CN111629432B - Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm - Google Patents

Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm Download PDF

Info

Publication number
CN111629432B
CN111629432B CN202010419147.XA CN202010419147A CN111629432B CN 111629432 B CN111629432 B CN 111629432B CN 202010419147 A CN202010419147 A CN 202010419147A CN 111629432 B CN111629432 B CN 111629432B
Authority
CN
China
Prior art keywords
data set
historical time
candidate
fingerprint
beacon device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN202010419147.XA
Other languages
Chinese (zh)
Other versions
CN111629432A (en
Inventor
王喆
张杨
刘鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Palmap Intelligent Technology Co ltd
Original Assignee
Shanghai Palmap Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Palmap Intelligent Technology Co ltd filed Critical Shanghai Palmap Intelligent Technology Co ltd
Priority to CN202010419147.XA priority Critical patent/CN111629432B/en
Publication of CN111629432A publication Critical patent/CN111629432A/en
Application granted granted Critical
Publication of CN111629432B publication Critical patent/CN111629432B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
    • G01S11/02—Systems for determining distance or velocity not using reflection or reradiation using radio waves
    • G01S11/06—Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/318—Received signal strength

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Quality & Reliability (AREA)
  • Electromagnetism (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The embodiment of the application discloses a Bluetooth fingerprint positioning method, device and equipment based on a multi-order filtering algorithm. The method is applied to positioning equipment and comprises the following steps: acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period; respectively determining initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods; respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filter group, and taking a corrected measured value output by the filter group as target position information; wherein at least two filters are cascaded. According to the technical scheme of the embodiment of the application, when the target position information is determined, the interference of noise signals is reduced, and the accuracy of the finally determined target position information is improved.

Description

Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm
Technical Field
The embodiment of the application relates to the technical field of positioning, in particular to a Bluetooth fingerprint positioning method, device and equipment based on a multi-order filtering algorithm.
Background
With the popularization and commercialization of beacon positioning technology, users have made higher demands on positioning effects.
In the prior art, the research of indoor positioning is usually based on a ranging algorithm, the indoor positioning is based on the ranging algorithm, generally, a corresponding mathematical model is established by using time or energy information of signal sending and receiving, the model is adjusted according to different environments, and the distance between a known node and an unknown node is solved through a mathematical mode according to the geometric relationship between positions.
However, the distance between the devices is short under the indoor condition, and the ranging signals have the condition of nonlinear propagation such as serious reflection and diffraction, so that the accuracy of indoor positioning by adopting a ranging algorithm is poor, and the positioning requirement of a user cannot be met. Meanwhile, a certain delay also exists in a positioning result when indoor positioning is carried out, and positioning efficiency is reduced.
Disclosure of Invention
The application provides a Bluetooth fingerprint positioning method, device and equipment based on a multi-order filtering algorithm so as to improve positioning precision and positioning efficiency.
In a first aspect, an embodiment of the present application provides a bluetooth fingerprint positioning method based on a multi-order filtering algorithm, which is applied to a positioning device, and includes:
acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period;
respectively determining initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods;
respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filtering group, and taking a corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
In a second aspect, an embodiment of the present application further provides a bluetooth fingerprint positioning apparatus based on a multi-order filtering algorithm, configured on a positioning device, including:
the sample data set forming module is used for acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining the current signal intensity and the historical signal intensity to form a sample data set of the historical time period;
the initial positioning module is used for respectively determining initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods;
the final positioning module is used for respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in a filtering group and taking the corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
In a third aspect, an embodiment of the present application further provides a positioning apparatus, including:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement a multi-order filtering algorithm based bluetooth fingerprint positioning method as provided in an embodiment of the first aspect.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for bluetooth fingerprint location based on a multiple-order filtering algorithm as provided in the embodiment of the first aspect.
The method comprises the steps of obtaining current signal intensity of each beacon device detected at the current moment and historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period; respectively determining initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods; respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filter group, and taking a corrected measured value output by the filter group as target position information; wherein at least two filters are cascaded. According to the technical scheme, the filter group formed by cascading at least two filters is introduced, the initial position information of at least two historical time periods is respectively used as the measured values of at least two filters in the filter group, and the corrected measured value output by the filter group is used as the target position information, so that the interference of noise signals is reduced when the target position information is determined, and the accuracy of the finally determined target position information is improved.
Drawings
FIG. 1 is a flowchart of a Bluetooth fingerprint positioning method based on a multi-order filtering algorithm according to an embodiment of the present application;
FIG. 2 is a flowchart of a Bluetooth fingerprint positioning method based on a multi-order filtering algorithm according to a second embodiment of the present application;
FIG. 3 is a flowchart of a Bluetooth fingerprint positioning method based on a multi-order filtering algorithm according to a third embodiment of the present application;
FIG. 4A is a flowchart of a Bluetooth fingerprint positioning method based on a multi-order filtering algorithm according to a fourth embodiment of the present application;
FIG. 4B is a flowchart of a fingerprint database construction method in the fourth embodiment of the present application;
fig. 4C is a flowchart of a method for determining initial positioning information in a fourth embodiment of the present application;
fig. 4D is a flowchart of a target location information determining method in the fourth embodiment of the present application;
FIG. 5 is a block diagram of a Bluetooth fingerprint positioning device based on a multi-order filtering algorithm according to a fifth embodiment of the present application;
fig. 6 is a block diagram of a positioning apparatus according to a sixth embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a multi-order filtering algorithm based bluetooth fingerprint positioning method in an embodiment of the present application, where the embodiment of the present application is applicable to a situation where a user is positioned in an indoor environment such as a mall, the method is executed by a multi-order filtering algorithm based bluetooth fingerprint positioning apparatus, the apparatus is implemented by software and/or hardware, and is specifically configured in a positioning device, and the positioning device may be a mobile positioning terminal such as a smart phone, a smart watch, or a smart bracelet having a wireless signal receiving function, or may be a server.
As shown in fig. 1, a bluetooth fingerprint positioning method based on a multi-order filtering algorithm includes:
s110, acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in the historical time period, and combining to form a sample data set of the historical time period.
The beacon device may send a wireless signal to the positioning terminal, and the positioning device obtains the signal strength of the wireless signal sent by the beacon device to the positioning terminal. The Wireless signal may be a bluetooth signal or a WIFI (Wireless Fidelity) signal, etc.
The sample data set of the historical time period includes the historical signal strength of each beacon device detected at the current time and the historical time period. In order to distinguish the historical signal strengths of different beacon devices, in the sample data set, a corresponding relation between each historical signal strength and the beacon device identification can be established.
Wherein the number of the history time periods is at least two. The time lengths of the respective history time periods may be the same or different. In order to reduce the time delay of the finally determined target location information, typically, the time lengths of the respective history time periods are different.
The time lengths of the different historical time periods can be determined by a technician according to needs or empirical values, and can also be determined repeatedly through a large number of experiments.
In order to facilitate effective control over the historical time period, a buffer queue with a set length may be set, and is used to sequentially store the current signal strength of the beacon device obtained each time, and combine data in the buffer queue to form a sample data set. The length of the buffer queue can be determined by a technician according to needs or empirical values, and can also be determined repeatedly through a large number of tests.
It is understood that, in order to reduce the consumption of the storage resources, a buffer queue with a corresponding length may be set only for the historical time period with the longest time length, and used for sequentially storing the signal strength and combining to form the sample data set. When a sample data set corresponding to a historical time period with a short time length is formed, data in a complementary time period of the historical time period with the long time length and the historical time period with the short time length in the formed sample data set are removed, and the sample data set of the historical time period with the short time length is obtained.
In order to avoid the situation that the subsequent positioning result is poor due to weak signal strength, in an optional implementation manner of the embodiment of the present application, the current signal strength in the sample data set may also be screened. For example, data in the sample data set having a current signal strength below a set threshold may be filtered. The set threshold may be set by a technician as needed or empirically, and may be-85 db, for example.
In order to avoid the situation that the signal data of a single beacon device is insufficient, which results in a poor subsequent positioning result, in an optional implementation manner of the embodiment of the present application, data in which the number of signal strengths of beacon devices in the sample data set is smaller than the set number threshold may also be filtered. The set number threshold may be set by a technician as needed or an empirical value, and may be 3 times, for example.
In order to reduce the data computation amount when the initial position information is determined according to the sample data set of the historical time period, in an optional implementation manner of the embodiment of the present application, the signal strength of the same beacon device in the sample data set may be further deduplicated by an averaging method.
S120, respectively determining initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods.
And for the sample data set of each historical time period, determining initial position information corresponding to the historical time period according to the sample data set of the historical time period.
For example, fingerprint point determination may be performed by means of fingerprint library matching, and initial location information corresponding to the historical time period may be determined according to the determined location information of the fingerprint point.
S130, respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filtering group, and taking a corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
The filter group comprises at least two cascaded filters to form a multi-order filter, and the multi-order filter is used for correcting the initial position information of the input filter group by orders through estimation values. Illustratively, the filter may be a kalman filter, a particle filter, or the like. The kalman filter may be an unscented kalman filter or an extended kalman filter, or the like.
Optionally, for every two adjacent filters in the filter group, the output value of the preceding filter is used as the estimated value of the following filter for correcting the initial position information input to the following filter.
Optionally, for a first filter in the filter group, the reference position information is determined according to at least two pieces of historical target position information, and the determined reference position information is used as an estimated value of the first filter.
It is understood that, in order to reduce the time delay when determining the target position, when each initial position information is corrected by using the filter set to determine the target position information, the initial position information of the history time period with a long time length is used as the measurement value of the filter which is sequentially before in the filter set. That is, when the filter group is used for determining the target position information, the initial position information is firstly sorted according to the time length of each historical time period from large to small; numbering filters contained in the filter group in sequence according to a cascade sequence; and taking the initial position information as the measured value of the filter with the corresponding number according to the sequencing order of the initial position information of each historical time period.
The method comprises the steps of obtaining current signal intensity of each beacon device detected at the current moment and historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period; respectively determining initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods; respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filter group, and taking a corrected measured value output by the filter group as target position information; wherein at least two filters are cascaded. According to the technical scheme, the filter group formed by cascading at least two filters is introduced, the initial position information of at least two historical time periods is respectively used as the measured values of at least two filters in the filter group, and the corrected measured value output by the filter group is used as the target position information, so that the interference of noise signals is reduced when the target position information is determined, and the accuracy of the finally determined target position information is improved.
Example two
Fig. 2 is a flowchart of a bluetooth fingerprint positioning method based on a multi-order filtering algorithm in the second embodiment of the present application, and the second embodiment of the present application performs optimization and improvement on the basis of the technical solutions of the above embodiments.
Further, the operation "respectively determining the initial position information of at least two historical time periods according to the sample data sets of at least two historical time periods" is refined into "for the sample data set of each historical time period, and a target fingerprint point matched with the sample data set is determined according to the mapping relation between a candidate fingerprint point and a candidate data set in a fingerprint database and is used for determining the initial position information; and the candidate data set is a set of reference signal strength and reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs, so as to perfect a determination mechanism of initial position information.
As shown in fig. 2, a bluetooth fingerprint positioning method based on a multi-order filtering algorithm includes:
s210, acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in the historical time period, and combining to form a sample data set of the historical time period.
S220, aiming at the sample data set of each historical time period, determining a target fingerprint point matched with the sample data set according to the mapping relation between the candidate fingerprint point and the candidate data set in the fingerprint database, and determining initial position information.
And the candidate data set is a set of reference signal strength and reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs.
In an optional implementation manner of the embodiment of the application, the fingerprint library including the mapping relationship between the candidate fingerprint point and the candidate data set may be pre-stored in the local location device, other storage devices associated with the location device, or the cloud, and the fingerprint library is searched and matched in the local location device, other storage devices associated with the location device, or the cloud when needed, specifically, a target fingerprint point matched with the sample data set is searched in the fingerprint library according to the mapping relationship, and the initial position information is determined according to the position information of the target fingerprint point.
In another optional implementation manner of the embodiment of the present application, the fingerprint library including the mapping relationship between the candidate fingerprint point and the candidate data set may be further generated by a positioning device before performing target fingerprint point matching using the fingerprint library.
Illustratively, the fingerprint library may be constructed in the following manner: dividing a target route at equal intervals to obtain at least two target road section areas, and taking the central point of each target road section area as the candidate fingerprint point; combining the reference signal strength and the reference beacon device identification collected in the target road segment area to form a candidate data set associated with the candidate fingerprint point; and constructing a fingerprint database according to the candidate data sets associated with the plurality of candidate fingerprint points.
The distance for dividing the target road section area can be determined by technicians according to needs or empirical values, and can also be determined through a large number of tests. For example, it may be 1 meter.
The candidate fingerprint point may be any coordinate point or any signal acquisition point in the target road segment area. Typically, in order to improve the matching degree of the subsequently determined candidate data set with the candidate fingerprint points and simultaneously reduce the data deviation between adjacent candidate fingerprint points, it is preferable to select the center point of the target link region as the candidate fingerprint point.
Generally, when the reference signal strength detection is performed, an inspector holds a detection tool to uniformly acquire the reference signal strengths at different positions along a target route. Then, the reference signal strength and the reference beacon device identifier acquired in the target road segment area corresponding to the candidate fingerprint point are used for replacing the reference signal strength and the reference beacon device identifier of a single acquisition point, and a candidate data set corresponding to the candidate fingerprint point is formed in a combined mode, so that data in the candidate data set is richer.
In order to avoid the situation that the initial positioning result is poor due to weak signal strength and the accuracy of the final positioning result is affected, in an optional implementation manner of the embodiment of the present application, the reference signal strength in the candidate data set may be further screened. For example, data with a reference signal strength lower than a set threshold value in the candidate data set may be received. The set threshold may be set by a technician as needed or empirically, and may be-85 db, for example.
In order to avoid the situation that the initial positioning result is poor due to different signal data of a single beacon device, and the accuracy of the final positioning result is affected, in an optional implementation manner of the embodiment of the present application, data in which the number of reference signal strengths corresponding to the reference beacon device identifiers in the candidate data set is smaller than the set number threshold may also be filtered. The set number threshold may be set by a technician as needed or an empirical value, and may be 3 times, for example.
In order to reduce the data computation amount in the fingerprint database matching process, in an optional implementation manner of the embodiment of the present application, the reference signal strength of the same beacon device in the candidate data set may also be deduplicated by taking an average value.
Illustratively, the reference signal strength of each reference beacon device detected in the target road segment area is averaged to obtain a new reference signal strength of the reference beacon device; and combining the new reference signal strength of each reference beacon device and the reference beacon device identification to form a candidate data set associated with the candidate fingerprint point.
In yet another optional implementation manner of the embodiment of the present application, in order to further expand the data amount of the candidate data set corresponding to the candidate fingerprint point, so as to improve the fault tolerance rate and accuracy in the use process of the fingerprint database, after the candidate data set is obtained, the candidate data set of the candidate fingerprint point may be updated according to the candidate data set of the adjacent candidate fingerprint point.
Illustratively, updating the candidate data set of candidate fingerprint points based on the candidate data sets of neighboring candidate fingerprint points may be: merging the candidate data sets of neighboring candidate fingerprint points into the candidate data set of candidate fingerprint points; in the merged candidate data set, performing mean processing on the reference signal intensity of each reference beacon device; and combining the processing result of each reference beacon device and the reference beacon device identification to form an updated candidate data set.
Wherein the neighboring candidate fingerprint points may be left neighboring candidate fingerprint points and/or right neighboring candidate fingerprint points. Wherein the number of neighboring candidate fingerprint points may be set by a skilled person according to need or empirical values, or determined repeatedly by a number of experiments. Illustratively, there may be 4 neighboring candidate fingerprint points. Typically, for a candidate fingerprint point, the candidate data set of the candidate fingerprint point is updated using the candidate data sets of two left-adjacent candidate fingerprint points and two right-adjacent candidate fingerprint points.
When constructing the fingerprint database, typically, a positioning area is set for a certain mall or a cell, a fingerprint database corresponding to the positioning area is constructed, and candidate data sets of candidate fingerprint points in target routes in the positioning area are combined to form the fingerprint database. The target route can be a route formed by any starting point and any ending point which are communicated with each other in the positioning area. For example, when the positioning area is a mall, the starting point may be an entrance of the mall, and the ending point may be an exit of the mall.
It is understood that, when a new target route is added to the location area, the mapping relationship between the candidate fingerprint point of the newly added target route and the candidate data set may also be added to the existing fingerprint database to update the content of the fingerprint database.
It can be understood that, for each target route in the fingerprint database, the reference signal strength and the reference beacon device identifier may be acquired for a plurality of times for a target road section region corresponding to each candidate fingerprint point, and the candidate data set may be determined according to the acquired data; merging the candidate data sets determined for multiple times, and then averaging the reference signal intensities of the same reference beacon equipment to obtain a new reference signal intensity of the reference beacon equipment; and combining the new reference signal strength of each reference beacon device with the reference beacon device identification to obtain a candidate data set.
S230, respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in a filtering group, and taking the corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
The method comprises the steps of refining initial position information into a sample data set aiming at each historical time period through determining operation, and determining target fingerprint points matched with the sample data set according to the mapping relation between candidate fingerprint points and candidate data sets in a fingerprint database for determining the initial position information; and the candidate data set is a set of the reference signal strength and the reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs. According to the technical scheme, when the fingerprint database is used for matching the target fingerprint points, the reference signal strength and the reference beacon device identification of each reference beacon device detected in the area where the candidate fingerprint points belong are adopted by the candidate data set in the fingerprint database to supplement the data detected at the positions of the candidate fingerprint points, so that the fault tolerance rate of fingerprint matching is improved in the using process of the fingerprint database, the influence of environmental factors or system errors is compensated, the accuracy of fingerprint matching is improved, and the accuracy of a final positioning result is improved.
EXAMPLE III
Fig. 3 is a flowchart of a bluetooth fingerprint positioning method based on a multi-order filtering algorithm in the third embodiment of the present application, and the third embodiment of the present application performs optimization and improvement on the basis of the technical solutions of the above embodiments.
Further, the operation of determining the target fingerprint points matched with the sample data set according to the mapping relation between the candidate fingerprint points and the candidate data set in the fingerprint database is refined into the operation of determining the distance deviation between the sample data set and each candidate data set contained in the fingerprint database; and screening the candidate data set according to the distance deviation, and taking the fingerprint points corresponding to the screened candidate data set as target fingerprint points so as to perfect a matching mechanism of the target fingerprint points.
As shown in fig. 3, a bluetooth fingerprint positioning method based on a multi-order filtering algorithm includes:
s310, acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period;
s320, determining the distance deviation between the sample data set and each candidate data set contained in the fingerprint database aiming at the sample data set of each historical time period;
and the candidate data set is a set of reference signal strength and reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs.
Exemplarily, for each candidate data set contained in the fingerprint database, determining a distance deviation between the candidate data set and the signal strength corresponding to the same beacon device identifier in the sample data set; and determining the final distance deviation according to the distance deviation of each beacon device identifier. Wherein the distance deviation may be a euclidean distance or a mahalanobis distance.
In an optional implementation manner of the embodiment of the present application, in order to further improve the matching degree of the target fingerprint point, determining a distance deviation between the sample data set and each candidate data set included in the fingerprint database may be: determining the similarity between the candidate data set and the sample data set according to the ratio of the coincidence quantity and the accumulation quantity of the beacon device identification and the reference beacon device identification in the candidate data set; and determining an initial distance deviation between the sample data set and each candidate data set contained in the fingerprint database; and determining the target distance deviation of the candidate data set according to the similarity and the initial distance deviation.
It should be noted that, the similarity determining operation and the initial distance deviation determining operation may be executed simultaneously or sequentially, and the optional implementation manner in the embodiment of the present application does not limit the order of the similarity determining operation and the initial distance deviation determining operation.
In order to reduce the amount of data computation when matching a target fingerprint point, before determining a distance deviation between the sample data set and each candidate data set included in the fingerprint database, the signal data sets in the fingerprint database may be further filtered according to the number of coincidences between the beacon device identifier and a reference beacon device identifier included in each candidate data set in the fingerprint database.
Illustratively, for each candidate data set in the fingerprint database, determining the coincidence quantity of the candidate data set and the beacon device identifier in the sample data set, and if the coincidence quantity is greater than a screening quantity threshold value, reserving the candidate data set for distance deviation determination; otherwise, the candidate data set is culled. Wherein, the screening quantity threshold value can be set by technicians according to needs or experience values, and can also be repeatedly determined through a large number of tests.
Optionally, the screening number threshold may be the number of beacon device identifications contained in the sample data set. In order to avoid the situation that the number of the retained candidate data sets is small, which causes the subsequent positioning inaccuracy, the screening number threshold value can be adjusted by setting an adjusting factor. The setting adjustment factor can be set by a technician according to needs or empirical values, and can be determined repeatedly through a large number of tests.
For example, the screening number threshold is determined by setting a product of the adjustment factor and the number of beacon device identifiers contained in the sample data set; wherein the adjustment factor is set to a positive number smaller than 1, such as 0.8. For another example, the filtering quantity threshold is determined by a difference between the quantity of beacon device identifiers contained in the sample data set and the set adjustment factor. Wherein, the adjustment factor is set to be a positive integer, such as 2.
S330, screening the candidate data set according to the distance deviation, and taking the fingerprint points corresponding to the screened candidate data set as target fingerprint points for determining initial position information.
For example, the candidate data sets are screened according to the distance deviations, and the distance deviations corresponding to the candidate data sets may be sorted; and screening out a set number of candidate data sets with the minimum distance deviation. The set number may be determined by a skilled person as needed or an empirical value, or may be determined repeatedly by a large number of experiments.
Alternatively, the set number may be a fixed value, for example, 5; or alternatively, the set number may also be a variable value, for example 5% of the number of candidate data sets.
Exemplarily, the fingerprint point corresponding to the screened candidate data set is used as a target fingerprint point for determining the initial position information, which may be the fingerprint point corresponding to the screened candidate data set as the target fingerprint point; and determining an average value of the position information of each target fingerprint point, and taking the determined average value as initial position information.
S340, respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in a filtering group, and taking the corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
The method comprises the steps of refining the determination operation of a target fingerprint point into the distance deviation between a determination sample data set and each candidate data set contained in a fingerprint database; the candidate data sets are screened according to the distance deviation, and the fingerprint points corresponding to the screened candidate data sets are used as target fingerprint points, so that the matching mechanism of the target fingerprint points is perfected, the matching degree between the determined target fingerprint points and the actual position information is improved through a distance deviation determining method, the accurate determination of the determined initial position information is improved, and the accuracy of the finally determined target position information is improved.
Example four
Fig. 4A is a flowchart of a bluetooth fingerprint positioning method based on a multi-order filtering algorithm in the fourth embodiment of the present application, and the embodiment of the present application provides a preferred implementation manner based on the technical solutions of the foregoing embodiments.
As shown in fig. 4A, a bluetooth fingerprint positioning method based on a multi-order filtering algorithm includes:
s410, collecting data and constructing a fingerprint database;
s420, performing initial positioning and determining initial positioning information;
and S430, correcting the initial positioning information to determine target positioning information.
Specifically, "collect data, construct fingerprint database", can be refined as S401 to S409.
The fingerprint database construction method shown in fig. 4B includes:
s401, uniformly collecting the signal intensity and the beacon device identification from the starting point to the end point in the target route, and recording the position coordinates and the collection time of the starting point and the end point.
Specifically, a target route is marked on a collection tool map, the collection tool is held in the target route from a starting point, the uniform speed straight line goes to an end point to carry out signal intensity and beacon equipment identification, and position coordinates and collection time of the starting point and the end point are recorded.
Wherein, the signal strength of gathering is bluetooth signal intensity, and beacon equipment is bluetooth equipment.
S402, filtering data with the signal intensity smaller than a set intensity threshold value.
Wherein the intensity threshold is set to-85 db.
And S403, dividing the target route at equal intervals to obtain a target road section area, and taking the central point of the target road section area as a fingerprint point.
Wherein the division distance is 1 meter.
And S404, respectively determining the acquisition time periods corresponding to the target road section areas according to the acquisition rate and the acquisition time of the starting point and the ending point.
S405, combining the signal intensity and the beacon equipment identification in the acquisition time period corresponding to the target road section area to form a candidate data set corresponding to the fingerprint point.
And S406, averaging and removing the weight of the signal intensity of the same beacon device in the candidate data set.
S407, aiming at each fingerprint point, merging the candidate data sets of the adjacent fingerprint points of the fingerprint point into the candidate data set of the fingerprint point.
And S408, averaging the signal intensity of the same beacon device in the merged candidate data set to remove the duplicate, and obtaining a final candidate data set.
And S409, combining the candidate data sets of the fingerprint points contained in each target route to construct a fingerprint database.
Specifically, "perform initial positioning and determine initial positioning information", may be refined to S411 to S419:
as shown in fig. 4C, an initial positioning information determining method includes:
s411, acquiring the signal intensity of the wireless signals and the beacon equipment identification collected every second, and writing the signal intensity and the beacon equipment identification into a buffer queue.
The length of the buffer queue is 6, that is, the buffer queue can store 6 seconds of signal strength data, and record the beacon device identifier corresponding to the signal strength data.
S412, reading data from different positions in the cache queue to the tail of the cache queue to obtain a first sample data set and a second sample data set.
The first sample data set comprises all data in the buffer queue; the second sample data set contains data written in the cache queue in the last two seconds.
S413, filtering data in the sample data set, wherein the signal intensity of the same beacon equipment identifier is less than the set number of the data;
wherein the set number is 3.
And S414, averaging and de-duplicating the signal intensity of the same beacon equipment identifier in the filtered sample data set.
S415, screening the coincidence quantity of the beacon device identification of the candidate data set in the fingerprint database and the beacon device identification of the sample data set, and meeting the candidate data set with the coincidence quantity threshold value.
And the coincidence quantity threshold value is a numerical value obtained by subtracting 2 from the quantity of the beacon equipment identifications in the sample data set.
And S416, aiming at each beacon device identification in each screened candidate data set, determining the initial Euclidean distance between the signal intensity of the beacon device identification in the candidate data set and the signal intensity in the sample data set.
S417, according to the ratio of the same number of the beacon device identifications in the candidate data set and the sample data set to the total amount, determining the similarity.
And S418, accumulating the products of the initial Euclidean distance and the similarity of each beacon equipment identifier to obtain the target Euclidean distance.
S419, selecting a set number of candidate data sets with the minimum Euclidean distance, taking the fingerprint points corresponding to the selected candidate data sets as target fingerprint points, and taking the average value of the position information of each target fingerprint point as initial position information.
Wherein the set number is 5.
Specifically, "correcting the initial positioning information to determine the target positioning information" may be refined to S421 to S423.
As shown in fig. 4D, a method for determining target location information includes:
and S421, determining a position estimation value at the current moment according to at least two pieces of historical target position information, and using the position estimation value as an estimation value of a first-order Kalman filter in a Kalman filter group.
The Kalman filtering set comprises a first-order Kalman filter and a second-order Kalman filter, and the first-order Kalman filter and the second-order Kalman filter are cascaded.
And S422, taking the initial position information corresponding to the first sample data set as a measurement value of a first-order Kalman filter to obtain reference position information.
And S423, taking the first-order positioning correction value as an estimated value of a second-order Kalman filter, and taking initial position information corresponding to the second sample data set as a measured value of the second-order Kalman filter to obtain target position information.
EXAMPLE five
Fig. 5 is a structure diagram of a bluetooth fingerprint positioning apparatus based on a multi-order filtering algorithm in the fifth embodiment of the present application, which is applicable to the situation of positioning a user through an indoor environment such as a mall, and the apparatus is implemented by software and/or hardware and is specifically configured in a positioning device, and the positioning device may be a mobile positioning terminal such as a smart phone, a smart watch, or a smart bracelet having a wireless signal receiving function, or may be a server.
Fig. 5 shows a bluetooth fingerprint positioning apparatus based on a multi-order filtering algorithm, which includes: a sample data set formation module 510, an initial positioning module 520 and a final positioning module 530. Wherein,
a sample data set forming module 510, configured to obtain current signal strengths of the beacon devices detected at the current time and historical signal strengths of the beacon devices detected in the historical time period, and combine the current signal strengths and the historical signal strengths to form a sample data set of the historical time period;
an initial positioning module 520, configured to determine initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods, respectively;
a final positioning module 530, configured to use initial position information of at least two historical time periods as measured values of at least two filters in a filter group, respectively, and use a corrected measured value output by the filter group as target position information; wherein the at least two filters are cascaded.
The method comprises the steps that a sample data set forming module is used for obtaining the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and the sample data set of the historical time period is formed in a combined mode; respectively determining initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods through an initial positioning module; respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in a filter group through a final positioning module, and taking the corrected measured value output by the filter group as target position information; wherein at least two filters are cascaded. According to the technical scheme, the filter group formed by cascading at least two filters is introduced, the initial position information of at least two historical time periods is respectively used as the measured values of at least two filters in the filter group, and the corrected measured value output by the filter group is used as the target position information, so that the interference of noise signals is reduced when the target position information is determined, and the accuracy of the finally determined target position information is improved.
Further, the final positioning module 530, when performing the step of using the initial position information of the at least two historical time periods as the measured values of the at least two filters in the filter group, is specifically configured to:
and taking the initial position information of the historical time period with large time length as the measured value of the filter which is sequentially before in the filter group.
Further, the final positioning module 530 is further configured to:
for every two adjacent filters, the output value of the preceding filter is taken as the estimated value of the following filter.
Further, the final positioning module 530 is further configured to:
and determining an estimated value of a first filter in the filter group according to at least two pieces of historical target position information.
Further, the filter is a kalman filter.
Further, the initial positioning module 520 is specifically configured to:
aiming at the sample data set of each historical time period, determining a target fingerprint point matched with the sample data set according to the mapping relation between the candidate fingerprint point and the candidate data set in the fingerprint database, wherein the target fingerprint point is used for determining initial position information;
and the candidate data set is a set of reference signal strength and reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs.
Further, the apparatus further comprises a fingerprint construction module, specifically configured to:
dividing a target route at equal intervals to obtain at least two target road section areas, and taking the central point of each target road section area as the candidate fingerprint point;
combining the reference signal strength and the reference beacon device identification collected in the target road segment area to form a candidate data set associated with the candidate fingerprint point;
and constructing a fingerprint database according to the candidate data sets associated with the plurality of candidate fingerprint points.
Further, the fingerprint construction module, when performing combining the reference signal strength and the reference beacon device identifier acquired in the target road segment area to form the candidate data set associated with the candidate fingerprint point, is specifically configured to:
carrying out mean value processing on the reference signal intensity of each reference beacon device collected in the target road section area to obtain a new reference signal intensity of the reference beacon device;
and combining the new reference signal strength of each reference beacon device and the reference beacon device identification to form a candidate data set associated with the candidate fingerprint point.
Further, the fingerprint construction module, after performing combining the new reference signal strength and the reference beacon device identification of each reference beacon device to form the candidate data set associated with the candidate fingerprint point, is further configured to:
the candidate data set of candidate fingerprint points is updated according to the candidate data sets of neighboring candidate fingerprint points.
Further, the fingerprint construction module, when performing updating the candidate data set of the candidate fingerprint points according to the candidate data sets of the neighboring candidate fingerprint points, is specifically configured to:
merging the candidate data sets of neighboring fingerprint points into the candidate data set of candidate fingerprint points;
in the merged candidate data set, performing mean processing on the reference signal intensity of each reference beacon device;
and combining the processing result of each reference beacon device and the reference beacon device identification to form an updated candidate data set.
The Bluetooth fingerprint positioning device based on the multi-order filtering algorithm can execute the Bluetooth fingerprint positioning method based on the multi-order filtering algorithm provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing the Bluetooth fingerprint positioning method based on the multi-order filtering algorithm.
EXAMPLE six
Fig. 6 is a block diagram of a positioning apparatus in a sixth embodiment of the present application, where the apparatus includes: an input device 610, an output device 620, a processor 630, and a storage device 640.
The input device 610 is configured to obtain a current signal strength of each beacon device detected at a current time and a historical signal strength of each beacon device detected in a historical time period;
an output device 620 for presenting the target location information;
one or more processors 630;
a storage device 640 for storing one or more programs.
The positioning device can be a mobile positioning terminal with a wireless signal detection function, such as a smart phone, a smart band or a smart watch, and can also be a server.
In fig. 6, a processor 630 is taken as an example, the input device 610 in the positioning apparatus may be connected to the output device 620, the processor 630 and the storage device 640 through a bus or other means, and the processor 630 and the storage device 640 are also connected through a bus or other means, which is taken as an example in fig. 6.
In this embodiment, the processor 630 in the positioning apparatus may control the input device 610 to obtain the current signal strength of each beacon apparatus detected at the current time, and the historical signal strength of each beacon apparatus detected in the historical time period; the data acquired by the input device 610 are combined to form a sample data set of the historical time period; the system is also used for respectively determining the initial position information of at least two historical time periods according to the sample data sets of the at least two historical time periods; the system is also used for respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in the filter group and taking the corrected measured value output by the filter group as the target position information; wherein at least two filters are cascaded; and also for controlling the output device 620 to present the target location information.
The storage device 640 of the positioning apparatus is a computer-readable storage medium, and can be used to store one or more programs, which may be software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the multi-order filtering algorithm-based bluetooth fingerprint positioning method in the embodiment of the present application (for example, the sample data set forming module 510, the initial positioning module 520, and the final positioning module 530 shown in fig. 5). The processor 630 executes various functional applications and data processing of the positioning apparatus by running software programs, instructions and modules stored in the storage device 640, so as to implement the bluetooth fingerprint positioning method based on the multi-order filtering algorithm in the above method embodiments.
The storage device 640 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like (current signal strength, historical signal strength, sample data set, initial location information, target location information, and the like as in the above-described embodiments). Further, the storage 640 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage device 640 may further include memory located remotely from the processor 630, which may be connected to a server over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE seven
The seventh embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a bluetooth fingerprint positioning apparatus based on a multi-order filtering algorithm, implements the bluetooth fingerprint positioning method based on the multi-order filtering algorithm provided in this application, and the method includes: acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period; respectively determining initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods; respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filtering group, and taking a corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods described in the embodiments of the present application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims (12)

1. A Bluetooth fingerprint positioning method based on a multi-order filtering algorithm is applied to positioning equipment, and the method comprises the following steps:
acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining to form a sample data set of the historical time period;
respectively determining initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods;
respectively taking initial position information of at least two historical time periods as measured values of at least two filters in a filtering group, and taking a corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded;
the time lengths of the at least two historical time periods are different;
setting a cache queue with a corresponding length for the historical time period with the longest time length, sequentially storing the signal intensity, and combining to form a sample data set; when a sample data set corresponding to a historical time period with a short time length is formed, data in a complementary time period of the historical time period with the long time length and the historical time period with the short time length in the formed sample data set are removed, and the sample data set of the historical time period with the short time length is obtained.
2. The method of claim 1, wherein using the initial position information of the at least two historical time periods as the measured values of the at least two filters in the filter set comprises:
and taking the initial position information of the historical time period with large time length as the measured value of the filter which is sequentially before in the filter group.
3. The method of claim 1, further comprising:
for every two adjacent filters, the output value of the preceding filter is taken as the estimated value of the following filter.
4. The method of claim 1, further comprising:
and determining an estimated value of a first filter in the filter group according to at least two pieces of historical target position information.
5. The method of claim 1, wherein the filter is a kalman filter.
6. The method according to any of claims 1-5, wherein determining initial location information for at least two historical time periods from sample data sets for the at least two historical time periods, respectively, comprises:
aiming at the sample data set of each historical time period, determining a target fingerprint point matched with the sample data set according to the mapping relation between the candidate fingerprint point and the candidate data set in the fingerprint database, wherein the target fingerprint point is used for determining initial position information;
and the candidate data set is a set of reference signal strength and reference beacon device identification of each detected reference beacon device in the area to which the candidate fingerprint point belongs.
7. The method of claim 6, wherein the fingerprint library is constructed based on:
dividing a target route at equal intervals to obtain at least two target road section areas, and taking the central point of each target road section area as the candidate fingerprint point;
combining the reference signal strength and the reference beacon device identification collected in the target road segment area to form a candidate data set associated with the candidate fingerprint point;
and constructing a fingerprint database according to the candidate data sets associated with the plurality of candidate fingerprint points.
8. The method of claim 7, wherein combining the reference signal strength and reference beacon device identification collected in the target road segment region to form the candidate data set of candidate fingerprint point associations comprises:
carrying out mean value processing on the reference signal intensity of each reference beacon device collected in the target road section area to obtain a new reference signal intensity of the reference beacon device;
and combining the new reference signal strength of each reference beacon device and the reference beacon device identification to form a candidate data set associated with the candidate fingerprint point.
9. The method of claim 7, wherein after combining the new reference signal strength and reference beacon device identification for each reference beacon device to form the candidate data set of candidate fingerprint point associations, the method further comprises:
the candidate data set of candidate fingerprint points is updated according to the candidate data sets of neighboring candidate fingerprint points.
10. The method of claim 9, wherein updating the candidate data set of candidate fingerprint points based on the candidate data sets of neighboring candidate fingerprint points comprises:
merging the candidate data sets of neighboring fingerprint points into the candidate data set of candidate fingerprint points;
in the merged candidate data set, performing mean processing on the reference signal intensity of each reference beacon device;
and combining the processing result of each reference beacon device and the reference beacon device identification to form an updated candidate data set.
11. A Bluetooth fingerprint positioning device based on a multi-order filtering algorithm, which is configured on a positioning device, the device comprises:
the sample data set forming module is used for acquiring the current signal intensity of each beacon device detected at the current moment and the historical signal intensity of each beacon device detected in a historical time period, and combining the current signal intensity and the historical signal intensity to form a sample data set of the historical time period;
the initial positioning module is used for respectively determining initial position information of at least two historical time periods according to sample data sets of the at least two historical time periods;
the final positioning module is used for respectively taking the initial position information of at least two historical time periods as the measured values of at least two filters in a filtering group and taking the corrected measured value output by the filtering group as target position information; wherein the at least two filters are cascaded;
the time lengths of the at least two historical time periods are different;
setting a cache queue with a corresponding length for the historical time period with the longest time length, sequentially storing the signal intensity, and combining to form a sample data set; when a sample data set corresponding to a historical time period with a short time length is formed, data in a complementary time period of the historical time period with the long time length and the historical time period with the short time length in the formed sample data set are removed, and the sample data set of the historical time period with the short time length is obtained.
12. A positioning apparatus, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for bluetooth fingerprint location based on a multiple-order filtering algorithm as recited in any of claims 1-10.
CN202010419147.XA 2020-05-18 2020-05-18 Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm Expired - Fee Related CN111629432B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010419147.XA CN111629432B (en) 2020-05-18 2020-05-18 Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010419147.XA CN111629432B (en) 2020-05-18 2020-05-18 Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm

Publications (2)

Publication Number Publication Date
CN111629432A CN111629432A (en) 2020-09-04
CN111629432B true CN111629432B (en) 2022-04-12

Family

ID=72260629

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010419147.XA Expired - Fee Related CN111629432B (en) 2020-05-18 2020-05-18 Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm

Country Status (1)

Country Link
CN (1) CN111629432B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732089A (en) * 2015-03-24 2015-06-24 北京科技大学 History data construction method for cross-regional positioning system filtering algorithm
CN111044050A (en) * 2019-12-30 2020-04-21 中电海康集团有限公司 Bluetooth positioning method based on particle filtering and Kalman filtering

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8638342B2 (en) * 2009-10-20 2014-01-28 Apple Inc. System and method for demosaicing image data using weighted gradients
CN102223596A (en) * 2010-04-15 2011-10-19 上海启电信息科技有限公司 Mobile positioning service method
US8855931B2 (en) * 2012-06-25 2014-10-07 Google Inc. Location history filtering
GB2507539A (en) * 2012-11-02 2014-05-07 Zwipe As Matching sets of minutiae using local neighbourhoods
US20170265041A1 (en) * 2016-03-09 2017-09-14 Honeywell International Inc. Systems, methods, and devices for indoor location
CN107770858A (en) * 2016-08-17 2018-03-06 上海新飞凡电子商务有限公司 Quick three-point fox method and its system based on RSSI and region division
CN107941211B (en) * 2017-11-13 2020-04-17 北京邮电大学 Multi-element fusion positioning method and device based on second-order cascade and electronic equipment
CN107948296B (en) * 2017-11-30 2020-06-30 中电科卫星导航运营服务有限公司 Indoor positioning system and method based on Bluetooth
CN108957434A (en) * 2018-07-03 2018-12-07 京信通信系统（中国）有限公司 Adaptive location method, device and positioning device
CN110166930A (en) * 2019-04-03 2019-08-23 华中科技大学 A kind of indoor orientation method and system based on WiFi signal
CN110929639B (en) * 2019-11-20 2023-09-19 北京百度网讯科技有限公司 Method, apparatus, device and medium for determining the position of an obstacle in an image
CN111159642B (en) * 2019-11-28 2023-04-28 南京航空航天大学 Online track prediction method based on particle filtering
CN110958575B (en) * 2019-12-02 2020-12-18 重庆邮电大学 Positioning method and system based on WiFi fusion prediction
CN111024075B (en) * 2019-12-26 2022-04-12 北京航天控制仪器研究所 Pedestrian navigation error correction filtering method combining Bluetooth beacon and map

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732089A (en) * 2015-03-24 2015-06-24 北京科技大学 History data construction method for cross-regional positioning system filtering algorithm
CN111044050A (en) * 2019-12-30 2020-04-21 中电海康集团有限公司 Bluetooth positioning method based on particle filtering and Kalman filtering

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
一种改进的例子滤波SLAM算法;王晓华等;《模式识别与人工智能》;20130615;第26卷(第6期);全文 *

Also Published As

Publication number Publication date
CN111629432A (en) 2020-09-04

Similar Documents

Publication Publication Date Title
CN111078818B (en) Address analysis method and device, electronic equipment and storage medium
CN106790468B (en) Distributed implementation method for analyzing WiFi (Wireless Fidelity) activity track rule of user
US8830909B1 (en) Methods and systems to determine user relationships, events and spaces using wireless fingerprints
WO2016127507A1 (en) Method and apparatus for analyzing track of user
CN105933294A (en) Network user positioning method, device and terminal
CN106558220B (en) A kind of statistical method and device of traffic volume of highway
CN113537584A (en) Inspection task conflict processing method and device, electronic equipment and storage medium
CN114242162B (en) Method for establishing drug synergy prediction model, prediction method and corresponding device
CN107274061A (en) A kind of smart city evaluation method based on entropy assessment
CN111475746B (en) Point-of-interest mining method, device, computer equipment and storage medium
CN111629432B (en) Bluetooth fingerprint positioning method, device and equipment based on multi-order filtering algorithm
CN108920601B (en) Data matching method and device
CN111343664B (en) User positioning method, device, equipment and medium
CN110782150A (en) Natural resource information collection system and method based on crowd sensing
CN110309948A (en) Complete vehicle logistics order forecast method and device, logistics system and computer-readable medium
CN114357102A (en) Road network data generation method and device
CN112445786B (en) Screening method and device for target users
CN110781161B (en) Service data processing method and device
CN116860904B (en) Target tracking method and device based on decentralization network
CN113505788B (en) Method, device and storage medium for acquiring road network information
CN113298971B (en) Power plant inspection method and system considering wireless signal interference among multiple devices
WO2024179555A1 (en) Method for identifying occupational and residential places of user, and electronic device and storage medium
CN117193676B (en) Method, system, equipment and medium for evaluating performance of storage equipment
CN112637768B (en) Mobile terminal positioning method and device based on cellular network
CN110019633B (en) Line density statistical method and system based on ArcGIS secondary development

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20220412