CN113347563A - Fingerprint library construction method and device based on mobile crowd sensing task model - Google Patents

Fingerprint library construction method and device based on mobile crowd sensing task model Download PDF

Info

Publication number
CN113347563A
CN113347563A CN202110605466.4A CN202110605466A CN113347563A CN 113347563 A CN113347563 A CN 113347563A CN 202110605466 A CN202110605466 A CN 202110605466A CN 113347563 A CN113347563 A CN 113347563A
Authority
CN
China
Prior art keywords
hotspots
fingerprint
sensing
task
data
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.)
Granted
Application number
CN202110605466.4A
Other languages
Chinese (zh)
Other versions
CN113347563B (en
Inventor
刘溪
岑健
伍银波
熊建斌
李争名
宋海鹰
刘军
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.)
Guangdong Polytechnic Normal University
Original Assignee
Guangdong Polytechnic Normal University
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 Guangdong Polytechnic Normal University filed Critical Guangdong Polytechnic Normal University
Priority to CN202110605466.4A priority Critical patent/CN113347563B/en
Publication of CN113347563A publication Critical patent/CN113347563A/en
Application granted granted Critical
Publication of CN113347563B publication Critical patent/CN113347563B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
    • 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
    • H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention relates to the field of indoor position positioning, in particular to a fingerprint database construction method and device based on a mobile crowd sensing task model. The invention formulates a task to carry out RSSI fingerprint acquisition by moving a crowd sensing task model, and establishes a fingerprint database according to the RSSI fingerprint. The target required to be collected by the perception task is defined through the definition of the object, and the position information of the target is not required; meanwhile, the RSSI fingerprint is sampled and obtained in a static state according to a rule formulated by a motion state under the condition that the position information of the user cannot be obtained, and the position characteristic of the RSSI fingerprint can be described more accurately compared with the RSSI instantaneous value recorded in the motion state, so that the indoor positioning accuracy is improved, the integrity of the collected data is ensured, and the omission or the loss of the data is avoided; and the quality of the collected data is ensured by the process, so that the data quality is improved, and the quality of the fingerprint database is greatly improved.

Description

Fingerprint library construction method and device based on mobile crowd sensing task model
Technical Field
The invention relates to the field of indoor position positioning, in particular to a fingerprint database construction method and device based on a mobile crowd sensing task model.
Background
The traditional fingerprint database construction method is realized by field survey, namely RSS acquisition is carried out by special personnel at a large number of indoor positions, and a large amount of manpower and time are consumed. The fingerprint database built by the method has the positioning accuracy gradually reduced along with the time, namely the effectiveness of the fingerprint database is reduced. To this end, researchers have proposed model-based fingerprint estimation methods and crowd-sourced fingerprint collection methods.
Among them, the model-based fingerprint estimation method predicts RSS observations at different locations (instead of manually collecting) by using various signal propagation models, forms fingerprints, and builds a fingerprint library. The fingerprint collection method based on crowdsourcing aims at the indoor environment where a WiFi fingerprint positioning system needs to be deployed, automatic collection of RSS observation values is achieved through daily activities of staff in a building, position marking is conducted on crowdsourced fingerprints through combination of other position obtaining means (such as manual setting and a Pedestrian Dead Reckoning (PDR) algorithm), and therefore a fingerprint library can be established.
However, the data acquired by the prior art still has the problem of low data quality, namely, the timeliness, the integrity and the accuracy are insufficient, so that the quality of the established fingerprint database is low. Therefore, a fingerprint database construction method and device based on a mobile crowd sensing task model, which can greatly improve the data quality, are needed nowadays.
Disclosure of Invention
The invention aims to solve the problem of low data quality of acquired data in the prior art, and provides a fingerprint database construction method and equipment based on a mobile crowd sensing task model.
In order to achieve the above purpose, the invention provides the following technical scheme:
a fingerprint library construction method based on a mobile crowd sensing task model comprises the following steps:
s1: acquiring RSSI fingerprints through a mobile crowd sensing task model;
s2: establishing a fingerprint database according to the RSSI fingerprint;
the mobile crowd sensing task model consists of three parts, namely an object, a process and a rule;
the objects are:
{R(Hotspots1,Hotspots2,…,Hotspotsm),LR(Hotspots1,Hotspots2,…,Hotspotsm)}，
wherein, R (Hotspots)1,Hotspots2,…,Hotspotsm) Represents the RSSI fingerprint, LR (Hotspots) at each hotspot1,Hotspots2,…,Hotspotsm) Representing the relative position relationship between each hotspot;
the process is omega and satisfies the following conditions:
Figure BDA0003093942670000021
omega is the process sequence of the acquisition task, u is fego(MP(ui) Is a process unit, ftaskDescribing a model for a task event; f. ofprocessDescribing the model, MP (u), for a sequence of task processesi) For sensing node uiMoving pattern of fegoAccording to the movement pattern MP (u)i) Obtaining fingerprint sensing data;
the rule is a perception node uiMoving pattern MP (u)i) And satisfies the following conditions:
MP(ui)＝<(Hotspotsi1,ti1s,ti1e),(Hotspotsi2,ti2s,ti2e),…,(Hotspotsix,tixs,tixe)>，
among them, HotspotsixRepresenting a sensing node uiPassing through x Hotspots, tixsFor sensing node uiInto HotspotsxTime of location, tixeFor sensing node uiLeave HotspotsxTime of location, hotspot, is a hotspot. The invention formulates a task to carry out RSSI fingerprint acquisition through a process-oriented mobile crowd sensing task model, namely, the target required to be acquired by the sensing task is defined through the definition of the object without the position information of the target; meanwhile, the RSSI fingerprint is sampled and obtained in a static state according to a rule formulated by a motion state under the condition that the position information of the user cannot be obtained, and the position characteristic of the RSSI fingerprint can be described more accurately compared with the RSSI instantaneous value recorded in the motion state, so that the indoor positioning accuracy is improved, the integrity of the collected data is ensured, and the omission or the loss of the data is avoided; and the quality of the collected data is ensured by the process, so that the data quality is improved, and the quality of the fingerprint database is greatly improved.
As a preferred embodiment of the present invention, the moving mode MP (u)i) Also satisfies:
Figure BDA0003093942670000031
wherein y ∈ (1, x)]，ε1,ε2,ε3,ε4Is four preset time thresholds. In the construction process of the fingerprint database based on mobile crowd sensing, after a crowd sensing user receives a sensing task, a sensing terminal held by the crowd sensing user continuously and passively detects and records sensing data in the data acquisition process, data redundancy is easily caused, a large number of resources such as terminal storage are occupied, meanwhile, the terminal energy consumption of the user can be increased in the long-time acquisition process, and the participation enthusiasm of the crowd sensing user is obviously reduced. The invention passes four parameters (epsilon) defined1,ε2,ε3,ε4) The terminal energy consumption in the sampling process is reduced while the indoor positioning precision is ensured.
As a preferred embodiment of the present invention, the time threshold ε1∈[2min,3min]And the method is used for preventing the sampling time of the static phase from being too short to influence the accuracy of the RSSI fingerprint average value.
As a preferred embodiment of the present invention, the time threshold ε2∈[5min,10min]And the method is used for preventing the sampling time of the quiescent stage from being too long so as to consume too much terminal resources.
As a preferred embodiment of the present invention, the time threshold ε3The mobile crowd sensing terminal is used for ensuring that a mobile crowd sensing user is in a normal walking state and avoiding wandering or shaking the terminal in an area.
As a preferred embodiment of the present invention, the time threshold ε4∈[7min,10min]The method and the device are used for ensuring that the moving crowd sensing user moving range is in a neighboring area, and the influence of accumulated errors caused by overlarge moving range is avoided.
An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention formulates a task to carry out RSSI fingerprint acquisition through a process-oriented mobile crowd sensing task model, namely, the target required to be acquired by the sensing task is defined through the definition of the object without the position information of the target; meanwhile, the RSSI fingerprint is sampled and obtained in a static state according to a rule formulated by a motion state under the condition that the position information of the user cannot be obtained, and the position characteristic of the RSSI fingerprint can be described more accurately compared with the RSSI instantaneous value recorded in the motion state, so that the indoor positioning accuracy is improved, the integrity of the collected data is ensured, and the omission or the loss of the data is avoided; and the quality of the collected data is ensured by the process, so that the data quality is improved, and the quality of the fingerprint database is greatly improved.
2. In the process of constructing the fingerprint database based on the mobile crowd sensing, the crowd sensingAfter the user receives the sensing task, the sensing terminal continuously and passively detects and records the sensing data in the data acquisition process, data redundancy is easily caused, a large number of resources such as terminal storage are occupied, meanwhile, the terminal energy consumption of the user can be increased in the long-time acquisition process, and the participation enthusiasm of the crowd sensing user is obviously reduced. The invention passes four parameters (epsilon) defined1,ε2,ε3,ε4) The terminal energy consumption in the sampling process is reduced while the indoor positioning precision is ensured.
Drawings
Fig. 1 is a schematic flowchart of a fingerprint database construction method based on a mobile crowd sensing task model according to an embodiment of the present invention;
fig. 2 is an electronic device according to embodiment 3 of the present invention, which utilizes the method for constructing a fingerprint library based on a mobile crowd sensing task model according to embodiment 1.
Detailed Description
Compared with professional measurement persons, the non-professionalism of the mobile crowd sensing user in the field causes that the mobile crowd sensing user does not know when, where and what information is sensed, a sensing platform is required to define a sensing task first, and as a space-time data collection mode, a typical mobile crowd sensing model defines the quantity and position information of objects to be sensed clearly.
The definition of the task model is the core of mobile crowd sensing, the mobile crowd sensing task is application driven, and generally, a mobile crowd sensing task needs to contain text task description facing to participants and formalized task description facing to data selection. Text task descriptions are natural language descriptions of parameters such as data quantity, time range, geographical range, data acquisition type, acquisition requirements, etc., and are often used for explicit (participatory) perception. Formal task description is required in implicit (opportunistic) perception, and as the task requirements of each task such as acquisition target, data volume and acquisition mode are different and the form of each task is different, the formal task description is generally abstractly defined as a six-tuple: < BI, Ty, vlmn, cont, whn, whr >, wherein BI represents task basic information, generally non-functional attribute information, including task ID, task name, function description, creator, source, etc.; ty denotes the perceptual data type; vlmn represents the desired amount of perceptual data; cont denotes a supplementary description for the task; whn denotes the start-stop time of the task, i.e. the valid interval of the perceptual data timestamp; whr denotes the location of the perception object.
However, in the sensing task constructed by the indoor fingerprint database, due to the defect of the GPS signal in the indoor, the RSSI data and the location information thereof collected by the user as the mobile sensing node are difficult to determine, and the uncertainty of the number and the location of the sensing targets makes the current typical mobile crowd sensing task model difficult to directly apply. Considering that the process-driven model is a series of continuous process sets described for events, the temporal-spatial causal relationship of changes inside spatial objects is refined while the interrelationship between events is expressed. Therefore, the invention firstly abstracts the node perception data entity in the fingerprint database construction process into a space object, and then defines the concrete operation record of the perception task process on the change of the space object.
The present invention will be described in further detail with reference to test examples and specific embodiments. It should be understood that the scope of the above-described subject matter is not limited to the following examples, and any techniques implemented based on the disclosure of the present invention are within the scope of the present invention.
Example 1
As shown in fig. 1, a fingerprint database construction method based on a mobile crowd sensing task model includes the following steps:
s1: acquiring RSSI fingerprints through a mobile crowd sensing task model;
s2: establishing a fingerprint database according to the RSSI fingerprint;
the mobile crowd sensing task model can be described as a triple model composed of an Object (Object), a Process (Process) and a Rule (Rule), namely < Object, Process, Rule >.
The fingerprint sensing task model based on the task process encapsulates the space (entity) object, the process and the semantic rule together to form an object structure model, so that the mutual relation among the space (entity) object, the process and the semantic rule is completely described, meanwhile, sensing node motion state information is used for replacing sensing task position information in the task model, and unified description and expression of the space, time, events and attributes of the object constructed by the fingerprint database can be realized.
In the perception task of indoor fingerprint database construction, an Object (Object) is defined as { R (Hotspots)1,Hotspots2,…,Hotspotsm),LR(Hotspots1,Hotspots2,…,Hotspotsm)}，
Wherein, R (Hotspots)1,Hotspots2,…,Hotspotsm) Represents the RSSI fingerprint, LR (Hotspots) at each hotspot1,Hotspots2,…,Hotspotsm) Showing the relative position relationship between each hotspot, which is a hotspot.
Recording a specific fingerprint acquisition task Process (Process) as omega, recording an acquisition task Process sequence as omega, and recording a Process unit as u, then:
Figure BDA0003093942670000071
wherein u ═ fego(MP(ui))，ftaskDescribing the model for task events, fprocessDescribing the model, MP (u), for a sequence of task processesi) As a rule, in the present invention, a sensing node uiMoving pattern of fegoAccording to the indicated movement pattern MP (u)i) And obtaining fingerprint sensing data.
The rule in the mobile crowd sensing task model is a sensing node uiMoving pattern MP (u)i) Satisfies the following conditions:
1)MP(ui)＝<(Hotspotsi1,ti1s,ti1e),(Hotspotsi2,ti2s,ti2e),…,(Hotspotsix,tixs,tixe)>，
among them, HotspotsixRepresenting a sensing node uiPassing through x Hotspots, tixsFor sensing node uiInto HotspotsxTime of location, tixeFor sensing node uiLeave HotspotsxThe time of the location.
2) Compared with the RSSI instantaneous value recorded by the sensing node (sensing node) in the motion state, the average value of the RSSI instantaneous value in the static state sampling can describe the position characteristic of the RSSI fingerprint more accurately, so that the qualified sensing node u is subjected to the positioning and the positioning of the RSSI fingerprintiMoving pattern MP (u) of (sensing node)i) Further satisfies the following conditions:
ε1≤tiye-tiys≤ε2，
considering when sensing node uiAfter the (sensing node) moves beyond a certain distance, the accumulated error of the sensing equipment obviously influences the accuracy of the moving track, so that in order to avoid the influence of the accumulated error caused by the overlarge movement range, the qualified sensing node u is ensurediMoving pattern MP (u) of (sensing node)i) Two adjacent positions are within one proximity area, namely:
ε3≤tiys-ti(y-1)e≤ε4，
wherein y ∈ (1, x)]，ε1,ε2,ε3,ε4Is four preset time thresholds.
For mobile crowd sensing, after sensing data is collected by a sensing platform end, task requirements are contrastively analyzed, the data quality condition provided by a sensing node is determined according to timeliness, integrity, accuracy and the like of the data, the sensing data quality control is realized through a task allocation mechanism, and verification can be performed through the following steps:
1) data timeliness
In mobile crowd sensing, data timeliness includes two layers of meanings, firstly, a sensing platform hopes to continuously collect sensing data in a whole Request Time Window (RTW), and a User completes a sensing task in a User Time Window (UTW). Suppose that
Figure BDA0003093942670000081
Namely, it is
Figure BDA0003093942670000082
The time perception platform starts to issue a perception task vj，tj eEnding the collection of perception data;
Figure BDA0003093942670000083
i.e. sensing node uiIn that
Figure BDA0003093942670000084
Start-at-time perception task vjIn a
Figure BDA0003093942670000085
End of time task vjAnd upload the data. Obviously, UTW needs to cover RTW, i.e.
Figure BDA0003093942670000086
On the other hand, to speed up the collection of mobile sensing data, data timeliness is often defined to represent how timely it sends sensing data to a sensing platform within a specified sensing time. In particular, definition of v for perceptual tasks according to UTWjSensing node uiIn that
Figure BDA0003093942670000087
End of time task vjAnd upload the data, thus sensing the node uiFor perceptual task vjPerceptual data timeliness of
Figure BDA0003093942670000088
2) Data integrity
In mobile crowd sensing, the integrity of sensing data represents the total amount of sensing data acquired by the mobile crowd sensing. Suppose a sensing node uiAt perception task vjIn actual acquisition of the amount of sensed data as dijAccording to the definition of the mobile crowd sensing task, the expected sensing data quantity when the task demander publishes the task is vlmn, and the total data quantity d can be normalized at the momentijV lmn to quantify sensing node uiTo feelingAwareness task vjThe integrity of (c).
3) Data accuracy
In mobile crowd sensing, the accuracy of sensing data describes the degree of conformity of the sensing data with the actual situation. For perceptual task vjSensing node uiActually acquiring the perception data as dijAnd perceive task vjThe actual situation data is dj realAnd thus can be determined by the absolute error | dj real－dijI quantization perception node uiFor perception task vjThe accuracy of (2).
According to the definition of the mobile crowd sensing task to the sensing node, the sensing data quality requirement in the mobile crowd sensing is defined as qwThen q iswThe ideal value of (b) is shown by the following formula:
Figure BDA0003093942670000091
for fingerprint database construction based on mobile crowd sensing, firstly, the sensing platform end does not know the sensing data quantity vlmn and the sensing task vjActual situation data, the method thus defines a perception task vjAfter the end, the perception platform finally obtains the total quantity d of perception dataij totalThe data total d can be normalizedij/dij totalTo quantize the sensing node uiFor perception task vjThe integrity of (c). Defining perception platform end to obtain perception task v according to summary informationjThe actual situation data is dj realAnd thus can be determined by the absolute error | dj real－dijI quantization perception node uiFor perception task vjThe accuracy of (2). While moving crowd-sourcing aware data quality qwThe ideal value of (b) is shown by the following formula:
Figure BDA0003093942670000092
example 2
This embodiment is a specific implementation process of step S1 described in embodiment 1. Different from the traditional indoor positioning system which passively detects and records fingerprint data in the whole process of the mobile crowd sensing user terminal in the sampling process, the invention sets four states for the data acquisition terminal: (start, sleep, stop, finish) to ensure validity and accuracy of the collected fingerprint information.
The sampling process flow is as follows:
1) when the received motion state information S is 1, the data collection state terminal state is set to start, and the RSSI information is continuously detected and recorded at a lower frequency.
2) When the received motion state information S becomes 0 and a preset condition is satisfied, the state of the data acquisition terminal is maintained at start.
3) When the received motion state information S becomes 1 again and the preset condition is satisfied, the data collection terminal state is maintained as finish. The position fingerprint D acquired and recorded in the whole processtAre all stored in the data acquisition terminal and the sampling process is ended.
Meanwhile, in the sampling process, the state of the data acquisition terminal is set to stop when the following conditions are met, the sampling process is immediately stopped at the moment, and the sampling data recorded in the current cache is cleared:
1) the duration of the static state of the data acquisition terminal is less than the parameter epsilon1I.e. T (S ═ 1) < ε1。
2) The duration time of the motion state of the data acquisition terminal is less than the parameter epsilon3Or greater than the parameter ε4I.e. T (S ═ 0) < ε3Or T (S ═ 0) > epsilon4。
In practice, it is found that the activities of users are often concentrated in a fixed area in a short period and have certain repeatability, and this characteristic can bring serious hidden trouble to the user terminal sampling, that is, the system is frequently switched between a stop state and a start state, and meanwhile, the measurement is repeatedly concentrated in a small area, so that the efficiency is low and the terminal resources are wasted. Therefore, the invention introduces a random rollback mechanism, closes the data acquisition terminal after the module enters a stop state and a finish state, and restarts after a period of random time. Practice shows that the random time can be randomly selected within 20-30 minutes in general.
In addition, considering that the improvement effect of the RSSI mean value is limited by overlong time sampling in a static state and the consumption of resources such as terminal energy consumption is increased, the invention defines a sleep state to solve the defects. In the sleep state, the data acquisition terminal state suspends the search of the RSSI information until the received motion state information S becomes 0, and at this time, unlike the stop state, the sampled data recorded in the current cache is retained and cannot be cleared. The sleep state triggering conditions set by the invention are as follows: t (S ═ 1) > epsilon2。
As described above, the present invention passes four parameters (ε) defined during the process of mobile crowd sensing fingerprinting1,ε2,ε3,ε4) The terminal energy consumption in the sampling process is reduced while the indoor positioning precision is ensured. The specific roles and suggested value ranges for the four parameter settings are shown in Table 1, and overall, the parameter ε1，ε2The method is used for ensuring that RSSI information recorded in the fingerprint database in a terminal static state is used for improving the accuracy of the position fingerprint, and the parameter epsilon3，ε4The method and the device ensure that the path information among the RSSI fingerprints recorded in the fingerprint database is limited within a certain time so as to reduce the accumulated error and improve the accuracy of the path information. The value range suggested in table 1 is obtained by engineering practice, and specific values may fluctuate according to different positioning scenes.
Table 1 function and value range of data acquisition and control submodule acquisition parameter setting
Figure BDA0003093942670000111
Figure BDA0003093942670000121
Meanwhile, specific operations performed in four states set with respect to the data acquisition terminal and trigger conditions thereof are shown in table 2.
TABLE 2 data acquisition and control submodule State setup Specification
Figure BDA0003093942670000122
In summary, from the viewpoint of motion state information, a successful complete sampling process includes 3 flows "still-motion-still". Thus for the successful sampling a, its recorded state information sequence (S)a) Can be expressed as (S)a)＝(Sa1,Sa2,Sa3) In which S isa1And Sa3The state information sequences, S, representing two static state records respectivelya2A sequence of state information representing a record of a state of motion. It is obvious that Sa1And Sa3Wherein the values of the elements are all 1, Sa2The values of the elements in (1) are all 0.
Example 3
As shown in fig. 2, an electronic device includes at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for building a fingerprint library based on a mobile crowd sensing task model according to the foregoing embodiments. The input and output interface can comprise a display, a keyboard, a mouse and a USB interface and is used for inputting and outputting data; the power supply is used for supplying electric energy to the electronic equipment.
Those skilled in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
When the integrated unit of the present invention is implemented in the form of a software functional unit and sold or used as a separate product, it may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (7)

1. A fingerprint database construction method based on a mobile crowd sensing task model is characterized in that,
s1: acquiring RSSI fingerprints through a process-oriented mobile crowd sensing task model;
s2: establishing a fingerprint database according to the RSSI fingerprint;
wherein the mobile crowd sensing task model consists of three parts of an object, a process and a rule,
the objects are:
{R(Hotspots1,Hotspots2,…,Hotspotsm),LR(Hotspots1,Hotspots2,…,Hotspotsm)}，
wherein, R (Hotspots)1,Hotspots2,…,Hotspotsm) Represents the RSSI fingerprint, LR (Hotspots) at each hotspot1,Hotspots2,…,Hotspotsm) Representing the relative position relationship between each hotspot;
the process is omega and satisfies the following conditions:
Figure FDA0003093942660000011
omega is the process sequence of the acquisition task, u is fego(MP(ui) Is a process unit, ftaskDescribing a model for a task event; f. ofprocessDescribing the model, MP (u), for a sequence of task processesi) For sensing node uiMoving pattern of fegoAccording to the movement pattern MP (u)i) Obtaining fingerprint sensing data;
the rule is a perception node uiMoving pattern MP (u)i) And satisfies the following conditions:
MP(ui)＝<(Hotspotsi1,ti1s,ti1e),(Hotspotsi2,ti2s,ti2e),…,(Hotspotsix,tixs,tixe)>，
among them, HotspotsixRepresenting a sensing node uiPassing through x Hotspots, tixsFor sensing node uiInto HotspotsxTime of location, tixeFor sensing node uiLeave HotspotsxTime of location, hotspot, is a hotspot.
2. The method as claimed in claim 1, wherein the mobile MP (u) is a mobile MP (u)i) Also satisfies:
Figure FDA0003093942660000012
wherein y ∈ (1, x)]，ε1,ε2,ε3,ε4Is four preset time thresholds.
3. The method as claimed in claim 2, wherein the time threshold epsilon is set according to the fingerprint library construction method based on the mobile crowd sensing task model1∈[2min,3min]Is used forThe sampling time in the static phase is prevented from being too short to influence the accuracy of the RSSI fingerprint average value.
4. The method as claimed in claim 2, wherein the time threshold epsilon is set according to the fingerprint library construction method based on the mobile crowd sensing task model2∈[5min,10min]And the method is used for preventing the sampling time of the quiescent stage from being too long so as to consume too much terminal resources.
5. The method as claimed in claim 2, wherein the time threshold epsilon is set according to the fingerprint library construction method based on the mobile crowd sensing task model3The mobile crowd sensing terminal is used for ensuring that a mobile crowd sensing user is in a normal walking state and avoiding wandering or shaking the terminal in an area.
6. The method as claimed in claim 2, wherein the time threshold epsilon is set according to the fingerprint library construction method based on the mobile crowd sensing task model4∈[7min,10min]The method and the device are used for ensuring that the moving crowd sensing user moving range is in a neighboring area, and the influence of accumulated errors caused by overlarge moving range is avoided.
7. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.
CN202110605466.4A 2021-05-31 2021-05-31 Fingerprint library construction method and device based on mobile crowd sensing task model Active CN113347563B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110605466.4A CN113347563B (en) 2021-05-31 2021-05-31 Fingerprint library construction method and device based on mobile crowd sensing task model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110605466.4A CN113347563B (en) 2021-05-31 2021-05-31 Fingerprint library construction method and device based on mobile crowd sensing task model

Publications (2)

Publication Number Publication Date
CN113347563A true CN113347563A (en) 2021-09-03
CN113347563B CN113347563B (en) 2021-12-07

Family

ID=77473645

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110605466.4A Active CN113347563B (en) 2021-05-31 2021-05-31 Fingerprint library construction method and device based on mobile crowd sensing task model

Country Status (1)

Country Link
CN (1) CN113347563B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114118843A (en) * 2021-12-01 2022-03-01 东南大学 Mobile crowd sensing task allocation method based on Monte Carlo position fingerprints
CN116184312A (en) * 2022-12-22 2023-05-30 泰州雷德波达定位导航科技有限公司 Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140018096A1 (en) * 2012-07-16 2014-01-16 Aisle411, Inc. System and method for indoor location mapping and tracking
WO2015009498A1 (en) * 2013-07-19 2015-01-22 Qualcomm Incorporated Indoor location fraud prevention and security and privacy
US20160189416A1 (en) * 2014-12-30 2016-06-30 Qualcomm Incorporated Maintaining heatmaps using tagged visual data
CN105979580A (en) * 2016-06-22 2016-09-28 广东工业大学 Residential area route map forming system and method based on crowd sensing network
CN106358233A (en) * 2016-08-24 2017-01-25 哈尔滨工业大学 RSS data flatting method based on multi-dimension analysis algorithm
CN109803225A (en) * 2019-03-13 2019-05-24 温州职业技术学院 A kind of power-economizing method applied to mobile gunz sensing network node
CN110072183A (en) * 2019-03-14 2019-07-30 天津大学 Passive type location fingerprint base construction method based on intelligent perception
CN110856112A (en) * 2019-11-14 2020-02-28 深圳先进技术研究院 Crowd-sourcing perception multi-source information fusion indoor positioning method and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140018096A1 (en) * 2012-07-16 2014-01-16 Aisle411, Inc. System and method for indoor location mapping and tracking
WO2015009498A1 (en) * 2013-07-19 2015-01-22 Qualcomm Incorporated Indoor location fraud prevention and security and privacy
US20160189416A1 (en) * 2014-12-30 2016-06-30 Qualcomm Incorporated Maintaining heatmaps using tagged visual data
CN105979580A (en) * 2016-06-22 2016-09-28 广东工业大学 Residential area route map forming system and method based on crowd sensing network
CN106358233A (en) * 2016-08-24 2017-01-25 哈尔滨工业大学 RSS data flatting method based on multi-dimension analysis algorithm
CN109803225A (en) * 2019-03-13 2019-05-24 温州职业技术学院 A kind of power-economizing method applied to mobile gunz sensing network node
CN110072183A (en) * 2019-03-14 2019-07-30 天津大学 Passive type location fingerprint base construction method based on intelligent perception
CN110856112A (en) * 2019-11-14 2020-02-28 深圳先进技术研究院 Crowd-sourcing perception multi-source information fusion indoor positioning method and system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
NING YU 等: "A Radio-Map Automatic Construction Algorithm Based on Crowdsourcing", 《SENSOR》 *
刘康伟: "基于群智感知的位置指纹库构建算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
陈荟慧: "面向移动群智感知的高质量数据收集方法研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114118843A (en) * 2021-12-01 2022-03-01 东南大学 Mobile crowd sensing task allocation method based on Monte Carlo position fingerprints
CN114118843B (en) * 2021-12-01 2024-04-30 东南大学 Mobile crowd sensing task allocation method based on Monte Carlo position fingerprint
CN116184312A (en) * 2022-12-22 2023-05-30 泰州雷德波达定位导航科技有限公司 Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi
CN116184312B (en) * 2022-12-22 2023-11-21 泰州雷德波达定位导航科技有限公司 Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi

Also Published As

Publication number Publication date
CN113347563B (en) 2021-12-07

Similar Documents

Publication Publication Date Title
CN113347563B (en) Fingerprint library construction method and device based on mobile crowd sensing task model
Wang et al. Vision-based framework for automatic progress monitoring of precast walls by using surveillance videos during the construction phase
EP3643017B1 (en) Structured schema for temporal graph storage and retrieval
CN106202528B (en) Information processing apparatus, information processing method, and computer program
JP7032408B2 (en) Site detection
US8665743B2 (en) User behavior model and statistical transition map to assist advanced WLAN applications
WO2019185039A1 (en) A data processing method and electronic apparatus
CN109560989B (en) Link monitoring system
CN110351662B (en) Method, platform and device for end cloud cooperation
CN111523167A (en) BIM model generation method, device, equipment and storage medium
US10034144B2 (en) Application and situation-aware community sensing
CN114610588A (en) Database performance analysis method and device, electronic equipment and storage medium
Fazzinga et al. Exploiting integrity constraints for cleaning trajectories of RFID-monitored objects
CN111721312B (en) Running track generation method and device
CN111475877A (en) Method, device and terminal for measuring and calculating space clear height based on BIM technology
US20190197029A1 (en) Methods, systems and apparatus to improve spatial-temporal data management
CN113779261A (en) Knowledge graph quality evaluation method and device, computer equipment and storage medium
CN110472192B (en) Evaluation index extraction method, evaluation index extraction device, storage medium, and server
JP6926978B2 (en) Parameter estimator, trip predictor, method, and program
CN103577499A (en) Integrated intelligent spatial comprehensive information platform
CN116167582A (en) Intelligent construction progress monitoring system based on BIM technology
Sasaki et al. Thematic geo-density heatmapping for walking tourism analytics using semi-ready GPS trajectories
Goyal et al. Smartphone context event sequence prediction with poermh and tke-rules algorithms
CN113283669A (en) Intelligent planning travel investigation method and system combining initiative and passive
US20210219159A1 (en) Information processing apparatus, information processing system, information processing method, and program

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