CN110811595B - Abnormal state detection method and device, electronic equipment and computer storage medium - Google Patents
Abnormal state detection method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN110811595B CN110811595B CN201911189664.6A CN201911189664A CN110811595B CN 110811595 B CN110811595 B CN 110811595B CN 201911189664 A CN201911189664 A CN 201911189664A CN 110811595 B CN110811595 B CN 110811595B
- Authority
- CN
- China
- Prior art keywords
- state
- user
- detected
- abnormal state
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/12—Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
Abstract
The invention provides a method and a device for detecting an abnormal state, electronic equipment and a computer storage medium, wherein the method comprises the following steps: acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment; processing the electrocardiosignals and the electroencephalogram signals of the user to be detected respectively to obtain characteristic vectors corresponding to the electrocardiosignals and characteristic vectors corresponding to the electroencephalogram signals respectively; processing the characteristic vector corresponding to the electrocardiosignal and the characteristic vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected; judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state; and if the target state corresponding to the user to be detected is judged to be an abnormal state, executing the processing operation corresponding to the abnormal state.
Description
Technical Field
The present invention relates to the field of computer science, and in particular, to a method and an apparatus for detecting an abnormal state, an electronic device, and a computer storage medium.
Background
At present, under various scenes, the real-time state of a user needs to be known, so that emergency operation is adopted according to different states of the user. For example: it is necessary to know whether the bank staff is in a dangerous state, whether the old people have sudden illness, and the like.
However, in the current technology, a user generally perceives the current state of the user autonomously, and if the user finds that the user is in an abnormal state, the user manually triggers the terminal device to feed back the current state. This way of passively feeding back information by the user is often not timely or accurate enough due to the limited personal perception capabilities of the user.
Therefore, there is an urgent need for a scheme capable of automatically feeding back a signal of a user state and automatically triggering an emergency operation according to different situations of the signal.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for detecting an abnormal state, an electronic device, and a computer storage medium, so as to provide a scheme for automatically triggering an emergency operation when an abnormal state of a user is detected.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the first aspect of the present invention provides a method for detecting an abnormal state, including:
acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment;
processing the electrocardiosignals and the electroencephalogram signals of the user to be detected respectively to obtain characteristic vectors corresponding to the electrocardiosignals and characteristic vectors corresponding to the electroencephalogram signals respectively;
processing the characteristic vector corresponding to the electrocardiosignal and the characteristic vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected;
judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state;
and if the target state corresponding to the user to be detected is judged to be an abnormal state, executing the processing operation corresponding to the abnormal state.
Optionally, the method for constructing the prediction model includes:
obtaining a plurality of training samples of an initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state;
calculating to obtain a characteristic vector corresponding to the central electric signal of each training sample and a characteristic vector corresponding to the electroencephalogram signal;
and respectively inputting the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal in each training sample into an initial GA-BP neural network model, and training the initial GA-BP neural network model by combining a genetic algorithm until convergence to obtain the prediction model.
Optionally, the determining whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state includes:
inquiring a comparison table according to the state predicted value to obtain a state interval where the state predicted value is located; wherein the look-up table comprises: the corresponding relation between the state interval and the target state;
determining a target state corresponding to the state interval;
and identifying whether the target state belongs to an abnormal state.
Optionally, if it is determined that the target state of the user to be detected is an abnormal state, executing a processing operation corresponding to the abnormal state, including:
if the target state of the user to be detected is judged to be a first abnormal state, generating and outputting reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state; if the target state of the user to be detected is judged to be a second abnormal state, sending alarm information to a target client, and detecting whether feedback information of the target client is received; if the feedback information is not detected within a preset time period, sending the alarm information to a target server; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for explaining that the user to be detected is in the second abnormal state currently.
A second aspect of the present invention provides an abnormal state detection apparatus, including:
the first acquisition unit is used for acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment;
the first processing unit is used for respectively processing the electrocardiosignals and the electroencephalogram signals of the user to be detected to respectively obtain the characteristic vectors corresponding to the electrocardiosignals and the electroencephalogram signals;
the second processing unit is used for processing the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected;
the judging unit is used for judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state;
and the execution unit is used for executing the processing operation corresponding to the abnormal state if the state of the user to be detected is judged to be the abnormal state.
In the above detection apparatus, optionally, the detection apparatus further includes:
the second acquisition unit is used for acquiring a plurality of training samples of the initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state;
the computing unit is used for computing to obtain a feature vector corresponding to the central electric signal of each training sample and a feature vector corresponding to the electroencephalogram signal;
a construction unit, configured to input a feature vector corresponding to the electrocardiographic signal and a feature vector corresponding to the electroencephalogram signal in each of the training samples into an initial GA-BP neural network model, respectively, train the initial GA-BP neural network model in combination with a genetic algorithm until convergence, and obtain the prediction model
Optionally, the determining unit includes:
the inquiring subunit is used for inquiring a comparison table according to the state prediction value to obtain a state interval where the state prediction value is located; wherein the look-up table comprises: the corresponding relation between the state interval and the target state;
the determining subunit is used for determining a target state corresponding to the state interval;
and the identification subunit is used for identifying whether the target state belongs to an abnormal state.
Optionally, the execution unit includes:
the generating unit is used for generating reminding information if the judging unit judges that the target state of the user to be detected is a first abnormal state;
the output unit is used for outputting the reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state;
the sending unit is used for sending alarm information to a target client if the judging unit judges that the target state of the user to be detected is a second abnormal state; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for indicating that the user to be detected is in the second abnormal state currently;
the detection unit is used for detecting whether feedback information of the target client is received or not after the sending unit sends the alarm information;
and the sending unit is further used for sending the alarm information to a target server if the detection unit does not detect the feedback information within a preset time period.
A third aspect of the invention provides an electronic device comprising a processor and a memory; wherein:
the memory is to store computer instructions;
the processor is configured to execute the computer instructions stored in the memory, and in particular, to perform the method for detecting an abnormal state provided in any one of the above.
A fourth aspect of the present invention provides a computer storage medium storing a program for implementing the method of detecting an abnormal state as provided in any one of the above.
Compared with the prior art, the invention has the following advantages:
in the method for detecting an abnormal state provided by the embodiment of the invention, an electrocardiosignal and an electroencephalogram signal of a user to be detected are obtained, the electrocardiosignal and the electroencephalogram signal of the user to be detected are respectively processed, and a feature vector corresponding to the electrocardiosignal and a feature vector corresponding to the electroencephalogram signal are respectively obtained; processing the characteristic vector corresponding to the electrocardiosignal and the characteristic vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected; judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state; and if the target state corresponding to the user to be detected is judged to be an abnormal state, executing the processing operation corresponding to the abnormal state. And when the abnormal state is the robbed state, the corresponding operation executed is automatic alarm. Therefore, by applying the method provided by the embodiment of the invention, the state of the user can be predicted according to the expression of the electrocardiosignals and the electroencephalograms of the user by acquiring the electrocardiosignals and the electroencephalograms of the user, and the emergency operation scheme is automatically triggered when the state of the user is in an abnormal state, so that the safety of personnel and property are protected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting an abnormal state according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of step S104 according to another embodiment of the present invention;
FIG. 3 is a flowchart of a method for detecting an abnormal state according to another embodiment of the present invention;
fig. 4 is a schematic structural diagram of an abnormal state detection apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
In this application, 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.
An embodiment of the present invention provides a method for detecting an abnormal state, which can refer to fig. 1, and includes:
s101, acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through the user wearing equipment.
In the embodiment of the invention, the electrocardiosignals and the electroencephalogram signals of the user to be detected can be obtained by detecting the user to be detected through the user wearing equipment, and the user wearing equipment can scan the brain of the user to be detected so as to obtain the electroencephalogram signals of the user to be detected. Of course, the pulse of the user can also be detected to obtain the electrocardiosignal of the user to be detected. For example: the user wearing equipment can include the intelligent bracelet, but by utilizing the built-in heart rate detection device real-time detection of intelligent bracelet to detect the electrocardiosignal who waits to detect the user.
S102, the electrocardiosignals and the electroencephalogram signals of a user to be detected are respectively processed to respectively obtain the characteristic vectors corresponding to the electrocardiosignals and the characteristic vectors corresponding to the electroencephalogram signals.
In the embodiment of the invention, the electrocardiosignals and the electroencephalogram signals of the user to be detected are respectively processed. For example, for the electrocardiosignal of the user to be detected, the abnormal value in the electrocardiosignal of the user to be detected can be removed by performing noise reduction and smoothing on the electrocardiosignal to obtain a processed electrocardiosignal, and then the processed electrocardiosignal is calculated to obtain a feature vector corresponding to the electrocardiosignal. The electroencephalogram signal of the user to be detected can be subjected to normalization processing, and then the electroencephalogram signal subjected to normalization processing is subjected to time synchronization framing to obtain a feature vector of the electroencephalogram signal.
It should be noted that the embodiments of the present invention include, but are not limited to, the above-mentioned processing method for the cardiac electrical signal and the electroencephalogram signal.
S103, processing the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected.
In the embodiment of the invention, on the basis of the pre-established prediction model, the electrocardio characteristics and the electroencephalogram characteristics of the user to be detected can be used as two characteristic vectors of the prediction model and input into the prediction model to output corresponding values, namely the state prediction value of the user to be detected. Optionally, the individual differences may also be calculated and input into the model as the third feature vector.
Optionally, in another embodiment of the present invention, the training process of the pre-established prediction model may refer to the following:
obtaining a plurality of training samples of an initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state.
In the implementation of the invention, the abnormal states can be different abnormal states, for example, the states of 50 users when being robbed can be taken as the abnormal states and taken as the training samples of the initial GA-BP prediction model, and the electrocardiosignals and the electroencephalograms in each training sample of the states when being robbed are utilized to carry out iterative training so as to train out the corresponding state prediction values when the users are robbed; the state of 50 users with overtime fatigue or tiredness and illness can be used as an abnormal state, the electrocardiosignals and the electroencephalogram signals in each training sample of the state of overtime fatigue or tiredness and illness are used for iterative training, and the state prediction value corresponding to the overtime fatigue or tiredness and illness is trained through the prediction model.
Optionally, states of 50 users in illegal operations can be used as abnormal states, and iterative training is performed by using the electrocardiosignals and the electroencephalogram signals in each training sample of the states in illegal operations, so as to train a state prediction value corresponding to the illegal operations of the users; the illegal operation refers to an illegal action made by a user who does not obey a rule of keeping watch; such as being on duty, etc.
It should be noted that different abnormal states are different training samples, but in the same prediction model, a plurality of abnormal states of the same type may be used as training samples of the prediction model, respectively, to train a prediction model including state prediction values corresponding to a plurality of abnormal states.
And calculating to obtain a characteristic vector corresponding to the central electric signal of each training sample and a characteristic vector corresponding to the electroencephalogram signal.
And respectively inputting the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal in each training sample into an initial GA-BP neural network model, and training the initial GA-BP neural network model by combining a genetic algorithm until convergence to obtain the prediction model.
In this embodiment, a three-layer neural network model may be established on the overall framework of the prediction model, and an initial value is assigned to each connection weight in the three-layer neural network model; the three-layer neural network model comprises an input layer, a hidden layer and an output layer. Furthermore, the number of nodes of the hidden layer is set, and a transfer function between the input layer and the hidden layer and a transfer function between the hidden layer and the output layer are established. And respectively inputting the electrocardiosignals and the electroencephalogram signals of all the request samples to carry out iterative training on the three-layer neural network model so as to respectively obtain the correction coefficient of each connection weight. And respectively correcting the initial value of each connection weight by using the correction coefficient of each connection weight until convergence so as to obtain a trained prediction model.
Optionally, according to the kolmogorov principle, one three-layer BP neural network is enough to complete any mapping from n dimensions to m dimensions, and generally only one implicit function layer is needed.
And S104, judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state.
In the embodiment of the present invention, after the electrocardiosignals and the electroencephalograms of the user to be detected are processed in step S103 to obtain the state prediction value of the user to be detected, it is further determined whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state.
Optionally, in another embodiment of the present invention, determining whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state may refer to fig. 2, where the method includes:
s201, inquiring according to a state prediction value comparison table to obtain a state interval where a state prediction value is located; wherein, the comparison table comprises: and the corresponding relation between the state interval and the target state.
In the embodiment of the invention, a comparison table of state predicted values is preset; therefore, the comparison table is inquired according to the state prediction value, and the state interval where the state prediction value is located can be obtained. It should be noted that, the abnormal state and the normal state both correspond to one state interval, and different abnormal states also correspond to different state intervals; therefore, the state interval where the state predicted value is located can be known by putting the state predicted value into the comparison table for query.
And S202, determining a target state corresponding to the state interval.
In the embodiment of the invention, after the state interval is obtained, the current state, namely the target state, of the user to be detected can be further determined according to the state interval.
S203, identifying whether the target state belongs to an abnormal state.
In the embodiment of the invention, whether the target state belongs to the abnormal state is finally determined, and if the target state belongs to the abnormal state, the type of the abnormal state to which the abnormal state belongs is identified.
And S105, if the target state of the user to be detected is judged to be an abnormal state, executing processing operation corresponding to the abnormal state.
In the embodiment of the invention, corresponding execution programs are pre-configured for each abnormal state, and when the target state of the user to be detected is judged to be the abnormal state, corresponding processing operation is executed according to the type of the abnormal state.
For example, when the target state of the user to be detected is determined to be overtime tired or tired and sick, a program for reminding the user to take a rest or seek medical advice in time is executed.
And when the target state of the user to be detected is judged to be the robbed state, executing an automatic alarm program.
And when the target state of the user to be detected is judged to be the illegal operation state, feeding back information to the background system so as to facilitate checking and processing by a worker.
It should be noted that, if it is determined that the target state of the user to be detected is a normal state, the process is not performed, and the process returns to the next detection operation.
Optionally, another embodiment of the present invention includes, but is not limited to: when the target state of the user to be detected is judged to be a first abnormal state, generating and outputting reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state at present. It is also noted that the first abnormal condition may be overtime tiredness or tiredness.
When the target state of the user to be detected is judged to be a second abnormal state, sending alarm information to the target client, and detecting whether feedback information of the target client is received; if the feedback information is not detected within a preset time period, sending alarm information to a target server; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for explaining that the user to be detected is in the second abnormal state currently.
In the method for detecting an abnormal state provided by the embodiment of the invention, an electrocardiosignal and an electroencephalogram signal of a user to be detected are obtained, the electrocardiosignal and the electroencephalogram signal of the user to be detected are respectively processed, and a feature vector corresponding to the electrocardiosignal and a feature vector corresponding to the electroencephalogram signal are respectively obtained; processing the characteristic vector corresponding to the electrocardiosignal and the characteristic vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected; judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state; and if the target state corresponding to the user to be detected is judged to be an abnormal state, executing the processing operation corresponding to the abnormal state. And when the abnormal state is the robbed state, the corresponding operation executed is automatic alarm. Therefore, by applying the method provided by the embodiment of the invention, the state of the operator can be predicted according to the expression of the electrocardiosignals and the electroencephalograms of the user by acquiring the electrocardiosignals and the electroencephalograms of the user, and the emergency operation scheme is automatically triggered when the state of the operator is in an abnormal state, so that the safety of personnel and property are protected.
Optionally, another embodiment of the present invention provides a method for detecting an abnormal state, which can be referred to fig. 3, including:
s301, acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting a user to be detected through user wearable equipment.
S302, the electrocardiosignals and the electroencephalogram signals of the user to be detected are processed respectively, and the feature vectors corresponding to the electrocardiosignals and the feature vectors corresponding to the electroencephalogram signals are obtained respectively.
S303, processing the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal by using the pre-established prediction model to obtain the state prediction value of the user to be detected.
In the embodiment of the present invention, the specific execution contents of step S301 to step S303 may refer to the contents of step S101 to step S103 in the embodiment of fig. 1, and are not described herein again.
S304, judging whether the target state corresponding to the state prediction value of the user to be detected is a robbed state.
It should be noted that, in the embodiment of the present invention, the robbed state is one of the abnormal states.
S305, if the detection state of the user to be detected is judged to be a robbed state, executing an alarm program, and pushing alarm information to a target client.
It should be noted that when the electrocardiographic signal and the electroencephalogram signal of the user to be detected are processed by the prediction model, and the state corresponding to the obtained state prediction value is the target state, it indicates that the user to be detected is likely to be robbed. Therefore, according to a preset program, the alarm program is executed to push the alarm information to the target client. The target client can be the intelligent device of the user, and the pushing mode can be realized through a short message or an information pushing function on the corresponding APP.
S306, if the to-be-detected user does not process the alarm information within the preset time, the alarm information is automatically sent to a target server.
For example, when a gangster is robbed by holding a gun, the gangster may be in charge of the hostage or otherwise coerce the officer to fail to alarm. If the user is forced to alarm at this time, the result can be hard to imagine. Therefore, by detecting the abnormal state of the user and when the abnormal state is the abnormal state during robbery, the alarm information is firstly pushed to the corresponding user, and if the alarm information is not processed by the member within the preset time, the alarm information is automatically sent to the public security system. At the moment, the gangster cannot know that the alarm is given, thereby being beneficial to reducing the bank loss and ensuring the safety of personnel and property. Alternatively, the preset time may be set in a customized manner, for example, one minute or two minutes.
According to the method provided by the embodiment of the invention, the electrocardiosignals and the electroencephalogram signals of the user are processed through the prediction model, and the state of the user is predicted; when the user is in the robbed state, an automatic alarm program is executed to protect the safety of personnel and property.
An embodiment of the present invention further provides a device for detecting an abnormal state, which can refer to fig. 4, and includes:
a first obtaining unit 401, configured to obtain an electrocardiographic signal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment;
the first processing unit 402 is configured to process the electrocardiographic signal and the electroencephalogram signal of the user to be detected respectively to obtain a feature vector corresponding to the electrocardiographic signal and a feature vector corresponding to the electroencephalogram signal respectively;
the second processing unit 403 is configured to process the feature vector corresponding to the electrocardiographic signal and the feature vector corresponding to the electroencephalogram signal by using a pre-established prediction model, so as to obtain a state prediction value of the user to be detected;
a determining unit 404, configured to determine whether a target state corresponding to the predicted state value of the user to be detected is an abnormal state;
and the executing unit 405 is configured to execute a processing operation corresponding to the abnormal state if the state of the user to be detected is determined to be the abnormal state.
It should be further noted that, in this embodiment, for specific execution processes of the first obtaining unit 401, the first processing unit 402, the second processing unit 403, the determining unit 404, and the executing unit 405, reference may be made to the content of the method embodiment corresponding to fig. 1, and details are not described here again.
In the apparatus provided by the embodiment of the present invention, a first obtaining unit 401 obtains an electrocardiographic signal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment; the first processing unit 402 respectively processes the electrocardiosignals and the electroencephalogram signals of the user to be detected to respectively obtain feature vectors corresponding to the electrocardiosignals and feature vectors corresponding to the electroencephalogram signals; the second processing unit 403 processes the feature vector corresponding to the electrocardiographic signal and the feature vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected; the determining unit 404 determines whether the target state corresponding to the predicted state value of the user to be detected is an abnormal state; when judging that the state of the user to be detected is an abnormal state, the execution unit 405 executes a processing operation corresponding to the abnormal state. For example, when the abnormal state is the robbed state, the corresponding operation executed is automatic alarm. Therefore, by applying the method provided by the embodiment of the invention, the state of the traveler can be predicted according to the expression of the electrocardiosignals and the electroencephalograms of the user by acquiring the electrocardiosignals and the electroencephalograms of the traveler, and the emergency operation scheme is automatically triggered when the state of the user is in an abnormal state, so that the safety of personnel and property are protected.
Optionally, in another embodiment of the present invention, the apparatus for detecting an abnormal state further includes:
the second acquisition unit is used for acquiring a plurality of training samples of the initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state.
And the computing unit is used for computing to obtain a feature vector corresponding to the central electric signal of each training sample and a feature vector corresponding to the electroencephalogram signal.
And the construction unit is used for respectively inputting the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal in each training sample into the initial GA-BP neural network model, and training the initial GA-BP neural network model by combining a genetic algorithm until convergence so as to obtain the prediction model.
It should be further noted that, in this embodiment, for specific execution processes of the second obtaining unit, the calculating unit and the constructing unit, reference may be made to the contents of the method embodiment corresponding to fig. 1, and details are not repeated here
Optionally, in another embodiment of the present invention, the determining unit 404 includes:
the inquiring subunit is used for inquiring the comparison table according to the state predicted value to obtain a state interval in which the state predicted value is located; wherein, the comparison table comprises: the corresponding relation between the state interval and the target state;
and the determining subunit is used for determining the target state corresponding to the state interval.
And the identification unit is used for identifying whether the target state belongs to the abnormal state.
It should be further noted that, in this embodiment, the specific execution processes of querying the sub-unit, determining the sub-unit, and identifying the sub-unit may refer to the contents of the method embodiment corresponding to fig. 1, which are not described herein again.
Optionally, in another embodiment of the present invention, the execution unit 405 includes:
a generating unit, configured to generate a prompting message if the determining unit 404 determines that the target state of the user to be detected is the first abnormal state.
The output unit is used for outputting the reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state currently.
The sending unit is used for sending alarm information to the target client if the judging unit judges that the target state of the user to be detected is a second abnormal state; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for explaining that the user to be detected is in the second abnormal state currently.
And the detection unit is used for detecting whether the feedback information of the target client is received or not after the sending unit sends the alarm information.
And the sending unit is further used for sending the alarm information to a target server if the detection unit does not detect the feedback information within a preset time period.
It should be further noted that, in this embodiment, for specific implementation processes of the generating unit, the outputting unit, the sending unit, and the detecting unit, reference may be made to the content of the method embodiment corresponding to fig. 3, and details are not described here again.
Another embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501 and a memory 502; wherein:
the memory 502 is used to store computer instructions;
the processor 501 is configured to execute the computer instructions stored in the memory, and in particular, to execute the method for managing advertisement delivery according to any of the embodiments described above.
Another embodiment of the present invention further provides a computer storage medium for storing a program, which when executed, is configured to implement the method for managing advertisement delivery provided in any one of the above embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. 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 invention. Thus, the present invention 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 (8)
1. A method for detecting an abnormal state, comprising:
acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment;
processing the electrocardiosignals and the electroencephalogram signals of the user to be detected respectively to obtain characteristic vectors corresponding to the electrocardiosignals and characteristic vectors corresponding to the electroencephalogram signals respectively;
processing the characteristic vector corresponding to the electrocardiosignal and the characteristic vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected;
judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state;
if the target state corresponding to the user to be detected is judged to be an abnormal state, executing processing operation corresponding to the abnormal state;
if the target state of the user to be detected is judged to be an abnormal state, executing processing operation corresponding to the abnormal state, wherein the processing operation comprises the following steps: if the target state of the user to be detected is judged to be a first abnormal state, generating and outputting reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state; if the target state of the user to be detected is judged to be a second abnormal state, sending alarm information to a target client, and detecting whether feedback information of the target client is received; if the feedback information is not detected within a preset time period, sending the alarm information to a target server; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for explaining that the user to be detected is in the second abnormal state currently.
2. The detection method according to claim 1, wherein the construction method of the prediction model comprises:
obtaining a plurality of training samples of an initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state;
calculating to obtain a characteristic vector corresponding to the central electric signal of each training sample and a characteristic vector corresponding to the electroencephalogram signal;
and respectively inputting the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal in each training sample into an initial GA-BP neural network model, and training the initial GA-BP neural network model by combining a genetic algorithm until convergence to obtain the prediction model.
3. The detection method according to claim 1, wherein the determining whether the target state corresponding to the predicted value of the state of the user to be detected is an abnormal state comprises:
inquiring a comparison table according to the state predicted value to obtain a state interval where the state predicted value is located; wherein the look-up table comprises: the corresponding relation between the state interval and the target state;
determining a target state corresponding to the state interval;
and identifying whether the target state belongs to an abnormal state.
4. An abnormal state detection device, comprising:
the first acquisition unit is used for acquiring an electrocardiosignal and an electroencephalogram signal of a user to be detected; the electrocardiosignal and the electroencephalogram signal are obtained by detecting the user to be detected through user wearing equipment;
the first processing unit is used for respectively processing the electrocardiosignals and the electroencephalogram signals of the user to be detected to respectively obtain the characteristic vectors corresponding to the electrocardiosignals and the electroencephalogram signals;
the second processing unit is used for processing the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal by using a pre-established prediction model to obtain a state prediction value of the user to be detected;
the judging unit is used for judging whether the target state corresponding to the state prediction value of the user to be detected is an abnormal state;
the execution unit is used for executing the processing operation corresponding to the abnormal state if the judging unit judges that the state of the user to be detected is the abnormal state;
the execution unit includes:
the generating unit is used for generating reminding information if the judging unit judges that the target state of the user to be detected is a first abnormal state;
the output unit is used for outputting the reminding information; the first abnormal state is used for explaining that the body of the user to be detected is in an abnormal state; the reminding information is used for reminding the user to be detected to be in the first abnormal state;
the sending unit is used for sending alarm information to a target client if the judging unit judges that the target state of the user to be detected is a second abnormal state; the second abnormal state is used for indicating that the user to be detected is in a dangerous state; the alarm information is used for indicating that the user to be detected is in the second abnormal state currently;
the detection unit is used for detecting whether feedback information of the target client is received or not after the sending unit sends the alarm information;
and the sending unit is further used for sending the alarm information to a target server if the detection unit does not detect the feedback information within a preset time period.
5. The detection device of claim 4, further comprising:
the second acquisition unit is used for acquiring a plurality of training samples of the initial GA-BP prediction model; the electrocardiosignal and the electroencephalogram signal in each training sample are obtained by detecting the user in an abnormal state;
the computing unit is used for computing to obtain a feature vector corresponding to the central electric signal of each training sample and a feature vector corresponding to the electroencephalogram signal;
and the construction unit is used for respectively inputting the feature vector corresponding to the electrocardiosignal and the feature vector corresponding to the electroencephalogram signal in each training sample into the initial GA-BP neural network model, and training the initial GA-BP neural network model by combining a genetic algorithm until convergence so as to obtain the prediction model.
6. The detection apparatus according to claim 4, wherein the determination unit includes:
the inquiring subunit is used for inquiring a comparison table according to the state prediction value to obtain a state interval where the state prediction value is located; wherein the look-up table comprises: the corresponding relation between the state interval and the target state;
the determining subunit is used for determining a target state corresponding to the state interval;
and the identification subunit is used for identifying whether the target state belongs to an abnormal state.
7. An electronic device comprising a processor and a memory; wherein:
the memory is to store computer instructions;
the processor is configured to execute the computer instructions stored in the memory, and in particular, to perform the method of detecting an abnormal state according to any one of claims 1 to 3.
8. A computer storage medium storing a program for implementing the abnormal state detection method according to any one of claims 1 to 3 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911189664.6A CN110811595B (en) | 2019-11-28 | 2019-11-28 | Abnormal state detection method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911189664.6A CN110811595B (en) | 2019-11-28 | 2019-11-28 | Abnormal state detection method and device, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110811595A CN110811595A (en) | 2020-02-21 |
| CN110811595B true CN110811595B (en) | 2022-04-08 |
Family
ID=69542638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911189664.6A Active CN110811595B (en) | 2019-11-28 | 2019-11-28 | Abnormal state detection method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110811595B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090082688A1 (en) * | 2006-01-05 | 2009-03-26 | Compumedics Ltd. | Localising and displaying electrophysiological signals |
| CN104665849A (en) * | 2014-12-11 | 2015-06-03 | 西南交通大学 | Multi-physiological signal multi-model interaction-based high-speed railway dispatcher stress detecting method |
| CN105877766A (en) * | 2016-06-21 | 2016-08-24 | 东北大学 | Mental state detection system and method based on multiple physiological signal fusion |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
| CN109447354A (en) * | 2018-10-31 | 2019-03-08 | 中国银行股份有限公司 | A kind of intelligent bank note distribution method and device based on GA-BP neural network |
| CN109498041A (en) * | 2019-01-15 | 2019-03-22 | 吉林大学 | Driver road anger state identification method based on brain electricity and pulse information |
-
2019
- 2019-11-28 CN CN201911189664.6A patent/CN110811595B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090082688A1 (en) * | 2006-01-05 | 2009-03-26 | Compumedics Ltd. | Localising and displaying electrophysiological signals |
| CN104665849A (en) * | 2014-12-11 | 2015-06-03 | 西南交通大学 | Multi-physiological signal multi-model interaction-based high-speed railway dispatcher stress detecting method |
| CN105877766A (en) * | 2016-06-21 | 2016-08-24 | 东北大学 | Mental state detection system and method based on multiple physiological signal fusion |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
| CN109447354A (en) * | 2018-10-31 | 2019-03-08 | 中国银行股份有限公司 | A kind of intelligent bank note distribution method and device based on GA-BP neural network |
| CN109498041A (en) * | 2019-01-15 | 2019-03-22 | 吉林大学 | Driver road anger state identification method based on brain electricity and pulse information |
Non-Patent Citations (3)
| Title |
|---|
| Facial and Bio-Signal Fusion Based Driver Alertness System Using Dynamic Bayesian Network;Sasikumar S 等;《IEEE》;20140308;全文 * |
| 基于生理信号的情感识别方法研究;温万惠;《中国博士学位论文全文数据库 哲学与人文科学辑》;20100815;全文 * |
| 基于生理参数融合的心理压力评估方法及系统研究;杨亚丹;《中国优秀硕士学位论文全文数据库 哲学与人文科学辑》;20160115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110811595A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5038899B2 (en) | Wireless sensor network and wireless sensor network method | |
| CN103561652A (en) | Method and system for assisting patients | |
| WO2019109738A1 (en) | Login method and apparatus, and electronic device | |
| CN106960126B (en) | Data early warning method and equipment | |
| CN105662384A (en) | Method and device for monitoring whether human heart rate is normal | |
| EP3640935B1 (en) | Notification information output method, server and monitoring system | |
| US11116413B2 (en) | Systems, devices, and/or methods for managing health | |
| CN112150766B (en) | Early warning method and device for remote safety prevention and control | |
| CN108156219A (en) | The method and server that a kind of equipment is given for change | |
| US20200194127A1 (en) | Biometric data capturing and analysis using a hybrid sensing systems | |
| CN110811595B (en) | Abnormal state detection method and device, electronic equipment and computer storage medium | |
| CN108108974A (en) | Method of payment and device and electronic equipment | |
| CN112446803A (en) | Monitoring system, monitoring method, monitoring device, and monitoring medium | |
| US20200138299A1 (en) | Hearing system with heart rate monitoring and related method | |
| KR20190080598A (en) | System for recognizing emotion using biometric data and method thereof | |
| CN109472195A (en) | Identify the methods, devices and systems of object | |
| CN112089593B (en) | Anti-losing method of neck massager, neck massager and storage device | |
| CN114586073A (en) | Biometric data capture and analysis using a hybrid sensing system | |
| US11666265B2 (en) | Hearing system with heart condition alert and related methods | |
| CN112396727A (en) | Response method and system of first-aid request and terminal equipment | |
| US20210109801A1 (en) | Anomaly assessment device, anomaly assessment method, and storage medium whereupon anomaly assessment program is recorded | |
| EP3448238A1 (en) | Physiological measurement processing | |
| CN107391938B (en) | Parameter evaluation method and equipment for human body implanted medical device | |
| CN116258489A (en) | Safe payment method applied to POS machine | |
| CN107682164B (en) | Data processing method and related equipment |
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 |