CN113553516A - Frequent track mining method based on fuzzy path - Google Patents
Frequent track mining method based on fuzzy path Download PDFInfo
- Publication number
- CN113553516A CN113553516A CN202111097900.9A CN202111097900A CN113553516A CN 113553516 A CN113553516 A CN 113553516A CN 202111097900 A CN202111097900 A CN 202111097900A CN 113553516 A CN113553516 A CN 113553516A
- Authority
- CN
- China
- Prior art keywords
- frequent
- prefix
- track
- threshold value
- mining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
- G06F16/24566—Recursive queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
Abstract
The invention discloses a fuzzy path-based frequent trajectory mining method, and particularly relates to the technical field of big data mining, which comprises the steps of segmenting collected space-time data, segmenting original space-time data into a plurality of trajectories according to a time interval larger than a threshold t, refining the original site serial numbers 1, 2 and 3 into detailed information containing time and trajectory longitude and latitude on the basis of prefix processing of a frequent item set, taking the gravity center position of a fuzzy trajectory as real trajectory information according to the longitude and latitude, screening a support threshold after replacing the original position information, and outputting the frequent trajectory of which the support degree of a target in a data period is larger than the threshold after inputting the space-time data of the target identity. The method overcomes the limitation that the conventional frequent sequence mining algorithm cannot process fuzzy track data, and solves the problem of low applicability when the classical frequent sequence mining is used for mining the frequent path of the fuzzy track.
Description
Technical Field
The invention relates to the technical field of big data mining, in particular to a frequent trajectory mining method based on a fuzzy path.
Background
With the development of wireless communication and positioning technology, mobile devices including a GPS are widely popularized (for example, mobile phones, pads, smart bands, automobiles, and the like), and a large amount of trajectory data can be conveniently acquired from a positioning terminal. The track data is a series of position sets with time marks arranged in sequence, records the activity rule of the mobile object in the real world, and reflects the behavior pattern of the mobile object, such as several preferred routes of the mobile object, the sequence of frequently visited places, and the like. Mining track patterns of interest from track data has attracted a great deal of attention from expert scholars. Among these, the spatio-temporal frequent trajectory pattern mining is one of the most interesting types in the trajectory data research, and represents a pattern or behavior in which a moving object is detected frequently from the historical trajectory data. By analyzing the track data, the behavior rules and the moving modes of the moving objects are found, and valuable information is provided for the field using the position service as guidance, such as useful information for the fields of position-based travel recommendation, advertisement recommendation, traffic management, navigation optimization, shared bicycle and shared automobile launching site selection.
In order to mine the main activity rule of the target to the user, the classical prefixSpan algorithm exists in the direction at present. Prefix span is an algorithm for mining frequent sequences in a dataset based on a single-dimensional dataset and a support threshold α. But when the position we obtained is not the exact position of the target, it is not possible to obtain the frequent trajectory of the target based on the fuzzy path. If we know the base station connection data of the target mobile phone now, we can know the accurate position of the base station connected by the mobile phone of the target at a certain moment, but we do not know the real accurate position of the target, and there is a certain deviation in the middle, and there may be a situation that the base station connected by the mobile phone is different at different moments when the same target is at the same site. The conventional algorithm cannot meet the requirement of frequent item mining of fuzzy tracks.
Disclosure of Invention
Therefore, the invention provides a fuzzy path-based frequent trajectory mining method, which can output frequent trajectories with the support degree of the target in a data time period larger than a threshold value after inputting the spatio-temporal data of the target identity, overcomes the limitation that the conventional frequent sequence mining algorithm cannot process fuzzy trajectory data, improves the applicability of the fuzzy trajectory in frequent trajectory mining, and solves the problem of frequent trajectory mining when the target path is unclear in the prior art.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions: a frequent track mining method based on fuzzy paths comprises the following steps:
the method comprises the following steps that firstly, collected space-time data are segmented, and original space-time data are segmented into a plurality of tracks according to the time interval greater than a threshold value t;
step two, setting a sequence data set D, a support degree threshold value alpha, a duplicate removal time interval threshold value delta T, a same track point time interval threshold value delta T and a same track point linear distance threshold value delta m according to the plurality of tracks segmented in the step one;
step three, carrying out duplicate removal on each sub-track in the sequence data set D: continuously acquiring at the same station twice or more, and only keeping the first acquisition record when the time difference from the first record is less than a set threshold value delta T;
step four, defining a variable k, defining the length of the prefix by using the variable k, then initializing the k, setting the initialization value of the k to be 1, and finding out all prefixes with the lengths of k and corresponding projection databases S;
counting prefixes with the length of 1, wherein the track points with the linear distance of the longitude and latitude of the station within delta m and the time difference within delta t are regarded as the same prefix, the gravity center points of a plurality of track points are used as new tracks to replace the original track points, the corresponding prefixes are also replaced, items corresponding to the prefixes with the support degree lower than the threshold value alpha are deleted from the data set S, and all the sequences of 1 frequent item are obtained;
step six, judging whether the frequent sequence obtained in the step five is an empty set, if so, executing the step eight, otherwise, executing the step seven;
step seven, performing recursive mining on each prefix which has the length of k +1 and meets the requirement of the support degree;
and step eight, outputting all frequent sequence sets to a disk.
Further, the specific operation of searching for the prefix in step four includes: s41: initializing i to 1; s42: processing the ith track in the data set D; initializing j to 1, taking a first position point in the sequence D (i) as a first prefix, wherein a subsequence with a backward prefix is a corresponding prefix projection; s43: if j is less than the sequence length, using the j position point in the sequence as the first prefix, and the subsequence with the backward prefix is the corresponding prefix projection, otherwise executing S44; s44: i +1, if i is less than the length of D, performing S42, otherwise, performing S45; s45: and outputting all prefixes with the length of 1 and corresponding prefix projections.
Further, the mining operation of the prefix in the step five specifically includes: s51: forming a one-dimensional tensor M by the time corresponding to the prefixes with the same sites, wherein if n sites exist, n elements exist in the M; s52: initializing i to 1, and starting to process the first element L in the tensor; s53: finding out two elements Time1 and Time2 with the minimum Time difference in L, if abs (Time1-Time2) < delta t, combining Time1 and Time2 into a group, replacing the original Time1 and Time2 with the mean value, entering step S54, and otherwise, exiting step V; s54: finding out two elements of Time3, Time4, Time3 and Time4 with the smallest Time difference in L, wherein the original groups of the two elements are List3 and List4, if abs (max (List3) -min (List4)) < delta t and abs (max (List3) -min (List4)) < delta t, combining Time3 and Time4 into a group, replacing the original Time3 and Time4 with the average value, repeating S53, and otherwise, exiting S54 and executing S55; s55: deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set; s56: if i is less than the length of tensor M, starting to process the ith element L in the tensor, executing step S53, otherwise executing step S57; s57: combining the candidate prefix sets of all the sites, and constructing a key-value pair set by taking the prefixes as keys and taking the occurrence times of the prefixes as values; s58: and deleting the items corresponding to the prefixes with the support degrees lower than the threshold value alpha from the set to obtain all frequent 1 sequences.
Further, the concrete operation of recursive mining in step seven includes: s71: initializing a frequent track with the length of k into a prefix with frequent k +1 items; s72: initializing i to 1; s73: judging the position of the ith k-frequent track in all tracks, and constructing a k +1 frequent track; s74: i is i + 1; if i is less than the number of k-frequent trace item sets, executing the step S73, otherwise, executing the step S74; s75: counting the occurrence times of k +1 frequent tracks; s76: and deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set.
The invention has the following advantages:
according to the invention, on the prefix processing of a frequent item set, the original site serial numbers 1, 2 and 3 are refined into detailed information containing time and track longitude and latitude, the gravity center position of a fuzzy track is taken as real track information according to the longitude and latitude, the original position information is replaced, then the screening of a support threshold is carried out, after the space-time data of a target identity is input, the frequent track with the support of the target being greater than the threshold in a data time period can be output, the limitation that the fuzzy track data cannot be processed by the conventional frequent sequence mining algorithm is overcome, the problem that the application is lower when the classical frequent sequence mining is used for mining the frequent path of the fuzzy track is solved, compared with the prior art, the frequent track mining can be carried out when the target path is unclear, and the applicability of the fuzzy track mining method is wider.
Drawings
FIG. 1 is a flow chart provided by the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to the specification and the attached fig. 1, the method for mining the frequent trace based on the fuzzy path of the embodiment includes the following steps:
the method comprises the steps that firstly, collected space-time data are segmented, original space-time data are segmented into a plurality of tracks according to the time interval larger than a threshold value T, a sequence data set D is formed, and the sequence data set D, a support degree threshold value alpha, a duplicate removal time interval threshold value delta T, a same track point time interval threshold value delta T and a same track point linear distance threshold value delta m are set according to the segmented tracks;
step two, acquiring a sequence data set D, a support degree threshold value alpha, a duplicate removal time interval threshold value delta T, a same track point time interval threshold value delta T and a same track point linear distance threshold value delta m according to the set values in the step one;
step three, carrying out duplicate removal on each sub-track in the sequence data set D: when the same station is continuously acquired twice or more than twice and the time difference from the first recording is smaller than a set threshold value delta T, only the first acquisition record is reserved, and the specific calculation is as follows: setting the track of a certain day as follows: < (time1, time1, long 1), (time2, time2, long 2), (time3, time3, long 3), (time4, time3, long 3), (time5, time4, long 4) >, if time4-time3< Δ T, then the collection record for time4 needs to be deleted, so the trajectory after deduplication is: < (time1, latitude1, longtude 1), (time2, latitude2, longtude 2), (time3, latitude3, longtude 3), (time5, latitude4, longtude 4) >;
step four, defining a variable k, defining the length of the prefix by using the variable k, then initializing the k, setting the initialization value of the k to be 1, and finding out all prefixes with the lengths of k and corresponding projection databases S, wherein the specific operation of searching the prefixes comprises the following steps: s41: initializing i to 1; s42: processing the ith track in the data set D; initializing j to 1, taking a first position point in the sequence D (i) as a first prefix, wherein a subsequence with a backward prefix is a corresponding prefix projection; s43: if j is less than the sequence length, using the j position point in the sequence as the first prefix, and the subsequence with the backward prefix is the corresponding prefix projection, otherwise executing S44; s44: i +1, if i is less than the length of D, performing S42, otherwise, performing S45; s45: outputting all prefixes with the length of 1 and prefix projections corresponding to the prefixes;
counting prefixes with the length of 1, wherein the track points with the linear distance of the longitude and latitude of the station within delta m and the time difference within delta t are regarded as the same prefix, the gravity center points of a plurality of track points are used as new tracks to replace the original track points, the corresponding prefixes are also replaced, items corresponding to the prefixes with the support degrees lower than the threshold value alpha are deleted from the data set S, and meanwhile, all the sequences of 1 frequent items are obtained, and the specific calculation is as follows: setting a track segmentation sequence of a certain period of time as
<(time1,latitude1,longitude1),(time2,latitude2,longitude2)>,<(time3,latitude3,longitude3) ,(time4,latitude4,longitude4)>，
If the following formula is satisfied
Then the two sequences exist 1 item set frequently, and the two sites < latitude1, longtude 1>, < latitude3, longtude 3> can be calculated to have the center of gravity of < (latitude1+ latitude3)/2, (longtude 1+ longtude 3)/2) >, then the prefix with length 1 is < (latitude1+ latitude3)/2, (longtude 1+ longtude 3)/2) >;
the prefix mining operation specifically comprises the following steps:
s51: forming a one-dimensional tensor M by the time corresponding to the prefixes with the same sites, wherein if n sites exist, n elements exist in the M;
s52: initializing i to 1, and starting to process the first element L in the tensor;
s53: finding out two elements Time1 and Time2 with the minimum Time difference in L, if abs (Time1-Time2) < delta t, combining Time1 and Time2 into a group, replacing the original Time1 and Time2 with the mean value, entering step S54, and otherwise, exiting step V;
s54: finding out two elements of Time3, Time4, Time3 and Time4 with the smallest Time difference in L, wherein the original groups of the two elements are List3 and List4, if abs (max (List3) -min (List4)) < delta t and abs (max (List3) -min (List4)) < delta t, combining Time3 and Time4 into a group, replacing the original Time3 and Time4 with the average value, repeating S53, and otherwise, exiting S54 and executing S55;
s55: deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set;
s56: if i is less than the length of tensor M, starting to process the ith element L in the tensor, executing step S53, otherwise executing step S57;
s57: combining the candidate prefix sets of all the sites, and constructing a key-value pair set by taking the prefixes as keys and taking the occurrence times of the prefixes as values;
s58: deleting the items corresponding to the prefixes with the support degrees lower than the threshold value alpha from the set to obtain all frequent 1 sequences;
step six, judging whether the frequent sequence obtained in the step five is an empty set, if so, executing the step eight, otherwise, executing the step seven;
step seven, performing recursive mining on each prefix which has the length of k +1 and meets the requirement of the support degree, wherein the specific operation of the recursive mining comprises the following steps: s71: initializing a frequent track with the length of k into a prefix with frequent k +1 items; s72: initializing i to 1; s73: judging the position of the ith k-frequent track in all tracks, and constructing a k +1 frequent track; s74: i is i + 1; if i is less than the number of k-frequent trace item sets, executing the step S73, otherwise, executing the step S74; s75: counting the occurrence times of k +1 frequent tracks; s76: deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set;
and step eight, outputting all frequent sequence sets to a disk.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (4)
1. A frequent track mining method based on fuzzy paths is characterized in that: the method comprises the following steps:
the method comprises the following steps that firstly, collected space-time data are segmented, and original space-time data are segmented into a plurality of tracks according to the time interval greater than a threshold value t;
step two, setting a sequence data set D, a support degree threshold value alpha, a duplicate removal time interval threshold value delta T, a same track point time interval threshold value delta T and a same track point linear distance threshold value delta m according to the plurality of tracks segmented in the step one;
step three, carrying out duplicate removal on each sub-track in the sequence data set D: continuously acquiring at the same station twice or more, and only keeping the first acquisition record when the time difference from the first record is less than a set threshold value delta T;
step four, defining a variable k, defining the length of the prefix by using the variable k, then initializing the k, setting the initialization value of the k to be 1, and finding out all prefixes with the lengths of k and corresponding projection databases S;
counting prefixes with the length of 1, wherein the track points with the linear distance of the longitude and latitude of the station within delta m and the time difference within delta t are regarded as the same prefix, the gravity center points of a plurality of track points are used as new tracks to replace the original track points, the corresponding prefixes are also replaced, items corresponding to the prefixes with the support degree lower than the threshold value alpha are deleted from the data set S, and all the sequences of 1 frequent item are obtained;
step six, judging whether the frequent sequence obtained in the step five is an empty set, if so, executing the step eight, otherwise, executing the step seven;
step seven, performing recursive mining on each prefix which has the length of k +1 and meets the requirement of the support degree;
and step eight, outputting all frequent sequence sets to a disk.
2. The fuzzy path-based frequent trace mining method according to claim 1, wherein: the specific operation of searching the prefix in the step four comprises the following steps: s41: initializing i to 1; s42: processing the ith track in the data set D; initializing j to 1, taking a first position point in the sequence D (i) as a first prefix, wherein a subsequence with a backward prefix is a corresponding prefix projection; s43: if j is less than the sequence length, using the j position point in the sequence as the first prefix, and the subsequence with the backward prefix is the corresponding prefix projection, otherwise executing S44; s44: i +1, if i is less than the length of D, performing S42, otherwise, performing S45; s45: and outputting all prefixes with the length of 1 and corresponding prefix projections.
3. The fuzzy path-based frequent trace mining method according to claim 1, wherein: the mining operation of the prefix in the step five specifically comprises the following steps: s51: forming a one-dimensional tensor M by the time corresponding to the prefixes with the same sites, wherein if n sites exist, n elements exist in the M; s52: initializing i to 1, and starting to process the first element L in the tensor; s53: finding out two elements Time1 and Time2 with the minimum Time difference in L, if abs (Time1-Time2) < delta t, combining Time1 and Time2 into a group, replacing the original Time1 and Time2 with the mean value, entering step S54, and otherwise, exiting step V; s54: finding out two elements of Time3, Time4, Time3 and Time4 with the smallest Time difference in L, wherein the original groups of the two elements are List3 and List4, if abs (max (List3) -min (List4)) < delta t and abs (max (List3) -min (List4)) < delta t, combining Time3 and Time4 into a group, replacing the original Time3 and Time4 with the average value, repeating S53, and otherwise, exiting S54 and executing S55; s55: deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set; s56: if i is less than the length of tensor M, starting to process the ith element L in the tensor, executing step S53, otherwise executing step S57; s57: combining the candidate prefix sets of all the sites, and constructing a key-value pair set by taking the prefixes as keys and taking the occurrence times of the prefixes as values; s58: and deleting the items corresponding to the prefixes with the support degrees lower than the threshold value alpha from the set to obtain all frequent 1 sequences.
4. The fuzzy path-based frequent trace mining method according to claim 1, wherein: the concrete operation of the recursive mining in the step seven comprises the following steps: s71: initializing a frequent track with the length of k into a prefix with frequent k +1 items; s72: initializing i to 1; s73: judging the position of the ith k-frequent track in all tracks, and constructing a k +1 frequent track; s74: i is i + 1; if i is less than the number of k-frequent trace item sets, executing the step S73, otherwise, executing the step S74; s75: counting the occurrence times of k +1 frequent tracks; s76: and deleting all candidate sets lower than the support degree threshold value alpha to obtain a candidate prefix set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111097900.9A CN113553516A (en) | 2021-09-18 | 2021-09-18 | Frequent track mining method based on fuzzy path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111097900.9A CN113553516A (en) | 2021-09-18 | 2021-09-18 | Frequent track mining method based on fuzzy path |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113553516A true CN113553516A (en) | 2021-10-26 |
Family
ID=78106388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111097900.9A Pending CN113553516A (en) | 2021-09-18 | 2021-09-18 | Frequent track mining method based on fuzzy path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553516A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432879A (en) * | 2023-04-03 | 2023-07-14 | 山东诺控智能科技有限公司 | Emergency lighting and evacuation indicating system |
| CN116432879B (en) * | 2023-04-03 | 2024-04-23 | 山东诺控智能科技有限公司 | Emergency lighting and evacuation indicating system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160070763A1 (en) * | 2013-05-31 | 2016-03-10 | Teradata Us, Inc. | Parallel frequent sequential pattern detecting |
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN111078754A (en) * | 2019-12-19 | 2020-04-28 | 南京柏跃软件有限公司 | Frequent trajectory extraction method based on massive space-time data and mining system thereof |
| CN113341719A (en) * | 2021-06-15 | 2021-09-03 | 上海应用技术大学 | AGV trajectory tracking control method integrating TEB algorithm and fuzzy control |
-
2021
- 2021-09-18 CN CN202111097900.9A patent/CN113553516A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160070763A1 (en) * | 2013-05-31 | 2016-03-10 | Teradata Us, Inc. | Parallel frequent sequential pattern detecting |
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN111078754A (en) * | 2019-12-19 | 2020-04-28 | 南京柏跃软件有限公司 | Frequent trajectory extraction method based on massive space-time data and mining system thereof |
| CN113341719A (en) * | 2021-06-15 | 2021-09-03 | 上海应用技术大学 | AGV trajectory tracking control method integrating TEB algorithm and fuzzy control |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432879A (en) * | 2023-04-03 | 2023-07-14 | 山东诺控智能科技有限公司 | Emergency lighting and evacuation indicating system |
| CN116432879B (en) * | 2023-04-03 | 2024-04-23 | 山东诺控智能科技有限公司 | Emergency lighting and evacuation indicating system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| Senaratne et al. | Urban mobility analysis with mobile network data: A visual analytics approach | |
| CN106912015B (en) | Personnel trip chain identification method based on mobile network data | |
| Mao et al. | Feature grouping-based outlier detection upon streaming trajectories | |
| Yuan et al. | Measuring similarity of mobile phone user trajectories–a Spatio-temporal Edit Distance method | |
| CN112182410B (en) | User travel mode mining method based on space-time track knowledge graph | |
| CN107679558A (en) | A kind of user trajectory method for measuring similarity based on metric learning | |
| CN109459045B (en) | Improved interactive voting matching method for low-frequency GPS track | |
| CN109948701B (en) | Data clustering method based on space-time correlation among tracks | |
| CN104850604A (en) | Tensor-based user track mining method | |
| CN108882172B (en) | Indoor moving trajectory data prediction method based on HMM model | |
| CN108986453A (en) | A kind of traffic movement prediction method based on contextual information, system and device | |
| CN111046968B (en) | Road network track clustering analysis method based on improved DPC algorithm | |
| CN105912683B (en) | A kind of chronologically-based path matching method | |
| CN108153867A (en) | User trajectory Forecasting Methodology and device based on temporal regularity | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| CN111292356B (en) | Method and device for matching motion trail with road | |
| CN111307164A (en) | Low-sampling-rate track map matching method | |
| CN111475746B (en) | Point-of-interest mining method, device, computer equipment and storage medium | |
| Zhang et al. | Transfer learning-based outdoor position recovery with cellular data | |
| CN113807457A (en) | Method, device and equipment for determining road network characterization information and storage medium | |
| CN115687429A (en) | Social media user behavior pattern mining method | |
| CN112765120A (en) | Method for analyzing and extracting user movement track based on mobile phone signaling | |
| CN112579922A (en) | Interest point recommendation method based on user track | |
| CN113553516A (en) | Frequent track mining method based on fuzzy path |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211026 |