CN112181055A - Indoor and outdoor state judgment method, wearable device and computer readable storage medium - Google Patents
Indoor and outdoor state judgment method, wearable device and computer readable storage medium Download PDFInfo
- Publication number
- CN112181055A CN112181055A CN202011038752.9A CN202011038752A CN112181055A CN 112181055 A CN112181055 A CN 112181055A CN 202011038752 A CN202011038752 A CN 202011038752A CN 112181055 A CN112181055 A CN 112181055A
- Authority
- CN
- China
- Prior art keywords
- state
- decision tree
- wearable device
- target data
- types
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000007637 random forest analysis Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000004891 communication Methods 0.000 claims abstract description 17
- 238000003066 decision tree Methods 0.000 claims description 149
- 230000006870 function Effects 0.000 claims description 28
- 238000013138 pruning Methods 0.000 claims description 25
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 238000005259 measurement Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/163—Wearable computers, e.g. on a belt
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C23/00—Combined instruments indicating more than one navigational value, e.g. for aircraft; Combined measuring devices for measuring two or more variables of movement, e.g. distance, speed or acceleration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/1633—Constructional details or arrangements of portable computers not specific to the type of enclosures covered by groups G06F1/1615 - G06F1/1626
- G06F1/1684—Constructional details or arrangements related to integrated I/O peripherals not covered by groups G06F1/1635 - G06F1/1675
- G06F1/1698—Constructional details or arrangements related to integrated I/O peripherals not covered by groups G06F1/1635 - G06F1/1675 the I/O peripheral being a sending/receiving arrangement to establish a cordless communication link, e.g. radio or infrared link, integrated cellular phone
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The embodiment of the application discloses an indoor and outdoor state judgment method, wearable equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring N types of target data measured by the wearable device at the current position, wherein the N types of target data correspond to preset N state characteristics respectively, the N state characteristics at least comprise motion characteristics of the wearable device and communication characteristics of the wearable device, and N is a positive integer greater than or equal to 2; processing the N types of target data by using a random forest classification model, and determining the state type of the current position; and the random forest classification model is obtained by training according to the wearable equipment and the sample data corresponding to the N state characteristics. Through implementing this application embodiment, can carry out accurate judgement to indoor outer state.
Description
Technical Field
The application relates to the technical field of positioning, in particular to an indoor and outdoor state judgment method, wearable equipment and a computer readable storage medium.
Background
At present, most wearable devices have a positioning function, can report position information of a user of the wearable device to terminal devices associated with the wearable devices in real time, but cannot accurately identify whether the current position is outdoor or indoor. The recognition of indoor and outdoor states is found in practice to have good application prospect in equipment worn by children, equipment worn by old people, pet wearing equipment and the like. Therefore, how to identify indoor and outdoor states becomes a problem which needs to be solved urgently.
Disclosure of Invention
The embodiment of the application discloses an indoor and outdoor state judgment method, wearable equipment and a computer-readable storage medium, which can accurately judge indoor and outdoor states.
The first aspect of the embodiment of the present application discloses a method for determining an indoor state and an outdoor state, including:
acquiring N types of target data measured by a wearable device at a current position, wherein the N types of target data correspond to preset N state characteristics respectively, the N state characteristics at least comprise motion characteristics of the wearable device and communication characteristics of the wearable device, and N is a positive integer greater than or equal to 2;
processing the N types of target data by using a random forest classification model, and determining the state type of the current position; the random forest classification model is obtained through training according to sample data corresponding to the wearable device and the N state features, and the state type of the current position is indoor or outdoor.
As an optional implementation manner, in the first aspect of this embodiment of the present application, the motion characteristic includes any one of velocity, relative displacement, and global positioning system GPS position, or a combination of several of them, and the communication characteristic includes reference signal received power and/or reference signal received quality.
As an optional implementation manner, in the first aspect of this embodiment of the present application, the processing the N types of target data by using a random forest classification model to determine the state type of the current location includes:
acquiring a processing result of each decision tree in a random forest classification model aiming at the N types of target data;
and obtaining the state type of the current position according to the processing result of each decision tree aiming at the N types of target data.
As an optional implementation manner, in the first aspect of the embodiment of the present application, the obtaining the state type of the current location according to the processing result of each decision tree for the N types of target data includes:
obtaining a first indoor probability of the state type of the current position according to the processing result of each decision tree for the N types of target data;
determining that the state type of the current location is indoor if the first probability is greater than a probability threshold;
determining that the state type of the current location is outdoors if the first probability is less than or equal to the probability threshold.
As an optional implementation manner, in the first aspect of this embodiment of this application, the random forest classification model includes k decision trees, and before the processing the N types of target data by using the random forest classification model and determining the state type of the current location, the method further includes:
acquiring k sample sets from sample data of the wearable device; wherein k is an integer greater than or equal to 2;
training the k decision trees according to the k sample sets, if the k decision trees do not meet a stopping rule, continuing to execute the step of acquiring the k sample sets from the sample data of the wearable device until the k decision trees meet the stopping rule, and obtaining k trained decision trees;
pruning each decision tree in the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree;
and combining k optimal decision trees to obtain the random forest classification model.
As an optional implementation manner, in the first aspect of the embodiment of the present application, the training the k decision trees according to the k sample sets includes:
determining internal nodes and leaf nodes of a first decision tree corresponding to the first sample set; wherein the first sample set is any one of the k sample sets.
As an optional implementation manner, in the first aspect of this embodiment of the present application, the determining an internal node and a leaf node of a first decision tree corresponding to a first sample set includes:
obtaining information gain of each state feature of the first sample set;
determining the state characteristic with the maximum information gain as a father node of the first decision tree;
classifying the first sample set according to the data interval corresponding to the father node to obtain a child node corresponding to the father node;
and under the condition that the state characteristics of the sub-nodes are not unique or the information gains of the state characteristics of the sub-nodes are all larger than or equal to a preset gain threshold, taking the data set corresponding to the sub-nodes as a first sample set, continuously executing the step of obtaining the information gain of each state characteristic of the first sample set until the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold are obtained, and taking the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold as leaf nodes.
As an optional implementation manner, in the first aspect of the embodiment of the present application, the performing pruning operation on each decision tree of the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree includes:
pruning and estimating the internal nodes of the second decision tree from the internal node at the bottommost part of the second decision tree according to the sequence from bottom to top to obtain a loss function corresponding to the internal node of the second decision tree; wherein the second decision tree is any one of the k trained decision trees;
pruning the second decision tree according to the loss function corresponding to each internal node of the second decision tree to obtain a sub-tree sequence;
acquiring the square error or the kini index of each subtree in the subtree sequence by using a verification sample set;
and taking the subtree with the minimum square error or the minimum kini index as the optimal decision tree corresponding to the second decision tree.
A second aspect of the embodiments of the present application discloses a wearable device, including:
the wearable device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring N types of target data measured by the wearable device at the current position, the N types of target data correspond to preset N state characteristics respectively, the N state characteristics at least comprise motion characteristics of the wearable device and communication characteristics of the wearable device, and N is a positive integer greater than or equal to 2;
the determining unit is used for processing the N types of target data by utilizing a random forest classification model and determining the state type of the current position; the random forest classification model is obtained through training according to sample data corresponding to the wearable device and the N state features, and the state type of the current position is indoor or outdoor.
A third aspect of an embodiment of the present application discloses a wearable device, including:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to perform part or all of the steps of any one of the methods of the first aspect of the present application.
A fourth aspect of embodiments of the present application discloses a computer-readable storage medium storing a computer program comprising a program code for performing some or all of the steps of any one of the methods of the first aspect of the present application.
A fifth aspect of embodiments of the present application discloses a computer program product, which, when run on a computer, causes the computer to perform part or all of the steps of any one of the methods of the first aspect.
A sixth aspect of embodiments of the present application discloses an application issuing system, configured to issue a computer program product, where the computer program product is configured to, when run on a computer, cause the computer to perform part or all of the steps of any one of the methods of the first aspect.
Compared with the prior art, the embodiment of the application has the following beneficial effects:
implementing the embodiment of the application, acquiring N types of target data measured by the wearable device at the current position, wherein the N types of target data correspond to N preset state characteristics respectively, the N state characteristics at least comprise motion characteristics of the wearable device and communication characteristics of the wearable device, and N is a positive integer greater than or equal to 2; processing the N types of target data by using a random forest classification model, and determining the state type of the current position; and the random forest classification model is obtained by training according to the wearable equipment and the sample data corresponding to the N state characteristics. Because the sample data for training the random forest classification model is the multidimensional characteristics, the random forest classification model has higher judgment precision on indoor and outdoor states compared with other models obtained by training the sample data with single characteristics.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without making a creative effort.
Fig. 1 is a schematic flow chart of a method for determining indoor and outdoor states disclosed in an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating another indoor/outdoor state determination method disclosed in the embodiment of the present application;
fig. 3a is a schematic flow chart of another indoor and outdoor state determination method disclosed in the embodiment of the present application;
FIG. 3b is a diagram illustrating the training of a decision tree;
FIG. 3c is a schematic diagram of a decision tree;
fig. 4 is a schematic structural diagram of a wearable device disclosed in an embodiment of the present application;
fig. 5 is a schematic structural diagram of another wearable device disclosed in the embodiments of the present application;
fig. 6 is a schematic structural diagram of another wearable device disclosed in the embodiments of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
It should be noted that the terms "comprises," "comprising," and any variations thereof in the embodiments and drawings of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The indoor and outdoor state judging method is suitable for wearable equipment, and the wearable equipment can be directly worn on a user body or integrated into clothes or accessories of the user. Wearable equipment is not only a hardware equipment, can realize powerful intelligent function through software support and data interaction, high in the clouds interaction more, for example: the system has the functions of calculation, positioning and alarming, and can be connected with wearable equipment and various terminals. Wearable devices may include, but are not limited to, wrist-supported watch types (e.g., wrist watches, wrist-supported products), foot-supported shoes types (e.g., shoes, socks, or other leg-worn products), head-supported Glass types (e.g., glasses, helmets, headbands, etc.), and various types of non-mainstream products such as smart clothing, bags, crutches, accessories, and the like.
The embodiment of the application discloses an indoor and outdoor state judgment method, wearable equipment and a computer-readable storage medium, which can accurately judge indoor and outdoor states.
The technical solution of the present application is further described below by way of example, and as shown in fig. 1, fig. 1 is a schematic flow chart of an indoor and outdoor state determination method disclosed in the present application. The method can comprise the following steps:
101. acquiring N types of target data measured by the wearable device at the current position.
It should be noted that N types of target data measured by the wearable device correspond to N preset state features, where the N state features at least include a motion feature of the wearable device and a communication feature of the wearable device, and N is a positive integer greater than or equal to 2. The motion characteristics of the wearable device may include any one or a combination of several of a velocity, a relative displacement, a Global Positioning System (GPS) position, and the like, where the velocity refers to an instantaneous velocity of the wearable device at a measurement time point; the relative displacement refers to relative position information of a current measurement time point with respect to a previous measurement time point, the relative position information including distance information and direction information. The communication characteristics of the wearable device can comprise Reference Signal Receiving Power (Reference Signal Receiving Power, RSRP) and/or Reference Signal Receiving Quality (RDRQ), wherein the RSRP is an average value of Signal Power received on all resource elements carrying cell-specific Reference signals in a Long Term Evolution (LTE) network, and the RDRQ is used for indicating a ratio of the Signal Power of the specific Reference signals to the total Signal Power.
The following are exemplary: the speed information of the wearable device measured at the current measurement time point is a1, the relative displacement information is a2, the GPS position information is a3, the reference signal received power information is a4, and the reference signal received quality is a 5. The motion characteristic data in the N-type target data may include any one or several of a1, a2, and a3, and the communication characteristic data in the N-type target data may include a4 and/or a 5. Illustratively, the N-type target data includes a1 and a 4; alternatively, a1, a3, and a 5; alternatively, a1, a2, a3, a4, and a 5.
In embodiments of the present application, the rate and relative displacement of the wearable device are collected by a motion sensor of the wearable device. The GPS position of the wearable device is collected through a GPS sensor of the wearable device. The RSRP and RDRQ of the wearable device are collected by a mobile communication module of the wearable device. Optionally, in consideration of the power consumption of the wearable device, the data acquisition may be performed in real time by using a multi-point acquisition strategy. Specifically, taking GPS location information acquisition of the wearable device as an example for explanation: the GPS sensor can acquire GPS position information (which can be represented by longitude and latitude information and the like) according to a preset acquisition frequency, can acquire a plurality of pieces of GPS position information acquired in a certain time period before and after a target moment, calculates an average value of the plurality of pieces of GPS position information, and can use the average value as the position information of the wearable device at the target moment. For example, assuming that the GPS sensor collects GPS location information at a frequency of n/2 τ (HZ) for a2 τ period around time t, the GPS location information for the 2 τ period may be represented as { x }0,…,xn-1Then the GPS position information at time t can be expressed as
It should be noted that the status feature may also include other features, such as behavior features of the user, and the target data may also include other data, not limited to the above-mentioned ones.
102. And processing the N types of target data by using a random forest classification model, and determining the state type of the current position.
A random forest model is a classifier that contains multiple decision trees. The random forest classification model is obtained through training according to sample data corresponding to the wearable device and the N state features, and the state type of the current position is indoor or outdoor.
And each decision tree included in the random forest model can identify whether the current position is outdoor or indoor according to the N types of target data, and under the condition that the number of the indoor corresponding decision trees is greater than that of the outdoor corresponding decision trees, the state type of the current position is determined to be indoor, otherwise, the state type of the current position is determined to be outdoor.
By implementing the method, the judgment of indoor and outdoor states can be realized based on the random forest classification model. Furthermore, because the sample data for training the random forest classification model is the multidimensional characteristics, the random forest classification model has higher judgment precision on indoor and outdoor states compared with other models obtained by training the sample data with single characteristics.
As shown in fig. 2, fig. 2 is a schematic flow chart of an indoor and outdoor state determination method disclosed in the embodiment of the present application. The method can comprise the following steps:
201. acquiring N types of target data measured by the wearable device at the current position.
It should be noted that step 201 in the embodiment of the present application may refer to step 101 in the embodiment shown in fig. 1, and is not described herein again.
202. And acquiring a processing result of each decision tree in the random forest classification model aiming at the N types of target data.
The processing result of each decision tree in the random forest classification model for the N types of target data may be that the wearable device is in an outdoor state or the wearable device is in an indoor state.
202. And obtaining the state type of the current position according to the processing result of each decision tree aiming at the N types of target data.
Optionally, obtaining the state type of the current location according to the processing result of each decision tree for the N types of target data may include:
in some embodiments, a first probability that the state type of the current location is indoor is obtained according to a processing result of each decision tree for the N types of target data; determining that the state type of the current position is indoor under the condition that the first probability is greater than the probability threshold; and determining that the state type of the current position is outdoor under the condition that the first probability is less than or equal to the probability threshold. It is understood that the first probability is a percentage of all decision trees of the random forest classification model of the decision trees that determine that the wearable device is in the indoor state.
In other embodiments, a second probability that the state type of the current position is outdoor is obtained according to the processing result of each decision tree for the N types of target data; determining that the state type of the current position is outdoor under the condition that the second probability is greater than the probability threshold; and under the condition that the second probability is less than or equal to the probability threshold, determining that the state type of the current position is indoor. It is understood that the first probability is a percentage of all decision trees of the random forest classification model of the decision trees that determine that the wearable device is in the outdoor state.
Optionally, the wearable device may further output first prompt information when the state type of the current location is not the preset type, where the first prompt information is used to prompt the wearable device user to return to the location corresponding to the preset type from the current location. It is understood that the preset type may be outdoor or indoor.
Optionally, the output mode of the first prompt message may be one or a combination of several of voice, text, and an indicator light.
Optionally, when the state type of the current location is not the preset type, second prompt information may be sent to the first terminal device in communication connection with the wearable device, where the second prompt information is used to prompt that the state type of the current location of the user of the first terminal device is not the preset type.
Further, after the wearable device sends the second prompt message to the first terminal device, the wearable device may also receive a control signal sent by the first terminal device; starting Bluetooth signal scanning according to the control signal so as to acquire a terminal identifier of a second terminal device within the Bluetooth radiation range of the wearable device; and sending preset information to the second terminal equipment according to the terminal identification, wherein the preset information comprises a user image of the wearable equipment user and the contact way of the first terminal equipment.
It is understood that the wearable device may be a child wearable device, the first terminal device is a home terminal, and the second terminal device is another user terminal. Assuming that the preset type may be indoor, in a case where the state type of the current location is outdoor, the child-wearing device may output a prompt message for prompting the child to return to indoor. In addition, the child wearing device can also send prompt information for informing parents of the child being outdoors to the parents. In addition, the child wearing device can also receive a control signal sent by the parent terminal, and based on the control signal, scanning of other user terminals is carried out, and then preset information containing child images and parent contact ways is sent to other user terminals. By implementing the method, under the condition that the child leaves the room, the effect of warning the child or warning parents can be achieved, the child can be found quickly by the help of other user terminals, and the child accident can be effectively avoided.
By implementing the method, the processing result of each decision tree in the random forest classification model on the N types of target data is integrated to determine the state type of the current position, so that the judgment precision of the state type of the current position can be further improved.
As shown in fig. 3a, fig. 3a is a schematic flow chart of an indoor and outdoor state determination method disclosed in the embodiment of the present application. The method can comprise the following steps:
301. acquiring k sample sets from sample data of the wearable device; wherein k is an integer of 2 or more.
In the embodiment of the present application, each sample in the sample data of the wearable device is a data set, and if the N-type target data includes a1, a2, a3, a4, and a5, the data set includes rate information, relative displacement information, GPS position information, RSRP information, and RDRQ information. The sample data of the wearable device may be historical measurement data of the wearable device and/or historical measurement data of other wearable devices. It should be noted that the other wearable devices and the wearable device may be wearable devices of the same model manufactured by the same manufacturer.
Optionally, the wearable device may obtain k sample sets from the sample data of the wearable device in a manner of having a sample-back. The sampling unit in the population is numbered from 1 to M, and the sampling unit is put back to the population after every sampling of one number. For any one extraction, the chances of the M numbers being extracted are equal, since the total capacity is unchanged.
302. And training the k decision trees according to the k sample sets, if the k decision trees do not meet the stopping rule, continuing to acquire the k sample sets from the sample data of the wearable device to train the k decision trees until the k decision trees meet the stopping rule, and obtaining the k trained decision trees.
It can be understood that each time k decision trees are obtained, the obtained k decision trees are used for forming a random forest model to be verified, the model precision of the random forest model to be verified is calculated by using a verification sample set, and under the condition that the model precision is judged to be greater than or equal to the preset precision, the k decision trees forming the random forest model to be verified are determined to meet a stopping rule, otherwise, the k decision trees forming the random forest model to be verified are determined not to meet the stopping rule. It should be noted that the verification sample set may be composed of samples that are not extracted from the sample data of the wearable device.
Optionally, training the k decision trees according to the k sample sets may include: determining internal nodes and leaf nodes of a first decision tree corresponding to the first sample set; wherein the first sample set is any one of the k sample sets. Wherein, the internal node is a state feature, and the leaf node is a data set.
Optionally, the determining, by the wearable device, the internal node and the leaf node of the first decision tree corresponding to the first sample set may include: obtaining information gain of each state feature of the first sample set; determining the state characteristic with the maximum information gain as a father node of the first decision tree; classifying the first sample set according to the data interval corresponding to the father node to obtain a child node corresponding to the father node; and under the condition that the state characteristics of the sub-nodes are not unique or the information gains of the state characteristics of the sub-nodes are all larger than or equal to a preset gain threshold, taking the data set corresponding to the sub-nodes as a first sample set, continuously executing the step of obtaining the information gain of each state characteristic of the first sample set until the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold are obtained, and taking the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold as leaf nodes.
Assuming that the first sample set is D, the information gain of any feature a of the first sample set D is g (D, a). The factors affecting the information gain g (D, a) of the feature a include the empirical entropy H (D) of the first sample set D and the empirical conditional entropy H (D | a) of the feature a. Specifically, the method comprises the following steps:
g(D,A)=H(D)-H(D|A) (3)
wherein K is the total number of categories of the state features in the first sample set D, CkThe number of samples corresponding to the kth state characteristic is obtained; n represents the number of sample sets obtained by dividing the first sample set D by the feature a, and i represents any data interval corresponding to the feature a.
Similarly, the information gain of each state feature of the first sample set can be obtained, so that the state feature with the largest information gain can be determined. It will be appreciated that each state feature corresponds to a data interval. Determining a data interval in which the father node data of the samples in the first sample set are located in a data interval corresponding to the father node; and dividing samples of the father node data in the same data interval into the same sample set to obtain child nodes corresponding to the father nodes. Therefore, the child node corresponding to the parent node is one or more sample sets. Note that the parent node is a certain state feature in the first sample set, and the parent node data of the sample is data corresponding to the certain state feature of the sample.
When the state characteristics of the sample data include velocity, relative displacement, GPS position, RSRP and RDRQ. For example, please refer to fig. 3b and fig. 3c, fig. 3b is a diagram illustrating a training process of a decision tree, and fig. 3c is a diagram illustrating a decision tree. Where u represents velocity, v represents relative displacement, w represents GPS position, x represents RSRP, and y represents RDRQ. A father node of the first sample set s is v, and 3 child nodes z1, z2 and z3 of v are obtained according to a data interval corresponding to v; assuming that a parent node of z1 is w, a parent node of z2 is u, and a parent node of z3 is x, classifying z1 according to a data interval corresponding to z1 to obtain a sample set o1 with unique state characteristics, and then o1 is a leaf node; classifying z2 according to the data interval corresponding to u to obtain a sample set o2 with unique state characteristics, wherein o2 is a leaf node; classifying samples contained in z3 according to the data interval corresponding to x to obtain a child node q1, wherein the state feature of q1 is not unique; assuming that the parent node of q1 is y, performing a sample set o3 with unique classification state characteristics on q1 by using a data interval corresponding to y, and then taking o3 as a leaf node; the decision tree shown in fig. 3c is finally obtained.
303. And performing pruning operation on each decision tree in the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree.
In order to avoid the fitting phenomenon of the trained decision tree, the process of simplifying the decision tree is called pruning. Pruning each of the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree, which may include: pruning and estimating the internal nodes of the second decision tree from the internal node at the bottommost part of the second decision tree according to the sequence from bottom to top to obtain a loss function corresponding to the internal node of the second decision tree; the second decision tree is any one of k trained decision trees; pruning the second decision tree according to the loss function corresponding to each internal node of the second decision tree to obtain a sub-tree sequence; acquiring the square error or the kini index of each subtree in the subtree sequence by using a verification sample set; and taking the subtree with the minimum square error or the minimum kini index as the optimal decision tree corresponding to the second decision tree.
In some embodiments, let the number of leaf nodes of the tree T be | T |, where T is a leaf node of the tree T, the leaf node having NtOne sample, NtThere are p classes of samples, where the sample of the ith class has NtiAnd (4) respectively.
The empirical entropy of a leaf node T is H (T)t):
The overall penalty function for the tree T is C (T):
the penalty function for a tree with t as a single node is: ca(t) ═ c (t) + a; subtree T with T as root nodetThe loss function of (d) is: ca(Tt)=C(Tt)+a|TtL, |; a is a pruning coefficient which is more than or equal to 0. When a is 0 or sufficiently small, there is an inequality Ca(Tt)<Ca(t); when a increases to a certain value, there is Ca(Tt)=Ca(t); when a continues to increase again, the inequality reverses, so long as a continues to increaseTtHas the same loss function as T, but T has fewer nodes, so T is greater than TtPreferably, for TtPruning is carried out.
Pruning estimation is performed on the internal nodes of the second decision tree T according to the sequence from bottom to top, loss functions before and after pruning of each internal node are calculated based on the formula, a pruning coefficient corresponding to each internal node is calculated according to the loss functions before and after pruning of each internal node, and the internal node with the minimum pruning coefficient is pruned to obtain a subtree T1. It should be noted that the operation of obtaining the subtree T1 may be referred to as a first-level recursion, and performing a second-level recursion on the subtree T1 may obtain the subtree T2. Similarly, a subtree Tn can be obtained by executing n-level recursion until a tree composed of single nodes is obtained, thereby triggering a recursion exit condition. It is understood that the sub-tree sequence may include T, T1.. Tn.
304. And combining the k optimal decision trees to obtain a random forest classification model.
By executing the step 303 and 304, pruning is performed on the trained decision tree to obtain an optimal decision tree, so that fitting of the decision tree can be effectively avoided, and the judgment precision of the random forest classification model can be improved.
305. Acquiring N types of target data measured by the wearable device at the current position.
306. And processing the N types of target data by using a random forest classification model, and determining the state type of the current position.
It should be noted that, the step 305 and 306 in the embodiment of the present application can refer to the description of the step 101 and 102 in the embodiment shown in fig. 1, and are not described herein again.
By implementing the method, the processing result of each decision tree in the random forest classification model on the N types of target data is integrated to determine the state type of the current position, so that the judgment precision of the state type of the current position can be further improved.
As shown in fig. 4, fig. 4 is a schematic structural diagram of a wearable device disclosed in the embodiments of the present application. The method can comprise the following steps:
an obtaining unit 401, configured to obtain N types of target data measured at a current location of the wearable device, where the N types of target data correspond to preset N state features respectively, the N state features at least include a motion feature of the wearable device and a communication feature of the wearable device, and N is a positive integer greater than or equal to 2.
A determining unit 402, configured to process the N types of target data by using a random forest classification model, and determine a state type of a current location; the random forest classification model is obtained through training according to sample data corresponding to the wearable device and the N state features, and the state type of the current position is indoor or outdoor.
Optionally, the motion characteristics of the wearable device may include any one or a combination of velocity, relative displacement, and global positioning system GPS position, and the communication characteristics of the wearable device may include RSRP and/or RDRQ.
Optionally, the determining unit 402 includes an acquiring subunit and a determining subunit. Wherein:
the acquisition subunit is used for acquiring the processing result of each decision tree in the random forest classification model for the N types of target data;
and the determining subunit is used for obtaining the state type of the current position according to the processing result of each decision tree for the N types of target data.
Optionally, the manner that the determining subunit is configured to obtain the state type of the current location according to the processing result of each decision tree for the N types of target data may specifically be: the determining subunit is configured to obtain, according to a processing result of each decision tree for the N types of target data, a first probability that the state type of the current location is indoor; determining that the state type of the current position is indoor under the condition that the first probability is greater than the probability threshold; and determining that the state type of the current position is outdoor under the condition that the first probability is less than or equal to the probability threshold. It can be understood that the first probability is a percentage of all decision trees included in the random forest classification model, where the decision trees corresponding to the indoor states of the wearable device are determined to be.
As shown in fig. 5, fig. 5 is a schematic structural diagram of another wearable device disclosed in the embodiment of the present application. The method can comprise the following steps: acquisition section 401, determination section 402, and modeling section 403.
Optionally, the modeling unit 403 may include a training subunit 4031 and an optimization subunit 4032. Wherein:
the training subunit 4031 is configured to acquire k sample sets from sample data of the wearable device; wherein k is an integer greater than or equal to 2; and training the k decision trees according to the k sample sets, if the k decision trees do not meet the stopping rule, continuing to acquire the k sample sets from the sample data of the wearable device to train the k decision trees until the k decision trees meet the stopping rule, and obtaining the k trained decision trees.
Optionally, the way that the training subunit 4031 is used to train k decision trees according to k sample sets may specifically be:
a training subunit 4031, configured to determine internal nodes and leaf nodes of the first decision tree corresponding to the first sample set; wherein the first sample set is any one of the k sample sets.
Further, the manner for the training subunit 4031 to determine the internal nodes and leaf nodes of the first decision tree corresponding to the first sample set may specifically be:
a training subunit 4031, configured to obtain information gain of each state feature of the first sample set; determining the state characteristic with the maximum information gain as a father node of the first decision tree; classifying the first sample set according to the data interval corresponding to the father node to obtain a child node corresponding to the father node; and under the condition that the state characteristics of the sub-nodes are not unique or the information gains of the state characteristics of the sub-nodes are all larger than or equal to a preset gain threshold, taking the data set corresponding to the sub-nodes as a first sample set, continuously executing the step of obtaining the information gain of each state characteristic of the first sample set until the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold are obtained, and taking the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold as leaf nodes.
An optimizing subunit 4032, configured to perform pruning operation on each of the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree; and combining the k optimal decision trees to obtain a random forest classification model.
Optionally, the optimization subunit 4032 is configured to perform pruning operation on each of the k trained decision trees, and a manner of obtaining an optimal decision tree corresponding to each decision tree may specifically be:
the optimization subunit 4032 is configured to perform pruning estimation on internal nodes of the second decision tree according to a bottom-to-top order from an internal node at the bottommost of the second decision tree to obtain a loss function corresponding to the internal node of the second decision tree; the second decision tree is any one of k trained decision trees; pruning the second decision tree according to the loss function corresponding to each internal node of the second decision tree to obtain a sub-tree sequence; acquiring the square error or the kini index of each subtree in the subtree sequence by using a verification sample set; and taking the subtree with the minimum square error or the minimum kini index as the optimal decision tree corresponding to the second decision tree.
As shown in fig. 6, which is a schematic view of another embodiment of the wearable device in the embodiment of the present application, the wearable device may include:
fig. 6 is a block diagram illustrating a partial structure of a wearable device provided in an embodiment of the present application. Referring to fig. 6, the wearable device includes: radio Frequency (RF) circuit 610, memory 620, input unit 630, display unit 640, sensor 650, audio circuit 660, wireless fidelity (WiFi) module 670, processor 680, and power supply 690. Those skilled in the art will appreciate that the wearable device structure shown in fig. 6 does not constitute a limitation of the wearable device, and may include more or fewer components than shown, or combine certain components, or a different arrangement of components.
The following describes the various components of the wearable device in detail with reference to fig. 6:
the RF circuit 610 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 680; in addition, the data for designing uplink is transmitted to the base station. In general, RF circuit 610 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuitry 610 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.
The memory 620 may be used to store software programs and modules, and the processor 680 may execute various functional applications and data processing of the wearable device by operating the software programs and modules stored in the memory 620. The memory 620 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phone book, etc.) created according to the use of the wearable device, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The input unit 630 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the wearable device. Specifically, the input unit 630 may include a touch panel 631 and other input devices 632. The touch panel 631, also referred to as a touch screen, may collect touch operations of a user (e.g., operations of the user on the touch panel 631 or near the touch panel 631 by using any suitable object or accessory such as a finger or a stylus) thereon or nearby, and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 631 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 680, and can receive and execute commands sent by the processor 680. In addition, the touch panel 631 may be implemented using various types, such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 630 may include other input devices 632 in addition to the touch panel 631. In particular, other input devices 632 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 640 may be used to display information input by or provided to the user and various menus of the wearable device. The Display unit 640 may include a Display panel 641, and optionally, the Display panel 641 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 631 can cover the display panel 641, and when the touch panel 631 detects a touch operation thereon or nearby, the touch panel is transmitted to the processor 680 to determine the type of the touch event, and then the processor 680 provides a corresponding visual output on the display panel 641 according to the type of the touch event. Although in fig. 6, the touch panel 631 and the display panel 641 are two separate components to implement the input and output functions of the wearable device, in some embodiments, the touch panel 631 and the display panel 641 may be integrated to implement the input and output functions of the wearable device.
The wearable device may also include at least one sensor 650, such as a light sensor, motion sensor, GPS sensor, and other sensors. In particular, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 641 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 641 and/or the backlight when the wearable device is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration) for recognizing wearable device attitude, and related functions (such as pedometer and tapping) for vibration recognition; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be further configured on the wearable device, detailed description is omitted here.
WiFi belongs to short-distance wireless transmission technology, and the wearable device can help a user to send and receive e-mails, browse webpages, access streaming media and the like through the WiFi module 670, and provides wireless broadband Internet access for the user. Although fig. 6 shows the WiFi module 670, it is understood that it does not belong to the essential constitution of the wearable device, and can be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 680 is a control center of the wearable device, and connects various parts of the entire wearable device through various interfaces and lines, and performs various functions of the wearable device and processes data by running or executing software programs and/or modules stored in the memory 620 and calling up data stored in the memory 620, thereby performing overall monitoring of the wearable device. Optionally, processor 680 may include one or more processing units; preferably, the processor 680 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 680.
The wearable device also includes a power supply 690 (e.g., a battery) for powering the various components, which may preferably be logically connected to the processor 680 via a power management system, such that functions of managing charging, discharging, and power consumption are performed via the power management system.
Although not shown, the wearable device may further include a camera, a bluetooth module, etc., which are not described herein.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by hardware instructions of a program, and the program may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), or other Memory, such as a magnetic disk, or a combination thereof, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
The indoor and outdoor state determination method, the wearable device, and the computer-readable storage medium disclosed in the embodiments of the present application are described in detail above, and specific examples are applied herein to explain the principle and the implementation manner of the present application, and the size of the step number in the specific examples does not mean that the execution sequence is necessarily sequential, and the execution sequence of each process should be determined by the function and the internal logic of the process, but should not form any limitation on the implementation process of the embodiments of the present application. The units described as separate parts may or may not be physically separate, and some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
The character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship. In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood, however, that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information. 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. If the integrated unit is implemented as a software functional unit and sold or used as a stand-alone product, it may be stored in a memory accessible to a computer. Based on such understanding, the technical solution of the present application, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, may be embodied in the form of a software product, stored in a memory, including several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of the embodiments of the present application.
The above description of the embodiments is only for the purpose of helping to understand the method of the present application and its core ideas; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. An indoor and outdoor state judgment method, characterized by comprising:
acquiring N types of target data measured by a wearable device at a current position, wherein the N types of target data correspond to preset N state characteristics respectively, the N state characteristics at least comprise motion characteristics of the wearable device and communication characteristics of the wearable device, and N is a positive integer greater than or equal to 2;
processing the N types of target data by using a random forest classification model, and determining the state type of the current position; the random forest classification model is obtained through training according to sample data corresponding to the wearable device and the N state features, and the state type of the current position is indoor or outdoor.
2. The method of claim 1, wherein the motion characteristics comprise any one or a combination of velocity, relative displacement, and Global Positioning System (GPS) position, and the communication characteristics comprise reference signal received power and/or reference signal received quality.
3. The method as claimed in claim 1 or 2, wherein the processing the N types of target data using a random forest classification model to determine the state type of the current location comprises:
acquiring a processing result of each decision tree in a random forest classification model aiming at the N types of target data;
and obtaining the state type of the current position according to the processing result of each decision tree aiming at the N types of target data.
4. The method according to claim 3, wherein the obtaining the state type of the current location according to the processing result of each decision tree for the N types of target data comprises:
obtaining a first indoor probability of the state type of the current position according to the processing result of each decision tree for the N types of target data;
determining that the state type of the current location is indoor if the first probability is greater than a probability threshold;
determining that the state type of the current location is outdoors if the first probability is less than or equal to the probability threshold.
5. A method as claimed in any one of claims 1, 2 and 4, wherein the random forest classification model comprises k decision trees, and wherein before processing the N classes of target data using the random forest classification model to determine the state type of the current location, the method further comprises:
acquiring k sample sets from sample data of the wearable device; wherein k is an integer greater than or equal to 2;
training the k decision trees according to the k sample sets, if the k decision trees do not meet a stopping rule, continuing to execute the step of acquiring the k sample sets from the sample data of the wearable device until the k decision trees meet the stopping rule, and obtaining k trained decision trees;
pruning each decision tree in the k trained decision trees to obtain an optimal decision tree corresponding to each decision tree;
and combining k optimal decision trees to obtain the random forest classification model.
6. The method according to claim 5, wherein said training the k decision trees from the k sample sets comprises:
determining internal nodes and leaf nodes of a first decision tree corresponding to the first sample set; wherein the first sample set is any one of the k sample sets.
7. The method of claim 6, wherein determining the internal nodes and leaf nodes of the first decision tree to which the first set of samples corresponds comprises:
obtaining information gain of each state feature of the first sample set;
determining the state characteristic with the maximum information gain as a father node of the first decision tree;
classifying the first sample set according to the data interval corresponding to the father node to obtain a child node corresponding to the father node;
and under the condition that the state characteristics of the sub-nodes are not unique or the information gains of the state characteristics of the sub-nodes are all larger than or equal to a preset gain threshold, taking the data set corresponding to the sub-nodes as a first sample set, continuously executing the step of obtaining the information gain of each state characteristic of the first sample set until the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold are obtained, and taking the sub-nodes with the unique state characteristics or the information gains of the state characteristics smaller than the preset gain threshold as leaf nodes.
8. The method according to claim 6, wherein the pruning each of the k trained decision trees to obtain an optimal decision tree corresponding to each of the k trained decision trees comprises:
pruning and estimating the internal nodes of the second decision tree from the internal node at the bottommost part of the second decision tree according to the sequence from bottom to top to obtain a loss function corresponding to the internal node of the second decision tree; wherein the second decision tree is any one of the k trained decision trees;
pruning the second decision tree according to the loss function corresponding to each internal node of the second decision tree to obtain a sub-tree sequence;
acquiring the square error or the kini index of each subtree in the subtree sequence by using a verification sample set;
and taking the subtree with the minimum square error or the minimum kini index as the optimal decision tree corresponding to the second decision tree.
9. A wearable device, characterized in that the wearable device comprises:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute part or all of the steps of the method according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program comprising instructions for carrying out some or all of the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011038752.9A CN112181055A (en) | 2020-09-28 | 2020-09-28 | Indoor and outdoor state judgment method, wearable device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011038752.9A CN112181055A (en) | 2020-09-28 | 2020-09-28 | Indoor and outdoor state judgment method, wearable device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112181055A true CN112181055A (en) | 2021-01-05 |
Family
ID=73945158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011038752.9A Pending CN112181055A (en) | 2020-09-28 | 2020-09-28 | Indoor and outdoor state judgment method, wearable device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112181055A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2013204138A1 (en) * | 2007-08-06 | 2013-05-09 | Trx Systems, Inc. | Locating, tracking, and/or monitoring personnel and/or assets both indoors and outdoors |
CN107423339A (en) * | 2017-04-29 | 2017-12-01 | 天津大学 | Popular microblogging Forecasting Methodology based on extreme Gradient Propulsion and random forest |
CN108834068A (en) * | 2018-07-17 | 2018-11-16 | 广东小天才科技有限公司 | Positioning method based on wearable device and wearable device |
CN109633721A (en) * | 2019-01-10 | 2019-04-16 | 广东小天才科技有限公司 | Indoor and outdoor judgment method and system |
CN111273131A (en) * | 2020-03-17 | 2020-06-12 | 辽宁工程技术大学 | Photovoltaic grid-connected power generation island detection method based on energy characteristics and random forest |
CN111368862A (en) * | 2018-12-25 | 2020-07-03 | 中兴通讯股份有限公司 | Method for distinguishing indoor and outdoor marks, training method and device of classifier and medium |
CN111638751A (en) * | 2020-05-19 | 2020-09-08 | 广东小天才科技有限公司 | Wearable device based safety early warning method and device and wearable device |
-
2020
- 2020-09-28 CN CN202011038752.9A patent/CN112181055A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2013204138A1 (en) * | 2007-08-06 | 2013-05-09 | Trx Systems, Inc. | Locating, tracking, and/or monitoring personnel and/or assets both indoors and outdoors |
CN107423339A (en) * | 2017-04-29 | 2017-12-01 | 天津大学 | Popular microblogging Forecasting Methodology based on extreme Gradient Propulsion and random forest |
CN108834068A (en) * | 2018-07-17 | 2018-11-16 | 广东小天才科技有限公司 | Positioning method based on wearable device and wearable device |
CN111368862A (en) * | 2018-12-25 | 2020-07-03 | 中兴通讯股份有限公司 | Method for distinguishing indoor and outdoor marks, training method and device of classifier and medium |
CN109633721A (en) * | 2019-01-10 | 2019-04-16 | 广东小天才科技有限公司 | Indoor and outdoor judgment method and system |
CN111273131A (en) * | 2020-03-17 | 2020-06-12 | 辽宁工程技术大学 | Photovoltaic grid-connected power generation island detection method based on energy characteristics and random forest |
CN111638751A (en) * | 2020-05-19 | 2020-09-08 | 广东小天才科技有限公司 | Wearable device based safety early warning method and device and wearable device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108834068B (en) | Positioning method based on wearable device and wearable device | |
CN108073605B (en) | Method and device for loading and pushing service data and generating interactive information | |
CN108255382B (en) | Method and device for recommending floating menu content | |
CN107608861B (en) | Cooling control method and device | |
CN106022062B (en) | Unlocking method and mobile terminal | |
CN110458655B (en) | Shop information recommendation method and mobile terminal | |
WO2015007092A1 (en) | Method, apparatus and device for controlling antenna of mobile device | |
CN107292235B (en) | fingerprint acquisition method and related product | |
CN109561420B (en) | Emergency help-seeking method and related equipment | |
CN107566604B (en) | Message reminding control method and user terminal | |
CN105100197B (en) | The method and device of application is installed | |
CN111125523A (en) | Searching method, searching device, terminal equipment and storage medium | |
CN107566909B (en) | Barrage-based video content searching method and user terminal | |
CN110771121A (en) | Application resource recommendation method and related equipment | |
CN107317918B (en) | Parameter setting method and related product | |
CN106714277B (en) | Network connection method and terminal | |
CN108616448A (en) | A kind of the path recommendation method and mobile terminal of Information Sharing | |
CN107256383B (en) | Fingerprint acquisition method and device, related terminal equipment and readable storage medium | |
CN108664288A (en) | A kind of image interception method and mobile terminal | |
CN109141355B (en) | Relative height measuring method based on multiple sensors and wearable equipment | |
CN112859136B (en) | Positioning method and related device | |
CN113015996A (en) | Advertisement pushing method and related equipment | |
CN107659718B (en) | Method and device for controlling mobile terminal, mobile terminal and storage medium | |
CN109041212B (en) | Positioning method and wearable device | |
CN112764543A (en) | Information output method, terminal equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210105 |