CN111478950B

CN111478950B - Object state pushing method and device

Info

Publication number: CN111478950B
Application number: CN202010225158.4A
Authority: CN
Inventors: 李家骥
Original assignee: Weimin Insurance Agency Co Ltd
Current assignee: Weimin Insurance Agency Co Ltd
Priority date: 2020-03-26
Filing date: 2020-03-26
Publication date: 2023-04-18
Anticipated expiration: 2040-03-26
Also published as: CN111478950A

Abstract

The application relates to a method and a device for pushing an object state, wherein the method comprises the following steps: detecting a target wireless network signal of a first terminal device in a listening range of a target access device in a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, and the first terminal device is configured on a target object; determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position; and executing target push operation corresponding to the target object state to second terminal equipment corresponding to the target scene. The problem of object monitoring mode among the correlation technique have the control human cost height, and the control timeliness is poor is solved in this application.

Description

Object state pushing method and device

Technical Field

The present application relates to the field of computers, and in particular, to a method and an apparatus for pushing an object state.

Background

Accidents inevitably occur to special people (such as the old with attention and body coordination hypofunction) during activities, if the treatment is not timely, the accidents can cause great damage to the human body, and if the treatment is timely, sequelae are not usually left.

Some special people are cared in a special institution, for example, some old people are cared in a nursing institution in a unified way. At present, the nursing organization usually cannot perform one-to-one 24-hour real-time nursing, and most nursing organizations monitor the old people (the nursed people) through manual video monitoring based on cameras.

However, video surveillance is labor-intensive and prone to negligence (e.g., there may be dead monitoring corners). Moreover, for hidden places such as a toilet, a bedroom and the like, videos are not suitable for being distributed and controlled, so that real-time monitoring is difficult to achieve through video monitoring, the video monitoring only can be used for post-inspection, and accidents cannot be handled in time.

Therefore, the object monitoring method in the related art has the problems of high monitoring labor cost and poor monitoring timeliness.

Disclosure of Invention

The application provides a pushing method and a pushing device for object states, and aims to at least solve the problems that monitoring labor cost is high and monitoring timeliness is poor in an object monitoring mode in the related technology.

According to an aspect of an embodiment of the present application, there is provided a method for pushing an object state, including: detecting a target wireless network signal of a first terminal device in a listening range of a target access device in a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, and the first terminal device is configured on a target object; determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position; and executing target pushing operation corresponding to the target object state to second terminal equipment corresponding to the target scene.

According to another aspect of the embodiments of the present application, there is provided an apparatus for pushing a state of an object, including: the detection unit is used for detecting a target wireless network signal of a first terminal device in a monitoring range of a target access device in a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, and the first terminal device is configured on a target object; the determining unit is used for determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position; and the first sending unit is used for executing the target pushing operation corresponding to the target object state to the second terminal equipment corresponding to the target scene.

Optionally, the determining unit includes: the extraction module is used for extracting target signal characteristics of the target wireless network signals through the target signal detection model; and the acquisition module is used for acquiring the movement parameter information corresponding to the target signal characteristics through the target signal detection model to obtain the target object state.

Optionally, the extraction module comprises: the first input submodule is used for inputting a target wireless network signal into a feature extraction layer of a target signal detection model; the first obtaining submodule is used for obtaining the signal intensity information and the time parameter information output by the feature extraction layer, wherein the target signal feature comprises the signal intensity information and the time parameter information.

Optionally, the obtaining module includes: the second input submodule is used for inputting a plurality of target signal characteristics to a full connection layer of a target signal detection model under the condition that a plurality of target access devices are provided, wherein the plurality of target signal characteristics correspond to a plurality of target wireless network signals detected by the plurality of target access devices at the same time; the second obtaining submodule is used for obtaining the moving parameter information output by the full connection layer, wherein the moving parameter information comprises at least one of the following: position, travel speed, dwell time; and the generation submodule is used for generating a target object state according to the output movement parameter information.

Optionally, the first sending unit includes: the first sending module is configured to push first prompt information to the second terminal device when the target object state is used to indicate a real-time state of the target object, where the real-time state includes at least one of: the system comprises position distribution, moving speed distribution, time distribution of executing target operation and time distribution in a target state, wherein first prompt information is used for prompting the real-time state of a target object; and the second sending module is used for pushing second prompt information to the second terminal equipment under the condition that the target object state is used for indicating that the target object is in an abnormal state, wherein the second prompt information is used for early warning the abnormal state of the target object.

Optionally, the apparatus further comprises: the acquisition unit is used for acquiring wireless network signal samples transmitted by first terminal equipment at a target position and detected by a plurality of access equipment before determining the target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target position belongs to a plurality of positions; the device comprises an input unit, a detection unit and a processing unit, wherein the input unit is used for inputting wireless network signal samples and device information of a plurality of access devices into an initial signal detection model to obtain position information output by the initial signal detection model, and the position information is used for indicating the probability that a target position is each of a plurality of positions; and the adjusting unit is used for adjusting the model parameters of the initial signal detection model according to the position information and the labeling position of the wireless network signal sample to obtain a target signal detection model, wherein in the position information output by the target signal detection model, the probability that the target position is the labeling position is greater than or equal to a target probability threshold value.

Optionally, the apparatus further comprises: the second sending unit is configured to send early warning information to a second terminal device after a target pushing operation corresponding to a target object state is executed to the second terminal device corresponding to a target scene, where the early warning information is used to early warn that the target object is not in a listening range of the multiple access devices, and when a wireless network signal of the first terminal device is not detected in the listening range of the multiple access devices.

According to still another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program that executes the above-described method when executed.

According to yet another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the above method through the computer program.

In the embodiment of the application, a plurality of access devices are arranged at different positions of a target scene, and the access devices are combined with terminal devices configured on an object, and a target wireless network signal of a first terminal device is detected in a monitoring range of a target access device in the plurality of access devices, wherein the plurality of access devices are arranged in the plurality of positions of the target scene, and the first terminal device is configured on the target object; determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position; the method comprises the steps of executing a target pushing operation corresponding to a target object state to a second terminal device corresponding to a target scene, performing model analysis on a target wireless network signal by detecting the target wireless network signal of a first terminal device in a monitoring range of a target access device in a plurality of access devices, and determining the corresponding target object state, thereby determining the object state of the target object configured with the first terminal device, executing different pushing operations to the second terminal device corresponding to the target scene according to different object states, achieving the purposes of automatically detecting the object state and actively pushing the object state of the target object to the second terminal device, thereby achieving the technical effects of reducing the labor cost of object state monitoring and improving the timeliness of object monitoring, and further solving the problems of high monitoring labor cost and poor monitoring timeliness of an object monitoring mode in the related technology.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

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, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

FIG. 1 is a schematic diagram of a hardware environment for a push method of object states according to an embodiment of the present application;

FIG. 2 is a flow chart of an alternative object state pushing method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an alternative subject monitoring modality according to an embodiment of the present application;

fig. 4 is a schematic diagram of wireless network signal detection according to an embodiment of the present application;

FIG. 5 is a schematic diagram of activating an access device monitoring function according to an embodiment of the application;

FIG. 6 is a schematic illustration of a push flow of object states in accordance with an alternative embodiment of the present application;

FIG. 7 is a schematic diagram of an alternative object state pushing device according to an embodiment of the present application; and

fig. 8 is a block diagram of a server according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, 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 only partial 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.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

According to an aspect of embodiments of the present application, an embodiment of a method for pushing an object state is provided.

Alternatively, in the present embodiment, the object state pushing method described above may be applied to a hardware environment formed by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, a server 103 is connected to a terminal 101 through a network, and may be configured to provide services (such as game services, application services, etc.) for the terminal or a client installed on the terminal, and a database may be provided on the server or separately from the server, and may be configured to provide data storage services for the server 103, where the network includes but is not limited to: the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, and the like. The object state pushing method in the embodiment of the present application may be executed by the server 103, the terminal 101, or both the server 103 and the terminal 101. The terminal 101 executing the object state pushing method according to the embodiment of the present application may also be executed by a client installed thereon.

Fig. 2 is a flowchart of an optional object state pushing method according to an embodiment of the present application, and as shown in fig. 2, the method may include the following steps:

step S202, a target wireless network signal of a first terminal device is detected in a monitoring range of a target access device in a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, and the first terminal device is configured on a target object;

step S204, determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model through a wireless network signal sample marked with a corresponding position;

step S206, executing a target pushing operation corresponding to the target object state to the second terminal device corresponding to the target scene.

Through the steps S202 to S206, by detecting a target wireless network signal of a first terminal device in the interception range of a target access device of the multiple access devices, performing model analysis on the target wireless network signal to determine a target object state corresponding to the target wireless network signal, thereby determining an object state of a target object configured with the first terminal device, and executing different pushing operations to a second terminal device corresponding to a target scene according to different object states, the purpose of automatically detecting the object state and actively pushing the object state of the target object to the second terminal device is achieved, thereby achieving the technical effects of reducing the labor cost of object state monitoring and improving the timeliness of object monitoring, and further solving the problems of high monitoring labor cost and poor monitoring timeliness of an object monitoring mode in the related art.

In the technical solution provided in step S202, a target wireless network signal of a first terminal device is detected in a listening range of a target access device of a plurality of access devices.

The target scene is a scene for monitoring the state of a target object, such as: an asylum (the target object may be an elderly person in the asylum), a welfare (the target object may be a child in the welfare), etc., which may contain multiple regional locations and may correspond to different places of activity in the target scene, such as: individual rooms, restrooms, wash stations, etc.

In a target scenario, a plurality of Access devices may be deployed, for example, a plurality of Access Points (APs), where an AP refers to a wireless switch for a wireless network. The access device may be obtained by performing secondary development on the basis of the routing device, that is, a plurality of access devices may be uniformly controlled and managed by the routing device.

The routing device can be an intelligent router, the intelligent router is an intelligently managed router, generally has an independent operating system, can be used for a user to install various applications by himself, and can control bandwidth, online number of people, browsing web pages, online time and the like by himself, and meanwhile has a powerful USB (Universal Serial Bus) sharing function, so that intelligent management of networks and devices is achieved.

For example, in order to ensure positioning accuracy and full-space coverage, multipoint deployment is required in the entire site, and in a room, wireless coverage may be performed using a panel AP, and in an open space such as an aisle or a living room, a ceiling AP may be used. In order to ensure that the space positioning function is normal, the number of the APs arranged in the site can be not less than 3.

The plurality of access devices can be controlled by the routing device, and the routing device can provide a wireless network and monitor the state of the target object. The listening range of the multiple access devices will typically be larger than the range of the target scenario.

Optionally, in this embodiment, each of the plurality of access devices may detect a wireless network signal within a coverage area of the access device when the access device operates. The target object may configure the first terminal device, e.g. to wear a wearable smart device. This first terminal equipment can integrate has wireless network signal emission module, for example, the WIFI function, can possess waterproof function simultaneously, can also possess dustproof, prevent falling the function, to other functions, for example, time display, SMS demonstration etc. can not integrate, thereby reduce first terminal equipment's cost, the volume, weight etc., conveniently carry, need not to remove and can accomplish operations such as washing one's face and rinsing one's mouth, the price of avoiding wearable equipment to exist is comparatively high, itself can hinder the old man action (for example, usually can remove earlier before washing one's face and rinsing one's mouth), be unfavorable for the problem of full time monitoring etc..

The target object can wear the first terminal device and move in the target scene, and the first terminal device can transmit wireless network signals to the surroundings. Because the access devices are located at different positions, the coverage areas are different, and therefore, part or all of the plurality of access devices (i.e., the target access device) can detect the wireless network signal (target wireless network signal) transmitted by the first terminal device.

For example, as shown in fig. 3, after the elderly wear a bracelet, the surrounding APs periodically send out probe frames to the bracelet, and report the summary of data to the control center.

The target wireless network signal may include, but is not limited to, a WIFI network signal, and the like. The target access device may detect a target wireless network signal within the listening range by means of, but not limited to, a WIFI probe.

As shown in fig. 4, when a WIFI device (e.g., a mobile phone with a WIFI function, a WIFI smart band) is in a monitoring range of the WIFI probe, the WIFI device sends any frame, and regardless of who the WIFI device is sent, the WIFI probe can intercept the frame, and analyze some information of a MAC (Media Access Control) layer and a physical layer of the frame, such as MAC addresses, frame types, signal strengths, and the like of sending and receiving devices. The WiFi probe does not need any interaction with surrounding equipment, does not send any WiFi signal, and therefore non-perception MAC information acquisition is achieved. For a device with WiFi function turned on, as shown in table 1, the access device may collect data through the WiFi probe, which may be but is not limited to MAC layer information, and transmit the collected data to the router, where the router performs data processing, for example, processing by a control center integrated by performing secondary development on the router.

TABLE 1

In the technical solution provided in step S204, a target object state corresponding to the target wireless network signal is determined by the target signal detection model.

The target signal detection model is obtained by training the initial signal detection model by using the wireless network signal samples labeled with corresponding positions, and the division mode of the positions can be determined according to an actual monitoring scene, such as: in a scenario of monitoring the activity location of an elderly person taking care of the elderly in a nursing home, the location may refer to a location of an area in a target scene, and may include, but is not limited to, at least one of: a living room, a bedroom (which may correspond to a specific room number), a restroom, a wash station, etc., but not limited thereto, other location division methods that can embody the current status of the target object may be used in this embodiment.

The object state is used to represent a current state of the target object, for example, a real-time position state, a moving state, and the like of the target object, or a personalized state determined based on the current state, for example, a moving speed distribution, and the like. The specific object state can be set as required.

In the technical solution provided in step S206, a target push operation corresponding to the target object state is executed to the second terminal device corresponding to the target scene.

Different object states can correspond to different pushing operations and can be divided according to the danger degree corresponding to the target object state, for example, if the target object is in a normal state, ordinary prompt information can be correspondingly pushed, and if the target object is in an abnormal state, for example, if the target object stays in a washroom for too long, the time for which the moving speed is zero is too long, the moving acceleration is too fast, and the like, abnormal prompt information can be correspondingly pushed so as to reflect emergency of the situation.

As an alternative embodiment, the determining, by the target signal detection model, a target object state corresponding to the target wireless network signal includes:

s11, extracting target signal characteristics of a target wireless network signal through a target signal detection model;

and S12, obtaining the moving parameter information corresponding to the target signal characteristics through the target signal detection model to obtain the target object state.

Optionally, in this embodiment, the target signal detection model may include, but is not limited to, a classification model, and the target signal characteristics of the target wireless network signal are classified by extracting the target signal characteristics in the target wireless network signal, so as to obtain the target object state, where the classification may be into different positions.

As an alternative embodiment, the extracting, by the target signal detection model, the target signal feature of the target wireless network signal includes:

s21, inputting a target wireless network signal into a feature extraction layer of a target signal detection model;

and S22, acquiring signal strength information and time parameter information output by the feature extraction layer, wherein the target signal features comprise the signal strength information and the time parameter information.

The target wireless network signal can be input into a feature extraction layer of the target signal detection model, and the feature extraction layer extracts the target signal feature of the target wireless network signal.

Optionally, in this embodiment, the target signal features may include, but are not limited to: the signal intensity information and the time parameter information are used for determining the movement parameters of the target object according to the signal intensity and the time parameter, and further determining the object state of the target object, so that the automatic identification of the object state represented by the wireless network signal is realized.

For example, parameters of wireless network signals may include, but are not limited to: all or part of the parameters can be used as target signal characteristics, and the characteristic description information of each parameter can be shown in table 2.

TABLE 2

Parameter name	Description of the features
		Device MAC address	One device with unique identifier
WiFi Signal Strength	-100dBm～-1dBm
		Reporting timestamps	To the order of seconds
Duration of persistent connection	0 to 1440 minutes (maximum value is 1 day)
		WiFi State	Connect/disconnect

As an optional embodiment, obtaining, by the target signal detection model, a movement parameter corresponding to a target signal feature, and obtaining a target object state includes:

s31, under the condition that a plurality of target access devices are arranged, inputting a plurality of target signal characteristics to a full connection layer of a target signal detection model, wherein the plurality of target signal characteristics correspond to a plurality of target wireless network signals detected by the plurality of target access devices at the same time;

s32, acquiring the movement parameter information output by the full connection layer, wherein the movement parameter information comprises at least one of the following: position, travel speed, dwell time;

and S33, generating a target object state according to the output movement parameter information.

Since a plurality of access devices are arranged in the target scene, a plurality of target access devices can be used for detecting the target wireless network signal transmitted by the first terminal device. If the number of the target access devices is multiple, multiple target wireless network signals detected by the multiple target access devices at the same time can be input to the feature extraction layer of the target signal detection model, multiple target signal features corresponding to the multiple target wireless network signals are obtained, and the manner of extracting the target signal features is similar to the foregoing, which is not described herein again.

It should be noted that, because distances between the first terminal device and the plurality of target access devices may not be completely the same, times when the target access devices detect the target wireless network signals may be different, and whether the target access devices detect the same wireless network signal may be determined by whether a time difference between the times when the wireless network signals are detected is smaller than a time difference threshold, and a specific determination manner may be set as needed, which is not specifically limited in this embodiment.

It should be noted that there may be multiple monitored subjects in the target scene, for example, multiple elderly people need to be monitored in an elderly care home, and therefore, there may be one or more terminal devices configured for the monitored subjects in the target scene. The wireless network signals transmitted by the terminal devices of different monitored objects can be distinguished through different terminal identifications, and the wireless network signals transmitted by the terminal devices of all monitored objects are processed by using a target signal detection model in a serial or parallel mode to obtain the object state of each monitored object. The manner of determining the object state of each monitored object is similar to the manner of determining the target object state, and is not described herein again.

For example, the control center may determine, using the terminal identifier of the first terminal device, a target wireless network signal transmitted by the first terminal device from the wireless network information sensed by the plurality of access devices, and determine a target object state corresponding to the target wireless network signal using the target signal detection model.

The plurality of target signal features may be input to a full link layer of the target signal detection model, and the full link layer outputs the movement parameter information corresponding to the plurality of target signal features. The movement parameter information may include, but is not limited to, at least one of: position, speed of movement, dwell time.

For example, by analyzing the signal characteristics as shown in table 2, the movement parameter information as shown in table 3 can be obtained.

TABLE 3

According to the movement parameter information output by the full connection layer, the target object state can be generated.

As an optional embodiment, the executing, to the second terminal device corresponding to the target scene, the target push operation corresponding to the target object state includes:

s41, under the condition that the target object state is used for indicating the real-time state of the target object, pushing first prompt information to the second terminal equipment, wherein the real-time state comprises at least one of the following: the system comprises position distribution, moving speed distribution, time distribution for executing target operation and time distribution in a target state, wherein first prompt information is used for prompting the real-time state of a target object;

and S42, under the condition that the target object state is used for indicating that the target object is in the abnormal state, pushing second prompt information to the second terminal equipment, wherein the second prompt information is used for early warning of the abnormal state of the target object.

The target object status indication may be a real-time status of the target object, which may be a location profile, a movement speed profile, a time profile for performing a target operation (e.g., washing, toileting, walking, standing at night, etc.), a time profile in a target state (e.g., a sleep state, an insomnia state, etc.).

The server can push first prompt information to the second terminal device to prompt the real-time state, so that the current state of the person under guardianship (for example, the guarded old person) is fed back in real time.

For example, based on the features as shown in table 3, in combination with the actual situation, a personalized real-time status view can be customized, for example:

(1) Regular washing and toileting

The time distribution and the time length of daily washing and toileting can be well used for feeding back the physical condition of the old.

(2) Speed of walking

By monitoring the walking speed distribution, possible accidents can be found in time.

(3) Duration of sleep

Frequent night and insomnia are monitored, and the sleep condition of the old can be effectively known, so that targeted coaching can be performed subsequently.

The target object state may indicate an abnormal state of the target object, and the abnormal state may be a state that is beyond a set normal state range, such as a state that the speed is too fast (for example, the current speed is not within a predetermined speed range), and the stay time is too long (for example, the stay time at the same position exceeds a predetermined time threshold).

For example, management and care personnel can view real-time conditions through a mobile phone, and can set early warning thresholds for special conditions based on feature combinations.

The server can push second prompt information to the second terminal device to prompt the abnormal state, so that the abnormal state of the target object is early warned, and the situation is prevented from spreading.

Optionally, in this embodiment, whether the target object state is normal or abnormal (even dangerous), and how to push the information may be set by the second terminal device.

Optionally, in this embodiment, in order to obtain the target signal detection model, the initial signal detection model may be trained first using the labeled training samples.

As an optional embodiment, before determining the target object state corresponding to the target wireless network signal through the target signal detection model, the method may further include:

s51, acquiring wireless network signal samples transmitted by a first terminal device at a target position, wherein the wireless network signal samples are detected by a plurality of access devices, and the target position belongs to a plurality of positions;

and S52, training the initial signal detection model by using the wireless network signal samples marked with the corresponding positions and the equipment information of the plurality of access equipment to obtain a target signal detection model.

Optionally, in this embodiment, before the target object monitoring functions of multiple access devices are used, differences between the devices and the environment may be calibrated through a simple activation operation, fig. 5 is a schematic diagram of activating the monitoring functions of the access devices according to an embodiment of the present application, and as shown in fig. 5, the activation process includes the following stages: signal acquisition, modeling, model parameter downloading, site labeling and model training.

In a signal acquisition phase, a target object or other objects may connect a first terminal device (e.g., a WiFi bracelet) to WiFi of a routing device (e.g., an intelligent router), and wear the first terminal device to stay and acquire data at the following positions respectively according to a flow guide on a second terminal device (e.g., a mobile terminal):

A. the living room is not separated from the router, and the distance is not more than 3 meters;

B. bedroom N, room door open state;

C. bedroom N, room door closed state;

D. the door is closed when the door is out;

E. the elevator door at the same floor is in a front door closing state;

F. in the elevator on the same floor, the front door and the elevator are both in a closed state;

G. upper and lower floors, and a front door closed state.

And each position stays for about 10 seconds, the routing equipment actively acquires data for 10 times, and after the acquisition of each position is completed, the next step displayed on the second terminal equipment is clicked until all the acquisition is completed.

In the modeling stage, all the collected data can be sent to the big data platform by the second terminal device (or the routing device), and the sent data comprises:

A. the model and MAC of the first terminal device;

B. the model, MAC, SSID (Service Set Identifier) of the routing device;

C. all acquired signal strengths and acquisition times.

In a model parameter downloading stage, the big data platform calculates model parameters suitable for a current place (such as an aged-care home) through summarizing and analyzing all data, the calculated mode parameters can be suitable for a scene of multiple access devices, hardware differences of different access devices are weakened, the model parameters are synchronized to the routing device, and then the platform does not acquire any user and router data any more, so that the user privacy is protected to the maximum extent.

In a site labeling stage, after system deployment (e.g., model deployment) is performed, a target object or other objects may wear a first terminal device, perform fixed-point sampling on positions (e.g., target positions) of the entire site, and label the positions, so that a room number, a washroom, and the like where the target object is located can be quickly located in subsequent monitoring.

In the model training stage, the initial signal detection model may be trained to obtain a target signal detection model by using wireless network signal samples and labeled positions (labeled positions) obtained by fixed-point sampling of each access device, and the obtained target signal detection model may be used at least to determine the position of a target object according to a target wireless network signal, thereby determining the state of the target object.

As an optional embodiment, the training of the initial signal detection model using the wireless network signal samples labeled with corresponding locations and the device information of the multiple access devices to obtain the target signal detection model includes:

s61, inputting a wireless network signal sample and equipment information of a plurality of access equipment into an initial signal detection model to obtain position information output by the initial signal detection model, wherein the position information is used for indicating the probability that a target position is each of a plurality of positions;

and S62, adjusting model parameters of the initial signal detection model according to the position information and the labeling position of the wireless network signal sample to obtain a target signal detection model, wherein in the position information output by the target signal detection model, the probability that the target position is the labeling position is greater than or equal to a target probability threshold value.

Optionally, in this embodiment, during model training, wireless network signal samples may be input to the feature extraction layer of the initial signal detection model, and the feature extraction layer extracts signal features of each wireless network signal sample; the extracted signal characteristics of the wireless network signal sample and the device information of the plurality of access devices are input into a full connection layer of the initial signal detection model, and the full connection layer determines the probability that the target position is each position in a position set (which can comprise a plurality of positions) according to the signal characteristics of the wireless network signal sample acquired by each access device, so as to output the position information.

The position set may be configured as a model parameter, different positions may be uniquely identified by different position identifiers, and the manner of identifying a plurality of positions may be set as needed, which is not limited in this embodiment.

According to the position information and the labeled position, the model parameters of the initial signal detection model can be adjusted to increase the probability corresponding to the labeled position in the position information output by the adjusted signal detection model. Through multiple rounds of adjustment, when the adjusted signal detection model meets the target function, the model training is finished, and a target signal model can be obtained, wherein the target function can be: in the position information output by the signal detection model, the probability that the target position is the labeling position is greater than or equal to the target probability threshold.

Multiple access devices may continuously detect wireless network signals within their listening range.

As an alternative embodiment, it is also possible:

and S71, when the wireless network signal of the first terminal device is not detected in the interception ranges of the plurality of access devices, sending early warning information to the second terminal device, wherein the early warning information is used for early warning that the target object is not in the interception ranges of the plurality of access devices.

After or before a target pushing operation corresponding to a target object state is executed to a second terminal device corresponding to a target scene, if each access device does not detect a wireless network signal of the first terminal device within a monitoring range, the target object is considered not to be in the monitoring range of the plurality of access devices, and early warning information can be sent to the second terminal device so as to early warn that the target object is not in the monitoring range of the plurality of access devices.

There are many possibilities that the wireless network signal of the first terminal device is not detected in the listening range of the multiple access devices, for example, a device is abnormal (power consumption, network abnormality), and the target object is outside the listening range of the multiple access devices.

The application also provides an optional embodiment, and this optional embodiment provides a real-time monitoring scheme of senior citizen's activities in the institute of old age based on wiFi probe technique, with the help of the wiFi probe technique of IEEE802.11 agreement set, wears the intelligent bracelet that is furnished with the wiFi module through the old age, and the state of bracelet is gathered through a plurality of APs to the system in real time, substitutes the model that big data platform found and calculates, real-time feedback analysis result. The platform also supports the combination of the actual situation of each old man, configures a corresponding early warning strategy and timely informs on-site nursing to carry out emergency treatment on the accident situation. The intelligent bracelet is a wearable intelligent device provided with a WiFi module, and can be connected with an intelligent router through WiFi.

As shown in fig. 3, a bracelet worn by the elderly is connected with the smart router, and a worker (e.g., a guardian) marks the bracelet on the App side of the mobile phone and adds the bracelet as a monitored object. A plurality of APs are arranged in an nursing home (nursing home or the like). Each AP can acquire information such as WiFi signal intensity and WiFi connection state of the bracelet at regular time (for example, every 15 seconds) (or the bracelet can transmit WiFi signals at regular time and each AP detects in real time) and sends the information to the control center, and the control center substitutes the model for calculation to obtain the current state of the monitored object.

According to the object state pushing method provided by the embodiment, the collected sample parameters and the manual labeling results are imported into the big data platform in the early stage, and the preliminary model parameters are obtained through background calculation. In practical application, equipment designated by a user and training parameters are standardized by means of a data acquisition process, and labeling errors caused by equipment differences are avoided. Fig. 6 is a schematic diagram of a pushing flow of object states according to an alternative embodiment of the present application, and as shown in fig. 6, the flow may include, but is not limited to, the following steps:

step 1, model deployment and initialization.

The guardian can issue an acquisition instruction to the control center through the mobile phone management APP, and data acquisition is triggered. The control center controls each AP to collect data of WiFi signals sent by the wristband of the person under guardianship and returns the data to the control center, and the control center can send the collected data to the big data platform.

The big data platform can calculate the model parameters suitable for the current place through the summary analysis of all data. The guardian can check the collected data through the mobile phone management APP and calibrate the model parameters. The big data platform may synchronize model parameters (or calibrated model parameters) to the control center. The modeling process described above may employ a machine learning algorithm.

The guardian can mark the acquired data through the mobile phone management APP, so that the model is trained, and model deployment and initialization are completed.

And 2, monitoring the state of the object in real time.

The deployed monitoring system can identify the real-time state of the old through monitoring the human motion characteristics, and judge the possibility of accidents.

Each AP can detect WiFi signals transmitted by a bracelet of a person under guardianship, detected data are reported to a control center, the control center performs characteristic analysis by using a deployed model, reported data are converted into characteristic data, the monitoring state of the person under guardianship is obtained, and the monitoring state is pushed to a mobile phone management APP of a guardian.

By the embodiment, the intelligent characteristic of software is fully exerted, the hardware cost is low, single indoor positioning and motion detection can be provided by combining the AP deployed at multiple points through the intelligent bracelet, and full-time monitoring is realized by combining a large data platform and feature engineering and machine learning and fully utilizing the large data capability of the platform; in addition, the accumulation of long-term monitoring data can be used for analyzing the health condition of the old, and helps to make some targeted nursing schemes.

It should be noted that for simplicity of description, the above-mentioned embodiments of the method are described as a series of acts, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.

According to another aspect of the embodiment of the application, a pushing device for object states is also provided, wherein the pushing device is used for implementing the pushing method for object states. Fig. 7 is a schematic diagram of an alternative object state pushing apparatus according to an embodiment of the present application, and as shown in fig. 7, the apparatus may include:

(1) A detecting unit 72, configured to detect a target wireless network signal of a first terminal device in a listening range of a target access device of a plurality of access devices, where the plurality of access devices are deployed in a plurality of locations of a target scene, and the first terminal device is configured on a target object;

(2) A determining unit 74, configured to determine a target object state corresponding to a target wireless network signal through a target signal detection model, where the target signal detection model is obtained by training an initial signal detection model using a wireless network signal sample labeled with a corresponding position;

(3) A first sending unit 76, configured to execute a target pushing operation corresponding to the target object state to the second terminal device corresponding to the target scene.

It should be noted that the detecting unit 72 in this embodiment may be configured to execute the step S202, the determining unit 74 in this embodiment may be configured to execute the step S204, and the first sending unit 76 in this embodiment may be configured to execute the step S206.

It should be noted here that the above units/modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may operate in a hardware environment as shown in fig. 1, and may be implemented by software or hardware.

Through the module, the target wireless network signal of the first terminal equipment in the interception range of the target access equipment in the multiple access equipment is detected, model analysis is carried out on the target wireless network signal, the corresponding target object state is determined, the object state of the target object configured with the first terminal equipment is determined, different pushing operations are executed to the second terminal equipment corresponding to the target scene according to different object states, the purposes of automatically detecting the object state and actively pushing the object state of the target object to the second terminal equipment are achieved, the technical effects of reducing the labor cost of object state monitoring and improving the timeliness of object monitoring are achieved, and the problems of high monitoring labor cost and poor monitoring timeliness of an object monitoring mode in the related technology are solved.

As an alternative embodiment, the determination unit 74 includes:

(1) The extraction module is used for extracting target signal characteristics of the target wireless network signals through the target signal detection model;

(2) And the acquisition module is used for acquiring the movement parameter information corresponding to the target signal characteristics through the target signal detection model to obtain the target object state.

As an alternative embodiment, the extraction module comprises:

(1) The first input submodule is used for inputting a target wireless network signal into a feature extraction layer of a target signal detection model;

(2) The first obtaining submodule is used for obtaining signal strength information and time parameter information output by the feature extraction layer, wherein the target signal feature comprises the signal strength information and the time parameter information.

As an alternative embodiment, the obtaining module includes:

(1) The second input submodule is used for inputting a plurality of target signal characteristics to a full connection layer of a target signal detection model under the condition that a plurality of target access devices are provided, wherein the plurality of target signal characteristics correspond to a plurality of target wireless network signals detected by the plurality of target access devices at the same time;

(2) The second obtaining submodule is used for obtaining the moving parameter information output by the full connection layer, wherein the moving parameter information comprises at least one of the following: position, travel speed, dwell time;

(3) And the generation submodule is used for generating a target object state according to the output movement parameter information.

As an alternative embodiment, the first sending unit 76 includes:

(1) The first sending module is configured to push first prompt information to the second terminal device when the target object state is used to indicate a real-time state of the target object, where the real-time state includes at least one of: the system comprises position distribution, moving speed distribution, time distribution for executing target operation and time distribution in a target state, wherein first prompt information is used for prompting the real-time state of a target object;

(2) And the second sending module is used for pushing second prompt information to the second terminal equipment under the condition that the target object state is used for indicating that the target object is in the abnormal state, wherein the second prompt information is used for early warning the abnormal state of the target object.

As an alternative embodiment, the apparatus further comprises:

(1) The acquisition unit is used for acquiring wireless network signal samples which are detected by a plurality of access devices and are transmitted by first terminal equipment at a target position before determining the target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target position belongs to a plurality of positions;

(2) The input unit is used for inputting the wireless network signal samples and the equipment information of the plurality of access equipment into the initial signal detection model to obtain the position information output by the initial signal detection model, and the position information is used for indicating the probability that the target position is each of the plurality of positions;

(3) And the adjusting unit is used for adjusting the model parameters of the initial signal detection model according to the position information and the labeling position of the wireless network signal sample to obtain a target signal detection model, wherein in the position information output by the target signal detection model, the probability that the target position is the labeling position is greater than or equal to a target probability threshold value.

As an alternative embodiment, the apparatus further comprises:

(1) The second sending unit is configured to send early warning information to a second terminal device after a target pushing operation corresponding to a target object state is executed to the second terminal device corresponding to a target scene, where the early warning information is used to early warn that the target object is not in a listening range of the multiple access devices, and when a wireless network signal of the first terminal device is not detected in the listening range of the multiple access devices.

It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may be operated in a hardware environment as shown in fig. 1, and may be implemented by software, or may be implemented by hardware, where the hardware environment includes a network environment.

According to another aspect of the embodiments of the present application, there is also provided an electronic device for implementing the method for pushing the object state, where the electronic device may be a server, a terminal, or a combination thereof.

Taking a server (for example, a control center deployed on an intelligent router or deployed independently) as an example, fig. 8 is a block diagram of a structure of a server according to an embodiment of the present application, and as shown in fig. 8, the server may include: one or more processors 801 (only one of which is shown), a memory 803, and a transmission device 805, as shown in fig. 8, the server may further include an input output device 807.

The memory 803 may be used to store software programs and modules, such as program instructions/modules corresponding to the object state pushing method and apparatus in the embodiment of the present application, and the processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 803, that is, implements the object state pushing method described above. The memory 803 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 803 may further include memory located remotely from the processor 801, which may be connected to a server via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 805 is used for receiving or sending data via a network, and may also be used for data transmission between a processor and a memory. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 805 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 805 is a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

Among them, the memory 803 is used to store an application program, in particular.

The processor 801 may call an application stored in the memory 803 via the transmission means 805 to perform the following steps:

the method comprises the following steps that S1, a target wireless network signal of a first terminal device is detected in a monitoring range of a target access device in a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, and the first terminal device is configured on a target object;

s2, determining a target object state corresponding to a target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model through a wireless network signal sample marked with a corresponding position;

and S3, executing a target pushing operation corresponding to the target object state to second terminal equipment corresponding to the target scene.

By adopting the embodiment of the application, a scheme for pushing the object state is provided. The method comprises the steps of carrying out model analysis on a target wireless network signal by detecting the target wireless network signal of a first terminal device in an interception range of a target access device in a plurality of access devices, and determining a target object state corresponding to the target wireless network signal, thereby determining the object state of a target object configured with the first terminal device, and executing different pushing operations to a second terminal device corresponding to a target scene according to different object states, thereby achieving the purposes of automatically detecting the object state and actively pushing the object state of the target object to the second terminal device, further achieving the technical effects of reducing the labor cost of object state monitoring and improving the timeliness of object monitoring, and further solving the problems of high monitoring labor cost and poor monitoring timeliness of an object monitoring mode in the related technology.

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.

It can be understood by those skilled in the art that the structure shown in fig. 8 is only an illustration, and the device implementing the method for pushing the object state may also be a terminal, and the terminal may be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 8 is a diagram illustrating a structure of the electronic device. For example, the terminal may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 8, or have a different configuration than shown in FIG. 8.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, read-Only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.

Embodiments of the present application also provide a storage medium. Alternatively, in this embodiment, the storage medium may be used to execute a program code of a push method of an object state.

Optionally, in this embodiment, the storage medium may be located on at least one of a plurality of network devices in a network shown in the above embodiment.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

and S3, executing target pushing operation corresponding to the target object state to second terminal equipment corresponding to the target scene.

Optionally, in this embodiment, the storage medium may include, but is not limited to: a U disk, a ROM, a RAM, a removable hard disk, a magnetic disk, or an optical disk.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, or the like) to execute all or part of the steps of the methods described in the embodiments of the present application.

In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and 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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method for pushing object states is characterized by comprising the following steps:

detecting a target wireless network signal of a first terminal device within a listening range of a target access device of a plurality of access devices, wherein the plurality of access devices are deployed in a plurality of positions of a target scene, the first terminal device is configured on a target object, each access device of the plurality of access devices is used for detecting a wireless network signal within the listening range of each access device through a WIFI probe, and the first terminal device is used for transmitting a wireless network signal;

determining a target object state corresponding to the target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position;

and executing target push operation corresponding to the target object state to second terminal equipment corresponding to the target scene.

2. The method of claim 1, wherein the determining, by a target signal detection model, a target object state corresponding to the target wireless network signal comprises:

extracting target signal characteristics of the target wireless network signals through the target signal detection model;

and obtaining moving parameter information corresponding to the target signal characteristics through the target signal detection model to obtain the target object state.

3. The method of claim 2, wherein the extracting, by the target signal detection model, the target signal feature of the target wireless network signal comprises:

inputting the target wireless network signal into a feature extraction layer of the target signal detection model;

and acquiring signal intensity information and time parameter information output by the feature extraction layer, wherein the target signal feature comprises the signal intensity information and the time parameter information.

4. The method of claim 2, wherein the obtaining of the motion parameter corresponding to the target signal feature by the target signal detection model to obtain the target object state comprises:

inputting a plurality of target signal characteristics to a full connection layer of the target signal detection model when the number of target access devices is multiple, wherein the plurality of target signal characteristics correspond to a plurality of target wireless network signals detected by the plurality of target access devices at the same time;

acquiring the motion parameter information output by the full connection layer, wherein the motion parameter information includes at least one of the following: position, travel speed, dwell time;

and generating the target object state according to the output movement parameter information.

5. The method according to claim 1, wherein the performing the target push operation corresponding to the target object state to the second terminal device corresponding to the target scene comprises:

under the condition that the target object state is used for indicating a real-time state of the target object, pushing first prompt information to the second terminal equipment, wherein the real-time state comprises at least one of the following: the first prompt information is used for prompting the real-time state of the target object;

and under the condition that the target object state is used for indicating that the target object is in an abnormal state, pushing second prompt information to the second terminal equipment, wherein the second prompt information is used for early warning of the abnormal state of the target object.

6. The method of claim 1, wherein before the determining, by the target signal detection model, the target object state corresponding to the target wireless network signal, the method further comprises:

acquiring wireless network signal samples, which are detected by the plurality of access devices and transmitted by the first terminal device at a target position, wherein the target position belongs to the plurality of positions;

inputting the wireless network signal samples and the device information of the plurality of access devices into the initial signal detection model to obtain location information output by the initial signal detection model, wherein the location information is used for indicating the probability that the target location is each of the plurality of locations;

and adjusting model parameters of the initial signal detection model according to the position information and the labeled position of the wireless network signal sample to obtain the target signal detection model, wherein in the position information output by the target signal detection model, the probability of the labeled position of the target position is greater than or equal to a target probability threshold value.

7. The method according to any one of claims 1 to 6, wherein after the performing of the target push operation corresponding to the target object state to the second terminal device corresponding to the target scene, the method further comprises:

and sending early warning information to the second terminal equipment under the condition that the wireless network signal of the first terminal equipment is not detected in the interception ranges of the plurality of access equipment, wherein the early warning information is used for early warning that the target object is not in the interception ranges of the plurality of access equipment.

8. An apparatus for pushing a state of an object, comprising:

the device comprises a detection unit, a first terminal device and a second terminal device, wherein the detection unit is used for detecting a target wireless network signal of a first terminal device in a listening range of a target access device in a plurality of access devices, the plurality of access devices are deployed in a plurality of positions of a target scene, the first terminal device is configured on a target object, each access device in the plurality of access devices is used for detecting a wireless network signal in the listening range of each access device through a WIFI probe, and the first terminal device is used for transmitting a wireless network signal;

the determining unit is used for determining a target object state corresponding to the target wireless network signal through a target signal detection model, wherein the target signal detection model is obtained by training an initial signal detection model by using a wireless network signal sample marked with a corresponding position;

and the first sending unit is used for executing a target pushing operation corresponding to the target object state to the second terminal equipment corresponding to the target scene.

9. A storage medium, comprising a stored program, wherein the program when executed performs the method of any of claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the method of any of the preceding claims 1 to 7 by means of the computer program.