CN108281203B - Method and device for predicting abnormal behavior - Google Patents
Method and device for predicting abnormal behavior Download PDFInfo
- Publication number
- CN108281203B CN108281203B CN201810169092.4A CN201810169092A CN108281203B CN 108281203 B CN108281203 B CN 108281203B CN 201810169092 A CN201810169092 A CN 201810169092A CN 108281203 B CN108281203 B CN 108281203B
- Authority
- CN
- China
- Prior art keywords
- monitored person
- data
- walking state
- predicting
- abnormal behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000006399 behavior Effects 0.000 claims abstract description 27
- 230000003542 behavioural effect Effects 0.000 claims abstract description 27
- 230000000694 effects Effects 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims description 67
- 230000005484 gravity Effects 0.000 claims description 57
- 230000035772 mutation Effects 0.000 claims description 32
- 230000005021 gait Effects 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 11
- 238000009434 installation Methods 0.000 claims description 8
- 230000036438 mutation frequency Effects 0.000 claims description 7
- 230000000474 nursing effect Effects 0.000 abstract description 22
- 230000008569 process Effects 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a method and a device for predicting abnormal behaviors, wherein the method comprises the following steps: acquiring behavior and activity data of a monitored person; generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person; and predicting whether the monitored person has abnormal behavior according to the walking state data. The automatic prediction mode for the abnormal behaviors can timely find the abnormal behaviors of the monitored person, not only reduces the manual nursing cost, but also avoids the nursing problem that people cannot gather spirit 24 hours a day by manual nursing.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for predicting abnormal behavior.
Background
With the aging of the population, effective nursing of the elderly will become an increasingly serious social problem. According to the existing nursing mode for the old people, all-weather nursing is performed manually, however, the manual nursing cost is high, nursing for gathering spirit 24 hours a day cannot be realized by manual nursing, and abnormal conditions (such as falling down) of the old people cannot be found in time, so that the abnormal conditions of the old people cannot be processed in time, and the personal safety of the old people cannot be guaranteed.
Disclosure of Invention
A primary object of the embodiments of the present application is to provide a method and an apparatus for predicting abnormal behavior, which can find the abnormal behavior of a monitored person in time.
The embodiment of the application provides a method for predicting abnormal behaviors, which comprises the following steps:
acquiring behavior and activity data of a monitored person;
generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person;
and predicting whether the monitored person has abnormal behavior according to the walking state data.
Optionally, the acquiring the behavioral activity data of the monitored person includes:
utilizing at least one infrared sensor, collecting behavioral activity data of the monitored person.
Optionally, the acquiring the behavioral activity data of the monitored person by using at least one infrared sensor includes:
determining the position information and/or the gravity center information of the monitored person according to the installation position of the at least one infrared sensor;
accordingly, the generating walking state data by analyzing the behavioral activity data comprises:
and generating walking state data by analyzing the position information and/or the gravity center information.
Optionally, the walking state data includes one or more of the following data:
a step frequency of the monitored person;
data reflecting gait continuity of the monitored person;
data reflecting the step change amplitude of the monitored person;
data reflecting the magnitude of change in the center of gravity of the monitored person.
Optionally, the predicting whether the monitored person has abnormal behavior according to the walking state data includes:
determining mutation probability of each item of the walking state data, wherein the mutation probability represents mutation frequency of the corresponding item of data in a preset time period;
predicting the probability of abnormal behaviors of the monitored person according to the mutation probability of each item of data;
judging whether the predicted probability is greater than a preset probability threshold value or not;
if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
Optionally, after predicting that the monitored person has abnormal behavior, the method further includes:
and predicting the abnormal behavior type of the monitored person according to the walking state data.
Optionally, the method further includes:
and adjusting the determination mode of the mutation probability and/or the size of the preset probability threshold according to the abnormal behavior type and the actual state of the monitored person.
Optionally, after predicting that the monitored person has abnormal behavior, the method further includes:
and sending early warning information to at least one preset communication device.
The embodiment of the present application further provides a device for predicting an abnormal behavior, including:
the behavior data acquisition unit is used for acquiring behavior activity data of a monitored person;
a walking data acquisition unit for generating walking state data by analyzing the behavior activity data, the walking state data reflecting the walking state of the monitored person;
and the abnormal behavior prediction unit is used for predicting whether the monitored person has abnormal behavior according to the walking state data.
Optionally, the behavior data acquiring unit includes:
the first data acquisition subunit is used for acquiring the behavior activity data of the monitored person by utilizing at least one infrared sensor.
Optionally, the first data collecting subunit includes:
the second data acquisition subunit is used for determining the position information and/or the gravity center information of the monitored person according to the installation position of the at least one infrared sensor;
accordingly, the walking data acquisition unit includes:
and the walking data acquisition subunit is used for generating walking state data by analyzing the position information and/or the gravity center information.
Optionally, the walking state data includes one or more of the following data:
a step frequency of the monitored person;
data reflecting gait continuity of the monitored person;
data reflecting the step change amplitude of the monitored person;
data reflecting the magnitude of change in the center of gravity of the monitored person.
Optionally, the abnormal behavior prediction unit includes:
the sudden change probability determining subunit is used for determining the sudden change probability of each item of data in the walking state data, and the sudden change probability represents the sudden change frequency of the corresponding item of data in a preset time period;
the abnormal probability determining subunit is used for predicting the probability of the abnormal behavior of the monitored person according to the mutation probability of each item of data;
the abnormal behavior prediction subunit is used for judging whether the predicted probability is greater than a preset probability threshold value; if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
Optionally, the apparatus further comprises:
and the behavior type prediction unit is used for predicting the abnormal behavior type of the monitored person according to the walking state data after the abnormal behavior of the monitored person is predicted.
Optionally, the apparatus further comprises:
and the trigger condition adjusting unit is used for adjusting the determination mode of the mutation probability and/or the size of the preset probability threshold according to the abnormal behavior type and the actual state of the monitored person.
Optionally, the apparatus further comprises:
and the early warning information sending unit is used for sending early warning information to at least one preset communication device after the abnormal behavior of the monitored person is predicted.
The embodiment of the present application further provides a device for predicting an abnormal behavior, which includes: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
the memory is for storing one or more programs, the one or more programs including instructions, which when executed by the processor, cause the processor to perform the method of any of the above.
The embodiment of the application also provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, and when the instructions are run on the terminal device, the terminal device is enabled to execute any implementation method of the method for predicting the abnormal behavior.
The method and the device for predicting the abnormal behavior, provided by the embodiment of the application, are used for collecting the behavior activity data of a monitored person; generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person; and predicting whether the monitored person has abnormal behavior according to the walking state data. Therefore, the automatic prediction mode for the abnormal behaviors can find the abnormal behaviors of the monitored person in time, not only reduces the manual nursing cost, but also avoids the nursing problem that people cannot focus on spirit 24 hours a day by manual nursing.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for predicting abnormal behavior according to an embodiment of the present disclosure;
fig. 2 is a second schematic flowchart of a method for predicting abnormal behavior according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram illustrating an abnormal behavior prediction apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic hardware structure diagram of an abnormal behavior prediction apparatus according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, 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 embodiments of the present application, but not all embodiments. 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 embodiment of the application provides a method for predicting abnormal behaviors, wherein the walking state of the old person is analyzed by collecting behavior activity data of a monitored person, for example, the behavior activity data of the old person is collected, so that whether the behavior of the old person is abnormal or not is predicted according to the analysis result of the walking state, and an automatic nursing mode is realized. By adopting the automatic nursing mode, the cost of manual nursing for the elderly can be greatly reduced, and the possible abnormal behaviors of the elderly, such as falling down and the like, can be quickly and accurately predicted in time, so that the potential risk of the elderly can be effectively reduced, and the nursing defect that people cannot gather together 24 hours a day in manual nursing is overcome.
The following specifically describes embodiments of the present application.
Referring to fig. 1, a flow chart of a method for predicting abnormal behavior provided in an embodiment of the present application is schematically illustrated, where the method includes the following steps:
s101: behavioral activity data of the monitored person is collected.
It should be noted that, the present embodiment does not limit the specific identity of the monitored person, and may be an elderly person with inconvenient actions or a patient with a disease.
Wherein the behavioral activity data is data relating to a behavioral activity of the monitored person. It should be noted that the behavioral activity data is actually a set of time-series data, so as to perform behavioral prediction on the monitored person based on the time-series data.
A sensing system including one or more sensors may be utilized to collect behavioral activity data of a monitored person while preserving privacy. Therefore, in an embodiment of the present application, step S101 may specifically include: the behavioral activity data of the monitored person is collected using at least one infrared sensor.
In this embodiment, for the monitoring environment (for example, in a home, a nursing home, etc.) where the monitored person is located, a plurality of infrared sensors may be installed in the monitoring environment according to the arrangement condition of the monitoring environment, the frequent activity area of the monitored person in the monitoring environment, the size of the sensor sensing area, and other factors, and the specific installation position may be considered in combination with the above factors, so that the behavior activity of the monitored person can be monitored as comprehensively as possible. For example, the infrared sensors may be deployed on a roof, a wall, etc., and the infrared sensors installed at different positions may collect the behavior activity data of the monitored person, and store the collected data in a database for data analysis by subsequent steps.
Further, in the foregoing specific implementation manner of S101, the position information and/or the center of gravity information of the monitored person may be specifically determined according to the installation position of the at least one infrared sensor. That is, as for the behavioral activity data, it may include position information of the monitored person and/or center of gravity information of the monitored person, and the position information and/or center of gravity information is determined based on the installation position of the infrared sensor that perceives the monitored person, and next, the position information and center of gravity information are specifically explained.
The location information may be a relative location of the monitored person within the monitoring environment, and the relative location may be a location interval.
Specifically, the spatial size of the monitoring environment may be predetermined, and a vertex position within the monitoring environment (e.g., one of four vertices of a roof) may be used as a start coordinate, such as the start coordinate being (0, 0), so that the position coordinates of other vertex positions within the monitoring environment and positions other than the vertices may be relative coordinates defined with respect to the start coordinate (0, 0).
Based on this, the position of each infrared sensor may be measured in advance, thereby defining the relative coordinates of each infrared sensor within the monitored environment. Therefore, when the position information of the monitored person is collected, the monitored person can be determined to be covered and sensed by the infrared sensors according to the signal output condition of the infrared sensors, and then the actual position of the monitored person is deduced according to the relative coordinates of the infrared sensors sensing the monitored person. For example, when the monitored person is sensed by two infrared sensors, sensor a and sensor B, at the same time, it can be determined that the monitored person is in the coverage area where sensor a and sensor B intersect, so that the specific coverage area where the monitored person is located can be determined according to the relative coordinates of sensor a and sensor B.
The center of gravity information may be center of gravity height information of the monitored person inferred from the sensing results of the infrared sensors installed at different heights, and the height information may be a height interval.
Specifically, the height of the center of gravity of the monitored person may be determined based on the fused information of the plurality of sensors. For example, if sensor a and sensor B sense the monitored person at the same time, the gravity center of the monitored person should be between 1.2 meters and 1.3 meters, assuming that sensor a covers a position with a height of between 1.2 meters and 2 meters and sensor B covers a position with a height of between 0 meters and 1.3 meters; if only sensor B senses the monitored person, the center of gravity of the monitored person should be below 1.2 meters at that time.
S102: generating walking state data by analyzing the behavioral activity data, wherein the walking state data reflects the walking state of the monitored person.
When the behavioral activity data includes the position information and/or the center of gravity information of the monitored person, S102 may specifically include: and generating walking state data by analyzing the position information and/or the gravity center information.
In this embodiment, the characteristic data of the monitored person, such as the step frequency, the gait continuity, the step change amplitude, the gravity center change amplitude, and the like, may be extracted and sorted based on the behavior activity data acquired in the time sequence, so as to form the walking state data.
Thus, in one embodiment of the present application, the walking state data may include one or more of the following 4 items of data:
item 1: the frequency of steps of the monitored person.
The step frequency refers to the number of steps taken by the monitored person within a preset time period, such as how many steps are taken per minute. Since the center of gravity of the monitored person is periodically changed during the walking process, the change of the center of gravity of the monitored person during the walking process can be known based on the center of gravity information mentioned in the above steps, and the number of steps taken by the monitored person within the preset time duration, for example, 20 steps per minute, can be further determined.
Item 2: data reflecting gait continuity of the monitored person.
As an example, the data reflecting the gait continuity may refer to whether the step frequency is smooth, and the related explanation of the step frequency may be referred to in item 1, which is not described herein again. For example, if the monitored person takes 30 steps in the first 1 minute and 15 steps in the next 1 minute, which indicates that the change of the step frequency is significant, it indicates that the step frequency is not stable, and thus the gait continuity is poor; if the monitored person takes 30 steps in the first 1 minute and 28 steps in the next 1 minute, which indicates that the change in the step frequency is not obvious, it indicates that the step frequency is relatively smooth, and thus that the gait continuity is relatively good.
As another example, the data reflecting the gait continuity may refer to whether the step distance is stable, the step distance refers to the distance that the monitored person takes using a preset number of steps, or how many steps the preset distance has taken, such as 10 steps finished by 7 meters. For example, if the monitored person walks 7 meters in the first 10 steps and walks 2 meters in the last 10 steps, which indicates that the distance change of each step is obvious, it indicates that the step distance is not stable, and thus the gait continuity is poor; if the monitored person walks 7 meters in the first 10 steps and walks 6 meters in the last 10 steps, which indicates that the distance change of each step is not obvious, the step distance is stable, and therefore the gait continuity is good.
The gravity center of the monitored person is periodically changed in the walking process, so that the gravity center change condition of the monitored person in the walking process can be obtained based on the gravity center information mentioned in the step, and the number of steps taken by the monitored person in the preset time duration is further determined; the distance traveled by the monitored person can be determined according to the position information mentioned in the above steps.
Item 3: data reflecting the magnitude of step change of the monitored person.
As an example, the step change amplitude may refer to the change amplitude of the step frequency mentioned in item 1 or item 2 above, and is referred to as step frequency change herein. Specifically, the number of steps and the duration of the steps may determine the frequency of the steps, and the average step frequency is calculated according to the statistical result of each time period (the monitored person is in a walking state), for example, the number of steps is counted for the monitored person every 1 minute, so that the step frequency change data can be calculated. For example, if the average step frequency of the monitored person in the first 1 minute is 30 steps/minute and the average step frequency of the next 1 minute is 16 steps/minute, it indicates that the step frequency change value (decrease value) is 14.
As another example, the step change amplitude may refer to the step distance change amplitude mentioned in item 2 above, referred to herein as a stride change. Specifically, the step size (i.e., the average distance traveled per step) may be determined by the number of steps and the distance, and the step size may be calculated according to a statistical result of each distance segment (in a walking state of the monitored person), for example, the monitored person counts the number of steps for each 3 meters traveled by the monitored person, and the average step size is calculated according to the statistical result, so as to calculate the step change data. For example, if the monitored person has an average stride of 0.5 m/step at the first 3 m and an average stride of 0.2 m/step at the last 3 m, it indicates that the stride change value (decrease value) is 0.3.
Item 4: data reflecting the magnitude of change in the center of gravity of the monitored person.
The gravity center variation amplitude can refer to the amplitude of the gravity center height variation of the monitored person in the walking process. Because the center of gravity of the person is periodically changed in the walking process, the change amplitude of the center of gravity of the monitored person in the walking process can be obtained based on the information of the center of gravity of the monitored person. For example, if the change amplitude of the center of gravity of the monitored person in the front and back 1 minute is not more than plus or minus 0.5 meter, the change amplitude of the center of gravity is normal, otherwise, the change amplitude of the center of gravity is abnormal.
S103: and predicting whether the monitored person has abnormal behavior according to the walking state data.
After the walking state data is generated, whether abnormal behaviors occur to the monitored person can be predicted according to the mutation frequency of each item of data in the walking state data.
Thus, as shown in fig. 2, in an embodiment of the present application, step S103 may specifically include the following steps:
s201: and determining mutation probability of each item of the walking state data, wherein the mutation probability represents mutation frequency of the corresponding item of data in a preset time period.
In this embodiment, if the walking state data includes the above item 1 data, that is, the step frequency of the monitored person, the abrupt change probability Pr1 of the step frequency needs to be determined, and specifically, the abrupt change probability Pr1 may be calculated according to the statistical result of the previous step frequency data and the current step frequency data. As an example, the mutation probability Pr1 may be calculated according to the number of mutations of the step frequency within a period of time, for example, the step frequency mutation occurs 3 times within a period of time (for example, 15 minutes) before the current time, and then Pr1 is equal to 3%.
In this embodiment, if the walking state data includes the above item 2 data, that is, the data reflecting the gait continuity of the monitored person, the abrupt change probability Pr2 of the gait continuity needs to be determined, and specifically, the abrupt change probability Pr2 can be calculated according to the statistical result of the previous gait continuity data and the current gait continuity data. As an example, the mutation probability Pr2 may be calculated according to the number of mutations of the gait continuity over a period of time, for example, the gait continuity mutation occurs 3 times in a period of time (for example, 15 minutes) before the current time, and then Pr2 is 3%.
In this embodiment, if the walking state data includes the above item 3 data, that is, the data reflecting the step variation amplitude of the monitored person, the abrupt change probability Pr3 of the step variation amplitude needs to be determined, and specifically, the abrupt change probability Pr3 may be calculated according to the statistical result of the previous step variation amplitude and the current step variation amplitude data. As an example, the mutation probability Pr3 may be calculated according to the number of mutations of the step change amplitude within a period of time, for example, the step change amplitude mutation occurs 3 times within a period of time (for example, 15 minutes) before the current time, and then Pr3 is equal to 3%.
In this embodiment, if the walking state data includes the above item 4 data, that is, the data reflecting the change amplitude of the center of gravity of the monitored person, the abrupt change probability Pr4 of the change amplitude of the center of gravity needs to be determined, and specifically, the abrupt change probability Pr4 may be calculated according to the statistical result of the change amplitude of the center of gravity of the previous step and the current change amplitude data of the center of gravity. As an example, the sudden change probability Pr4 may be calculated according to the number of sudden changes of the gravity center change amplitude within a period of time, for example, the gravity center change amplitude occurs 3 times within a period of time (for example, 15 minutes) before the current time, and then Pr4 is 3%.
S202: and predicting the probability of the abnormal behavior of the monitored person according to the mutation probability of each item of data.
The mutation probability parameters are input into a pre-established abnormal behavior prediction model, so that the probability Pr of the abnormal behavior of the monitored person can be predicted, and the method specifically comprises the following steps:
Pr＝1-(1-Pr1)*(1-Pr2)*(1-Pr3)*(1-Pr4)*100％
note that, for a data item not included in the walking state data, the mutation probability value corresponding to the data item is 1.
S203: judging whether the predicted probability is greater than a preset probability threshold value or not; if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
A probability threshold may be set, and when the probability Pr is greater than the probability threshold, it is determined that the monitored person has abnormal behavior, whereas when the probability Pr is not greater than the probability threshold, it is determined that the monitored person has no abnormal behavior. The probability threshold value can be determined according to statistical experience, and can be adjusted according to the actual situation of the monitored person.
Further, after the step S103 or step S203 predicts that the abnormal behavior occurs in the monitored person, the present embodiment may also predict which kind of abnormal behavior occurs in the monitored person, and therefore, in an embodiment of the present application, the method may further include: and predicting the abnormal behavior type of the monitored person according to the walking state data.
In this embodiment, as for each item of data included in the walking state data introduced in step S102, that is, as for the relevant data such as the step frequency, the gait continuity, the step change amplitude, the gravity center change amplitude, etc., one or more items of data may be used to predict the type of abnormal behavior that may occur in the monitored person.
For example, it can be determined from the data of the step change amplitude of the monitored person whether the step is suddenly accelerated or suddenly decelerated; if the pace is suddenly accelerated, the type of abnormal behavior of the monitored person may be "possible fall"; if the pace is suddenly slowed down, the type of abnormal behavior of the monitored person may be "may be faint".
On the basis, the gravity center change amplitude data of the monitored person can be further combined for prediction. Specifically, whether the center of gravity of the human body suddenly drops or not can be judged from the center of gravity change amplitude data of the monitored person by combining the specific occurrence time; if the gravity center suddenly drops and the judgment shows that the pace is suddenly accelerated, the abnormal behavior type of the monitored person can be 'fall'; if the gravity center does not drop suddenly and the judgment shows that the pace is suddenly accelerated, the abnormal behavior type of the monitored person can be 'unsuccessful fall'; if the gravity center suddenly drops and the judgment shows that the pace is suddenly slowed down, the abnormal behavior type of the monitored person can be 'faint'; if the center of gravity does not drop suddenly and the above determination yields that the pace is suddenly slowed down, the abnormal behavior pattern of the monitored person may be "mental state is not good enough".
Further, after the abnormal behavior of the monitored person is predicted through the step S103 or the step S203, an early warning function may be triggered, and specifically, early warning information may be sent to at least one preset communication device. The preset communication device may be a communication device of a guardian or an emergency contact, for example, if the monitored environment in which the monitored person is located is a home, the preset communication device may be a mobile phone of the family or a neighbor of the monitored person; if the monitored environment is a hospital or a nursing home, the preset communication device may be the family or the related person in charge of the monitored person. The early warning information may be prompt information indicating that the monitored person has abnormal behavior, such as text and/or voice information, and on the basis, a specific abnormal behavior type may be given.
Further, after the abnormal behavior type of the monitored person is predicted, the prediction result may be accurate or inaccurate because the abnormal behavior type is a prediction result, so that actual information fed back by a guardian and the like can be acquired to determine whether the prediction result is consistent with the actual state of the monitored person, thereby realizing self-learning, adjustment and optimization of the parameters of the prediction system, that is, adjusting the triggering conditions and parameters for sending out the early warning based on the actual condition of the monitored person.
Therefore, in an embodiment of the present application, the determination manner of the mutation probability and/or the magnitude of the preset probability threshold may be adjusted according to the abnormal behavior type and the actual state of the monitored person. For example, when the step frequency of the monitored person changes from 10 steps per minute to 14 steps per minute, although the monitored person does not actually have an abnormal phenomenon although the change occurs, the triggering of the warning information may be avoided by adjusting the mutation probability determination mode corresponding to the data and/or the size of the preset probability threshold.
In summary, the method for predicting abnormal behavior provided in the embodiment of the present application collects behavior activity data of a monitored person; generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person; and predicting whether the monitored person has abnormal behavior according to the walking state data. Therefore, the automatic prediction mode for the abnormal behaviors can find the abnormal behaviors of the monitored person in time, not only reduces the manual nursing cost, but also avoids the nursing problem that people cannot focus on spirit 24 hours a day by manual nursing.
Referring to fig. 3, a schematic diagram of a device for predicting abnormal behavior according to an embodiment of the present application is shown, where the device 300 includes:
a behavior data acquisition unit 301, configured to acquire behavior activity data of a monitored person;
a walking data obtaining unit 302, configured to generate walking state data by analyzing the behavior activity data, where the walking state data reflects a walking state of the monitored person;
an abnormal behavior prediction unit 303, configured to predict whether an abnormal behavior occurs in the monitored person according to the walking state data.
In one embodiment of the present application, the behavior data collecting unit 301 includes:
the first data acquisition subunit is used for acquiring the behavior activity data of the monitored person by utilizing at least one infrared sensor.
In one embodiment of the present application, the first data acquisition subunit includes:
the second data acquisition subunit is used for determining the position information and/or the gravity center information of the monitored person according to the installation position of the at least one infrared sensor;
accordingly, the walking data acquisition unit 302 includes:
and the walking data acquisition subunit is used for generating walking state data by analyzing the position information and/or the gravity center information.
In one embodiment of the present application, the walking state data includes one or more of the following data:
a step frequency of the monitored person;
data reflecting gait continuity of the monitored person;
data reflecting the step change amplitude of the monitored person;
data reflecting the magnitude of change in the center of gravity of the monitored person.
In one embodiment of the present application, the abnormal behavior prediction unit 303 includes:
the sudden change probability determining subunit is used for determining the sudden change probability of each item of data in the walking state data, and the sudden change probability represents the sudden change frequency of the corresponding item of data in a preset time period;
the abnormal probability determining subunit is used for predicting the probability of the abnormal behavior of the monitored person according to the mutation probability of each item of data;
the abnormal behavior prediction subunit is used for judging whether the predicted probability is greater than a preset probability threshold value; if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
In one embodiment of the present application, the apparatus 300 further comprises:
and the behavior type prediction unit is used for predicting the abnormal behavior type of the monitored person according to the walking state data after the abnormal behavior of the monitored person is predicted.
In one embodiment of the present application, the apparatus 300 further comprises:
and the trigger condition adjusting unit is used for adjusting the determination mode of the mutation probability and/or the size of the preset probability threshold according to the abnormal behavior type and the actual state of the monitored person.
In one embodiment of the present application, the apparatus 300 further comprises:
and the early warning information sending unit is used for sending early warning information to at least one preset communication device after the abnormal behavior of the monitored person is predicted.
Referring to fig. 4, a schematic diagram of a hardware structure of an abnormal behavior prediction apparatus provided in an embodiment of the present application is a hardware structure of the apparatus 400, where the apparatus 400 includes a memory 401 and a receiver 402, and a processor 403 connected to the memory 401 and the receiver 402, respectively, where the memory 401 is configured to store a set of program instructions, and the processor 403 is configured to call the program instructions stored in the memory 401 to perform the following operations:
acquiring behavior and activity data of a monitored person;
generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person;
and predicting whether the monitored person has abnormal behavior according to the walking state data.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
utilizing at least one infrared sensor, collecting behavioral activity data of the monitored person.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
determining the position information and/or the gravity center information of the monitored person according to the installation position of the at least one infrared sensor;
and generating walking state data by analyzing the position information and/or the gravity center information.
In one embodiment of the present application, the walking state data includes one or more of the following data:
a step frequency of the monitored person;
data reflecting gait continuity of the monitored person;
data reflecting the step change amplitude of the monitored person;
data reflecting the magnitude of change in the center of gravity of the monitored person.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
determining mutation probability of each item of the walking state data, wherein the mutation probability represents mutation frequency of the corresponding item of data in a preset time period;
predicting the probability of abnormal behaviors of the monitored person according to the mutation probability of each item of data;
judging whether the predicted probability is greater than a preset probability threshold value or not;
if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
and predicting the abnormal behavior type of the monitored person according to the walking state data.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
and adjusting the determination mode of the mutation probability and/or the size of the preset probability threshold according to the abnormal behavior type and the actual state of the monitored person.
In one embodiment of the present application, the processor 403 is further configured to call the program instructions stored in the memory 401 to perform the following operations:
and sending early warning information to at least one preset communication device.
In some embodiments, the processor 403 may be a Central Processing Unit (CPU), the Memory 401 may be an internal Memory of a Random Access Memory (RAM) type, and the receiver 402 may include a common physical interface, which may be an Ethernet (Ethernet) interface or an Asynchronous Transfer Mode (ATM) interface. The processor 403, receiver 402, and memory 401 may be integrated into one or more separate circuits or hardware, such as: application Specific Integrated Circuit (ASIC).
Further, an embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is caused to execute any implementation method of the above method for predicting an abnormal behavior.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A method for predicting abnormal behavior, comprising:
acquiring behavior activity data of a monitored person based on a time sequence; the time-based sequence acquisition of behavioral activity data of a monitored person includes:
collecting behavioral activity data of the monitored person using at least one infrared sensor;
generating walking state data by analyzing the behavioral activity data, the walking state data reflecting a walking state of the monitored person;
predicting whether the monitored person has abnormal behavior according to the mutation frequency of the walking state data; the walking state data comprises one or more of the following data:
a step frequency of the monitored person;
data reflecting gait continuity of the monitored person;
data reflecting the step change amplitude of the monitored person;
data reflecting the magnitude of change in the center of gravity of the monitored person.
2. The method of claim 1, wherein collecting behavioral activity data of the monitored person using at least one infrared sensor comprises:
determining the position information and/or the gravity center information of the monitored person according to the installation position of the at least one infrared sensor;
accordingly, the generating walking state data by analyzing the behavioral activity data comprises:
and generating walking state data by analyzing the position information and/or the gravity center information.
3. The method of claim 1, wherein predicting whether the monitored person is behaving abnormally based on the walking state data comprises:
determining mutation probability of each item of the walking state data, wherein the mutation probability represents mutation frequency of the corresponding item of data in a preset time period;
predicting the probability of abnormal behaviors of the monitored person according to the mutation probability of each item of data;
judging whether the predicted probability is greater than a preset probability threshold value or not;
if yes, predicting abnormal behaviors of the monitored person; if not, predicting that the monitored person does not have abnormal behaviors.
4. The method of claim 3, wherein after predicting the abnormal behavior of the monitored person, further comprising:
and predicting the abnormal behavior type of the monitored person according to the walking state data.
5. The method of claim 4, further comprising:
and adjusting the determination mode of the mutation probability and/or the size of the preset probability threshold according to the abnormal behavior type and the actual state of the monitored person.
6. The method of claim 3, wherein after predicting the abnormal behavior of the monitored person, further comprising:
and sending early warning information to at least one preset communication device.
7. An apparatus for predicting abnormal behavior, comprising:
the behavior data acquisition unit is used for acquiring behavior activity data of the monitored person based on the time sequence; the time-based sequence acquisition of behavioral activity data of a monitored person includes: collecting behavioral activity data of the monitored person using at least one infrared sensor;
a walking data acquisition unit for generating walking state data by analyzing the behavior activity data, the walking state data reflecting the walking state of the monitored person; the walking state data comprises one or more of the following data: a step frequency of the monitored person; data reflecting gait continuity of the monitored person; data reflecting the step change amplitude of the monitored person; data reflecting the magnitude of change in the center of gravity of the monitored person;
and the abnormal behavior prediction unit is used for predicting whether the monitored person has abnormal behavior according to the mutation frequency of the walking state data.
8. An apparatus for predicting abnormal behavior, comprising: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
the memory is to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1-6.
9. A computer-readable storage medium having stored therein instructions which, when run on a terminal device, cause the terminal device to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810169092.4A CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810169092.4A CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108281203A CN108281203A (en) | 2018-07-13 |
| CN108281203B true CN108281203B (en) | 2021-10-22 |
Family
ID=62808721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810169092.4A Active CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108281203B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118081B (en) * | 2018-08-08 | 2021-07-16 | 成都保源酷码科技有限公司 | Operation safety supervision system and method based on image processing mode |
| CN109492595B (en) * | 2018-11-19 | 2020-10-16 | 浙江传媒学院 | Behavior prediction method and system suitable for fixed group |
| CN111053562A (en) * | 2019-11-29 | 2020-04-24 | 广州三拾七度智能家居有限公司 | Tumble judgment method and device and terminal |
| CN111243369A (en) * | 2020-01-16 | 2020-06-05 | 西安科技大学 | Container type fire-fighting hidden danger accident recurrence experience training system |
| CN115065585A (en) * | 2022-04-29 | 2022-09-16 | 北京达佳互联信息技术有限公司 | Business abnormity monitoring method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577810A (en) * | 2013-11-13 | 2014-02-12 | 汕头大学 | Intelligent nursing method |
| CN105989695A (en) * | 2015-02-15 | 2016-10-05 | 中国移动通信集团公司 | Guarding object movement risk evaluation method and device |
| CN106919892A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | Behavior monitoring method and device |
| CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130158367A1 (en) * | 2000-06-16 | 2013-06-20 | Bodymedia, Inc. | System for monitoring and managing body weight and other physiological conditions including iterative and personalized planning, intervention and reporting capability |
| CN100450179C (en) * | 2006-05-30 | 2009-01-07 | 浙江工业大学 | Household safe and security equipment for solitary old person based on omnibearing computer vision |
| FR2929427B1 (en) * | 2008-03-26 | 2012-12-28 | Univ Rennes | METHOD FOR ASSESSING HEALTH AND / OR FORM, DEVICE AND CORRESPONDING COMPUTER PROGRAM PRODUCT |
| CN102811343B (en) * | 2011-06-03 | 2015-04-29 | 南京理工大学 | Intelligent video monitoring system based on behavior recognition |
| CN105286874B (en) * | 2015-11-03 | 2018-06-19 | 长安大学 | A kind of system and method for being used to predict Falls in Old People risk |
| CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | User behavior monitoring method and wearable equipment |
-
2018
- 2018-02-28 CN CN201810169092.4A patent/CN108281203B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577810A (en) * | 2013-11-13 | 2014-02-12 | 汕头大学 | Intelligent nursing method |
| CN105989695A (en) * | 2015-02-15 | 2016-10-05 | 中国移动通信集团公司 | Guarding object movement risk evaluation method and device |
| CN106919892A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | Behavior monitoring method and device |
| CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108281203A (en) | 2018-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108281203B (en) | Method and device for predicting abnormal behavior | |
| CN106097654B (en) | A kind of fall detection method and wearable falling detection device | |
| US8103477B2 (en) | System and method for measuring and reporting changes in walking speed | |
| US10508974B2 (en) | Storing analytical machine data based on change in scalar machine data indicating alert condition | |
| US20190110741A1 (en) | Life rhythm measurement system and life rhythm measurement method | |
| TWI624815B (en) | Behavior detection system and method thereof | |
| CN106510720B (en) | User state prompting method and device | |
| CN111414828B (en) | Abnormal aggregation identification method and device | |
| CN107255526A (en) | A kind of temperature checking method, detection module and detecting system | |
| JP6708980B2 (en) | Image processing system, image processing device, image processing method, and image processing program | |
| CN111506625A (en) | Alarm threshold determination method and device | |
| CN106919892B (en) | Behavior monitoring method and device | |
| CN110022529B (en) | Method and device for counting number of people in target area based on two sensing modes | |
| JP2019067207A (en) | Work determination program, work determination method and work determination apparatus | |
| CN112637021A (en) | Dynamic flow monitoring method and device based on linear regression algorithm | |
| CN112205939A (en) | Control method of cleaning robot, cleaning robot and Internet of things system | |
| JP2018174885A (en) | Determination device, terminal device, determination system, program, and determination method | |
| US20120270192A1 (en) | Behavior estimation apparatus, behavior estimation method, and computer readable medium | |
| CN106092133A (en) | Start the decision method of guest mode, device | |
| CN113671489A (en) | State reminding method and device, electronic equipment and computer readable storage medium | |
| CN112949442A (en) | Abnormal event pre-recognition method and device, electronic equipment and monitoring system | |
| CN111466918A (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
| EP3669338B1 (en) | Passive care control method and associated systems | |
| EP2982300B1 (en) | A system for identifying a change in walking speed of a person | |
| EP3929932A1 (en) | Method and system for frailty detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |