WO2021232585A1 - Artificial intelligence-based positioning data processing method and related device - Google Patents

Abstract

An artificial intelligence-based positioning data processing method, comprising: acquiring multiple pieces of positioning data indicating user travel and recorded by a user terminal (S11); preprocessing the positioning data to obtain processing data (S12); processing the processing data on a spatial layer by using a clustering algorithm DBSCAN and a K-nearest neighbor classification algorithm KNN to obtain candidate regions comprising multiple categories, wherein each candidate region comprises a plurality of candidate stay points belonging to the same category (S13); for each category of candidate regions, according to cluster identifiers of a plurality of positioning points corresponding to the candidate regions, subdividing the plurality of candidate stay points in a time layer to obtain a stay point set, wherein the stay point set comprises a final stay point of the user travel (S14); and uploading the stay point set to a blockchain (S15). The method may be applied to smart transportation scenarios so as to promote the construction of smart cities.

Description

Artificial intelligence-based positioning data processing method and related equipment

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on May 21, 2020. The application number is 202010438159.7. The invention title is "Artificial intelligence-based positioning data processing method and related equipment". The entire content is incorporated by reference. In this application.

Technical field

This application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based positioning data processing method and related equipment.

Background technique

Traffic travel volume OD analysis is to obtain users' daily traffic travel data. Through data analysis, the characteristics and distribution of users' needs for the entire city's traffic and other urban functions can be mined, and it can provide information and decision-making support for urban traffic planning and construction. Among them, the OD matrix is a very critical analysis data.

The OD matrix is the starting and ending point matrix. It is necessary to know the starting point and ending point of all traffic trips of users in this city during this time period, that is, the travel stop point. There are many positioning points in the user's travel positioning data. The inventor has realized that how to identify the user's travel stay point based on these positioning points is a technical problem that needs to be solved urgently.

Summary of the invention

In view of the above, it is necessary to provide an artificial intelligence-based positioning data processing method and related equipment, which can identify the user's travel stop point based on the positioning point.

The first aspect of the present application provides an artificial intelligence-based positioning data processing method. The artificial intelligence-based positioning data processing method includes:

Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

Preprocessing the positioning data to obtain processing data;

The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

Upload the set of stay points to the blockchain.

A second aspect of the present application provides an electronic device, wherein the electronic device includes a processor and a memory, and the processor is configured to execute at least one computer-readable instruction stored in the memory to implement the following steps:

Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

Preprocessing the positioning data to obtain processing data;

The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

Upload the set of stay points to the blockchain.

A third aspect of the present application provides a computer-readable storage medium on which at least one computer-readable instruction is stored, wherein the at least one computer-readable instruction implements the following steps when executed by a processor:

Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

Preprocessing the positioning data to obtain processing data;

The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

Upload the set of stay points to the blockchain.

A fourth aspect of the present application provides a positioning data processing device, the positioning data processing device includes:

The obtaining module is used to obtain multiple positioning data representing the user's travel recorded by the user terminal;

The first processing module is configured to preprocess the positioning data to obtain processed data;

The second processing module is configured to use the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories, where each candidate region includes Multiple candidate stay points belonging to the same category;

The third processing module is configured to subdivide the multiple candidate stay points on the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate areas of each category to obtain A set of staying points, wherein the set of staying points includes the final staying point of the user when traveling;

The upload module is used to upload the set of stay points to the blockchain.

Based on the above technical solutions, this application can be applied to areas that require positioning data processing, such as smart city management, smart security, smart logistics, and smart transportation, so as to promote the development of smart cities. In this application, the DBSCAN algorithm and the KNN algorithm are used to cluster the positioning points on the spatial layer and optimize the clustering results, and then the candidate stay points are divided and selected on the time layer to realize the space-time two-layer clustering , It can effectively identify the staying point, at the same time, it removes part of the drift point of the positioning, and also improves the recognition accuracy of the staying point.

Description of the drawings

Fig. 1 is a flowchart of a preferred embodiment of a positioning data processing method based on artificial intelligence disclosed in the present application.

Fig. 2 is a functional module diagram of a preferred embodiment of a positioning data processing device disclosed in the present application.

FIG. 3 is a schematic structural diagram of an electronic device implementing a preferred embodiment of the artificial intelligence-based positioning data processing method according to the present application.

Detailed ways

In order to be able to understand the above objectives, features and advantages of the application more clearly, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other if there is no conflict.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of this application. The terms used in the specification of the application herein are only for the purpose of describing specific embodiments, and are not intended to limit the application.

Please refer to FIG. 1. FIG. 1 is a flowchart of a preferred embodiment of an artificial intelligence-based positioning data processing method disclosed in the present application. Among them, according to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted.

S11. Obtain a plurality of positioning data recorded by the user terminal and representing the user's travel.

Among them, the positioning data includes the geographic location of the positioning point and the arrival time of each positioning point.

S12. Preprocess the positioning data to obtain processed data.

Specifically, the preprocessing the positioning data to obtain processed data includes:

Perform equal time interval processing on the positioning data to obtain intermediate data;

The drift data in the intermediate data is deleted to obtain processed data.

Among them, the preprocessing can include equal time interval processing, such as dividing the positioning data for a period of time according to a preset time interval (such as 10min), and the preprocessing also includes deleting the drift data, where the drift data includes drift points. , Usually, the anchor point whose moving speed is greater than the maximum speed of urban traffic is usually a drift point. The existence of drift points will greatly affect the recognition effect of stay points, so they need to be deleted.

S13. Adopt the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple categories belonging to the same category. Candidate stay points.

Among them, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a representative density-based clustering algorithm. Its purpose is to filter out the low-density part and identify the high-density sample points. The clustering algorithm can not only identify clusters of any shape and size, but also has high anti-interference ability. The main idea of the DBSCAN clustering algorithm is: select an unprocessed sample point P from the sample point set D, detect the sample points in the Eps. neighborhood of the point P to search for clusters that meet the requirements, if the Eps. neighbors of the point P If the number of points in the domain is greater than or equal to MinPts, it is determined that the point P belongs to the core point, and a new cluster C is created based on the core point P, and then all the points with direct density reachable from the core point P are searched from the sample point set D. When all After all the points are processed, the clustering ends.

In the embodiments of this application, the length of time the user stays at a certain place can be obtained from the density of the positioning points in space. Therefore, the density-based DBSCAN algorithm can be used to cluster the positioning points on the spatial layer, which is preliminary realized Obtaining the user's travel candidate staying point.

Among them, the neighbor algorithm or K-Nearest Neighbor (k-Nearest Neighbor, kNN) classification algorithm is one of the simplest methods in data mining classification technology. The main idea of KNN is: for a given sample, if most of the K instances closest to this sample belong to a certain category, then it is determined that this sample also belongs to this category.

In the embodiments of the present application, because the positioning data of the user terminal is collected non-isochronously and unevenly, and the time interval between two consecutive positioning data collections is sometimes large, this makes it possible even if a certain positioning point is between a certain positioning point and the previous positioning point. The displacement speed of is less than the maximum speed of urban traffic, but the positioning point may still be a drift point. Therefore, only the displacement speed between the two positioning points cannot identify all the positioning drift points, and the existence of these positioning drift points will greatly Affect the recognition effect of stay points. Their existence may divide a long-term stay point into multiple short-term stay points, and may even cause some stay points to be unrecognized at all. Therefore, in order to more accurately identify the staying point of a user's travel, it is necessary to use the idea of the KNN algorithm to optimize the clustering results.

Specifically, the use of the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories includes:

The DBSCAN algorithm is used to process the processed data on the spatial layer to obtain a plurality of first stop points for the user to travel;

Using the KNN algorithm to classify the multiple first stay points to obtain multiple categories of first stay points;

According to the first stay point belonging to the same category, a candidate area is constructed.

Among them, the DBSCAN algorithm is used to obtain a plurality of first stay points that are initially identified. Since there are unavoidable drift points in the processed data, it is also necessary to use the KNN algorithm to further optimize the classification of the plurality of first stay points.

Specifically, the use of the DBSCAN algorithm to process the processed data on the spatial layer to obtain multiple first stay points for the user to travel includes:

Using the DBSCAN algorithm, on the spatial layer, for any locating point in the processed data, construct a neighborhood centered on the any locating point and the radius is the preset stopping point discriminating distance threshold;

Judging whether the number of positioning points in the neighborhood is greater than or equal to a preset stop point discrimination time threshold, where the length of each positioning point in the time dimension is one unit time;

If the number of positioning points in the neighborhood is greater than or equal to the preset stop point discrimination time threshold, the geometric center points of all positioning points in the neighborhood are calculated, and the geometric center points are determined as the travel of the user The first stop point.

Due to a certain degree of error in the positioning of the user terminal, the positioning result will change to a certain extent even if the user’s position does not move. According to the definition of travel by traffic, travel refers to travel by means of transportation for more than 500 meters or time-consuming walking Activities that exceed 5 minutes, therefore, the user's position movement within a small area reflected from the positioning data does not mean that the user has made a trip. Based on the above considerations, it is possible to set the threshold for the distance of the stay point to be 500 meters, and the threshold value for the time for the point of stay to be 5 minutes.

The user’s stay point can be defined as: For any locating point P, if the number N of locating points in the neighborhood with point P as the center and radius R (stay point discrimination distance threshold) is greater than or equal to the stay point discrimination time threshold, Then the geometric center points of all anchor points in the R. neighborhood are called stay points, the time to reach the stay point is the arrival time of the first anchor point in the R. neighborhood, and the stay time is N (unit time). Among them, the length of each anchor point in the time dimension is the same, which is a unit time, and the number of anchor points in the R. neighborhood of the point P is the stay time of the stay point.

Optionally, after the KNN algorithm is used to classify the multiple first stay points, and after the first stay points of the multiple categories are obtained, the method further includes:

Judging whether the multiple categories include a category of drift points;

If the multiple categories include the category of drift points, delete the category that includes the drift points;

According to the first stay points belonging to the same category, constructing the candidate area includes:

For the first stay points of other categories after the category including the drift point is deleted, a candidate area is constructed according to the first stay points belonging to the same category.

Among them, the KNN algorithm is used to classify the multiple first stay points, and the drift points can be classified into one category. In order to reduce the recognition effect of the drift points on the stay points, the categories including the drift points can be deleted, For the remaining categories, to further optimize.

Specifically, the use of the KNN algorithm to classify the plurality of first stay points, and obtain the first stay points of the plurality of categories includes:

For each of the first stay points, obtain a plurality of positioning point sets corresponding to the first stay points;

The KNN algorithm is used to change the cluster identifier of any anchor point in the plurality of anchor point sets;

The first stay points corresponding to the anchor points with the same cluster identifier after the change are classified into the same category.

Among them, the specific steps for optimizing the clustering results based on the idea of KNN algorithm are as follows:

1) Let set D={p ₁ , p ₂ ,..., p _n } represent the set of positioning points after spatial layer clustering, the parameter K in the initialization KNN algorithm is 4, and the initialization i=3;

2) Select the anchor point p _i for optimization: check _{the cluster IDs of K/2 anchor points before and after the point p i} . If the number of occurrences of a certain cluster ID exceeds K/2, then the cluster of the _{point p i} Change the ID to the cluster ID, _{and change the latitude and longitude value of the point p i to} the latitude and longitude value of the cluster center of the cluster ID; otherwise, the cluster ID of the _{point p i remains unchanged;}

3) i=i+1, if i=n-2, the optimization ends, otherwise, go to step 2).

Among them, each anchor point data contains a cluster ID field. Through the above steps, the first stay points corresponding to the anchor points with the same cluster ID can be divided into the same category, and the clustering result of the DBSCAN algorithm is realized. Further optimization.

S14. For the candidate regions of each category, perform subdivision processing on the multiple candidate stay points on the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate regions to obtain a stay point set, where , The set of staying points includes the final staying point of the user when traveling.

Among them, after clustering and optimizing the user travel location points, the candidate stay points for the user travel are extracted from the location data of the user terminal. Since the positioning points that are similar in the spatial dimension may be far apart in the time dimension, for example, a user works at location A in the morning, leaves location A for lunch at noon, and continues to work at location A in the afternoon, only for the user on the spatial layer The clustering of trajectory points will cluster its work location A in the morning and afternoon into the same cluster, that is, only one candidate stay point can be identified, but in fact, the user stayed at location A twice. In theory, there should be Two staying points, so the candidate staying points need to be further processed in the time dimension to get the final staying point of the user's travel.

In the embodiment of the present application, based on the candidate stay points extracted after spatial layer clustering and optimization, clustering is performed on the time layer to divide and select candidate stay points.

Specifically, the step of subdividing the plurality of candidate stay points on the time layer according to the cluster identifiers of the plurality of anchor points corresponding to the candidate area to obtain a set of stay points includes:

Sequentially reading the first cluster identifier of any anchor point corresponding to the candidate area;

Judging whether the first cluster identifier is equal to the initialized cluster identifier, wherein the initialized cluster identifier is the cluster identifier of the anchor point with the earliest arrival time;

If the first cluster identifier is equal to the initialized cluster identifier, the first cluster identifier is added to the new cluster until the first cluster identifier of the currently read anchor point is not equal to the initialized cluster identifier, the new cluster identifier is determined Whether the number of anchor points in the cluster is greater than or equal to the preset stay point discrimination time threshold;

If the number of anchor points in the new cluster is greater than or equal to the preset stay point discrimination time threshold, obtain the target candidate stay points corresponding to all the currently read anchor points, and add the target candidate stay points to Stay in the collection.

Optionally, the method further includes:

If the currently read anchor point is not the last anchor point, set the initialized cluster identifier as the cluster identifier of the currently read anchor point and perform iteration.

Optionally, the method further includes:

If the number of anchor points in the new cluster is less than the preset stay point discrimination time threshold, and the currently read anchor point is not the last anchor point, set the initialized cluster identifier as the cluster of the currently read anchor point Identify and iterate.

Among them, for each candidate area, the specific implementation steps in the time layer are as follows:

1) Initialization parameters i = 0, j = i, num = 0, initialize the cluster identifier cid, let cid represent the cluster ID of the first anchor point (ie the anchor point with the earliest arrival time), and the set of stay points SP is initially an empty set ；

2) Create a new cluster C;

3) Let i=i+1, read a piece of positioning data p _i , and judge whether _{the cluster ID of p i} is equal to cid. If they are equal, _{add point p i} to cluster C and go to step 3); if not, go to step 4);

4) If the number N of anchor points in the new cluster C is greater than or equal to the stay point discrimination time threshold, obtain the target candidate stay points corresponding to all the anchor points that have been read before, that is, the anchor points {p _j , The geometric center point of p _j+1 ,...,pi _-1 }, where the arrival time of the target candidate stay point is _{the positioning time of p i} , and the stay time is N (minutes). Add the target candidate stay point to the stay In the point set SP, then go to step 5); if the number N of anchor points in the new cluster C is less than the stay point discrimination time threshold, go directly to step 5);

5) If p _i is not the last point, set cid = _{the cluster ID of p i} and j = i, and then go to step 2); otherwise, the time-level clustering ends.

Optionally, the method further includes:

Connect the final stay points according to the arrival time sequence of the final stay points included in the stay point set to obtain the travel chain of the user's travel.

Wherein, the above steps 1)-5) are iterated in ascending order of the arrival time of the anchor points. Therefore, the final stay points in the obtained stay point set SP are also arranged in ascending order of time, and the stay points can be set directly The included final stay points are connected to obtain the travel chain of the user's travel.

S15. Upload the set of stay points to the blockchain.

Among them, the final set of stay points can be uploaded to the blockchain, and the data in the set of stay points can be saved through the blockchain, which can ensure the privacy and security of the data.

In the method flow described in Figure 1, the DBSCAN algorithm and the KNN algorithm are used to cluster the positioning points on the spatial layer and optimize the clustering results, and then the candidate stay points are divided and selected on the time layer to realize the space- The two-layer clustering of time can effectively identify the staying point, at the same time, it removes part of the drift points of the positioning, and also improves the recognition accuracy of the staying point.

It can be seen from the above embodiments that this application can be applied to areas that require processing of positioning data, such as smart city management, smart security, smart logistics, and smart transportation, so as to promote the development of smart cities.

Fig. 2 is a functional module diagram of a preferred embodiment of a positioning data processing device disclosed in the present application.

In some embodiments, the positioning data processing device runs in an electronic device. The positioning data processing device may include multiple functional modules composed of program code segments. The program code of each program segment in the positioning data processing device may be stored in a memory and executed by at least one processor to execute part or all of the steps in the artificial intelligence-based positioning data processing method described in FIG. 1 .

In this embodiment, the positioning data processing device may be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 201, a first processing module 202, a second processing module 203, a third processing module 204, and an uploading module 205. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in a memory.

The obtaining module 201 is configured to obtain multiple positioning data recorded by the user terminal and representing the user's travel.

Among them, the positioning data includes the geographic location of the positioning point and the arrival time of each positioning point.

The first processing module 202 is configured to preprocess the positioning data to obtain processed data.

Specifically, the preprocessing the positioning data to obtain processed data includes:

Perform equal time interval processing on the positioning data to obtain intermediate data;

The drift data in the intermediate data is deleted to obtain processed data.

Among them, the preprocessing can include equal time interval processing, such as dividing the positioning data for a period of time according to a preset time interval (such as 10min), and the preprocessing also includes deleting the drift data, where the drift data includes drift points. , Usually, the anchor point whose moving speed is greater than the maximum speed of urban traffic is usually a drift point. The existence of drift points will greatly affect the recognition effect of stay points, so they need to be deleted.

The second processing module 203 is configured to use the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each of the candidate regions Including multiple candidate stay points belonging to the same category.

Among them, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a representative density-based clustering algorithm. Its purpose is to filter out the low-density part and identify the high-density sample points. The clustering algorithm can not only identify clusters of any shape and size, but also has high anti-interference ability. The main idea of the DBSCAN clustering algorithm is: select an unprocessed sample point P from the sample point set D, detect the sample points in the Eps. neighborhood of the point P to search for clusters that meet the requirements, if the Eps. neighbors of the point P If the number of points in the domain is greater than or equal to MinPts, it is determined that the point P belongs to the core point, and a new cluster C is created based on the core point P, and then all the points with direct density reachable from the core point P are searched from the sample point set D. When all After all the points are processed, the clustering ends.

In the embodiments of this application, the length of time the user stays at a certain place can be obtained from the density of the positioning points in space. Therefore, the density-based DBSCAN algorithm can be used to cluster the positioning points on the spatial layer, which is preliminary realized Obtaining the user's travel candidate staying point.

Among them, the neighbor algorithm or K-Nearest Neighbor (k-Nearest Neighbor, kNN) classification algorithm is one of the simplest methods in data mining classification technology. The main idea of KNN is: for a given sample, if most of the K instances closest to this sample belong to a certain category, then it is determined that this sample also belongs to this category.

In the embodiments of the present application, because the positioning data of the user terminal is collected non-isochronously and unevenly, and the time interval between two consecutive positioning data collections is sometimes large, this makes it possible even if a certain positioning point is between a certain positioning point and the previous positioning point. The displacement speed of is less than the maximum speed of urban traffic, but the positioning point may still be a drift point. Therefore, only the displacement speed between the two positioning points cannot identify all the positioning drift points, and the existence of these positioning drift points will greatly Affect the recognition effect of stay points. Their existence may divide a long-term stay point into multiple short-term stay points, and may even cause some stay points to be unrecognized at all. Therefore, in order to more accurately identify the staying point of a user's travel, it is necessary to use the idea of the KNN algorithm to optimize the clustering results.

Specifically, the use of the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories includes:

The DBSCAN algorithm is used to process the processed data on the spatial layer to obtain multiple first stop points for the user to travel;

Using the KNN algorithm to classify the multiple first stay points to obtain multiple categories of first stay points;

According to the first stay point belonging to the same category, a candidate area is constructed.

Among them, the DBSCAN algorithm is used to obtain a plurality of first stay points that are initially identified. Since there are unavoidable drift points in the processed data, it is also necessary to use the KNN algorithm to further optimize the classification of the plurality of first stay points.

Specifically, the use of the DBSCAN algorithm to process the processed data on the spatial layer to obtain multiple first stay points for the user to travel includes:

Using the DBSCAN algorithm, on the spatial layer, for any locating point in the processed data, construct a neighborhood centered on the any locating point and the radius is the preset stopping point discriminating distance threshold;

Judging whether the number of positioning points in the neighborhood is greater than or equal to a preset stop point discrimination time threshold, where the length of each positioning point in the time dimension is one unit time;

If the number of positioning points in the neighborhood is greater than or equal to the preset stop point discrimination time threshold, the geometric center points of all the positioning points in the neighborhood are calculated, and the geometric center points are determined as the travel of the user The first stop point.

Due to a certain degree of error in the positioning of the user terminal, the positioning result will change to a certain extent even if the user’s position does not move. According to the definition of travel by traffic, travel refers to travel by means of transportation over 500 meters or time-consuming walking Activities that exceed 5 minutes, therefore, the user's position movement within a small area reflected from the positioning data does not mean that the user has made a trip. Based on the above considerations, it is possible to set the threshold for the distance of the stay point to be 500 meters, and the threshold for the time for the point of stay to be 5 minutes.

The user’s stay point can be defined as: For any locating point P, if the number N of locating points in the neighborhood with point P as the center and radius R (stay point discrimination distance threshold) is greater than or equal to the stay point discrimination time threshold, Then the geometric center points of all anchor points in the R. neighborhood are called stay points, the time to reach the stay point is the arrival time of the first anchor point in the R. neighborhood, and the stay time is N (unit time). Among them, the length of each anchor point in the time dimension is the same, which is a unit time, and the number of anchor points in the R. neighborhood of point P is the stay time of the stay point.

Among them, the KNN algorithm is used to classify the multiple first stay points, and the drift points can be classified into one category. In order to reduce the recognition effect of the drift points on the stay points, the categories including the drift points can be deleted, For the remaining categories, to further optimize.

Specifically, the use of the KNN algorithm to classify the multiple first stay points, and obtain the first stay points of the multiple categories includes:

For each of the first stay points, obtain a plurality of positioning point sets corresponding to the first stay points;

The KNN algorithm is used to change the cluster identifier of any anchor point in the plurality of anchor point sets;

The first stay points corresponding to the anchor points with the same cluster identifier after the change are classified into the same category.

Among them, the specific steps for optimizing the clustering results based on the idea of KNN algorithm are as follows:

1) Let set D={p ₁ , p ₂ ,..., p _n } represent the set of positioning points after spatial layer clustering, the parameter K in the initialization KNN algorithm is 4, and the initialization i=3;

2) Select the anchor point p _i for optimization: check _{the cluster IDs of K/2 anchor points before and after the point p i} . If the number of occurrences of a certain cluster ID exceeds K/2, then the cluster of the _{point p i} Change the ID to the cluster ID, _{and change the latitude and longitude value of the point p i to} the latitude and longitude value of the cluster center of the cluster ID; otherwise, the cluster ID of the _{point p i remains unchanged;}

3) i=i+1, if i=n-2, the optimization ends, otherwise, go to step 2).

Among them, each anchor point data contains a cluster ID field. Through the above steps, the first stay points corresponding to the anchor points with the same cluster ID can be divided into the same category, and the clustering result of the DBSCAN algorithm is realized. Further optimization.

The third processing module 204 is configured to subdivide the multiple candidate stay points on the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate areas of each category, and Obtain a set of staying points, where the set of staying points includes the final staying point of the user traveling.

Among them, after clustering and optimizing the user travel location points, the candidate stay points for the user travel are extracted from the location data of the user terminal. Since the positioning points that are similar in the spatial dimension may be far apart in the time dimension, for example, a user works at location A in the morning, leaves location A for lunch at noon, and continues to work at location A in the afternoon, only for the user on the spatial layer The clustering of trajectory points will cluster its work location A in the morning and afternoon into the same cluster, that is, only one candidate stay point can be identified, but in fact, the user stayed at location A twice. In theory, there should be Two staying points, so the candidate staying points need to be further processed in the time dimension to get the final staying point of the user's travel.

In the embodiment of the present application, based on the candidate stay points extracted after spatial layer clustering and optimization, clustering is performed on the time layer to divide and select candidate stay points.

Specifically, the step of subdividing the plurality of candidate stay points on the time layer according to the cluster identifiers of the plurality of anchor points corresponding to the candidate area to obtain a set of stay points includes:

Sequentially reading the first cluster identifier of any anchor point corresponding to the candidate area;

Judging whether the first cluster identifier is equal to the initialized cluster identifier, wherein the initialized cluster identifier is the cluster identifier of the anchor point with the earliest arrival time;

If the first cluster identifier is equal to the initialized cluster identifier, the first cluster identifier is added to the new cluster until the first cluster identifier of the currently read anchor point is not equal to the initialized cluster identifier, the new cluster identifier is determined Whether the number of anchor points in the cluster is greater than or equal to the preset stay point discrimination time threshold;

If the number of anchor points in the new cluster is greater than or equal to the preset stay point discrimination time threshold, obtain the target candidate stay points corresponding to all the currently read anchor points, and add the target candidate stay points to Stay in the collection.

The upload module 205 is configured to upload the stay point set to the blockchain.

In the positioning data processing device described in Figure 2, the DBSCAN algorithm and the KNN algorithm are used to cluster the positioning points on the spatial layer and optimize the clustering results, and then the candidate stay points are divided and selected on the time layer to achieve The space-time double-layer clustering can effectively identify the stay points, and at the same time, it removes part of the drift points of the positioning, and also improves the recognition accuracy of the stay points.

As shown in FIG. 3, FIG. 3 is a schematic structural diagram of an electronic device implementing a preferred embodiment of the artificial intelligence-based positioning data processing method according to the present application. The electronic device 3 includes a memory 31, at least one processor 32, a computer program 33 stored in the memory 31 and running on the at least one processor 32, and at least one communication bus 34.

Those skilled in the art can understand that the schematic diagram shown in FIG. 3 is only an example of the electronic device 3, and does not constitute a limitation on the electronic device 3. It may include more or less components than those shown in the figure, or a combination. Certain components, or different components, for example, the electronic device 3 may also include input and output devices, network access devices, and so on.

The electronic device 3 is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit (ASIC), and field programmable Gate array (FPGA), digital signal processor (DSP), embedded device, etc. The electronic equipment may also include network equipment and/or user equipment. Wherein, the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of hosts or network servers based on Cloud Computing. The user equipment includes, but is not limited to, any electronic product that can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, and a personal digital device. Assistant PDA, etc.

The at least one processor 32 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), and application specific integrated circuits (ASICs). ), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 32 can be a microprocessor, or the processor 32 can also be any conventional processor, etc. The processor 32 is the control center of the electronic device 3, and connects the entire electronic device 3 through various interfaces and lines. Parts.

The memory 31 may be used to store the computer program 33 and/or modules/units. The processor 32 runs or executes the computer programs and/or modules/units stored in the memory 31 and calls the computer programs and/or modules/units stored in the memory 31. The data in 31 realizes various functions of the electronic device 3. The memory 31 may mainly include a storage program area and a storage data area. The storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may Data (such as audio data) created according to the use of the electronic device 3 and the like are stored. In addition, the memory 31 may include volatile and non-volatile memory, such as random access memory (RAM), hard disk, memory, plug-in hard disk, smart media card (SMC), and security A digital (Secure Digital, SD) card, a flash card (Flash Card), at least one magnetic disk storage device, a flash memory device, or other computer-readable storage media that can be used to carry or store data. The computer-readable storage medium may be non-volatile or volatile.

With reference to FIG. 1, the memory 31 in the electronic device 3 stores multiple instructions to implement an artificial intelligence-based positioning data processing method, and the processor 32 can execute the multiple instructions to achieve:

Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

Preprocessing the positioning data to obtain processing data;

The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

Upload the set of stay points to the blockchain.

Specifically, for the specific implementation method of the above-mentioned instructions by the processor 32, reference may be made to the description of the relevant steps in the embodiment corresponding to FIG. 1, which will not be repeated here.

In the electronic device 3 described in Figure 3, the positioning points are clustered on the spatial layer using the DBSCAN algorithm and the KNN algorithm, and the clustering results are optimized, and then the candidate stay points are divided and selected on the time layer to realize the spatial -Time double-layer clustering can effectively identify the stay points, and at the same time, remove part of the drift points of the positioning, and also improve the recognition accuracy of the stay points.

If the integrated module/unit of the electronic device 3 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, it can implement the steps of the foregoing method embodiments. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, and read-only memory (ROM, Read-Only Memory) .

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store Data created by the use of nodes, etc.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

This application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, including Distributed computing environment for any of the above systems or equipment, etc. This application may be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments. In these distributed computing environments, tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional modules.

For those skilled in the art, it is obvious that the present application is not limited to the details of the foregoing exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description, and therefore it is intended to fall into the claims. All changes in the meaning and scope of the equivalent elements of are included in this application. Any associated diagram marks in the claims should not be regarded as limiting the claims involved. Multiple units or devices stated in the system claims can also be implemented by software or hardware.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application and not to limit them. Although the application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the application can be Make modifications or equivalent replacements without departing from the spirit and scope of the technical solution of the present application.

Claims (20)

1. An artificial intelligence-based positioning data processing method, wherein the artificial intelligence-based positioning data processing method includes:

   Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

   Preprocessing the positioning data to obtain processing data;

   The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

   For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

   Upload the set of stay points to the blockchain.
2. The artificial intelligence-based positioning data processing method according to claim 1, wherein the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain the data including multiple categories. The candidate areas include:

   The DBSCAN algorithm is used to process the processed data on the spatial layer to obtain multiple first stop points for the user to travel;

   Using the KNN algorithm to classify the multiple first stay points to obtain multiple categories of first stay points;

   According to the first stay point belonging to the same category, a candidate area is constructed.
3. The artificial intelligence-based positioning data processing method according to claim 2, wherein said using the DBSCAN algorithm to process the processed data on the spatial layer to obtain the plurality of first stay points for the user to travel comprises:

   Using the DBSCAN algorithm, on the spatial layer, for any locating point in the processed data, construct a neighborhood centered on the any locating point and the radius is the preset stopping point discriminating distance threshold;

   Judging whether the number of positioning points in the neighborhood is greater than or equal to a preset stop point discrimination time threshold, where the length of each positioning point in the time dimension is one unit time;

   If the number of positioning points in the neighborhood is greater than or equal to the preset stop point discrimination time threshold, the geometric center points of all positioning points in the neighborhood are calculated, and the geometric center points are determined as the travel of the user The first stop point.
4. The artificial intelligence-based positioning data processing method according to claim 2, wherein the KNN algorithm is used to classify the multiple first stay points, and after the first stay points of multiple categories are obtained, the The artificial intelligence positioning data processing method also includes:

   Judging whether the multiple categories include a category of drift points;

   If the multiple categories include the category of drift points, delete the category that includes the drift points;

   According to the first stay points belonging to the same category, constructing the candidate area includes:

   For the first stay points of other categories after the category including the drift point is deleted, a candidate area is constructed according to the first stay points belonging to the same category.
5. The artificial intelligence-based positioning data processing method according to claim 2, wherein said using KNN algorithm to classify said multiple first stay points to obtain multiple categories of first stay points comprises:

   For each of the first stay points, obtain a plurality of positioning point sets corresponding to the first stay points;

   The KNN algorithm is used to change the cluster identifier of any anchor point in the plurality of anchor point sets;

   The first stay points corresponding to the anchor points with the same cluster identifier after the change are classified into the same category.
6. The artificial intelligence-based positioning data processing method according to claim 1, wherein the plurality of candidate stay points are subdivided on a time level according to the cluster identifiers of the plurality of positioning points corresponding to the candidate area Processing and obtaining a set of stay points include:

   Sequentially reading the first cluster identifier of any anchor point corresponding to the candidate area;

   Judging whether the first cluster identifier is equal to the initialized cluster identifier, wherein the initialized cluster identifier is the cluster identifier of the anchor point with the earliest arrival time;

   If the first cluster identifier is equal to the initialized cluster identifier, the first cluster identifier is added to the new cluster until the first cluster identifier of the currently read anchor point is not equal to the initialized cluster identifier, the new cluster identifier is determined Whether the number of anchor points in the cluster is greater than or equal to the preset stay point discrimination time threshold;

   If the number of anchor points in the new cluster is greater than or equal to the preset stay point discrimination time threshold, obtain the target candidate stay points corresponding to all the currently read anchor points, and add the target candidate stay points to Stay in the collection.
7. The method for processing positioning data based on artificial intelligence according to claim 6, wherein the method for processing positioning data based on artificial intelligence further comprises:

   If the currently read anchor point is not the last anchor point, set the initialized cluster identifier as the cluster identifier of the currently read anchor point and perform iteration.
8. An electronic device, wherein the electronic device includes a processor and a memory, and the processor is configured to execute at least one computer-readable instruction stored in the memory to implement the following steps:

   Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

   Preprocessing the positioning data to obtain processing data;

   The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

   For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

   Upload the set of stay points to the blockchain.
9. The electronic device according to claim 8, wherein the processor executes the at least one computer-readable instruction to implement the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN, and the processing is performed on the spatial layer When the data is processed to obtain candidate regions that include multiple categories, it specifically includes:

   The DBSCAN algorithm is used to process the processed data on the spatial layer to obtain multiple first stop points for the user to travel;

   Using the KNN algorithm to classify the multiple first stay points to obtain multiple categories of first stay points;

   According to the first stay point belonging to the same category, a candidate area is constructed.
10. The electronic device according to claim 9, wherein the processor executes the at least one computer-readable instruction to implement the use of the DBSCAN algorithm to process the processed data on the spatial layer to obtain the user travel When there are multiple first stay points, specifically include:

    Using the DBSCAN algorithm, on the spatial layer, for any locating point in the processed data, construct a neighborhood centered on the any locating point and the radius is the preset stopping point discriminating distance threshold;

    Judging whether the number of positioning points in the neighborhood is greater than or equal to a preset stop point discrimination time threshold, where the length of each positioning point in the time dimension is one unit time;

    If the number of positioning points in the neighborhood is greater than or equal to the preset stop point discrimination time threshold, the geometric center points of all positioning points in the neighborhood are calculated, and the geometric center points are determined as the travel of the user The first stop point.
11. The electronic device according to claim 9, wherein the KNN algorithm is used to classify the plurality of first stay points, and after obtaining the first stay points of a plurality of categories, the processor executes the at least one The computer readable instructions are also used to perform the following steps:

    Judging whether the multiple categories include a category of drift points;

    If the multiple categories include the category of drift points, delete the category that includes the drift points;

    According to the first stay points belonging to the same category, constructing the candidate area includes:

    For the first stay points of other categories after the category including the drift point is deleted, a candidate area is constructed according to the first stay points belonging to the same category.
12. The electronic device according to claim 9, wherein the processor executes the at least one computer-readable instruction to implement the KNN algorithm to classify the plurality of first stay points to obtain a plurality of categories When the first stop point, specifically include:

    For each of the first stay points, obtain a plurality of positioning point sets corresponding to the first stay points;

    The KNN algorithm is used to change the cluster identifier of any anchor point in the plurality of anchor point sets;

    The first stay points corresponding to the anchor points with the same cluster identifier after the change are classified into the same category.
13. The electronic device according to claim 8, wherein the processor executes the at least one computer-readable instruction to implement the cluster identification of the plurality of anchor points corresponding to the candidate area, and compare all locations on the time level. When the multiple candidate stay points are subdivided, and the set of stay points is obtained, it specifically includes:

    Sequentially reading the first cluster identifier of any anchor point corresponding to the candidate area;

    Judging whether the first cluster identifier is equal to the initialized cluster identifier, wherein the initialized cluster identifier is the cluster identifier of the anchor point with the earliest arrival time;

    If the first cluster identifier is equal to the initialized cluster identifier, the first cluster identifier is added to the new cluster until the first cluster identifier of the currently read anchor point is not equal to the initialized cluster identifier, the new cluster identifier is determined Whether the number of anchor points in the cluster is greater than or equal to the preset stay point discrimination time threshold;

    If the number of anchor points in the new cluster is greater than or equal to the preset stay point discrimination time threshold, obtain the target candidate stay points corresponding to all the currently read anchor points, and add the target candidate stay points to Stay in the collection.
14. The electronic device according to claim 13, wherein the processor executing the at least one computer readable instruction is further configured to execute the following steps:

    If the currently read anchor point is not the last anchor point, set the initialized cluster identifier as the cluster identifier of the currently read anchor point and perform iteration.
15. A computer-readable storage medium has at least one computer-readable instruction stored thereon, wherein the at least one computer-readable instruction implements the following steps when executed by a processor:

    Obtain multiple positioning data recorded by the user terminal indicating the user's travel;

    Preprocessing the positioning data to obtain processing data;

    The clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN are used to process the processed data on the spatial layer to obtain candidate regions including multiple categories, wherein each candidate region includes multiple candidates belonging to the same category Stop point

    For the candidate area of each category, the multiple candidate stay points are subdivided in the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate area to obtain a stay point set, where The set of staying points includes the final staying point for the user to travel;

    Upload the set of stay points to the blockchain.
16. The storage medium according to claim 15, wherein the at least one computer-readable instruction is executed by the processor to implement the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN, and the When processing data for processing to obtain candidate regions that include multiple categories, it specifically includes:

    The DBSCAN algorithm is used to process the processed data on the spatial layer to obtain multiple first stop points for the user to travel;

    Using the KNN algorithm to classify the multiple first stay points to obtain multiple categories of first stay points;

    According to the first stay point belonging to the same category, a candidate area is constructed.
17. The storage medium according to claim 16, wherein the at least one computer-readable instruction is executed by the processor to implement the use of the DBSCAN algorithm to process the processed data on the spatial layer to obtain the user The multiple first stop points during travel include:

    Using the DBSCAN algorithm, on the spatial layer, for any locating point in the processed data, construct a neighborhood centered on the any locating point and the radius is the preset stopping point discriminating distance threshold;

    Judging whether the number of positioning points in the neighborhood is greater than or equal to a preset stop point discrimination time threshold, where the length of each positioning point in the time dimension is one unit time;

    If the number of positioning points in the neighborhood is greater than or equal to the preset stop point discrimination time threshold, the geometric center points of all positioning points in the neighborhood are calculated, and the geometric center points are determined as the travel of the user The first stop point.
18. The storage medium according to claim 16, wherein the KNN algorithm is used to classify the plurality of first stay points, and after the first stay points of a plurality of categories are obtained, the at least one computer-readable instruction is The processor also implements the following steps when executing:

    Judging whether the multiple categories include a category of drift points;

    If the multiple categories include the category of drift points, delete the category that includes the drift points;

    According to the first stay points belonging to the same category, constructing the candidate area includes:

    For the first stay points of other categories after the category including the drift point is deleted, a candidate area is constructed according to the first stay points belonging to the same category.
19. The storage medium according to claim 16, wherein the at least one computer-readable instruction is executed by the processor to implement the use of the KNN algorithm to classify the plurality of first stay points to obtain a plurality of categories When the first stop point, specifically include:

    For each of the first stay points, obtain a plurality of positioning point sets corresponding to the first stay points;

    The KNN algorithm is used to change the cluster identifier of any anchor point in the plurality of anchor point sets;

    The first stay points corresponding to the anchor points with the same cluster identifier after the change are classified into the same category.
20. A positioning data processing device, wherein the positioning data processing device includes:

    The obtaining module is used to obtain multiple positioning data representing the user's travel recorded by the user terminal;

    The first processing module is configured to preprocess the positioning data to obtain processed data;

    The second processing module is configured to use the clustering algorithm DBSCAN and the K nearest neighbor classification algorithm KNN to process the processed data on the spatial layer to obtain candidate regions including multiple categories, where each candidate region includes Multiple candidate stay points belonging to the same category;

    The third processing module is configured to subdivide the multiple candidate stay points on the time layer according to the cluster identifiers of the multiple anchor points corresponding to the candidate areas of each category to obtain A set of staying points, wherein the set of staying points includes the final staying point of the user when traveling;

    The upload module is used to upload the set of stay points to the blockchain.

Images