CN107784046B - POI information processing method and device - Google Patents
POI information processing method and device Download PDFInfo
- Publication number
- CN107784046B CN107784046B CN201611005761.1A CN201611005761A CN107784046B CN 107784046 B CN107784046 B CN 107784046B CN 201611005761 A CN201611005761 A CN 201611005761A CN 107784046 B CN107784046 B CN 107784046B
- Authority
- CN
- China
- Prior art keywords
- poi
- terminals
- terminal
- track
- space
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
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)
- Navigation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a POI information processing method and a device, wherein the method comprises the following steps: acquiring position information of a plurality of terminals; mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space; marking the position information as track points of the terminal in the POI space, and generating a movable track corresponding to the terminal by using a plurality of track points; and calculating the similarity between the plurality of terminals by using the activity track and the POI information. By adopting the method, the user activity tracks can be compared across areas.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for processing Point of Interest (POI) information.
Background
With the development of internet technology, a variety of researches for analyzing user behaviors emerge. Wherein, the user behavior can be analyzed through the activity track of the user. The activity track of the user may be determined from the geographic location information of the user. In a conventional manner, only GPS (Global Positioning System) information is used as the geographical location information, and the information is too deficient. It is difficult to compare the user activity traces in different areas due to the lack of corresponding context information. How to compare the user activity tracks in different areas becomes a technical problem to be solved at present.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a POI information processing method and apparatus that can compare the user activity tracks across areas.
A POI information processing method, the method comprising:
acquiring position information of a plurality of terminals;
mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space;
marking the position information as track points of the terminal in the POI space, and generating a movable track corresponding to the terminal by using a plurality of track points;
and calculating the similarity between the plurality of terminals by using the activity track and the POI information.
In one embodiment, the mapping the location information to a POI space, and the retrieving the POI information in a preset range corresponding to the location information in the POI space includes:
determining a positioning grid of the terminal in an electronic map according to the position information;
acquiring a plurality of corresponding nearby grids in the preset range of the positioning grid;
and searching interest points in the positioning grid and the nearby grid to obtain POI information in a preset range corresponding to the position information.
In one embodiment, after the step of calculating the similarity between the plurality of terminals by using the activity track and the POI information, the method further includes:
acquiring a distance function for calculating the similarity between a plurality of terminals;
and extracting the space vectors of the plurality of terminals in the POI space by using the activity tracks and the distance functions of the plurality of terminals.
In one embodiment, after the step of extracting the space vectors of the plurality of terminals in the POI space according to the similarity between the plurality of terminals, the method further includes:
obtaining a prediction model;
inputting the space vectors of a plurality of terminals into the prediction model;
and predicting the consumption tendency corresponding to the plurality of terminals through the prediction model.
In one embodiment, after the step of calculating the similarity between the plurality of terminals by using the activity track and the POI information, the method further includes:
extracting a plurality of activity tracks with similarity within a preset range;
recording a plurality of activity tracks with the similarity within a preset range as similar tracks;
after the step of predicting the consumption tendency corresponding to a plurality of terminals through the prediction model, the method further comprises the following steps:
and acquiring corresponding recommendation information according to the consumption tendency, and sending the recommendation information to a plurality of terminals corresponding to similar tracks.
A POI information processing apparatus, the apparatus comprising:
the acquisition module is used for acquiring the position information of a plurality of terminals;
the retrieval module is used for mapping the position information to a POI space and retrieving POI information in a preset range corresponding to the position information in the POI space;
the recording module is used for marking the position information as a track point of the terminal in the POI space;
the track generation module is used for generating a movable track corresponding to the terminal by utilizing the plurality of track points;
and the calculating module is used for calculating the similarity between the plurality of terminals by using the activity track and the POI information.
In one embodiment, the retrieval module is further configured to determine a positioning grid of the terminal in an electronic map according to the location information; acquiring a plurality of corresponding nearby grids in the preset range of the positioning grid; and searching interest points in the positioning grid and the nearby grid to obtain POI information in a preset range corresponding to the position information.
In one embodiment, the obtaining module is further configured to obtain a distance function for calculating similarity between the plurality of terminals;
the device further comprises:
and the vector extraction module is used for extracting the space vectors of the plurality of terminals in the POI space by using the activity tracks and the distance functions of the plurality of terminals.
In one embodiment, the obtaining module is further configured to obtain a prediction model;
the device further comprises:
an input module, configured to input spatial vectors of a plurality of terminals into the prediction model;
and the prediction module is used for predicting the consumption tendency corresponding to the plurality of terminals through the prediction model.
In one embodiment, the obtaining module is further configured to extract a plurality of activity tracks with similarity within a preset range; the recording module is further used for recording a plurality of activity tracks with the similarity within a preset range as similar tracks; the acquisition module is also used for acquiring corresponding recommendation information according to the consumption tendency;
the device further comprises:
and the sending module is used for sending the recommendation information to a plurality of terminals corresponding to the similar tracks.
According to the POI information processing method and device, the position information of the plurality of terminals is mapped to the POI space, the POI information in the preset range of the position information is retrieved in the POI space, the position information is marked as track points of the terminals in the POI space, and the plurality of track points are used for generating the movable track corresponding to the terminals. Since the POI information can reflect the environment condition of the terminal, the comparison of the activity tracks of different users across the area can be realized by calculating the similarity between a plurality of terminals according to the activity track and the POI information.
Drawings
FIG. 1 is a flowchart of a POI information processing method in one embodiment;
FIG. 2 is a diagram of a Sudoku search in one embodiment;
FIG. 3 is a diagram of circle search in one embodiment;
FIG. 4 is a diagram illustrating the display of POI information in an electronic map, in one embodiment;
FIG. 5 is a schematic diagram of a server in one embodiment;
FIG. 6 is a schematic configuration diagram of a POI information processing apparatus in one embodiment;
fig. 7 is a schematic configuration diagram of a POI information processing apparatus in another embodiment;
fig. 8 is a schematic structural view of a POI information processing apparatus in yet another embodiment;
fig. 9 is a schematic configuration diagram of a POI information processing apparatus in still another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In an embodiment, as shown in fig. 1, a POI information processing method is provided, which is described by taking an example that the method is applied to a server, and specifically includes:
and 102, acquiring the position information of a plurality of terminals.
The terminal may have a positioning function by which location information of a geographical location where the terminal is located may be captured. The location information may be expressed in terms of longitude and latitude. And the terminal uploads the position information to the server. The plurality of terminals may upload the location information to the server at the same time, or may upload the location information to the server at different times, respectively.
And step 104, mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space.
The POI space refers to a space including POI information. The POI information includes a name, a category, a longitude, a latitude, and the like. The POI space may be a plurality of dimensions, which may be determined according to categories in the POI information. For example, dimensions include: finance, education, dining, entertainment, and the like. The POI space can also be considered as a multi-dimensional space. Different POIs may be located in different buildings or may be located within the same building. The server can map the position information uploaded by the terminals into the POI space, and retrieve the POI information of multiple dimensions in a preset range corresponding to the position information in the POI space.
In one embodiment, mapping the location information to a POI space, and retrieving POI information in a preset range corresponding to the location information in the POI space includes: determining a positioning grid of the terminal in the electronic map according to the position information; acquiring a plurality of corresponding nearby grids in a preset range of a positioning grid; and searching interest points in the positioning grids and nearby grids to obtain POI information in a preset range corresponding to the position information.
The server can divide a plurality of grids on the electronic map in advance, and the divided grids can be displayed on the electronic map or can be hidden. The mesh may be divided by a preset size. Furthermore, in order to improve the retrieval effect, different areas can also adopt different preset sizes to divide grids. Meshing in areas where buildings are dense may be smaller in size than meshing in areas where buildings are sparse. For example, the size used for dividing a grid on an electronic map of an area with dense buildings is 50 meters, and the size used for dividing a grid on an electronic map of an area with sparse buildings is 200 meters.
And the server determines a grid corresponding to the terminal in the electronic map according to the position information uploaded by the terminal, and the grid is used as a positioning grid of the terminal in the POI space. The server acquires a plurality of grids within a preset range of the positioning grid, and the grids are used as nearby grids of the positioning grid. The plurality of meshes of the preset range may be meshes adjacent to the positioning mesh. For example, the grid is square, and the positioning grid and the adjacent grid form a nine-square grid. As shown in fig. 2, the middle black grid is a positioning grid, and the grid adjacent to the black grid is a nearby grid. When the server searches the interest points, the interest point search can be carried out according to a nine-square lattice formed by the positioning grid and the adjacent grid. And obtaining POI information of multiple dimensions in a preset range corresponding to the position information.
The multiple grids in the preset range can also be obtained in a circumferential range by taking the central point of the positioning grid as the center of a circle and the preset distance as the radius. For example, the grid is square, as shown in fig. 3, where the black grid is a positioning grid, and the grids intersecting with the circumference and the circumferential range (grids other than the positioning grid) are all referred to as nearby grids. When the server searches the interest points, the interest point search can be performed on grids of the circumference intersection and the circumference range. And obtaining POI information of multiple dimensions in a preset range corresponding to the position information.
In a traditional information retrieval mode, a full-disc scanning mode is adopted, and if a plurality of POI information in a preset range of the position of a terminal needs to be retrieved, all interest points of the area where the terminal is located need to be scanned in a full disc mode. In the traditional method, the full-disc scanning adopts a Cartesian product algorithm, which results in overlong calculation time and overhigh calculation complexity and seriously influences the efficiency of information retrieval. In the embodiment, when the POI information is retrieved, full-disc scanning is not needed, and the POI information in the preset range of the position of the terminal can be quickly obtained by retrieving the POI in the positioning grid and the plurality of nearby grids, so that the retrieval efficiency is effectively improved.
POIs in different regions can be close to each other, for example, the distribution of points of interest such as enterprises, banks, restaurants, leisure, etc. is close to each other to some extent in the science and technology park of Shenzhen compared with the Zhongguancun of Beijing. The POI information reflects the environmental condition of the position of the terminal, so that users in different areas can be compared and analyzed through the POI information.
And 106, marking the position information as track points of the terminal in the POI space, and generating a movable track corresponding to the terminal by using the plurality of track points.
The server maintains the position information uploaded by the terminal and records the position information as track points of the terminal in the POI space. The server acquires the plurality of track points and generates the moving track of the terminal in the POI space by utilizing the plurality of track points. The corresponding active track of the terminal is the active track of the user. Before generating the movable track corresponding to the terminal, in order to avoid mixing abnormal track points into the movable track, the server acquires all track points to perform clustering analysis, and the abnormal track points are used as noise points to perform denoising processing so as to eliminate the abnormal track points.
In order to further improve the effectiveness of the activity track comparison, a time dimension can be added to the POI information. The time corresponding to the time dimension may be a time when the terminal uploads the location information. The server acquires a plurality of track points within preset time, and generates a moving track of the terminal in the POI space within the preset time by using the track points. For example, the preset time is 9:00-10:00 a.m. The server may compare the activity traces corresponding to the plurality of terminals during the time period. The terminal may have one motion trail or a plurality of motion trails. Due to the fact that the time periods are the same, the server can obtain a plurality of activity tracks which are closer, and therefore the effectiveness of activity track analysis can be further improved.
And step 108, calculating the similarity between the plurality of terminals by using the activity track and the POI information.
The server acquires the activity track and the POI information corresponding to the terminals and respectively calculates the track distance between every two terminals. The trajectory distance may also be referred to as the similarity of the terminals to each other. The server may calculate the track distance between the terminals by using a Frechet distance algorithm (an algorithm for measuring the spatial distance) or a Hausdorff distance algorithm (an algorithm for measuring the spatial distance), and the like. The distance function that calculates the trajectory distance between terminals may be as follows:
wherein A (alpha (t)) represents the activity track of the terminal A in the POI space; b (beta (t) represents the activity track of the B terminal in the POI space, alpha (t) represents the parameter function of the activity track of the A terminal in the POI space, beta (t) represents the parameter function of the activity track of the B terminal in the POI space, alpha (t) and beta (t) can be the same or different, and F (A, B) represents the value of solving the minimum value of max { d (A (alpha (t)), B (beta (t))) }, and the minimum value is taken as the similarity between the A terminal and the B terminal.
The server can respectively calculate the similarity between the plurality of terminals in the above manner. The higher the similarity, the closer the trajectories between the terminals are, and the lower the similarity, the more the trajectory difference between the terminals is. The closer the trajectories are, the closer the user's activity is represented. Thereby facilitating classification analysis of user populations.
In this embodiment, position information where a plurality of terminals are located is mapped to a POI space, POI information in a preset range with the position information is retrieved in the POI space, the position information is marked as track points of the terminal in the POI space, and a movable track corresponding to the terminal is generated by using the plurality of track points. Since the POI information can reflect the environment condition of the terminal, the comparison of the activity tracks of different users across the area can be realized by calculating the similarity between a plurality of terminals according to the activity track and the POI information.
In one embodiment, after the step of calculating the similarity between the plurality of terminals by using the activity track and the POI information, the method further includes: acquiring a distance function for calculating the similarity between a plurality of terminals; and extracting the space vectors of the plurality of terminals in the POI space by using the activity tracks and the distance functions of the plurality of terminals.
In this embodiment, in order to further analyze the user behavior, a spatial vector of the terminal in the POI space needs to be extracted. Because the corresponding motion tracks of the terminal are not equal in length and the number of track points in the motion tracks can be different, the original track data cannot be directly used for calculation during user behavior analysis, and the traditional characteristic engineering method has the problems of high labor cost and high information loss during extraction of space vectors.
In this embodiment, in order to quickly extract the space vectors of the multiple terminals in the POI space from the mass data, the server may compress the trajectory data by using the motion trajectories and the distance functions corresponding to the multiple terminals, and extract the space vectors of the multiple terminals. Wherein the trajectory data includes an activity trajectory and POI information. The distance function includes a distance function that calculates the similarity of a plurality of terminals to each other. For example, the server may use an MDS (multidimensional scaling) -Fast Mapping algorithm to compress the trajectory data corresponding to the plurality of terminals by using the active trajectories and the distance functions of the plurality of terminals, so as to extract space vectors with equal length. Therefore, the labor cost and the time cost consumed in the space vector extraction process can be effectively reduced, and the information retention rate can be ensured.
Further, before extracting the space vector, the server may perform a dimension reduction process on the trajectory data. For example, POI information includes 20 dimensions and a spatial vector may include 10 dimensions. Redundant information can be eliminated through dimension reduction processing, and information with a closer relation with user behavior analysis is obtained.
In one embodiment, after the step of extracting the spatial vectors of the plurality of terminals in the POI space according to the similarity between the plurality of terminals, the method further includes: obtaining a prediction model; inputting the space vectors of a plurality of terminals into a prediction model; and predicting the consumption tendency corresponding to the plurality of terminals through the prediction model.
In this embodiment, after extracting the spatial vectors of the multiple terminals in the POI space, the server may predict the consumption tendency corresponding to the terminals by using the spatial vectors. Specifically, the server may establish a model, and train the model using the space vectors of the plurality of terminals to obtain the prediction model.
The server can input the space vector of the terminal into the prediction model, and the space vector is calculated through the prediction model to obtain a plurality of POIs of which the access frequency corresponding to the terminal exceeds a first preset value. And the server takes the POIs with the access frequencies exceeding the first preset value as the POIs with higher access frequencies. The access frequency may be the number of times of accessing each POI accessed to the terminal within a certain time period. The server predicts the consumption tendency corresponding to the terminal according to the POI with high access frequency. For example, the server inputs the space vector of the terminal a into the prediction model, and obtains 3 POIs with high frequency of terminal entrance and exit, which are respectively a financial institution, an education institution and a fitness place, from the POI information corresponding to the terminal. The server can predict the user's consumption propensity for financial, educational, and fitness based on the 3 POIs. Therefore, the target user can be obtained more accurately among massive users.
In addition to predicting consumption tendencies of a single user, the server may also predict group consumption tendencies of multiple users. The server can input the space vectors of the terminals into the prediction model, and the space vectors are clustered through the prediction model to obtain the POIs with the input and output amounts of the terminals exceeding the second preset value. And the server predicts the group consumption tendency according to the POI with the access amount exceeding the second preset value. For example, the server inputs the spatial vectors of 10 ten thousand terminals into the prediction model, and obtains POIs of 3 top-ranked in the amount of input and output, which are restaurants, financial institutions, and medical institutions, respectively. Thereby predicting the group consumption tendency to be food, financial and medical. And in turn, may help develop businesses and products associated with consumption tendencies.
In one embodiment, after the step of calculating the similarity between the plurality of terminals by using the activity track and the POI information, the method further includes: extracting a plurality of activity tracks with similarity within a preset range; recording a plurality of activity tracks with the similarity within a preset range as similar tracks; after the step of predicting the consumption tendency corresponding to a plurality of terminals through the prediction model, the method further comprises the following steps: and acquiring corresponding recommendation information according to the consumption tendency, and sending the recommendation information to a plurality of terminals corresponding to similar tracks.
In this embodiment, the higher the similarity of the activity tracks is, the higher the similarity of the user behaviors is. The server can extract a plurality of activity tracks with the similarity within a preset range, and record the plurality of activity tracks with the similarity within the preset range as similar tracks. The server can predict the consumption tendency of the user by adopting the method provided in the embodiment. Due to the fact that POIs of the multiple terminals corresponding to the similar tracks are similar, the consumption tendency of the multiple terminals of the similar tracks does not need to be predicted one by one, the consumption tendency corresponding to the multiple terminals with the similar tracks can be known only by predicting the consumption tendency corresponding to one of the terminals, and the prediction efficiency of the consumption tendency of the multiple terminals is effectively improved. Since the consumption tendency is predicted according to POI (point of interest) of the terminal, and is not limited by the geographical position, a plurality of terminals with similar tracks in different areas can be predicted. The server can acquire recommendation information corresponding to the consumption tendency and send the recommendation information to a plurality of terminals corresponding to the similar tracks. Therefore, recommendation information can be conveniently and quickly sent to a plurality of terminals, and a plurality of users with similar degrees can know the related recommendation information.
In one embodiment, an application is installed on the terminal, and by running the application, the terminal can present the electronic map. The terminal can access the server through the application program, and upload the position information to the server through the application program. The server acquires the position information of the terminal and determines the position of the terminal in the electronic map. The geographical position of the terminal can be shown in the electronic map through the application program. And mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space. And the server returns the searched POI information in the preset range to the terminal and displays the POI information on the electronic map.
If a plurality of places of the same type exist in the same grid, the number of places of the same type can be identified in the electronic map. If the places of the same type are in different grids, the places can be respectively identified in the electronic map. If the number of places is not marked on the electronic map, the number of places can be considered as 1, and the number of places can also be marked by characters below the electronic map. And the server returns the electronic map added with the place information to the terminal. And the terminal receives and displays the electronic map added with the place information. As shown in fig. 4, the electronic map with the location information added is displayed in the terminal. The places near the terminal include 1 gas station, 4 restaurants, and 1 hospital.
Conventionally, there may be multiple controls in a presentation page of an electronic map, including a control that queries for a nearby environment, e.g., the control is "nearby". After clicking nearby, the terminal can display a classification page of the interest points, and if a user wants to navigate to a certain interest point through the terminal, the user needs to manually select the type of the interest point to know the information of the interest point. In the process, a user needs to manually operate for many times, and the operation is not simple, convenient and flexible enough. In the embodiment, a plurality of nearby POI information can be retrieved only by obtaining the position information of the terminal, and the information of nearby interest points can be known without multiple manual operations of a user, so that convenience is brought to the user. When the user can select the required interest point, the terminal can quickly navigate according to the POI information.
In one embodiment, as shown in FIG. 5, a server 500 is provided that includes a processor 501, an internal memory 502, a non-volatile storage medium 503, and a network interface 504 connected by a system bus. The operating system 5031 and the POI information processing device 5032 are stored in the nonvolatile storage medium 503 of the server, and the POI information processing device 5032 is used for conveniently and quickly acquiring information of a plurality of nearby places without manual operations of a user for a plurality of times. The processor 501 of the server 500, for providing computing and control capabilities, is configured to perform a POI information processing method. The internal memory 502 of the server 500 provides an environment for the operation of the POI information processing apparatus 5032 in the non-volatile storage medium, and computer-readable instructions, which when executed by the processor, cause the processor to execute a POI information processing method, may be stored in the internal memory 502. The network interface 504 of the server 500 is used for communicating with an external terminal through a network connection, such as acquiring location information of the terminal and transmitting an electronic map or the like to which a plurality of location information is added to the terminal. The server 500 may be implemented as a stand-alone server or as a server cluster comprising a plurality of servers. Those skilled in the art will appreciate that the architecture shown in fig. 3 is a block diagram of only a portion of the architecture associated with the subject application, and does not constitute a limitation on the servers to which the subject application applies, as a particular server may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, as shown in fig. 6, there is provided a POI information processing apparatus characterized by comprising: an obtaining module 602, a retrieving module 604, a recording module 606, a track generating module 608, and a calculating module 610, wherein:
an obtaining module 602, configured to obtain location information of multiple terminals.
The retrieving module 604 is configured to map the location information to a POI space, and retrieve POI information in a preset range corresponding to the location information in the POI space.
And a recording module 606, configured to mark the position information as a track point of the terminal in the POI space.
The track generating module 608 generates an active track corresponding to the terminal by using the plurality of track points.
A calculating module 610, configured to calculate similarity between multiple terminals by using the activity track and the POI information.
In one embodiment, the retrieving module 604 is further configured to determine a positioning grid of the terminal in the electronic map according to the position information; acquiring a plurality of corresponding nearby grids in a preset range of a positioning grid; and searching interest points in the positioning grids and nearby grids to obtain POI information in a preset range corresponding to the position information.
In one embodiment, the obtaining module 602 is further configured to obtain a distance function for calculating similarity between the plurality of terminals; as shown in fig. 7, the apparatus further includes: and a vector extraction module 612, configured to extract spatial vectors of the multiple terminals in the POI space by using the activity tracks and the distance functions of the multiple terminals.
In one embodiment, the obtaining module 602 is further configured to obtain a prediction model; as shown in fig. 8, the apparatus further includes: an input module 614 and a prediction module 616, wherein:
an input module 614, configured to input the spatial vectors of the plurality of terminals into the prediction model.
And a predicting module 616, configured to predict consumption trends corresponding to the multiple terminals through the prediction model.
In one embodiment, the obtaining module 602 is further configured to extract a plurality of activity tracks with similarity within a preset range; the recording module 606 is further configured to record a plurality of active tracks with similarity within a preset range as similar tracks; the obtaining module 602 is further configured to obtain corresponding recommendation information according to the consumption tendency; as shown in fig. 9, the apparatus further includes: a sending module 618, configured to send the recommendation information to a plurality of terminals corresponding to the similar tracks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A POI information processing method, the method comprising:
acquiring position information of a plurality of terminals;
mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space;
marking the position information as track points of the terminal in the POI space, and generating a movable track corresponding to the terminal by using a plurality of track points;
calculating the track distance between every two terminals by using the activity track and the POI information to obtain the similarity between a plurality of terminals;
acquiring a distance function for calculating the similarity between a plurality of terminals;
compressing and reducing the dimension of the track data corresponding to the terminals by using the active tracks and the distance functions of the terminals, and extracting equal-length space vectors of the terminals in the POI space;
the step of mapping the position information to a POI space, and retrieving POI information in a preset range corresponding to the position information in the POI space, includes:
determining a positioning grid of the terminal in the electronic map according to the position information, wherein the size of the grid for dividing the area with dense buildings is smaller than that of the grid for dividing the area with sparse buildings;
acquiring a plurality of corresponding nearby grids in the preset range of the positioning grid;
searching interest points in the positioning grid and the nearby grid to obtain POI information in a preset range corresponding to the position information;
the distance function for calculating the similarity between the plurality of terminals is as follows:
2. The method according to claim 1, wherein the predetermined range of meshes includes a plurality of meshes within a circumferential range obtained by taking a center point of the positioning mesh as a center and a predetermined distance as a radius, or a plurality of meshes adjacent to the positioning mesh and forming a nine-square grid with the positioning mesh.
3. The method of claim 1, wherein predicting the consumption tendency corresponding to the terminal by using the spatial vector comprises:
obtaining a prediction model;
inputting the space vectors of a plurality of terminals into the prediction model;
and predicting the consumption tendency corresponding to the plurality of terminals through the prediction model.
4. The method according to claim 3, wherein after the step of calculating a track distance between two terminals by using the activity track and the POI information to obtain a similarity between a plurality of terminals, the method further comprises:
extracting a plurality of activity tracks with similarity within a preset range;
recording a plurality of activity tracks with the similarity within a preset range as similar tracks;
after the step of predicting the consumption tendency corresponding to a plurality of terminals through the prediction model, the method further comprises the following steps:
and acquiring corresponding recommendation information according to the consumption tendency, and sending the recommendation information to a plurality of terminals corresponding to similar tracks.
5. A POI information processing apparatus characterized by comprising:
the acquisition module is used for acquiring the position information of a plurality of terminals;
the retrieval module is used for mapping the position information to a POI space and retrieving POI information in a preset range corresponding to the position information in the POI space;
the recording module is used for marking the position information as a track point of the terminal in the POI space;
the track generation module is used for generating a movable track corresponding to the terminal by utilizing the plurality of track points;
the calculation module is used for calculating the track distance between every two terminals by using the activity track and the POI information to obtain the similarity between a plurality of terminals;
the acquisition module is also used for acquiring a distance function for calculating the similarity between the plurality of terminals;
the system comprises a vector extraction module, a route selection module and a route selection module, wherein the vector extraction module is used for compressing the track data corresponding to a plurality of terminals by using the active tracks and the distance functions of the plurality of terminals and extracting equal-length space vectors of the plurality of terminals in a POI space;
the retrieval module is also used for determining a positioning grid of the terminal in the electronic map according to the position information, and the size of the grid for dividing the region with dense buildings is smaller than that of the grid for dividing the region with sparse buildings; acquiring a plurality of corresponding nearby grids in the preset range of the positioning grid; searching interest points in the positioning grid and the nearby grid to obtain POI information in a preset range corresponding to the position information;
the distance function for calculating the similarity between the plurality of terminals is as follows:
6. The apparatus according to claim 5, wherein the predetermined range of meshes includes a plurality of meshes within a circumferential range obtained by taking a center point of the positioning mesh as a center and a predetermined distance as a radius, or a plurality of meshes adjacent to the positioning mesh and forming a nine-square with the positioning mesh.
7. The apparatus of claim 5, wherein the obtaining module is further configured to obtain a prediction model;
the device further comprises:
an input module, configured to input spatial vectors of a plurality of terminals into the prediction model;
and the prediction module is used for predicting the consumption tendency corresponding to the plurality of terminals through the prediction model.
8. The device according to claim 7, wherein the obtaining module is further configured to extract a plurality of activity tracks with similarity within a preset range; the recording module is further used for recording a plurality of activity tracks with the similarity within a preset range as similar tracks; the acquisition module is also used for acquiring corresponding recommendation information according to the consumption tendency;
the device further comprises:
and the sending module is used for sending the recommendation information to a plurality of terminals corresponding to the similar tracks.
9. A server comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method of any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611005761.1A CN107784046B (en) | 2016-11-14 | 2016-11-14 | POI information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611005761.1A CN107784046B (en) | 2016-11-14 | 2016-11-14 | POI information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784046A CN107784046A (en) | 2018-03-09 |
| CN107784046B true CN107784046B (en) | 2021-05-04 |
Family
ID=61437674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611005761.1A Active CN107784046B (en) | 2016-11-14 | 2016-11-14 | POI information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107784046B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629001A (en) * | 2018-05-03 | 2018-10-09 | 成都瀚涛天图科技有限公司 | A kind of De-weight method of geography information big data |
| CN109029446B (en) * | 2018-06-22 | 2020-11-20 | 北京邮电大学 | Pedestrian position prediction method, device and equipment |
| CN111132027B (en) * | 2019-12-16 | 2021-10-01 | 中国移动通信集团内蒙古有限公司 | Scene recognition network graph drawing method, scene recognition method and device |
| CN113157817B (en) * | 2021-03-15 | 2024-05-10 | 平安科技（深圳）有限公司 | Method, device and computer equipment for distinguishing drivers |
| CN114895982B (en) * | 2022-05-13 | 2024-02-09 | 中国电信股份有限公司 | Application calling method, system, equipment and storage medium based on user information |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408043A (en) * | 2014-10-17 | 2015-03-11 | 深圳大学 | Information processing method and server |
| CN106022934A (en) * | 2016-05-05 | 2016-10-12 | 北京邮电大学 | Potential friend discovering method based on moving trajectory pattern and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023977B (en) * | 2012-11-19 | 2015-07-01 | 华南理工大学 | Recommendation system and method based on positional information |
| CN106021305A (en) * | 2016-05-05 | 2016-10-12 | 北京邮电大学 | Mode and preference sensing POI recommendation method and system |
| CN106095841B (en) * | 2016-06-05 | 2019-05-03 | 西华大学 | A kind of mobile Internet advertisement recommended method based on collaborative filtering |
-
2016
- 2016-11-14 CN CN201611005761.1A patent/CN107784046B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408043A (en) * | 2014-10-17 | 2015-03-11 | 深圳大学 | Information processing method and server |
| CN106022934A (en) * | 2016-05-05 | 2016-10-12 | 北京邮电大学 | Potential friend discovering method based on moving trajectory pattern and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784046A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784046B (en) | POI information processing method and device | |
| Miah et al. | A big data analytics method for tourist behaviour analysis | |
| CN108921221B (en) | User feature generation method, device, equipment and storage medium | |
| Long et al. | A review of quantitative methods for movement data | |
| Jurgens et al. | Geolocation prediction in twitter using social networks: A critical analysis and review of current practice | |
| Yuan et al. | Measuring similarity of mobile phone user trajectories–a Spatio-temporal Edit Distance method | |
| Matioli et al. | A new algorithm for clustering based on kernel density estimation | |
| CN111212383B (en) | Method, device, server and medium for determining number of regional permanent population | |
| Larson et al. | Spatial ranking methods for geographic information retrieval (GIR) in digital libraries | |
| Wang et al. | Comparative performance of logistic regression and survival analysis for detecting spatial predictors of land-use change | |
| JP2017151876A (en) | Image clustering system, image clustering method, image clustering program, and community structure detecting system | |
| US10969518B2 (en) | Flexible framework for ecological niche modeling | |
| Frontiera et al. | A comparison of geometric approaches to assessing spatial similarity for GIR | |
| Lansley et al. | Big data and geospatial analysis | |
| Zhang et al. | Terrafly geocloud: an online spatial data analysis and visualization system | |
| Lin et al. | Extracting urban landmarks from geographical datasets using a random forests classifier | |
| JP2004118290A (en) | Device and method for generating index for moving locus data retrieval, device and method for retrieving moving locus data, index generating program for moving locus data retrieval, recording medium recording the same, moving locus data retrieval program and recording medium recording the same | |
| Alia et al. | On the exploitation of GPS-based data for real-time visualisation of pedestrian dynamics in open environments | |
| Qiao et al. | Rapid trajectory clustering based on neighbor spatial analysis | |
| CN113704373A (en) | User identification method and device based on movement track data and storage medium | |
| Yokoyama et al. | EBSCAN: An entanglement-based algorithm for discovering dense regions in large geo-social data streams with noise | |
| Qadir et al. | Estimation of spatial deformation for nonstationary processes via variogram alignment | |
| Amboni et al. | The effect of species geographical distribution estimation methods on richness and phylogenetic diversity estimates | |
| Lyu et al. | Movement-aware map construction | |
| Stefanakis | SELF: Semantically enriched line simplification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |