notification behavior, wherein the report signal S2 is the actual behavior of the user for the reminder. Then, the reminding device 100 adjusts the weight and the notification utility value Q corresponding to the second rule stateYAnd no notification utility value QNObtaining an updated utility value Qn+1(s, a). The device 100 is then alerted to update the utility value Qn+1(s, a) replacing the first maximum corresponding to the first rule state.
The reminder device 100 includes a controller 110, a determining unit 120, a selecting unit 130, a notification behavior determining unit 140, a calculating unit 150, and a reminder device communication unit 160. The controller 110 is electrically connected to the determining unit 120, the selecting unit 130, the notification behavior determining unit 140, the calculating unit 150 and the reminder communication unit 160, so as to control these units in a unified manner. In one embodiment, at least two of the controller 110, the determining unit 120, the selecting unit 130, the notification behavior determining unit 140, the calculating unit 150 and the reminder communicating unit 160 may be integrated into a single unit. The controller 110, the determining unit 120, the selecting unit 130, the notification behavior determining unit 140, the calculating unit 150 and the reminder communicating unit 160 may adopt a physical circuit structure formed by a semiconductor process. The reminder device communication unit 160 is, for example, a wireless communication module, such as a Wi-Fi communication module, a Bluetooth communication module, or a communication module supporting other communication protocols.
The following is a detailed implementation of the reminder device 1001 according to the embodiment of the present invention illustrated in fig. 2. Fig. 2 is a flowchart of a reminding method of the reminding device 100 of fig. 1.
In step S110, the determining unit 120 determines the first current user status of the user according to the sensing signal S1 transmitted from the sensor 200. As shown in the following table one, the current user status includes "location of the user", "physiological status of the user (e.g., walking, still or sleeping)", "current time", "whether the current time belongs to a work day", "whether the user is in a meeting", "actual behavior of the user in the first time interval T1 (e.g., whether the electronic device 300 has been used) and/or" first notification behavior in the second time interval T2 (e.g., whether the notification device 100 has sent out "). However, the present invention is not limited to the type of the current user status, and the current user status may include other types depending on the actual application.
Watch 1
In one embodiment, the reminder device 100 can learn the user's habits by using reinforcement learning (e.g., Q-learning), which can also be referred to as Q-Table.
In an embodiment, the determining unit 120 may be configured to: (1) acquiring the position of the user according to the signal transmitted by the GPS module; (2) acquiring the physiological status of the user according to the sensing signal transmitted by the physiological signal sensing module; (3) the current time is known from the clock of the user worn personal device or the clock of the reminder device 100 itself; (4) judging whether the current date belongs to the working day; (5) whether the user is in the meeting or not is determined according to the calendar, the current time and the current date in the reminding device 100; (6) determining whether the user has used the electronic device 300 within a first time interval T1 according to a report signal S2 of the electronic device 300; and (7) according to the signal of the notification behavior determination unit 140, determining whether the reminder device 100 has sent a notification within the second time interval T2.
The electronic device 300 includes a main body 305, a sensor 310 and an electronic device communication unit 320, wherein the sensor 310 and the electronic device communication unit 320 are disposed on the main body 305, and the sensor 310 can sense whether the main body 305 is used. When the main body 305 is used, the sensor 310 sends a signal to the electronic device communication unit 320, and the electronic device communication unit 320 sends a signal S2 back to the reminder device communication unit 160 of the reminder device 100. For example, when the electronic device 300 is a canister, the sensor 310 may be disposed on a lid of the canister. When the sensor 310 senses that the lid of the medicine container is opened, the electronic device communication unit 320 transmits a report signal S2 to the reminding device communication unit 160 of the reminding device 100. For another example, when the electronic device 300 is a sports apparatus, the sensor 310 may be electrically connected to or integrated with a processor (processor) of the sports apparatus. When the sensor 310 senses that the sports equipment is used, the electronic device communication unit 320 transmits a report signal S2 to the reminder communication unit 160 of the reminder device 100. For another example, when the electronic device 300 is a medical examination apparatus, the sensor 310 may be disposed on the body of the medical examination apparatus or electrically connected to the processor of the medical examination apparatus. When the sensor 310 senses that the medical examination apparatus is used, the electronic device communication unit 320 transmits the report signal S2 to the reminder device communication unit 160 of the reminder device 100.
The sensor 310 is, for example, a location sensor, an acceleration sensor, or other sensors capable of sensing the use of the electronic device 300. The electronic device communication unit 320 is, for example, a wireless communication module, such as a Wi-Fi communication module, a Bluetooth communication module, or a communication module supporting other communication protocols.
In this embodiment, the "position of the user" in the first current user state is exemplified by "located in the area a", "walking" in the "physiological state of the user", the "current time" is exemplified by "6: 00", whether the "current time belongs to the work day" is exemplified by "yes", whether the user is in the meeting is exemplified by "no", whether the user has used the electronic device 300 in the first time interval T1 is exemplified by "no", and whether the reminder 100 has issued a notification in the second time interval T2 is exemplified by "no".
In step S115, referring to Table I, the selecting unit 130 selects a plurality of rule states RiA first rule state is selected that corresponds to the first current user state.
Rule State RiAre all permutations of possible scenarios for the various user status types described above. For example, as shown in table one, there are 3 cases "where the user is located", there are 3 cases "where the user's physiological status", 2 cases "whether the current date belongs to the work day", 24 cases "where the current time" belongs to (for example, 1 day is divided into 24 time periods), "2 cases" where the user is in the meeting ", 2 cases" where the user has used the electronic device 300 in the first time interval T1 ", and" where the reminder 100 has issued a notification in the second time interval T2 ", there are 2 cases. Accordingly, rule state RiA total of 3456 permutations and combinations (formula: 3 × 3 × 2 × 24 × 2 × 2 ═ 3456) can be formed. Table one lists only 14 of them. However, the rule state R is determined by the type of user state and the number of possible situationsiOther numbers of combinations may be arranged.
In this embodiment, as shown in Table I, the first current user state and the rule state R1In agreement, the selection unit 130 therefore selects the rule state R1As a first rule state.
In step S120, the notification behavior determination unit 140 determines the first rule state (the rule state R)1Example) corresponding notification utility value QYAnd no notification utility value QNDetermines a first notification behavior for the reminder. For example, as shown in table one, the notification behavior determination unit 140 determines the notification utility value Q in the first rule state (taking rule state R1 as an example)YAnd no noticeUtility value QNAnd selecting the largest of the two, e.g. not to signal the utility value QN(As shown in Table one, no notification utility value QNIs 1, is greater than the notification utility value QY0) and determines a first notification action accordingly. For example, the first maximum is the non-notification utility value QNTherefore, the notification behavior determination unit 140 does not issue any notification signal.
In another embodiment, if the first maximum is the notification utility value QYThen the notification behavior determination unit 140 sends out a notification signal N1. Although not shown, the reminder device 100 further includes an annunciator, and the annunciator sends an annunciation according to the annunciation signal N1. When the annunciator is, for example, a speaker, the annunciation is a voice or a sound. When the annunciator is, for example, a display screen, the annunciation is a character or symbol of a display screen. When the annunciator is, for example, a vibrator, the annunciation is a vibration. When the annunciator is, for example, a light emitting element, the annunciation is a light.
After the user receives the notification signal N1 (based on the first notification behavior), if the timing of sending the notification signal N1 matches the habit of the user using the electronic device 300, the user will use the electronic device 300 based on the notification signal N1 for a period of time, such as taking medicine, using sports equipment, using medical examination equipment to measure the physical status, etc. When the notification signal N1 is not issued according to the habit of the user using the electronic device 300, the user usually disregards the notification signal N1, i.e., will not use or cannot use the electronic device 300. In another case, it is also possible to remind the device 100 not to send the notification signal N1 (based on the first notification behavior), but during a period of time, the user uses the electronic device 300, such as taking medicine, using sports equipment, using medical examination equipment to measure the physical status, etc.
Therefore, after a period of time, the reminding device 100 updates the non-notification utility value Q according to the current user status of the user within a period of timeNValue of or notification utility value QYThe value of (2) is set so that the reminding mode of the reminding device 100 is more suitable for the original habit or changed habit of the user. The following furtherFor example.
In step S125, after a period of time, the determining unit 120 determines the second current user status of the user according to the sensing signal S1 transmitted from the sensor 200. The period of time may be, for example, seconds, minutes (e.g., 10 minutes, 15 minutes), or hours.
In the second current user state of the present embodiment, the "location of the user" is taken as an example of "located in the area C", the "physiological state of the user" is taken as an example of "sleep", the "current time" is taken as an example of "8: 00", the "whether the current time belongs to the work day" is taken as an example of "no", the "whether the user is in the conference" is taken as an example of "no", the "whether the user has used the electronic device 300 in the first time interval T1" is taken as an example of "yes", and the "whether the reminding device 100 has issued a notification in the second time interval T2" is taken as an example of "no".
In step S130, the selecting unit 130 selects a second rule state corresponding to the second current user state from the plurality of rule states Ri.
In the present embodiment, as shown in table one, the second current user status corresponds to the rule status R3, so the selecting unit 130 selects the rule status R3As a second rule state.
In step S135, the first notification behavior and the report signal S transmitted by the electronic device 300 are followed2The calculating unit 150 obtains the adjustment weight r.
For example, as shown in the following table two, when the relationship between the first notification behavior and the report signal S2 is "notification about reminder and actual behavior about reminder" the calculating unit 150 sets the adjustment weight r to be the first weight value. When the first notification action is "not notify about reminder item" and there is no report signal S2 (indicating that the user' S actual action is "not act on reminder item (e.g., not using the electronic device 300)), the calculating unit 150 sets the adjusting weight r to be a second weight value, wherein the first weight value is greater than the second weight value. In an embodiment, the first weight value is, for example, 0.5, and the second weight value is, for example, 0. As shown in table two, when the relationship between the first notification behavior and the report signal S2 is "no notification is given to the reminder item and the actual behavior is an action on the reminder item", the calculating unit 150 sets the adjustment weight r to be a third weight value; when the first notification action is "notification about reminder item" and there is no report signal S2 (indicating that the user' S actual action is "no action about reminder item (e.g., not using the electronic device 300)), the calculating unit 150 sets the adjustment weight r to be a fourth weight value. In an embodiment, the third weight value is equal to the fourth weight value, such as-0.5, and is smaller than the first weight value and the second weight value. In another embodiment, the third weight value and the fourth weight value may be different. In addition, as long as the first weight value, the second weight value, the third weight value and the fourth weight value conform to the foregoing relationship, the embodiment of the present invention does not limit the numerical range of the weight values.
Watch two
By adjusting the weight r, the notification behavior subsequently determined by the reminder device 100 can better conform to the habit of the user. For example, for the first notification behavior and the report signal S2The relationship (b) indicates that the first notification behavior determined by the reminder device 100 actually matches the usage habit of the user on the electronic device 300 in the current user state, and therefore, the calculating unit 150 increases the proportion of the adjustment weight r, for example, the first weight value is greater than the second weight value, the third weight value and the fourth weight value. The two cases that the first notification behavior is "not notify about reminder item" but the actual behavior of the user is "action about reminder item" and the first notification behavior is "notify about reminder item" but the actual behavior of the user is "not action about reminder item" indicate that the first notification behavior determined by the reminder device 100 does not conform to the usage habit of the user for the electronic device 300 in the current user state, so the calculating unit 150 reduces the proportion of the adjustment weight r, for example, the third weight value and the fourth weight value are both smaller than the first weight value and the second weight value.
In summary, during the actual operation of the reminder device 100, the adjustment weight r corresponding to the current user state is continuously set, so that the accuracy of the notification behavior determined by the reminder device 100 can be increased, and the notification behavior determined by the reminder device 100 in the current user state can be as good as possible in accordance with the usage habit of the user for the electronic device 300.
After using the reminder device 100 for a long time, the notification behavior determined by the reminder device 100 generally conforms to more than 80% of the usage habit of the user, i.e., when the notification behavior determined by the reminder device 100 is to issue a notification, the user has 80% of the possibility (probability or habit) to use the electronic device 300. Similarly, when the notification action determined by the reminder device 100 is not to issue a notification, the user has a 80% probability (probability or habit) not to use the electronic device 300.
Since the reminder device 100 will continue to increase the consistency between the determined notification behavior and the user's habits, each rule state R of the table one will be maintained even at the beginning of the use of the reminder device 100iIs given a notice utility value QYAnd no notification utility value QNIs any preset value, such as any preset value between 0 and 1 (inclusive). In one embodiment, rule state RiIs given a notice utility value QYAnd no notification utility value QNOne may be preset to 0 and the other to 1. As the reminding device 100 of the embodiment of the present invention continuously updates the utility value, after the reminding device 100 is used for a long time, the notification behavior determined by the reminding device 100 conforms to more than 80% of the usage habit of the user.
In step S140, as shown in the following formula (1), the calculating unit 150 adjusts the weight W and the second rule state (the rule state R in the present embodiment)3Example) corresponding notification utility value QYAnd no notification utility value QNObtaining the updated utility value Qn+1(s,a)。
Formula (1):
in the equation (1), R represents an adjustment weight, α represents a learning rate, γ represents a discount coefficient, s represents a first rule state (in this example, the rule state R1 is taken as an example), a represents the first notification behavior (in this example, the notification is not sent out), and Q represents the adjustment weightn(s, a) represents the first maximum (in this example, the non-notification utility value Q of the rule state R1NFor example), s 'represents the second rule state (in this example, rule state R3 is taken as an example), a' represents the second maximum (in this example, notification utility value Q of rule state R3 is taken as an example)YFor example) corresponding to the second notification behavior (in this example, the notification signal N1 is sent),indicates the second largest (in this case, the rule state R)3Is given a notice utility value QYFor example), and Qn+1(s, a) represents an updated utility value.
In the embodiment, the learning rate α is a predetermined value, for example, between 0 and 1, inclusive. The refraction factor γ is a predetermined value, for example, between 0 and 1, and includes the end points.
The second largest value of the learning rate alpha, the discount coefficient gammaAdjusting weights r and QnThe values of (s, a) can be obtained by the above steps, and the updated utility value Q can be obtained (calculated) after the values are substituted into the formula (1)n+1(s,a)。
In step S145, the calculation unit 150 updates the utility value Qn+1(s, a) in place of the first maximum corresponding to the first rule state (in this example, rule state R1) (in this example, rule state R)1Is not notified of the utility value QNFor example). For example, as shown in Table one, if the utility value Q is updatedn+1If (s, a) is 0.8, 0.8 is substituted for the non-notification utility value Q in the first rule state (in this example, rule state R1 is taken as an example)N. After the replacement, table one is updated as table three below. Non-notice utility value Q except for rule state R1NIn addition, other rule states RiRemain unchanged and are therefore not shown in table three.
Watch III
Next, after a period of time, the reminding apparatus 100 can obtain the rule status R according to the similar or same steps S110 to S1453The updated utility value. With this principle, after each lapse of a certain period of time, the rule states RiA notification utility value Q ofYValue of or not to notify utility value QNThe value of (d) is replaced with the updated utility value.
In one embodiment, when the reminding device 100 finds that the habit of the user changes suddenly, the rule state R of the table one can be resetiContent to relearn new habits of the user. For example, when the reminder device 100 determines that the current user status indicates that the user's location is changed (e.g., the current user status is changed to a new location that is more than several hundred kilometers away from the original location), it can send a notification signal to ask the user whether to re-enter the rule status R of the rule status RiContent, e.g. resetting rule state RiIs given a notice utility value QYAnd no notification utility value QNE.g. rule state RiIs given a notice utility value QYAnd no notification utility value QNOne is reset to 0 and the other is reset to 1. When the user agrees to reset, the reminding device 100 re-lists the rule state RiThe contents. When the user does not agree with the reset, the reminder device 100 can suspend the learning function, and when the function suspension time is over or the user returns to the original area, the reminder device 100 resumes the learning function. In another embodiment, when the reminder device 100 finds that the habit of the user changes suddenly, the reminder device 100 uniformly resets the rule state R of the table one regardless of whether the user agreesiContent or suspend the learning function.
In summary, although the present invention has been described with reference to the above embodiments, the present invention is not limited thereto. Various modifications and alterations can be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (12)
1. A reminding method is used for judging whether to send out notice to a user, and the user is provided with a sensor, and the reminding method is characterized by comprising the following steps:
a reminding device for judging a first current user state of the user according to at least one sensing signal transmitted by the sensor;
the reminding device selects a first rule state which is consistent with the first current user state from a plurality of rule states;
the reminding device determines a first notification behavior to a reminding item according to a first maximum one of a notification utility value and a non-notification utility value corresponding to the first rule state;
after a period of time, the reminding device judges a second current user state of the user according to the sensing signal transmitted by the sensor;
the reminding device selects a second rule state which is consistent with the second current user state from the rule states;
the reminding device obtains an adjusting weight according to a relative relation between a return signal transmitted by an electronic device and the first notification behavior, wherein the return signal is an actual behavior of the user on the reminding item;
the reminding device obtains an updated utility value according to the adjustment weight and a second maximum of the notification utility value and the non-notification utility value corresponding to the second rule state; and
replacing the first maximum corresponding to the first rule state with the updated utility value.
2. The method as claimed in claim 1, wherein the first current user status includes a location of the user, a physiological status of the user, a current time, whether the current time belongs to work days, whether the user is in a meeting, the actual behavior of the user in a first time interval, and/or the first notification behavior in a second time interval.
3. The method of claim 1, wherein the step of obtaining the updated utility value is performed according to equation (1), where r represents the adjustment weight, α represents a learning rate, γ represents a discount coefficient, s represents the first rule state, a represents the first notification behavior, and Q represents the first notification behaviorn(s, a) represents the first maximum, s 'represents the second rule state, a' represents a second notification behavior corresponding to the second maximum,represents the second maximum, Qn+1(s, a) represents the updated utility value;
4. the method as claimed in claim 1, wherein the step of obtaining the updated utility value comprises:
calculating a sum of the adjustment weight, the first maximum value and the second maximum value; and
and taking the sum value as the updated utility value.
5. The reminding method as claimed in claim 1, wherein the step of obtaining the adjustment weight comprises:
when the first notification behavior is that the reminder item is notified and the actual behavior is that the reminder item is acted, setting the adjustment weight as a first weight value; and
when the first notification behavior is not notifying the reminder and the actual behavior is not acting on the reminder, setting the adjustment weight as a second weight value;
wherein the first weight value is greater than the second weight value.
6. The reminding method of claim 5, wherein the step of obtaining the adjusted weight comprises:
when the first notification behavior is not notified to the reminder and the actual behavior is an action on the reminder, setting the adjustment weight as a third weight; and
when the first notification behavior is that the reminder item is notified and the actual behavior is that the reminder item does not act, setting the adjustment weight as a fourth weight value;
the third weight value is equal to the fourth weight value and is smaller than the first weight value and the second weight value.
7. A kind of reminding device, in order to judge whether to send out the notice to a user, this user disposes a perceptron, characterized by that, this reminding device includes:
a judging unit for judging a first current user state of the user;
a selecting unit for selecting a first rule state corresponding to the first current user state from a plurality of rule states;
a notification behavior determination unit for determining a first notification behavior for a reminder according to a first maximum one of a notification utility value and a non-notification utility value corresponding to the first rule state;
a computing unit;
wherein the determining unit is further configured to: after a period of time, judging a second current user state of the user according to the sensing signal transmitted by the sensor; the selection unit is further configured to: selecting a second rule state corresponding to the second current user state from the rule states; the computing unit is used for: obtaining an adjustment weight according to a relative relationship between a report signal transmitted by an electronic device and the first notification behavior, wherein the report signal is an actual behavior of the user on the reminder; obtaining an updated utility value according to a second maximum of the notification utility value and the non-notification utility value corresponding to the second rule state and the adjustment weight; and replacing the first maximum corresponding to the first rule state with the updated utility value.
8. The apparatus as claimed in claim 7, wherein the first current user status comprises a location of the user, a physical action of the user, a current time period, whether the current time period belongs to work days, whether the user is in a meeting, the actual behavior of the user in a first time interval, and/or the first notification behavior in a second time interval.
9. The warning apparatus as claimed in claim 7, wherein the computing unit is further configured to obtain the updated utility value according to equation (1);
wherein, in the formula (1), r represents the adjustment weight, α represents a learning rate, γ represents a discount coefficient, s represents the first rule state, a represents the first notification behavior, and Q represents the first rule staten(s, a) represents the first maximum, s 'represents the second rule state, a' represents a second notification behavior corresponding to the second maximum,represents the second maximum, Qn+1(s, a) represents the updated utility value;
10. the apparatus as claimed in claim 7, wherein the computing unit is further configured to:
calculating a sum of the adjustment weight, the first maximum value and the second maximum value; and
and taking the sum value as the updated utility value.
11. The apparatus as claimed in claim 7, wherein the computing unit is further configured to:
when the first notification behavior is that the reminder item is notified and the actual behavior is that the reminder item is acted, setting the adjustment weight as a first weight value;
when the first notification behavior is not notifying the reminder and the actual behavior is not acting on the reminder, setting the adjustment weight as a second weight value;
wherein the first weight value is greater than the second weight value.
12. The alert device of claim 11, wherein the computing unit is further configured to:
when the first notification behavior is not notified to the reminder and the actual behavior is an action on the reminder, setting the adjustment weight as a third weight; and
when the first notification behavior is that the reminder item is notified and the actual behavior is that the reminder item does not act, setting the adjustment weight as a fourth weight value;
the third weight value is equal to the fourth weight value and is smaller than the first weight value and the second weight value.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910890147.5A CN110599748B (en) | 2019-09-20 | 2019-09-20 | Reminding method and reminding device applying same |
| TW108146069A TWI747108B (en) | 2019-09-20 | 2019-12-16 | Reminder method and reminder device using the same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910890147.5A CN110599748B (en) | 2019-09-20 | 2019-09-20 | Reminding method and reminding device applying same |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110599748A true CN110599748A (en) | 2019-12-20 |
| CN110599748B CN110599748B (en) | 2021-05-11 |
Family
ID=68861480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910890147.5A Active CN110599748B (en) | 2019-09-20 | 2019-09-20 | Reminding method and reminding device applying same |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110599748B (en) |
| TW (1) | TWI747108B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976579A (en) * | 2015-03-13 | 2016-09-28 | 胡渐佳 | Bad learning state reminding method and reminding device |
| CN107479408A (en) * | 2017-06-20 | 2017-12-15 | 深圳市橙方智能科技有限公司 | A kind of smart machine controller and control method |
| US20170365156A1 (en) * | 2014-03-24 | 2017-12-21 | Samsung Electronics Co., Ltd. | Method of providing activity notification and device thereof |
| CN109785595A (en) * | 2019-02-26 | 2019-05-21 | 成都古河云科技有限公司 | A kind of vehicle abnormality track real-time identification method based on machine learning |
| CN110549901A (en) * | 2018-03-30 | 2019-12-10 | 比亚迪股份有限公司 | electric automobile and system and method for prompting according to user using habits of electric automobile |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106527703B (en) * | 2016-10-27 | 2021-04-23 | 北京小米移动软件有限公司 | Message reminding method and device |
| CN109145145A (en) * | 2017-06-16 | 2019-01-04 | 阿里巴巴集团控股有限公司 | A kind of data-updating method, client and electronic equipment |
| US10270899B1 (en) * | 2018-03-06 | 2019-04-23 | Titan Health & Security Technologies, Inc. | Community safety, security, health communication and emergency notification system providing emergency source tracking |
| CN109345942A (en) * | 2018-10-25 | 2019-02-15 | 重庆鲁班机器人技术研究院有限公司 | Study habit antidote, device and robot |
-
2019
- 2019-09-20 CN CN201910890147.5A patent/CN110599748B/en active Active
- 2019-12-16 TW TW108146069A patent/TWI747108B/en active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170365156A1 (en) * | 2014-03-24 | 2017-12-21 | Samsung Electronics Co., Ltd. | Method of providing activity notification and device thereof |
| CN105976579A (en) * | 2015-03-13 | 2016-09-28 | 胡渐佳 | Bad learning state reminding method and reminding device |
| CN107479408A (en) * | 2017-06-20 | 2017-12-15 | 深圳市橙方智能科技有限公司 | A kind of smart machine controller and control method |
| CN110549901A (en) * | 2018-03-30 | 2019-12-10 | 比亚迪股份有限公司 | electric automobile and system and method for prompting according to user using habits of electric automobile |
| CN109785595A (en) * | 2019-02-26 | 2019-05-21 | 成都古河云科技有限公司 | A kind of vehicle abnormality track real-time identification method based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI747108B (en) | 2021-11-21 |
| CN110599748B (en) | 2021-05-11 |
| TW202113812A (en) | 2021-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230004580A1 (en) | Data tagging | |
| CN110638421B (en) | Method, system, and apparatus for displaying visibility changes in response to user gestures | |
| US9640057B1 (en) | Personal fall detection system and method | |
| WO2011027651A1 (en) | Body movement detecting device and body movement detecting method | |
| CN106030246B (en) | The equipment that is counted for the number of cycles of the cycle movement to object, method and system | |
| US20220211271A1 (en) | Activity and context-aware prediction of stress for mobile and wearable systems | |
| AU2010231550A1 (en) | Method and system for detecting a fall of a user | |
| CN105342625B (en) | A kind of intelligence waistband and the monitoring method based on the waistband | |
| EP2820831A1 (en) | Adaptable mobile communication device functions | |
| KR20100022217A (en) | Apparatus and methods for revising living habits | |
| US20240221482A1 (en) | System, method and smart wearable device for user posture monitoring | |
| US20230294000A1 (en) | Program, method, and information processing device | |
| JP2017169732A (en) | Information processing device, and information processing method and program | |
| CN110139599A (en) | User terminal | |
| CN110599748B (en) | Reminding method and reminding device applying same | |
| JP2019069207A (en) | Drowsiness calculation device | |
| JP2014030494A (en) | System and method for improving sleep | |
| CN103654744B (en) | A kind of sleep quality monitoring method | |
| CN115316969A (en) | Body energy estimation method, wearable device and computer storage medium | |
| CN114903457A (en) | Dynamic blood pressure monitoring device and system with positive and negative correlation of human physiological parameters | |
| JP6790456B2 (en) | Biometric device and biometric method | |
| JP2020009013A (en) | Health management support device, method, and program | |
| JP2018190250A (en) | Diet support system | |
| US20230176087A1 (en) | Method for accurate and reliable detection of falls using digital motion sensors | |
| JP2005283339A (en) | Electronic pedometer |
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 |