WO2019042275A1 - 目标区域范围内的移动模式的确定方法及电子设备 - Google Patents

目标区域范围内的移动模式的确定方法及电子设备 Download PDF

Info

Publication number
WO2019042275A1
WO2019042275A1 PCT/CN2018/102673 CN2018102673W WO2019042275A1 WO 2019042275 A1 WO2019042275 A1 WO 2019042275A1 CN 2018102673 W CN2018102673 W CN 2018102673W WO 2019042275 A1 WO2019042275 A1 WO 2019042275A1
Authority
WO
WIPO (PCT)
Prior art keywords
moving
sequence
movement
sub
mode
Prior art date
Application number
PCT/CN2018/102673
Other languages
English (en)
French (fr)
Inventor
王新珩
内择瑞安汗择⋅伊雷
陈涛
Original Assignee
知谷（上海）网络科技有限公司
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 知谷（上海）网络科技有限公司 filed Critical 知谷（上海）网络科技有限公司
Publication of WO2019042275A1 publication Critical patent/WO2019042275A1/zh

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
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases

Definitions

  • the present invention relates to the field of geographic information technology, and in particular, to a method for determining a mobile mode within a target area and an electronic device.
  • the mining and prediction of mobile behavior has a very broad application prospect.
  • resources can be efficiently allocated to the region where the target is most likely to go, rather than blind resource allocation. Efficient allocation of resources will result in higher resource utilization and lower latency for accessing resources.
  • predicting subsequent locations can provide insight into many existing broad applications, such as targeted advertising and service recommendations.
  • the method of mobile behavior prediction is generally based on mobile mode prediction.
  • the movement of the target does not occur randomly in many applications but follows a discernible pattern, the mobile mode. It is assumed that in a large number of moving trajectories, the moving trajectory of the target often accesses the B area after accessing the A area, and then accesses the C area after accessing the B area. It can be considered that the moving mode of the target is A-B-C. If the current target is accessing the A zone, then it can be determined according to the target's mobile mode that the target is likely to access the B zone next. Therefore, these models can provide reasonable predictions if certain conditions are met. The main idea of these methods is that these patterns can be used to make more accurate prediction rules.
  • the extraction method of this mode is slightly insufficient, especially when different regions in the mobile environment
  • the deficiencies of this approach become more apparent when there are often hot and unpopular access situations. For example, patterns in the unpopular area will not have a chance to be discovered.
  • the inventors considered that while some areas are less popular with popular targets, so that there are fewer available movements, there are still useful patterns.
  • the present invention proposes the following scheme.
  • an embodiment of the present invention provides a method for determining a mobility mode applied to a target area of an electronic device, including:
  • each of the historical movement trajectories in the target region range is converted into a movement sequence composed of the number of the sub-regions, and a movement is generated based on the movement sequence converted by each historical movement trajectory.
  • a subset of the moving sequence with the number Si is filtered from the set of moving sequences, and based on the subset of the moving sequence with the number Si, the Si is acquired as a moving sequence. All moving sequence segments generated at the cutoff point, and counting the frequency of occurrence of various moving sequence segments in all the moving sequence segments, wherein the same moving sequence segments are one class;
  • the moving sequence segment in which the frequency reaches or exceeds the frequency threshold is determined to be the quasi-moving mode.
  • the embodiment of the present invention further provides a non-volatile computer storage medium storing a computer executable program for executing the target area according to any one of the above aspects of the present invention.
  • the method of determining the movement mode is not limited to any one of the above aspects of the present invention.
  • an embodiment of the present invention further provides an electronic device, including: at least one processor; a memory and a communication interface capable of communicating with the smart mobile device; wherein the memory is stored by the at least one processor Executing a program executed by the at least one processor to enable the at least one processor to perform a method of determining a movement pattern within a range of any of the above-described target regions of the present invention.
  • the embodiment of the invention realizes the method for determining the movement mode in the target region and the electronic device, and by dividing the target region, respectively determining the proportion of each moving track segment passing through each region in the region,
  • the moving track segment reaching the specific gravity is determined to be the moving mode, so that not only the modes of some unpopular areas can be determined, but also the accuracy of the determined moving mode can be ensured, and the mining of the moving mode is more sufficient.
  • FIG. 1 is a flowchart of a method for determining a movement mode within a target area according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a method for determining a mobility mode within a target area according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a method for determining a mobility mode within a target area according to another embodiment of the present invention.
  • FIG. 4 is a flowchart of a method for determining a mobility mode within a target area according to another embodiment of the present invention.
  • FIG. 5 is a flowchart of a method for determining a mobility mode within a target area according to another embodiment of the present invention.
  • FIG. 6 is a flowchart of a method for determining a movement mode within a target area according to still another embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of an electronic device for determining a mobile mode within a target area according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for determining a mobile mode within a target area according to an embodiment of the present invention, where the method may be performed on an electronic device, such as a server of a suitable type and/or number. Including the following steps:
  • S102 Refer to the divided n sub-regions S1...Sn, and convert each historical movement trajectory in the target region range into a movement sequence composed of the number of the sub-regions, based on the movement sequence of each historical movement trajectory transformation, Generating a set of moving sequences;
  • S104 Determine a moving sequence segment whose frequency reaches or exceeds a frequency threshold as a quasi-moving mode.
  • the method can be applied to an airport management system in an application field that effectively predicts a location, wherein the airport management system operates on an electronic device.
  • the airport management system operates on an electronic device.
  • a number of smart carts with positioning functions are provided for passengers in the airport, and electronic devices running the airport management system can communicate with the smart carts by wire or wirelessly.
  • Some passengers move inside the airport and upload their movement trajectory through the mobile trolley, so that the airport management system can know the movement trajectory of the passenger through the smart cart and store the movement trajectory obtained by it as a historical movement trajectory.
  • the historical movement trajectory stored by the airport management system is periodically updated as new trajectories are continuously acquired. Then, by turning the trajectories into sequences, the regions they route are stored in a centralized sequence of moving sequences in a moving sequence.
  • the movement pattern of the passenger can be determined by the movement sequence, and the position of the passenger who is using the trolley can be predicted by the determined movement mode, and if the movement trajectory of the passenger who is using the trolley is completely in the order of numbering in the movement mode, then The destination to be reached by the passenger can be determined to provide a more efficient service.
  • the target airport area is divided into n sub-areas S1...Sn, as shown in FIG. 2, the division into the airport area is divided into 22 sub-areas. Among them, for the convenience of expression, the airport area is evenly divided here.
  • step S102 referring to the divided 22 sub-regions S1...S22, each historical movement trajectory in the area of the airport area is converted into a movement sequence composed of numbers of sub-areas.
  • the process of transforming a moving trajectory into a sequence includes that the form of the moving trajectory is as follows: ⁇ (l l , t 1 ), (l 2 , t 2 ), ..., (l k , t k )>, where l represents the arrival The area, the time k reaches the area, and t 1 ⁇ t 2 ⁇ ... ⁇ t k .
  • the region of the path through which the trajectory is moved is extracted in the trajectory order as (l 1 , l 2 , ..., l k ). For example, a trajectory ⁇ (S21, t 1 ), (S20, t 2 ), (S11, t 3 ), (S10, t 4 )> in FIG.
  • the sequence of the conversion is composed of the numbering sequence of the addresses of the path of the moving track, and the converted track cannot be changed to the order of the area number.
  • a moving sequence in which one of the historical trajectories is converted into (S21, S20, S11, S10), based on a sequence of each historical moving trajectory transformation generates a moving sequence set as follows ⁇ (S21, S20, S11, S10), ( S21, S20, S11, S10), (S21, S20, S11, S10), (S1, S9, S10), (S2, S3, S4), (S2, S3, S4), (S7, S4), ( S18, S13, S12), (S18, S13, S12), (S18, S13, S14), (S18, S13, S14), (S22, S17, S16, S15, S6, S5), (S16, S15, S6, S5) ⁇ .
  • a subset of the moving sequence with the number Si is selected from the set of moving sequences, for example, the sub-region S10, and the moving sequence with the number S10 is selected from the moving sequence set.
  • Subsets ⁇ (S21, S20, S11, S10), (S21, S20, S11, S10), (S21, S20, S11, S10), (S1, S9, S10) ⁇ .
  • the sub-area S11 filters out the moving sequence sub-sets with S11 from the set of moving sequences ⁇ (S21, S20, S11, S10), (S21, S20, S11, S10), (S21, S20, S11, S10) ) ⁇ .
  • All the moving sequence segments generated when the sub-region S11 is taken as the cut-off point in the moving sequence are ⁇ (S21, S20, S11), (S21, S20, S11), (S21, S20, S11) ⁇ , and various types are counted.
  • the frequency of occurrence of each type of sequence in the moving sequence segment occurs three times in the sequence segment of the sub-region S11 (S21, S20, S11).
  • the method for generating the moving sequence segments of the remaining sub-areas is the same here, and will not be described again.
  • the moving sequence segment whose frequency has reached or exceeded the frequency threshold is determined to be the quasi-moving mode. For example, if the frequency threshold is set to 60%, the moving sequence segment (S21, S20, S11, S10) of the sub-region S10 occupies 75% of the subset of the moving sequence, exceeding a preset frequency, so the moving sequence segment is determined (S21, S20, S11, S10) is a quasi-moving mode, and the quasi-moving mode is S21-S20-S11 ⁇ S10.
  • the moving sequence segment set of the sub-region S10 is ⁇ (S21, S20, S11, S10), (S21, S20, S11, S10), (S21, S20, S11) , S10), (S1, S9, S10) ⁇ , in the figure with PS10 ⁇ (S21, S20, S11), (S21, S20, S11), (S21, S20, S11), (S1, S9) ⁇ The way to do this. Empty means that the moving sequence fragment is empty.
  • the implementation method provides a method for determining a movement pattern within a target region, and converts the historical movement trajectory into a movement sequence, and separately determines each region through which each movement sequence passes, and determines each The frequency occupied by each mobile sequence segment that reaches the region in an area determines the quasi-movement mode implied by each mobile sequence segment in each region according to the local support frequency threshold.
  • the quasi-movement mode is determined by moving the trajectory segments in each region. A meaningful quasi-movement pattern in the less cold area can be found.
  • the quasi-moving mode can be quickly determined for judging the destination moving within the target range.
  • the divided n sub-regions respectively have different personality features, and the personality features include: a service item or a house number.
  • the divided sub-areas have different service functions.
  • various shopping areas, dining areas, boarding areas, etc. may be included in the airport, and in the case of dividing the area, according to the airport.
  • the functional areas are divided into, for example, shopping area 1, shopping area 2, shopping area n, dining area 1, dining area 2, dining area m, boarding area 1, boarding area 2, boarding area k.
  • the movement trajectory of a passenger can be seen as follows: (shopping area 2, shopping area 4, shopping area 5, dining area 2, boarding area 8). In this way, when the mode is determined, not only can the passenger's mobile mode be determined, but also which areas are more popular with passengers, so that the functional areas can be modified according to the preferences of the passengers to achieve higher resource utilization. .
  • FIG. 4 is a flowchart of a method for determining a mobile mode within a target area according to another embodiment of the present invention, including the following steps:
  • S201 Determine, according to the moving sequence segment belonging to the quasi-moving mode, a corresponding supporting sequence, where the supporting sequence is a sequence after the number of the moving sequence segment belonging to the quasi-moving mode is removed;
  • S202 Determine an appearance frequency corresponding to the support sequence according to the frequency of occurrence of each type of mobile sequence segment in the all the mobile sequence segments that are counted;
  • S203 Determine a confidence level of the quasi-moving mode according to a ratio of an appearance frequency of the moving sequence segment belonging to the quasi-moving mode and a corresponding appearance frequency of the supporting sequence.
  • S204 Determine a quasi-movement mode in which the confidence level reaches or exceeds a confidence threshold as an effective movement mode.
  • the confidence threshold of each quasi-moving mode is determined.
  • a corresponding supporting sequence is determined, for example, (S21, S20, S11, S10) described in the embodiment of FIG. 1 is a quasi-moving mode, and the mobile belonging to the quasi-mobile mode is to be moved.
  • the sequence of the sequence segment removal cut-off point number (S21, S20, S11) is a corresponding support sequence, and for example (S18, S13, S12) is a quasi-moving mode, and according to the above method, the corresponding support sequence is determined as (S18, S13) ).
  • step S202 according to the frequency of occurrence of each type of moving sequence segment in all the sequence segments that have been counted, and the frequency of occurrence of the corresponding support sequence, for example, (S21, S20, S11, S10) shown in step S201.
  • the frequency of occurrence is 3, the frequency of the corresponding support sequence (S21, S20, S11) is 3, the frequency of occurrence of (S18, S13, S12) is 2, and the frequency of the corresponding support sequence (S18, S13) is 4.
  • the confidence level of the quasi-moving mode is determined according to the ratio of the appearance frequency of the moving sequence segment of the data quasi-moving mode and the appearance frequency of the corresponding supporting sequence, for example, step S201 shown in step S202 (S21)
  • the frequency of occurrence of S20, S11, S10) is 3, the frequency of the corresponding support sequence (S21, S20, S11) is 3, and the confidence level of the quasi-moving mode (S21, S20, S11, S10) is equal to 3/3. 100%, (S18, S13, S12) appears twice, the corresponding support sequence (S18, S13) has a frequency of 4, and the confidence level of the quasi-moving mode (S18, S13, S12) is equal to 2/4 equal to 50. %.
  • the confidence calculations of the remaining quasi-mobile modes are the same as those described above, and are not described here.
  • the quasi-movement mode that meets or exceeds the confidence threshold is determined to be a valid movement mode, such as a confidence threshold of 60%.
  • the confidence level of the quasi-moving mode (S21, S20, S11, S10) exceeds the confidence threshold, so (S21, S20, S11, S10) is the effective movement mode, and the confidence of the quasi-moving mode (S18, S13, S12) is not reached.
  • the confidence threshold, so (S18, S13, S12) is not a valid movement mode.
  • the determination of the remaining effective movement modes is the same as the above method, and will not be described herein.
  • the implementation method provides a method for determining a movement pattern within a target area.
  • the quasi-movement mode With the confidence exceeding the threshold is determined as the effective movement mode.
  • the accuracy of the quasi-moving mode can be determined. In the case where the number of historical moving tracks is small, the moving mode within the target area can be determined more accurately.
  • FIG. 5 is a flowchart of a method for determining a mobile mode within a target area according to another embodiment of the present invention, including the following steps:
  • S301 Establish a projection database for each sub-region Si, wherein all the moving sequence segments are stored in the sub-region Si after the acquiring all moving sequence segments generated when Si is used as a cut-off point in the moving sequence
  • the frequency of occurrence of the various types of moving sequence segments can be counted by searching the projection database of the sub-regions Si;
  • a projection database is established for each sub-area. As shown in FIG. 2, a projection database is established for each of the sub-areas S1-S22. For example, based on the subset of moving sequences with S10 is ⁇ (S21, S20, S11, S10), (S21, S20, S11, S10), (S21, S20, S11, S10), (S1, S9, S10) ⁇ , the moving sequence segment generated when S10 is the cutoff point is stored in the projection database of the sub-region S10, and the frequency of occurrence of various moving sequence segments is counted, such as in the projection database S10 (S21, S20, S11, S10).
  • the number of times is 3, and the number of times (S1, S9, S10) is 1.
  • S13 is The moving sequence segment generated at the cutoff point is stored in the projection database of the sub-region S13, which is ⁇ (S18, S13), (S18, S13), (S18, S13), (S18, S13) ⁇ , and counts various types of movement.
  • the frequency at which the sequence segment appears, in the projection database S13, (S18, S13) is four.
  • the projection database establishment method of the other sub-areas is the same as the above method, and will not be described again here.
  • the projection database of each sub-region Si is updated according to the new movement trajectory generated in the periodic acquisition target region. For example, a new movement trajectory is generated, and the new movement trajectory is (S18, S13, S12), and each projection database acquires a new movement trajectory and is updated.
  • the movement trajectory database of the sub-area S12 is updated, it becomes ⁇ (S18, S13, S12), (S18, S13, S12), (S18, S13, S12) ⁇
  • the movement trajectory database of the sub-area S13 is updated to become ⁇ (S18, S13), (S18, S13), (S18, S13), (S18, S13), (S18, S13), (S18, S13) ⁇ .
  • the frequency of the mobile sequence segment is recalculated, and the frequency of (S18, S13, S12) is 100%, which exceeds the set frequency threshold.
  • (S18, S13, S12) is the quasi-moving mode, and the ratio of the frequency of the support sequence (S18, S13, S12) to its supporting sequence is continued, and the frequency of occurrence of (S18, S13, S12) is 3, and (S18, S13, S12)
  • the corresponding support sequence (S18, S13) has an appearance frequency of 5, and the confidence level of (S18, S13, S12) is 3/5 equals 60%, and the set reliability threshold is reached. Therefore, the updated (S18, S13, S12) is also the effective movement mode.
  • the implementation method by storing a projection database for each sub-region to store the data of the moving trajectory, the moving sequence segment whose sub-region is the cut-off point is stored, and the moving mode determined by acquiring the new moving trajectory is used. Update. By updating the determined movement pattern with a new movement trajectory, the movement pattern can be optimized to more closely match the movement rules of the target.
  • FIG. 6 is a flowchart of a method for determining a mobile mode within a target area according to another embodiment of the present invention, where generating a mobile sequence set may include the following steps:
  • S401 Determine a length of a moving sequence transformed by each historical moving track, where the length is measured by the number of numbers;
  • S402 For the first moving sequence whose length exceeds the length threshold j, a sequence consisting of the last m-bit number is selected, and is determined to be a valid moving sequence, where m is less than or equal to j;
  • step S401 the length of the moving sequence converted by each piece of historical movement trajectory is determined. As shown in FIG. 2, for example, the length of the moving sequence (S22, S17, S16, S15, S6, S5) is 6, and the moving sequence (S16, The length of S15, S6, S5) is 4.
  • step S402 if the length threshold is set to 4, a sequence consisting of 4 bit numbers at the end of the movement sequence exceeding the length threshold 4 is determined as a valid movement sequence. For example, if the length of the moving sequence (S22, S17, S16, S15, S6, S5) exceeds the threshold length, then the sequence consisting of the last 4 digits is determined as the effective sequence, and the moving sequence becomes (S16, S15, S6, S5). It is also possible to take a number less than 4 digits to form a valid moving sequence, for example 3 or 2 bits.
  • step S403 for the second movement sequence not exceeding the length threshold 4, for example, the movement sequence (S16, S15, S6, S5), it is directly determined as the effective sequence.
  • a set of moving sequences is generated based on all valid sequences after the determination.
  • the moving sequence segment set of the sub-region S5 is ⁇ (S16, S15, S6, S5), (S16, S15, S6, S5) ⁇ , where (S16, S15, S6, S5)
  • the support frequency is 100%, so after cutting the excessively long moving sequence, (S16, S15, S6, S5) is in the quasi-moving mode.
  • the embodiment of the present application provides a non-volatile computer storage medium, where the computer storage medium stores a computer executable program, which can execute a mobile mode within a target area in any of the foregoing method embodiments. Determining method;
  • the non-transitory computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store the collected movement track and according to Data created by the method of determining the movement pattern within the target area.
  • the non-transitory computer readable storage medium may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, flash memory device, or other nonvolatile solid state storage device.
  • the non-transitory computer readable storage medium optionally includes a memory remotely disposed relative to the processor, the remote memory being connectable to the electronic device running the determining method of the mobile mode within the target area . Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • FIG. 7 is a schematic structural diagram of an electronic device for determining a mobile mode in a target area according to an embodiment of the present invention. As shown in FIG. 7, the device includes:
  • One or more processors 710 and memory 720, communication interface 750 can be in network communication with a smart mobile device, such as a cart, such as one processor 710 in FIG.
  • the electronic device shown in FIG. 7 may further include: an input device 730 and an output device 740.
  • the processor 710, the memory 720, the input device 730, and the output device 740 may be connected by a bus or other means, as exemplified by a bus connection in FIG.
  • the memory 720 is the non-volatile computer readable storage medium described above.
  • the processor 710 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 720, that is, determining the movement mode within the target area of the above method embodiment. method.
  • the input device 730 can receive the input digital or character information, and generate a key signal input related to the function control of the determination method of the movement mode within the target region range of the above-described method embodiment.
  • the output device 740 can include a display device such as a display screen.
  • the above product can perform the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
  • the above product can perform the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
  • the electronic device includes: at least one processor; a memory communicatively coupled to the at least one processor; and a communication interface capable of communicating with the smart mobile device; wherein the memory is stored with the at least a program executed by a processor, the program being executed by the at least one processor to enable the at least one processor to execute:
  • each of the historical movement trajectories in the target region range is converted into a movement sequence composed of the number of the sub-regions, and a movement is generated based on the movement sequence converted by each historical movement trajectory.
  • a subset of the moving sequence with the number Si is filtered from the set of moving sequences, and based on the subset of the moving sequence with the number Si, the Si is acquired as a moving sequence. All moving sequence segments generated at the cutoff point, and counting the frequency of occurrence of various moving sequence segments in all the moving sequence segments, wherein the same moving sequence segments are one class;
  • the moving sequence segment in which the frequency reaches or exceeds the frequency threshold is determined to be the quasi-moving mode.
  • the at least one processor is further capable of:
  • the supporting sequence Determining, according to the moving sequence segment belonging to the quasi-moving mode, the supporting sequence, wherein the supporting sequence is a sequence after the number of the moving sequence segment removal cutoff point belonging to the quasi-moving mode;
  • the quasi-movement mode in which the confidence level reaches or exceeds the confidence threshold is determined as the effective movement mode.
  • a projection database is established for the memory in each of the sub-regions Si, wherein all of the moving sequence segments are stored in the sub-segment after the acquisition of all moving sequence segments generated with Si as a cut-off point in the moving sequence
  • the projection database of the region Si is established for the memory in each of the sub-regions Si, wherein all of the moving sequence segments are stored in the sub-segment after the acquisition of all moving sequence segments generated with Si as a cut-off point in the moving sequence
  • the frequency of occurrence of the various types of moving sequence segments can be counted by retrieving a projection database of the sub-regions Si stored in the memory;
  • the projection database of each of the sub-regions Si stored in the memory is updated according to periodically acquiring a new movement trajectory generated in the target region.
  • the electronic device of the embodiment of the invention exists in various forms, including but not limited to:
  • Server equipment This type of equipment is characterized by data processing functions and provides the main objectives of data extraction, data processing, and data analysis.
  • Such terminals include: entry-level servers, workgroup-level servers, departmental servers, and enterprise servers.
  • Ultra-mobile computer devices with mobile Internet access These devices belong to the category of computers and have computing and processing functions.
  • Such terminals include: superbooks with 3G/4G Internet access, PDAs, MIDs, and UMPC devices.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种目标区域范围内的移动模式的确定方法及电子设备。该方法包括：将目标区域划分为n个子区域S1…Sn（S101）；参照划分后的n个子区域，将目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合（S102）；对于每一个子区域Si，从移动序列集合中筛选出带有Si的移动序列子集合，并基于带有Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，统计所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类（S103）；将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式（S104）。所述方法实现了确定区域范围内的移动模式，保证精度的同时确定更多的移动模式。

Description

目标区域范围内的移动模式的确定方法及电子设备 技术领域
本发明涉及地理信息技术领域，尤其涉及一种目标区域范围内的移动模式的确定方法及电子设备。
背景技术
移动行为的挖掘和预测有着非常广泛的应用前景。通过预测目标的下一个移动区域，可以将资源有效地分配给目标最可能去的区域，而不是盲目的资源分配。将资源高效分配将导致更高的资源利用率和更低的访问资源的延迟。此外，预测随后的位置可以为许多现有的广泛应用提供洞察力，如有针对性的广告和服务推荐。
移动行为预测的方法一般是基于移动模式预测。现实中，目标的移动在许多应用中不是随机发生的而是遵循某种可辨别的模式，即移动模式。假设在海量的移动轨迹中，目标的移动轨迹经常在访问A区域之后下一步访问B区域，接着又在访问B区域之后又总是去访问C区域。可以考虑目标的移动模式为A-B-C。如果当前目标正在访问A区域，那么，根据目标的移动模式可以确定，该目标下一步很可能访问B区域。因此，这些模式如果满足某些条件，则可以提供合理的预测。这些方法的主要思想是，可以将这些移动模式(pattern)用来做更准确的预测规则。
在实现本发明过程中，发明人发现相关技术中至少存在如下问题：
虽然可以尝试利用达到同类移动轨迹(movement trajectories)的最小支持数量(min-support)来确定移动模式，但是这种模式的提取的方法略显不足，尤其当移动环境(mobile environment)中的不同区域往往存在热门访问和冷门访问的情况时，这种方法的不足之处变得更加明显。例如，冷门区域中的模式不会有机会被发现。发明人考虑到虽然有些地区不太受大众目标的欢迎，以至于可用移动轨迹较少，但是仍存在着有用的模式。虽然可以通过将上述最小支持数量的阈值设置成较低来尽可能挖掘更多的有用模式，但是此时，挖掘的模式(pattern mining)的数量可能会非常大，出现较多没有意义的移动模式，导致效率和精度较低；同时，一旦所设置的阈值较高时，则不能挖掘出一些有用的移动模式，这样导致可预测 性降低。
发明内容
为了至少解决现有技术中对移动模式的挖掘不充分的问题，本发明提出了如下方案。
第一方面，本发明实施例提供一种应用于电子设备的目标区域范围内的移动模式的确定方法，包括：
将目标区域划分为n个子区域S1…Sn；
参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
第二方面，本发明实施例还提供了一种非易失性计算机存储介质，存储有计算机可执行程序，所述计算机可执行程序用于执行本发明上述任一项所述的目标区域范围内的移动模式的确定方法。
第三方面，本发明实施例还提供了一种电子设备，包括：至少一个处理器；存储器以及能够与智能移动设备通讯的通讯接口；其中，所述存储器存储有可被所述至少一个处理器执行的程序，所述程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行本发明上述任一项目标区域范围内的移动模式的确定方法。
本发明实施例实现了目标区域范围内的移动模式的确定方法及电子设备，通过对目标区域进行划分，分别求出每一个区域内经过的各移动轨 迹片段在其区域内所占的比重，将达到比重的移动轨迹片段确定为移动模式，这样不但可以将一些冷门区域的模式确定出来，同时也可以保证确定出的移动模式的精度，使移动模式的挖掘更加充分。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图；
图2是本发明一实施例提供的一种目标区域范围内的移动模式的确定方法的示意图；
图3是本发明另一实施例提供的一种目标区域范围内的移动模式的确定方法的示意图；
图4是本发明另一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图；
图5是本发明又一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图；
图6是本发明再一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图；
图7是本发明一实施例提供的用于目标区域范围内的移动模式的确定的电子设备的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
如图1所示为本发明一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图，所述方法可以在电子设备上，例如适当类型和/或数量的服务器上执行，包括如下步骤：
S101：将目标区域划分为n个子区域S1…Sn；
S102：参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
S103：对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
S104：将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
在本实施方式中，可以将所述方法应用于有效预测位置的应用领域中的机场管理系统，其中机场管理系统运行在电子设备上。在机场中，设置若干量带有定位功能的智能手推车以供机场内的乘客使用，运行有机场管理系统的电子设备可以通过有线或无线地方式与智能手推车进行通讯。一些乘客在机场内移动，并通过移动小推车上传他们的移动轨迹，使得机场管理系统可以通过智能手推车知悉乘客的移动轨迹并存储其所获得的移动轨迹以作为历史移动轨迹。机场管理系统存储的历史移动轨迹会随着不断采集的新的移动轨迹而周期性地更新。然后，通过将轨迹转为序列，他们所途径的区域被以移动序列(Moving Sequences)的模式存储在集中的移动序列数据库中。可以通过移动序列来确定乘客的移动模式，通过确定的移动模式来对正在使用小推车的乘客预测位置，若正在使用小推车的乘客的移动轨迹完全按照移动模式中编号的顺序行动，则可以确定乘客所要达到的目的地，从而提供更有效的服务。
对于步骤S101，将目标机场区域划分为n个子区域S1…Sn，如图2中示出了对机场区域的划分，划分为22个子区域。其中，为了表述方便，在此对机场区域进行均匀划分。
对于步骤S102，参照划分后的22个子区域S1...S22，将机场区域范围内每一条历史移动轨迹进行转化，转化为有子区域的编号构成的移动序列。
移动轨迹转化为序列的过程包括，移动轨迹的形式如下<(l l,t 1),(l 2,t 2),...,(l k,t k)>，其中，l代表所到达的区域，k到达该区域的时间，并且t 1<t 2<…<t k。将其移动轨迹的途径的区域按照轨迹顺序提取出来为(l 1,l 2,…,l k)。例如，图2中的一条轨迹<(S21,t 1),(S20,t 2),(S11,t 3),(S10,t 4)>，将移动轨迹所到达的区域提取出来，转化为移动序列(S21，S20，S11，S10)。其中，转化的序列由移动轨迹所途径地址的编号顺序组成，转化的轨迹不可更变其区域编号的顺序。
例如，其中的一条历史轨迹转化为的移动序列是(S21，S20，S11，S10)，基于每一条历史移动轨迹转化的序列，生成移动序列集合如下{(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S1，S9，S10),(S2，S3，S4)，(S2，S3，S4)，(S7，S4)，(S18，S13，S12)，(S18，S13，S12)，(S18，S13，S14)，(S18，S13，S14)，(S22，S17，S16，S15，S6，S5)，(S16，S15，S6，S5)}。
对于步骤S103，对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列子集合，例如，子区域S10，从移动序列集合中筛选出带有编号S10的移动序列的子集合{(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S1，S9，S10)}。例如，子区域S11，从移动序列集合中筛选出带有S11的移动序列子集合{(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S21，S20，S11，S10)}。获取以子区域S11作为移动序列中的截止点时生成的所有移动序列片段为{(S21，S20，S11)，(S21，S20，S11)，(S21，S20，S11)}，并统计各类移动序列片段中各类序列出现的频次，以子区域S11为例(S21，S20，S11)的序列片段出现3次。其余子区域的移动序列片段生成方法于此相同，不再赘述。
对于步骤S104，将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。例如设定频次阈值为60％，子区域S10的移动序列片段(S21，S20，S11，S10)占移动序列子集合的75％，超过预设的频次，所以确定移动序列片段(S21，S20，S11，S10)为准移动模式，准移动模式为S21-S20-S11→S10。
又根据准移动模式S21-S20-S11→S10，可以得到S21-S20→S10、S21-S11→S10、S20-S11→S10、S21→S10、S20→S10、S11→S10。其余移动序列片段确定方法与此相同，在此不再赘述。由于轨迹条数较多，文字说明非常繁杂，为了便于理解，将上述步骤转化为视图，如图3所示。其中，为了简化视图，例如，在移动序列片段中，子区域S10的移动序列片段集合为{(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S1，S9，S10)}，在图中以PS10{(S21，S20，S11)、(S21，S20，S11)、(S21，S20，S11)、(S1，S9)}的方式进行示例。Empty指移动序列片段为空。
通过该实施方法可以看出，本实施方法提供了一种目标区域范围内的移动模式的确定方法，将历史移动轨迹转化为移动序列，通过对每一条移动序列经过的区域都单独区分，确定每一个区域中截止到达该区域的各移动序列片段所占的频次，根据本地支持频次阈值确定每一个区域中的各移动序列片段所隐含的准移动模式。通过对每一个区域中的移动轨迹片段确定准移动模式。可以发现较冷门区域中有意义的准移动模式。同时当历史移动轨迹较多时，可以快速的确定出准移动模式，以供用于判断目标范围内移动的目的地。
作为一种实施方式，在本实施例中，划分后的所述n个子区域分别具有不同的个性特征，所述个性特征包括：服务项目或门牌号。
在本实施方式中，例如，划分后的子区域具有不同服务功能的特征，在机场环境中，可以将机场中有着各种购物区，餐饮区，登机区等，在划分区域时，按照机场内各功能区域分，例如可以划分为：购物区1、购物区2…购物区n，餐饮区1、餐饮区2…餐饮区m，登机区1、登机区2…登机区k。从而在历史移动轨迹中，例如，可以看到某旅客的移动轨迹如下：(购物区2，购物区4，购物区5，餐饮区2，登机区8)。通过该种方式划分区域在模式确定时，不但可以确定旅客的移动模式，还可以了解到哪些区域更受旅客喜爱，从而针对与旅客的喜好对各功能区进行改造，达到更高的资源利用率。
通过该实施方法可以看出，通过将区域按照功能划分可以更适用于当前环境。从而提高资源利用率。
如图4所示为本发明另一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图，包括如下步骤：
S201：根据属于准移动模式的移动序列片段，确定相应的支持序列，其中所述支持序列为所述属于准移动模式的移动序列片段去除截止点的编号之后的序列；
S202：根据所述已统计的所述所有移动序列片段中各类移动序列片段的出现频次，从中确定对应于所述支持序列的出现频次；
S203：根据所述属于准移动模式的移动序列片段的出现频次和对应的所述支持序列的出现频次的比值，确定所述准移动模式的置信度；
S204：将所述置信度达到或超过置信度阈值的准移动模式确定为有效移动模式。
在本实施方式中，在图1实施例确定出准移动模式后，对各准移动模式的置信度(confidence threshold)进行确定。
对于步骤S201，根据属于准移动模式的移动序列片段，确定相应的支持序列，例如图1实施例中所述的(S21，S20，S11，S10)为准移动模式，将属于准移动模式的移动序列片段去除截止点编号的序列(S21，S20，S11)为相应的支持序列，又例如(S18，S13，S12)为准移动模式，根据上述方法，确定其相应的支持序列为(S18，S13)。
对于步骤S202，根据所述已统计的所有序列片段中各类移动序列片段的出现频次，和其相对应的支持序列的出现频次，例如，步骤S201示出的(S21，S20，S11，S10)的出现频次为3，对应的支持序列(S21，S20，S11)的频次为3，(S18，S13，S12)的出现频次为2，对应的支持序列(S18，S13)的频次为4。
对于步骤S203，根据所述数据准移动模式的移动序列片段的出现频次和对应的支持序列的出现频次的比值，确定准移动模式的置信度，例如步骤S202示出的步骤S201示出的(S21，S20，S11，S10)的出现频次为3，对应的支持序列(S21，S20，S11)的频次为3，得到准移动模式(S21，S20，S11，S10)的置信度等于3/3为100％，(S18，S13，S12)的出现频次为2，对应的支持序列(S18，S13)的频次为4，得到准移动模式(S18，S13，S12)的置信度等于2/4等于50％。其余的准移动模式的置信度计算与上述方法相同， 在此不在赘述。
对于步骤S204，将达到或超过置信度阈值的准移动模式确定为有效移动模式，例如置信度阈值为60％。准移动模式(S21，S20，S11，S10)的置信度超过置信度阈值，所以(S21，S20，S11，S10)为有效移动模式，准移动模式(S18，S13，S12)的置信度没有达到置信度阈值，所以(S18，S13，S12)不是有效移动模式。其余有效移动模式的确定与上述方法相同，在此不再赘述。
通过该实施方法可以看出，本实施方法提供了一种目标区域范围内的移动模式的确定方法，通过计算准移动模式的置信度，将置信度超过阈值的准移动模式确定为有效移动模式，可以确定该准移动模式的准确性。在历史移动轨迹条数较少的情况下，可以更精确的确定目标区域范围内的移动模式。
如图5所示为本发明又一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图，包括如下步骤：
S301：为每一个子区域Si建立投影数据库，其中，在所述获取以Si作为移动序列中的截止点时生成的所有移动序列片段之后，将所述所有移动序列片段存入所述子区域Si的投影数据库中，通过检索所述子区域Si的投影数据库能够统计所述各类移动序列片段的出现频次；
S302：所述各子区域Si的投影数据库根据周期性地采集目标区域内产生的新移动轨迹而更新。
对于步骤S301，为每一个子区域建立投影数据库，如图2为例，对子区域S1-S22分别建立投影数据库。例如，基于带有S10的移动序列子集合为{(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S21，S20，S11，S10)，(S1，S9，S10)}，将以S10为截止点时生成的移动序列片段存入子区域S10的投影数据库中，并统计各类移动序列片段出现的频次，如投影数据库S10中(S21，S20，S11，S10)的次数为3，(S1，S9，S10)的次数为1。又如基于带有S13的移动序列子集合为{(S18，S13，S12)，(S18，S13，S12)，(S18，S13，S14)，(S18，S13，S12)}，将以S13为截止点时生成的移动序列片段存入子区域S13的投影数据库中，为{(S18，S13)，(S18，S13)，(S18，S13)，(S18，S13)}，并统计各类移动序列片段出 现的频次，投影数据库S13中，(S18，S13)的次数为4。其他子区域的投影数据库建立方法与上述方法相同，在此，不再赘述。
对于步骤S302，各子区域Si的投影数据库根据周期性采集目标区域内产生的新的移动轨迹而更新。例如，有一条新的移动轨迹产生，新的移动轨迹为(S18，S13，S12)，各投影数据库采集新的移动轨迹而更新。例如子区域S12的移动轨迹数据库更新后变为{(S18，S13，S12)，(S18，S13，S12)，(S18，S13，S12)}，子区域S13的移动轨迹数据库更新后变为{(S18，S13)，(S18，S13)，(S18，S13)，(S18，S13)，(S18，S13)}。此时，由于数据库更新，重新计算移动序列片段所占频次，(S18，S13，S12)所占频次为100％，超过所设频次阈值。(S18，S13，S12)为准移动模式，继续计算(S18，S13，S12)与其支持序列的频次的比值，(S18，S13，S12)的出现频次为3，与(S18，S13，S12)对应的支持序列(S18，S13)的出现频次为5，(S18，S13，S12)的置信度为3/5等于60％，达到所设置信度阈值。所以更新后的(S18，S13，S12)也为有效移动模式。
通过该实施方法可以看出，通过对每个子区域建立投影数据库来存储移动轨迹的数据，来存储以其子区域为截止点的移动序列片段，通过采集新的移动轨迹来对其确定的移动模式进行更新。通过新的移动轨迹来更新其确定的移动模式，可以优化移动模式，更符合目标的移动规则。
如图6所示为本发明再一实施例提供的一种目标区域范围内的移动模式的确定方法的流程图，其中，生成移动序列集合可以包括如下步骤：
S401：判断各条历史移动轨迹转化的移动序列的长度，其中，长度由编号的个数度量；
S402：对于长度超过长度阈值j的第一移动序列，选取末尾m位编号组成的序列，确定为有效移动序列，m小于或等于j；
S403：对于长度不超过长度阈值j的第二移动序列，确定为有效移动序列；
S404：基于确定后的所有有效移动序列，生成所述移动序列集合。
对于步骤S401，判断各条历史移动轨迹转化的移动序列的长度，如图2所示，例如，移动序列(S22，S17，S16，S15，S6，S5)的长度为6， 移动序列(S16，S15，S6，S5)的长度为4。
对于步骤S402，若设定长度阈值为4，则将超过长度阈值4的移动序列末尾的4位编号组成的序列确定为有效移动序列。例如移动序列(S22，S17，S16，S15，S6，S5)的长度超过阈值长度，那么将末尾4位编号组成的序列确定为有效序列，移动序列变为(S16，S15，S6，S5)，其中也可以取小于4位的编号来组成有效移动序列，例如3位或者2位。
对于步骤S403，对于不超过长度阈值4的第二移动序列，例如移动序列(S16，S15，S6，S5)，则直接确定为有效序列。
对于步骤S404，基于确定后的所有有效序列，生成移动序列集合。例如，经过步骤S402处理后，子区域S5的移动序列片段集合为{(S16，S15，S6，S5)，(S16，S15，S6，S5)}，其中，(S16，S15，S6，S5)支持频次为100％，所以在将过长的移动序列切割后，(S16，S15，S6，S5)为准移动模式。
通过该实施方法可以看出，由于区域范围内的移动轨迹大不相同，会出现特别长的移动轨迹，在确定移动模式中造成困难，通过将过长的移动序列进行去头，采集其信息含量较高的最后行走的部分区域，将历史数据进行优化，可以确定更多的移动模式。
本申请实施例提供了一种非易失性计算机存储介质，所述计算机存储介质存储有计算机可执行程序，该计算机可执行程序可执行上述任意方法实施例中的目标区域范围内的移动模式的确定方法；
非易失性计算机可读存储介质可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储所采集的移动轨迹以及根据目标区域范围内的移动模式的确定方法所创建的数据等。此外，非易失性计算机可读存储介质可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，非易失性计算机可读存储介质可选包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至运行有目标区域范围内的移动模式的确定方法的电子设备。上述网络的实例包括但不限于互联网、企业内部网、 局域网、移动通信网及其组合。
图7是本发明一实施例提供的用于目标区域范围内的移动模式的确定的电子设备的结构示意图，如图7所示，该设备包括：
一个或多个处理器710以及存储器720，通讯接口750(未示出)，其能够与智能移动设备，例如与手推车进行网络通讯，图7中以一个处理器710为例。
图7所示的电子设备还可以包括：输入装置730和输出装置740。
处理器710、存储器720、输入装置730和输出装置740可以通过总线或者其他方式连接，图7中以通过总线连接为例。
存储器720为上述的非易失性计算机可读存储介质。处理器710通过运行存储在存储器720中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例的目标区域范围内的移动模式的确定方法。
输入装置730可接收输入的数字或字符信息，以及产生与上述方法实施例的目标区域范围内的移动模式的确定方法的功能控制有关的键信号输入。输出装置740可包括显示屏等显示设备。
上述产品可执行本发明实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例所提供的方法。
作为一种实施方式，该电子设备包括：至少一个处理器；与所述至少一个处理器通信连接的存储器以及能够与智能移动设备通讯的通讯接口；其中，所述存储器存储有可被所述至少一个处理器执行的程序，所述程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行：
将目标区域划分为n个子区域S1…Sn；
参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的 移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
以使所述至少一个处理器还能够执行：
根据属于准移动模式的移动序列片段，确定相应的支持序列，其中所述支持序列为所述属于准移动模式的移动序列片段去除截止点的编号之后的序列；
根据所述已统计的所述所有移动序列片段中各类移动序列片段的出现频次，从中确定对应于所述支持序列的出现频次；
根据所述属于准移动模式的移动序列片段的出现频次和对应的所述支持序列的出现频次的比值，确定所述准移动模式的置信度；
将所述置信度达到或超过置信度阈值的准移动模式确定为有效移动模式。
以使所述至少一个处理器能够执行：
为每一个子区域Si在所述存储器建立投影数据库，其中，在所述获取以Si作为移动序列中的截止点时生成的所有移动序列片段之后，将所述所有移动序列片段存入所述子区域Si的投影数据库中，
通过检索所述存储器内存储的所述子区域Si的投影数据库能够统计所述各类移动序列片段的出现频次；
其中，所述存储器内存储的所述各子区域Si的投影数据库根据周期性地采集目标区域内产生的新移动轨迹而更新。
本发明实施例的电子设备以多种形式存在，包括但不限于:
(1)服务器设备:这类设备的特点是具备数据处理功能，并且以提供数据提取，数据处理，数据分析主要目标。这类终端包括:入门级服务器、工作组级服务器、部门级服务器和企业级服务器等。
(2)具备移动上网特性的超移动计算机设备:这类设备属于计算机的范畴，有计算和处理功能。这类终端包括:具备3G/4G上网功能的超级本、 PDA、MID和UMPC设备等。
(3)其他具有数据处理功能的电子装置。
在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”，不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种应用于电子设备的目标区域范围内的移动模式的确定方法，包括：
    将目标区域划分为n个子区域S1…Sn；
    参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
    对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
    将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
  2. 根据权利要求1所述的方法，在将出现频次达到或超过额定频次的移动序列片段确定为准移动模式后，所述方法还包括：
    根据属于准移动模式的移动序列片段，确定相应的支持序列，其中所述支持序列为所述属于准移动模式的移动序列片段去除截止点的编号之后的序列；
    根据所述已统计的所述所有移动序列片段中各类移动序列片段的出现频次，从中确定对应于所述支持序列的出现频次；
    根据所述属于准移动模式的移动序列片段的出现频次和对应的所述支持序列的出现频次的比值，确定所述准移动模式的置信度；
    将所述置信度达到或超过置信度阈值的准移动模式确定为有效移动模式。
  3. 根据权利要求1所述的方法，其中，所述方法还包括：
    为每一个子区域Si建立投影数据库，其中，在所述获取以Si作为移动序列中的截止点时生成的所有移动序列片段之后，将所述所有移动序列片段存入所述子区域Si的投影数据库中，通过检索所述子区域Si的投影 数据库能够统计所述各类移动序列片段的出现频次；
    其中，所述各子区域Si的投影数据库根据周期性地采集目标区域内产生的新移动轨迹而更新。
  4. 根据权利要求1所述的方法，其中，所述基于每一条历史移动轨迹转化的移动序列，生成移动序列集合包括：
    判断各条历史移动轨迹转化的移动序列的长度，其中，长度由编号的个数度量；
    对于长度超过长度阈值j的第一移动序列，选取末尾m位编号组成的序列，确定为有效移动序列，m小于或等于j；
    对于长度不超过长度阈值j的第二移动序列，确定为有效移动序列；
    基于确定后的所有有效移动序列，生成所述移动序列集合。
  5. 根据权利要求1所述的方法，其中，划分后的所述n个子区域分别具有不同的个性特征，所述个性特征包括：服务项目或门牌号。
  6. 一种非易失性计算机可读存储介质，其特征在于，所述非易失性计算机可读存储介质存储有计算机程序，所述计算机程序用于使所述计算机执行：
    将目标区域划分为n个子区域S1…Sn；
    参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
    对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
    将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
  7. 根据权利要求6所述的非易失性计算机可读存储介质，其特征在于，所述计算机程序还用于使所述计算机执行：
    根据属于准移动模式的移动序列片段，确定相应的支持序列，其中所述支持序列为所述属于准移动模式的移动序列片段去除截止点的编号之后的序列；
    根据所述已统计的所述所有移动序列片段中各类移动序列片段的出现频次，从中确定对应于所述支持序列的出现频次；
    根据所述属于准移动模式的移动序列片段的出现频次和对应的所述支持序列的出现频次的比值，确定所述准移动模式的置信度；
    将所述置信度达到或超过置信度阈值的准移动模式确定为有效移动模式。
  8. 一种电子设备，包括：至少一个处理器；存储器；以及能够与智能移动设备通讯的通讯接口；其中，所述存储器存储有可被所述至少一个处理器执行的程序，所述程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行：
    将目标区域划分为n个子区域S1…Sn；
    参照所述划分后的n个子区域S1…Sn，将所述目标区域范围内的每一条历史移动轨迹转化为由子区域的编号构成的移动序列，基于每一条历史移动轨迹转化的移动序列，生成移动序列集合；
    对于每一个子区域Si，从所述移动序列集合中筛选出带有编号Si的移动序列的子集合，并基于所述带有编号Si的移动序列的子集合，获取以Si作为移动序列中的截止点时生成的所有移动序列片段，并统计所述所有移动序列片段中各类移动序列片段的出现频次，其中，相同的移动序列片段为一类；
    将出现频次达到或超过频次阈值的移动序列片段确定为准移动模式。
  9. 根据权利要求8所述的电子设备，所述程序被所述至少一个处理器执行，以使所述至少一个处理器还能够执行：
    根据属于准移动模式的移动序列片段，确定相应的支持序列，其中所 述支持序列为所述属于准移动模式的移动序列片段去除截止点的编号之后的序列；
    根据所述已统计的所述所有移动序列片段中各类移动序列片段的出现频次，从中确定对应于所述支持序列的出现频次；
    根据所述属于准移动模式的移动序列片段的出现频次和对应的所述支持序列的出现频次的比值，确定所述准移动模式的置信度；
    将所述置信度达到或超过置信度阈值的准移动模式确定为有效移动模式。
  10. 根据权利要求8或9所述的一种电子设备，其特征在于，所述程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行：
    为每一个子区域Si在所述存储器建立投影数据库，其中，在所述获取以Si作为移动序列中的截止点时生成的所有移动序列片段之后，将所述所有移动序列片段存入所述子区域Si的投影数据库中，
    通过检索所述存储器内存储的所述子区域Si的投影数据库能够统计所述各类移动序列片段的出现频次；
    其中，所述存储器内存储的所述各子区域Si的投影数据库根据周期性地采集目标区域内产生的新移动轨迹而更新。
PCT/CN2018/102673 2017-08-28 2018-08-28 目标区域范围内的移动模式的确定方法及电子设备 WO2019042275A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710749638.9A CN107526815A (zh) 2017-08-28 2017-08-28 目标区域范围内的移动模式的确定方法及电子设备
CN201710749638.9 2017-08-28

Publications (1)

Publication Number Publication Date
WO2019042275A1 true WO2019042275A1 (zh) 2019-03-07

Family

ID=60682702

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102673 WO2019042275A1 (zh) 2017-08-28 2018-08-28 目标区域范围内的移动模式的确定方法及电子设备

Country Status (2)

Country Link
CN (1) CN107526815A (zh)
WO (1) WO2019042275A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107526815A (zh) * 2017-08-28 2017-12-29 知谷（上海）网络科技有限公司 目标区域范围内的移动模式的确定方法及电子设备
CN109614066B (zh) * 2018-12-19 2022-09-20 北京南师信息技术有限公司 信息显示方法及装置
JP7136680B2 (ja) * 2018-12-25 2022-09-13 株式会社日立製作所 エレベーターシステム
CN110879830A (zh) * 2019-09-19 2020-03-13 京东城市(北京)数字科技有限公司 一种数据管理方法、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120254084A1 (en) * 2009-10-19 2012-10-04 Eads Deutschland Gmbh Passenger motion prediction and optimization system
CN104268243A (zh) * 2014-09-29 2015-01-07 华为技术有限公司 一种位置数据处理方法及装置
CN104700434A (zh) * 2015-03-27 2015-06-10 北京交通大学 一种用于复杂结构化场景的人群运动轨迹异常检测方法
CN106779218A (zh) * 2016-12-16 2017-05-31 深圳达实智能股份有限公司 一种人员活动轨迹的预测方法
CN107526815A (zh) * 2017-08-28 2017-12-29 知谷（上海）网络科技有限公司 目标区域范围内的移动模式的确定方法及电子设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170184410A1 (en) * 2015-12-29 2017-06-29 Le Holdings (Beijing) Co., Ltd. Method and electronic device for personalized navigation
CN105894358A (zh) * 2016-03-31 2016-08-24 百度在线网络技术（北京）有限公司 通勤订单识别方法和装置
CN106355203A (zh) * 2016-08-31 2017-01-25 无锡知谷网络科技有限公司 活动人群的分类方法和系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120254084A1 (en) * 2009-10-19 2012-10-04 Eads Deutschland Gmbh Passenger motion prediction and optimization system
CN104268243A (zh) * 2014-09-29 2015-01-07 华为技术有限公司 一种位置数据处理方法及装置
CN104700434A (zh) * 2015-03-27 2015-06-10 北京交通大学 一种用于复杂结构化场景的人群运动轨迹异常检测方法
CN106779218A (zh) * 2016-12-16 2017-05-31 深圳达实智能股份有限公司 一种人员活动轨迹的预测方法
CN107526815A (zh) * 2017-08-28 2017-12-29 知谷（上海）网络科技有限公司 目标区域范围内的移动模式的确定方法及电子设备

Also Published As

Publication number Publication date
CN107526815A (zh) 2017-12-29

Similar Documents

Publication Publication Date Title
WO2019042275A1 (zh) 目标区域范围内的移动模式的确定方法及电子设备
Zhu et al. Effective and efficient trajectory outlier detection based on time-dependent popular route
CN110210604B (zh) 一种终端设备移动轨迹预测方法及装置
Yu et al. Scalable distributed processing of K nearest neighbor queries over moving objects
US9122982B2 (en) Device and method for destination prediction
US20190329788A1 (en) Road condition status prediction method, device, and server, and storage medium
WO2021232585A1 (zh) 基于人工智能的定位数据处理方法及相关设备
WO2017031856A1 (zh) 信息预测的方法和装置
Chen et al. Most reliable path-finding algorithm for maximizing on-time arrival probability
CN110533055B (zh) 一种点云数据的处理方法和装置
JP6797944B2 (ja) 注文振り分け装置及び方法
WO2022227303A1 (zh) 信息处理方法、装置、计算机设备及存储介质
WO2018190428A1 (ja) 需要予測装置
US20240046164A1 (en) Active notification using transportation service prediction
CN116136413A (zh) 排放优化的车辆路径和充电
Anastasiou et al. ASTRO: reducing COVID-19 exposure through contact prediction and avoidance
JP2016500862A (ja) 位置に基づくネットワークにおける区域のサンプリングおよび推定のための方法および装置
Zou et al. A novel taxi dispatch system for smart city
Wang et al. Protecting the location privacy of mobile social media users
US20210004728A1 (en) Determining arrival of transportation providers to pickup locations utilizing a hiking distance predictor model
CN114997414A (zh) 数据处理方法、装置、电子设备和存储介质
CN108376157B (zh) 目标用户查询方法、系统和装置
CN112070288B (zh) 出发时间预估方法、装置、设备以及存储介质
Li et al. Discovering real-time reachable area using trajectory connections
Chen et al. Periodic pattern mining based on GPS trajectories

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 02/10/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18852430

Country of ref document: EP

Kind code of ref document: A1