WO2019192120A1 - Procédé d'interrogation de suivi, dispositif électronique et support de stockage - Google Patents

Procédé d'interrogation de suivi, dispositif électronique et support de stockage Download PDF

Info

Publication number
WO2019192120A1
WO2019192120A1 PCT/CN2018/100149 CN2018100149W WO2019192120A1 WO 2019192120 A1 WO2019192120 A1 WO 2019192120A1 CN 2018100149 W CN2018100149 W CN 2018100149W WO 2019192120 A1 WO2019192120 A1 WO 2019192120A1
Authority
WO
WIPO (PCT)
Prior art keywords
query
point
track
candidate
distance
Prior art date
Application number
PCT/CN2018/100149
Other languages
English (en)
Chinese (zh)
Inventor
王健宗
吴天博
黄章成
肖京
Original Assignee
平安科技（深圳）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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019192120A1 publication Critical patent/WO2019192120A1/fr

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
    • 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

Definitions

  • the present application relates to the field of data query, and in particular, to a track query method, an electronic device, and a storage medium.
  • the semantic trajectory data not only contains time and space information, but also contains rich user behavior information: what people think and feel, through different media means
  • the semantic trajectory represents the retrieval of textual similarity by users, paying attention to the difference of "shape" between texts. For example, through the semantic trajectory query in the prior art, "drinking coffee” and track point description "Starbucks" are considered irrelevant. Can not be retrieved, so the subject-related trajectory can not be retrieved, reducing the accuracy of the query.
  • a track query method comprising:
  • the result is output to the user.
  • An electronic device comprising a memory and a processor, the memory for storing at least one instruction, the processor for executing the at least one instruction to implement the track query method of any of any of the embodiments .
  • a non-volatile readable storage medium storing at least one instruction, the at least one instruction being executed by a processor, implementing the track query method of any of any of the embodiments .
  • the present application obtains a query set including a description of each query point; and converts the description of each query point into an attached position corresponding to each query point by a similarity measurement function based on the topic distribution. And a topic probability distribution of the time stamp; searching and matching each query point with a semantic trajectory data set in the database based on a corresponding topic probability distribution of each query point, searching for a candidate trajectory set of the query set; A candidate track set of the query set, calculating a distance between the query set and each candidate track in the candidate track set of the query set, and sorting the candidate track set of the query set according to the distance size; according to the sorted candidate track Set, output the result to the user.
  • the present application utilizes a semantic trajectory representation model to represent a query point and a track point in a database, and converts the text description of the track point and the query point into a topic probability distribution, that is, a series of topic probability distributions with position and time labels, enabling A good understanding of the intrinsic meaning of text descriptions, and their semantic associations are characterized by similarity based on topic distribution, thereby improving retrieval accuracy. Therefore, the present application can perform a query based on the trajectory related to the subject, thereby improving the retrieval precision.
  • FIG. 1 is a flow chart of a preferred embodiment of a track query method of the present application.
  • FIG. 2 is a functional block diagram of a preferred embodiment of the track query device of the present application.
  • FIG. 3 is a schematic structural diagram of a preferred embodiment of an electronic device in at least one example of the present application.
  • FIG. 1 it is a flowchart of a first preferred embodiment of the track query method of the present application.
  • the order of the steps in the flowchart may be changed according to different requirements, and some steps may be omitted.
  • the set of queries Q includes at least one query point.
  • a description of a plurality of locations input by a user on a user interface requires querying data of a description of the plurality of locations, wherein a description of the location is a query point, such as the financial of Company B under Ping An Technology.
  • the query set Q may include two query points, the query point one: a description of Ping An Technology Company, and a query point 2: a description of the company B.
  • each query point is composed of a textual description.
  • the text description includes a location and time tag.
  • the semantic trajectory representation model is used to represent the topic probability distribution with location and time tags corresponding to each query point.
  • the calculation formula corresponding to each topic TD W [Z i ] in the probability topic distribution TD W corresponding to W is as follows:
  • N w ⁇ (W ⁇ Wz) represents the number of keywords in W
  • ⁇ represents a symmetric boundary, usually set to 0.1
  • represents the number of keywords in W
  • represents the total number of topics.
  • each track point in the semantic trajectory data set includes position coordinates and topic distribution information
  • a hierarchical index structure including a spatial layer and a topic layer is established based on each track point including position coordinates and topic distribution information.
  • the spatial layer uses a quadtree to establish an index structure to achieve fast convergence in the spatial layer, and each leaf node in the quadtree of the spatial layer represents multiple track points, which is represented for each leaf node.
  • Track points, the LSH index structure corresponding to each leaf node based on the position-sensitive hash is established in the topic layer, so that similar track points in multiple track points represented by each leaf node are mapped to the same by using a hash function Hash bucket.
  • the quadtree index is a tree structure that recursively divides location information into different levels. Divide the space of the known range into four equal subspaces, and recursively until the level of the tree reaches a certain depth or stops the segmentation after satisfying certain requirements.
  • the structure of the quadtree is relatively simple, and when the spatial data objects are distributed evenly, the spatial data insertion and query efficiency are relatively high.
  • the track points are stored on the leaf nodes, and the middle nodes and the root nodes do not store track points.
  • the search is matched with the semantic trajectory data set corresponding to the topic probability distribution corresponding to each query point, and the candidate trajectory points of each query point are obtained, and the trajectory of the candidate trajectory points including each query point is taken as the Query Point of each query point.
  • a candidate track, the candidate track of each query point is used as a candidate track of the query set Q.
  • finding a candidate track of a query point q (the query point q is any one of the query points) comprises the following steps:
  • the priority queues are sorted in ascending order of mdist(q, N), the mdist( q, N) represents the minimum distance between the query point q and the plurality of track points represented by the leaf node N.
  • the formula for calculating mdist(q, N) is as follows:
  • D S (q, N) is the minimum boundary matrix N.rect based on the leaf node N, the smallest spatial distance from the query point q to the leaf node N;
  • D T (q, N) is from q to The minimum subject distance of the plurality of track points represented by the leaf node N.
  • a candidate track point, a track of a candidate track point including the query point is used as a candidate track of the query point, and a candidate track of the query point is used as a part of a candidate track of the query set Q.
  • the order in the priority queue is: the second node, the first node.
  • the multi-probe LSH indexing technique is used to traverse the track points under the second node, and then the track points under the first node are searched.
  • the multi-probe LSH indexing technique utilizes a carefully derived probing sequence to obtain a plurality of hash buckets approximate to the query point.
  • LSH we know that if the data close to the query point q is not mapped to the same bucket as the query point q, it is likely to be mapped to the surrounding bucket (ie, the hash values of the two buckets are only slightly The difference), so the goal of this method is to locate these adjacent buckets in order to increase the chances of finding neighbor data.
  • Each query point is queried according to the above steps (1) and (2), and candidate trajectories of each query point in the query set Q are obtained.
  • the similarity between each query point and the trajectory point in the semantic trajectory data set is calculated, and the similarity of the topic distribution is used to represent the relationship between the query point and the trajectory point of the semantic trajectory data set.
  • Semantic associations enable a better understanding of the intrinsic meaning of textual descriptions.
  • the query description "drinking coffee” and the track point description "Starbucks” will be considered relevant due to their similar subject distribution. This will make the query more accurate.
  • the query description "drinking coffee” and the track point description "Starbucks” will be considered relevant due to their similar topic distribution. This will make the query more accurate.
  • a semantic trajectory data set ⁇ a finite set of topics Z, a query set Q containing a series of query points, a user-specified shaping variable k(k ⁇
  • the User-oriented Trajectory Similarity Query returns independent k trajectories from ⁇ , and the k trajectories have a top-k minimum distance D Q (Tr) from the query set Q.
  • the calculating the distance between the query set Q and any one of the candidate track Tr in the candidate track set of the query set Q includes:
  • the distance from a track point p to its distance can be based on the spatial proximity and subject relevance metric between them.
  • the specific formula is as follows:
  • D S (q,p) is the spatial Euclidean distance. This paper also uses the sigmoid function to regulate the distance in the interval [ Between 0,1]; D T (q,p), is a simplification of D T (qW,pW), representing the subject distance between q and p text records.
  • the track point p can be expressed as the most relevant track point (MRP) in the track with the query point q, defined as Tr.MRP(q).
  • Tr.MRP(q) the most relevant track point
  • Tr.MRP(q) the distance from the most relevant point Tr.MRP(q) to the track point q is expressed as the distance from the query point to the track. Specifically, it can be defined as follows:
  • the most relevant point set MRPs of each query point in the query form the most relevant point set of the query, Tr.MRPs(Q), so the most relevant point set MRPs for finding a query set Q can be decomposed into Find the most relevant point MRP for each query point in the query.
  • the sorted candidate track sets are displayed on the user interface, and the sorted candidate track sets are sorted according to the distance from small to large. This allows the most relevant results to be displayed first for the user to visually see the most relevant query results.
  • the present application converts the description of each query point into a topic probability distribution with a position and time tag corresponding to each query point by a similarity measure function based on the topic distribution, based on the corresponding topic probability distribution of each query point, Searching and matching each query point with a semantic trajectory data set in the database, searching for a candidate trajectory set of the query set Q, and calculating the query set Q and the query set based on the candidate trajectory set of the query set Q
  • the candidate track set of Q is the distance of each track, and the candidate track set of the query set Q is sorted according to the distance size, and the result is output to the user according to the sorted candidate track set.
  • the present application utilizes a semantic trajectory representation model to represent a query point and a track point in a database, and converts the text description of the track point and the query point into a topic probability distribution, that is, a series of topic probability distributions with position and time labels, enabling Well understand the intrinsic meaning of text descriptions and characterize their semantic associations based on the similarity of topic distributions, thus improving retrieval accuracy.
  • FIG. 2 is a functional block diagram of a first preferred embodiment of the track query device of the present application.
  • the track query device 2 includes, but is not limited to, one or more of the following modules: an acquisition module 20, a conversion module 21, a lookup module 22, a sorting module 23, and an output module 24.
  • a unit referred to in this application refers to a series of computer readable instruction segments that can be executed by the processor of the track query device 2 and that are capable of performing fixed functions, which are stored in the memory. The function of each unit will be detailed in the subsequent embodiments.
  • the obtaining module 20 acquires a query set Q including a description of each query point.
  • the set of queries Q includes at least one query point.
  • a description of a plurality of locations input by a user on a user interface requires querying data of a description of the plurality of locations, wherein a description of the location is a query point, such as the financial of Company B under Ping An Technology.
  • the query set Q may include two query points, the query point one: a description of Ping An Technology Company, and a query point 2: a description of the company B.
  • the conversion module 21 converts the description of each query point into a topic probability distribution with a location and time tag corresponding to each query point.
  • each query point is composed of a textual description.
  • the text description includes a location and time tag.
  • the semantic trajectory representation model is used to represent the topic probability distribution with location and time tags corresponding to each query point.
  • the calculation formula corresponding to each topic TD W [Z i ] in the probability topic distribution TD W corresponding to W is as follows:
  • N w ⁇ (W ⁇ Wz) represents the number of keywords in W
  • ⁇ represents a symmetric boundary, usually set to 0.1
  • represents the number of keywords in W
  • represents the total number of topics.
  • the searching module 22 searches and matches each query point with the semantic trajectory data set in the database based on the corresponding topic probability distribution of each query point, and searches for the candidate track set of the query set Q.
  • each track point in the semantic trajectory data set includes position coordinates and topic distribution information
  • a hierarchical index structure including a spatial layer and a topic layer is established based on each track point including position coordinates and topic distribution information.
  • the spatial layer uses a quadtree to establish an index structure to achieve fast convergence in the spatial layer, and each leaf node in the quadtree of the spatial layer represents multiple track points, which is represented for each leaf node.
  • Track points, the LSH index structure corresponding to each leaf node based on the position-sensitive hash is established in the topic layer, so that similar track points in multiple track points represented by each leaf node are mapped to the same by using a hash function Hash bucket.
  • the quadtree index is a tree structure that recursively divides location information into different levels. Divide the space of the known range into four equal subspaces, and recursively until the level of the tree reaches a certain depth or stops the segmentation after satisfying certain requirements.
  • the structure of the quadtree is relatively simple, and when the spatial data objects are distributed evenly, the spatial data insertion and query efficiency are relatively high.
  • the track points are stored on the leaf nodes, and the middle nodes and the root nodes do not store track points.
  • the search is matched with the semantic trajectory data set corresponding to the topic probability distribution corresponding to each query point, and the candidate trajectory points of each query point are obtained, and the trajectory of the candidate trajectory points including each query point is taken as the Query Point of each query point.
  • a candidate track, the candidate track of each query point is used as a candidate track of the query set Q.
  • the searching module 22 searches for candidate tracks of a query point q (the query q point is any one of the query points), including the following steps:
  • the priority queues are sorted in ascending order of mdist(q, N), the mdist( q, N) represents the minimum distance between the query point q and the plurality of track points represented by the leaf node N.
  • the formula for calculating mdist(q, N) is as follows:
  • D S (q, N) is the minimum boundary matrix N.rect based on the leaf node N, the smallest spatial distance from the query point q to the leaf node N;
  • D T (q, N) is from q to The minimum subject distance of the plurality of track points represented by the leaf node N.
  • a candidate track point, a track of a candidate track point including the query point is used as a candidate track of the query point, and a candidate track of the query point is used as a part of a candidate track of the query set Q.
  • the order in the priority queue is: the second node, the first node.
  • the multi-probe LSH indexing technique is used to traverse the track points under the second node, and then the track points under the first node are searched.
  • the multi-probe LSH indexing technique utilizes a carefully derived probing sequence to obtain a plurality of hash buckets approximate to the query point.
  • LSH we know that if the data close to the query point q is not mapped to the same bucket as the query point q, it is likely to be mapped to the surrounding bucket (ie, the hash values of the two buckets are only slightly The difference), so the goal of this method is to locate these adjacent buckets in order to increase the chances of finding neighbor data.
  • Each query point is queried according to the above steps (1) and (2), and candidate trajectories of each query point in the query set Q are obtained.
  • the similarity between each query point and the trajectory point in the semantic trajectory data set is calculated, and the similarity of the topic distribution is used to represent the relationship between the query point and the trajectory point of the semantic trajectory data set.
  • Semantic associations enable a better understanding of the intrinsic meaning of textual descriptions.
  • the query description "drinking coffee” and the track point description "Starbucks" will be considered relevant due to their similar subject distribution. This will make the query more accurate.
  • the ranking module 23 calculates a distance between the query set Q and each track of the candidate track set of the query set Q based on the candidate track set of the query set Q, and selects the query set Q according to the distance size. Each candidate track in the track set is sorted.
  • a semantic trajectory data set ⁇ a finite set of topics Z, a query set Q containing a series of query points, a user-specified shaping variable k(k ⁇
  • the User-oriented Trajectory Similarity Query returns independent k trajectories from ⁇ , and the k trajectories have a top-k minimum distance D Q (Tr) from the query set Q.
  • the ranking module 23 calculates the distance between the query set Q and any one of the candidate track Tr in the candidate track set of the query set Q includes:
  • the distance from a track point p to its distance can be based on the spatial proximity and subject relevance metric between them.
  • the specific formula is as follows:
  • D S (q,p) is the spatial Euclidean distance. This paper also uses the sigmoid function to regulate the distance in the interval [ Between 0,1]; D T (q,p), is a simplification of D T (qW,pW), representing the subject distance between q and p text records.
  • the track point p can be expressed as the most relevant track point (MRP) in the track with the query point q, defined as Tr.MRP(q).
  • Tr.MRP(q) the most relevant track point
  • Tr.MRP(q) the distance from the most relevant point Tr.MRP(q) to the track point q is expressed as the distance from the query point to the track. Specifically, it can be defined as follows:
  • the most relevant point set MRPs of each query point in the query form the most relevant point set of the query, Tr.MRPs(Q), so the most relevant point set MRPs for finding a query set Q can be decomposed into Find the most relevant point MRP for each query point in the query.
  • the output module 24 outputs the result to the user according to the sorted candidate track set.
  • the output module 24 displays the sorted candidate track set on the user interface, and the sorted candidate track set is sorted according to the distance from small to large. This allows the most relevant results to be displayed first for the user to visually see the most relevant query results.
  • the present application converts the description of each query point into a topic probability distribution with a position and time tag corresponding to each query point by a similarity measure function based on the topic distribution, based on the corresponding topic probability distribution of each query point, Searching and matching each query point with a semantic trajectory data set in the database, searching for a candidate trajectory set of the query set Q, and calculating the query set Q and the query set based on the candidate trajectory set of the query set Q
  • the candidate track set of Q is the distance of each track, and the candidate track set of the query set Q is sorted according to the distance size, and the result is output to the user according to the sorted candidate track set.
  • the present application utilizes a semantic trajectory representation model to represent a query point and a track point in a database, and converts the text description of the track point and the query point into a topic probability distribution, that is, a series of topic probability distributions with position and time labels, enabling Well understand the intrinsic meaning of text descriptions and characterize their semantic associations based on the similarity of topic distributions, thus improving retrieval accuracy.
  • the above-described integrated unit implemented in the form of a software function module can be stored in a non-volatile readable storage medium.
  • the above software function module is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute the method described in each embodiment of the present application. Part of the steps.
  • the electronic device 3 comprises at least one transmitting device 31, at least one memory 32, at least one processor 33, at least one receiving device 34 and at least one communication bus.
  • the communication bus is used to implement connection communication between these components.
  • the electronic device 3 is a device capable of automatically performing numerical calculation and/or information processing according to an instruction set or stored in advance, and the hardware includes but is not limited to a microprocessor and an application specific integrated circuit (ASIC). ), Field-Programmable Gate Array (FPGA), Digital Signal Processor (DSP), embedded devices, etc.
  • the electronic device 3 may also comprise a network device and/or a user device.
  • the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud computing-based cloud composed of a large number of hosts or network servers, where the cloud computing is distributed computing.
  • a super virtual computer consisting of a group of loosely coupled computers.
  • the electronic device 3 can be, but is not limited to, any electronic product that can interact with a user through a keyboard, a touch pad, or a voice control device, such as a tablet, a smart phone, or a personal digital assistant (Personal Digital Assistant). , PDA), smart wearable devices, camera equipment, monitoring equipment and other terminals.
  • a keyboard e.g., a keyboard
  • a touch pad e.g., a touch pad
  • a voice control device such as a tablet, a smart phone, or a personal digital assistant (Personal Digital Assistant). , PDA), smart wearable devices, camera equipment, monitoring equipment and other terminals.
  • PDA Personal Digital Assistant
  • the network in which the electronic device 3 is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • the Internet includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), and the like.
  • VPN virtual private network
  • the receiving device 34 and the transmitting device 31 may be wired transmission ports, or may be wireless devices, for example, including antenna devices, for performing data communication with other devices.
  • the memory 32 is used to store program code.
  • the memory 32 may be a circuit having a storage function, such as a RAM (Random-Access Memory), a FIFO (First In First Out), or the like, which has no physical form in the integrated circuit.
  • the memory 32 may also be a memory having a physical form, such as a memory stick, a TF card (Trans-flash Card), a smart media card, a secure digital card, a flash memory card.
  • Storage devices such as (flash card) and the like.
  • the processor 33 can include one or more microprocessors, digital processors.
  • the processor 33 can call program code stored in the memory 32 to perform related functions. For example, the various modules described in FIG. 2 are program code stored in the memory 32 and executed by the processor 33 to implement a track query method.
  • the processor 33 also known as a central processing unit (CPU), is a very large-scale integrated circuit, which is a computing core (Core) and a control unit (Control Unit).
  • the embodiment of the present application further provides a non-volatile readable storage medium having stored thereon computer instructions that, when executed by an electronic device including one or more processors, cause the electronic device to perform the method as described above
  • the trajectory query method described in the example is not limited to:
  • the memory 32 in the electronic device 3 stores a plurality of instructions to implement a track query method, and the processor 33 can execute the plurality of instructions to implement:
  • the distances of each candidate track are concentrated, and each candidate track in the candidate track set of the query set is sorted according to the distance size; according to the sorted candidate track set, the result is output to the user.
  • the above-described characteristic means of the present application can be implemented by an integrated circuit and control the function of implementing the track query method in any of the above embodiments. That is, the integrated circuit of the present application is installed in the electronic device, so that the electronic device performs the following functions: acquiring a query set including a description of each query point; converting the description of each query point into a corresponding corresponding to each query point The topic probability distribution with the location and time tags; based on the corresponding topic probability distribution of each query point, each query point is searched and matched with the semantic trajectory data set in the database to find the candidate track set of the query set Calculating a distance between the query set and each candidate track in the candidate track set of the query set based on the candidate track set of the query set, and performing, for each candidate track in the candidate track set of the query set according to the distance size; Sort; output the result to the user according to the sorted candidate track set.
  • the functions that can be implemented by the trajectory query method in any of the embodiments can be installed in the electronic device by using the integrated circuit of the present application, so that the electronic device can be implemented by the trajectory query method in any embodiment. Function, no longer detailed here.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a non-volatile readable storage medium.
  • a computer device which may be a personal computer, server or network device, etc.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like.

Landscapes

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

Abstract

La présente invention concerne un procédé d'interrogation de suivi. Le procédé consiste à : acquérir des ensembles d'interrogations de descriptions comprenant tous les points d'interrogation ; convertir les descriptions de tous les points d'interrogation en distributions de probabilité de sujet qui ont des étiquettes de position et de temps fixées correspondant à tous les points d'interrogation ; rechercher et mettre en correspondance des ensembles de données de piste sémantiques dans une base de données pour tous les points d'interrogation sur la base des distributions de probabilité de sujet correspondant à tous les points d'interrogation, et rechercher des ensembles de pistes candidates des ensembles d'interrogations ; calculer la distance entre les ensembles d'interrogations et toutes les pistes candidates dans les ensembles de pistes candidates sur la base des ensembles de pistes candidates des ensembles d'interrogations, et trier toutes les pistes candidates dans les ensembles de pistes candidates des ensembles d'interrogations en fonction de la longueur des distances ; et fournir les résultats à un utilisateur en fonction des ensembles de pistes candidates triées. La présente invention concerne également un dispositif électronique et un support de stockage. La présente invention peut améliorer la précision de la recherche.
PCT/CN2018/100149 2018-04-04 2018-08-13 Procédé d'interrogation de suivi, dispositif électronique et support de stockage WO2019192120A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810303902.0A CN108536813B (zh) 2018-04-04 2018-04-04 轨迹查询方法、电子设备及存储介质
CN201810303902.0 2018-04-04

Publications (1)

Publication Number Publication Date
WO2019192120A1 true WO2019192120A1 (fr) 2019-10-10

Family

ID=63482647

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/100149 WO2019192120A1 (fr) 2018-04-04 2018-08-13 Procédé d'interrogation de suivi, dispositif électronique et support de stockage

Country Status (2)

Country Link
CN (1) CN108536813B (fr)
WO (1) WO2019192120A1 (fr)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109492150B (zh) * 2018-10-30 2021-07-27 石家庄铁道大学 基于语义轨迹大数据的反向最近邻查询方法及装置
CN111241217B (zh) * 2018-11-29 2023-05-30 阿里巴巴集团控股有限公司 数据处理的方法、装置和系统
CN110543457A (zh) * 2019-09-11 2019-12-06 北京明略软件系统有限公司 轨迹类文档处理方法和装置、存储介质及电子装置
CN111221353B (zh) * 2020-04-16 2020-08-14 上海特金信息科技有限公司 无人机的飞行轨迹处理方法、装置、电子设备与存储介质
CN112487256B (zh) * 2020-12-10 2024-05-24 中国移动通信集团江苏有限公司 对象查询方法、装置、设备及存储介质
CN112597190A (zh) * 2020-12-28 2021-04-02 京东城市(北京)数字科技有限公司 点近邻轨迹查询方法、装置、电子设备和可读存储介质
CN114117260B (zh) * 2021-12-02 2022-09-23 中国人民解放军国防科技大学 时空轨迹索引与查询处理方法、装置、设备及介质
CN115510303B (zh) * 2022-11-02 2023-04-14 深圳市瑞达飞行科技有限公司 一种离场程序的识别方法、系统、计算机设备及存储介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102214215A (zh) * 2011-06-07 2011-10-12 陆嘉恒 一种基于文本信息的快速反近邻查询方法
CN104834679A (zh) * 2015-04-14 2015-08-12 苏州大学 一种行为轨迹的表示、查询方法及装置

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102214215A (zh) * 2011-06-07 2011-10-12 陆嘉恒 一种基于文本信息的快速反近邻查询方法
CN104834679A (zh) * 2015-04-14 2015-08-12 苏州大学 一种行为轨迹的表示、查询方法及装置

Also Published As

Publication number Publication date
CN108536813A (zh) 2018-09-14
CN108536813B (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
WO2019192120A1 (fr) Procédé d'interrogation de suivi, dispositif électronique et support de stockage
CN108038183B (zh) 结构化实体收录方法、装置、服务器和存储介质
JP6434542B2 (ja) 検索のためのテーブルの理解
JP6402653B2 (ja) 物体認識装置、物体認識方法、およびプログラム
CN108304444B (zh) 信息查询方法及装置
JP6216467B2 (ja) 視覚・意味複合ネットワーク、および当該ネットワークを形成するための方法
CN102750375B (zh) 一种基于随机游走的服务和标签推荐方法
CN106484764A (zh) 基于人群画像技术的用户相似度计算方法
US8527564B2 (en) Image object retrieval based on aggregation of visual annotations
WO2022141876A1 (fr) Procédé, appareil et dispositif de recherche basés sur l'incorporation de mots, et support de stockage
WO2018176913A1 (fr) Procédé et appareil de recherche, et support d'informations lisible par ordinateur non temporaire
WO2019227581A1 (fr) Procédé de reconnaissance de point d'intérêt, appareil, borne et support d'informations
CN106294815B (zh) 一种url的聚类方法及装置
CN116881436A (zh) 基于知识图谱的文献检索方法、系统、终端及存储介质
CN103761286B (zh) 一种基于用户兴趣的服务资源检索方法
KR20100023630A (ko) 카테고리 태그 정보를 이용한 웹 페이지 분류 방법, 그 시스템 및 이를 기록한 기록매체
CN112925912B (zh) 文本处理方法、同义文本召回方法及装置
CN114328800A (zh) 文本处理方法、装置、电子设备和计算机可读存储介质
Li et al. A probabilistic topic-based ranking framework for location-sensitive domain information retrieval
Hu et al. Embracing information explosion without choking: Clustering and labeling in microblogging
JP5486667B2 (ja) クエリ結果を多様化するための方法および装置
JP5362807B2 (ja) ドキュメントランク付け方法および装置
CN106777395A (zh) 一种基于社区文本数据的话题发现系统
TW202004519A (zh) 影像自動分類的方法
Zaw et al. Web document clustering using Gauss distribution based cuckoo search clustering algorithm

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 1205 DATED 01/02/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18913409

Country of ref document: EP

Kind code of ref document: A1