CN110737786A - data comparison collision method and device - Google Patents
data comparison collision method and device Download PDFInfo
- Publication number
- CN110737786A CN110737786A CN201910954940.7A CN201910954940A CN110737786A CN 110737786 A CN110737786 A CN 110737786A CN 201910954940 A CN201910954940 A CN 201910954940A CN 110737786 A CN110737786 A CN 110737786A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- space
- spatiotemporal
- collision
- 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.)
- Withdrawn
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
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses data comparison collision methods and devices, and the method comprises the steps of obtaining a designated space-time range, carrying out data processing on track data in the space-time range, wherein the data processing comprises the steps of standardizing the track data into space-time data and carrying out space-time index processing on the space-time data, extracting collision data to be compared from a preset space-time feature library according to space-time index dimensions obtained after the space-time index processing, carrying out track similarity calculation on the track data and the collision data to be compared, and completing the space-time data comparison collision.
Description
Technical Field
The present invention relates to data processing technologies, and in particular, to data comparison collision methods and apparatuses.
Background
The problem of trajectory comparison collision is that trajectory correlation are compared and searched, and the correlation between entities such as found people or objects in a public security service scene is provided, clues in actual research, judgment and analysis are found through the correlation, and technical support is provided for work such as public security case solving, intelligence and the like.
The prior art uses rule calculation to directly calculate the original trajectory data by giving a data collision rule, and completes the trajectory comparison collision requirement of the client according to the rule matching of time and space, and the calculation amount is large and the comparison speed is slow.
Disclosure of Invention
The embodiment of the invention provides data comparison collision methods and devices, which can rapidly complete data extraction, reduce the calculated amount and realize rapid comparison collision of real-time tracks.
To achieve the purpose of the embodiment of the present invention, the embodiment of the present invention provides data alignment collision methods, where the method may include:
acquiring a specified space-time range;
carrying out data processing on the trajectory data in the space-time range; the data processing comprises: standardizing the trajectory data into space-time data and performing space-time index processing on the space-time data;
extracting collision data to be compared from a preset time-space feature library according to the time-space index dimension obtained after the time-space index processing;
and calculating the track similarity of the track data and the collision data to be compared to finish the comparison and collision of the spatio-temporal data.
In an exemplary embodiment of the present invention, the normalizing the trajectory data into spatiotemporal data may include:
assigning -only entity identities IDs to behavioral entities associated with the trajectory data;
defining each spatial position in the trajectory data as unique spatial location IDs;
and equally dividing the acquisition time in the track data into equal parts according to a preset time interval.
In an exemplary embodiment of the present invention, the normalizing the trajectory data into spatiotemporal data may further include: tabulating the spatiotemporal data;
the tabulating the spatiotemporal data comprises:
directory item with entity ID as table;
using the space place ID as a second item directory;
and taking the acquisition time as a third item list, wherein every equally divided time periods are sequentially listed in the third item list according to the time sequence.
In an exemplary embodiment of the invention, the spatiotemporal index dimensions may include any or more of an entity dimension, a time dimension, and a space dimension;
the spatiotemporal indexing of the spatiotemporal data comprises storing the spatiotemporal data according to or more preset spatiotemporal indexing dimensions.
In an exemplary embodiment of the invention, storing the spatiotemporal data according to entity dimensions may include storing all spatial positions corresponding to each entity ID in a preset th place slice, storing all equally-divided period data corresponding to each entity ID in a preset th time slice, and compressing the th place slice and the th time slice corresponding to each entity ID into a th file.
In an exemplary embodiment of the invention, storing the spatiotemporal data according to spatial dimensions may include storing all entity IDs corresponding to each spatial position in a preset th entity slice, storing all equally-divided period data corresponding to each spatial position in a preset second time slice, and compressing th entity slice and the second time slice corresponding to each spatial position in a second file.
In an exemplary embodiment of the present invention, storing the spatiotemporal data in a time dimension may include: and storing all entity IDs corresponding to each equal time interval into a preset second entity fragment, storing all spatial positions corresponding to each equal time interval into a preset second place fragment, and compressing the second entity fragment and the second place fragment corresponding to each equal time interval into a third file.
In an exemplary embodiment of the invention, the method may further include performing the data processing on every trajectory data acquired in real time in advance, and storing spatiotemporal index data obtained after the data processing into a specified database to constitute the spatiotemporal feature library.
In an exemplary embodiment of the present invention, the calculating the trajectory similarity between the trajectory data and the collision data to be compared may include:
th track vector of the track data and a second track vector of the collision data to be compared are obtained;
calculating the similarity of the th track vector and the second track vector according to a cosine similarity algorithm;
and comparing the calculation result with a preset similarity threshold, and determining whether the th space-time trajectory corresponding to the trajectory data is similar to the second space-time trajectory corresponding to the collision data to be compared according to the comparison result.
An data comparison collision device provided by the embodiments of the present invention may include a processor and a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed by the processor, the data comparison collision method described in any above is implemented.
The embodiment of the invention comprises the steps of obtaining a specified space-time range; carrying out data processing on the trajectory data in the space-time range; the data processing comprises: standardizing the trajectory data into space-time data and performing space-time index processing on the space-time data; extracting collision data to be compared from a preset time-space feature library according to the time-space index dimension obtained after the time-space index processing; and calculating the track similarity of the track data and the collision data to be compared to finish the comparison and collision of the spatio-temporal data. Through the scheme of the embodiment, the space-time trajectory data in the given space-time range of the electronic map is quickly converted into the space-time dimension index data, the data extraction is quickly completed, the calculated amount is reduced, and the quick comparison and collision of the real-time trajectory are realized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the present invention and constitute a part of this specification, serve to explain the present invention with example of the present application and do not constitute a limitation on the present invention.
FIG. 1 is a flow chart of a data comparison collision method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data comparison collision method according to an embodiment of the present invention;
fig. 3 is a block diagram of a data comparison collision device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
The steps illustrated in the flowchart of the figure may be performed in a computer system such as sets of computer-executable instructions and, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that illustrated herein.
To achieve the object of the embodiment of the present invention, the embodiment of the present invention provides data alignment collision methods, as shown in fig. 1 and fig. 2, the methods may include S101 to S104:
and S101, acquiring a specified space-time range.
In an exemplary embodiment of the present invention, the spatiotemporal range may be a spatiotemporal range circled on an electronic map, or may be a spatiotemporal range given by spatiotemporal range data and/or names (e.g., time period, longitude and latitude, location, etc.).
S102, carrying out data processing on the trajectory data in the space-time range; the data processing comprises: and standardizing the trajectory data into space-time data and performing space-time index processing on the space-time data.
In an exemplary embodiment of the present invention, the spatiotemporal range and/or the given spatiotemporal range on the selected electronic map may be represented as spatiotemporal indexes (or spatiotemporal dimension indexes), so as to obtain the required trajectory records (i.e. the collision data to be compared) from the spatiotemporal dimension index into the corresponding index file (such as the spatiotemporal feature library described below) to find the trajectory records of the collision.
In an exemplary embodiment of the present invention, the normalizing the trajectory data into spatiotemporal data may include:
assigning -only entity identities IDs to behavioral entities associated with the trajectory data;
defining each spatial position in the trajectory data as unique spatial location IDs;
and equally dividing the acquisition time in the track data into equal parts according to a preset time interval.
In an exemplary embodiment of the present invention, the normalizing the trajectory data into spatiotemporal data may further include: tabulating the spatiotemporal data;
the tabulating the spatiotemporal data comprises:
directory item with entity ID as table;
using the space place ID as a second item directory;
and taking the acquisition time as a third item list, wherein every equally divided time periods are sequentially listed in the third item list according to the time sequence.
In an exemplary embodiment of the present invention, the trajectory data is normalized to spatiotemporal data, and the trajectory data is stored in the form of a determined entity ID, time, and place ID.
In an exemplary embodiment of the invention, the track data is normalized to provide a normalized track data format and a normalized track data time interval to provide an input to the system for the following spatio-temporal feature extraction the normalized track data format may be as shown in table and table two, where table is a wireless fidelity Wifi fence data sample and table two is an electronic fence data sample:
TABLE
Physical address MAC | Start time STARTTIME | LOCATION of LOCATION |
DA:A1:19:17:AC:12 | 2019-08-06 16:20:13 | Location ID1 |
DA:A5:11:19:AC:10 | 2019-08-05 16:20:12 | Location ID2 |
Watch two
Each behavioral entity (e.g., car, person, etc.) may be assigned a -only entity ID, which is referred to as directory, each spatial locality is defined as spatial locality IDs, which is referred to as a second directory, and then the data is divided equally at preset time intervals (e.g., 24 hours per day), and the data for each divided period (e.g., each hour) is stored under entries, where the data for each divided period (e.g., hours) is deduplicated, which greatly reduces the amount of data storage.
Watch III
Entity ID | Location ID | Time of acquisition |
001 | 100 | 2019-08-15 16:05:10 |
001 | 100 | 2019-08-15 17:35:20 |
001 | 100 | 2019-08-15 18:55:50 |
001 | 101 | 2019-08-15 17:05:10 |
001 | 101 | 2019-08-15 18:35:20 |
001 | 101 | 2019-08-15 19:55:50 |
In an exemplary embodiment of the invention, the spatiotemporal index dimensions may include any or more of an entity dimension, a time dimension, and a space dimension;
the spatiotemporal indexing of the spatiotemporal data comprises storing the spatiotemporal data according to or more preset spatiotemporal indexing dimensions.
In an exemplary embodiment of the present invention, spatio-temporal index processing, that is, spatio-temporal data fragmentation storage, specifically, spatio-temporal data is processed according to defined attributes and formats, then the processed data is fragmented according to defined entities, places and times, and finally corresponding data is stored in corresponding fragments.
In an exemplary embodiment of the invention, the spatiotemporal data constructs a spatiotemporal dimension index, and the purpose is to construct a dimension index for the spatiotemporal data according to the dimensions of an entity, time or space, and the like, so as to accelerate data search by a dimension index method.
In the exemplary embodiment of the invention, types of calculation in the space-time trajectory comparison collision is calculation of the similarity of trajectory data of a plurality of different types of entity IDs, for example, pieces of data of a certain vehicle with partial trajectories are given, similar trajectories of other vehicles related to the certain vehicle or trajectories with IMSI numbers collected by a checkpoint are found through the partial trajectory data.
In an exemplary embodiment of the present invention, for the above scenario of comparing and colliding trajectory data of different types of entity IDs, a spatio-temporal index dimension may be determined as an entity dimension, and the spatio-temporal data is stored according to the entity dimension.
In an exemplary embodiment of the invention, storing the spatiotemporal data according to entity dimensions may include storing all spatial positions corresponding to each entity ID in a preset th place slice, storing all equally-divided period data corresponding to each entity ID in a preset th time slice, and compressing the th place slice and the th time slice corresponding to each entity ID into a th file.
In the exemplary embodiment of the present invention, the above scheme mainly converts the spatiotemporal position corresponding to each entity ID into spatiotemporal trajectory memory slice, and then compresses and stores the information in files, so as to be able to quickly retrieve the spatiotemporal point of a specific entity ID.
Watch four
In an exemplary embodiment of the present invention, the spatiotemporal data may also be stored according to a time dimension and a space dimension for different application scenarios, so as to implement a fast search according to different dimensions.
In an exemplary embodiment of the invention, storing the spatiotemporal data according to spatial dimensions may include storing all entity IDs corresponding to each spatial position in a preset th entity slice, storing all equally-divided period data corresponding to each spatial position in a preset second time slice, and compressing th entity slice and the second time slice corresponding to each spatial position in a second file.
In an exemplary embodiment of the present invention, storing the spatiotemporal data in a time dimension may include: and storing all entity IDs corresponding to each equal time interval into a preset second entity fragment, storing all spatial positions corresponding to each equal time interval into a preset second place fragment, and compressing the second entity fragment and the second place fragment corresponding to each equal time interval into a third file.
S103, extracting collision data to be compared from a preset space-time feature library according to the space-time index dimension obtained after the space-time index processing.
In an exemplary embodiment of the invention, the method may further include performing the data processing on every trajectory data acquired in real time in advance, and storing spatiotemporal index data obtained after the data processing into a specified database to constitute the spatiotemporal feature library.
In an exemplary embodiment of the present invention, when a large amount of trajectory data acquired in real time is subjected to data processing, normalized spatiotemporal data may be stored in any or more of a physical dimension, a temporal dimension, and a spatial dimension, so as to rapidly extract data from a spatiotemporal feature library according to different dimensions.
In an exemplary embodiment of the invention, in an actual scene of a specific comparison collision, after a corresponding space-time range is directly obtained through electronic map selection or giving of the space-time range, corresponding dimension processing of space-time data can be completed through data standardization and space-time index processing, so that corresponding data is extracted from a space-time feature library through the dimension to serve as collision data to be compared.
And S104, calculating the track similarity of the track data and the collision data to be compared to finish the comparison and collision of the spatio-temporal data.
In an exemplary embodiment of the present invention, the calculating the trajectory similarity between the trajectory data and the collision data to be compared may include:
th track vector of the track data and a second track vector of the collision data to be compared are obtained;
calculating the similarity of the th track vector and the second track vector according to a cosine similarity algorithm;
and comparing the calculation result with a preset similarity threshold, and determining whether the th space-time trajectory corresponding to the trajectory data is similar to the second space-time trajectory corresponding to the collision data to be compared according to the comparison result.
In the exemplary embodiment of the invention, a similarity threshold value can be preset to provide a basis for similarity calculation and accelerate the search of the spatio-temporal feature vectors, so that the comparison collision of spatio-temporal trajectories is realized quickly.
In an exemplary embodiment of the present invention, it may be determined that two spatiotemporal trajectories are similar when the calculated similarity is greater than or equal to the similarity threshold. Namely, the trajectory similarity calculation of the trajectory data and the collision data to be compared is substantially carried out through the comparison of the feature vectors, and the trajectories with the similarity larger than or equal to the set similarity threshold are searched in the feature vector set.
In an exemplary embodiment of the present invention, the similarity calculation of two spatio-temporal feature vectors may be completed using a cosine similarity algorithm, that is, the similarity of two vector representations is obtained by performing cosine similarity calculation respectively on a vector representation of a given query trajectory and a vector representation of a searched trajectory in a vector set.
In the exemplary embodiment of the invention, the trajectory data in the given or electronic map selected space-time range is quickly mapped to the space-time dimension index space through the scheme of the embodiment of the invention, and then the space-time dimension comparison collision calculation is completed through the trajectory similarity calculation, so that the quick data extraction is completed, the calculation amount is reduced, and the quick comparison collision of the real-time trajectory is realized.
An data comparison collision device 1 is provided, as shown in fig. 3, and may include a processor 11 and a computer-readable storage medium 12, where the computer-readable storage medium 12 stores instructions, and when the instructions are executed by the processor 11, the data comparison collision method described in any above is implemented.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods disclosed above, functional modules/units in systems, devices may be implemented as software, firmware, hardware, and suitable combinations thereof, in a hardware implementation, the division between functional modules/units mentioned in the above description is not a division corresponding to physical components, e.g., physical components may have multiple functions, or functions or steps may be performed cooperatively by several physical components.
Claims (10)
1, data alignment collision method, which is characterized in that the method comprises:
acquiring a specified space-time range;
carrying out data processing on the trajectory data in the space-time range; the data processing comprises: standardizing the trajectory data into space-time data and performing space-time index processing on the space-time data;
extracting collision data to be compared from a preset time-space feature library according to the time-space index dimension obtained after the time-space index processing;
and calculating the track similarity of the track data and the collision data to be compared to finish the comparison and collision of the spatio-temporal data.
2. The data alignment collision method according to claim 1, wherein the normalizing the trajectory data into spatiotemporal data comprises:
assigning -only entity identities IDs to behavioral entities associated with the trajectory data;
defining each spatial position in the trajectory data as unique spatial location IDs;
and equally dividing the acquisition time in the track data into equal parts according to a preset time interval.
3. The data alignment collision method according to claim 2, wherein the normalizing the trajectory data into spatiotemporal data further comprises: tabulating the spatiotemporal data;
the tabulating the spatiotemporal data comprises:
directory item with entity ID as table;
using the space place ID as a second item directory;
and taking the acquisition time as a third item list, wherein every equally divided time periods are sequentially listed in the third item list according to the time sequence.
4. The data alignment collision method of claim 2, wherein the spatiotemporal index dimensions include any or more of a physical dimension, a temporal dimension, and a spatial dimension;
the spatiotemporal indexing of the spatiotemporal data comprises storing the spatiotemporal data according to or more preset spatiotemporal indexing dimensions.
5. The data comparison collision method according to claim 4, wherein the storing the spatiotemporal data according to the entity dimensions comprises storing all spatial positions corresponding to each entity ID into a preset th place slice, storing all equally-divided period data corresponding to each entity ID into a preset th time slice, and compressing the th place slice and the th time slice corresponding to each entity ID into a th file.
6. The data comparison and collision method as claimed in claim 4, wherein the storing the spatiotemporal data according to spatial dimensions comprises storing all entity IDs corresponding to each spatial position in a preset th entity slice, storing all equally-divided period data corresponding to each spatial position in a preset second time slice, and compressing the th entity slice and the second time slice corresponding to each spatial position in a second file.
7. The data comparison collision method of claim 4, wherein storing the spatiotemporal data in a time dimension comprises: and storing all entity IDs corresponding to each equal time interval into a preset second entity fragment, storing all spatial positions corresponding to each equal time interval into a preset second place fragment, and compressing the second entity fragment and the second place fragment corresponding to each equal time interval into a third file.
8. The data comparison collision method as claimed in any of claims 1-7, further comprising pre-processing each trace data collected in real time and storing the spatio-temporal index data obtained after data processing into a designated database to form the spatio-temporal feature library.
9. The data alignment collision method according to any of claims 1-7 , wherein the calculating the trajectory similarity of the trajectory data and the collision data to be aligned comprises:
th track vector of the track data and a second track vector of the collision data to be compared are obtained;
calculating the similarity of the th track vector and the second track vector according to a cosine similarity algorithm;
and comparing the calculation result with a preset similarity threshold, and determining whether the th space-time trajectory corresponding to the trajectory data is similar to the second space-time trajectory corresponding to the collision data to be compared according to the comparison result.
10, data alignment collision device, comprising a processor and a computer readable storage medium having instructions stored therein, wherein the instructions, when executed by the processor, implement the data alignment collision method of any of claims 1-9- .
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910954940.7A CN110737786A (en) | 2019-10-09 | 2019-10-09 | data comparison collision method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910954940.7A CN110737786A (en) | 2019-10-09 | 2019-10-09 | data comparison collision method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110737786A true CN110737786A (en) | 2020-01-31 |
Family
ID=69268504
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910954940.7A Withdrawn CN110737786A (en) | 2019-10-09 | 2019-10-09 | data comparison collision method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110737786A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325267A (en) * | 2020-02-18 | 2020-06-23 | 京东城市(北京)数字科技有限公司 | Data fusion method, device and computer readable storage medium |
CN111352974A (en) * | 2020-03-02 | 2020-06-30 | 北京明略软件系统有限公司 | Data processing method and device, storage medium and electronic device |
CN111563137A (en) * | 2020-04-28 | 2020-08-21 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
CN111831769A (en) * | 2020-06-18 | 2020-10-27 | 汉海信息技术(上海)有限公司 | Track processing method and device, electronic equipment and storage medium |
CN112383875A (en) * | 2020-06-28 | 2021-02-19 | 中国信息通信研究院 | Data processing method and electronic equipment |
CN113326257A (en) * | 2020-04-30 | 2021-08-31 | 阿里巴巴集团控股有限公司 | Index construction method, recommendation method, device, electronic equipment and computer storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107590250A (en) * | 2017-09-18 | 2018-01-16 | 广州汇智通信技术有限公司 | A kind of space-time orbit generation method and device |
CN109165215A (en) * | 2018-07-27 | 2019-01-08 | 苏州视锐信息科技有限公司 | Construction method, device and the electronic equipment of temporal index under a kind of cloud environment |
CN110275885A (en) * | 2019-06-12 | 2019-09-24 | 南京邮电大学 | Multi-level track data storage device based on Hadoop |
CN110287391A (en) * | 2019-06-12 | 2019-09-27 | 南京邮电大学 | Multi-level trajectory data storage method, storage medium and terminal based on Hadoop |
-
2019
- 2019-10-09 CN CN201910954940.7A patent/CN110737786A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107590250A (en) * | 2017-09-18 | 2018-01-16 | 广州汇智通信技术有限公司 | A kind of space-time orbit generation method and device |
CN109165215A (en) * | 2018-07-27 | 2019-01-08 | 苏州视锐信息科技有限公司 | Construction method, device and the electronic equipment of temporal index under a kind of cloud environment |
CN110275885A (en) * | 2019-06-12 | 2019-09-24 | 南京邮电大学 | Multi-level track data storage device based on Hadoop |
CN110287391A (en) * | 2019-06-12 | 2019-09-27 | 南京邮电大学 | Multi-level trajectory data storage method, storage medium and terminal based on Hadoop |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325267A (en) * | 2020-02-18 | 2020-06-23 | 京东城市(北京)数字科技有限公司 | Data fusion method, device and computer readable storage medium |
CN111325267B (en) * | 2020-02-18 | 2024-02-13 | 京东城市(北京)数字科技有限公司 | Data fusion method, device and computer readable storage medium |
CN111352974A (en) * | 2020-03-02 | 2020-06-30 | 北京明略软件系统有限公司 | Data processing method and device, storage medium and electronic device |
CN111563137A (en) * | 2020-04-28 | 2020-08-21 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
CN111563137B (en) * | 2020-04-28 | 2022-05-17 | 厦门市美亚柏科信息股份有限公司 | Analysis method and system for coincident track |
CN113326257A (en) * | 2020-04-30 | 2021-08-31 | 阿里巴巴集团控股有限公司 | Index construction method, recommendation method, device, electronic equipment and computer storage medium |
CN113326257B (en) * | 2020-04-30 | 2023-12-15 | 阿里巴巴集团控股有限公司 | Index construction method, recommendation method, device, electronic equipment and computer storage medium |
CN111831769A (en) * | 2020-06-18 | 2020-10-27 | 汉海信息技术(上海)有限公司 | Track processing method and device, electronic equipment and storage medium |
CN112383875A (en) * | 2020-06-28 | 2021-02-19 | 中国信息通信研究院 | Data processing method and electronic equipment |
CN112383875B (en) * | 2020-06-28 | 2021-07-30 | 中国信息通信研究院 | Data processing method and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110737786A (en) | data comparison collision method and device | |
CN109634946B (en) | Intelligent track matching correlation analysis method based on big data mining | |
CN106453437B (en) | equipment identification code acquisition method and device | |
EP2973034B1 (en) | Methods and systems for arranging and searching a database of media content recordings | |
CN109784270B (en) | Processing method for improving face picture recognition integrity | |
CA2905385C (en) | Methods and systems for arranging and searching a database of media content recordings | |
CN109376940B (en) | Method and device for acquiring rainfall spatial-temporal distribution rule in rainfall process | |
CN107665289B (en) | Operator data processing method and system | |
CN112966137A (en) | Image retrieval method and system based on global and local feature rearrangement | |
CN109492066B (en) | Method, device, equipment and storage medium for determining branch names of points of interest | |
US10088324B2 (en) | Trajectory data compression | |
CN112232148A (en) | Image clustering method, target track tracking method, electronic device and storage medium | |
CN111831852A (en) | Video retrieval method, device, equipment and storage medium | |
CN110851675B (en) | Data extraction method, device and medium | |
CN115422479A (en) | Track association method and device, electronic equipment and machine-readable storage medium | |
CN114078277A (en) | One-person-one-file face clustering method and device, computer equipment and storage medium | |
CN111666443A (en) | Service processing method and device, electronic equipment and computer readable storage medium | |
CN111177195A (en) | Data comparison collision method and device | |
CN106575353B (en) | Hash-based media search | |
CN110765221A (en) | Management method and device of space-time trajectory data | |
CN109471907B (en) | Traffic law analysis system and method based on checkpoint data | |
CN105468748B (en) | Distributed storage position data method and system | |
CN102446186B (en) | Chinese geocoding and coding/decoding method and device | |
CN111860222B (en) | Video behavior recognition method, system, computer device and storage medium based on dense-segmented frame sampling | |
CN109408727B (en) | Intelligent user attention information recommendation method and system based on multidimensional perception data |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200131 |