CN112381126B - Indoor and outdoor scene recognition method and device, electronic equipment and storage medium - Google Patents

Indoor and outdoor scene recognition method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112381126B
CN112381126B CN202011205236.0A CN202011205236A CN112381126B CN 112381126 B CN112381126 B CN 112381126B CN 202011205236 A CN202011205236 A CN 202011205236A CN 112381126 B CN112381126 B CN 112381126B
Authority
CN
China
Prior art keywords
noise ratio
signal
visible satellite
visible
current
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011205236.0A
Other languages
Chinese (zh)
Other versions
CN112381126A (en
Inventor
才正国
高国松
赵明喜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Huami Health Technology Co Ltd
Original Assignee
Anhui Huami Health Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Anhui Huami Health Technology Co Ltd filed Critical Anhui Huami Health Technology Co Ltd
Priority to CN202011205236.0A priority Critical patent/CN112381126B/en
Publication of CN112381126A publication Critical patent/CN112381126A/en
Application granted granted Critical
Publication of CN112381126B publication Critical patent/CN112381126B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • 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

Abstract

The invention discloses an indoor and outdoor scene recognition method, an indoor and outdoor scene recognition device, electronic equipment and a storage medium. The indoor and outdoor scene recognition method comprises the following steps of: obtaining visible satellite message sentences in the current updating period; analyzing the visible satellite message statement to determine the current visible satellite signal-to-noise ratio characteristic; inputting the current signal-to-noise ratio characteristics of the visible satellite into a preset classification model to obtain a type label output by the classification model; and determining the current indoor and outdoor scenes according to the type labels. The method judges the current indoor or outdoor scene by classifying the characteristics of the signal-to-noise ratio difference of the visible satellite in the indoor or outdoor scene, has simple recognition mode, less calculation amount, higher accuracy and reliability, has smaller influence of factors such as environment, position, wearing mode and the like on the visible satellite message statement, and has wider application range.

Description

Indoor and outdoor scene recognition method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of electronic devices, and in particular, to an indoor and outdoor scene recognition method and apparatus, an electronic device, and a storage medium.
Background
With the development of electronic technology, today's electronic devices have many functions and can provide various types of services to users. For example, by identifying whether the current location is indoor or outdoor, to provide auxiliary analysis of the scene in which the user is located to various applications in the electronic device, corresponding functions are assisted.
In the related art, environmental data such as ambient illumination intensity, air pressure change, temperature and the like are collected through various sensors arranged in an electronic device, or the current indoor and outdoor scenes are identified through a mode that behavior characteristics such as running, stopping behaviors and turning behaviors of a user are detected through devices such as an acceleration sensor, a gyroscope and a magnetic sensor in the electronic device.
However, the applicant found that in the above method, the sensor is easily affected by factors such as shielding of clothes of a user, differences in wearing modes, interference of surrounding environments, and the like when collecting environmental data, and when the user performs complex movements in different environments, a large amount of data operations are required to be performed on equipment such as an acceleration sensor, a gyroscope, and the like, calculation deviation is easily generated, and the sensor is easily affected by factors such as geographical positions, weather conditions, and the like, so that travel cannot be accurately detected. Therefore, the method for detecting the indoor and outdoor scenes by the electronic equipment in the related art has lower accuracy and practicability, and the detection process is more complex.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present invention is to provide an indoor and outdoor scene recognition method, which classifies features representing signal-to-noise ratio differences of visible satellites in indoor and outdoor scenes to determine whether the scene is indoor or outdoor, has simple recognition method, less calculation amount, higher accuracy and reliability, and has wider application range due to less influence of factors such as environment, position and wearing mode on visible satellite message sentences.
A second object of the present invention is to provide an indoor and outdoor scene recognition apparatus.
A third object of the present invention is to propose an electronic device.
A fourth object of the present invention is to propose a non-transitory computer readable storage medium.
In order to achieve the above object, the first aspect of the present invention provides an indoor and outdoor scene recognition method, which includes the following steps:
obtaining visible satellite message sentences in the current updating period;
analyzing the visible satellite message statement to determine the current visible satellite signal-to-noise ratio characteristic;
inputting the current signal-to-noise ratio characteristics of the visible satellite into a preset classification model to obtain a type label output by the classification model;
And determining the current indoor and outdoor scenes according to the type labels.
According to the indoor and outdoor scene recognition method, firstly, visible satellite message sentences in a current update period are acquired, then the visible satellite message sentences are analyzed to determine the current signal-to-noise ratio characteristics of the visible satellites, the current signal-to-noise ratio characteristics of the visible satellites are input into a preset classification model to acquire type labels output by the classification model, and finally, the current indoor and outdoor scenes are determined according to the type labels. The method judges the current indoor or outdoor scene by classifying the characteristics used for representing the satellite signal difference under the indoor and outdoor scenes based on the signal-to-noise ratio, has simple recognition mode, less calculation amount, higher accuracy and reliability, and has less influence of factors such as environment, place, wearing mode and the like on the visible satellite message statement, thereby having wide application range.
To achieve the above object, a second aspect of the present invention provides an indoor and outdoor scene recognition device, including:
the first acquisition module is used for acquiring visible satellite message sentences in the current updating period;
the first determining module is used for analyzing the visible satellite message statement to determine the current visible satellite signal-to-noise ratio characteristic;
The second acquisition module is used for inputting the signal-to-noise ratio characteristics of the current visible satellite into a preset classification model so as to acquire a type label output by the classification model;
and the second determining module is used for determining the current indoor and outdoor scenes according to the type tag.
According to the indoor and outdoor scene recognition device, firstly, visible satellite message sentences in a current update period are acquired, then the visible satellite message sentences are analyzed to determine the signal-to-noise ratio characteristics of the current visible satellites, the signal-to-noise ratio characteristics of the current visible satellites are input into a preset classification model to acquire type labels output by the classification model, and finally, the current indoor and outdoor scenes are determined according to the type labels. The device judges that the indoor or outdoor scene is present by classifying the characteristics of the signal-to-noise ratio difference of the visible satellite in the indoor or outdoor scene, has simple recognition mode, less calculation amount, higher accuracy and reliability, and has wider application range because the visible satellite message statement is less influenced by factors such as environment, position, wearing mode and the like.
To achieve the above object, a third aspect of the present invention provides an electronic device, including: a processor; and a memory communicatively coupled to the processor; the memory stores instructions executable by the processor, and when the instructions are called and executed by the processor, the indoor and outdoor scene recognition method in any aspect can be realized.
To achieve the above object, a fourth aspect of the present invention proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions, when executed, implement the indoor and outdoor scene recognition method of any one of the above aspects.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a schematic flow chart of an indoor and outdoor scene recognition method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for determining the signal-to-noise ratio characteristics of a current visible satellite according to an embodiment of the present invention;
FIG. 3 is a flow chart of a specific method for determining the signal-to-noise ratio characteristics of a current visible satellite according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of a specific indoor and outdoor scene recognition method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an indoor and outdoor scene recognition device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a specific indoor and outdoor scene recognition device according to an embodiment of the present invention;
Fig. 7 shows a block diagram of an exemplary electronic device suitable for use in implementing the indoor and outdoor scene recognition method of an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The indoor and outdoor scene recognition method according to the embodiment of the present invention is described below with reference to the accompanying drawings.
The indoor and outdoor scene recognition method provided by the embodiment of the invention can be executed by electronic equipment provided with a satellite positioning module, wherein the electronic equipment can be wearable equipment or mobile terminal equipment and the like, and the built-in satellite positioning module can be a global positioning system (Global Positioning System, abbreviated as GPS) module or Beidou positioning module and the like, and is not limited in any way.
Fig. 1 is a flow chart of an indoor and outdoor scene recognition method provided by an embodiment of the present invention, as shown in fig. 1, the indoor and outdoor scene recognition method includes the following steps:
Step 101, obtaining a visible satellite message statement in a current update period.
The visible satellite message sentence (Global Navigation Satellite System Satellites in View, abbreviated as GSV) is a message output sentence conforming to the standard protocol of the global navigation satellite system, and is used for representing the information of the visible satellite that can be received by the positioning module, including the number (ID), the elevation angle, the azimuth angle, the signal-to-noise ratio, and the like of the satellite.
Specifically, when the current indoor and outdoor scenes need to be identified, a visible satellite message statement in the current update period can be obtained through the satellite positioning module, wherein the update period can be determined according to the period of update data when the satellite positioning system performs positioning, for example, the update period can be 1 second.
For example, when the wearable device identifies the current indoor and outdoor fields Jing Shi, the GPS module built in the device is started first, then the GPS module searches for satellite signals, and obtains returned message sentences conforming to the national marine electronics association (National Marine Electronics Association, NMEA) 0183 protocol of the GPS module, and then screens all GSV sentences returned in the current 1 second.
In one embodiment of the present invention, in order to improve accuracy of scene recognition, visible satellite message sentences transmitted by different types of satellite systems may be acquired, for example, any one of visible satellite message sentences of types such as a visible satellite message sentence (GPSGSV) transmitted by a global positioning system, a visible satellite message sentence (GLGSV) transmitted by a GLONASS system, a visible satellite message sentence (BDGSV) transmitted by a beidou navigation system, and a visible satellite message sentence (GAGSV) transmitted by a galileo system may be acquired. The indoor and outdoor scene recognition method provided by the embodiment of the invention can be realized by a plurality of types of GPS modules such as single mode, double mode or multiple modes at present aiming at GSV sentences of different types and numbers, thereby improving the practicability and universality of the indoor and outdoor scene recognition method provided by the embodiment of the invention.
Step 102, parsing the visible satellite message sentence to determine the current visible satellite signal-to-noise ratio characteristic.
Specifically, all visible satellite message sentences in the acquired current update period are analyzed to acquire information contained in the visible satellite message sentences. As a possible way, the display of each visible satellite message sentence is converted, the visible satellite message sentences are displayed in a mode of combining a plurality of fields, and a message list corresponding to the set of visible satellite message sentences is generated so as to read the visible satellite information corresponding to each visible satellite message sentence according to the message list.
In order to more clearly describe the parsed visible satellite message statement in the embodiment of the present invention, a parsed GPGSV statement is taken as an example to specifically describe the following:
$GPGSV,3,1,10,20,78,331,45,01,59,235,47,22,41,069,,13,32,252,45*70
as shown above, the visible satellite message sentence contains a plurality of fields after analysis, each field corresponds to different information, wherein field 0 is "$gpgsv", indicating that the sentence ID is GPS Satellites in View; the field 1 is 3, which indicates that the total GPGSV statement number is 3; the field 2 is "1", which indicates that the present GSV statement is the 1 st one in the total GSV statement; field 3 is "10" indicating a total of 10 satellites in view; the field 4 is "20", indicating that the satellite number is 20, i.e., the information of the visible satellite number 20 follows; field 5 is "78", indicating that the satellite has an elevation angle of 78 degrees; field 6 is "331", indicating that the azimuth of the satellite is 331 degrees; field 7 is "45" indicating that the signal-to-noise ratio of the satellite to the current device is 45; field 8 is "01" indicating that satellite number 01, i.e., information for satellite number 01, and so on, elevation, azimuth, and signal-to-noise information for satellites number 01, 22, and 13 can be obtained in the manner described above. Where field 15 is null indicating that the signal-to-noise ratio for satellite number 22 is null.
Further, after the visible satellite message statement is parsed, the current visible satellite signal-to-noise ratio characteristic can be calculated according to the information in the obtained visible satellite message statement, such as the number of the visible satellites and the signal-to-noise ratio of each visible satellite.
It should be noted that, the signal-to-noise ratio of the visible satellite message sentences received by the electronic device in different scenes is different. For example, the signal-to-noise ratios of the satellites to the wearable device are different in indoor or outdoor scenes, so that the signal-to-noise ratios of the visible satellites contained in the visible satellite message sentences are calculated, the signal-to-noise ratio characteristics of the visible satellites used for representing the indoor and outdoor scene distinction based on the signal-to-noise ratios can be obtained, and the calculated signal-to-noise ratio characteristics can be conveniently classified through a preset classification model, so that the indoor and outdoor scenes corresponding to the signal-to-noise ratio characteristics can be determined.
In one embodiment of the invention, when determining the signal-to-noise ratio characteristics of the current visible satellites, the signal-to-noise ratio of each visible satellite can be counted in different modes, and the signal-to-noise ratio characteristics of the multi-dimensional satellites are determined, for example, the mean value, the variance and the standard deviation of the signal-to-noise ratio of each visible satellite are counted respectively, so that the signal-to-noise ratio characteristics of the three-dimensional satellites are obtained, the signal-to-noise ratio of the current visible satellites can be evaluated more comprehensively, and the accuracy of indoor and outdoor scene recognition is improved.
And step 103, inputting the signal-to-noise ratio characteristics of the current visible satellite into a preset classification model to obtain a type label output by the classification model.
Step 104, determining the current indoor and outdoor scenes according to the type tag.
The classification model maps acquired data (namely the signal-to-noise ratio characteristic of the visible satellite in the invention) to one of given categories (namely one of indoor scenes or outdoor scenes), and outputs a corresponding type label according to the mapping result, so as to predict the category to which the data belongs.
In specific implementation, as a possible implementation manner, the current signal-to-noise ratio characteristic of the visible satellite is input into a preset two-class classifier for judging indoor and outdoor, and whether the current signal-to-noise ratio characteristic of the visible satellite corresponds to an indoor scene or an outdoor scene is determined through an indoor scene label or an outdoor scene label output by the classifier.
Specifically, several groups of visible satellite message sentences under different conditions of time, place, weather and the like are collected in advance, then analysis, feature extraction, vectorization and the like are performed on the collected sentences according to the mode in the embodiment, and then the processed data set is split to form a training set and a verification set. And selecting a corresponding algorithm for machine learning training, for example, selecting a decision tree, logistic regression, naive Bayes, a neural network and other algorithms for training, wherein the output of the classifier is set to be a set indoor scene label or an outdoor scene label, namely, the final classification decision made by the class II classifier is determined, and further, the classifier model is finally obtained through continuous evaluation and parameter adjustment. And then, inputting the signal-to-noise ratio characteristics of the current visible satellite into a trained classifier, and outputting a corresponding type label by the classifier.
Further, the current indoor and outdoor scenes are determined according to the type labels. Specifically, if the classifier outputs an indoor scene tag, the electronic device is determined to be currently in an indoor scene according to the tag, and if the classifier outputs an outdoor scene tag, the electronic device is determined to be currently in an outdoor scene according to the tag. Thereby, the recognition result of the indoor and outdoor scenes is obtained.
In the embodiment of the invention, in order to reduce the data operand, a decision tree algorithm can be selected to train a classifier model, and the current indoor and outdoor scenes are identified through a decision tree classifier with lower computational complexity, so that the complexity of identifying the indoor and outdoor scenes is reduced. Of course, the invention can also select other machine learning methods such as naive Bayes algorithm and support vector machine algorithm or artificial neural network algorithm according to actual needs, and the invention is not limited herein.
As another possible implementation manner, a large number of experiments for determining the signal-to-noise ratio characteristics of the visible satellites are performed indoors and outdoors in advance, and the signal-to-noise ratio characteristics of the standard visible satellites in the indoor scene and the signal-to-noise ratio characteristics of the standard visible satellites in the outdoor scene are determined by carrying out statistics, analysis and other processes on experimental results. And then, after the signal-to-noise ratio characteristic of the current visible satellite is obtained, carrying out similar operation on the signal-to-noise ratio characteristic of the current visible satellite and the two standard characteristics respectively to obtain the distance between the signal-to-noise ratio characteristic of the current visible satellite and the two standard characteristics, and determining the current indoor and outdoor scene according to the magnitude relation of the two distance values. For example, if the distance between the signal-to-noise ratio feature of the current visible satellite and the signal-to-noise ratio feature of the standard visible satellite in the indoor scene is smaller than the distance between the signal-to-noise ratio feature of the current visible satellite and the signal-to-noise ratio feature of the standard visible satellite in the outdoor scene, the signal-to-noise ratio feature of the current visible satellite is indicated to be in the signal-to-noise ratio feature range of the standard visible satellite in the indoor scene, and the current indoor scene is determined.
Therefore, the indoor and outdoor scene recognition method of the invention determines the current indoor and outdoor scenes according to the signal-to-noise ratio characteristics of the current visible satellites, and has low calculation complexity and easy realization because the influence of factors such as shielding of obstacles, geographic positions, weather conditions and the like on the visible satellite message sentences sent by the receiving satellites is small and negligible, the recognition method is not limited by conditions such as environment, places and the like, the accuracy of recognition results is high, and the recognition results can be obtained by analyzing and extracting the characteristics of fewer visible satellite message sentences.
In summary, in the indoor and outdoor scene recognition method of the embodiment of the invention, the visible satellite message statement in the current update period is acquired first, then the visible satellite message statement is parsed to determine the current signal-to-noise ratio characteristic of the visible satellite, and then the current signal-to-noise ratio characteristic of the visible satellite is input into the preset classification model to acquire the type label output by the classification model, and finally the current indoor and outdoor scene is determined according to the type label. The method judges the current indoor or outdoor scene by classifying the characteristics of the signal-to-noise ratio difference of the visible satellite in the indoor or outdoor scene, has simple recognition mode, less calculation amount, higher accuracy and reliability, and has less influence on the visible satellite message statement by factors such as environment, position, wearing mode and the like, thereby having wide application range.
Based on the above embodiment, in order to more clearly describe a specific process of analyzing the visible satellite message sentence to determine the signal-to-noise ratio characteristic of the current visible satellite, the invention further provides a method for determining the signal-to-noise ratio characteristic of the current visible satellite.
Fig. 2 is a flowchart of a method for determining a signal-to-noise ratio characteristic of a current visible satellite according to an embodiment of the present invention, as shown in fig. 2, where the method includes:
step 201, parse the visible satellite message sentence to obtain the number of visible satellites and the signal-to-noise ratio of each visible satellite contained in the message sentence.
Specifically, referring to the method in the above embodiment, all visible satellite message sentences in the obtained current update period may be parsed, a complete message list corresponding to the set of visible satellite message sentences is generated, and the number of visible satellites and the signal to noise ratio of each visible satellite are obtained from the message list. Since in practical applications different types and numbers of GSV statements are generally available, the process of obtaining the number of visible satellites contained in a message statement and the signal-to-noise ratio of the individual visible satellites is described in detail below in two examples.
In the first example, when the obtained GSV sentence includes two GPSGSV sentences and one GLGSV sentence, the three GSV sentences are converted respectively, so as to generate a message list corresponding to the set of visible satellite message sentences as shown in table 1 below.
TABLE 1
$GPGSV，2，1，07 01,01,186，， 04,39,232，， 07,18,316，15， 08,68,239，，
$GPGSV，2，2，07 18,02,035，， 21,10,042，00， 31,09,132，，
$GLGSV，1，1，03 69,10,247，， 70,08,302，14， 88,24,032，，
As shown in table 1, as is clear from the data on each field in each converted visible satellite message sentence, the number of visible satellites returning to the GPSGSV sentence is 7, and the number of visible satellites returning to the GLGSV sentence is 3, so that the number of visible satellites included in the set of message sentences is 10 by adding 7 to 3. In the signal-to-noise ratio of each visible satellite, the number of satellites with data on the field representing the signal-to-noise ratio is 3, namely, the number of satellites with number 07, number 21 and number 70 respectively, and the corresponding signal-to-noise ratios are 15,0 and 14.
In a second example, when two GPSGSV sentences are included in the obtained GSV sentence, the two GPSGSV sentences are converted respectively, and a message list corresponding to the set of visible satellite message sentences is generated as shown in table 2 below.
TABLE 2
$GPGSV，2，1，08 01,28,179，19， 04,16,209，13， 07,44,312，26， 08,70,352，28，
$GPGSV，2，2，08 09,22,244，33， 11,66,191，25， 23,21,254，， 30,13,318,00，
As shown in table 2, the number of visible satellites returned to the GPSGSV sentence is 8, and there are no other satellites, as is known from the data on each field in each converted visible satellite message sentence, and therefore the number of visible satellites included in the set of message sentences is 8. In the signal-to-noise ratio of each visible satellite, the number of satellites with data on a field representing the signal-to-noise ratio is 7, and the signal-to-noise ratios of the satellites are respectively 19, 13, 26, 28, 33, 25 and 0, and the signal-to-noise ratios of the satellites with the number of 23 are respectively 19, 13, 26, 28, 33, 25 and 0.
Step 202, determining the current signal-to-noise ratio characteristic of the visible satellites according to the number of the visible satellites and the signal-to-noise ratio of each visible satellite.
The visible satellite signal-to-noise ratio features in the embodiment of the invention comprise various features which can be used for representing indoor and outdoor satellite signal differences based on the signal-to-noise ratio, and the dimension of the visible satellite signal-to-noise ratio features can be determined according to actual needs.
As one possible implementation, the following is an exemplary illustration of a specific method for determining the signal-to-noise ratio characteristics of a current visible satellite according to the present invention
Fig. 3 is a flowchart of a specific method for determining a signal-to-noise ratio characteristic of a current visible satellite according to an embodiment of the present invention, as shown in fig. 3, after obtaining the number of visible satellites and the signal-to-noise ratio of each visible satellite included in a message statement, the method further includes:
step 301, determining the number of the effective satellites currently according to the signal-to-noise ratio of each visible satellite.
The number of effective satellites may be the number of satellites whose signal-to-noise ratio is not null in this embodiment.
With continued reference to both examples in step 201, in the first example the number of active visible satellites is 3, and in the second example the number of active visible satellites is 7.
Step 302, determining whether the number of currently available satellites is greater than a first threshold, if so, executing step 303, and if not, executing step 304.
The first threshold may be set according to a requirement of detection accuracy. For example, in this embodiment, when it is only determined that the vehicle is currently located indoors or outdoors, and the accuracy requirement for the specific location coordinate is low, the first threshold may be set to 3.
With continued reference to both examples of step 201, in a first example, the number of active visible satellites is 3, if the first threshold is 3, then the number of active visible satellites is not greater than the first threshold, then step 304 is performed subsequently. In a second example, the number of available satellites is 7, and if the first threshold is 3, the number of available satellites is greater than the first threshold, then step 303 is performed subsequently.
Step 303, calculating the mean, variance and median of the signal-to-noise ratio of the current effective visible satellite according to the signal-to-noise ratio of each effective visible satellite.
Specifically, corresponding statistical operation is performed on the signal-to-noise ratio of each effective visible satellite, and the mean, variance and median of the signal-to-noise ratio of the current effective visible satellite are calculated. For example, referring to the second example in step 201, the mean, variance, and median of the signal-to-noise ratios 19, 13, 26, 28, 33, 25, and 0 of the effective satellites are calculated to obtain the mean, variance, and median of the signal-to-noise ratios of 20.5714, 11.1184, and 25, respectively.
Step 304, determining that the signal-to-noise ratio mean, variance and median of the current effective visible satellite are all preset values.
Specifically, the preset value may be any value outside the effective snr range of the visible satellite. For example, the effective signal-to-noise ratio of the visible satellite ranges from 0 to 99, and then the preset value may be 100, 101, 102, or may be-1, -2, -3, etc. In practical use, the signal to noise ratio is usually null but is only an accidental event, and in order to avoid the influence of the accidental event on the long-term detection result, in the embodiment of the present application, the preset value may be a value with a smaller difference from the effective signal to noise ratio, for example, the preset value may be-1, -2, etc. Accordingly, referring to the first example in step 201, the mean, variance, and median of the signal-to-noise ratio of the current active visible satellite may be set to-1.
Step 305, determining the signal-to-noise ratio characteristic of the current visible satellite according to the signal-to-noise ratio mean, variance and median of the current effective visible satellite.
Specifically, vectorizing the obtained signal-to-noise ratio mean value, variance and median of the effective visible satellite to obtain the signal-to-noise ratio characteristics of the visible satellite with different dimensionalities. For example, a 3-dimensional visible satellite signal-to-noise characteristic vector (mean, variance) may be generated directly from the mean, variance, and median of the signal-to-noise ratios.
In one embodiment of the present invention, the number of invalid visible satellites may be determined according to the current number of visible satellites and the number of valid visible satellites, and then the number of invalid visible satellites may be compared with the number of visible satellites to determine the current duty cycle of the invalid visible satellites. With continued reference to both examples in step 201, in the first example, the number of nulled visible satellites with a signal-to-noise ratio of null is 7, then the current nulled visible Wei Xingzhan is 7/10. In a second example, the number of invalid visible satellites with a null signal-to-noise ratio is 1 and the number of visible satellites is 8, then the current invalid visible Wei Xingzhan is 1/8.
Further, the signal-to-noise ratio characteristics of the current visible satellite are determined according to the signal-to-noise ratio mean, variance, median and invalid visible Wei Xingzhan ratio of the current valid visible satellite. Therefore, the dimension of the signal-to-noise ratio characteristic of the visible satellite is expanded, and the accuracy of indoor and outdoor scene recognition is improved.
In summary, the method for determining the signal-to-noise ratio characteristics of the current visible satellite according to the embodiment of the invention firstly analyzes the visible satellite message statement to obtain the number of visible satellites and the signal-to-noise ratio of each visible satellite contained in the message statement, and then determines the signal-to-noise ratio characteristics of the current visible satellite according to the number of visible satellites and the signal-to-noise ratio of each visible satellite, wherein the signal-to-noise ratio average value, variance and median of the current effective visible satellite can be calculated according to the signal-to-noise ratio of the effective visible satellite to determine the signal-to-noise ratio characteristics of the current visible satellite. According to the method, indoor and outdoor scenes can be accurately identified by analyzing, information extracting and statistical operation on a small number of visible satellite message sentences, the data calculation amount is small, the complexity of indoor and outdoor scene identification is low, and the accuracy is high.
Based on the above embodiment, in practical application, in order to avoid the influence of unexpected factors in the operation process of recognizing indoor and outdoor scenes, the invention further improves the accuracy of indoor and outdoor scene recognition.
Fig. 4 is a schematic flow chart of a specific indoor and outdoor scene recognition method according to an embodiment of the present invention, as shown in fig. 4, after the step of determining the signal-to-noise ratio characteristic of the current visible satellite, the method further includes:
step 401, acquiring N groups of visible satellite message sentences corresponding to the first N update periods adjacent to the current update period, where N is a positive integer greater than 1.
Specifically, after the visible satellite signal-to-noise ratio characteristics corresponding to the visible satellite message sentences in the current update period are determined, the visible satellite message sentences in each of the N update periods before the current update period, that is, N groups of visible satellite message sentences corresponding to the N periods before the current update period on the time axis, are acquired. Wherein, N can be set according to the accuracy requirement of identifying indoor and outdoor scenes, for example, N is set to 3, etc.
In one embodiment of the present invention, after the visible satellite message sentences in each update period are obtained, the visible satellite message sentences in each update period can be cached, so that the visible satellite message sentences in the current update period can be queried in the subsequent update period. In order to reduce the occupied storage space, when the interval between the update period and the current update period in the stored data is determined to be greater than a preset threshold value, the data corresponding to the update period exceeding the preset threshold value can be deleted.
Of course, the visible satellite message sentences corresponding to the first N update periods may also be obtained in other manners, for example, after an application in the electronic device obtains the visible satellite message sentences in each update period, the visible satellite message sentences are sent to the cloud platform for storage, when the visible satellite message sentences in the period need to be obtained, a request for obtaining the corresponding visible satellite message sentences is sent to the cloud platform according to the identification of the update period.
Step 402, parse the N sets of visible satellite message sentences to obtain the number of visible satellites corresponding to each set of visible satellite message sentences and the signal-to-noise ratio of each visible satellite.
Step 403, determining the signal-to-noise ratio characteristics of the N groups of visible satellites according to the number of the N groups of visible satellites and the signal-to-noise ratio of each visible satellite.
Specifically, the N sets of visible satellite message sentences are parsed to obtain the number of visible satellites corresponding to each set of visible satellite message sentences and the signal to noise ratio of each visible satellite, and further, according to the number of the N sets of visible satellites and the signal to noise ratio of each visible satellite, the specific implementation manner of the signal to noise ratio characteristics of the N sets of visible satellites is determined, and the description of the signal to noise ratio characteristics of the visible satellites corresponding to the current determination update period in the above embodiment may be referred to, which is not repeated herein.
In one embodiment of the invention, after the visible satellite signal-to-noise ratio characteristics corresponding to each updating period are determined, the determined visible satellite signal-to-noise ratio characteristics can be cached, so that the visible satellite signal-to-noise ratio characteristics corresponding to the previous N periods can be directly queried according to the time sequence.
Step 404, correcting the current visible satellite signal-to-noise ratio characteristic according to the N groups of visible satellite signal-to-noise ratio characteristics to generate the target visible satellite signal-to-noise ratio characteristic.
Specifically, correcting the signal-to-noise ratio characteristic of the current visible satellite includes calculating the signal-to-noise ratio characteristic of the visible satellite of the second time for N groups of the signal-to-noise ratio characteristics of the visible satellite and the signal-to-noise ratio characteristic of the current visible satellite to obtain the signal-to-noise ratio characteristic of the visible satellite with more dimensions, and taking the signal-to-noise ratio characteristic of the visible satellite as the signal-to-noise ratio characteristic of the target visible satellite after correction.
In one embodiment of the present invention, in the N sets of visible satellite signal-to-noise characteristics and the current visible satellite signal-to-noise characteristics, if each set of visible satellite signal-to-noise characteristics includes an effective visible satellite signal-to-noise average value, an effective visible satellite signal-to-noise variance, an effective visible satellite signal-to-noise median, and an ineffective visible satellite duty cycle, then there is n+1 sets of effective visible satellite signal-to-noise ratios, an effective visible satellite signal-to-noise variance, an effective visible satellite signal-to-noise median, and an ineffective visible Wei Xingzhan ratio. Further, a first mean, a first variance, and a first median corresponding to the mean of the signal-to-noise ratios of the n+1 sets of effective satellites are calculated, a second mean, a second variance, and a second median corresponding to the variance of the signal-to-noise ratios of the n+1 sets of effective satellites are calculated, a third mean, a third variance, and a third median corresponding to the median of the signal-to-noise ratios of the n+1 sets of effective satellites are calculated, and a fourth mean, a fourth variance, and a fourth median corresponding to the n+1 sets of ineffective visible Wei Xingzhan ratios are calculated. From this, after vectorizing the first mean, the first variance, the first median, the second mean, the second variance, the second median, the third mean, the third variance, the third median, the fourth mean, the fourth variance, and the fourth median, 12-dimensional target visible satellite signal-to-noise ratio features are generated.
And step 405, inputting the signal-to-noise ratio characteristics of the target visible satellite into a preset classification model to obtain a type tag output by the classification model.
Specifically, the manner of inputting the signal-to-noise ratio characteristic of the target visible satellite into the preset classification model to obtain the type label output by the classification model may refer to the related description in the above embodiment, which is not described herein again.
Therefore, according to the indoor and outdoor scene recognition method provided by the embodiment of the invention, N adjacent visible satellite signal-to-noise ratio features before the current updating period are acquired, and then the current visible satellite signal-to-noise ratio features are corrected according to the N visible satellite signal-to-noise ratio features so as to generate the target visible satellite signal-to-noise ratio features with more dimensions. Because the update period corresponding to the N groups of visible satellite signal-to-noise ratio features is continuous in time with the current update period, the corrected target visible satellite signal-to-noise ratio features are smoother in the time dimension, so that accidental errors and result jumps possibly occurring in the operation process of recognizing indoor and outdoor scenes are fewer, and the accuracy and reliability of recognizing indoor and outdoor scenes are further improved.
Based on the above embodiment, after the current indoor and outdoor scenes are determined by the indoor and outdoor scene recognition method provided by the embodiment of the invention, each function provided by the electronic equipment can be improved and adjusted according to the current scene recognition result, so that each function provided by the electronic equipment is more in line with the current scene, and the satisfaction degree of users is improved. The following describes an example of applying the indoor and outdoor scene recognition method according to the embodiment of the present invention to a wearable device.
In one embodiment of the invention, before the wearable device acquires the visible satellite message statement in the current update period, the application scene of the current wearable device is determined, namely, the function executed by the wearable device in the current scene is determined.
For example, when the user is in motion, the wearable device performs motion recognition detection functions, such as the wearable device recognizing that the user is running and recording the number of steps and mileage the user is running; when a user needs to listen to music, the wearable device executes a music playing function, and the current application scene of the wearable device is determined to be multimedia playing; when the wearable device is sending reminding information such as an incoming call reminder, a short message reminder, a sedentary reminder and the like to the user, determining that the application scene of the wearable device is a reminding scene and the like.
Then, after the current indoor and outdoor scenes are determined in the manner in the embodiment, the corresponding functions provided by the wearable device in the current application scene are improved and optimized according to the indoor and outdoor scene recognition result.
With continued reference to the above example, when the user is exercising, after determining the current indoor and outdoor scenes, the current exercise statistics parameters are modified according to the current indoor and outdoor scenes.
Specifically, the correction of the current motion statistics includes refinement of motion categories and correction of motion index parameters. For example, after determining the current indoor and outdoor scenes, the original running exercise identification is subdivided into indoor running and outdoor running, the original swimming exercise identification is subdivided into indoor swimming pool swimming and open water swimming, and the original riding exercise identification is subdivided into indoor spinning and outdoor riding, so that the follow-up reevaluation of the detected exercise index parameters according to the exercise category is facilitated, the exercise category in the currently displayed exercise statistics parameters can be updated, and the satisfaction degree of the user is improved.
Further, the statistical motion indexes are corrected according to the refined motion categories. For example, after running is divided into indoor running or outdoor running according to the current indoor and outdoor scenes, the step length and the estimated distance of the user are corrected, the step length and the distance before the indoor and outdoor scenes are identified, and after correction, the new step length and the distance under the indoor running scenes are obtained, so that the optimization of the statistical motion index parameters is realized, and the accuracy of the statistical motion index parameters is improved.
When the current application scene of the wearable device is multimedia playing, after the current indoor and outdoor scenes are determined, the current playing volume is adjusted according to the current indoor and outdoor scenes.
Specifically, when the wearable device is playing music, if the current scene is identified to switch from indoor to outdoor, the volume is automatically increased to resist environmental noise sounds and the like, and if the current scene is identified to switch from outdoor to indoor, the volume is automatically reduced to protect hearing and save electric quantity and the like.
Of course, after the current indoor and outdoor scenes are determined according to the indoor and outdoor scene recognition method provided by the embodiment of the invention, other functions which can be integrated with the indoor and outdoor scene recognition results and are provided by the wearable device can be improved according to the current scene recognition results, for example, when the wearable device is applied to a reminding scene, the heart rate voice broadcasting frequency is automatically adjusted according to the indoor and outdoor scene recognition results, and the voice broadcasting frequency is improved in an outdoor environment, so that a user is more closely reminded of the change of physiological indexes, the risk of accidents is reduced, for example, the frequency of sedentary reminding is automatically adjusted according to the indoor and outdoor scene recognition results, the reminding frequency is improved in the indoor environment, the user is reminded of the active body, the health of the user is facilitated, and the like, and the method is not repeated.
Therefore, according to the indoor and outdoor scene recognition method provided by the embodiment of the invention, the motion statistics, multimedia playing and other functions of the electronic equipment are corrected according to the current recognition result of the indoor and outdoor scenes, and the optimization of the various functions such as scene analysis, multimedia playing and the like of motion recognition and detection can be realized on the basis of the original functions, so that the functions provided by the electronic equipment are enriched, and the satisfaction degree of users is improved.
In order to achieve the above embodiment, the present invention further provides an indoor and outdoor scene recognition device. Fig. 5 is a schematic structural diagram of an indoor and outdoor scene recognition device according to an embodiment of the present invention.
As shown in fig. 5, the indoor and outdoor scene recognition apparatus includes: the first acquisition module 100, the first determination module 200, the second acquisition module 300, and the second determination module 400.
The first obtaining module 100 is configured to obtain a visible satellite message sentence in a current update period.
The first determining module 200 is configured to parse the visible satellite message sentence to determine a current signal-to-noise ratio characteristic of the visible satellite.
The second obtaining module 300 is configured to input the current signal-to-noise ratio feature of the visible satellite into a preset classification model to obtain a type tag output by the classification model.
The second determining module 400 is configured to determine the current indoor and outdoor scene according to the type tag.
In one possible implementation manner of the embodiment of the present invention, the first determining module 200 is specifically configured to parse the visible satellite message statement to obtain the number of visible satellites included in the message statement and the signal-to-noise ratio of each visible satellite; and determining the current signal-to-noise ratio characteristics of the visible satellites according to the number of the visible satellites and the signal-to-noise ratio of each visible satellite.
In one possible implementation manner of the embodiment of the present invention, when the user is moving, after determining the current indoor and outdoor scenes, the second determining module 400 is further configured to modify the current motion statistics parameter according to the current indoor and outdoor scenes, in one possible implementation manner of the embodiment of the present invention, if the current application scene is multimedia playing, after determining the current indoor and outdoor scenes, the second determining module 400 is further configured to adjust the current playing volume according to the current indoor and outdoor scenes.
In one embodiment of the present invention, on the basis of fig. 5, the indoor and outdoor scene recognition device as shown in fig. 6, the first determining module 200 further includes: a first determination unit 210, a first calculation unit 220, a second calculation unit 230, and a second determination unit 240. The second acquisition module 300 further includes: a first acquisition unit 310, an analysis unit 320, a third determination unit 330, a correction unit 340, and a second acquisition unit 350.
The first determining unit 210 is configured to determine, according to signal-to-noise ratios of the visible satellites, a current number of available visible satellites; a first calculating unit 220, configured to calculate, if the number of the current effective satellites is greater than the first threshold, a mean, variance and median of the signal-to-noise ratios of the current effective satellites according to the signal-to-noise ratios of the effective satellites; the second calculating unit 230 is configured to determine that the signal-to-noise ratio mean, variance, and median of the current effective visible satellites are all preset values if the number of the current effective visible satellites is less than or equal to the first threshold; the second determining unit 240 is configured to determine the signal-to-noise ratio characteristic of the current visible satellite according to the mean, variance and median of the signal-to-noise ratio of the current effective visible satellite.
Further, the second determining unit 240 is further configured to determine a current invalid visible satellite duty ratio according to the current number of visible satellites and the valid number of visible satellites; and determining the signal-to-noise ratio characteristics of the current visible satellite according to the signal-to-noise ratio mean value, variance, median and invalid visible Wei Xingzhan ratio of the current valid visible satellite.
With continued reference to the apparatus shown in fig. 6, a first obtaining unit 310 is configured to obtain N groups of visible satellite message sentences corresponding to the first N update periods adjacent to the current update period, where N is a positive integer greater than 1; the parsing unit 320 is configured to parse N groups of visible satellite message sentences to obtain the number of visible satellites corresponding to each group of visible satellite message sentences and the signal-to-noise ratio of each visible satellite; a third determining unit 330, configured to determine signal-to-noise characteristics of the N groups of visible satellites according to the number of the N groups of visible satellites and signal-to-noise ratios of each visible satellite; the correcting unit 340 is configured to correct the current signal-to-noise ratio feature of the visible satellite according to the N groups of signal-to-noise ratio features of the visible satellite, so as to generate a target signal-to-noise ratio feature of the visible satellite; and a second obtaining 350, configured to input the signal-to-noise ratio characteristic of the target visible satellite into a preset classification model, so as to obtain a type tag output by the classification model.
In one embodiment of the invention, the visible satellite signal-to-noise ratio features include: the correction unit 340 is specifically configured to: calculating a first mean value, a first variance and a first median corresponding to the N+1 groups of effective visible satellite signal-to-noise ratio mean values; calculating a second mean value, a second variance and a second median corresponding to the N+1 groups of effective visible satellite signal-to-noise ratio variances; calculating a third mean value, a third variance and a third median corresponding to the N+1 group of effective visible satellite signal-to-noise ratios median; calculating a fourth mean, a fourth variance and a fourth median corresponding to the N+1 group of invalid visible Wei Xingzhan ratios; and determining the signal-to-noise ratio characteristics of the target visible satellite according to the first mean, the first variance, the first median, the second mean, the second variance, the second median, the third mean, the third variance, the third median, the fourth mean, the fourth variance and the fourth median.
It should be noted that, the foregoing explanation of the embodiment of the indoor and outdoor scene recognition method is also applicable to the indoor and outdoor scene recognition device of this embodiment, and the implementation principle and process of each module may refer to the foregoing method embodiment, so that the description is omitted herein.
In summary, the indoor and outdoor scene recognition device according to the embodiment of the present invention obtains the visible satellite message statement in the current update period, then parses the visible satellite message statement to determine the current signal-to-noise ratio characteristic of the visible satellite, further inputs the current signal-to-noise ratio characteristic of the visible satellite into the preset classification model to obtain the type tag output by the classification model, and finally determines the current indoor and outdoor scene according to the type tag. The device judges that the indoor or outdoor scene is present by classifying the characteristics of the signal-to-noise ratio difference of the visible satellite in the indoor or outdoor scene, has simple recognition mode, less calculation amount, higher accuracy and reliability, and has wider application range because the visible satellite message statement is less influenced by factors such as environment, position, wearing mode and the like.
In order to achieve the above embodiments, the embodiments of the present invention further provide a wearing device. As shown in fig. 7, the wearing apparatus 1000 includes: a processor 2000, a memory 3000 communicatively coupled to the processor 2000; the memory stores instructions executable by the processor 2000, and when the instructions are called and executed by the processor 2000, the indoor and outdoor scene recognition method according to any of the above embodiments can be implemented.
In order to implement the above embodiments, the embodiments of the present invention also propose a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions, when executed, implement the indoor and outdoor scene recognition method of any one of the above embodiments.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims (14)

1. An indoor and outdoor scene recognition method is characterized by comprising the following steps:
obtaining visible satellite message sentences in the current updating period;
analyzing the visible satellite message statement to determine the current visible satellite signal-to-noise ratio characteristic;
acquiring N groups of visible satellite signal-to-noise ratio characteristics corresponding to the first N updating periods adjacent to the current updating period, wherein the N groups of visible satellite signal-to-noise ratio characteristics are obtained by analyzing N groups of visible satellite message sentences, and N is a positive integer greater than 1;
correcting the current visible satellite signal-to-noise ratio characteristics according to the N groups of visible satellite signal-to-noise ratio characteristics to generate target visible satellite signal-to-noise ratio characteristics;
inputting the signal-to-noise ratio characteristics of the target visible satellite into a preset classification model to obtain a type label output by the classification model;
determining the current indoor and outdoor scenes according to the type tag; wherein,
Correcting the current visible satellite signal-to-noise ratio characteristic according to the N groups of visible satellite signal-to-noise ratio characteristics to generate a target visible satellite signal-to-noise ratio characteristic, including:
and calculating the signal-to-noise ratio characteristics of the visible satellites again for the N groups of the signal-to-noise ratio characteristics of the visible satellites and the current signal-to-noise ratio characteristics of the visible satellites to obtain the signal-to-noise ratio characteristics of the visible satellites with more dimensions, and taking the signal-to-noise ratio characteristics of the visible satellites with more dimensions as the signal-to-noise ratio characteristics of the target visible satellites.
2. The method of claim 1, wherein parsing the visible satellite message statement to determine a current visible satellite signal-to-noise ratio characteristic comprises:
analyzing the visible satellite message statement to obtain the number of visible satellites contained in the message statement and the signal-to-noise ratio of each visible satellite;
and determining the current signal-to-noise ratio characteristics of the visible satellites according to the number of the visible satellites and the signal-to-noise ratio of each visible satellite.
3. The method of claim 2, wherein determining the current visible satellite signal-to-noise ratio characteristic based on the current number of visible satellites and the signal-to-noise ratio of each visible satellite comprises:
Determining the number of the current effective visible satellites according to the signal-to-noise ratio of each visible satellite;
if the number of the current effective visible satellites is larger than a first threshold, calculating the mean value, variance and median of the signal-to-noise ratios of the current effective visible satellites according to the signal-to-noise ratios of the effective visible satellites;
and determining the signal-to-noise ratio characteristics of the current effective visible satellite according to the signal-to-noise ratio mean value, variance and median of the current effective visible satellite.
4. The method of claim 3, further comprising, prior to said determining said current visible satellite signal-to-noise ratio signature from said current effective visible satellite signal-to-noise ratio mean, variance, and median:
and if the number of the current effective visible satellites is smaller than or equal to a first threshold value, determining that the signal-to-noise ratio mean value, variance and median of the current effective visible satellites are all preset values.
5. The method of claim 3, wherein said determining the current visible satellite signal-to-noise ratio signature based on the signal-to-noise ratio mean, variance, and median of the current effective visible satellite comprises:
determining the current invalid visible satellite duty ratio according to the current visible satellite number and the valid visible satellite number;
And determining the signal-to-noise ratio characteristics of the current visible satellite according to the signal-to-noise ratio mean value, variance, median and invalid visible Wei Xingzhan ratio of the current valid visible satellite.
6. The method of claim 1, wherein the visible satellite signal-to-noise ratio feature comprises: the effective visible satellite signal-to-noise ratio average value, effective visible satellite signal-to-noise ratio variance, effective visible satellite signal-to-noise ratio median and ineffective visible Wei Xingzhan ratio, the correcting the current visible satellite signal-to-noise ratio characteristic according to the N groups of visible satellite signal-to-noise ratio characteristics to generate a target visible satellite signal-to-noise ratio characteristic comprises:
calculating a first mean value, a first variance and a first median corresponding to the N+1 groups of effective visible satellite signal-to-noise ratio mean values;
calculating a second mean value, a second variance and a second median corresponding to the effective visible satellite signal-to-noise ratio variance of the N+1 group;
calculating a third mean value, a third variance and a third median corresponding to the median of the effective visible satellite signal-to-noise ratio of the N+1 group;
calculating a fourth mean, a fourth variance and a fourth median corresponding to the n+1 groups of invalid visible Wei Xingzhan ratios;
and determining the signal-to-noise ratio characteristics of the target visible satellite according to the first mean, the first variance, the first median, the second mean, the second variance, the second median, the third mean, the third variance, the third median, the fourth mean, the fourth variance and the fourth median.
7. An indoor and outdoor scene recognition device, comprising:
the first acquisition module is used for acquiring visible satellite message sentences in the current updating period;
the first determining module is used for analyzing the visible satellite message statement to determine the current visible satellite signal-to-noise ratio characteristic;
the second acquisition module is used for acquiring N groups of visible satellite signal-to-noise ratio characteristics corresponding to the previous N update periods adjacent to the current update period, wherein the N groups of visible satellite signal-to-noise ratio characteristics are obtained by analyzing N groups of visible satellite message sentences, and N is a positive integer greater than 1;
correcting the current visible satellite signal-to-noise ratio characteristics according to the N groups of visible satellite signal-to-noise ratio characteristics to generate target visible satellite signal-to-noise ratio characteristics;
inputting the signal-to-noise ratio characteristics of the target visible satellite into a preset classification model to obtain a type label output by the classification model;
the second determining module is used for determining the current indoor and outdoor scenes according to the type tag; wherein,
the second obtaining module corrects the current visible satellite signal-to-noise ratio characteristic according to the N groups of visible satellite signal-to-noise ratio characteristics to generate a target visible satellite signal-to-noise ratio characteristic, including:
And calculating the signal-to-noise ratio characteristics of the visible satellites again for the N groups of the signal-to-noise ratio characteristics of the visible satellites and the current signal-to-noise ratio characteristics of the visible satellites to obtain the signal-to-noise ratio characteristics of the visible satellites with more dimensions, and taking the signal-to-noise ratio characteristics of the visible satellites with more dimensions as the signal-to-noise ratio characteristics of the target visible satellites.
8. The apparatus of claim 7, wherein the first determining module is specifically configured to:
analyzing the visible satellite message statement to obtain the number of visible satellites contained in the message statement and the signal-to-noise ratio of each visible satellite;
and determining the current signal-to-noise ratio characteristics of the visible satellites according to the number of the visible satellites and the signal-to-noise ratio of each visible satellite.
9. The apparatus of claim 8, wherein the first determining module comprises:
the first determining unit is used for determining the number of the current effective visible satellites according to the signal-to-noise ratio of each visible satellite;
the first calculating unit is used for calculating the mean value, variance and median of the signal-to-noise ratios of the current effective visible satellites according to the signal-to-noise ratio of each effective visible satellite if the number of the current effective visible satellites is larger than a first threshold;
And the second determining unit is used for determining the signal-to-noise ratio characteristics of the current effective visible satellite according to the signal-to-noise ratio mean value, the variance and the median of the current effective visible satellite.
10. The apparatus of claim 9, wherein the first determining module further comprises:
and the second calculation unit is used for determining that the signal-to-noise ratio mean value, the variance and the median of the current effective visible satellites are all preset values if the number of the current effective visible satellites is smaller than or equal to a first threshold value.
11. The apparatus of claim 9, wherein the second determining unit is further configured to:
determining the current invalid visible satellite duty ratio according to the current visible satellite number and the valid visible satellite number;
and determining the signal-to-noise ratio characteristics of the current visible satellite according to the signal-to-noise ratio mean value, variance, median and invalid visible Wei Xingzhan ratio of the current valid visible satellite.
12. The indoor and outdoor scene recognition device of claim 7, wherein the visible satellite signal-to-noise ratio feature comprises: the effective visible satellite signal-to-noise ratio average value, effective visible satellite signal-to-noise ratio variance, effective visible satellite signal-to-noise ratio median and ineffective visible Wei Xingzhan ratio, the correcting the current visible satellite signal-to-noise ratio characteristic according to the N groups of visible satellite signal-to-noise ratio characteristics to generate a target visible satellite signal-to-noise ratio characteristic comprises:
Calculating a first mean value, a first variance and a first median corresponding to the N+1 groups of effective visible satellite signal-to-noise ratio mean values;
calculating a second mean value, a second variance and a second median corresponding to the effective visible satellite signal-to-noise ratio variance of the N+1 group;
calculating a third mean value, a third variance and a third median corresponding to the median of the effective visible satellite signal-to-noise ratio of the N+1 group;
calculating a fourth mean, a fourth variance and a fourth median corresponding to the n+1 groups of invalid visible Wei Xingzhan ratios;
and determining the signal-to-noise ratio characteristics of the target visible satellite according to the first mean, the first variance, the first median, the second mean, the second variance, the second median, the third mean, the third variance, the third median, the fourth mean, the fourth variance and the fourth median.
13. An electronic device, comprising:
a processor; and
a memory communicatively coupled to the processor; wherein,
the memory stores instructions executable by the processor, which when invoked and executed by the processor, implement the indoor and outdoor scene recognition method of any one of claims 1-6.
14. A non-transitory computer readable storage medium storing computer instructions which, when executed, implement the indoor and outdoor scene recognition method of any one of claims 1-6.
CN202011205236.0A 2020-11-02 2020-11-02 Indoor and outdoor scene recognition method and device, electronic equipment and storage medium Active CN112381126B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011205236.0A CN112381126B (en) 2020-11-02 2020-11-02 Indoor and outdoor scene recognition method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011205236.0A CN112381126B (en) 2020-11-02 2020-11-02 Indoor and outdoor scene recognition method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112381126A CN112381126A (en) 2021-02-19
CN112381126B true CN112381126B (en) 2023-11-17

Family

ID=74576120

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011205236.0A Active CN112381126B (en) 2020-11-02 2020-11-02 Indoor and outdoor scene recognition method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112381126B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113905438B (en) * 2021-12-10 2022-03-22 腾讯科技（深圳）有限公司 Scene identification generation method, positioning method and device and electronic equipment
CN114831356B (en) * 2022-07-05 2022-11-01 深圳市恒尔创科技有限公司 Electronic cigarette control method based on mobile terminal and related equipment
CN115859158B (en) * 2023-02-16 2023-07-07 荣耀终端有限公司 Scene recognition method, system and terminal equipment
CN117436086A (en) * 2023-10-26 2024-01-23 华中科技大学 Knowledge graph-based software supply chain security analysis method and system

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8694248B1 (en) * 2011-02-08 2014-04-08 Brunswick Corporation Systems and methods of monitoring the accuracy of a global positioning system receiver in a marine vessel
CN105096319A (en) * 2015-09-10 2015-11-25 北京空间机电研究所 Staring-imaging-based in-orbit signal-to-noise ratio test method of satellite
CN105611043A (en) * 2015-10-30 2016-05-25 东莞酷派软件技术有限公司 Screen brightness adjusting method and device and terminal
CN106248107A (en) * 2016-09-22 2016-12-21 中国电子科技集团公司第二十二研究所 A kind of flight path based on indoor earth magnetism path matching infers calibration steps and device
CN106851584A (en) * 2015-12-07 2017-06-13 高德信息技术有限公司 Recognize the method and device of mobile device local environment
CN108931802A (en) * 2018-07-23 2018-12-04 中国科学院计算技术研究所 A kind of indoor and outdoor scene detection method
CN109239749A (en) * 2018-08-22 2019-01-18 深圳普创天信科技发展有限公司 Localization method, terminal and computer readable storage medium
CN109891934A (en) * 2017-08-23 2019-06-14 华为技术有限公司 A kind of localization method and device
CN110927757A (en) * 2019-12-26 2020-03-27 广东星舆科技有限公司 Quality control method and device for satellite observation data and positioning device
CN111045052A (en) * 2019-10-14 2020-04-21 广东星舆科技有限公司 Pseudo-range differential positioning and quality control method for intelligent terminal

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8694248B1 (en) * 2011-02-08 2014-04-08 Brunswick Corporation Systems and methods of monitoring the accuracy of a global positioning system receiver in a marine vessel
CN105096319A (en) * 2015-09-10 2015-11-25 北京空间机电研究所 Staring-imaging-based in-orbit signal-to-noise ratio test method of satellite
CN105611043A (en) * 2015-10-30 2016-05-25 东莞酷派软件技术有限公司 Screen brightness adjusting method and device and terminal
CN106851584A (en) * 2015-12-07 2017-06-13 高德信息技术有限公司 Recognize the method and device of mobile device local environment
CN106248107A (en) * 2016-09-22 2016-12-21 中国电子科技集团公司第二十二研究所 A kind of flight path based on indoor earth magnetism path matching infers calibration steps and device
CN109891934A (en) * 2017-08-23 2019-06-14 华为技术有限公司 A kind of localization method and device
CN108931802A (en) * 2018-07-23 2018-12-04 中国科学院计算技术研究所 A kind of indoor and outdoor scene detection method
CN109239749A (en) * 2018-08-22 2019-01-18 深圳普创天信科技发展有限公司 Localization method, terminal and computer readable storage medium
CN111045052A (en) * 2019-10-14 2020-04-21 广东星舆科技有限公司 Pseudo-range differential positioning and quality control method for intelligent terminal
CN110927757A (en) * 2019-12-26 2020-03-27 广东星舆科技有限公司 Quality control method and device for satellite observation data and positioning device

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Wide Area Remote Sensing Image On Orbit Target Extraction and Identification Method;Zongling Li等;《2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP)》;20200821;第1-8页 *
周波等.基于 ADS-B 的新型跟踪监视算法.基于 ADS-B 的新型跟踪监视算法.2014,第21卷(第7期),第41-45、55页. *
基于位置和功率协同优化的煤矿工作面可见光通信光源分布;游春霞等;《中国激光》;20190430;第46卷(第4期);第1-8页 *
陈恺等.基于JAVA的空管自动化主备同步监测系统设计.《工业控制计算机》.2020,第33卷(第4期),第4-7页. *

Also Published As

Publication number Publication date
CN112381126A (en) 2021-02-19

Similar Documents

Publication Publication Date Title
CN112381126B (en) Indoor and outdoor scene recognition method and device, electronic equipment and storage medium
CN107240398B (en) Intelligent voice interaction method and device
CN107635204B (en) Indoor fusion positioning method and device assisted by exercise behaviors and storage medium
US10043084B2 (en) Hierarchical context-aware extremity detection
CN102985897B (en) Efficient gesture processes
US10676097B1 (en) Driver identification among a limited pool of potential drivers
US10254123B2 (en) Navigation system with vision augmentation mechanism and method of operation thereof
US20230076568A1 (en) Mobile Device And System For Automated Transport Mode Recognition And Corresponding Method Thereof
CN115641443A (en) Method for training image segmentation network model, method for processing image and product
CN112684430A (en) Indoor old person walking health detection method and system, storage medium and terminal
CN111743740A (en) Blind guiding method and device, blind guiding equipment and storage medium
KR100682953B1 (en) Apparatus and method for detecting person
CN108286973A (en) A kind of running data method of calibration and device and hybrid navigation system
CN114299546A (en) Method and device for identifying pet identity, storage medium and electronic equipment
CN112001453B (en) Method and device for calculating accuracy of video event detection algorithm
EP3382570A1 (en) Method for characterizing driving events of a vehicle based on an accelerometer sensor
CN114280583B (en) Laser radar positioning accuracy verification method and system without GPS signal
CN111081102A (en) Dictation result detection method and learning equipment
CN114580979A (en) High-temperature disaster prevention index detection method, device, equipment, storage medium and product
JP2020034451A (en) Data structure, storage medium, and storage device
CN114972950A (en) Multi-target detection method, device, equipment, medium and product
CN110934565B (en) Method and device for measuring pupil diameter and computer readable storage medium
CN114464216A (en) Acoustic detection method and device under unmanned driving environment
CN112583860A (en) Method, device and equipment for detecting abnormal internet traffic
CN113415292A (en) Driving takeover capability evaluation method and electronic device

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
CB02 Change of applicant information

Address after: 230051 No. 01, 5th floor, building B2, Zhongan chuanggu Science Park, No. 900, Wangjiang West Road, high tech Zone, Hefei City, Anhui Province

Applicant after: Anhui huami Health Technology Co.,Ltd.

Address before: Room 189, building H2, phase II, innovation industrial park, 2800 innovation Avenue, high tech Zone, Hefei City, Anhui Province

Applicant before: ANHUI HUAMI INTELLIGENT TECHNOLOGY CO.,LTD.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant