CN116095610A

CN116095610A - Method, device, server and computer readable storage medium for identifying track

Info

Publication number: CN116095610A
Application number: CN202310373168.6A
Authority: CN
Inventors: 李宁宁; 魏婵娟; 关鹏飞; 张晚辰; 杨伟
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-04-10
Filing date: 2023-04-10
Publication date: 2023-05-09
Anticipated expiration: 2043-04-10
Also published as: CN116095610B

Abstract

The application is applicable to the technical field of computers, and provides a method, a device, a server and a computer readable storage medium for identifying tracks. In the method for identifying the tracks, a server acquires the tracks to be classified; matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree; if the first matching degree is smaller than a first threshold value, continuously matching the track to be classified with an indoor fingerprint library of an indoor area to obtain a second matching degree; if the second matching degree is larger than a second threshold value, determining that the track to be classified is an indoor track; the method and the device can identify the place where the track belongs more accurately, and provide more reliable data basis for subsequent position location.

Description

Method, device, server and computer readable storage medium for identifying track

Technical Field

The present application belongs to the field of computer technology, and in particular, relates to a method, an apparatus, a server, and a computer readable storage medium for identifying a track.

Background

With the rapid development of science and technology, people use location information more and more frequently. The common positioning system mainly depends on satellites or the Internet of things to realize positioning; however, for indoor positioning, the signal is weakened because the indoor environment is easy to be shielded, so that the indoor positioning information may have larger deviation and the positioning accuracy is low.

Disclosure of Invention

The application provides a track identification method, a track identification device, a server and a computer readable storage medium, which can identify an indoor track and provide a reliable data basis for subsequent more accurate indoor positioning so as to improve indoor positioning accuracy.

A first aspect of the present application provides a method of identifying a trajectory, comprising: the server acquires the tracks to be classified; matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree; if the first matching degree is smaller than a first threshold value, continuously matching the track to be classified with an indoor fingerprint library of an indoor area to obtain a second matching degree; and if the second matching degree is greater than a second threshold value, determining the track to be classified as an indoor track.

According to the method, the server performs rough identification of the outdoor fingerprint guard band on the track to be classified to obtain the first matching degree, when the first matching degree of the track to be classified with the outdoor fingerprint guard band is judged to be smaller than a first threshold value, the track to be classified is possibly the track except the outdoor fingerprint guard band or the track indoors, the track to be classified (other tracks to be classified except the outdoor fingerprint guard band) is further matched with the track indoors, fine identification is performed again to obtain the second matching degree, whether the track to be classified is the track indoors is judged based on the second matching degree, and when the second matching degree is larger than the second threshold value, the track to be classified is determined to be the track indoors; therefore, the track to be classified can be more accurately identified, and further, based on the identified indoor track, a more accurate and rich indoor fingerprint library can be obtained, so that more reliable indoor data support is further provided for subsequent more accurate indoor positioning.

In a possible implementation manner of the first aspect, before acquiring the track to be classified, the method further includes:

collecting outdoor track data and indoor track data corresponding to each place respectively; according to the outdoor track data, constructing an outdoor fingerprint library of the outdoor fingerprint protection belt corresponding to each place; and constructing an indoor fingerprint library of the indoor area corresponding to each place according to the indoor track data.

In a possible implementation manner of the first aspect, collecting outdoor track data and indoor track data corresponding to each location respectively includes:

acquiring outdoor track data based on outdoor positions in outdoor distance ranges preset in all places; and acquiring indoor track data based on indoor positions preset in each place.

For example, before matching the track to be classified with the outdoor fingerprint database of the outdoor fingerprint guard band and the indoor fingerprint database of the indoor area, outdoor track data and indoor track data at positions of designated areas of different places can be acquired respectively, so that an outdoor fingerprint database and an indoor fingerprint database which can be used for matching are constructed first; the outdoor fingerprint library and the indoor fingerprint library are databases represented by track feature vectors respectively.

Through the mode, before matching, the server can acquire the outdoor track data and the indoor track data with higher confidence coefficient through the equipment, and the outdoor fingerprint library and the indoor fingerprint library corresponding to different places are formed, so that more accurate identification can be realized when tracks to be classified are matched, and the identification result is more accurate and reliable.

In a possible implementation manner of the first aspect, the outdoor track data includes first wireless signal data and first location information at each outdoor location; according to the outdoor track data, constructing an outdoor fingerprint library of an outdoor fingerprint protection belt corresponding to each place, comprising:

and constructing an outdoor fingerprint library according to the first wireless signal data and the first position information at the outdoor position.

In a possible implementation manner of the first aspect, the indoor track data includes second wireless signal data and second location information at each indoor location; according to the indoor track data, constructing an indoor fingerprint library of an indoor area corresponding to each place, comprising:

and constructing an indoor fingerprint library according to the second wireless signal data and the second position information at the indoor position.

The outdoor fingerprint library and the indoor fingerprint library are respectively obtained based on feature vectors corresponding to tracks formed by wireless signal data at various positions when track data are acquired and combined with position information.

and constructing a place fingerprint library corresponding to the place according to the outdoor track data or the indoor track data and the name of the place.

In a possible implementation manner of the first aspect, the outdoor track data includes first location information of an outdoor location, and the indoor track data includes second location information of an indoor location; constructing a place fingerprint library corresponding to the place according to the outdoor track data or the indoor track data, comprising:

determining location position information of each location according to first location information of an outdoor location or second location information of an indoor location; and constructing a place fingerprint library according to the place position information and the name of the place.

For example, the first location information may include longitude and latitude information of an outdoor track collected, the second location information may include longitude and latitude information of an indoor track collected, and the location information may include longitude and latitude information of a location where the location is located; based on the latitude and longitude information of the outdoor position and the latitude and longitude information of the indoor position, the latitude and longitude information of the places can be calculated, so that a place fingerprint library is obtained based on databases corresponding to all places generated by the latitude and longitude information of each place and the name of the place.

In a possible implementation manner of the first aspect, before matching the track to be classified with the outdoor fingerprint library of the outdoor fingerprint guard band to obtain the first matching degree, the method further includes:

matching the track to be classified with a place fingerprint library corresponding to each place, and determining a target place to which the track to be classified belongs; the target location is one of the locations.

By the method, the server can recognize the tracks to be classified according to various places in any area, so that the breadth and applicability of the track recognition to be classified are improved, and the method is not limited to the indoor or outdoor recognition of a single place; and matching is carried out on the basis of the to-be-classified fingerprint database and the place fingerprint database, so that the accuracy of track identification is improved.

In a possible implementation manner of the first aspect, matching the track to be classified with a location fingerprint database corresponding to each location, and determining a target location to which the track to be classified belongs includes:

and matching the track data of the tracks to be classified with the location information of the fingerprint database of each location, and determining the name of the target location.

The location fingerprint library includes location information, and track data of the track to be classified is matched with the location information in the location fingerprint library to determine a target location to which the track to be classified belongs. The location information may include latitude and longitude information of the location or wireless device information, signal strength information, etc. associated with the location, for example, if satellite signal data in track data of a track to be classified is within or near a preset distance range (such as a range of an outdoor fingerprint guard band) of the latitude and longitude information of the target location, or if the signal strength data and the wireless device information in the track data are matched with the location information in a location fingerprint library of the target location, the track to be classified may be primarily identified as belonging to the target location.

In a possible implementation manner of the first aspect, after matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree, the method further includes:

and if the first matching degree is greater than or equal to a first threshold value, the track to be classified is an outdoor track.

The first threshold is a threshold of similarity between the track to be classified and the outdoor fingerprint database, and when the similarity between the track to be classified and the outdoor fingerprint database, i.e. the first matching degree, is greater than the first threshold, the track to be classified is identified as the outdoor track.

In a possible implementation manner of the first aspect, after matching the track to be classified with the indoor fingerprint library of the indoor area to obtain the second matching degree, the method further includes:

and if the second matching degree is smaller than or equal to a second threshold value, the track to be classified is an outdoor track.

The second threshold is a threshold of similarity between the track to be classified and the indoor track; when the similarity (i.e., the second matching degree) between the track to be classified and the indoor track is smaller than or equal to the second threshold, the track to be classified does not belong to the indoor track, and is determined to be an outdoor track.

In a possible implementation manner of the first aspect, matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree includes:

And calculating the first similarity between the track feature vector corresponding to the track to be classified and the track feature vector in the outdoor fingerprint library, and taking the maximum value of the first similarity as the first matching degree.

The outdoor fingerprint library may include information of a plurality of tracks, in which in the matching process, the track to be classified is matched with each track in the outdoor fingerprint library, the similarity with each track is calculated, and the track with the largest similarity in all tracks is used as the track which is matched with the track to be classified, i.e. the maximum value in the first similarity is used as the first matching degree.

Correspondingly, if the first matching degree of the track to be classified and the track which is the most similar does not reach the first threshold value, the track to be classified does not belong to the track of the outdoor fingerprint protection band (may be an outdoor track or an indoor track which is far away from a building); if the first matching degree reaches a first threshold value, the track to be classified is an outdoor track belonging to the outdoor fingerprint guard band.

In a possible implementation manner of the first aspect, matching the track to be classified with an indoor fingerprint library of the indoor area to obtain a second matching degree includes:

and calculating the similarity between the track feature vector corresponding to the track to be classified and the track feature vector in the indoor fingerprint library, wherein the maximum value of the similarity is used as the second matching degree.

The indoor fingerprint library may include information of a plurality of tracks, in which in the matching process, the track to be classified is matched with each track in the indoor fingerprint library, the similarity with each track is calculated, and the track with the largest similarity in all tracks is used as the track which is matched with the track to be classified, i.e. the maximum value in the second similarity is used as the second matching degree.

Correspondingly, if the second matching degree of the track to be classified and the track which is the most similar does not reach the second threshold value, the track to be classified does not belong to the track of the indoor area, and is an outdoor track except an outdoor fingerprint protection belt; and if the second matching degree reaches a second threshold value, determining that the track to be classified belongs to the indoor track of the indoor area.

By the method, after outdoor rough identification is carried out on the track to be classified, if the track to be classified does not belong to an outdoor track, the track to be classified may be in an outdoor area except an outdoor fingerprint guard band or belongs to an indoor area; carrying out indoor precise identification on the track waiting for classification again, if the similarity is not higher than a second threshold value, determining that the track waiting for classification does not belong to an indoor track and is an outdoor track; thereby improving the accuracy of identifying the track to be classified; through double identification, the indoor and outdoor tracks in each place are accurately identified; the track is accurately identified based on smaller data volume, the calculation magnitude of a subsequent positioning algorithm is reduced, meanwhile, an indoor fingerprint library with higher accuracy is ensured, and reliable data support is provided for subsequent indoor positioning.

In a possible implementation manner of the first aspect, the method further includes:

and after the track to be classified is identified as the indoor track, adding the track to be classified identified as the indoor track into the indoor fingerprint library to form a new indoor fingerprint library.

The to-be-classified track further accurately identified as the indoor track is added into the indoor fingerprint library to form a new indoor fingerprint library. If the server identifies the track to be classified as an outdoor track of the outdoor fingerprint guard band, track data of the outdoor track can be added into the outdoor fingerprint database to continuously perfect the outdoor fingerprint database, so that identification accuracy is improved.

By the method, track data of the identified indoor track is added into the indoor fingerprint library, the indoor fingerprint library is continuously perfected, and the outdoor track of the outdoor fingerprint guard band is added into the outdoor fingerprint library, so that the outdoor fingerprint library is continuously perfected; by continuously updating and perfecting the fingerprint database, the track recognition precision is improved, and a more accurate and reliable data base is provided for subsequent indoor positioning.

A second aspect of the present application provides an apparatus for identifying a trajectory, comprising:

the acquisition unit is used for acquiring the tracks to be classified;

The first identification unit is used for matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint protection belt to obtain a first matching degree;

the second recognition unit is used for matching the track to be classified with the indoor fingerprint library of the indoor area if the first matching degree is smaller than the first threshold value, so as to obtain a second matching degree;

and the output unit is used for judging whether the track to be classified is an indoor track if the second matching degree is larger than a second threshold value.

In another possible implementation manner of the second aspect, the apparatus further includes a data acquisition unit and a data processing unit; the data acquisition unit is used for acquiring outdoor track data and indoor track data corresponding to each place respectively; the data processing unit is used for constructing an outdoor fingerprint library of the outdoor fingerprint protection belt corresponding to each place according to the outdoor track data; and constructing an indoor fingerprint library of the indoor area corresponding to each place according to the indoor track data.

In another possible implementation manner of the second aspect, the data acquisition unit is further configured to acquire outdoor track data based on outdoor positions within an outdoor distance range preset in each location; and acquiring indoor track data based on indoor positions preset in each place.

In another possible implementation manner of the second aspect, the data processing unit is further configured to construct an outdoor fingerprint library according to the first wireless signal data and the first location information at the outdoor location.

In another possible implementation manner of the second aspect, the data processing unit is further configured to construct an indoor fingerprint library according to the second wireless signal data and the second location information at the indoor location.

In another possible implementation manner of the second aspect, the data processing unit is further configured to construct a location fingerprint library corresponding to the location according to the outdoor track data or the indoor track data, and a name of the location.

In another possible implementation manner of the second aspect, the data processing unit is further configured to determine location information of each location according to first location information of an outdoor location or second location information of an indoor location; and constructing a place fingerprint library according to the place position information and the name of the place.

In another possible implementation manner of the second aspect, the apparatus further includes a third identifying unit, configured to match the track to be classified with a location fingerprint library corresponding to each location, and determine a target location to which the track to be classified belongs; the target location is one of the locations.

In another possible implementation manner of the second aspect, the identifying unit is further configured to match track data of the track to be classified with location information of each location fingerprint library, and determine a name of the target location.

In another possible implementation manner of the second aspect, the output unit is further configured to, if the first matching degree is greater than or equal to the first threshold, determine that the track to be classified is an outdoor track.

In another possible implementation manner of the second aspect, the output unit is further configured to, if the second matching degree is less than or equal to the second threshold, determine that the track to be classified is an outdoor track.

In another possible implementation manner of the second aspect, the first identifying unit is further configured to calculate a first similarity between a track feature vector corresponding to the track to be classified and a track feature vector in the outdoor fingerprint library, and use a maximum value of the first similarity as the first matching degree.

In another possible implementation manner of the second aspect, the second identifying unit is further configured to calculate a second similarity between a track feature vector corresponding to the track to be classified and a track feature vector in the indoor fingerprint library, and use a maximum value of the second similarity as the second matching degree.

In another possible implementation manner of the second aspect, the output unit is further configured to add the trajectory to be classified identified as the indoor trajectory to the indoor fingerprint library after identifying the trajectory to be classified as the indoor trajectory, so as to form a new indoor fingerprint library; the indoor fingerprint library is used for providing data support when indoor positioning is performed.

A third aspect of the present application provides a server comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said server implementing the steps of the method as described above when said computer program is executed by said processor.

A fourth aspect of the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, causes a server to carry out the steps of a method as described above.

A fifth aspect of the present application provides a computer program product for causing a server to carry out the steps of the method as described above when the computer program product is run on the server.

A sixth aspect of the present application provides a chip comprising a processor, the processor being coupled to a memory for storing computer program instructions which, when executed by the processor, cause the chip to perform the steps of the method as described in the first aspect.

It will be appreciated that the advantages of the second to sixth aspects may be found in the relevant description of the first aspect, and are not described here again.

Drawings

Fig. 1 is a schematic system architecture diagram of a track recognition method according to an embodiment of the present application;

fig. 2 is an application scenario schematic diagram of a track recognition method provided in an embodiment of the present application;

FIG. 3 is a schematic flow chart of a track recognition method according to an embodiment of the present application;

FIG. 4 is a schematic illustration of a venue area provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of trace matching provided in an embodiment of the present application;

FIG. 6 is a schematic flow chart of a method for identifying a track according to an embodiment of the present application;

FIG. 7 is a schematic overall flow chart of a method for identifying trajectories according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a device for identifying a track according to an embodiment of the present disclosure;

fig. 9 is a schematic hardware structure of a server according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to illustrate the technical solutions described in the present application, the following description is made by specific examples.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Along with the rapid development of the technology of the internet of things and the configuration capability of hardware, people frequently utilize indoor position information in life, and the dependence on indoor position services is stronger, for example, the indoor position information is applied to factories, hospitals, markets and other places; acquiring accurate indoor location data is also a research hotspot. The biggest problems faced by indoor positioning technology are high cost, large power consumption and low positioning accuracy, especially in indoor environment with stronger signal shielding.

Currently, the most widely used location service technology is the global positioning system, which has high positioning accuracy in outdoor environments; however, in a complex indoor environment, the satellite signals are attenuated and even shielded due to the shielding of the building, so that the positioning difficulty is increased and accurate position information cannot be obtained. Therefore, in order to solve the problems of large indoor positioning deviation and low accuracy, the indoor fingerprint library can be obtained through the identification of indoor and outdoor scenes, so that accurate indoor positioning can be realized based on the indoor fingerprint library. However, in the related art, a large amount of sample data is generally required for identifying indoor and outdoor scenes, and then algorithm model training is performed; a large amount of sample data is not easy to obtain and is cumbersome and difficult to implement.

Based on the above problems, the embodiment of the application provides a track identification method, which can realize accurate identification of indoor and outdoor tracks under the condition of smaller data volume, and can synchronously perfect and update a required data set, so that the indoor tracks and the outdoor tracks are identified more accurately, and an accurate and reliable indoor fingerprint library is obtained.

The application scenario of the track identification method provided in the embodiment of the present application is specifically described below.

Referring to fig. 1, fig. 1 is a schematic system architecture diagram of a track recognition method according to an embodiment of the present application. As shown in fig. 1, the system architecture may include a server 10 and an electronic device 20 for use by a user. The electronic device 20 may support various positioning software to implement a positioning function for a user; the server 10 may serve as a background service providing support for data processing for the electronic device 20. For example, when the electronic device 20 starts the positioning software, after obtaining the authorization of the user, the server 10 may obtain current track data (such as satellite signal data or wireless signal data) collected by the electronic device 20 used by the user.

It should be noted that, in an indoor environment, the track data collected by the electronic device 20 may be data with a certain deviation, for example, satellite signal data obtained by a satellite positioning system, and an error of tens of meters or even hundreds of meters may exist indoors. Accordingly, the trajectory data collected by the electronic device 20 includes position information (position information having a certain deviation) preliminarily determined based on satellite signal data, or wireless signal data (which may include wireless signal strength and wireless device information) acquired in the environment of the current location.

In a possible implementation manner, the server 10 obtains track data of a current track of a user uploaded by the electronic device 20, identifies a location where the user is located based on the track data, determines that the track of the user is located in an indoor area of the location, feeds back a determination result to the electronic device 20, and the electronic device 20 further realizes accurate positioning in the indoor area based on the determination result, so that probability of positioning deviation caused by factors of complex indoor scenes is reduced.

Referring to fig. 2, fig. 2 is an application scenario schematic diagram of a track recognition method according to an embodiment of the present application. As shown in fig. 2, embodiments of the present application identify trajectories for indoor and outdoor areas of any venue (or building). According to the track identification method provided by the embodiment of the application, by arranging the outdoor fingerprint protection belt (outdoor transition area) shown in the figure 2, outdoor track data of the outdoor fingerprint protection belt and indoor track data of an indoor area are respectively acquired, and a place fingerprint library of the place, an indoor fingerprint library of the indoor area and an outdoor fingerprint library of the outdoor fingerprint protection belt are constructed; identifying a target place to which the track to be classified belongs based on a place fingerprint library, and identifying similarity based on an outdoor fingerprint library and an indoor fingerprint library, judging whether the current track to be classified of a user is an indoor track or an outdoor track, realizing accurate identification of the indoor track and the outdoor track, and reducing the calculation magnitude of a subsequent algorithm; after the indoor track is determined, the identified track information is added into an indoor fingerprint database, so that the indoor fingerprint database is continuously perfected; therefore, the fingerprint database corresponding to the target place can be quickly established, and meanwhile, higher recognition accuracy is ensured, and reliable and accurate data support is provided for the follow-up accurate indoor positioning.

The implementation of the track recognition method is further described by way of specific embodiments in conjunction with fig. 3, 4 and 5.

Referring to fig. 3, fig. 3 is a schematic flow chart of a track recognition method according to an embodiment of the present application. As shown in fig. 3, there may be track data of a plurality of tracks to be classified in an indoor area of a target site and an outdoor area in the vicinity; the indoor area at the target site may include one or more pieces of indoor trajectory data collected in advance with high confidence.

The tracks to be classified may be track data obtained from the electronic device 20 by the server 10, that is, when the electronic device 20 starts the positioning software or the map software, current track data is collected and uploaded to the server 10 after the user authorization.

For example, each track to be classified may be a track formed by a plurality of location points, that is, track data of a plurality of location points collected by the electronic device 20 along with movement of a user during a use process of the user; the trajectory data may include data related to the electronic device 20 at each location point or the entire trajectory, such as satellite signal data or wireless signal data for each location point or the entire trajectory, etc.

As shown in fig. 3, for the target location, the server is provided with data of an outdoor fingerprint guard band (outdoor transition area), which may also include acquired track data of an outdoor track with high confidence, i.e. outdoor track data; the outdoor fingerprint guard band may be disposed within a range of 100 meters around the periphery of the target location, and the size of the range may be specifically set according to the size or type of each location, which is not specifically limited herein.

In some embodiments, before the tracks to be classified are identified, acquisition may be performed first, that is, indoor track data of indoor areas of each place and outdoor track data of outdoor fingerprint guard bands are acquired.

For example, during the data acquisition process, as shown in the schematic diagram of the location shown in the (a) diagram of fig. 4, the outdoor fingerprint protection belt of the location may be moved in the a direction and the indoor area in the B direction by moving the data acquisition device at a constant speed to acquire track data of each location point, for example, moving and sampling at a moving speed of 1 m/s; the direction a, the direction B, the moving speed and the like are only schematically illustrated, and a specific moving collection mode is not limited, for example, a suitable moving direction and speed can be selected for data collection according to the layout characteristics of an indoor area of a place and the scene characteristics of an outdoor fingerprint protection belt, so as to initially construct an indoor fingerprint library and an outdoor fingerprint library.

In one possible implementation, the acquired trajectory data may include wireless signal data, sensor information, location information, and the like for each location point. The method comprises the steps that wireless signal data and sensor information of each position point of an indoor area and an outdoor fingerprint guard band can be collected through electronic equipment (such as a mobile phone); and acquiring the position information of each position point of the indoor area and the outdoor fingerprint guard band through an indoor positioning instrument.

By way of example, the wireless signal data may include wireless WiFi signal strength, wireless WiFi address, bluetooth signal strength, and bluetooth device address. Bluetooth devices or wireless access point devices may be disposed in the location, so that the electronic device 20 may obtain information such as wireless WiFi signal strength, wireless WiFi device address, bluetooth signal strength, and Bluetooth device address through searching or sensor detection of wireless signals. The location information collected by the indoor positioning instrument can be longitude and latitude information with high confidence coefficient of each location point.

For example, when data acquisition is performed, position information of a corresponding location, that is, longitude and latitude information of each location may be determined based on the acquired indoor track data or outdoor track data. As shown in (a), (b) and (c) of fig. 4, each location may have a different shape, and from the collected position information in the indoor track data or the collected position information in the outdoor track data, the position information at each vertex position of the location may be determined, so that the position information of the location may be determined based on the position information at each vertex position, that is, the latitude and longitude information at each vertex represents the latitude and longitude information of the location. For example, the indoor track data or the outdoor track data may include therein position information at the vertex of each location; or based on the division range of the outdoor fingerprint guard band and the outdoor track data, calculating to obtain the position information of each place. As further shown in fig. 4 (c), when the site does not have an absolute vertex position, the location information of the site may be determined based on the circumscribed rectangle of the site and the indoor track data or the outdoor track data.

The calculation process and the representation of the location information are only schematically illustrated, and are not particularly limited; because both indoor track data and outdoor track data can comprise track position information, the position information of the place can be deduced based on the acquired indoor track data or outdoor track data. Meanwhile, after determining the location information of each location, the location information of the location and the name of the location are recorded and stored. In addition, the data collected above may be obtained by the server 10 through wired or wireless means; the track data acquired in the mode are accurate and reliable data with high confidence, so that an indoor fingerprint library, an outdoor fingerprint library and a place fingerprint library constructed based on the acquired track data can be used as the basis for accurately identifying the indoor track or the outdoor track.

In some embodiments, after data collection is completed, an indoor fingerprint library corresponding to an indoor area, an outdoor fingerprint library corresponding to an outdoor fingerprint guard band, and a place fingerprint library corresponding to each place are respectively constructed based on the collected track data.

The indoor fingerprint library is track data of an indoor area and can be recorded based on a feature vector formed by the collected indoor track data; the outdoor fingerprint library is track data of an outdoor fingerprint guard band and can be recorded based on a characteristic vector formed by the collected outdoor track data; the location fingerprint library is data corresponding to a location, and can be recorded based on a mapping relationship between location information of the location and a name of the location.

For example, if k wireless access point devices and m bluetooth devices are disposed in the venue, the collected indoor track data may include the acquired wireless WiFi signal strength and address of each wireless access point device, the acquired bluetooth signal strength and address of each bluetooth device, and location information (such as latitude and longitude information) corresponding to each location. For example, the feature vector formed based on the foregoing data is s= (BSSID ₁ ，BSSID ₂ ，...，BSSID _k ，RSSIAP ₁ ，RSSIAP ₂ ，...， RSSIAP _k ，MAC ₁ ，MAC ₂ ，…，MAC _m ，RSSIMAC ₁ ，RSSIMAC ₂ ，...，RSSIMAC _m ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein the BSSID ₁ To BSSID _k Wireless WiFi device addresses, RSSIAP, respectively representing k wireless access point devices corresponding at each location on the track ₁ To RSSIAP _k Wireless WiFi signal strengths, MAC, respectively representing k wireless access point devices corresponding at each location on the track ₁ To MAC _m Bluetooth device addresses, RSSIMAC, respectively representing m Bluetooth devices corresponding at each location on the track ₁ To RSSIMAC _m Respectively representing Bluetooth signal strengths of m Bluetooth devices corresponding to each position on the track; and taking the characteristic vector as a wireless signal fingerprint of the track. And combining the wireless signal fingerprint of the track with longitude and latitude information of the track to form an indoor fingerprint library.

The latitude and longitude information in the trajectory data may be high confidence data directly acquired by a data acquisition device (e.g., a device with an indoor positioning system (Indoor Positioning System, IPS)).

For example, in the same manner as the indoor fingerprint library, the outdoor fingerprint library of the outdoor fingerprint guard band may include the same feature data as the indoor fingerprint library, that is, the wireless signal fingerprint based on the outdoor track and the longitude and latitude information of the outdoor track, to form the outdoor fingerprint library.

In addition, the data used for constructing the indoor fingerprint database, the outdoor fingerprint database or the venue fingerprint database may be data represented by other parameters, such as Radio frequency identification (Radio Frequency Identification, RFID) data, bluetooth low energy (Bluetooth Low Energy, BLE) data, ultra Wide Band (UWB) data, 5G signal data, long Range Radio (LoRa) data, etc., which are only illustrative herein, and specific data representation forms in the indoor fingerprint database, the outdoor fingerprint database and the venue fingerprint database are not limited.

As shown in fig. 3, an outdoor fingerprint library of an outdoor fingerprint guard band is constructed around the place through a high-confidence fingerprint library collected outdoors in the place, and an outdoor isolated track can be intercepted through the outdoor fingerprint guard band; if the points on the track to be classified have higher similarity with the track of the outdoor fingerprint guard band, the track to be classified can be judged to be close to the outdoor fingerprint guard band in the actual physical distance, and the track to be classified is not a pure indoor track and is intercepted.

It should be noted that, based on different application scenarios in different places, different signal parameters may be corresponding, the feature vector may be constructed based on other data, with updating and upgrading of the electronic device positioning system, based on the data parameters that may be collected, and a fingerprint library related to other data parameters corresponding to the feature vector may be constructed, where the constructed fingerprint library is only schematically illustrated and does not constitute limitation of specific data representation forms.

In some embodiments, after the fingerprint database is built, the server may perform track recognition on the obtained track to be classified, and determine the target field to which the track to be classified belongs and the indoor area or the outdoor area of the target field.

In an actual application scene, after obtaining the authorization of the user, the server can acquire track data of the tracks to be classified uploaded by the electronic equipment in real time or stored track data of the acquired tracks to be classified. The track data of the track to be classified can comprise satellite signal data or wireless signal data and the like; the satellite signal data may represent preliminary position information (possibly position information with a certain deviation in the room) of the track to be classified, for example, longitude and latitude information is preliminarily determined based on the satellite signal data.

In a possible implementation manner, in a track recognition process, a server firstly extracts preliminary position information (namely, preliminarily determined longitude and latitude information) in track data of a track to be classified, matches the preliminary position information with position information in a place fingerprint library, determines place position information corresponding to the track to be classified, and then determines a target place (place name) to which the track to be classified belongs based on a mapping relation between the place position information and the place name.

For example, the acquired trajectory data of the trajectory to be classified may include various information, such as wireless signal related information, sensor information, latitude and longitude information, and other parameter information. After the server obtains the track data of the track to be classified, the track data of the track to be classified can be preprocessed, for example, unnecessary data is deleted, the data format is converted, and information for identifying places in the track data is extracted.

The track data is data related to the track to be classified, which is obtained through authorization of the user, and is data which is acquired and uploaded to a server based on electronic equipment used by the user, such as signal intensity data, wireless equipment information, satellite signal data or the like at each position in the track to be classified.

For example, if the parameter used for representing the position information in the place fingerprint library is longitude and latitude information (for example, based on data collected by an indoor positioning system), the longitude and latitude information determined based on satellite signal data is extracted from the track data of the track to be classified; therefore, longitude and latitude information in the track to be classified can be matched with longitude and latitude information in the place fingerprint library, so that the target place to which the track to be classified belongs can be determined.

For example, if parameters used for representing the location information in the location fingerprint database are other wireless signal data (such as data of wireless WiFi or bluetooth, etc.), extracting wireless signal data collected based on a wireless sensor or a bluetooth device from track data of the track to be classified; therefore, the wireless signal data in the track to be classified and the wireless signal data in the place fingerprint library can be matched to determine the target place to which the track to be classified belongs.

Therefore, the process of identifying the target location to which the track to be classified belongs may be performed based on different parameters, and the above description is merely illustrative and not limiting. For example, a place fingerprint library constructed in the server may include data of various parameters, and when the place is identified on the track to be identified, the data which can be matched with the parameters in the place fingerprint library is extracted based on the track data of the track to be classified, so that the place is identified on the track to be classified.

In one possible implementation manner, when a plurality of tracks to be classified exist, the name of the target location to which each track to be classified belongs can be identified based on matching the tracks to be classified with a location fingerprint library; classifying the tracks to be classified according to the matched target market names, for example, adding building1, building2 and building N marks to the classified tracks; and then extracting a corresponding fingerprint library (an outdoor fingerprint library comprising an indoor fingerprint library and an outdoor fingerprint guard band) based on the name of each target place, and further carrying out indoor and outdoor identification.

For example, after the locus identification is performed on the locus to be classified, the locus similarity identification may be further performed on the locus to be classified based on the indoor fingerprint library of the target locus and the outdoor fingerprint library of the outdoor fingerprint guard band.

Firstly, as shown in fig. 3, the server performs outdoor fingerprint guard band interception on tracks to be classified based on an outdoor fingerprint library of outdoor fingerprint guard bands, and performs coarse recognition on the tracks to be classified; and carrying out identification judgment on each track to be classified, and calculating the similarity of the track to be classified and an outdoor fingerprint database of the outdoor fingerprint guard band based on a Euclidean distance similarity identification algorithm. The server can calculate the similarity of the track to be classified and the data of each track of the outdoor fingerprint library to obtain a calculation result with the maximum similarity, and the calculation result is used as a value for comparing with a threshold value.

When the euclidean distance is calculated, the feature vector of the track to be classified can be extracted based on the track data in the track to be classified, and the feature vector of the track recorded in the outdoor fingerprint database can be used for calculating the euclidean distance between the feature vector and the feature vector. The server establishes a mapping relation between the actual distance in the actual physical scene and the calculated Euclidean distance, and calculates a mapping relation between the Euclidean distance and the similarity. And thus, the actual distance and the value of the similarity in the actual physical scene can be determined based on the calculated Euclidean distance. For example, the calculated euclidean distance corresponding to the actual distance 25m of the actual physical scene is 18, and the value of the corresponding similarity when the euclidean distance is 18 may be 35%.

Illustratively, as shown in the (a) diagram in fig. 5, the track L to be classified is sequentially matched with the track X and the track Z of the outdoor fingerprint guard band, and the similarity is calculated; if the similarity between the position points on the track to be classified and the fingerprint library of the outdoor fingerprint guard band is greater than or equal to a threshold (i.e., a first threshold), for example, the similarity corresponding to the euclidean distance between the track L and the track X is greater than the threshold, it is determined that the track to be classified has an intersection with the outdoor fingerprint guard band, and it is further determined that the track to be classified is an outdoor track. Otherwise, if the similarity is smaller than the first threshold, the indoor track is primarily determined, as shown in the (b) diagram in fig. 5, and the track L is the indoor track; it is also possible that the track L is an outdoor track outside the outdoor fingerprint guard band, as shown in fig. 5 (c).

The first threshold is a similarity threshold between the track to be classified and the outdoor fingerprint database, and may be set to 35%.

And then, continuously matching the tracks to be classified with the matching degree smaller than the first threshold value after the rough verification with an indoor fingerprint library of the target place. Calculating the similarity between the position points on each track to be classified after coarse recognition and the indoor fingerprint library based on the Euclidean distance similarity algorithm; if the calculated similarity corresponding to the Euclidean distance exceeds a threshold (namely a second threshold), as shown in a graph (b) in fig. 5, the similarity between the track L and the indoor track Y is greater than the second threshold, and the track to be classified is judged to be the indoor track; on the contrary, as shown in the graph (c) in fig. 5, if the similarity between the track L and the indoor track Y is smaller than or equal to the second threshold, the track L is determined to be an outdoor track; thus completing the classification of indoor tracks and outdoor tracks.

The second threshold is a similarity threshold between the track to be classified and the indoor fingerprint library, and may be set to 45%.

It should be noted that, the tracks in fig. 5 are only schematically illustrated, and in the actual calculation process, the indoor fingerprint library and the outdoor fingerprint library may both include data of multiple tracks, and the tracks to be classified may also be multiple tracks, which are not limited specifically herein.

The threshold value is merely schematically illustrated, and is not particularly limited herein; for example, the specific threshold size may be set based on different application scenarios (e.g., size of the venue, complexity of the indoor and outdoor environments, etc.).

As shown in fig. 3, the track indicated by the broken line is an outdoor track intercepted by the guard band, the track indicated by the solid line in the room finally obtained is an accurately identified indoor track, and the identified indoor track is added to the indoor fingerprint library of the target place to perfect and update the indoor fingerprint library, so that the track identification is more accurate, and the accuracy of the track identification result is higher.

For example, if the identified track is a track of an outdoor fingerprint guard band, track data of the track may be further added to an outdoor fingerprint library of the outdoor fingerprint guard band.

According to the embodiment of the application, based on track data of the track to be classified, matching is carried out with a place fingerprint library, a target place to which the track to be classified belongs is determined, and an indoor fingerprint library of an indoor area of the target place and an outdoor fingerprint library of an outdoor fingerprint protection belt are called; and judging the similarity between the track to be classified and the outdoor fingerprint library based on a similarity recognition algorithm of the Euclidean distance, if the similarity between the position points on the track to be classified and the outdoor fingerprint library is lower than a first threshold, primarily judging the track to be classified as an indoor track (possibly an outdoor track except an outdoor fingerprint protection belt), further matching the roughly recognized indoor track with the indoor fingerprint library, calculating the similarity, and if the similarity is higher than a second threshold, finally judging the track to be an indoor track, realizing the recognition of the indoor track and the outdoor track, adding the track data of the recognized indoor track to the indoor fingerprint library, and perfecting the information of the indoor fingerprint library with high precision in each place.

Referring to fig. 6, fig. 6 is a flowchart illustrating a method for identifying a track according to an embodiment of the present application. Based on the same implementation principle as the above embodiment, no description is given here; as shown in fig. 6, the method for identifying a track provided in the embodiment of the present application may include the following steps:

s601, the server acquires tracks to be classified.

The track to be classified may be track data (data uploaded through user authorization) uploaded by the electronic device in real time received by the server, or stored acquired track data.

S602, matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree.

The first matching degree is the similarity calculated by a similarity recognition algorithm based on Euclidean distance. And performing traversal matching on each track to be classified and each track data of the outdoor fingerprint library, calculating to obtain similarity, and taking the maximum value of the similarity as the first matching degree.

And S603, if the first matching degree is smaller than a first threshold value, continuing to match the track to be classified with the indoor fingerprint library of the indoor area to obtain a second matching degree.

When the first matching degree is smaller than a first threshold value, the track to be classified is arranged in an outdoor fingerprint guard band, and the track to be classified may be a track of an indoor area or a track outside the outdoor fingerprint guard band; and further accurately identifying the track to be classified based on the indoor fingerprint database. And traversing and matching the residual track after the interception of the outdoor fingerprint guard band with each piece of track data of the indoor fingerprint library based on a similarity recognition algorithm of the Euclidean distance, and calculating to obtain similarity, wherein the maximum value of the similarity is used as the second matching degree.

And S604, if the second matching degree is greater than a second threshold value, determining that the track to be classified is an indoor track.

And if the second matching degree is larger than a second threshold value, judging that the track to be classified meets the condition of the indoor track, and completing the identification of the indoor track.

In one possible implementation, before acquiring the track to be classified, the method further includes:

The outdoor track data are track data of outdoor fingerprint protection bands of each place, and the indoor track data are track data of indoor areas of each place. The outdoor fingerprint library includes feature vectors and position information formed based on outdoor trajectory data, and the indoor fingerprint library includes feature vectors and position information formed based on indoor trajectory data.

In one possible implementation, collecting outdoor track data and indoor track data corresponding to each location includes:

The preset outdoor distance range can be set as an outdoor fingerprint protection band of each place; the outdoor position in the outdoor distance range preset in each place can be each position point through which the track of the outdoor fingerprint guard band passes; outdoor trajectory data is acquired based on the data of all the location points. The indoor position preset in each place can be a track in an indoor area, each passing position point is used for acquiring indoor track data based on data of all the position points.

Through the mode, before matching, the server can acquire the outdoor track data and the indoor track data with higher confidence coefficient through the equipment, and an outdoor fingerprint library in different places are formed, so that more accurate identification can be realized when tracks to be classified are matched, and the identification result is more accurate and reliable.

In one possible implementation, the outdoor trajectory data includes first wireless signal data and first location information at each outdoor location; according to the outdoor track data, constructing an outdoor fingerprint library of an outdoor fingerprint protection belt corresponding to each place, comprising:

The first wireless signal data may include wireless signal strength and wireless device address at each location where the outdoor track passes, and the first location information may include longitude and latitude information at each location where the outdoor track passes.

In one possible implementation, the indoor trajectory data includes second wireless signal data and second location information at each indoor location; according to the indoor track data, constructing an indoor fingerprint library of an indoor area corresponding to each place, comprising:

The second wireless signal data may include wireless signal strength and wireless device address at each location where the indoor track passes, and the second location information may include longitude and latitude information at each location where the indoor track passes.

In one possible implementation, the outdoor trajectory data includes first location information of an outdoor location, and the indoor trajectory data includes second location information of an indoor location; constructing a place fingerprint library corresponding to the place according to the outdoor track data or the indoor track data, comprising:

The location information comprises longitude and latitude information of a location; and (5) associating and mapping the location information and the location name to form a location fingerprint library.

In one possible implementation manner, before matching the track to be classified with the outdoor fingerprint library of the outdoor fingerprint guard band to obtain the first matching degree, the method further includes:

By the method, the server can recognize the tracks to be classified according to various places in any area, so that the breadth and applicability of the track recognition to be classified are improved, and the method is not limited to the indoor or outdoor recognition of a single place; and matching is performed on the basis of the position information and the place fingerprint library, so that the accuracy of track identification is improved.

In one possible implementation manner, matching the track to be classified with a location fingerprint library corresponding to each location, and determining a target location to which the track to be classified belongs, including:

The track data is data related to the track to be classified, which is obtained through user authorization, and is data which is acquired based on electronic equipment used by a user and uploaded to a server, such as signal intensity data, wireless equipment information, satellite signal data or the like at each position in the track to be classified; preliminary location information of the trajectories to be classified may be represented by signal strength data, wireless device information, or satellite signal data at various locations. The place fingerprint library comprises place position information, place names and a mapping relation of the place position information and the place names, and the names of the target places can be determined by matching the track data of the tracks to be classified with the place position information.

In one possible implementation manner, after matching the track to be classified with the outdoor fingerprint library of the outdoor fingerprint guard band, the method further includes:

In one possible implementation manner, after matching the track to be classified with the indoor fingerprint library of the indoor area to obtain the second matching degree, the method further includes:

In one possible implementation manner, matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree includes:

In one possible implementation manner, matching the track to be classified with an indoor fingerprint library of the indoor area to obtain a second matching degree includes:

and calculating the second similarity of the track feature vector corresponding to the track to be classified and the track feature vector in the indoor fingerprint library, and taking the maximum value of the second similarity as the second matching degree.

By the method, after outdoor identification is carried out on the track to be classified, if the track to be classified does not belong to an outdoor track, the track to be classified is possibly located in an outdoor area outside an outdoor fingerprint protection band or belongs to an indoor area, indoor identification is carried out on the track to be classified again, and if the similarity is not higher than a second threshold, the track to be classified does not belong to an indoor track, and the track to be classified is determined to be an outdoor track; thereby improving the accuracy of identifying the track to be classified; through double identification, the indoor and outdoor accurate identification of each place is realized; the track is accurately identified based on smaller data quantity, the calculation magnitude of a subsequent positioning algorithm is reduced, meanwhile, higher accuracy is guaranteed, a reliable and accurate data base is provided for indoor positioning, and indoor positioning deviation is reduced.

In one possible implementation, the method further includes:

after the track to be classified is identified as an indoor track, adding the track to be classified identified as the indoor track into an indoor fingerprint library to form a new indoor fingerprint library; the indoor fingerprint library is used for providing data support when indoor positioning is performed.

By the method, track data of the identified indoor track is added into the indoor fingerprint library, the indoor fingerprint library is continuously perfected, and the outdoor track of the outdoor fingerprint guard band is added into the outdoor fingerprint library, so that the outdoor fingerprint library is continuously perfected; by continuously updating and perfecting the track fingerprint database, the track recognition precision is improved, and a more accurate and reliable data basis is provided for subsequent position positioning.

Referring to fig. 7, fig. 7 is a flowchart of an overall method for identifying a track according to an embodiment of the present application. The implementation principle of the overall method flowchart is the same as that of the foregoing embodiment, and will not be described herein again; as shown in fig. 7, the overall method flow may include the steps of:

s701, acquiring indoor track data of a place.

S702, extracting characteristic values of indoor track data.

S703, establishing an indoor fingerprint library.

S704, acquiring outdoor track data of a place.

S705, extracting the characteristic value in the outdoor track data.

S706, an outdoor fingerprint library of the outdoor fingerprint guard band is established.

S707, obtaining the track to be classified.

S708, track data in the tracks to be classified are acquired.

S709, performing location identification based on the trajectory data, and determining the target location.

S710, carrying out similarity recognition on the track to be classified and an outdoor fingerprint library of the target place.

S711, judging whether the similarity is larger than or equal to a first threshold; if not, then S712 is performed; if yes, S716 is performed.

S712, roughly identifying the track to be classified as an indoor track.

S713, performing similarity recognition on the track to be classified and the indoor fingerprint library of the target place.

S714, judging whether the similarity is larger than a second threshold value; if yes, then execution S715; if not, S716 is performed.

S715, determining the track to be classified as an indoor track.

S716, determining the track to be classified as an outdoor track.

S717, the identified indoor track is added to the indoor fingerprint library of the target place.

S718, the outdoor track of the identified outdoor protecting band is added to the outdoor fingerprint library of the target place.

The indoor fingerprint library can be used for providing reliable data support when indoor positioning is performed after a certain amount of collected track data is achieved.

According to the embodiment of the application, the server firstly carries out rough identification of the outdoor fingerprint protection belt on the track to be classified to obtain a first matching degree, when the first matching degree of the track to be classified with the outdoor fingerprint protection belt is judged to be smaller than a first threshold value, the track to be classified is possibly the track beyond the outdoor fingerprint protection belt or the track indoors, the track to be classified is further matched with the track indoors, fine identification is carried out again to obtain a second matching degree, whether the track to be classified is the track indoors is judged based on the second matching degree, and when the second matching degree is larger than a second threshold value, the track to be classified is determined to be the track indoors; therefore, the track to be classified can be more accurately identified, and further, based on the identified indoor track, a more accurate and rich indoor fingerprint library can be obtained, so that more reliable indoor data support is further provided for subsequent more accurate indoor positioning.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.

Corresponding to the method for identifying a track described in the above embodiments, fig. 8 shows a block diagram of a device for identifying a track provided in the embodiment of the present application, and for convenience of explanation, only a portion related to the embodiment of the present application is shown.

Referring to fig. 8, the apparatus includes:

an acquiring unit 81 for acquiring a trajectory to be classified;

the first identifying unit 82 is configured to match the track to be classified with an outdoor fingerprint database of an outdoor fingerprint guard band, so as to obtain a first matching degree;

the second identifying unit 83 is configured to match the track to be classified with an indoor fingerprint database of the indoor area if the first matching degree is smaller than a first threshold value, so as to obtain a second matching degree;

and an output unit 84, configured to, if the second matching degree is greater than the second threshold, determine that the track to be classified is an indoor track.

In one possible implementation, the apparatus further includes a data acquisition unit and a data processing unit; the data acquisition unit is used for acquiring outdoor track data and indoor track data corresponding to each place respectively; the data processing unit is used for constructing an outdoor fingerprint library of the outdoor fingerprint protection belt corresponding to each place according to the outdoor track data; and constructing an indoor fingerprint library of the indoor area corresponding to each place according to the indoor track data.

In one possible implementation manner, the data acquisition unit is further configured to acquire outdoor track data based on outdoor positions within an outdoor distance range preset in each location; and acquiring indoor track data based on indoor positions preset in each place.

In a possible implementation manner, the data processing unit is further configured to construct an outdoor fingerprint library according to the first wireless signal data and the first location information at the outdoor location.

In a possible implementation manner, the data processing unit is further configured to construct an indoor fingerprint library according to the second wireless signal data and the second location information at the indoor location.

In one possible implementation manner, the data processing unit is further configured to construct a location fingerprint library corresponding to the location according to the outdoor track data or the indoor track data and the name of the location.

In a possible implementation manner, the data processing unit is further configured to determine location position information of each location according to first location information of an outdoor location or second location information of an indoor location; and constructing a place fingerprint library according to the place position information and the name of the place.

In one possible implementation manner, the device further comprises a third identification unit, which is used for matching the track to be classified with the location fingerprint database corresponding to each location, and determining the target location to which the track to be classified belongs; the target location is one of the locations.

In a possible implementation manner, the identification unit is further configured to match track data of the tracks to be classified with location position information of each location fingerprint library, and determine a name of the target location.

In one possible implementation, the output unit is further configured to, if the first matching degree is greater than or equal to a first threshold, determine that the track to be classified is an outdoor track.

In one possible implementation, the output unit is further configured to, if the second matching degree is less than or equal to the second threshold, determine that the track to be classified is an outdoor track.

In one possible implementation manner, the first identifying unit is further configured to calculate a first similarity between a track feature vector corresponding to the track to be classified and a track feature vector in the outdoor fingerprint database, and use a maximum value of the first similarity as the first matching degree.

In one possible implementation manner, the second identifying unit is further configured to calculate a second similarity between a track feature vector corresponding to the track to be classified and a track feature vector in the indoor fingerprint library, and use a maximum value of the second similarity as the second matching degree.

In a possible implementation manner, the output unit is further configured to add the track to be classified identified as the indoor track into the indoor fingerprint library after identifying that the track to be classified is the indoor track, so as to form a new indoor fingerprint library; the indoor fingerprint library is used for providing data support when indoor positioning is performed.

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein again.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

Fig. 9 shows a hardware configuration diagram of the server 10.

As shown in fig. 9, the server 10 of this embodiment includes: at least one processor 101 (only one is shown in fig. 9), a memory 102, said memory 102 having stored therein a computer program 103 executable on said processor 101. The processor 101, when executing the computer program 103, implements the steps in the method embodiments of identifying tracks described above, such as S601 to S604 shown in fig. 6. Alternatively, the processor 101 may perform the functions of the modules/units in the above-described device embodiments, such as the functions of the units 81 to 84 shown in fig. 8, when executing the computer program 103.

It should be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the server 10. In other embodiments of the present application, the server 10 may include more or less components than illustrated, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The server 10 may be a computing device such as a desktop or cloud server. The server may include, but is not limited to, a processor 101, a memory 102. It will be appreciated by those skilled in the art that fig. 9 is merely an example of the server 10 and is not limiting of the server 10, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the server may also include an input transmitting device, a network access device, a bus, etc.

The processor 101 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

A memory may also be provided in the processor 101 for storing instructions and data. In some embodiments, the memory in the processor 101 is a cache memory. The memory may hold instructions or data that has just been used or recycled by the processor 101. If the processor 101 needs to reuse the instruction or data, it may be called directly from the memory. Repeated accesses are avoided and the latency of the processor 101 is reduced, thus improving the efficiency of the system.

The storage 102 may be an internal storage unit of the server 10, such as a hard disk or a memory of the server 10, in some embodiments. The memory 102 may also be an external storage device of the server 10, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the server 10. Further, the memory 102 may also include both internal storage units and external storage devices of the server 10. The memory 102 is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs, such as program code for a computer program. The memory 102 may also be used to temporarily store data that has been transmitted or is to be transmitted.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

It should be noted that the structure of the electronic device is only illustrated by way of example, and other entity structures may be included based on different application scenarios, and the entity structure of the electronic device is not limited herein.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

The present application also provides a computer readable storage medium storing a computer program which, when executed by a processor, implements steps for implementing the various method embodiments described above.

The present embodiments provide a computer program product which, when run on a server, causes the server to perform steps that enable the implementation of the method embodiments described above.

The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each method embodiment described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.

The server, the computer storage medium, and the computer program product provided in the embodiments of the present application are all configured to execute the method provided above, so that the beneficial effects achieved by the server, the computer storage medium, and the computer program product can refer to the beneficial effects corresponding to the method provided above, and are not described herein again.

It should be understood that the foregoing is only intended to assist those skilled in the art in better understanding the embodiments of the present application and is not intended to limit the scope of the embodiments of the present application. It will be apparent to those skilled in the art from the foregoing examples that various equivalent modifications or variations can be made, for example, certain steps may not be necessary in the various embodiments of the detection methods described above, or certain steps may be newly added, etc. Or a combination of any two or more of the above. Such modifications, variations, or combinations are also within the scope of embodiments of the present application.

It should also be understood that the manner, condition, class and division of the embodiments in the embodiments of the present application are for convenience of description only and should not be construed as being particularly limited, and the various manners, classes, conditions and features of the embodiments may be combined without contradiction.

It is also to be understood that in the various embodiments of the application, terms and/or descriptions of the various embodiments are consistent and may be referenced to one another in the absence of a particular explanation or logic conflict, and that the features of the various embodiments may be combined to form new embodiments in accordance with their inherent logic relationships.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Finally, it should be noted that: the foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of identifying a trajectory, comprising:

acquiring a track to be classified;

matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint protection belt to obtain a first matching degree;

if the first matching degree is smaller than a first threshold value, matching the track to be classified with an indoor fingerprint library of an indoor area to obtain a second matching degree;

and if the second matching degree is greater than a second threshold value, the track to be classified is an indoor track.

2. The method of claim 1, wherein prior to the acquiring the trajectory to be classified, the method further comprises:

collecting outdoor track data and indoor track data corresponding to each place respectively;

constructing the outdoor fingerprint library of the outdoor fingerprint protection belt corresponding to each place according to the outdoor track data;

and constructing the indoor fingerprint library of the indoor area corresponding to each place according to the indoor track data.

3. The method of claim 2, wherein the acquiring outdoor track data and indoor track data respectively corresponding to each location comprises:

acquiring the outdoor track data based on outdoor positions in outdoor distance ranges preset in each place;

And acquiring the indoor track data based on indoor positions preset in each place.

4. The method of claim 3, wherein the outdoor trajectory data comprises first wireless signal data and first location information at each of the outdoor locations; the constructing the outdoor fingerprint library of the outdoor fingerprint guard band corresponding to each place according to the outdoor track data comprises the following steps:

and constructing the outdoor fingerprint database according to the first wireless signal data and the first position information at the outdoor position.

5. The method of claim 3, wherein the indoor trajectory data comprises second wireless signal data and second location information at each of the indoor locations; the building the indoor fingerprint library of the indoor area corresponding to each place according to the indoor track data comprises the following steps:

and constructing the indoor fingerprint library according to the second wireless signal data and the second position information at the indoor position.

6. A method according to claim 3, wherein prior to said acquiring the trajectory to be classified, the method further comprises:

7. The method of claim 6, wherein the outdoor trajectory data comprises first location information of the outdoor location and the indoor trajectory data comprises second location information of the indoor location; the constructing the place fingerprint library corresponding to the place according to the outdoor track data or the indoor track data comprises the following steps:

determining location position information of each location according to the first location information of the outdoor location or the second location information of the indoor location;

and constructing the place fingerprint library according to the place position information and the name of the place.

8. The method of claim 7, wherein prior to said matching the trajectory to be classified with the outdoor fingerprint library of the outdoor fingerprint guard band to obtain a first degree of matching, the method further comprises:

matching the track to be classified with the place fingerprint database corresponding to each place, and determining the target place to which the track to be classified belongs; the target site is one of the sites.

9. The method of claim 8, wherein the matching the trajectory to be classified with the venue fingerprint library corresponding to each venue, and determining the target venue to which the trajectory to be classified belongs, comprises:

and matching the track data of the tracks to be classified with the location position information of each location fingerprint library, and determining the name of the target location.

10. The method of claim 1, wherein after said matching the trajectory to be classified with the outdoor fingerprint library of the outdoor fingerprint guard band to obtain a first matching degree, the method further comprises:

and if the first matching degree is greater than or equal to the first threshold value, the track to be classified is an outdoor track.

11. The method of claim 1, wherein after said matching the trajectory to be classified with the indoor fingerprint library of the indoor area to obtain a second matching degree, the method further comprises:

and if the second matching degree is smaller than or equal to the second threshold value, the track to be classified is an outdoor track.

12. The method according to any one of claims 1 to 11, wherein the matching the track to be classified with an outdoor fingerprint library of an outdoor fingerprint guard band to obtain a first matching degree includes:

And calculating first similarity between the track feature vector corresponding to the track to be classified and the track feature vector in the outdoor fingerprint library, and taking the maximum value of the first similarity as the first matching degree.

13. The method according to any one of claims 1 to 11, wherein the matching the trajectory to be classified with an indoor fingerprint library of an indoor area to obtain a second matching degree includes:

and calculating second similarity between the track feature vector corresponding to the track to be classified and the track feature vector in the indoor fingerprint library, and taking the maximum value of the second similarity as the second matching degree.

14. The method of any one of claims 1 to 11, wherein the method further comprises:

after the track to be classified is identified as the indoor track, adding the track to be classified identified as the indoor track into the indoor fingerprint library to form a new indoor fingerprint library;

the indoor fingerprint library is used for providing data support when indoor positioning is performed.

15. An apparatus for identifying a trajectory, comprising:

the acquisition unit is used for acquiring the tracks to be classified;

the second recognition unit is used for matching the track to be classified with an indoor fingerprint library of an indoor area if the first matching degree is smaller than a first threshold value to obtain a second matching degree;

16. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the server implements the steps of the method according to any of claims 1 to 14 when the processor executes the computer program.

17. A computer readable storage medium storing a computer program, which, when executed by a processor, causes an electronic device to carry out the steps of the method according to any one of claims 1 to 14.