CN113923293A

CN113923293A - Drinking reminding method and electronic equipment

Info

Publication number: CN113923293A
Application number: CN202111516921.XA
Authority: CN
Inventors: 邸皓轩; 李丹洪; 张晓武
Original assignee: Honor Device Co Ltd
Current assignee: Shanghai Glory Smart Technology Development Co ltd
Priority date: 2021-12-13
Filing date: 2021-12-13
Publication date: 2022-01-11
Anticipated expiration: 2041-12-13
Also published as: CN113923293B

Abstract

The embodiment of the application provides a water drinking reminding method and electronic equipment. In the method, the electronic equipment judges whether the user drinks water in a drinking detection period according to user behavior state information and physiological parameter change information detected in the drinking detection period. If the user does not drink water in the drinking detection period, reminding the user of drinking water when the drinking detection period is finished, and otherwise not reminding the user of drinking water. Therefore, no matter the electronic equipment is used outdoors or indoors, the electronic equipment can remind the user of drinking water in time, whether the user needs to be reminded of drinking water or not can be judged according to the behavior state information and the physiological parameter change of the user, the universality and the intelligence are high, the effect of reminding drinking water with better quality can be achieved, and the use experience of the user is improved.

Description

Drinking reminding method and electronic equipment

Technical Field

The application relates to the technical field of intelligent terminals, in particular to a drinking reminding method and electronic equipment.

Background

Water is a source of life, and sufficient water plays a great role in human health. However, as the pace of life and work increases, people often forget to drink water.

At present, in order to remind oneself of drinking water, some people rely on a water cup with a water drinking reminding function, and some people rely on an alarm clock. However, it is unlikely that the user will carry the cup at any time during daily activities, and once the user is away from the cup, the drinking reminding function thereof will be disabled. Moreover, the intelligence and flexibility of the alarm clock reminding mode are poor, and the better drinking reminding effect cannot be achieved.

Disclosure of Invention

In order to solve the technical problem, an embodiment of the application provides a drinking reminding method and an electronic device. In the method, the electronic equipment judges whether the user drinks water in a drinking detection period according to user behavior state information and physiological parameter change information detected in the drinking detection period. If the user does not drink water in the drinking detection period, reminding the user of drinking water when the drinking detection period is finished, and otherwise not reminding the user of drinking water. Therefore, no matter the electronic equipment is used outdoors or indoors, the electronic equipment can remind the user of drinking water in time, whether the user needs to be reminded of drinking water or not can be judged according to the behavior state information and the physiological parameter change of the user, the universality and the intelligence are high, the effect of reminding drinking water with better quality can be achieved, and the use experience of the user is improved.

In a first aspect, an embodiment of the present application provides a method for reminding drinking. The method comprises the following steps: the electronic equipment acquires behavior state information and physiological parameter change information of a user in a current drinking detection period; the electronic equipment judges whether the user drinks water in the current drinking detection period according to the behavior state information and the physiological parameter change information; and if the user does not drink water in the current water drinking detection period, the electronic equipment reminds the user of drinking water when the current water drinking detection period is finished. Therefore, the electronic equipment can remind the user of drinking water in time no matter outdoors or indoors. Moreover, the electronic equipment can judge whether the user needs to be reminded of drinking water according to the behavior state information and the physiological parameter change of the user, so that the accuracy of judging whether the user drinks water by the electronic equipment is improved, and the misjudgment probability is greatly reduced.

According to a first aspect, the electronic device determining whether a user has drunk water within a current drinking detection period according to behavior state information and physiological parameter change information includes: the electronic equipment matches the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence; the electronic equipment counts the sum of the confidence degrees of the drunk water corresponding to the current drinking water detection period according to the matching result; if the sum of the confidence degrees of the drunk water does not reach the preset confidence degree threshold value, the electronic equipment judges that the user does not drink water in the current drinking detection period. Therefore, the electronic equipment combines the behavior state information and the occurrence time sequence of the physiological parameter change information, counts the drinking confidence of the user in the current drinking detection period, and judges whether the user drinks water in the current drinking detection period according to the drinking confidence, so that the accuracy of the judgment result of the electronic equipment on whether the user drinks water in the current drinking detection period is improved.

According to the first aspect, or any implementation manner of the first aspect, the matching, by the electronic device, the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence includes: the electronic equipment matches the behavior state information and the physiological parameter change information stored in the state queue with a plurality of preset state transfer paths; the behavior state information and the physiological parameter change information in the state queue are arranged according to occurrence time sequence. Therefore, the electronic equipment is provided with the state queue for storing the behavior state information and/or the physiological parameter change information of the user according to the occurrence time sequence, so that the electronic equipment can conveniently count the drinking confidence of the user in the current drinking detection period by combining the occurrence time sequence of the behavior state information and the physiological parameter change information.

According to the first aspect or any one of the foregoing implementation manners of the first aspect, the counting, by the electronic device, a sum of confidence levels of the drunk water corresponding to the current drinking detection period according to the matching result includes: if the successfully matched target state transition path exists, the electronic equipment acquires the water drinking confidence coefficient of the target state transition path; wherein, each state transition path is preset with a corresponding drinking confidence; and the electronic equipment takes the accumulated sum of the drinking confidence degrees of the state transition paths of the items as the sum of the drinking confidence degrees. Therefore, the corresponding drinking confidence degrees are respectively arranged on different state transition paths, so that the accuracy of the sum of the drinking confidence degrees counted by the electronic equipment according to the matching result is higher.

According to the first aspect, or any implementation manner of the first aspect, the state transition path includes behavior state information and/or physiological parameter change information; or the state transition path comprises a plurality of user behavior state information and/or physiological parameter change information which are arranged in sequence. Therefore, the forms of the state transition paths are various, and the analysis of the behavior state information and the physiological parameter change information of the user is facilitated.

According to the first aspect, or any implementation manner of the first aspect, the acquiring, by an electronic device, behavior state information of a user of the electronic device in a current drinking detection period includes: the electronic equipment identifies the behavior state information of the user according to the relevant data acquired in real time in the current drinking detection period. Therefore, the electronic equipment identifies the behavior state information of the user according to the relevant data acquired in real time, and the reliability is high.

According to the first aspect, or any one implementation manner of the first aspect, the identifying, by the electronic device, the behavior state information of the user according to the relevant data collected in real time in the current drinking detection period includes: the electronic equipment respectively extracts the characteristics of the related data acquired in real time in the current drinking detection period to obtain at least two data characteristics; the electronic equipment performs feature fusion on at least two data features to obtain fusion features; and the electronic equipment inputs the fusion characteristics into a behavior state recognition model obtained by pre-training to obtain the behavior state information of the user output by the behavior state recognition model. Therefore, the electronic equipment identifies the behavior state information of the user by using the behavior state identification model obtained by pre-training based on a machine learning mode, and the intelligence and the accuracy are high.

According to the first aspect, or any implementation manner of the first aspect, after the electronic device obtains at least two data features, the method further includes: the electronic device performs dimensional expansion on at least one data feature. Therefore, the more the feature dimensionality is, the more accurate the feature dimensionality is, the more beneficial the behavior state recognition model learns the features with better generalization, and the recognition effect of the behavior state recognition model is improved.

According to the first aspect as such or any implementation manner of the first aspect above, the relevant data comprises acceleration data and audio data. Therefore, the intelligent watch integrates the audio features on the basis of the acceleration features, and is beneficial to effectively identifying the user behavior state information.

According to the first aspect, or any one of the above implementation manners of the first aspect, when the electronic device establishes a wireless communication connection with the water dispenser device through the wireless fidelity module, the related data includes acceleration data, audio data, and related data of a wireless fidelity signal; or when the electronic equipment establishes wireless communication connection with the water dispenser equipment through the Bluetooth module, the related data comprises acceleration data, audio data and Bluetooth signal related data. Therefore, the electronic equipment integrates audio features, Bluetooth features and/or WiFi features on the basis of the acceleration features, and effective identification of user behavior state information is facilitated.

According to the first aspect, or any implementation of the first aspect above, the audio data is desensitized audio data. Therefore, the intelligent identification does not relate to the privacy of the user when the user behavior state is identified by combining the audio data.

According to a first aspect or any implementation manner of the first aspect above, the behavior state information includes at least one of: the method comprises the following steps of opening a water cup, sitting still, walking, receiving water, wearing electronic equipment by the left hand, wearing the electronic equipment by the right hand, placing the water cup and drinking water.

According to the first aspect, or any implementation manner of the first aspect above, the physiological parameter variation information includes at least one of: body temperature is raised, pulse rate is accelerated, and blood oxygen changes.

According to the first aspect, or any one of the above implementation manners of the first aspect, the method further includes: when the current drinking detection period is finished, the electronic equipment judges whether the current time is within a preset drinking reminding time period or not; if yes, updating the current drinking detection period. Therefore, whether the user drinks water or not is periodically detected by the electronic equipment.

According to the first aspect, or any one of the above implementation manners of the first aspect, the method further includes: in response to the received first operation, the electronic device sets a start time and an end time of the drinking water reminder period. Therefore, the user can set the starting time and the ending time of the drinking reminding time period according to the personal actual condition, and the flexibility and the practicability are higher.

According to the first aspect, or any one of the above implementation manners of the first aspect, the method further includes: setting the duration of the drinking water detection period in response to the received second operation. Therefore, the user can set the duration of the drinking detection period according to the personal actual condition, and the flexibility and the practicability are higher.

According to a first aspect, or any one implementation manner of the first aspect, an electronic device performs drinking reminding for a user, including: the electronic device displays drinking reminder information, as well as vibrations and/or bells. Thus, diversification of drinking reminding modes of the electronic equipment is realized.

According to a first aspect or any one of the above implementation manners of the first aspect, the electronic device is a smart watch.

In a second aspect, an embodiment of the present application provides an electronic device. The electronic device includes: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored on the memory, which when executed by the one or more processors, cause the electronic device to perform the drinking water reminder method as claimed in any one of the first aspect and the first aspect.

Any one implementation manner of the second aspect and the second aspect corresponds to any one implementation manner of the first aspect and the first aspect, respectively. For technical effects corresponding to any one implementation manner of the second aspect and the second aspect, reference may be made to the technical effects corresponding to any one implementation manner of the first aspect and the first aspect, and details are not repeated here.

In a third aspect, an embodiment of the present application provides an electronic device. The electronic device includes: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored on the memory, and when executed by the one or more processors, cause the electronic device to perform the steps of: the method comprises the steps that the electronic equipment acquires behavior state information and physiological parameter change information of a user in a current drinking detection period; the electronic equipment judges whether the user drinks water in the current drinking detection period according to the behavior state information and the physiological parameter change information; and if the user does not drink water in the current water drinking detection period, the electronic equipment reminds the user of drinking water when the current water drinking detection period is finished.

According to a third aspect, the computer program, when executed by one or more processors, causes an electronic device to perform the steps of: the electronic equipment matches the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence; the electronic equipment counts the sum of the confidence degrees of the drunk water corresponding to the current drinking water detection period according to the matching result; if the sum of the confidence degrees of the drunk water does not reach the preset confidence degree threshold value, the electronic equipment judges that the user does not drink water in the current drinking detection period.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: the electronic equipment matches the behavior state information and the physiological parameter change information stored in the state queue with a plurality of preset state transfer paths; the behavior state information and the physiological parameter change information in the state queue are arranged according to occurrence time sequence.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: if the successfully matched target state transition path exists, the electronic equipment acquires the water drinking confidence coefficient of the target state transition path; wherein, each state transition path is preset with a corresponding drinking confidence; and the electronic equipment takes the accumulated sum of the drinking confidence degrees of the state transition paths of the items as the sum of the drinking confidence degrees.

According to the third aspect, or any implementation manner of the third aspect above, the state transition path includes behavior state information and/or physiological parameter change information; or the state transition path comprises a plurality of user behavior state information and/or physiological parameter change information which are arranged in sequence.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: the electronic equipment identifies the behavior state information of the user according to the relevant data acquired in real time in the current drinking detection period.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: the electronic equipment respectively extracts the characteristics of the related data acquired in real time in the current drinking detection period to obtain at least two data characteristics; the electronic equipment performs feature fusion on at least two data features to obtain fusion features; and the electronic equipment inputs the fusion characteristics into a behavior state recognition model obtained by pre-training to obtain the behavior state information of the user output by the behavior state recognition model.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: after obtaining the at least two data features, the electronic device performs dimension expansion on the at least one data feature.

According to a third aspect, or any implementation form of the third aspect above, the correlation data comprises acceleration data and audio data.

According to the third aspect, or any implementation manner of the third aspect, when the electronic device establishes a wireless communication connection with the water dispenser device through the wireless fidelity module, the related data includes acceleration data, audio data, and wireless fidelity signal related data; or when the electronic equipment establishes wireless communication connection with the water dispenser equipment through the Bluetooth module, the related data comprises acceleration data, audio data and Bluetooth signal related data.

According to the third aspect, or any implementation form of the third aspect above, the audio data is desensitized audio data.

According to the third aspect, or any implementation manner of the third aspect above, the behavior state information includes at least one of: the method comprises the following steps of opening a water cup, sitting still, walking, receiving water, wearing electronic equipment by the left hand, wearing the electronic equipment by the right hand, placing the water cup and drinking water.

According to the third aspect, or any implementation manner of the above third aspect, the physiological parameter variation information includes at least one of: body temperature is raised, pulse rate is accelerated, and blood oxygen changes.

According to a third aspect, or any implementation of the above third aspect, the computer program, when executed by the one or more processors, causes the electronic device to further perform the steps of: when the current drinking detection period is finished, the electronic equipment judges whether the current time is within a preset drinking reminding time period or not; and if so, updating the current drinking detection period by the electronic equipment.

According to a third aspect, or any implementation of the above third aspect, the computer program, when executed by the one or more processors, causes the electronic device to further perform the steps of: in response to the received first operation, the electronic device sets a start time and an end time of the drinking water reminder period.

According to a third aspect, or any implementation of the above third aspect, the computer program, when executed by the one or more processors, causes the electronic device to further perform the steps of: in response to the received second operation, the electronic device sets a duration of the drinking detection period.

According to a third aspect, or any implementation of the third aspect above, the computer program, when executed by the one or more processors, causes the electronic device to perform the steps of: the electronic equipment displays drinking reminding information and vibrates and/or rings to remind a user of drinking.

According to a third aspect, or any implementation form of the third aspect above, the electronic device is a smart watch.

Any one implementation manner of the third aspect corresponds to any one implementation manner of the first aspect. For technical effects corresponding to any one implementation manner of the third aspect and the third aspect, reference may be made to the technical effects corresponding to any one implementation manner of the first aspect and the first aspect, and details are not repeated here.

In a fourth aspect, an embodiment of the present application provides a drinking reminding system. The system comprises: smart watches and mobile phones; the smart watch and the mobile phone are in communication connection; the intelligent watch is used for judging whether the user drinks water in the current drinking detection period according to the behavior state information and the physiological parameter change information of the user in the current drinking detection period and sending a judgment result to the mobile phone; the mobile phone is used for reminding the user of drinking water when the user does not drink water in the current drinking water detection period and the current drinking water detection period is over.

According to the fourth aspect, the smart watch judges whether the user has drunk water in the current drinking detection period according to the behavior state information and the physiological parameter change information, and includes: the intelligent watch matches the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence; the intelligent watch counts the sum of the confidence degrees of the drunk water corresponding to the current drinking water detection period according to the matching result; if the sum of the confidence degrees of the drunk water does not reach the preset confidence degree threshold value, the intelligent watch judges that the user does not drink water in the current drinking detection period.

According to a fourth aspect or any implementation manner of the fourth aspect, the matching, by the smartwatch, the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence includes: the intelligent watch matches the behavior state information and the physiological parameter change information stored in the state queue with a plurality of preset state transfer paths; the behavior state information and the physiological parameter change information in the state queue are arranged according to occurrence time sequence.

According to the fourth aspect, or any one implementation manner of the above fourth aspect, the method for counting the total of the confidence degrees of drinking water corresponding to the current drinking water detection period by the smart watch according to the matching result includes: if the target state transition path successfully matched exists, the intelligent watch acquires the water drinking confidence of the target state transition path; wherein, each state transition path is preset with a corresponding drinking confidence; and the intelligent watch takes the accumulated sum of the drinking confidence degrees of the state transition paths of the items as the sum of the drinking confidence degrees.

According to a fourth aspect or any implementation manner of the fourth aspect above, the state transition path includes behavior state information and/or physiological parameter change information; or the state transition path comprises a plurality of user behavior state information and/or physiological parameter change information which are arranged in sequence.

According to a fourth aspect, or any one implementation manner of the fourth aspect, the method for acquiring behavior state information of a user in a current drinking detection period by a smart watch includes: the intelligent watch identifies the behavior state information of the user according to the related data acquired in real time in the current drinking detection period.

According to a fourth aspect, or any one implementation manner of the fourth aspect, the method for identifying the behavior state information of the user by the smart watch according to the relevant data collected in real time in the current drinking detection period includes: the intelligent watch respectively extracts the characteristics of the related data acquired in real time in the current drinking detection period to obtain at least two data characteristics; the smart watch performs feature fusion on at least two data features to obtain fusion features; and the smart watch inputs the fusion characteristics into a behavior state recognition model obtained through pre-training to obtain behavior state information of the user output by the behavior state recognition model.

According to the fourth aspect, or any implementation manner of the fourth aspect, after obtaining the at least two data features, the smart watch further performs dimension expansion on the at least one data feature.

According to a fourth aspect, or any implementation form of the fourth aspect above, the correlation data comprises acceleration data and audio data.

According to the fourth aspect, or any one of the above implementation manners of the fourth aspect, when the smart watch establishes a wireless communication connection with the water dispenser device through the wireless fidelity module, the related data includes acceleration data, audio data, and related data of a wireless fidelity signal; or when the intelligent watch is in wireless communication connection with the water dispenser device through the Bluetooth module, the related data comprises acceleration data, audio data and Bluetooth signal related data.

According to a fourth aspect, or any implementation form of the fourth aspect above, the audio data is desensitized audio data.

According to a fourth aspect, or any implementation manner of the fourth aspect above, the behavior state information includes at least one of: the intelligent watch is placed on the left hand, and the intelligent watch is placed on the right hand.

According to a fourth aspect, or any implementation manner of the fourth aspect above, the physiological parameter variation information includes at least one of: body temperature is raised, pulse rate is accelerated, and blood oxygen changes.

According to the fourth aspect or any implementation manner of the fourth aspect, when the current drinking detection cycle is finished, the smart watch judges whether the current time is within a preset drinking reminding time period; if yes, updating the current drinking detection period.

According to a fourth aspect, or any implementation of the fourth aspect above, in response to the received first operation, the smart watch sets a start time and an end time of the drinking water reminder period.

According to a fourth aspect, or any implementation manner of the fourth aspect, the duration of the drinking detection period is set in response to the received second operation.

According to the fourth aspect or any implementation manner of the fourth aspect, the mobile phone displays drinking reminding information and vibrates and/or rings to remind a user of drinking.

Any one implementation manner of the fourth aspect and the fourth aspect corresponds to any one implementation manner of the first aspect and the first aspect, respectively. For technical effects corresponding to any one implementation manner of the fourth aspect and the fourth aspect, reference may be made to the technical effects corresponding to any one implementation manner of the first aspect and the first aspect, and details are not repeated here.

In a fifth aspect, an embodiment of the present application provides a drinking water reminding system, including: smart watches and mobile phones; the system includes, one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored on the memory, which when executed by the one or more processors, cause the electronic device to perform the drinking water reminder method as claimed in any one of the first aspect and the first aspect.

Any one implementation manner of the fifth aspect and the fifth aspect corresponds to any one implementation manner of the first aspect and the first aspect, respectively. For technical effects corresponding to any one of the implementation manners of the fifth aspect and the fifth aspect, reference may be made to the technical effects corresponding to any one of the implementation manners of the first aspect and the first aspect, and details are not repeated here.

In a sixth aspect, embodiments of the present application provide a computer-readable storage medium. The computer readable storage medium comprises a computer program which, when run on an electronic device, causes the electronic device to perform the drinking water reminder method of any one of the first aspect and the first aspect.

Any one implementation form of the sixth aspect and the sixth aspect corresponds to any one implementation form of the first aspect and the first aspect, respectively. For technical effects corresponding to any one implementation manner of the sixth aspect and the sixth aspect, reference may be made to the technical effects corresponding to any one implementation manner of the first aspect and the first aspect, and details are not described here again.

In a seventh aspect, an embodiment of the present application provides a computer program product, which includes a computer program and when the computer program is executed, causes a computer to execute the drinking water reminding method according to the first aspect or any one of the first aspects.

Any one of the implementations of the seventh aspect and the seventh aspect corresponds to any one of the implementations of the first aspect and the first aspect, respectively. For technical effects corresponding to any one of the implementation manners of the seventh aspect and the seventh aspect, reference may be made to the technical effects corresponding to any one of the implementation manners of the first aspect and the first aspect, and details are not repeated here.

Drawings

FIG. 1a is a schematic diagram of an exemplary application scenario;

FIG. 1b is a schematic diagram of an exemplary application scenario;

fig. 2 is a schematic diagram of a hardware structure of an exemplary electronic device;

fig. 3 is a schematic diagram of a software structure of an exemplary electronic device;

fig. 4 is a schematic view of a water drinking reminder according to an embodiment of the present application;

FIG. 5 is a schematic diagram of an exemplary application scenario;

FIG. 6 is a schematic diagram of an exemplary application scenario;

FIG. 7 is a schematic diagram of module interaction provided by an embodiment of the present application;

FIG. 8 is a schematic block diagram of a drinking water reminding algorithm model according to an embodiment of the present application;

fig. 9 is a schematic view of a drinking detection process according to an embodiment of the present application;

FIG. 10 is a schematic diagram of feature extraction provided in an embodiment of the present application;

FIG. 11 is a schematic diagram of an exemplary application scenario;

FIG. 12 is a schematic diagram of module interaction provided by an embodiment of the present application;

fig. 13 is a schematic view of a drinking detection process according to an embodiment of the present application;

FIG. 14 is a schematic diagram of feature extraction provided in an embodiment of the present application;

fig. 15 is a schematic flow chart of a water drinking reminding method according to an embodiment of the present application;

fig. 16 is a schematic view of a drinking reminding system according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.

The terms "first" and "second," and the like, in the description and in the claims of the embodiments of the present application are used for distinguishing between different objects and not for describing a particular order of the objects. For example, the first target object and the second target object, etc. are specific sequences for distinguishing different target objects, rather than describing target objects.

In the embodiments of the present application, words such as "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

In the description of the embodiments of the present application, the meaning of "a plurality" means two or more unless otherwise specified. For example, a plurality of processing units refers to two or more processing units; the plurality of systems refers to two or more systems.

Sufficient moisture plays a great role in human health, and people need to replenish moisture in time whether indoors or outdoors.

Fig. 1a is a schematic diagram of an exemplary application scenario. With the pace of work and life increasing, the working pressure of users is increasing. Referring to fig. 1a, when a user works at a desk, the user often forgets to drink water once the user is busy. At the moment, the user can purchase the water cup with the water drinking reminding function to remind the user of drinking water, and once the user is far away from the workbench for placing the water cup, the water drinking reminding function of the water cup is about to fail. The user can also remind him to drink water through setting up the alarm clock, but the alarm clock reminds the mode and can not adjust according to the user actually drinks water the condition is nimble remind time and remind the number of times, and is intelligent relatively poor.

Fig. 1b shows an exemplary illustration of another application scenario. Outdoor activities are beneficial to human health, but people need to replenish water in time during outdoor activities. Referring to fig. 1b, when a user rides a bicycle outdoors, the user often forgets to drink water on time, and cannot replenish water to the body in time. At this time, the user is unlikely to carry a water cup with a water drinking reminding function, and carries a common portable water bottle instead. Even if the user reminds the user to drink water by setting the alarm clock, the better drinking reminding effect can not be achieved. Therefore, it is a problem to be solved to intelligently remind the user to drink water to replenish water in time in a universal way no matter outdoors or indoors, and the user does not need to additionally bear the cost of purchasing special equipment (such as a water cup with a water drinking reminding function).

The embodiment of the application provides a drinking reminding method. The user wears an electronic device, which may be a smart watch, for example. The electronic equipment detects the behavior state information of the wearing user in real time, such as behavior states of opening a water cup, sitting still, walking, receiving water, placing the water cup, drinking water and the like, and detects the physiological parameter change information of the wearing user in real time, such as the physiological parameter changes of body temperature rise, pulse rate acceleration, blood oxygen change and the like. The electronic equipment judges whether the wearing user drinks water in a period of time according to the behavior state information and the physiological parameter change information detected in the period of time. If the electronic equipment judges that the wearing user does not drink water in the time period, the wearing user is reminded to drink water, and otherwise, the wearing user is not reminded to drink water.

For example, in an application scenario shown in fig. 1a, if a user wears the smart watch 10, the smart watch 10 may remind the user of drinking based on the drinking reminding method provided in the embodiment of the present application. The smart watch 10 can detect the behavior state and the physiological parameter change of the wearing user in real time during the work period of the wearing user at desk, and judge whether the wearing user drinks water in the time period according to the behavior state information and the physiological parameter change information of the wearing user detected in the water drinking detection period. Wherein, the time interval that whether the user has drunk water is detected to the intelligent wrist-watch that the time quantum that the detection cycle of drinking water corresponds indicates. If the smart watch 10 judges that the wearing user does not drink water in the time period, the wearing user is reminded to drink water at the end of the water drinking detection period, otherwise, the wearing user is not reminded to drink water.

Further exemplarily, in the application scenario shown in fig. 1b, if the user wears the smart watch 10, the smart watch 10 may remind the user to drink based on the drinking reminding method provided in the embodiment of the present application. The smart watch 10 may detect the behavior state and the physiological parameter change of the user in real time during the outdoor activities of the user, and determine whether the user has drunk water in the time period according to the behavior state information and the physiological parameter change information of the user detected in the drinking water detection period. If the smart watch 10 judges that the wearing user does not drink water in the time period, the wearing user is reminded to drink water at the end of the water drinking detection period, otherwise, the wearing user is not reminded to drink water.

Therefore, no matter the watch is outdoors or indoors, the intelligent watch can remind the user of drinking water in time, and the universality is high. Moreover, the intelligent watch can determine whether to drink water to the wearing user according to the behavior state and the physiological parameter change of the wearing user, and the intelligence is high. In addition, the user does not need to additionally bear the expense of purchasing special equipment (such as a water cup with a water drinking reminding function).

Fig. 2 is a schematic structural diagram of the electronic device 100. Optionally, the electronic device 100 may be referred to as a terminal, and may also be referred to as a terminal device, and the terminal may be a wearable electronic device, for example, a smart watch, which is not limited in this application. It should be noted that the schematic structural diagram of the electronic device 100 can be applied to the smart watch 10 in fig. 1a and 1 b. It should be understood that the electronic device 100 shown in fig. 2 is only one example of an electronic device, and that the electronic device 100 may have more or fewer components than shown in the figures, may combine two or more components, or may have a different configuration of components. The various components shown in fig. 2 may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The electronic device 100 may include: the mobile terminal includes a processor 110, an external memory interface 120, an internal memory 121, a Universal Serial Bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, a Subscriber Identity Module (SIM) card interface 195, and the like. Wherein the sensor module 180 may include a pressure sensor, a gyroscope sensor, an acceleration sensor, a temperature sensor, a PPG (Photo pulse wave) sensor, a motion sensor, an air pressure sensor, a magnetic sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, etc.

Processor 110 may include one or more processing units, such as: the processor 110 may include an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a memory, a video codec, a Digital Signal Processor (DSP), a baseband processor, and/or a neural-Network Processing Unit (NPU), etc. The different processing units may be separate devices or may be integrated into one or more processors. A memory may also be provided in processor 110 for storing instructions and data.

The charging management module 140 is configured to receive charging input from a charger. The charging management module 140 may also supply power to the electronic device through the power management module 141 while charging the battery 142.

The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, a modem processor, a baseband processor, and the like. The mobile communication module 150 may provide a solution including 2G/3G/4G/5G wireless communication applied to the electronic device 100. The wireless communication module 160 may provide a solution for wireless communication applied to the electronic device 100, including Wireless Local Area Networks (WLANs) (e.g., wireless fidelity (Wi-Fi) networks), bluetooth (bluetooth, BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), Infrared (IR), and the like.

In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150 and antenna 2 is coupled to wireless communication module 160 so that electronic device 100 can communicate with networks and other devices through wireless communication techniques.

The electronic device 100 implements display functions via the GPU, the display screen 194, and the application processor. The processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

The display screen 194 is used to display images, video, and the like. The display screen 194 includes a display panel. In some embodiments, the electronic device 100 may include 1 or N display screens 194, with N being a positive integer greater than 1.

The external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to extend the memory capability of the electronic device 100. The internal memory 121 may be used to store computer-executable program code, which includes instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by executing instructions stored in the internal memory 121, so that the electronic device 100 implements the drinking reminding method in the embodiment of the present application.

In the embodiment of the present application, the internal memory 121 may be configured to store a drinking reminding algorithm model, a heart rate algorithm model, and the like for implementing the drinking reminding method in the embodiment of the present application.

The electronic device 100 may implement audio functions via the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone interface 170D, and the application processor. Such as music playing, recording, etc.

The audio module 170 is used to convert digital audio information into an analog audio signal output and also to convert an analog audio input into a digital audio signal. The audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be disposed in the processor 110, or some functional modules of the audio module 170 may be disposed in the processor 110.

In the embodiment of the present application, the microphone 170C may be used to collect sounds made by a user wearing the electronic device 100, for example, the sounds may be sounds of drinking water, sounds of receiving water, sounds of placing a water cup, and the like. Audio module 170 may convert analog audio input collected by microphone 170C into digital audio signals.

The gyro sensor may be used to detect a motion gesture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 about three axes (i.e., the x, y, and z axes) may be determined by a gyroscope sensor. In some embodiments, the gyro sensor may also be used to recognize gestures of the electronic device to enable recognition of a behavioral state of a user wearing or holding the electronic device 100.

The acceleration sensor may be used to detect the magnitude of acceleration of the electronic device 100 in various directions (typically three axes). In some embodiments, when the electronic device 100 is stationary, the magnitude and direction of gravity may be detected by the acceleration sensor. In some embodiments, the acceleration sensor may also be used to recognize the pose of the electronic device to enable recognition of the behavioral state of a user wearing or holding the electronic device 100.

The temperature sensor may be used to detect the temperature of the electronic device 100. In some embodiments, the body temperature of the user wearing the electronic device 100 may be detected by a temperature sensor.

A PPG (Photo pulse wave) sensor may be used to detect physiological parameter information of the wearer of the electronic device 100. The principle of the PPG sensor is to optically detect the fluctuation change of blood volume in a tissue microvascular bed under the action of systole and diastole. For example, when the heart contracts, the blood volume of the tissue increases and the amount of light absorption increases, and the light intensity detected by the photodetector is small; when the blood volume of the tissue decreases and the amount of light absorption decreases at the time of diastole, the light intensity detected by the photodetector becomes large. Since changes in light intensity of the PPG sensor are associated with small changes in blood perfusion of the tissue, they can be used to provide information about the cardiovascular system of the wearer of the electronic device 100, such as physiological parameter information, for example blood pressure, blood oxygen, pulse rate (heart rate) and respiration rate.

The pressure sensor is used for sensing a pressure signal and converting the pressure signal into an electric signal. In some embodiments, the pressure sensor may be disposed on the display screen 194. The electronic apparatus 100 may also calculate the touched position based on the detection signal of the pressure sensor.

Touch sensors, also known as "touch panels". The touch sensor may be disposed on the display screen 194, and the touch sensor and the display screen 194 form a touch screen, which is also called a "touch screen". The touch sensor is used to detect a touch operation applied thereto or nearby. The touch sensor can communicate the detected touch operation to the application processor to determine the touch event type.

The keys 190 include a power-on key, a volume key, and the like. The keys 190 may be mechanical keys. Or may be touch keys. The electronic apparatus 100 may receive a key input, and generate a key signal input related to user setting and function control of the electronic apparatus 100.

The motor 191 may generate a vibration cue. The motor 191 may be used for incoming call vibration cues, as well as for touch vibration feedback. For example, when the electronic device 100 reminds the user to drink water, a vibration effect may be provided through the motor 191 to remind the user to drink water in time.

The indicator 192 may be an indicator light, and may be used to indicate the charging status and the power change, or may be used to indicate a message, such as a message reminding the user to drink water in time.

The software system of the electronic device 100 may employ a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present application takes an operating system with a layered architecture as an example, and exemplifies a software structure of the electronic device 100.

Fig. 3 is a block diagram of a software structure of the electronic device 100 according to the embodiment of the present application.

The layered architecture of the electronic device 100 divides the software into several layers, each layer having a clear role and division of labor. The layers communicate with each other through a software interface. In some embodiments, taking the electronic device 100 as a smart watch as an example, as shown in fig. 3, the operating system may be divided into six layers, which are, from top to bottom, a UI (User Interface) application layer, a system service layer, an algorithm layer, a hardware abstraction layer, a kernel layer, and a driver layer.

The UI application layer may include a series of application packages, which may be, for example, a dial, a sports record, a call, an exercise, and the like.

The system services layer may include a series of system services. As shown in fig. 3, the system service layer may include a heart rate service, and the heart rate service may provide physiological parameter information of the smart watch wearer, such as blood pressure, blood oxygen, pulse rate, respiratory rate, body temperature, and the like, and may also detect physiological parameter variation information of the smart watch wearer. The system services layer may also include a step-counting service, a calorie service, a heart health service.

The algorithm layer may include a series of algorithm models. As shown in fig. 3, the algorithm layer may include a heart rate algorithm model and a drinking water reminder algorithm model. The heart rate algorithm model is used for calculating physiological parameters of a smart watch wearer, and the drinking reminding algorithm model is used for detecting whether the smart watch wearer drinks water within a set time period. The algorithm layer may also include a sleep algorithm model, a wear algorithm model, and the like.

In the embodiment of the application, the drinking reminding algorithm model can judge whether the wearing user drinks water in the set time period according to the user behavior state and physiological parameter change detected in the set time period, and sends the judgment result to the UI application layer. And the system of the UI application layer receives the judgment result and carries out UI reminding on the wearing user when the judgment result indicates that the wearing user does not drink water in the time period.

A Hardware Abstraction Layer (HAL) is an interface layer between the operating system kernel and the hardware circuitry. As shown in fig. 3, the HAL layer includes, but is not limited to, an audio HAL. The audio HAL is used for processing the audio stream, for example, performing noise reduction, directional enhancement, and the like on the audio stream.

The kernel layer and the driver layer are layers between hardware and software. As shown in fig. 3, the kernel layer at least includes an operating system kernel, and the driver layer at least includes a sensor driver, a motor driver, a bluetooth driver, a WiFi driver, and the like. The sensor drive may include a drive corresponding to the gyroscope sensor and the acceleration sensor, and is used for detecting the angle change of the electronic device.

It is to be understood that the layers in the software structure shown in fig. 3 and the components included in each layer do not constitute a specific limitation of the electronic device 100. In other embodiments of the present application, electronic device 100 may include more or fewer layers than those shown, and may include more or fewer components in each layer, which is not limited in this application.

It is understood that, in order to implement the drinking reminding method in the embodiment of the present application, the electronic device includes hardware and/or software modules corresponding to the execution of the respective functions. The present application is capable of being implemented in hardware or a combination of hardware and computer software in conjunction with the exemplary algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, with the embodiment described in connection with the particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The following describes a water drinking reminding method provided by the embodiment of the application in detail by taking an electronic device as an intelligent watch as an example. Referring to fig. 4, the smart watch detects drinking water to the wearing user in each drinking water detection period of a preset drinking water reminding time period every day, and determines whether the wearing user has drunk water in each drinking water detection period. If the intelligent watch judges that the wearing user does not drink water in a certain drinking detection period, the intelligent watch carries out drinking reminding on the wearing user when the drinking detection period is finished, otherwise, the intelligent watch does not carry out drinking reminding on the wearing user when the drinking detection period is finished. Wherein, the starting time point of the preset drinking reminding time period is the starting time T of the intelligent watch executing the drinking reminding method₀And the preset end time point of the drinking reminding time period is the end time T of the intelligent watch executing the drinking reminding method_n. For a time period T₀~T_nEach drinking water detection period T_i~T_i+1I is more than or equal to 0 and less than n, i is an integer, the intelligent watch respectively carries out drinking detection on the wearing user, and the intelligent watch detects drinking water at T_i+1The time point judges that the wearing user drinks the water detection period T_i~T_i+1Whether or not to drink water inside.

For example, the wearing user may preset the drinking reminding time period of the smart watch, that is, preset the start time and the end time of the drinking reminding time period. That is to say, the wearing user can preset the starting time and the ending time of the execution of the drinking reminding method by the smart watch. Referring to fig. 5 (1), the user clicks on a settings option 501 in the smart watch application menu interface. In response to the user's click operation, the smart watch displays a setup menu interface, which can be seen in (2) of fig. 5. In the setting menu interface of the smart watch, a plurality of options including a drinking reminding option 502 are provided. The user may perform a slide operation or the like in the setup menu interface to find the drinking reminder option 502. As shown in fig. 5 (2), the user clicks on the drink reminder option 502. In response to the click operation of the user, the smart watch displays a drinking reminder setting interface, which can be seen in (3) of fig. 5. As shown in (3) in fig. 5, the user can set the start time and the end time of the drinking reminding time period of the smart watch by pulling up and down the start time option 503 and the end time option 504. At this time, the drinking reminding interval (which may also be referred to as a drinking detection interval) when the smart watch executes the drinking reminding method, that is, the above-mentioned drinking detection period, may be default for the system, for example, two hours. As shown in (3) in fig. 5, the user slides the close reminding option 505, and then the start setting or the close setting of the intelligent watch drinking reminding function can be realized.

For example, the wearing user may set a drinking reminding interval when the smart watch executes the drinking reminding method. As shown in (4) in fig. 5, the drinking reminding setting interface enables a user to set on and off the drinking reminding function of the smart watch, presets the drinking reminding time period of the smart watch, and presets the drinking reminding interval of the smart watch when the drinking reminding method is executed. Referring to fig. 5 (4), the user pulls the reminding interval option 506 up and down, so that the setting of the drinking reminding interval when the intelligent watch executes the drinking reminding method can be realized.

For example, the user sets the start time T of the drinking reminder period of the smart watch₀7:30, end time T_nAt 22:00, the drinking reminder interval was 1.5 hours. That is, the smart watch executes the start time T of the drinking reminding method₀The ratio is 7:30, the intelligent watch carries out drinking water liftingEnd time T of waking method_nThe drinking rate was 22:00, and the drinking test was performed every 1.5 hours. At the moment, the first drinking detection period of the smart watch is 7: 30-9: 00, the second drinking detection period is 9: 00-10: 30, and the rest is done in the same way. In the first drinking detection period, if the smart watch judges that the wearing user drinks water in the drinking detection period according to the behavior state and the physiological parameter change of the wearing user, drinking reminding is not performed on the wearing user at the end time 9:00 of the drinking detection period. In the second drinking detection period, if the smart watch judges that the wearing user does not drink water in the drinking detection period according to the behavior state and the physiological parameter change of the wearing user, drinking reminding is carried out on the wearing user at the end time 10:30 of the drinking detection period. For example, the reminding mode of the smart watch can be seen in fig. 6. As shown in fig. 6, when the smart watch reminds the wearing user to drink water, a drinking reminder message 601, such as "you have not drunk water for a long time …", may be displayed on the display interface. Meanwhile, the smart watch can vibrate and/or ring, so that the drinking reminding effect is improved. Exemplarily, when the smart watch drinks and reminds, if the wearing user wants the smart watch to stop drinking and remind, the smart watch can be lifted or shaken, so that the smart watch stops drinking and reminding. Regarding the way that makes smart watch stop drinking water and remind, this application embodiment does not do the restriction.

One drinking water detection period T is described below_i~T_i+1For example, a detailed explanation is given to a flow of the smart watch performing drinking detection on the wearing user in the drinking detection period.

Scene one

In this scenario, the water cup and the water dispenser device used by the smart watch wearing user can be arbitrary. That is, the technical scheme that this scene provided is applicable to intelligent wrist-watch and drinks water detection and remind to its wearing user under arbitrary scene.

The drinking water reminding algorithm model of the intelligent watch receives data collected by the acceleration sensor and the microphone in real time, performs feature extraction on the data, and identifies behavior state information of a wearing user in the drinking water detection period according to extracted fusion features. Meanwhile, the drinking reminding algorithm model obtains the physiological parameter change information of the wearing user detected by the heart rate service. Furthermore, the drinking reminding algorithm model can count the confidence sum of the drinking of the wearing user in the drinking detection period according to the behavior state information and the physiological parameter change information of the wearing user in the drinking detection period. In the drinking detection period, if the calculated confidence sum reaches a preset confidence threshold, the drinking reminding algorithm model judges that the wearing user drinks water in the drinking detection period, otherwise, the drinking reminding algorithm model judges that the wearing user does not drink water in the drinking detection period.

Fig. 7 is a schematic diagram showing interaction among modules of the smart watch. Referring to fig. 7, a flow of a drinking reminding method provided in the embodiment of the present application specifically includes:

and S71, the acceleration sensor sends the acceleration data acquired in real time to the drinking reminding algorithm model through the sensor drive.

In response to various actions of the smart watch wearing user, the acceleration sensor of the smart watch can acquire acceleration values of the smart watch on 3 axes (x, y and z axes) and send the acquired acceleration values to a sensor driver (such as an acceleration sensor driver) in real time. And after receiving the data sent by the acceleration sensor, the sensor driver performs related processing and sends the processed acceleration data to the drinking reminding algorithm model. The processing process of the data acquired by the acceleration sensor by the sensor drive can refer to the technical scheme of the prior art embodiment, and is not repeated in the application.

And sending the acceleration data acquired by the acceleration sensor to the drinking reminding algorithm model so as to facilitate the drinking reminding algorithm model to identify the behavior state information of the wearing user and judge whether the wearing user drinks water according to the behavior state information of the wearing user. The behavior state information of the wearing user may be, for example, that a water receiving action or a water drinking action is triggered.

Optionally, if the smart watch is provided with the acceleration sensor and the gyroscope sensor at the same time, in the embodiment of the application, the drinking reminding algorithm model can identify behavior state information of the wearing user in the drinking detection period according to the acceleration data and the angular velocity data. At the moment, the acceleration sensor sends acceleration data acquired in real time to the drinking reminding algorithm model through the sensor drive, and the gyroscope sensor sends angular velocity data acquired in real time to the drinking reminding algorithm model through the sensor drive.

And S72, the microphone sends the audio data acquired in real time to the drinking reminding algorithm model through the audio HAL.

The microphone of the intelligent watch can collect audio data around the intelligent watch in real time and send the audio data to the audio HAL. And the audio HAL performs relevant processing on the received audio data and then sends the processed audio data to the drinking reminding algorithm model. For example, the audio HAL performs noise reduction, directional enhancement, and the like on the received audio data, and then sends the audio data to the drinking reminding algorithm model.

The audio data collected by the microphone are sent to the water drinking reminding model, so that the water drinking reminding model can judge whether the wearing user drinks water or not by combining voice characteristics, for example, the voice characteristics of the wearing user who drinks water falls into water at the moment of water receiving, the voice characteristics of the wearing user who swallows water when drinking water and the like, and further the misjudgment rate of the water drinking reminding model is reduced.

As an optional implementation manner of this embodiment, after the audio HAL receives the audio data, desensitization processing may be performed on the audio data, and the desensitized audio data may be sent to the drinking reminding algorithm model, so as to avoid the privacy problem of the user. Illustratively, the audio HAL matches the received audio data with a desensitization entity in a preset set of desensitization entities, and desensitizes words in the audio data that match the desensitization entity.

As another optional implementation manner of this embodiment, after receiving the audio data and performing relevant processing, such as noise reduction, directional enhancement, etc., the audio HAL sends the audio data to a desensitization service of the system service layer. Desensitization processing is carried out on the received audio data by desensitization service, and the desensitized audio data are sent to the drinking reminding algorithm model, so that the drinking reminding algorithm model is combined with the desensitized audio data to judge whether a wearing user drinks water, and the problem of user privacy is avoided.

S73, the heart rate service sends the physiological parameter change information detected in real time to the drinking reminding algorithm model.

The heart rate service in the system service layer can provide physiological parameter information of a smart watch wearer, such as blood pressure, blood oxygen, pulse rate, respiratory rate, body temperature and the like. Illustratively, the temperature sensor and the PPG sensor of the smart watch transmit data acquired in real time to the heart rate algorithm model in the algorithm layer via sensor driving. The heart rate algorithm model calculates the physiological parameters of the wearing user according to the received data, such as blood pressure, blood oxygen, pulse rate, respiratory rate, body temperature and the like, and sends the calculated physiological parameter values to the heart rate service.

The heart rate service can provide physiological parameter information of the intelligent watch wearer, and can also detect physiological parameter change information of the intelligent watch wearer, such as whether the body temperature is temporarily increased, whether the pulse rate is temporarily accelerated, whether the blood oxygen is instantaneously changed, and the like. When the information service detects that the physiological parameter information of the intelligent watch wearer changes, the detected physiological parameter change information is sent to the drinking reminding algorithm model, so that the drinking reminding model can judge whether the wearing user drinks water or not by combining the physiological parameter change information.

The body temperature of a human body can rise transiently after drinking water, heartbeat can be accelerated (particularly obvious when a large amount of water is drunk or water is drunk quickly), and blood oxygen can also be improved instantly, so that the water drinking reminding model can judge whether a wearing user drinks water or not by combining with physiological parameter change information, the accuracy of a judgment result can be effectively improved, and the misjudgment rate is reduced.

If the heart rate service is not set in the system service layer of the smart watch, the drinking reminding algorithm model can detect the physiological parameter change information of the smart watch wearer according to the data acquired in real time by the temperature sensor and the PPG sensor. Illustratively, the temperature sensor and the PPG sensor of the smart watch transmit data acquired in real time to the drinking reminding algorithm model through sensor driving. The drinking reminding algorithm model calculates the physiological parameters of the user according to the received data, such as blood pressure, blood oxygen, pulse rate, respiratory rate, body temperature and the like, and detects the physiological parameter change information of the intelligent watch wearer according to the calculation result, such as whether the body temperature is temporarily increased, whether the pulse rate is temporarily increased, whether the blood oxygen is instantaneously changed or not and the like.

And S74, the drinking reminding algorithm model carries out drinking detection on the wearing user according to the acceleration data, the audio data and the physiological parameter change information, and sends the judgment result of whether the wearing user drinks water in the drinking detection period to the UI application layer system.

The drinking reminding algorithm model identifies behavior state information of the smart watch wearing user in a drinking detection period according to the acceleration data and the audio data, and judges whether the wearing user drinks water in the drinking detection period by combining physiological parameter change information of the smart watch wearing user in the drinking detection period.

As shown in fig. 8, the drinking reminding algorithm module may include a feature extraction and fusion module, a behavior state recognition model and a drinking detection module. The feature extraction and fusion module is used for performing feature extraction and feature fusion on the acceleration data and the audio data to obtain fusion features. And the behavior state identification model is used for identifying the behavior state information of the wearing user according to the fusion characteristics to obtain the behavior state information of the wearing user. And the drinking detection module is used for carrying out drinking detection on the wearing user according to the behavior state information and the physiological parameter change information of the wearing user to obtain a judgment result of whether the wearing user drinks water in the drinking detection period.

Fig. 9 is a schematic flow chart of the drinking water detection performed by the smart watch drinking water reminding algorithm model. Referring to fig. 9, the process of detecting drinking of a wearing user by using the drinking reminding algorithm model provided in the embodiment of the present application specifically includes:

and S91, performing feature extraction on the acceleration data and the audio data by the drinking reminding algorithm model to obtain fusion features.

The acceleration data and the audio data are input into a feature extraction and fusion module in the drinking reminding algorithm model, the feature extraction and fusion module extracts acceleration features and audio signal features according to the acceleration data and the audio data respectively, and performs feature fusion on the acceleration features and the audio signal features to obtain fusion features. The audio data input into the feature extraction and fusion module can be desensitized audio data, and then the feature extraction and fusion module can provide audio signal features according to the desensitized audio signals. Illustratively, the feature extraction and fusion module splices the features to realize feature fusion to obtain fusion features, for example, the acceleration features and the audio signal features are spliced to obtain the fusion features.

Referring to fig. 10, the feature extraction and fusion module extracts three-axis acceleration values as three basic dimensional values of acceleration features according to the acceleration data. Meanwhile, the feature extraction and fusion module can also process the three-axis acceleration feature value to realize the dimension extension of the acceleration feature. For example, the feature extraction fusion module may extend acceleration features from three dimensions to four dimensions, or even more. For example, the feature extraction fusion module may calculate a combined acceleration value according to the three-axis acceleration values, and use the combined acceleration value as a fourth dimension value of the acceleration feature. For another example, the feature extraction and fusion module may count an acceleration average value, an acceleration maximum value, an acceleration minimum value, and the like according to the three-axis acceleration value, and use the values as values of other dimensions of the acceleration feature. The feature extraction and fusion module extracts one or more values of audio signal features, such as sound intensity, loudness, pitch, audio frequency, signal-to-noise ratio, harmonic-to-noise ratio and other feature values, according to the audio data, and the values are used as basic dimension values of the audio signal features. Meanwhile, the feature extraction and fusion module can also process the audio signal to realize the dimension extension of the acceleration feature. For example, the feature extraction fusion module may calculate a signal peak value of the audio signal as a value of an extension dimension of the audio signal feature. And then, the feature extraction and fusion module performs feature fusion on the acceleration features and the audio signal features after the dimension expansion to obtain fusion features. The embodiment does not specifically limit the dimension extension mode of the acceleration characteristic and the audio signal characteristic.

And S92, identifying the behavior state information of the wearing user by the water drinking reminding algorithm model according to the fusion characteristics to obtain the behavior state information of the wearing user.

And inputting the fusion characteristics into a behavior state recognition model obtained by pre-training. The behavior state recognition model recognizes the user behavior state corresponding to the fusion characteristics based on a deep learning mode, and outputs the behavior state information of the wearing user. Illustratively, the behavior state recognition module outputs the behavior state information of the wearing user according to the fusion features, for example, the behavior state information may be water cup opening, sitting still, walking, water receiving, smart watch wearing on the left hand, smart watch wearing on the right hand, water cup placement, water drinking and the like.

For example, the behavior state recognition model may employ a supervised deep learning training model. The training process of the behavior state recognition model may include the steps of:

and S01, acquiring a large number of fusion feature training samples.

And the fusion feature training sample refers to fusion features used for training the behavior state recognition model. It should be noted that the fusion feature obtained by feature extraction of the acceleration data and the audio data by the drinking reminding algorithm model in S91 is consistent with the fusion feature training sample in the number of feature dimensions and the fusion sequence involved in the two. The more and more accurate the characteristic dimensionality of the fused characteristic training sample is, the more and more beneficial the behavior state recognition model to learn the characteristics with better generalization, and the recognition effect of the behavior state recognition model is improved.

And S02, obtaining the expected value of the user behavior state corresponding to each fused feature training sample.

In this embodiment, the expected value of the user behavior state is used as a label for supervision in the training process of the behavior state recognition model.

And S03, training the behavior state recognition model according to a large number of fusion characteristic training samples by taking the expected value of the user behavior state corresponding to each fusion characteristic training sample as supervision.

When the behavior state recognition model is trained, the expected value of the user behavior state is used as supervision, and the predicted value of the user behavior state output by the behavior state recognition model aiming at the fusion feature training sample is close to the expected value of the user behavior state.

Exemplarily, the fusion feature training sample is input into an untrained behavior state recognition model to obtain a user behavior state prediction value. And determining a target loss value according to the difference (such as Euclidean distance, distribution difference and the like) between the predicted value of the user behavior state and the expected value of the user behavior state. And when the change rate of the target loss value is smaller than a preset threshold value, determining that the behavior state recognition model completes training. Optionally, one or more loss functions may be designed during the training of the behavior state recognition model, and then when the variation rates of one or more target loss values are all smaller than a preset threshold, it is determined that the training of the behavior state recognition model is completed.

The fusion characteristic training samples are input into the behavior state recognition model, and are sequentially processed through each processing layer according to the processing layer setting sequence in the behavior state recognition model, so that the user behavior state predicted value is obtained. For example, the processing layers in the behavioral state recognition model may include convolutional layers, anti-convolutional layers, pooling layers, and fully-connected layers. The number of the convolution layers can be multiple, and the number of the deconvolution layers can be multiple, so that the capacity of the neural network is increased, and the learning capacity of the neural network is improved. Optionally, a jump connection is established between at least one pair of convolution layer and deconvolution layer with equal size in the behavior state recognition model, so that the gradient can directly jump to other processing layers, the neural network is easier to train, and the problem that the behavior state recognition model is not sufficiently trained due to too fast gradient descent is avoided.

After the training of the behavior state recognition model is finished, the fusion characteristic inspection sample is input into the behavior state recognition model, and the behavior state recognition model is tested and inferred, so that the training effect of the behavior state recognition model is verified.

S93, the drinking reminding algorithm model carries out drinking detection on the wearing user according to the behavior state information and the physiological parameter change information of the wearing user, and a judgment result of whether the wearing user drinks water in a drinking detection period is obtained.

The behavior state information and the physiological parameter change information of the wearing user are sent to the drinking detection module, and the drinking detection module identifies the state change condition of the user according to the behavior state information and the physiological parameter change information of the wearing user.

Wherein, the water drinking detection module can be based on many preset state transition paths, discerns user's state change condition. The state transition path may be behavior state information of one user or physiological parameter change information, or may be a plurality of behavior state information of users and/or physiological parameter change information arranged in sequence.

The drinking detection module matches the detected behavior state information and physiological parameter change information of the wearing user with a plurality of preset state transition paths according to the occurrence time sequence, and counts the drinking confidence coefficient sum corresponding to the current drinking detection period according to the matching result. The more state transition paths are successfully matched, the larger the sum of the confidence degrees of the drunk water corresponding to the current drinking water detection period is. For example, each time the behavior state information and the physiological parameter change information of the user are successfully matched with each other, the sum of the confidence degrees of the drinking water corresponding to the current drinking water detection period is increased by 1. And if the sum of the confidence degrees of the drunk water does not reach the preset confidence degree threshold value, the water drinking detection module judges that the wearing user does not drink water in the current water drinking detection period.

Optionally, a drinking confidence coefficient is set for each state transition path, and the drinking confidence coefficient is used for evaluating the confidence degree of drinking when the state change of the wearing user is shown as the state transition path. Wherein the drinking confidence for each state transition path is determined by a number of sample analysis adjustments.

Illustratively, the state transition path is: the drinking action, the corresponding drinking confidence is f 1.

As another example, the state transition path is: water reception → drinking action → body temperature rise, and the corresponding confidence coefficient of drinking is f 2; the state transition path is: sitting still → placing a cup → raising the body temperature, the corresponding confidence coefficient of drinking is f 3; the state transition path is: sitting still → placing a cup → raising the heart rate, the corresponding confidence coefficient of drinking is f 4; the state transition path is: sedentary → body temperature, heart rate and blood oxygen change, the corresponding confidence of drinking is f 5; the state transition path is: walking → receiving water → body temperature and heart rate change, the corresponding confidence coefficient of drinking water is f 6; and so on.

Optionally, the drinking detection module sets a status queue. And the drinking detection module stores the behavior state information or the physiological parameter change information in the state queue every time the behavior state information or the physiological parameter change information of the wearing user is received. That is, the behavioral state information and the physiological parameter change information in the state queue are arranged according to the occurrence time sequence. That is, the order of arrangement of the behavioral state information and physiological parameter change information stored in the state queue is consistent with the order of occurrence of the behavioral state and physiological parameter change of the wearing user. At the beginning of each drink detection cycle, the drink detection module empties the status queue. That is, only the behavior state information and the physiological parameter change information of the wearing user in the current drinking detection period are stored in the state queue.

In a drinking detection period, every time the drinking detection module receives behavior state information or physiological parameter change information, the behavior state information or the physiological parameter change information is stored in a state queue. The drinking detection module matches the drinking detection module with each preset state transfer path, or matches the drinking detection module with each preset state transfer path in combination with other behavior state information and/or physiological parameter change information in the state queue. If the successfully matched state transition path exists, the drinking detection module acquires the drinking confidence fi of the successfully matched state transition path and accumulates the drinking confidence fi into the drinking confidence sum F corresponding to the drinking detection period. And when each drinking detection period starts, the drinking detection module clears the drinking confidence coefficient sum F.

If the behavior state information and/or the physiological parameter variation information in the state queue are successfully matched to a plurality of state transition paths in the drinking detection period, the drinking confidence sum F corresponding to the drinking detection period is the cumulative sum of a plurality of corresponding drinking confidences, such as F = F1+ F2+. + fn.

For example, assume that during the drinking detection period, the order stored in the status queue is: sit still → take water → rise body temperature. When the behavior state information 'drinking action' is stored in the state queue by the drinking detection module, the 'drinking action' in the state queue is successfully matched with the 'drinking action' in the state transition path. At this time, the drunk confidence sum F = F1 corresponding to the drinking detection period. When the drinking detection module stores the physiological parameter change information 'body temperature rise' in the state queue, the matching of the 'water receiving → drinking motion → body temperature rise' in the state queue and the state transition path 'water receiving → drinking motion → body temperature rise' is successful. At this time, the drunk confidence sum F = F1+ F2 corresponding to the drinking detection period.

For example, it is assumed that the behavioral state information and the physiological parameter variation information stored in the state queue cannot be successfully matched with any state transition path in the drinking detection period. At this time, the drunk confidence sum F =0 corresponding to the drinking detection period.

When the drinking detection period is finished, the drinking detection module judges whether the drinking confidence sum F corresponding to the drinking detection period reaches a preset confidence threshold value. If so, the drinking detection module judges that the wearing user drinks water in the drinking detection period; if not, the drinking detection module judges that the wearing user does not drink water in the drinking detection period.

As an optional implementation manner, in a drinking detection period, every time the drinking detection module receives one behavior state information or physiological parameter change information, the behavior state information or physiological parameter change information is stored in the state queue. The drinking detection module matches the drinking detection module with each preset state transfer path, or matches the drinking detection module with each preset state transfer path in combination with other behavior state information and/or physiological parameter change information in the state queue. If the successfully matched state transition path exists, the drinking detection module acquires the drinking confidence fi of the successfully matched state transition path, accumulates the drinking confidence fi into the drinking confidence sum F corresponding to the drinking detection period, and judges whether the drinking confidence sum F reaches a preset confidence threshold value. If the drinking confidence sum F does not reach the preset confidence threshold, the drinking detection module continues to perform the drinking detection operation in the drinking detection period. If the drinking confidence coefficient sum F currently reaches the preset confidence coefficient threshold, the drinking detection module does not perform the drinking detection operation in the drinking detection period, and the drinking confidence coefficient sum F is cleared when the next drinking detection period starts, so that the power consumption of the intelligent watch is reduced.

After the water drinking detection module obtains the judgment result of whether the wearing user drinks water in the water drinking detection period, the judgment result is sent to the UI application layer system, so that the UI application layer system determines whether the wearing user needs to be reminded of drinking water according to the judgment result.

And S75, when the judgment result indicates that the wearing user does not drink water in the water drinking detection period, the UI application layer system carries out water drinking reminding on the wearing user.

And the UI application layer system receives a judgment result of whether the wearing user drinks water in the water drinking detection period, and determines whether to remind the wearing user of drinking water according to the judgment result. When the judgment result indicates that the wearing user drinks water in the water drinking detection period, the UI application layer system does not remind the wearing user of drinking water. When the judgment result indicates that the wearing user does not drink water in the drinking detection period, the UI application layer system reminds the wearing user of drinking water, for example, a drinking water reminding message "you have not drunk water for a long time and …" is displayed on a display interface of the smart watch, and at this time, see fig. 6. The UI application layer system can also instruct the intelligent watch to vibrate and/or ring so as to improve the effect of drinking reminding.

Scene two

In this scene, the water dispenser equipment that user used is dressed to the intelligence wrist-watch possesses bluetooth module or wiFi module. At this moment, the distance change of wearing user and water dispenser equipment can be judged according to bluetooth signal or wiFi signal to the intelligence wrist-watch, and then combines the distance change of wearing user and water dispenser equipment to judge whether wearing the user drinks water to this accuracy that improves the judged result.

The drinking reminding algorithm model of the intelligent watch receives data collected by the acceleration sensor, the microphone and the WiFi module (or the Bluetooth module) in real time, performs feature extraction on the data, and identifies behavior state information of a wearing user in the drinking detection period according to extracted fusion features. Meanwhile, the drinking reminding algorithm model obtains the physiological parameter change information of the wearing user detected by the heart rate service. Furthermore, the drinking reminding algorithm model can count the confidence sum of the drinking of the wearing user in the drinking detection period according to the behavior state information and the physiological parameter change information of the wearing user in the drinking detection period. In the drinking detection period, if the calculated confidence sum reaches a preset confidence threshold, the drinking reminding algorithm model judges that the wearing user drinks water in the drinking detection period, otherwise, the drinking reminding algorithm model judges that the wearing user does not drink water in the drinking detection period.

It should be noted that in this scenario, if the drinking reminding algorithm model of the smart watch identifies the behavior state information of the wearing user by combining the data acquired by the WiFi module in real time, the smart watch needs to be in the same WiFi network as the water dispenser device; if the drinking reminding algorithm model of the smart watch identifies the behavior state information of the wearing user by combining with the data acquired by the Bluetooth module in real time, the smart watch needs to be in Bluetooth pairing connection with the water dispenser device in advance.

The following explanation takes the water dispenser device with a WiFi module as an example. As shown in fig. 11, the water dispenser device 20 has a WiFi module, and is located in a WiFi network with the smart watch 10, and the smart watch 10 may establish a WiFi connection with the water dispenser device 20 to determine the device identifier of the water dispenser device 20. As the wearing user of the smart watch 10 gets closer to the water dispenser device 20, the WiFi signal between the two gets stronger. Further, the smart watch 10 may extract the distance feature between the smart watch 10 and the water dispenser device 20 based on the feature change of the WiFi signal.

Fig. 12 is a schematic diagram showing interaction among modules of the smart watch. Referring to fig. 12, a flow of the drinking reminding method provided in the embodiment of the present application specifically includes:

and S121, the acceleration sensor sends acceleration data acquired in real time to the drinking reminding algorithm model through the sensor drive.

And S122, the microphone transmits the audio data acquired in real time to the drinking reminding algorithm model through the audio HAL.

And S123, the WiFi module sends the WiFi signal related data detected in real time between the drinking water machine and the WiFi module to the drinking water reminding algorithm model through WiFi driving.

The WiFi module of the water dispenser equipment is started, and WiFi signals are sent outwards. The WiFi module sends the WiFi signals detected in real time between the WiFi module and the water dispenser device to the WiFi driver. And after receiving the signal sent by the WiFi module, the WiFi driver performs related processing and sends the processed signal related data to the drinking reminding algorithm model. The WiFi driver may refer to the technical scheme of the prior art embodiment for processing the signal sent by the WiFi module, which is not described in detail herein.

And transmitting the WiFi signal related data to the drinking reminding algorithm model so as to facilitate the drinking reminding algorithm model to identify the behavior state information of the wearing user and judge whether the wearing user drinks water according to the behavior state information of the wearing user. The behavior state information of the wearing user can be, for example, approaching the water dispenser, being closer to the water dispenser, and the like. Illustratively, if the drinking reminding algorithm model identifies that the user drinks the water when the drinking reminding algorithm model identifies that the user is closer to the water dispenser, the confidence level of the water drunk by the user is higher, and therefore the accuracy of the judgment result is improved.

And S124, the heart rate service sends the physiological parameter change information detected in real time to the drinking reminding algorithm model.

And S125, carrying out drinking detection on the wearing user according to the acceleration data, the audio data, the WiFi signal related data and the physiological parameter change information by the drinking reminding algorithm model, and sending a judgment result of whether the wearing user drinks water in a drinking detection period to the UI application layer system.

The drinking reminding algorithm model identifies behavior state information of the smart watch wearing user in a drinking detection period according to the acceleration data, the audio data and the WiFi signal related data, and judges whether the wearing user drinks water in the drinking detection period by combining physiological parameter change information of the smart watch wearing user in the drinking detection period.

Fig. 13 is a schematic flow chart of the drinking water detection performed by the smart watch drinking water reminding algorithm model. Referring to fig. 13, the process of detecting drinking of a wearing user by using the drinking reminding algorithm model provided in the embodiment of the present application specifically includes:

s131, the drinking reminding algorithm model performs feature extraction on the acceleration data, the audio data and the WiFi signal related data to obtain fusion features.

The method comprises the steps that acceleration data and audio data WiFi signal related data are input into a feature extraction and fusion module in a drinking reminding algorithm model, the feature extraction and fusion module extracts acceleration features, audio signal features and WiFi signal features respectively according to the acceleration data, the audio data and the WiFi signal related data, and the acceleration features, the audio signal features and the WiFi signal features are fused to obtain fusion features.

Referring to fig. 14, the feature extraction and fusion module extracts features of the WiFi signal according to WiFi signal related data, and then extracts distance features between the smart watch and the water dispenser device based on feature processing of the WiFi signal as WiFi signal features. And then, the feature extraction and fusion module performs feature fusion on the acceleration feature and the audio signal feature after the dimensionality expansion and the WiFi signal feature to obtain fusion features.

Similarly, if the water dispenser device is provided with the Bluetooth module, the feature extraction and fusion module extracts the features of the Bluetooth signals according to the relevant data of the Bluetooth signals, and then extracts the distance features between the intelligent watch and the water dispenser device based on the feature processing of the Bluetooth signals to serve as the Bluetooth signal features. And then, the feature extraction and fusion module performs feature fusion on the acceleration feature and the audio signal feature after the dimensionality extension and the Bluetooth signal feature to obtain a fusion feature.

Optionally, if the water dispenser device is provided with the WiFi module and the Bluetooth module at the same time, the feature extraction and fusion module can respectively extract WiFi signal features and Bluetooth signal features, and performs feature fusion on the acceleration features and the audio signal features after the dimensionality extension, and the WiFi signal features and the Bluetooth signal features to obtain fusion features.

S132, identifying the behavior state information of the wearing user according to the fusion characteristics by the drinking reminding algorithm model to obtain the behavior state information of the wearing user.

And inputting the fusion characteristics into a behavior state recognition model obtained by pre-training. The behavior state recognition model recognizes the user behavior state corresponding to the fusion characteristics based on a deep learning mode, and outputs the behavior state information of the wearing user. Illustratively, the behavior state recognition module outputs the behavior state information of the wearing user according to the fusion features, for example, the behavior state information may be water cup opening, sitting still, walking, receiving water, wearing a smart watch on the left hand, wearing a smart watch on the right hand, placing a water cup, drinking water, walking into a water dispenser, being close to the water dispenser, and the like.

It should be noted that the feature type, the feature dimension, and the fusion sequence related to the fusion feature output by the feature extraction and fusion module in S131 need to be consistent with the fusion feature training sample used in training the behavior state recognition model.

In the scene, WiFi signal characteristics and/or Bluetooth signal characteristics are introduced into the fusion characteristic training samples, so that the recognition accuracy of the behavior state recognition model obtained through training can be effectively improved.

S133, the drinking reminding algorithm model carries out drinking detection on the wearing user according to the behavior state information and the physiological parameter change information of the wearing user, and a judgment result of whether the wearing user drinks water in a drinking detection period is obtained.

And S126, when the UI application layer system indicates that the wearing user does not drink water in the water drinking detection period according to the judgment result, carrying out water drinking reminding on the wearing user.

In this scenario, reference may be made to the foregoing scenario where a detailed explanation is not given, and details are not repeated here.

In this scene technical scheme, the intelligence wrist-watch fuses the audio frequency characteristic on the basis of the acceleration characteristic, bluetooth characteristic and/or wiFi characteristic, helps wearing the effective discernment of user's action state information. Meanwhile, on the basis of identifying the behavior state information of the user, the intelligent watch also introduces state context awareness and physiological parameter change identification, so that the accuracy of judging whether the user drinks water or not by the intelligent watch is improved, and the misjudgment probability is greatly reduced.

Fig. 15 is a schematic flow chart of a water drinking reminding method for a smart watch. Referring to fig. 15, a flow of a smart watch drinking reminding method provided in an embodiment of the present application specifically includes:

s151, the smart watch judges whether the current time reaches the water drinking reminding starting time T₀If yes, S152 is executed, and if no, S151 is executed.

Drinking reminding start time T₀The time period to the drinking reminding end time Tn refers to a preset drinking reminding time period for the smart watch to execute the drinking reminding method. Wherein, the drinking reminding start time T₀And the drinking reminding end time Tn can be set by the user according to the requirement, see fig. 5, and will not be described herein.

S152, the intelligent watch carries out drinking detection on the wearing user in the current drinking detection period, and the drinking confidence coefficient sum F is counted.

A drinking detection period for indicating a time interval for the smart watch to detect whether the user has drunk water, the time interval being T_i~T_i+1And (4) showing. Wherein i is more than or equal to 0 and less than n, i is an integer, and the initial value of i is 0. Correspondingly, the first drinking detection period is the time period T₀~T₁。

The intelligent watch determines the behavior state of a wearing user according to the related data acquired in real time in the current drinking detection period. The related data acquired by the smart watch in real time can be acceleration data acquired by an accelerator sensor of the smart watch and audio data acquired by a microphone. Under the condition that the intelligent watch is in wireless communication connection with the water dispenser device through the WiFi module, the related data acquired by the intelligent watch in real time can be acceleration data acquired by an accelerator sensor of the intelligent watch, audio data acquired by a microphone and WiFi signal related data acquired by the WiFi module. Under the condition that the intelligent watch is in wireless communication connection with the water dispenser device through the Bluetooth module, the related data acquired by the intelligent watch in real time can be acceleration data acquired by an accelerator sensor of the intelligent watch, audio data acquired by a microphone and related data of a Bluetooth signal acquired by the Bluetooth module.

The smart watch respectively extracts the characteristics of the collected related data to obtain corresponding data characteristics, and performs characteristic fusion on the obtained data characteristics to obtain fusion characteristics. Illustratively, the data feature may be an acceleration feature, an audio signal feature, a WiFi signal feature, or a bluetooth signal feature. Correspondingly, the fusion feature may be obtained by fusing the acceleration feature and the audio signal feature, may also be obtained by fusing the acceleration feature, the audio signal feature and the WiFi signal feature, may also be obtained by fusing the acceleration feature, the audio signal feature and the bluetooth signal feature, and may also be obtained by fusing the acceleration feature, the audio signal feature, the WiFi signal feature and the bluetooth signal feature.

Optionally, the audio data extracted by the smart watch is desensitized audio data.

Optionally, the smart watch performs feature extraction on the collected related data, and after the corresponding data features are obtained, dimension expansion can be performed on the data features. Illustratively, the smart watch dimensionally expands the acceleration feature and/or the audio signal feature.

The smart watch inputs the fusion characteristics into a behavior state recognition model obtained through pre-training, and behavior state information of the wearing user output by the behavior state recognition model is obtained. Furthermore, the intelligent watch can judge whether the wearing user drinks water in the current drinking detection period according to the behavior state information and the physiological parameter change information of the wearing user in the current drinking detection period.

Optionally, the smart watch matches behavior state information and physiological parameter change information in the current drinking detection period with multiple preset state transition paths according to the occurrence time sequence, and counts the drinking confidence sum F corresponding to the current drinking detection period according to the matching result. If the drinking confidence sum F does not reach the preset confidence threshold, the intelligent watch judges that the user is worn in the current drinking detection period and does not drink water.

For detailed explanation of drinking detection of the wearing user and statistics of the drinking confidence summation of the smart watch in the current drinking detection period, reference may be made to the foregoing, and details are not repeated here.

S153, when the current drinking detection period is over, the smartwatch determines whether the drinking confidence sum F reaches a preset confidence threshold, if so, then S155 is executed, and if not, then S154 is executed.

S154, the smart watch reminds the user of drinking water.

A schematic diagram of the smart watch reminding a user of drinking water by wearing the smart watch can be seen in fig. 6.

And S155, the smart watch judges whether the current time reaches the drinking reminding end time Tn, if not, S156 is executed, and if yes, the flow is ended.

And S156, updating the current drinking detection period by the smart watch.

At the drinking reminding start time T₀And in the time period of the drinking reminding ending time Tn, one drinking detection period is ended, and the current drinking detection period can be updated to be the next drinking detection period. Illustratively, if the time period T is passed_i~T_i+1And the drinking detection period is represented, and when the drinking detection period is i +1, the current drinking detection period can be updated to be the next drinking detection period.

It should be noted that if the drinking reminding start time T is set₀When the water drinking reminding is finishedThe time period Tn is not an integral multiple of the preset or default drinking detection period, the end time of the last drinking detection period may be directly set as the drinking reminding end time Tn (at this time, the duration of the last drinking detection period is shorter than the preset or default drinking detection period), or the drinking reminding process of the embodiment of the present application may be stopped when the current time reaches the drinking reminding end time Tn, which is not specifically limited in this embodiment.

The embodiment also provides a drinking reminding system. Referring to fig. 16, the drinking reminding system provided in the embodiment of the present application specifically includes: a smart watch 10 and a handset 30. The smart watch 10 and the cell phone 30 establish a communication connection in advance, which may be a bluetooth communication connection, for example.

The smart watch 10 determines whether the user has drunk water in the current drinking detection period according to the acquired behavior state information and physiological parameter change information of the user in the current drinking detection period, and sends a determination result to the mobile phone.

For a detailed explanation on whether the smart watch 10 determines that the user has drunk water in the current drinking detection period according to the behavior state information and the physiological parameter change information of the user in the current drinking detection period, reference may be made to the foregoing embodiment, which is not described herein again.

The mobile phone 30 receives a determination result of whether the user has drunk water in the current water drinking detection period, which is sent by the smart watch 10. If the received judgment result indicates that the user does not drink water in the current drinking detection period, the mobile phone 30 reminds the user of drinking water when the current drinking detection period is over. If the received judgment result indicates that the user has drunk water in the current water drinking detection period, the mobile phone 30 does not remind the user of drinking water.

For example, the mobile phone 30 may remind the user of drinking water by displaying the drinking water reminding information and vibrating and/or ringing.

The embodiment also provides a computer storage medium, where computer instructions are stored in the computer storage medium, and when the computer instructions are run on an electronic device, the electronic device is caused to execute the above related method steps to implement the drinking reminding method in the above embodiment.

The embodiment also provides a computer program product, which when running on a computer, causes the computer to execute the relevant steps to implement the drinking reminding method in the embodiment.

In addition, embodiments of the present application also provide an apparatus, which may be specifically a chip, a component or a module, and may include a processor and a memory connected to each other; when the device runs, the processor can execute the computer execution instruction stored in the memory, so that the chip can execute the drinking reminding method in the embodiments of the methods.

In this embodiment, the electronic device (e.g., a smart watch), the computer storage medium, the computer program product, or the chip are all configured to execute the corresponding method provided above, so that the beneficial effects achieved by the electronic device (e.g., a smart watch) may refer to the beneficial effects in the corresponding method provided above, and are not described herein again.

Through the description of the above embodiments, those skilled in the art will understand that, for convenience and simplicity of description, only the division of the above functional modules is used as an example, and in practical applications, the above function distribution may be completed by different functional modules as needed, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a module or a unit may be divided into only one logic function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another apparatus, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. The drinking reminding method is applied to electronic equipment and comprises the following steps:

acquiring behavior state information and physiological parameter change information of a user in a current drinking detection period;

judging whether the user drinks water in the current drinking detection period or not according to the behavior state information and the physiological parameter change information;

and if the user does not drink water in the current drinking detection period, carrying out drinking reminding on the user when the current drinking detection period is finished.

2. The method of claim 1, wherein the determining whether the user has drunk water within the current drinking detection period according to the behavior state information and the physiological parameter change information comprises:

matching the behavior state information and/or the physiological parameter change information with a plurality of preset state transition paths according to the occurrence time sequence;

counting the sum of the confidence degrees of the drunk water corresponding to the current drinking water detection period according to the matching result;

and if the sum of the confidence degrees of the drunk water does not reach a preset confidence degree threshold value, judging that the user does not drink water in the current drinking detection period.

3. The method according to claim 2, wherein the matching the behavior state information and/or the physiological parameter variation information with a plurality of preset state transition paths according to the occurrence time sequence comprises:

matching the behavior state information and the physiological parameter change information stored in the state queue with a plurality of preset state transfer paths;

and the behavior state information and the physiological parameter change information in the state queue are arranged according to occurrence time sequence.

4. The method of claim 2, wherein the counting the confidence sum of the drunk water corresponding to the current drinking detection period according to the matching result comprises:

if a successfully matched target state transition path exists, acquiring the water drinking confidence of the target state transition path; each state transition path is preset with a corresponding drinking confidence coefficient;

and taking the sum of the drinking confidence degrees of all the target state transition paths as the sum of the drinking confidence degrees.

5. The method according to any one of claims 2-4, wherein the state transition path comprises a behavior state information and/or a physiological parameter change information; alternatively, the first and second electrodes may be,

the state transition path comprises a plurality of user behavior state information and/or physiological parameter change information which are arranged in sequence.

6. The method of claim 1, wherein the obtaining of the behavior state information of the user in the current drinking detection period comprises:

and identifying the behavior state information of the user according to the related data acquired in real time in the current drinking detection period.

7. The method of claim 6, wherein identifying the behavioral state information of the user based on the relevant data collected in real time during the current drinking detection period comprises:

respectively carrying out feature extraction on related data acquired in real time in the current drinking detection period to obtain at least two data features;

performing feature fusion on the at least two data features to obtain fusion features;

and inputting the fusion characteristics to a behavior state recognition model obtained by pre-training to obtain the behavior state information of the user output by the behavior state recognition model.

8. The method of claim 7, further comprising, after said obtaining at least two data characteristics:

and performing dimension expansion on at least one data feature.

9. The method of claim 7, wherein the related data comprises acceleration data and audio data.

10. The method of claim 7, wherein the related data comprises acceleration data, audio data, and wireless fidelity signal related data when the electronic device establishes a wireless communication connection with the water dispenser device through a wireless fidelity module; alternatively, the first and second electrodes may be,

when the electronic equipment is in wireless communication connection with the water dispenser equipment through the Bluetooth module, the related data comprises acceleration data, audio data and Bluetooth signal related data.

11. The method of claim 9 or 10, wherein the audio data is desensitized audio data.

12. The method of claim 1, wherein the behavioral state information includes at least one of:

the method comprises the following steps of opening a water cup, sitting still, walking, receiving water, wearing electronic equipment by the left hand, wearing the electronic equipment by the right hand, placing the water cup and drinking water.

13. The method of claim 1, wherein the physiological parameter change information comprises at least one of:

body temperature is raised, pulse rate is accelerated, and blood oxygen changes.

14. The method of claim 1, further comprising:

when the current drinking detection period is finished, judging whether the current time is within a preset drinking reminding time period;

and if so, updating the current drinking detection period.

15. The method of claim 14, further comprising:

setting a start time and an end time of the drinking water reminder period in response to the received first operation.

16. The method of claim 15, further comprising:

setting the duration of the drinking detection period in response to the received second operation.

17. The method of claim 1, wherein said alerting the user to drink comprises:

displaying drinking reminding information, and vibrating and/or ringing.

18. The method of claim 1, wherein the electronic device is a smart watch.

19. An electronic device, comprising:

one or more processors;

a memory;

and one or more computer programs, wherein the one or more computer programs are stored on the memory, and when executed by the one or more processors, cause the electronic device to perform the drinking water reminder method of any one of claims 1 to 18.

20. A drinking reminding system is characterized by comprising an intelligent watch and a mobile phone; the system includes, one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored on the memory, which when executed by the one or more processors, cause the system to perform the drinking water reminder method of any one of claims 1 to 18.

21. A computer-readable storage medium comprising a computer program, which, when run on an electronic device, causes the electronic device to perform the drinking water reminder method of any one of claims 1-18.