CN112243063A - Automatic alarm method and device based on mobile terminal and mobile terminal - Google Patents
Automatic alarm method and device based on mobile terminal and mobile terminal Download PDFInfo
- Publication number
- CN112243063A CN112243063A CN201910652129.3A CN201910652129A CN112243063A CN 112243063 A CN112243063 A CN 112243063A CN 201910652129 A CN201910652129 A CN 201910652129A CN 112243063 A CN112243063 A CN 112243063A
- Authority
- CN
- China
- Prior art keywords
- mobile terminal
- terminal
- sensor data
- state
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/016—Personal emergency signalling and security systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/12—Details of telephonic subscriber devices including a sensor for measuring a physical value, e.g. temperature or motion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Telephone Function (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides an automatic alarm method and device based on a mobile terminal and the mobile terminal, wherein the method comprises the following steps: reading sensor data generated by at least one sensor in the current mobile terminal within a specified time period; transmitting the sensor data to a preset terminal state identification model, identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and outputting an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state; and determining the user behavior of the user based on the alarm signal, and automatically triggering alarm logic corresponding to the user behavior to alarm. Based on the scheme provided by the invention, a user does not need to search and open the terminal to actively alarm for help, and only needs to identify that the user is in an emergency help-seeking state based on the sensor data of the mobile terminal, the automatic alarm logic can be triggered, so that the user can be helped to realize quick alarm.
Description
Technical Field
The invention relates to the technical field of internet application, in particular to an automatic alarm method and device based on a mobile terminal and the mobile terminal.
Background
At present, when a user encounters an emergency or a dangerous situation, the following modes are mostly adopted to realize alarming or warning: 1. a user directly uses the smart phone to dial an alarm call or a friend-friend call for help; 2. long pressing or continuous pressing of a side key of the smart phone for a plurality of times triggers the dialing of an alarm call; 3. a user sets an alarm object (110 or relatives and friends) in the APP in advance, and when the user encounters danger, the user enters the APP to click an alarm button to give an alarm; 4. a user sets an alarm time point or an alarm place in the APP in advance, and when the set time point or the set place is reached, an alarm is triggered; 5. the warning function is realized on dangerous people by clicking and playing prestored videos and audios with the warning function or recording videos and uploading the videos to the system.
However, in some emergency situations, such as when the user has limited sight and limited action, the user may not be able to quickly take out the mobile phone from the pocket or satchel for help or alarm, which may delay the best alarm time.
Disclosure of Invention
The invention provides an automatic alarm method and device based on a mobile terminal and the mobile terminal, which aim to overcome the problems or at least partially solve the problems.
According to an aspect of the embodiments of the present invention, there is provided an automatic alarm method based on a mobile terminal, including:
reading sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
transmitting the sensor data to a preset terminal state identification model, identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and outputting an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and determining the user behavior of the user based on the alarm signal, and automatically triggering alarm logic corresponding to the user behavior to alarm.
Optionally, the reading of sensor data generated by at least one sensor in the current mobile terminal within a specified time period includes:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
Optionally, the transmitting the sensor data to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model includes:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
Optionally, before transmitting the sensor data to the preset terminal state identification model, the method further includes:
and training a terminal state recognition model in advance.
Optionally, the pre-training of the terminal state recognition model includes:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a first feature vector of the first sensor data;
and training by using a deep learning algorithm based on the training data to obtain a terminal state recognition model from the feature vector to the use state of the mobile terminal.
Optionally, the extracting the feature vector of the first sensor data includes:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time as a feature vector.
Optionally, after the pre-training of the terminal state recognition model, the method further includes:
generating an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
Optionally, the transmitting the sensor data to a preset terminal state recognition model, recognizing, by the terminal state recognition model, a use state of the mobile terminal corresponding to the sensor data, and outputting an alarm signal when it is determined that a user currently using the mobile terminal is in an emergency help-seeking state includes:
transmitting the feature vector to a local SDK recognition model component in the designated application program and/or a cloud end SDK recognition model component of the business cloud end;
performing feature matching on the basis of the special parameters through the local SDK identification model component and/or the cloud end SDK identification model component, and identifying the use state of the mobile terminal corresponding to the feature vector;
judging whether a user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
Optionally, after generating the SDK data packet according to the terminal state identification model, the method further includes:
collecting multiple groups of second sensor data generated by at least one sensor in the mobile terminal in different using states of the mobile terminal;
updating the terminal state recognition model based on the second sensor data;
and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
Optionally, the user behavior comprises at least one of: the method comprises the steps of beating the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal.
Optionally, the sensor comprises at least one of: gyroscopes, accelerometers, gravimeters, altimeters.
According to another aspect of the present invention, there is also provided an automatic alarm device based on a mobile terminal, including:
the reading module is configured to read sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
the identification module is configured to transmit the sensor data to a preset terminal state identification model, identify the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and output an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and the alarm module is configured to determine the user behavior of the user based on the alarm signal and automatically trigger alarm logic corresponding to the user behavior to alarm.
Optionally, the reading module is further configured to:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
Optionally, the identification module is further configured to:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
Optionally, the apparatus further comprises:
and the training module is configured to train the terminal state recognition model in advance.
Optionally, the training module is further configured to:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a first feature vector of the first sensor data;
and training a terminal state recognition model from the first feature vector to the use state of the mobile terminal based on the training data by using a deep learning algorithm.
Optionally, the training module is further configured to:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time to serve as a first feature vector.
Optionally, the apparatus further comprises:
the generating module is configured to generate an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
Optionally, the identification module is further configured to:
transmitting the feature vector to a local SDK recognition model component in the designated application program and/or a cloud end SDK recognition model component of the business cloud end;
performing feature matching on the basis of the special parameters through the local SDK identification model component and/or the cloud end SDK identification model component, and identifying the use state of the mobile terminal corresponding to the feature vector;
judging whether a user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
Optionally, the apparatus further comprises:
the updating module is configured to collect multiple groups of second sensor data generated by at least one sensor in the mobile terminal in different using states of the mobile terminal;
updating the terminal state recognition model based on the second sensor data;
and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
Optionally, the user behavior comprises at least one of: the method comprises the steps of beating the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal.
Optionally, the sensor comprises at least one of: gyroscopes, accelerometers, gravimeters, altimeters.
According to another aspect of the present invention, there is also provided a computer storage medium storing computer program code which, when run on a mobile terminal, causes the mobile terminal to perform any one of the above-described mobile terminal-based automatic alert methods.
According to another aspect of the present invention, there is also provided a mobile terminal including:
a processor;
a memory storing computer program code;
the computer program code, when executed by the processor, causes the mobile terminal to perform any of the mobile terminal based autoalarm methods described above.
The invention provides an automatic alarm method, an automatic alarm device and a mobile terminal based on a mobile terminal efficiently. Based on the automatic alarm method based on the mobile terminal provided by the invention, a user does not need to search and open the terminal for active alarm and help, and only needs to identify the use state of the mobile terminal based on the sensor data of the mobile terminal, so that an alarm signal is output when the user is judged to be in an emergency help-seeking state, and an automatic alarm logic is triggered. According to the scheme provided by the embodiment of the invention, the association between the use state of the mobile terminal and the user behavior is realized, and the related data of the sensor of the mobile terminal is marked into the signal of the user for actively transmitting the emergency, so that the user is helped to realize quick alarm.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flow chart illustrating an automatic alarm method based on a mobile terminal according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a method for training a terminal state recognition model according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating an automatic alarm method based on a mobile terminal according to a preferred embodiment of the present invention;
FIG. 4 is a schematic diagram of a three-dimensional coordinate structure according to an embodiment of the invention;
FIG. 5 is a schematic structural diagram of an automatic alarm device based on a mobile terminal according to an embodiment of the present invention;
fig. 6 is a schematic structural view of an automatic alarm device based on a mobile terminal according to a preferred embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a schematic flow chart of an automatic alarm method based on a mobile terminal according to an embodiment of the present invention, and it can be known from fig. 1 that the automatic alarm method based on the mobile terminal according to the embodiment of the present invention may include:
step S102, reading sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
step S104, transmitting the sensor data to a preset terminal state identification model, identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and outputting an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and step S106, determining the user behavior of the user based on the alarm signal, and automatically triggering the alarm logic corresponding to the user behavior to alarm.
The embodiment of the invention provides an automatic alarm method based on a mobile terminal efficiently, which comprises the steps of firstly reading sensor data of at least one sensor in the current mobile terminal in a specified time period, further transmitting the sensor data to a preset terminal state identification model for identification, outputting an alarm signal when the terminal state identification model judges that a user using the mobile terminal is in an emergency help-seeking state, and triggering alarm logic corresponding to user behavior based on the alarm signal to alarm. Based on the automatic alarm method based on the mobile terminal provided by the embodiment of the invention, a user does not need to search and open the terminal to actively alarm for help, and only needs to identify the use state of the mobile terminal based on the sensor data of the mobile terminal, so that an alarm signal is output when the user is judged to be in an emergency help-seeking state, and an automatic alarm logic is triggered. According to the scheme provided by the embodiment of the invention, the association between the use state of the mobile terminal and the user behavior is realized, and the related data of the sensor of the mobile terminal is marked into the signal of the user for actively transmitting the emergency, so that the user is helped to realize quick alarm.
The step S102 mentioned above refers to reading sensor data generated by at least one sensor in the previous mobile terminal within a specified time period. The sensor in the mobile terminal may be a gyroscope, an accelerometer, a gravimeter, an altimeter, a geomagnetic rotation vector sensor, and the like, which is not limited in the embodiments of the present invention. When the data of each sensor is read, the data generated by each sensor in a specified time period may be read in real time or at certain time intervals (for example, at intervals of 30s or 1min, etc.), and the specified time period may be set based on different models of mobile terminals or according to different scene requirements, which is not limited in the present invention.
In an optional embodiment of the present invention, the step S102 may further include: reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector. That is, after the sensor data of each sensor is read, the amount of change in the value of each sensor per unit time is calculated based on the sensor data, and the change in the value of each sensor is used as the feature vector.
Further, when the sensor data is identified by the terminal state identification model in step S104, the feature vector may be transmitted to a preset terminal state identification model, and the use state of the mobile terminal corresponding to the feature vector may be identified by the terminal state identification model.
The value change of each sensor provided therein is also differentiated due to different use states for the mobile terminal. For example, the instantaneous or interval state of the mobile terminal, such as by altimeter data determining that the mobile terminal is in several floors; the shaking degree (such as the shaking state within 1 second, whether shaking is serious or not, the numerical value change amplitude of the gyroscope) of the mobile terminal is sensed through the gyroscope, and the like, so that the state of the mobile terminal is distinguished based on subtle numerical value change of data, and soft association or hard association between the use state of the mobile terminal and user behaviors is realized. For example, when the user actively beats the mobile phone, the data change through the corresponding hardware is particularly obvious, and the data is marked as the situation that the user actively expresses that the user is in a dangerous state.
As described above, the sensor data of the mobile terminal is read and then transmitted to the predetermined terminal state recognition model. Optionally, before the step S104, the terminal state recognition model needs to be trained in advance. Fig. 2 is a schematic flow chart illustrating a method for training a terminal state recognition model according to an embodiment of the present invention, and as can be seen from fig. 2, the terminal state recognition model can be trained in the following manner:
step S202, collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor of the mobile terminal in different using states; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
step S204, extracting a first feature vector of the first sensor data; for any group of first sensor data, calculating the numerical value variation of each sensor in a first preset period in unit time to serve as a first feature vector;
and step S206, training by using a deep learning algorithm based on the training data to obtain a terminal state recognition model from the first feature vector to the use state of the mobile terminal.
That is to say, when training the terminal state recognition model, first, taking a first preset period as an evaluation period, data in the first preset period needs to be collected in advance as training data, where the collected training data includes data generated by at least one sensor in a plurality of groups of mobile terminals where individuals are under a safe condition and sensor data generated by at least one sensor in the mobile terminals when the plurality of groups of individuals send danger signals. The first preset period may be freely set, and the present invention is not limited thereto.
Secondly, for each group of sensor data, the value variation of each main sensor (such as an acceleration sensor, a gyroscope and the like) of the mobile terminal in a unit time t is used as a first feature vector in a first preset period, and the first feature vector is mapped to the corresponding use state of the mobile terminal. Such as the use state of the mobile terminal in a safe situation, the use state of the mobile terminal when the user may be in danger, and the use state of the mobile terminal when the user must be in danger, etc.
Finally, a deep learning algorithm is used to train a terminal state recognition model from the first feature vector to the usage state of the mobile terminal. The terminal state recognition model is preferably a deep learning classifier model, and after the terminal state recognition model is obtained through training, sensor data continuously generated by the terminal equipment can be tested to recognize the use state of the corresponding mobile terminal, so that whether a user using the mobile terminal is in an emergency help-seeking state or not is judged. The process of establishing and training the terminal state recognition model can be carried out through a preset artificial intelligence cloud end, or can be carried out on a mobile terminal locally or other servers.
In an alternative embodiment of the present invention, the terminal state recognition model may be embedded in the application program of the mobile terminal in the form of an SDK packet. Optionally, after the terminal state recognition model is obtained through training, an SDK data packet may be generated according to the terminal state recognition model; and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
Further, when the step S104 inputs the sensor data to the terminal state recognition model, the method may include:
s1, transmitting the feature vectors to a local SDK recognition model component in the appointed application program and/or a cloud end SDK recognition model component of the business cloud end;
s2, performing feature matching based on the special parameters through a local SDK recognition model component and/or a cloud end SDK recognition model component, and recognizing the use state of the mobile terminal corresponding to the feature vector;
s3, judging whether the user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and S4, if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
In the embodiment of the invention, the SDK data packet with the terminal state identification function can be integrated by developing an alarm application program APP or in an installed application program APP in the mobile terminal. The sensor data of the mobile terminal can be read through a designated application program when read, and after the sensor data of the sensor in the mobile terminal is read, the read sensor data can be directly transmitted to the application program integrated with the SDK data packet to be used as a local SDK identification model component, and then feature matching is carried out on the basis of a feature vector extracted by the sensor data through the application program based on the embedded local SDK identification model component, the use state of the mobile terminal is identified, whether a user using the mobile terminal at present is in an emergency help state is judged, and whether an alarm signal is output or not is determined. Specifically, the use state of the mobile terminal can be identified based on matching the feature vector with a first feature vector adopted in training the state identification model.
In addition, the SDK data packet can be stored to the service cloud end of the application program to serve as a cloud end SDK identification model component, after the specified application program reads the sensor data of the mobile terminal sensor, the sensor data can be uploaded to the corresponding service cloud end in a networking state, the cloud end SDK identification model component of the service cloud end extracts the characteristic vector and then performs special matching with the data in the model, and the using state of the mobile terminal is identified. Meanwhile, whether a user using the mobile terminal is in an emergency help-seeking state or not is judged, and whether an alarm signal is output or not is further determined.
That is, if the user needs to alarm when encountering a danger, the user can quickly tap the mobile phone in the pocket or the bag, and the application program transmits data generated by the sensor in the mobile phone to the local SDK identification model component or the cloud SDK identification model component and obtains corresponding feedback to decide which alarm logic to execute. The SDK data packet is statically embedded into a designated application, and a local SDK identification model component is set, so that automatic alarm can be realized under the condition that a user mobile phone is not networked. And by setting the cloud SDK recognition model component, the terminal state recognition model can be updated conveniently in time, so that the use state recognition result of the mobile terminal is more accurate.
Optionally, the terminal state recognition model may output different alarm signals corresponding to different user behaviors. By way of example, the user behavior includes at least one of: the method comprises the steps of flapping the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal. Pat the mobile terminal and can also divide different dynamics of patting, rock the mobile terminal and can also divide into different degree of rocking etc.. In this embodiment, a corresponding relationship may be established based on the user behavior and the alarm signal, and when the terminal state identification model sends the alarm signal, the user behavior corresponding to the alarm signal may be quickly obtained. In addition, different alarm logics can be matched for different user behaviors, and then the corresponding alarm logics are automatically triggered based on the behaviors. The alarm logic in this embodiment may include: the method comprises the steps of dialing an alarm call through the cloud, sending alarm information (calling or sending a short message) to an emergency contact preset by a user, and the like. In addition to the above, other alarm logic may be included, which is not described in detail herein.
Further, after the emergency contact or other rescue workers receive the alarm information, feedback information for confirming rescue can be fed back to the cloud end, the received request for help is represented, and real-time rescue can be carried out immediately; in addition, the user of the mobile terminal asking for help can be notified through the cloud.
In practical application, since parameters such as data and scene are changeable, after generating the SDK packet according to the terminal state identification model, the method may further include: collecting multiple groups of second sensor data generated by at least one sensor in the mobile terminal in different using states of the mobile terminal; updating the terminal state recognition model based on the second sensor data; and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
For each group of second sensors, the numerical variation of each sensor in a second preset period in unit time can be calculated and used as a feature vector, and the feature vector obtained by the calculation is used for adjusting and updating the terminal state identification model. In practical application, with the increase of data volume, the embodiment of the invention can perform self-learning such as correction, decision evolution and the like on the terminal state recognition model based on a large amount of collected practical application data, so that the recognition effect of the terminal state recognition model is higher.
And after the terminal state identification model is updated, generating a new SDK data packet according to a regular period so as to update the local SDK identification model component and/or the cloud end SDK identification model component at the same time. The correction and the update of the terminal state recognition model can be executed at the artificial intelligence cloud terminal, and the mobile terminal can also actively acquire a new SDK data packet from the artificial intelligence cloud terminal periodically to update the local SDK functional component.
The mobile terminal based automatic alarm method provided by the above embodiment is described in detail by a preferred embodiment.
Fig. 3 is a schematic flow chart illustrating an automatic alarm method based on a mobile terminal according to a preferred embodiment of the present invention, and it can be known from fig. 3 that in this embodiment, taking the mobile terminal as a mobile phone as an example, the automatic alarm method based on the mobile terminal may include:
1. when a user encounters an emergency or an emergency dangerous condition, the user can cause the data of each sensor in the mobile phone to change through flapping or other actions on the mobile phone;
2. the method comprises the steps that a specified application program in the mobile phone transmits collected sensor data to a terminal state recognition model, the terminal state recognition model carries out feature matching to recognize the use state of the mobile phone corresponding to the sensor data, judges that a user is possibly in an emergency help-seeking state at present, and sends an alarm signal, namely an alarm instruction for informing to alarm, to a local application program of the mobile phone or a service cloud service of the application program;
3. sending alarm and help-seeking information to appointed rescue workers by the service cloud;
4. the designated rescue personnel can also send an instruction for confirming receipt and implementing assistance to the business cloud service;
5. and the business cloud service transmits the information of confirmed assistance implementation to the help seeking user.
In this embodiment, a description is given by taking sensor data acquired by a geomagnetic rotation vector sensor as an example:
for the first time:
and (3) for the second time:
and thirdly:
fourth time:
fifth step:
from the sensor data collected over the five times above, it can be seen that the value values within items are not the same:
"items":{"value0":-0.008299952,"value1":3.5291482E-4,"value2":-0.8331914,"value3":0.5529223,"value4":0}
wherein, value0 represents the value change of the X coordinate axis direction; value1 represents the change of value of Y coordinate axis direction; value2 represents the change in value in the direction of the Z coordinate axis. The reference coordinate system is defined by direct orthogonal bases, as shown in fig. 4. The coordinate system shown in fig. 4 has the following features:
the first, X axis is defined by vector product Y X Z, it is tangent to the ground at the present position of the equipment, and points to east;
secondly, the Y axis is tangent to the ground at the current position of the equipment and points to the north pole of the geomagnetic field;
and thirdly, Z points to the sky and is vertical to the ground.
Therefore, the state of the mobile terminal can be effectively distinguished through subtle numerical value changes of the sensor data, and whether the user is in an emergency help-seeking state or not is accurately and quickly judged.
Based on the same inventive concept, an embodiment of the present invention further provides an automatic alarm device based on a mobile terminal, as shown in fig. 5, the device may include:
a reading module 510 configured to read sensor data generated by at least one sensor in a current mobile terminal within a specified time period;
the identification module 520 is configured to transmit the sensor data to a preset terminal state identification model, identify the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and output an alarm signal when judging that a user currently using the mobile terminal is in an emergency help-seeking state;
an alarm module 530 configured to determine a user behavior of the user based on the alarm signal and automatically trigger an alarm logic corresponding to the user behavior to alarm.
In an optional embodiment of the present invention, the reading module 510 may be further configured to:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
In an optional embodiment of the present invention, the identifying module 520 may be further configured to:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
In an alternative embodiment of the present invention, as shown in fig. 6, the apparatus may further include:
a training module 540 configured to train the terminal state recognition model in advance.
In an optional embodiment of the present invention, the training module 540 may be further configured to:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a first feature vector of the first sensor data;
and training a terminal state recognition model from the first feature vector to the use state of the mobile terminal based on the training data by using a deep learning algorithm.
In an optional embodiment of the present invention, the training module 540 may be further configured to:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time to serve as a first feature vector.
In an alternative embodiment of the present invention, as shown in fig. 6, the apparatus may further include:
a generating module 550 configured to generate an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
In an optional embodiment of the present invention, the identifying module 520 may be further configured to:
transmitting the feature vector to a local SDK recognition model component in the designated application program and/or a cloud end SDK recognition model component of the business cloud end;
performing feature matching based on the special parameters through the local SDK identification model component and/or the cloud end SDK identification model component, and identifying the use state of the mobile terminal corresponding to the sensor data;
judging whether a user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
In an alternative embodiment of the present invention, as shown in fig. 6, the apparatus may further include:
an updating module 560 configured to collect multiple sets of second sensor data generated by at least one sensor in the mobile terminal in different usage states of the mobile terminal;
updating the terminal state recognition model based on the second sensor data;
and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
In an optional embodiment of the invention, the user behavior may comprise at least one of: the method comprises the steps of beating the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal.
In an alternative embodiment of the invention, the sensor may comprise at least one of: gyroscopes, accelerometers, gravimeters, altimeters.
Based on the same inventive concept, the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer program codes, and when the computer program codes run on a mobile terminal, the mobile terminal is caused to execute the automatic alarm method based on the mobile terminal according to any one of the above embodiments.
Based on the same inventive concept, an embodiment of the present invention further provides a mobile terminal, including:
a processor;
a memory storing computer program code;
the computer program code, when executed by the processor, causes the mobile terminal to perform the mobile terminal based automatic alert method of any of the above embodiments.
The embodiment of the invention provides an automatic alarm method, an automatic alarm device and a mobile terminal based on a mobile terminal, which are efficient. Based on the automatic alarm method based on the mobile terminal provided by the embodiment of the invention, a user does not need to search and open the terminal to actively alarm for help, and only needs to identify the use state of the mobile terminal based on the sensor data of the mobile terminal, so that an alarm signal is output when the user is judged to be in an emergency help-seeking state, and an automatic alarm logic is triggered. According to the scheme provided by the embodiment of the invention, the association between the use state of the mobile terminal and the user behavior is realized, and the related data of the sensor of the mobile terminal is marked into a signal for the user to actively transmit emergency, so that the user is helped to rapidly alarm.
In addition, the embodiment of the invention can identify the use state of the mobile terminal based on the local and cloud sensor data so as to meet different scene requirements. And moreover, the trained terminal state recognition model is updated in time by collecting a large amount of sensor data again, so that the use state recognition result of the mobile terminal is more accurate.
It is clear to those skilled in the art that the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and for the sake of brevity, further description is omitted here.
In addition, the functional units in the embodiments of the present invention may be physically independent of each other, two or more functional units may be integrated together, or all the functional units may be integrated in one processing unit. The integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.
Those of ordinary skill in the art will understand that: the integrated functional units, if implemented in software and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computing device (e.g., a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention when the instructions are executed. And the aforementioned storage medium includes: u disk, removable hard disk, Read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disk, and other various media capable of storing program code.
Alternatively, all or part of the steps of implementing the foregoing method embodiments may be implemented by hardware (such as a computing device, e.g., a personal computer, a server, or a network device) associated with program instructions, which may be stored in a computer-readable storage medium, and when the program instructions are executed by a processor of the computing device, the computing device executes all or part of the steps of the method according to the embodiments of the present invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can be modified or some or all of the technical features can be equivalently replaced within the spirit and principle of the present invention; such modifications or substitutions do not depart from the scope of the present invention.
According to an aspect of the embodiments of the present invention, there is provided a1 a method for automatic alarm based on a mobile terminal, including:
reading sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
transmitting the sensor data to a preset terminal state identification model, identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and outputting an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and determining the user behavior of the user based on the alarm signal, and automatically triggering alarm logic corresponding to the user behavior to alarm.
A2, the method according to A1, wherein the reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period includes:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
A3, the method according to a2, wherein the transmitting the sensor data to a preset terminal state recognition model, and recognizing the use state of the mobile terminal corresponding to the sensor data through the terminal state recognition model, comprises:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
A4, the method according to A2, wherein the transmitting the sensor data to a preset terminal state recognition model further comprises:
and training a terminal state recognition model in advance.
A5, the method of A4, wherein the pre-training terminal state recognition model comprises:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a first feature vector of the first sensor data;
and training a terminal state recognition model from the first feature vector to the use state of the mobile terminal based on the training data by using a deep learning algorithm.
A6, the method of A5, wherein the extracting the feature vector of the first sensor data comprises:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time to serve as a first feature vector.
A7, the method according to A4, wherein the pre-training the terminal state recognition model further comprises:
generating an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
A8, the method according to a7, wherein the transmitting the sensor data to a preset terminal state recognition model, recognizing the use state of the mobile terminal corresponding to the sensor data through the terminal state recognition model, and outputting an alarm signal when determining that the user currently using the mobile terminal is in an emergency state, comprises:
transmitting the feature vector to a local SDK recognition model component in the designated application program and/or a cloud end SDK recognition model component of the business cloud end;
performing feature matching on the basis of the special parameters through the local SDK identification model component and/or the cloud end SDK identification model component, and identifying the use state of the mobile terminal corresponding to the feature vector;
judging whether a user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
A9, the method according to A8, wherein after the generating the SDK data packet according to the terminal state recognition model, the method further comprises:
collecting multiple groups of second sensor data generated by at least one sensor in the mobile terminal in different using states of the mobile terminal;
updating the terminal state recognition model based on the second sensor data;
and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
A10, the method according to any one of A1-A9, wherein the user behavior comprises at least one of: the method comprises the steps of beating the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal.
A11, the method of any one of A1-A9, wherein the sensor comprises at least one of: gyroscopes, accelerometers, gravimeters, altimeters.
According to another aspect of the embodiment of the present invention, there is also provided B12, an automatic alarm device based on a mobile terminal, including:
the reading module is configured to read sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
the identification module is configured to transmit the sensor data to a preset terminal state identification model, identify the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and output an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and the alarm module is configured to determine the user behavior of the user based on the alarm signal and automatically trigger alarm logic corresponding to the user behavior to alarm.
B13, the apparatus of B12, wherein the reading module is further configured to:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
The apparatus of B14, the apparatus of B13, wherein the identification module is further configured to:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
B15, the device according to B13, wherein further comprising:
and the training module is configured to train the terminal state recognition model in advance.
The apparatus of B16, the apparatus of B15, wherein the training module is further configured to:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a feature vector of the first sensor data;
and training by using a deep learning algorithm based on the training data to obtain a terminal state recognition model from the feature vector to the use state of the mobile terminal.
The apparatus of B17, the apparatus of B16, wherein the training module is further configured to:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time as a feature vector.
B18, the device according to B16, wherein further comprising:
the generating module is configured to generate an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
The apparatus of B19, the apparatus of B18, wherein the identification module is further configured to:
transmitting the feature vector to a local SDK recognition model component in the designated application program and/or a cloud end SDK recognition model component of the business cloud end;
performing feature matching on the basis of the special parameters through the local SDK identification model component and/or the cloud end SDK identification model component, and identifying the use state of the mobile terminal corresponding to the feature vector;
judging whether a user using the mobile terminal is in an emergency help-seeking state or not based on the use state of the mobile terminal;
and if the user using the mobile terminal is judged to be in the emergency help-seeking state, outputting an alarm signal.
B20, the device according to B19, wherein further comprising:
the updating module is configured to collect multiple groups of second sensor data generated by at least one sensor in the mobile terminal in different using states of the mobile terminal;
updating the terminal state recognition model based on the second sensor data;
and generating a new SDK data packet according to the updated terminal state identification model, and updating the local SDK identification model component and/or the cloud end SDK identification model component based on the new SDK data packet.
B21, the apparatus according to any one of B12-B20, wherein the user behavior comprises at least one of: the method comprises the steps of beating the mobile terminal, shaking the mobile terminal, triggering a preset button in the mobile terminal and triggering a preset gesture on a screen of the mobile terminal.
B22, the device according to any one of B12-B20, wherein the sensor comprises at least one of: gyroscopes, accelerometers, gravimeters, altimeters.
According to another aspect of the embodiments of the present invention, there is also provided C23, a computer storage medium storing computer program code which, when run on a mobile terminal, causes the mobile terminal to execute the mobile terminal-based automatic alert method of any one of a1-a 11.
According to another aspect of the embodiments of the present invention, there is also provided a D24, a mobile terminal, including:
a processor;
a memory storing computer program code;
the computer program code, when executed by the processor, causes the mobile terminal to perform any of the mobile terminal based autoalarm methods of A1-A11.
Claims (10)
1. An automatic alarm method based on a mobile terminal comprises the following steps:
reading sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
transmitting the sensor data to a preset terminal state identification model, identifying the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and outputting an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and determining the user behavior of the user based on the alarm signal, and automatically triggering alarm logic corresponding to the user behavior to alarm.
2. The method of claim 1, wherein the reading sensor data generated by at least one sensor in a current mobile terminal over a specified time period comprises:
reading sensor data generated by at least one sensor in the current mobile terminal in a specified time period, and calculating the numerical variation of each sensor in the specified time period in a unit time as a feature vector.
3. The method of claim 2, wherein the transmitting the sensor data to a preset terminal state recognition model, and recognizing the use state of the mobile terminal corresponding to the sensor data through the terminal state recognition model comprises:
and transmitting the characteristic vector to a preset terminal state identification model, and identifying the use state of the mobile terminal corresponding to the characteristic vector through the terminal state identification model.
4. The method of claim 2, wherein said transmitting said sensor data to a predetermined terminal state recognition model further comprises:
and training a terminal state recognition model in advance.
5. The method of claim 4, wherein the pre-training a terminal state recognition model comprises:
collecting training data in a first preset period; the training data comprises a plurality of groups of first sensor data generated by at least one sensor in different using states of the mobile terminal; the use state of the mobile terminal comprises the use state of a user to which the mobile terminal belongs under a safe condition and the use state of the user under a dangerous condition;
extracting a first feature vector of the first sensor data;
and training a terminal state recognition model from the first feature vector to the use state of the mobile terminal based on the training data by using a deep learning algorithm.
6. The method of claim 5, wherein the extracting the feature vector of the first sensor data comprises:
and for any group of first sensor data, calculating the numerical variation of each sensor in the first preset period in unit time to serve as a first feature vector.
7. The method of claim 4, wherein after the pre-training the terminal state recognition model, further comprising:
generating an SDK data packet according to the terminal state identification model;
and embedding the SDK data packet into a specified application program of the mobile terminal to serve as a local SDK identification model component, and meanwhile, storing the SDK data packet into a service cloud of the specified application program to serve as a cloud SDK identification model component.
8. An automatic alarm device based on a mobile terminal comprises:
the reading module is configured to read sensor data generated by at least one sensor in the current mobile terminal within a specified time period;
the identification module is configured to transmit the sensor data to a preset terminal state identification model, identify the use state of the mobile terminal corresponding to the sensor data through the terminal state identification model, and output an alarm signal when judging that a user using the mobile terminal is in an emergency help-seeking state;
and the alarm module is configured to determine the user behavior of the user based on the alarm signal and automatically trigger alarm logic corresponding to the user behavior to alarm.
9. A computer storage medium storing computer program code which, when run on a mobile terminal, causes the mobile terminal to perform the mobile terminal based automatic alert method of any one of claims 1 to 7.
10. A mobile terminal, comprising:
a processor;
a memory storing computer program code;
the computer program code, when executed by the processor, causes the mobile terminal to perform the mobile terminal based autoalarm method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910652129.3A CN112243063A (en) | 2019-07-18 | 2019-07-18 | Automatic alarm method and device based on mobile terminal and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910652129.3A CN112243063A (en) | 2019-07-18 | 2019-07-18 | Automatic alarm method and device based on mobile terminal and mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112243063A true CN112243063A (en) | 2021-01-19 |
Family
ID=74168102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910652129.3A Pending CN112243063A (en) | 2019-07-18 | 2019-07-18 | Automatic alarm method and device based on mobile terminal and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112243063A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103533153A (en) * | 2013-06-13 | 2014-01-22 | 广州七七八二信息科技有限公司 | Shaking help-seeking mechanism based on mobile terminal |
| CN105227709A (en) * | 2015-09-23 | 2016-01-06 | 努比亚技术有限公司 | The apparatus and method of crying for help are carried out by mobile terminal |
| CN105681599A (en) * | 2016-03-31 | 2016-06-15 | 维沃移动通信有限公司 | Mobile terminal emergency help-seeking method and mobile terminal |
| CN106331357A (en) * | 2016-08-29 | 2017-01-11 | 珠海格力电器股份有限公司 | Emergency alarm method, device and terminal |
| CN107045623A (en) * | 2016-12-30 | 2017-08-15 | 厦门瑞为信息技术有限公司 | A kind of method of the indoor dangerous situation alarm based on human body attitude trace analysis |
| CN107959748A (en) * | 2016-10-17 | 2018-04-24 | 腾讯科技（深圳）有限公司 | Automatic alarm method and device |
| CN108012022A (en) * | 2017-10-30 | 2018-05-08 | 努比亚技术有限公司 | Terminal alarms control method, mobile terminal and computer-readable recording medium |
| CN108040182A (en) * | 2018-01-16 | 2018-05-15 | 维沃移动通信有限公司 | A kind of alarm method and mobile terminal |
| CN108510718A (en) * | 2018-05-28 | 2018-09-07 | 深圳市零度智控科技有限公司 | Alarm method, device, terminal device based on big data and readable storage medium storing program for executing |
| CN109166141A (en) * | 2018-08-10 | 2019-01-08 | Oppo广东移动通信有限公司 | Dangerous based reminding method, device, storage medium and mobile terminal |
| CN109309761A (en) * | 2018-10-30 | 2019-02-05 | 努比亚技术有限公司 | Emergent calling method, mobile terminal and computer readable storage medium |
-
2019
- 2019-07-18 CN CN201910652129.3A patent/CN112243063A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103533153A (en) * | 2013-06-13 | 2014-01-22 | 广州七七八二信息科技有限公司 | Shaking help-seeking mechanism based on mobile terminal |
| CN105227709A (en) * | 2015-09-23 | 2016-01-06 | 努比亚技术有限公司 | The apparatus and method of crying for help are carried out by mobile terminal |
| CN105681599A (en) * | 2016-03-31 | 2016-06-15 | 维沃移动通信有限公司 | Mobile terminal emergency help-seeking method and mobile terminal |
| CN106331357A (en) * | 2016-08-29 | 2017-01-11 | 珠海格力电器股份有限公司 | Emergency alarm method, device and terminal |
| CN107959748A (en) * | 2016-10-17 | 2018-04-24 | 腾讯科技（深圳）有限公司 | Automatic alarm method and device |
| CN107045623A (en) * | 2016-12-30 | 2017-08-15 | 厦门瑞为信息技术有限公司 | A kind of method of the indoor dangerous situation alarm based on human body attitude trace analysis |
| CN108012022A (en) * | 2017-10-30 | 2018-05-08 | 努比亚技术有限公司 | Terminal alarms control method, mobile terminal and computer-readable recording medium |
| CN108040182A (en) * | 2018-01-16 | 2018-05-15 | 维沃移动通信有限公司 | A kind of alarm method and mobile terminal |
| CN108510718A (en) * | 2018-05-28 | 2018-09-07 | 深圳市零度智控科技有限公司 | Alarm method, device, terminal device based on big data and readable storage medium storing program for executing |
| CN109166141A (en) * | 2018-08-10 | 2019-01-08 | Oppo广东移动通信有限公司 | Dangerous based reminding method, device, storage medium and mobile terminal |
| CN109309761A (en) * | 2018-10-30 | 2019-02-05 | 努比亚技术有限公司 | Emergent calling method, mobile terminal and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108922129B (en) | A kind of method, apparatus, cloud and system adjusting security sensor alarm threshold value | |
| CN108256404B (en) | Pedestrian detection method and device | |
| KR102465105B1 (en) | Apparatus and method for detecting disaster based on artificial intelligence model using thermal image complex data | |
| CN111767888A (en) | Object state detection method, computer device, storage medium, and electronic device | |
| US11516336B2 (en) | Surface detection for mobile devices | |
| US20220246015A1 (en) | Fall detection method and apparatus, and wearable device | |
| CN110209281A (en) | Method, electronic equipment and the medium that motor message is handled | |
| Kolobe et al. | A review on fall detection in smart home for elderly and disabled people | |
| US11076264B2 (en) | Localization of a mobile device based on image and radio words | |
| JP6590477B2 (en) | Information processing apparatus, information processing method, and program | |
| CN112243063A (en) | Automatic alarm method and device based on mobile terminal and mobile terminal | |
| JP2022081882A (en) | Wild animal monitoring system, wild animal monitoring method, and program | |
| CN110674743A (en) | Tumble detection method based on triaxial acceleration data | |
| KR20190031786A (en) | Electronic device and method of obtaining feedback information thereof | |
| CN110612503B (en) | Intelligent context sub-sampling device system | |
| CN112926445A (en) | Parabolic behavior recognition method, model training method and related device | |
| JP7198052B2 (en) | image surveillance system | |
| KR20190047644A (en) | Method and wearable device for providing feedback on exercise | |
| CN112818929B (en) | Method and device for detecting people fighting, electronic equipment and storage medium | |
| JP6981553B2 (en) | Identification system, model provision method and model provision program | |
| CN111797878B (en) | Data processing method and device, storage medium and electronic equipment | |
| JP7220057B2 (en) | image surveillance system | |
| JP7197334B2 (en) | image surveillance system | |
| JP7161920B2 (en) | store equipment | |
| CN114882577B (en) | Health state identification method and device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |