Trajectory Data Processing Method, Apparatus, Computer Device, and Storage Medium

Abstract

The present disclosure provides a trajectory data processing method, apparatus, computer device, and storage medium. The method includes: obtaining an index type corresponding to reference index information, determining a target data table corresponding to the index type, determining, from multiple candidate index information in the target data table, candidate index information that matches the reference index information, extracting a target trajectory corresponding to the matching candidate index information, and performing a target operation on the target trajectory. Through the present disclosure, since the target data table that matches is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query scope, the trajectory query scope is effectively narrowed while effectively ensuring the accuracy of the query search. When the query target trajectory is used to assist in performing the target operation, the effective connection between the trajectory query and the trajectory processing is achieved, effectively ensuring the coherence of the trajectory processing and improving the overall execution effect of the trajectory processing.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technologies, and in particular, to a method and apparatus for processing trajectory data, a computer device, and a storage medium. Background Art

[0002] With the development of Internet technologies, various sensors and applications can collect the trajectories of moving objects. In related technologies, the trajectories are usually saved in a database, and a partitioning strategy is adopted to allocate the trajectories to different device partitions, and the partitioning index and the global index are used to query and analyze the trajectories.

[0003] In this way, it is difficult to change the index structure of trajectory storage, and it is difficult to adjust the partitioning structure of the trajectories, resulting in difficulty in realizing real-time updates of the trajectories, which is not conducive to effective query and search for the trajectories, leading to a more cumbersome process for subsequent execution and processing of the trajectories, and poor trajectory processing effects. Summary of the Invention

[0004] The present disclosure aims to at least solve one of the technical problems in the related technologies to some extent.

[0005] To this end, the present disclosure aims to provide a method and apparatus for processing trajectory data, a computer device, and a storage medium. Since the target data table that matches is indexed according to the index type, the index type is associated with the reference index information, and the target data table is used as the query range, the trajectory query range is effectively reduced while effectively ensuring the accuracy of query and search. When the target trajectory obtained by query is used to assist in executing the target operation, the effective connection between trajectory query and trajectory processing is realized, the coherence of trajectory processing is effectively ensured, and the overall execution and processing effect of trajectory processing is improved.

[0006] To achieve the above object, a method for processing trajectory data according to a first aspect embodiment of the present disclosure includes: obtaining reference index information, where the reference index information has a corresponding index type; determining a target data table corresponding to the index type, where the target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information; determining, from the plurality of candidate index information, candidate index information that matches the reference index information, and extracting a target trajectory corresponding to the matching candidate index information, where the target trajectory belongs to the plurality of candidate trajectories; and performing a target operation on the target trajectory.

[0007] The trajectory data processing method proposed in the embodiment of the first aspect of the present disclosure obtains reference index information, where the reference index information has a corresponding index type, determines a target data table corresponding to the index type, determines a candidate index information that matches the reference index information from multiple candidate index information in the target data table, extracts the target trajectory corresponding to the matching candidate index information, and performs a target operation on the target trajectory. Since the target data table is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query range, the trajectory query range is effectively narrowed while effectively ensuring the accuracy of the query search. When the obtained target trajectory is used to assist in performing the target operation, the effective connection between trajectory query and trajectory processing is achieved, effectively ensuring the coherence of trajectory processing and improving the overall execution effect of trajectory processing.

[0008] To achieve the above object, the trajectory data processing device proposed in the embodiment of the second aspect of the present disclosure includes: a first acquisition module for acquiring reference index information, where the reference index information has a corresponding index type; a first determination module for determining a target data table corresponding to the index type, where the target data table includes: multiple candidate index information and multiple candidate trajectories respectively corresponding to the multiple candidate index information; a second determination module for determining a candidate index information that matches the reference index information from the multiple candidate index information and extracting the target trajectory corresponding to the matching candidate index information, where the target trajectory belongs to the multiple candidate trajectories; and an execution module for performing a target operation on the target trajectory.

[0009] The trajectory data processing device proposed in the embodiment of the second aspect of the present disclosure obtains reference index information, where the reference index information has a corresponding index type, determines a target data table corresponding to the index type, determines a candidate index information that matches the reference index information from multiple candidate index information in the target data table, extracts the target trajectory corresponding to the matching candidate index information, and performs a target operation on the target trajectory. Since the target data table is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query range, the trajectory query range is effectively narrowed while effectively ensuring the accuracy of the query search. When the obtained target trajectory is used to assist in performing the target operation, the effective connection between trajectory query and trajectory processing is achieved, effectively ensuring the coherence of trajectory processing and improving the overall execution effect of trajectory processing.

[0010] The third aspect of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the trajectory data processing method provided in the first aspect of the present disclosure.

[0011] The fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the trajectory data processing method provided in the first aspect of the present disclosure.

[0012] The fifth aspect of the present disclosure provides a computer program product. When the instructions in the computer program product are executed by a processor, they execute the trajectory data processing method provided in the first aspect of the present disclosure.

[0013] Additional aspects and advantages of the present disclosure will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and / or additional aspects and advantages of the present disclosure will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0015] Figure 1 is a schematic flowchart of a trajectory data processing method provided in an embodiment of the present disclosure;

[0016] Figure 2 is a schematic structural diagram of an index type in an embodiment of the present disclosure;

[0017] Figure 3 is a schematic diagram of a target query language in an embodiment of the present disclosure;

[0018] Figure 4 is a schematic diagram of the effect of trajectory processing in an embodiment of the present disclosure;

[0019] Figure 5 is a schematic structural diagram of a trajectory processing system in an embodiment of the present disclosure;

[0020] Figure 6 is a schematic flowchart of a trajectory data processing method provided in another embodiment of the present disclosure;

[0021] Figure 7 is a schematic flowchart of a trajectory data processing method provided in another embodiment of the present disclosure;

[0022] Figure 8 is a schematic structural diagram of an SQL engine in an embodiment of the present disclosure;

[0023] Figure 9Schematic diagram of data loading statement in an embodiment of the present disclosure;

[0024] Figure 10 Schematic diagram of structured trajectory query statement in an embodiment of the present disclosure;

[0025] Figure 11 Schematic diagram of structured language parsing statement in an embodiment of the present disclosure;

[0026] Figure 12 Schematic diagram of the structure of a trajectory data processing device proposed in an embodiment of the present disclosure;

[0027] Figure 13 Schematic diagram of the structure of a trajectory data processing device proposed in another embodiment of the present disclosure;

[0028] Figure 14 Block diagram of an exemplary computer device suitable for implementing the embodiments of the present disclosure is shown. Detailed implementation manners

[0029] Embodiments of the present disclosure will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary only for explaining the present disclosure and should not be construed as limiting the present disclosure. On the contrary, the embodiments of the present disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0030] Figure 1 Flowchart of a trajectory data processing method proposed in an embodiment of the present disclosure.

[0031] It should be noted that the execution subject of the trajectory data processing method in this embodiment is a trajectory data processing device, which can be implemented in software and / or hardware, and the device can be configured in a computer device, which can include but is not limited to a terminal, a server, etc.

[0032] As Figure 1 shown, the trajectory data processing method includes:

[0033] S101: Obtain reference index information, where the reference index information has a corresponding index type.

[0034] Among them, the index information for which trajectory search is to be performed can be referred to as reference index information. The reference index information can specifically be time information, space information, time and space information, etc. The reference index information can be used to identify the query requirements of the query user. For example, if the query user hopes to query the trajectory in the time dimension, the reference index information entered by the query user can be time information, and so on. There is no limitation on this.

[0035] Among them, the form of the reference index information can specifically be a combination form of characters, numbers, texts, etc. There is no limitation on this.

[0036] In the embodiment of the present disclosure, when obtaining the reference index information, a query request interface can be provided in the trajectory data processing device, and the query request of the query user can be received through the query request interface. Then, the query request is parsed to obtain the reference index information. Of course, it is also possible to receive the query request sent by a third-party device and parse the query request to obtain the reference index information. There is no limitation on this.

[0037] Optionally, in some embodiments, when obtaining the reference index information, a query request can be received. The query request is adapted to the initial query language supported by the query user side device and is converted into a target query request. The target query request supports a first query language, and the first query language is different from the initial query language. The reference index information is parsed from the target query request, so that the application scenario of trajectory query can be effectively expanded. It not only supports trajectory query according to the reference index information in the query request, but also can effectively support parsing query requests in different query languages and converting the formats of query requests in different query languages, thus facilitating the query use of the query user.

[0038] Among them, the query language supported by the user side device can be referred to as the initial query language. The initial query language can be a visual language, or the language corresponding to a query request text obtained by converting voice data, or it can also be an unstructured query language. Correspondingly, the first query language can be, for example, a structured language. Then, converting the query request into a target query request means converting the unstructured query language into a structured language, so that the trajectory data processing device can effectively identify and parse the query request, and quickly obtain the reference index information, so as to facilitate efficient trajectory query.

[0039] After obtaining the reference index information, the embodiments of the present disclosure can perform parsing and analysis processing on the reference index information to determine the index type corresponding to the reference index information. Among them, the index type can be pre-configured and classified. After multiple index types are pre-configured and classified, corresponding data tables can be constructed for each index type. The data table can be referred to as a candidate data table. The data table corresponding to the index type indicates the index architecture method for the candidate trajectory in the data table, which is determined with reference to the corresponding index type. For specific details, please refer to the subsequent embodiments.

[0040] The index architecture method, for example, storing according to time information, storing according to space information, storing according to time and space information, is not limited thereto.

[0041] After the embodiments of the present disclosure pre-construct multiple candidate data tables, the index architecture method for the candidate trajectory in each candidate data table can be used to summarize the corresponding index type, and the index type can be used as the candidate index type corresponding to the candidate data table.

[0042] In the actual trajectory search application scenario, when parsing and analyzing the reference index information to determine the index type corresponding to the reference index information, the subsequent processing logic of matching the target data table according to the index type can be triggered.

[0043] Optionally, in some embodiments, the index type corresponding to the reference index information can be any one of the following: time index type, space index type, and spatio-temporal index type. Therefore, the embodiments of the present disclosure can support fast and efficient trajectory query based on the index type of the reference index information. Moreover, since the index architecture method in the target data table matching the index type is determined based on the corresponding index type, the obtained target trajectory can also represent the feature dimension concerned by the query user side, thereby assisting in improving the query application effect.

[0044] Of course, the index type can also be configured as any other possible dimensional types, such as trajectory data size type, time range type corresponding to the identity of the trajectory owner, trajectory similarity type, k-nearest neighbor type, etc. The trajectory data size type, time range type corresponding to the identity of the trajectory owner, trajectory similarity type, k-nearest neighbor type, etc. can also be classified as the above spatio-temporal index type, which is not limited thereto.

[0045] Among them, the time index type can refer to the type of indexing the trajectory based on the time dimension, and the time dimension can be the time range between the start point and the end point of the trajectory.

[0046] For example, as Figure 2 shownFigure 2 It is a schematic structural diagram of the index type in the embodiments of the present disclosure. Timerange (time period) can be, for example, a reference index information of a time index type. Using the function Bin(t s ) = [0, t] to query the trajectory within a given time range from the starting point 0 to the ending point t of the trajectory time range. Wherein, when the query user is querying, assuming that the input time period of the trajectory time range is between the starting point 0 and the ending point t, this time period of the trajectory time range between the starting point 0 and the ending point t can be called the reference index information. Correspondingly, the index type corresponding to this reference index information is the time index type.

[0047] Among them, the spatial index type can refer to the type of indexing the trajectory based on the spatial dimension. The spatial dimension can refer to the spatial geographical location covered between the starting point and the ending point of the trajectory.

[0048] For example, Figure 2 XZ in + can be, for example, a fine-grained spatial index type. Using the static spatial index to divide and refine the position space where the trajectory is located to obtain the minimum bounding rectangle of the trajectory (represented by a dashed box). When the query user is querying, assuming that the input is this minimum bounding rectangle (represented by a dashed box), then this minimum bounding rectangle (represented by a dashed box) can be used as the reference index information. The index type corresponding to this reference index information is the spatial index type, so as to effectively assist in querying to obtain the trajectory within a given spatial range.

[0049] Among them, the spatio-temporal index type can refer to the type of indexing the trajectory based on the combination of time and spatial dimension. The combination of time and spatial dimension can be, for example, the time range between the starting point and the ending point of the trajectory, and combined with the spatial geographical location covered between the starting point and the ending point of the trajectory.

[0050] For example, Figure 2 XZ in + T can be, for example, a spatio-temporal index type. First, the time dimension is split into timeperiod 1 to time period nMultiple non - overlapping time periods, and then within each time period, the spatial geographical location where the trajectory is located is segmented and refined according to the spatial index type to obtain the minimum bounding rectangle of the trajectory, so as to obtain the corresponding trajectory using the spatio - temporal range. When a query user makes a query, assuming that the input time range of the trajectory is between the starting point 0 and the ending point t, and the minimum bounding rectangle (represented by a dotted box) in the above example, then correspondingly, the time range of the trajectory between the starting point 0 and the ending point t combined with the minimum bounding rectangle (represented by a dotted box) can be jointly used as reference index information. Correspondingly, the index type corresponding to this reference index information is the spatio - temporal index type.

[0051] S102: Determine the target data table corresponding to the index type, where the target data table includes: multiple candidate index information and multiple candidate trajectories respectively corresponding to the multiple candidate index information.

[0052] After obtaining the reference index information and determining the index type corresponding to the reference index information, the target data table corresponding to the index type can be determined. The target data table is used to store multiple candidate index information and multiple candidate trajectories respectively corresponding to the multiple candidate index information. The target data table can be a data table in a relational database or a data table in other forms, and there is no limit to this.

[0053] That is to say, assuming that after pre - configuring and classifying multiple index types, a corresponding data table can be constructed for each index type. The determined target data table corresponding to the index type can indicate that the index architecture method for the candidate trajectory in the target data table is determined with reference to the corresponding index type. The index architecture method, for example, stores according to time information, stores according to spatial information, stores according to time and spatial information, and there is no limit to this.

[0054] Then the target data table corresponding to the index type indicates that its index architecture method for the candidate trajectory is adapted to the index type of the reference index information, thus ensuring the efficiency of trajectory query while ensuring the accuracy of trajectory query.

[0055] Among them, the range of multiple candidate index information in the target data table is usually larger than the range of the reference index information, that is, the index architecture method for the trajectory in the target data table matches the index type of the reference index information. Moreover, the trajectories stored in the target data table are collected and stored for a large number of trajectories based on the index architecture method. Therefore, the trajectories stored in the target data table can be called candidate trajectories, and the storage method for the candidate trajectories in the target data table corresponds to an index type. Then, the information used to identify the index position of the candidate trajectory generated after storing multiple candidate trajectories can be called candidate index information.

[0056] In the embodiments of the present disclosure, the target data table matching the index type can be first determined, and then, based on the reference index information in the target data table, the trajectory matching the reference index information is retrieved as the target trajectory.

[0057] In the embodiments of the present disclosure, when determining the target data table corresponding to the index type, the index type corresponding to each data table can be matched with the index type of the reference index information, and the data table matching the index type of the reference index information is obtained as the target data table, or the target data table corresponding to the index type can be obtained by referring to the index architecture mode of the data table, and there is no limitation thereto.

[0058] Optionally, in some embodiments, the target data table belongs to multiple candidate data tables. The candidate data tables include: multiple key-value pairs, where the key in the key-value pair stores the candidate index information, and the value corresponding to the key stores the candidate trajectory. Thus, the candidate index information and the candidate trajectory corresponding to the candidate index information are stored in the form of key-value pairs, which can effectively reduce the consumption of trajectory storage resources and the input / output (I / O) overhead.

[0059] For example, the candidate index information can be used as the key in the key-value pair, and the candidate trajectory corresponding thereto can be processed as the value corresponding to the key, and the field traj is used to represent the value of the trajectory, so as to support query and analysis operations on this field when querying the trajectory, and assist in improving the convenience and effect of query processing.

[0060] That is to say, the multiple candidate data tables can be pre-constructed, and the above index types can be pre-configured and classified. After multiple index types are pre-configured and classified, the corresponding data tables can be constructed for each index type, and the data tables can be referred to as candidate data tables. Among them, the data table corresponding to the index type indicates the index architecture mode for the candidate trajectory in the data table, which is determined with reference to the corresponding index type. When determining the target data table according to the index type, it can be retrieved from multiple candidate data tables. Each of the candidate data tables includes: multiple key-value pairs, where the key in the key-value pair stores the candidate index information, and the value corresponding to the key stores the candidate trajectory.

[0061] In the embodiments of the present disclosure, since the target data table can be determined from multiple candidate data tables, the target data table can also include multiple key-value pairs. Among them, the key in the key-value pair stores candidate index information, and the value corresponding to the key stores a candidate trajectory. That is, the target data table includes multiple candidate index information and multiple candidate trajectories respectively corresponding to the multiple candidate index information. Then, it is possible to trigger query processing directly based on the content stored in the target data table, effectively implementing query and analysis operations on trajectories using the values in the key-value pairs of the target data table. Storing trajectories in the form of key-value pairs reduces the storage occupancy of the database and the access overhead of trajectories.

[0062] S103: Determine the candidate index information that matches the reference index information from multiple candidate index information, and extract the target trajectory corresponding to the matching candidate index information. The target trajectory belongs to multiple candidate trajectories.

[0063] After determining the target data table corresponding to the index type as described above, where the target data table includes: multiple candidate index information and multiple candidate trajectories respectively corresponding to the multiple candidate index information, it is possible to determine the candidate index information that matches the reference index information from multiple candidate index information, and extract the target trajectory corresponding to the matching candidate index information.

[0064] In some embodiments, when determining the candidate index information that matches the reference index information from multiple candidate index information, the reference index information can be input into a hash function to calculate the key corresponding to the reference index information. The candidate index information corresponding to this key is the candidate index information that matches the reference index information.

[0065] In other embodiments, it is also possible to determine the similarity between the reference index information and each candidate index information, and use the candidate index information with the highest similarity as the candidate index information that matches the reference index information, and there is no limitation on this.

[0066] In the embodiments of the present disclosure, the target data table stores multiple candidate trajectories respectively corresponding to multiple candidate index information. When extracting the target trajectory information corresponding to the matching candidate index information, the key of the candidate index information that matches the reference index information can be used to locate the address where the corresponding value is located, and the value corresponding to this key is taken out as the target trajectory corresponding to the candidate index information. The target trajectory belongs to multiple candidate trajectories, and the number of the target trajectories can be one or more. Different target trajectories can belong to the same or different moving objects (the moving object can be referred to as a subject, and the subject can be, for example, a person, a vehicle, a movable device, etc., and there is no limitation on this).

[0067] S104: Perform a target operation on the target trajectory.

[0068] In the embodiments of the present disclosure, after extracting the corresponding target trajectory from the target data table according to the reference index information, the target operation on the target trajectory can be directly triggered. The target operation can be to analyze and process the target trajectory to output a data report, etc., and there is no limitation thereto.

[0069] In the embodiments of the present disclosure, the above-mentioned reference index information and processing method can both be configured in the query request. Thus, when the query request is converted into a structured query language, the converted target query language can include the semantics of querying according to the reference index information and the semantics of performing the target operation according to the processing method.

[0070] For example, taking the most commonly used spatial query and stay point detection in the trajectory query and analysis scenario as an example, in this scenario, stay points can be detected from the query results (multiple target trajectories) of the spatio-temporal index type. A stay point is a spatial area, such as an area where the courier stays for more than a given time threshold (minStayTimeInSecond), and the spatial area of this location is not greater than the distance threshold (maxStayDisInMeter).

[0071] Therefore, the area indicated by the stay point can be the delivery address, and the corresponding target query language can be as Figure 3 shown Figure 3 is a schematic diagram of the target query language in the embodiments of the present disclosure; among them, lines 7 to 10 indicate that the target trajectory is obtained from the database query using the spatio-temporal index type (the corresponding reference index information is the spatio-temporal range). Lines 1 to 3 perform the Stay Point Detection operation (stay point detection) on the extracted target trajectory, and lines 2 to 3 are the Stay Point Detection operation (stay point detection). As Figure 4 shown Figure 4 is a schematic diagram of the trajectory processing effect in the embodiments of the present disclosure, showing the original trajectory and the final processing result (multiple stay points obtained by processing) on the map.

[0072] In this embodiment, by obtaining reference index information, where the reference index information has a corresponding index type, determining a target data table corresponding to the index type, determining, from multiple candidate index information in the target data table, candidate index information that matches the reference index information, extracting a target trajectory corresponding to the matching candidate index information, and performing a target operation on the target trajectory. Since the target data table is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query scope, the trajectory query scope is effectively narrowed while effectively ensuring the accuracy of the query search. When the obtained target trajectory is used to assist in performing the target operation, the effective connection between trajectory query and trajectory processing is achieved, effectively ensuring the coherence of trajectory processing and improving the overall execution effect of trajectory processing.

[0073] In this embodiment, an architecture schematic of a trajectory data processing system can also be provided, as Figure 5 shown, Figure 5 is a schematic diagram of the architecture of the trajectory processing system in an embodiment of the present disclosure, including multiple data sources. The multiple data sources can be, for example, Disk Files, Hadoop distributed storage systems, the data warehouse tool Hive, and the distributed publish-subscribe messaging system Kafka. Multiple initial trajectories can be obtained from the multiple data sources, and then stored in multiple candidate data tables according to the multiple initial trajectories. Different candidate data tables correspond to different index storage structures, and the stored multiple candidate data tables can support querying of reference index information of different index types. The reference index information can be, for example, identity (ID) query information, spatial range query information, similar trajectory query information, k-nearest neighbor query information, spatio-temporal range query information, etc. Before querying and storing each candidate trajectory, corresponding preprocessing can also be performed on the multiple candidate trajectories respectively. For example, denoising, segmentation, interpolation, and map matching are supported to solve trajectory query and trajectory processing in one stop. Trajectory processing can include, for example, aggregation, clustering, stay point detection, and contact mining. The obtained processing results can be used for various trajectory applications, such as determining real-time reachable areas, crowd flow analysis, epidemic prevention and control, and publishing to online websites, etc., without limitation.

[0074] Based on the above Figure 5 shown architecture schematic of the trajectory processing system, another trajectory data processing method can also be provided in an embodiment of the present disclosure, as follows:

[0075] Figure 6 is a flowchart of the trajectory data processing method proposed in another embodiment of the present disclosure.

[0076] As Figure 6 shown, the trajectory data processing method includes:

[0077] S601: Obtain multiple initial trajectories.

[0078] Among them, the initial trajectory can be a trajectory pre - stored in multiple data sources. This trajectory can be detected by using sensors or applications, etc., for the running actions of a moving object. For example, the Global Positioning System (GPS) log information can be sampled at a certain sampling rate to obtain multiple trajectories, which are stored in multiple data sources. Thus, the trajectory processing system can directly obtain multiple trajectories from multiple data sources and use them as multiple initial trajectories respectively.

[0079] S602: Pre - process the multiple initial trajectories respectively to obtain multiple candidate trajectories.

[0080] In the embodiments of the present disclosure, after obtaining multiple initial trajectories from multiple data sources, the multiple initial trajectories can be pre - processed. This pre - processing can be noise filtering and segmentation processing of the initial trajectories, etc., and there is no limitation thereto.

[0081] In the embodiments of the present disclosure, the multiple initial trajectories are pre - processed respectively to obtain multiple candidate trajectories, so as to avoid the influence of data noise and sampling rate of the collected original GPS log data on the accuracy and processing performance of trajectory processing.

[0082] S603: Determine multiple time - distribution features respectively corresponding to the multiple candidate trajectories, and determine multiple space - distribution features respectively corresponding to the multiple candidate trajectories.

[0083] Among them, there is a time - distribution feature and a space - distribution feature respectively corresponding to each candidate trajectory. The time - distribution feature is used to characterize the feature distribution of the candidate trajectory in the time dimension. For example, the time period between the start time and the end time of the candidate trajectory. The space - distribution feature is used to characterize the feature distribution of the candidate trajectory in the space dimension. For example, the position area between the start position and the end position of the candidate trajectory, and there is no limitation thereto.

[0084] The time - distribution feature and the space - distribution feature determined in the embodiments of the present disclosure can be used to determine the candidate index information corresponding to the candidate trajectory and assist in determining the index architecture method for storing the multiple candidate trajectories.

[0085] For example, according to the time distribution characteristics, the candidate trajectory can be stored in the candidate data table corresponding to the time index type, or according to the spatial distribution characteristics, the candidate trajectory can be stored in the candidate data table corresponding to the spatial index type, or according to the combination of the time distribution characteristics and the spatial distribution characteristics, the candidate trajectory can be stored in the candidate data table corresponding to the spatio-temporal index type. That is to say, in order to adapt to different index types, the same candidate trajectory can be stored in multiple candidate data tables, and there is no limitation on this.

[0086] In the embodiments of the present disclosure, when determining multiple time distribution characteristics respectively corresponding to multiple candidate trajectories, the multiple candidate trajectories can be input into a time feature recognition model, and the time feature recognition model is used to perform time feature analysis and processing on the multiple candidate trajectories respectively, and calculate multiple time distribution characteristics respectively corresponding to the multiple candidate trajectories.

[0087] In the embodiments of the present disclosure, when determining multiple spatial distribution characteristics respectively corresponding to multiple candidate trajectories, the multiple candidate trajectories can be input into a spatial feature recognition model, and the spatial feature recognition model is used to perform spatial feature analysis and processing on the multiple candidate trajectories respectively, and calculate multiple spatial distribution characteristics respectively corresponding to the multiple candidate trajectories.

[0088] In the embodiments of the present disclosure, corresponding fusion processing can also be performed on the time distribution characteristics and the spatial distribution characteristics of the candidate trajectory to obtain spatio-temporal distribution characteristics, and the spatio-temporal distribution characteristics can also be used to determine candidate index information corresponding to the candidate trajectory and assist in determining the index architecture method for storing the multiple candidate trajectories.

[0089] Optionally, in some embodiments, at least some of the time distribution characteristics satisfy the time similarity condition, and / or at least some of the spatial distribution characteristics satisfy the spatial similarity condition. The time similarity condition can be used to assist in classifying some candidate trajectories with similar time distribution characteristics in the time dimension, and the spatial similarity condition can be used to assist in classifying some candidate trajectories with similar spatial distribution characteristics in the spatial dimension, so as to facilitate the construction of the candidate data table, assist in classifying and storing some candidate trajectories that satisfy the time similarity condition in the candidate data table corresponding to the time index type, and assist in classifying and storing some candidate trajectories that satisfy the spatial similarity condition in the candidate data table corresponding to the spatial index type, and classifying and storing some candidate trajectories that satisfy both the time similarity condition and the spatial similarity condition in the candidate data table of the spatio-temporal index type.

[0090] Of course, other arbitrary possible classification methods can also be used to determine the candidate trajectories classified into the same candidate data table, such as the semantic matching method, the method of corresponding subject identification association relationship, etc., and there is no limitation on this.

[0091] Among them, the time similarity condition can be a pre-set inspection condition, which can be configured such that the proportion of the same part of multiple time distribution features is greater than a numerical threshold; the space similarity condition can be a pre-set inspection condition, which can be configured such that the proportion of the same part of multiple space distribution features is greater than a numerical threshold, and there is no limitation on this.

[0092] In the embodiments of the present disclosure, after determining multiple time distribution features corresponding to multiple candidate trajectories respectively and determining multiple space distribution features corresponding to multiple candidate trajectories respectively, the time similarity condition and the space similarity condition can be used to inspect the multiple time distribution features and the multiple space distribution features. If the proportion of the same part of the time distribution features is greater than the numerical threshold, then the time similarity condition is satisfied among some of the time distribution features; if the proportion of the same part of the space distribution features is greater than the numerical threshold, then the space similarity condition is satisfied among some of the space distribution features; at least some of the time distribution features satisfy the time similarity condition, and at least some of the space distribution features satisfy the space similarity condition.

[0093] S604: Determine a combined feature corresponding to the index type, where the combined feature includes: at least some of the time distribution features and / or at least some of the space distribution features.

[0094] In the embodiments of the present disclosure, after determining multiple time distribution features corresponding to multiple candidate trajectories respectively and determining multiple space distribution features corresponding to multiple candidate trajectories respectively, some of the time distribution features, some of the space distribution features, and the spatio-temporal distribution features that fuse the some of the time distribution features and the some of the space distribution features can be taken out according to a certain proportion, and the some of the time distribution features, the some of the space distribution features, and the spatio-temporal distribution features that fuse the some of the time distribution features and the some of the space distribution features are jointly used as the combined feature.

[0095] It can be understood that since the some of the time distribution features, the some of the space distribution features, and the spatio-temporal distribution features that fuse the some of the time distribution features and the some of the space distribution features meet the above time similarity condition and space similarity condition, the candidate index information can be assisted to be formed based on the combined feature that meets the condition, and the candidate trajectory to which the corresponding combined feature belongs is stored in the candidate data table indicated by the candidate index information, so as to complete the construction of multiple candidate data tables.

[0096] For example, according to the combined feature that meets the condition to assist in forming candidate index information, taking the candidate index information as the key and the corresponding candidate trajectory as the value to form a key-value pair, storing the key-value pair in the candidate data table, and using the candidate index type of the candidate index information to identify the candidate data table.

[0097] S605: Generate candidate index information corresponding to the index type according to the combined features.

[0098] After determining various combined features as described above, candidate index information corresponding to the index type can be generated according to each combined feature. This candidate index information can be used to index the corresponding candidate trajectories in the corresponding candidate data table.

[0099] When generating candidate index information corresponding to the index type according to the combined features, numerical processing can be performed on the combined features to obtain feature values, and these feature values can be used as candidate index information. Alternatively, the combined features can also be input into an index value generation model to obtain the candidate index information generated by the index value generation model. There is no limitation on this.

[0100] For example, after combining at least part of the time distribution features and / or at least part of the space distribution features into combined features, algorithm can be used to generate candidate index information corresponding to the index type according to the combined features. If the combined features are composed of part of the time distribution features, the index type of the candidate index information formed at this time is the time index type. If the combined features are composed of part of the space distribution features, the index type of the candidate index information formed at this time is the space index type. If the combined features are composed of part of the time distribution features and part of the space distribution features, the index type of the candidate index information formed at this time is the spatio-temporal index type.

[0101] S606: Generate a candidate data table according to the candidate trajectories corresponding to the combined features and the candidate index information corresponding to the combined features.

[0102] In the embodiments of the present disclosure, after generating candidate index information corresponding to the index type according to the combined features, a candidate data table can be generated according to the candidate trajectories corresponding to the combined features and the candidate index information corresponding to the combined features.

[0103] In the embodiments of the present disclosure, when generating a candidate data table according to the candidate trajectories corresponding to the combined features and the candidate index information corresponding to the combined features, a candidate data table can be created using a database definition language. The candidate index information and the candidate trajectories are two fields in the candidate data table respectively.

[0104] For example, key-value pairs can be generated according to the candidate index information and the candidate trajectories. Multiple candidate trajectories can be correspondingly stored in multiple key-value pairs, and then the multiple key-value pairs are stored in the candidate data table.

[0105] Therefore, in the embodiments of the present disclosure, by obtaining a plurality of initial trajectories, respectively preprocessing the plurality of initial trajectories to obtain a plurality of candidate trajectories, determining a plurality of time distribution features respectively corresponding to the plurality of candidate trajectories, and determining a plurality of spatial distribution features respectively corresponding to the plurality of candidate trajectories, determining a combined feature corresponding to the index type, the combined feature includes: at least part of the time distribution features and / or at least part of the spatial distribution features, and forming candidate index information corresponding to the index type according to the combined feature, and generating the candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature, so that the candidate trajectories in multiple data sources (Disk Files, Hadoop distributed storage system, data warehouse tool Hive, and distributed publish-subscribe messaging system Kafka) can be efficiently stored in different candidate data tables through different index types. By using these multiple index types and the candidate data tables corresponding to each index type, it is possible to efficiently support spatio-temporal queries of trajectories (such as ID time range query, spatial range query, similar trajectory query, k-nearest neighbor query, spatio-temporal range query), etc.

[0106] S607: Receive a query request, and the query request adapts to the initial query language supported by the query user side device.

[0107] Among them, the query request is sent by the query user, and the query request is composed of an initial query language supported by the query user side device. The initial query language can be an initial database query statement.

[0108] In the embodiments of the present disclosure, a standard interface for the program to access the database can be configured in the database, and the query request is received via this interface, and the target trajectory to be queried is parsed from the query request.

[0109] S608: Convert the query request into a target query request. The target query request supports a first query language, and the first query language is different from the initial query language.

[0110] In the embodiments of the present disclosure, after receiving the query request, the query request can be converted by using a database language conversion tool. The query request is converted into a target query request. The converted target query request supports a first query language. The converted target query request is different from the initial query request. The first query language supported by the target query request is different from the initial query language corresponding to the initial query request. Thus, the application scenario of trajectory query can be effectively expanded. It not only supports trajectory query according to the reference index information in the query request, but also can effectively support parsing query requests in different query languages and converting the formats of query requests in different query languages, so as to facilitate the query use of query users.

[0111] Optionally, in some embodiments, the first query language is Structured Query Language (SQL).

[0112] Among them, the structured query language has a structured query syntax and a parsing tool, and the target query request can be parsed by the structured query language parsing tool to obtain reference index information.

[0113] Among them, the query language supported by the user-side device can be referred to as the initial query language. The initial query language can be a visual language, or a language corresponding to a query request text obtained by converting voice data, or it can also be an unstructured query language. Correspondingly, the first query language can be, for example, a structured language. Then, the query request is converted into a target query request, that is, the unstructured query language is converted into a structured language, so as to effectively facilitate the recognition and parsing of the query request by the trajectory data processing device, facilitate the rapid acquisition of reference index information, and facilitate the efficient trajectory query.

[0114] S609: Parse reference index information from the target query request.

[0115] In the embodiments of the present disclosure, after the query request is converted into a target query request as described above, a parsing tool capable of parsing the first query language can be used to parse the target query request. Among them, the first query language is a structured query language, and the structured query language parsing tool can be used to parse and verify the target query language, and generate a regular expression or a spatio-temporal operator expression required to query the target trajectory from the candidate trajectories as the reference index information.

[0116] S610: Determine a target data table corresponding to the index type, where the target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information.

[0117] S611: Determine candidate index information that matches the reference index information from the plurality of candidate index information, and extract the target trajectory corresponding to the matching candidate index information. The target trajectory belongs to the plurality of candidate trajectories.

[0118] For the description of S610-S611, specific reference can be made to the above embodiments, which will not be elaborated here.

[0119] S612: Perform a target operation on the target trajectory.

[0120] In the embodiments of the present disclosure, after the target trajectory corresponding to the reference index information is extracted from the target data table, a target operation on the target trajectory can be directly triggered. The target operation can be to analyze and process the target trajectory to output a data report, etc., which is not limited thereto.

[0121] Optionally, in some embodiments, after parsing the reference index information from the target query request, the target operation type and operation parameters can be parsed from the target query request. Then, performing the target operation on the target trajectory, the target operation corresponding to the target operation type can be determined, and according to the operation parameters, the target operation is performed on the target trajectory. Thus, the target operation type and operation parameters can be parsed from the target query request, and targeted operation processing is performed on the target trajectory, improving the coherence of trajectory query and trajectory processing, and effectively improving the parallel processing efficiency of the trajectory.

[0122] Among them, the target operation type refers to the type of the target operation performed on the target trajectory. The target operation type can be operations such as processing, aggregation, dwell point detection, and clustering, without limitation.

[0123] Among them, the operation parameters are the parameters used when performing the target operation on the target trajectory. For example, when the target operation type is dwell point detection, the operation parameter can be a given time threshold, and it can be determined according to this time threshold that the area indicated by the dwell point may be a delivery address, etc.

[0124] In the embodiments of the present disclosure, when parsing the target operation type and operation parameters from the target query request, a database query statement for trajectory analysis can be used to parse the target query request to obtain the target operation type and operation parameters, and according to the operation parameters, the target operation is performed on the target trajectory.

[0125] Optionally, in some embodiments, the number of target trajectories is multiple. When performing the target operation on the target trajectories, aggregation processing can be performed on the multiple target trajectories, and / or dwell point detection processing can be performed on the multiple target trajectories, and / or clustering processing can be performed on the multiple target trajectories to obtain a target trajectory set. The target trajectory set includes: at least part of the target trajectories, where at least part of the target trajectories are used to analyze the motion pattern of the subject to which they belong, and / or at least part of the target trajectories are used to analyze the spatial association relationship between the first subject and the second subject, and the first subject and the second subject respectively belong to multiple subjects. Thus, multiple target operations can be performed on the target trajectories, improving the processing efficiency of the trajectories in the actual application scenario.

[0126] In the embodiments of the present disclosure, after preprocessing the initial trajectory, the target trajectory can be queried, and the target operation can be performed on the target trajectory.

[0127] In the embodiments of the present disclosure, when performing aggregation processing on multiple target trajectories, a function can be used to perform aggregation processing on the multiple target trajectories, such as the maximum value function max, or the minimum value function min, etc., without limitation.

[0128] Among them, the dwell point detection process is used to detect the dwell event types of moving objects. For example, the dwell event type can be a vehicle dwelling for refueling, a courier dwelling waiting for goods delivery, etc. When performing dwell point detection processing on multiple target trajectories, the dwell events of moving objects can be obtained by analyzing the locations where the trajectory points stop.

[0129] Among them, the clustering process is used to cluster similar trajectories together and can be used to analyze group movement patterns.

[0130] In the embodiments of the present disclosure, when performing clustering processing on multiple target trajectories, some similar target trajectories can be extracted to form a target trajectory set, and the target trajectory set is used to analyze the movement pattern of its subject.

[0131] In the embodiments of the present disclosure, some dissimilar target trajectories can be extracted to analyze the spatial association relationship between the first subject and the second subject. The first subject and the second subject respectively belong to multiple subjects. The target trajectories can be respectively input into a data analysis model to output corresponding data features, and the data features are used to analyze the spatial association relationship between the first subject and the second subject. The spatial association relationship, for example, whether the first subject and the second subject are close contacts, etc., is not limited thereto.

[0132] In this embodiment, while effectively narrowing the trajectory query range, the accuracy of query search is effectively guaranteed. When using the queried target trajectory to assist in executing the target operation, the effective connection between trajectory query and trajectory processing is realized, the coherence of trajectory processing is effectively guaranteed, and the overall execution and processing effect of trajectory processing is improved. By obtaining multiple initial trajectories, preprocessing the multiple initial trajectories respectively to obtain multiple candidate trajectories, determining multiple time distribution features respectively corresponding to the multiple candidate trajectories, determining multiple spatial distribution features respectively corresponding to the multiple candidate trajectories, determining a combined feature corresponding to the index type, the combined feature includes: at least part of the time distribution features and / or at least part of the spatial distribution features, and forming candidate index information corresponding to the index type according to the combined feature, and generating the candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature, so that the candidate trajectories in multiple data sources (Disk Files, Hadoop distributed storage system, data warehouse tool Hive, and distributed publish-subscribe messaging system Kafka) can be efficiently stored in different candidate data tables through different index types. By using the multiple index types and the candidate data tables corresponding to each index type, the spatio-temporal query of trajectories (such as ID time range query, spatial range query, similar trajectory query, k-nearest neighbor query, spatio-temporal range query, etc.) can be efficiently supported. It can effectively expand the application scenarios of trajectory query, not only support trajectory query according to the reference index information in the query request, but also effectively support parsing the query requests in different query languages and converting the formats of the query requests in different query languages, so as to facilitate the query use of query users. After parsing the reference index information from the target query request, the target operation type and operation parameters can be parsed from the target query request, then the target operation corresponding to the target operation type can be determined for the target trajectory, and the target operation is executed on the target trajectory according to the operation parameters, so that the target operation type and operation parameters can be parsed from the target query request, and targeted operation processing is performed on the target trajectory, improving the coherence of trajectory query and trajectory processing, and effectively improving the parallel processing efficiency of trajectories.

[0133] Figure 7 It is a schematic flowchart of a trajectory data processing method proposed by an embodiment of the present disclosure.

[0134] As Figure 7 shown, the trajectory data processing method includes:

[0135] S701: Determine multiple data sources, and the multiple data sources respectively correspond to multiple types and multiple data source addresses.

[0136] Among them, the database for storing trajectories can be referred to as a data source, which can be, for example, a Hadoop distributed storage system, a data warehouse tool Hive, a distributed publish-subscribe messaging system Kafka, etc., without limitation.

[0137] In the embodiments of the present disclosure, trajectories can come from multiple data sources. The multiple data sources respectively correspond to multiple types and multiple data source addresses. The type corresponding to the data source characterizes the data type of the trajectories stored in the data source, and the data source address is used to identify the corresponding address of the data source. The corresponding data source can be located based on the data source address.

[0138] S702: Determine multiple mapping association relationships between multiple data sources respectively corresponding thereto and the values corresponding to the keys according to the multiple types.

[0139] After determining the multiple data sources as described above, the trajectories from the multiple data sources can be loaded into a structured data processing engine, and the structured data processing engine is used for data processing.

[0140] For example, as Figure 8 shown, Figure 8 is a schematic diagram of the SQL engine architecture in the embodiments of the present disclosure. After loading the trajectories from multiple data sources into the data processing engine, the trajectories can be selected using SQL statements, and the SQL statements can be parsed and processed using the Apache Calcite parsing tool.

[0141] For example, data loading can be implemented using structured query language.

[0142] For example, as Figure 9 shown, Figure 9 is a schematic diagram of the data loading statement in the embodiments of the present disclosure. Among them, the <source type> in the first row is the corresponding data source address. The data source can be a Hadoop distributed storage system, a data warehouse tool Hive, a distributed publish-subscribe messaging system Kafka, etc., without limitation.

[0143] In the embodiments of the present disclosure, after loading the trajectories from multiple data sources into the structured data processing engine, multiple mapping association relationships between multiple data sources respectively corresponding thereto and the values corresponding to the keys can be determined according to the multiple types of the data sources, and structured query language can be used to implement the construction of multiple mapping association relationships from the data sources to the values corresponding to the keys of the multiple data sources respectively corresponding thereto.

[0144] For example, Figure 8 the CONFIG keyword in the second row statement in

[0145] S703: Generate a query statement that supports the second query language according to the type, data source address, and mapping association relationship.

[0146] Among them, the second query language is a database query language used to query and extract trajectories from a data table.

[0147] In the embodiments of the present disclosure, after determining multiple types and multiple data source addresses corresponding to multiple data sources, and determining various mapping association relationships between the multiple data sources and the values corresponding to the keys respectively, a query statement can be generated according to the type, data source address, and mapping association relationship of the data source by using the database query statement syntax, so that the query and extraction of trajectories can be performed in multiple data sources by using the query statement of the second query language.

[0148] Optionally, in some embodiments, the second query language is the Structured Query Language.

[0149] Among them, the Structured Query Language can select trajectories from a data table by using structured query statements. The Structured Query Language can select trajectories based on multiple dimension types, and the dimension type can be the trajectory data size type, the time range type corresponding to the subject identifier of the trajectory, the trajectory similarity type, the k-nearest neighbor type, etc., and there is no limitation thereto.

[0150] S704: Query multiple initial trajectories from the corresponding multiple data sources according to multiple query statements.

[0151] In the embodiments of the present disclosure, when querying multiple initial trajectories from the corresponding multiple data sources according to multiple query statements, multiple initial trajectories can be queried from multiple data sources by using structured query statements. Among them, when querying multiple initial trajectories from multiple data sources by using structured query statements, trajectories can be selected based on multiple dimension types.

[0152] For example, as Figure 10 shown, Figure 10 is a schematic diagram of a structured trajectory query statement in the embodiments of the present disclosure. Taking the selection of trajectories based on the spatial index type as an example, where st_makeBBox is the spatial range covered between the starting point (lng1, lat1) and the ending point (lng2, lat2) of the trajectory, st_within indicates that the trajectory is inside this space, and traj in the statement represents the value of the trajectory, so as to select trajectories from the data table based on the spatial dimension by using the second query language as initial trajectories.

[0153] S705: Preprocess multiple initial trajectories respectively to obtain multiple candidate trajectories.

[0154] Optionally, in some embodiments, when preprocessing multiple initial trajectories to obtain multiple candidate trajectories, noise reduction processing can be performed on the multiple initial trajectories respectively to obtain multiple candidate trajectories, and / or the initial trajectories can be segmented to obtain multiple trajectory segments and use them as multiple candidate trajectories, and / or interpolation processing can be performed on the multiple initial trajectories respectively to obtain multiple candidate trajectories, and / or the multiple initial trajectories can be mapped to a road network map respectively to map and obtain multiple road trajectories, and use the multiple road trajectories as multiple candidate trajectories. Thus, preprocessing operations can be performed on the initial trajectories by means of noise reduction processing and segmentation processing, etc., to avoid the impact of data noise on the accuracy of trajectory analysis and avoid the impact of data distribution imbalance caused by the sampling rate on the performance of trajectory processing.

[0155] Among them, the noise reduction processing is used to filter out abnormal data in the initial trajectory, and the trajectory after noise reduction can be used as multiple candidate trajectories. For example, when performing noise reduction processing on GPS log data, abnormal logs in the GPS log data can be filtered. The abnormal log can be, for example, a point that significantly deviates from the trajectory, and then the error point in the trajectory can be removed to implement the noise reduction processing of the GPS log data.

[0156] In the embodiments of the present disclosure, when segmenting the initial trajectory, the initial trajectory can be divided into several segments according to certain rules, and the segmented initial trajectory can be used as multiple candidate trajectories. Using some of the segmented trajectory segments for trajectory analysis can reduce the computational complexity when performing data analysis tasks and improve the data analysis efficiency.

[0157] In the embodiments of the present disclosure, when performing interpolation processing on multiple initial trajectories, some new trajectory points can be inserted into the initial trajectory. The new trajectory points can be some important logs ignored by the terminal, such as low battery power, etc., and there is no limitation thereto.

[0158] In the embodiments of the present disclosure, when mapping multiple initial trajectories to a road network map respectively, the initial trajectories can be projected onto the road network to obtain multiple road trajectories, and the multiple road trajectories can be used as multiple candidate trajectories.

[0159] S706: Determine multiple time distribution features respectively corresponding to the multiple candidate trajectories, and determine multiple spatial distribution features respectively corresponding to the multiple candidate trajectories.

[0160] Optionally, in some embodiments, when determining multiple time distribution features corresponding to multiple candidate trajectories respectively and determining multiple spatial distribution features corresponding to multiple candidate trajectories respectively, multiple trajectory start times corresponding to multiple candidate trajectories can be determined, multiple trajectory end times corresponding to multiple candidate trajectories can be determined, and the multiple trajectory start times and the corresponding multiple trajectory end times are respectively used as multiple time distribution features, multiple boundary rectangle features corresponding to multiple candidate trajectories are determined, and the multiple boundary rectangle features are respectively used as multiple spatial distribution features, so that the time distribution features and spatial distribution features corresponding to multiple candidate trajectories can be extracted. Since the trajectory start time and the trajectory end time are used to characterize the time distribution features, and the boundary rectangle features are used to characterize the spatial distribution features, the expression effect of the time distribution features on the time dimension features of the candidate trajectories can be effectively improved, and the expression effect of the spatial distribution features on the spatial dimension features of the candidate trajectories can be improved, assisting in quickly and accurately querying the trajectories according to the spatio-temporal distribution of the trajectories when determining the candidate index information using the time distribution features and the spatial distribution features subsequently, and significantly improving the query efficiency of the trajectories.

[0161] In the embodiments of the present disclosure, when determining multiple trajectory start times and multiple trajectory end times corresponding to multiple candidate trajectories respectively, the multiple candidate trajectories can be input into a time feature recognition model, and the time feature recognition model is used to perform time feature analysis and processing on the multiple candidate trajectories respectively, calculate multiple trajectory start times and multiple trajectory end times corresponding to the multiple candidate trajectories respectively, and the multiple trajectory start times and the corresponding multiple trajectory end times are respectively used as multiple time distribution features.

[0162] In the embodiments of the present disclosure, when determining multiple boundary rectangle features corresponding to multiple candidate trajectories respectively, the multiple candidate trajectories can be input into a spatial feature recognition model, and the spatial feature recognition model is used to perform spatial feature analysis and processing on the multiple candidate trajectories respectively, calculate multiple boundary rectangle features corresponding to the multiple candidate trajectories respectively, and the multiple boundary rectangle features are respectively used as multiple spatial distribution features.

[0163] S707: Determine a combined feature corresponding to the index type, where the combined feature includes: at least part of the time distribution features and / or at least part of the spatial distribution features.

[0164] S708: Form candidate index information corresponding to the index type according to the combined feature.

[0165] S709: Generate a candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature.

[0166] S710: Obtain reference index information, where the reference index information has a corresponding index type.

[0167] S711: Determine a target data table corresponding to the index type, where the target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information.

[0168] S712: Determine, from the plurality of candidate index information, the candidate index information that matches the reference index information, and extract the target trajectory corresponding to the matching candidate index information, where the target trajectory belongs to the plurality of candidate trajectories.

[0169] For the descriptions of S707 - S712, specific reference may be made to the above - mentioned embodiments, which will not be elaborated here.

[0170] S713: Perform a target operation on the target trajectory.

[0171] In the embodiments of the present disclosure, when performing a target operation on the target trajectory, a structured data processing engine may be used to analyze a specific statement of a structured query language, so as to parse and obtain the type of the target operation performed on the target trajectory.

[0172] For example, as Figure 11 shown, Figure 11 is a schematic diagram of a structured language parsing statement in the embodiments of the present disclosure, where <analyzing operation> is the type of the target operation, and parameters are operation parameters corresponding to the type of the target operation.

[0173] In this embodiment, by obtaining reference index information, where the reference index information has a corresponding index type, a target data table corresponding to the index type is determined. The target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information. A candidate index information that matches the reference index information is determined from the plurality of candidate index information, and a target trajectory corresponding to the matching candidate index information is extracted. The target trajectory belongs to the plurality of candidate trajectories, and a target operation is performed on the target trajectory. It is possible to query the target trajectory from the target data table using the reference index and process and analyze the target trajectory. Since the target data table is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query range, the trajectory query range is effectively narrowed while effectively ensuring the accuracy of the query search. When the target trajectory obtained by the query is used to assist in performing the target operation, the effective connection between trajectory query and trajectory processing is realized, effectively ensuring the coherence of trajectory processing and improving the overall execution effect of trajectory processing. The initial trajectory is preprocessed by means of noise reduction processing and segmentation processing, etc., so as to avoid the influence of data noise on the accuracy of trajectory analysis and avoid the influence of data distribution imbalance caused by the sampling rate on the performance of trajectory processing. Since the starting time and ending time of the trajectory are used to characterize the time distribution feature and the boundary rectangle feature is used to characterize the spatial distribution feature, the expression effect of the time distribution feature on the time dimension feature of the candidate trajectory can be effectively improved, and the expression effect of the spatial distribution feature on the spatial dimension feature of the candidate trajectory can be improved, assisting in quickly and accurately querying the trajectory according to the spatio-temporal distribution of the trajectory when determining the candidate index information using the time distribution feature and the spatial distribution feature subsequently, and significantly improving the query efficiency of the trajectory.

[0174] Figure 12 It is a schematic structural diagram of a trajectory data processing device proposed in an embodiment of the present disclosure.

[0175] As Figure 12 shown, the trajectory data processing device 120 includes:

[0176] A first acquisition module 1201, configured to acquire reference index information, where the reference index information has a corresponding index type;

[0177] A first determination module 1202, configured to determine a target data table corresponding to the index type, where the target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information;

[0178] The second determination module 1203 is configured to determine, from multiple candidate index information, candidate index information that matches the reference index information, and extract a target trajectory corresponding to the matching candidate index information, where the target trajectory belongs to multiple candidate trajectories;

[0179] The execution module 1204 is configured to perform a target operation on the target trajectory.

[0180] In some embodiments of the present disclosure, the target data table belongs to multiple candidate data tables, and the candidate data tables include: multiple key-value pairs, where the key in the key-value pair stores the candidate index information, and the value corresponding to the key stores the candidate trajectory.

[0181] In some embodiments of the present disclosure, the index type is any one of the following: a time index type, a space index type, and a spatio-temporal index type.

[0182] In some embodiments of the present disclosure, as Figure 13 shown, Figure 13 is a schematic structural diagram of a trajectory data processing device proposed in another embodiment of the present disclosure, and further includes:

[0183] The second acquisition module 1205 is configured to acquire multiple initial trajectories before acquiring the reference index information;

[0184] The preprocessing module 1206 is configured to preprocess each of the multiple initial trajectories to obtain multiple candidate trajectories;

[0185] The third determination module 1207 is configured to determine multiple time distribution features respectively corresponding to the multiple candidate trajectories, and determine multiple space distribution features respectively corresponding to the multiple candidate trajectories;

[0186] The fourth determination module 1208 is configured to determine a combined feature corresponding to the index type, where the combined feature includes: at least part of the time distribution features and / or at least part of the space distribution features;

[0187] The first generation module 1209 is configured to form candidate index information corresponding to the index type according to the combined feature;

[0188] The second generation module 1210 is configured to generate the candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature.

[0189] In some embodiments of the present disclosure, at least part of the time distribution features satisfy a time similarity condition; and / or at least part of the space distribution features satisfy a space similarity condition.

[0190] In some embodiments of the present disclosure, the third determination module 1207 is specifically configured to:

[0191] Determine multiple trajectory start times corresponding to multiple candidate trajectories respectively;

[0192] Determine multiple trajectory end times corresponding to multiple candidate trajectories respectively, and use the multiple trajectory start times and the corresponding multiple trajectory end times as multiple time distribution features respectively;

[0193] Determine multiple bounding rectangle features corresponding to multiple candidate trajectories respectively, and use the multiple bounding rectangle features as multiple spatial distribution features respectively.

[0194] In some embodiments of the present disclosure, the preprocessing module 1206 is specifically configured to:

[0195] Perform noise reduction processing on multiple initial trajectories respectively to obtain multiple candidate trajectories; and / or

[0196] Perform segmentation processing on the initial trajectories to obtain multiple trajectory segments and use them as multiple candidate trajectories; and / or

[0197] Perform interpolation processing on multiple initial trajectories respectively to obtain multiple candidate trajectories; and / or

[0198] Map multiple initial trajectories to a road network map respectively to map multiple road trajectories, and use the multiple road trajectories as multiple candidate trajectories.

[0199] In some embodiments of the present disclosure, the execution module 1204 further includes:

[0200] An aggregation sub-module 12041 for performing aggregation processing on multiple target trajectories;

[0201] A detection sub-module 12042 for performing dwelling point detection processing on multiple target trajectories;

[0202] A clustering sub-module 12043 for performing clustering processing on multiple target trajectories to obtain a target trajectory set, the target trajectory set including: at least some of the target trajectories, where at least some of the target trajectories are used to analyze the motion pattern of the subject to which they belong, and / or at least some of the target trajectories are used to analyze the spatial association relationship between a first subject and a second subject, the first subject and the second subject belonging to multiple subjects respectively.

[0203] In some embodiments of the present disclosure, the first acquisition module 1201 is specifically configured to:

[0204] Receive a query request, and the query request is adapted to the initial query language supported by the query user-side device;

[0205] Convert the query request into a target query request, the target query request supporting a first query language, and the first query language is different from the initial query language;

[0206] Parse the reference index information from the target query request.

[0207] In some embodiments of the present disclosure, the second acquisition module 1205 is specifically configured to:

[0208] Determine a plurality of data sources, where the plurality of data sources respectively correspond to a plurality of types and a plurality of data source addresses;

[0209] Determine a variety of mapping association relationships between the plurality of data sources corresponding to the plurality of types and the values corresponding to the keys;

[0210] Generate a query statement that supports the second query language according to the type, the data source address, and the mapping association relationship;

[0211] Query a plurality of initial trajectories from the corresponding plurality of data sources according to the plurality of query statements.

[0212] In some embodiments of the present disclosure, the first acquisition module 1201 is further configured to:

[0213] After parsing the reference index information from the target query request, parse the target operation type and operation parameters from the target query request;

[0214] Wherein, the execution module 1204 is further configured to:

[0215] Determine a target operation corresponding to the target operation type;

[0216] Execute the target operation on the target trajectory according to the operation parameters.

[0217] In some embodiments of the present disclosure, the first query language is the Structured Query Language.

[0218] In some embodiments of the present disclosure, the second query language is the Structured Query Language.

[0219] Corresponding to the Figures 1 to 11 trajectory data processing method provided in the above Figures 1 to 11 embodiment, the present disclosure further provides a trajectory data processing device. Since the trajectory data processing device provided in the embodiments of the present disclosure corresponds to the

[0220] In this embodiment, by obtaining reference index information, where the reference index information has a corresponding index type, a target data table corresponding to the index type is determined. The target data table includes: a plurality of candidate index information and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information. A candidate index information that matches the reference index information is determined from the plurality of candidate index information, and a target trajectory corresponding to the matching candidate index information is extracted. The target trajectory belongs to the plurality of candidate trajectories, and a target operation is performed on the target trajectory. Since the target data table is indexed according to the index type, which is associated with the reference index information, and the target data table is used as the query range, the trajectory query range is effectively reduced while effectively ensuring the accuracy of the query search. When the obtained target trajectory is used to assist in performing the target operation, the effective connection between trajectory query and trajectory processing is realized, effectively ensuring the coherence of trajectory processing and improving the overall execution effect of trajectory processing.

[0221] To implement the above embodiment, the present disclosure also proposes a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the trajectory data processing method proposed in the foregoing embodiment of the present disclosure is implemented.

[0222] To implement the above embodiment, the present disclosure also proposes a non-transitory computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the trajectory data processing method proposed in the foregoing embodiment of the present disclosure is implemented.

[0223] To implement the above embodiment, the present disclosure also proposes a computer program product. When the instruction processor in the computer program product executes, the trajectory data processing method proposed in the foregoing embodiment of the present disclosure is executed.

[0224] Figure 14 A block diagram of an exemplary computer device suitable for implementing the embodiments of the present disclosure is presented. Figure 14 The computer device 12 shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0225] As Figure 14 shown, the computer device 12 is presented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0226] Bus 18 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, an Accelerated Graphics Port, a processor, or a local bus using any of the various bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnection (PCI) bus.

[0227] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and nonvolatile media, removable and non-removable media.

[0228] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / nonvolatile computer system storage media. By way of example only, storage system 34 can be used for reading and writing on non-removable, nonvolatile magnetic media ( Figure 14 not shown, typically referred to as a "hard disk drive").

[0229] Although Figure 14 not shown in the figure, a disk drive for reading and writing on a removable nonvolatile disk (such as a "floppy disk") and an optical disk drive for reading and writing on a removable nonvolatile optical disk (such as: Compact Disc Read Only Memory (CD-ROM), Digital Video Disc Read Only Memory (DVD-ROM), or other optical media) can be provided. In these cases, each drive can be connected to bus 18 through one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present disclosure.

[0230] A program / utilities 40 having a set (at least one) of program modules 42 can be stored, for example, in a memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 42 generally execute the functions and / or methods in the embodiments described in the present disclosure.

[0231] The computer device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 12, and / or communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 22. Moreover, the computer device 12 can also communicate with one or more networks (such as a Local Area Network (LAN), a Wide Area Network (WAN), and / or a public network, such as the Internet) through a network adapter 20. As shown in the figure, the network adapter 20 communicates with other modules of the computer device 12 through a bus 18. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0232] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the trajectory data processing method mentioned in the foregoing embodiments.

[0233] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0234] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

[0235] It should be noted that in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. In addition, in the description of the present disclosure, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0236] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present disclosure includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed. This should be understood by those skilled in the art to which the embodiments of the present disclosure pertain.

[0237] It should be understood that the various parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0238] Those of ordinary skill in the art of the present technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0239] In addition, the functional units in the various embodiments of the present disclosure can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0240] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc.

[0241] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0242] Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for processing trajectory data, characterized in that, the method includes: obtaining reference index information, wherein the reference index information has a corresponding index type; determining a target data table corresponding to the index type, wherein the target data table includes: a plurality of candidate index information, and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information; determining, from the plurality of candidate index information, candidate index information that matches the reference index information, and extracting a target trajectory corresponding to the matching candidate index information, the target trajectory belonging to the plurality of candidate trajectories; and performing a target operation on the target trajectory; Before obtaining the reference index information, it further includes: obtaining a plurality of initial trajectories; respectively preprocessing the plurality of initial trajectories to obtain a plurality of candidate trajectories; determining a plurality of time distribution features respectively corresponding to the plurality of candidate trajectories, and determining a plurality of spatial distribution features respectively corresponding to the plurality of candidate trajectories; determining a combined feature corresponding to the index type, the combined feature including: at least part of the time distribution features and / or at least part of the spatial distribution features; forming candidate index information corresponding to the index type according to the combined feature; generating a candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature.

2. The method according to claim 1, characterized in that, the target data table belongs to a plurality of candidate data tables, the candidate data tables including: a plurality of key-value pairs, wherein the key in the key-value pair stores the candidate index information, and the value corresponding to the key stores the candidate trajectory.

3. The method according to claim 2, characterized in that, the index type is any one of the following: time index type, spatial index type, and spatio-temporal index type.

4. The method according to claim 1, characterized in that, wherein, the at least part of the time distribution features satisfy a time similarity condition; and / or the at least part of the spatial distribution features satisfy a spatial similarity condition.

5. The method according to claim 1, characterized in that, the determining a plurality of time distribution features respectively corresponding to the plurality of candidate trajectories, and determining a plurality of spatial distribution features respectively corresponding to the plurality of candidate trajectories, includes: determining a plurality of trajectory start times respectively corresponding to the plurality of candidate trajectories; determining a plurality of trajectory end times respectively corresponding to the plurality of candidate trajectories, and using the plurality of trajectory start times and the corresponding plurality of trajectory end times as the plurality of time distribution features respectively; determining a plurality of boundary rectangle features respectively corresponding to the plurality of candidate trajectories, and using the plurality of boundary rectangle features as the plurality of spatial distribution features respectively.

6. The method according to claim 1, characterized in that, the respectively preprocessing the plurality of initial trajectories to obtain a plurality of candidate trajectories includes: respectively performing noise reduction processing on the plurality of initial trajectories to obtain the plurality of candidate trajectories; and / or Segment the initial trajectory to obtain multiple trajectory segments and use them as the multiple candidate trajectories; and / or Perform interpolation processing on the multiple initial trajectories respectively to obtain the multiple candidate trajectories; and / or Map the multiple initial trajectories to a road network map respectively to map and obtain multiple road trajectories, and use the multiple road trajectories as the multiple candidate trajectories.

7. The method according to claim 1,[[]] wherein,[[]] the number of the target trajectories is multiple, and the performing a target operation on the target trajectories includes:[[]] Performing aggregation processing on the multiple target trajectories; and / or Performing a dwell point detection process on the multiple target trajectories; and / or Performing clustering processing on the multiple target trajectories to obtain a target trajectory set, the target trajectory set including: at least part of the target trajectories, wherein, the at least part of the target trajectories are used to analyze the motion pattern of the subject to which they belong, and / or the at least part of the target trajectories are used to analyze the spatial association relationship between a first subject and a second subject, the first subject and the second subject respectively belonging to multiple subjects.

8. The method according to claim 1,[[]] wherein,[[]] the obtaining the reference index information includes:[[]] Receiving a query request, the query request being adapted to an initial query language supported by a query user-side device; Converting the query request into a target query request, the target query request supporting a first query language, the first query language being different from the initial query language; Parsing the reference index information from the target query request.

9. The method according to claim 1,[[]] wherein,[[]] the obtaining the multiple initial trajectories includes:[[]] Determining multiple data sources, the multiple data sources corresponding to multiple types and multiple data source addresses respectively; Determining multiple mapping association relationships between the multiple data sources corresponding to the multiple types respectively and the values corresponding to the keys; Generating a query statement supporting a second query language according to the type, the data source address, and the mapping association relationship; Querying the multiple initial trajectories from the corresponding multiple data sources according to the multiple query statements.

10. The method according to claim 8,[[]] wherein,[[]] after parsing the reference index information from the target query request, it further includes:[[]] Parsing a target operation type and operation parameters from the target query request; wherein, the performing a target operation on the target trajectories includes:[[]] Determining a target operation corresponding to the target operation type; Performing the target operation on the target trajectories according to the operation parameters.

11. The method according to claim 8,[[]] wherein,[[]] the first query language is a structured query language.

12. The method according to claim 9,[[]] wherein,[[]] the second query language is a structured query language.

13. A trajectory data processing device,[[]] wherein,[[]] the device includes:[[]] A first acquisition module for acquiring reference index information, wherein the reference index information has a corresponding index type; The first determination module is configured to determine a target data table corresponding to the index type, where the target data table includes: a plurality of candidate index information, and a plurality of candidate trajectories respectively corresponding to the plurality of candidate index information; The second determination module is configured to determine, from the plurality of candidate index information, candidate index information that matches the reference index information, and extract a target trajectory corresponding to the matching candidate index information, where the target trajectory belongs to the plurality of candidate trajectories; The execution module is configured to perform a target operation on the target trajectory; The second acquisition module is configured to acquire a plurality of initial trajectories before acquiring the reference index information; The preprocessing module is configured to perform preprocessing on the plurality of initial trajectories respectively to obtain a plurality of candidate trajectories; The third determination module is configured to determine a plurality of time distribution features respectively corresponding to the plurality of candidate trajectories, and determine a plurality of spatial distribution features respectively corresponding to the plurality of candidate trajectories; The fourth determination module is configured to determine a combined feature corresponding to the index type, where the combined feature includes: at least part of the time distribution features and / or at least part of the spatial distribution features; The first generation module is configured to form candidate index information corresponding to the index type according to the combined feature; The second generation module is configured to generate a candidate data table according to the candidate trajectories corresponding to the combined feature and the candidate index information corresponding to the combined feature; 14. The apparatus according to claim 13, wherein, the target data table belongs to a plurality of candidate data tables, and the candidate data table includes: a plurality of key-value pairs, where the key in the key-value pair stores the candidate index information, and the value corresponding to the key stores the candidate trajectory; 15. The apparatus according to claim 14, wherein, the index type is any one of the following: a time index type, a spatial index type, and a spatio-temporal index type; 16. The apparatus according to claim 13, wherein, wherein, the at least part of the time distribution features satisfy a time similarity condition; and / or the at least part of the spatial distribution features satisfy a spatial similarity condition; 17. The apparatus according to claim 13, wherein, the third determination module is specifically configured to: determine a plurality of trajectory start times respectively corresponding to the plurality of candidate trajectories; determine a plurality of trajectory end times respectively corresponding to the plurality of candidate trajectories, and use the plurality of trajectory start times and the corresponding plurality of trajectory end times as the plurality of time distribution features respectively; determine a plurality of boundary rectangle features respectively corresponding to the plurality of candidate trajectories, and use the plurality of boundary rectangle features as the plurality of spatial distribution features respectively; 18. The apparatus according to claim 13, wherein, the preprocessing module is specifically configured to: perform noise reduction processing on the plurality of initial trajectories respectively to obtain the plurality of candidate trajectories; and / or perform segmentation processing on the initial trajectories to obtain a plurality of trajectory segments and use them as the plurality of candidate trajectories; and / or perform interpolation processing on the plurality of initial trajectories respectively to obtain the plurality of candidate trajectories; and / or Map the multiple initial trajectories to a road network map respectively to obtain multiple road trajectories, and use the multiple road trajectories as the multiple candidate trajectories.

19. The apparatus according to claim 13, wherein, the execution module further includes: an aggregation sub-module for aggregating multiple target trajectories; a detection sub-module for detecting stationary points of multiple target trajectories; a clustering sub-module for clustering multiple target trajectories to obtain a set of target trajectories, the set of target trajectories including: at least some of the target trajectories, wherein at least some of the target trajectories are used to analyze the motion pattern of the subject to which they belong, and / or at least some of the target trajectories are used to analyze the spatial association relationship between a first subject and a second subject, the first subject and the second subject belonging to multiple subjects respectively.

20. The apparatus according to claim 13, wherein, the first acquisition module is specifically configured to: receive a query request, the query request being adapted to an initial query language supported by a query user-side device; convert the query request into a target query request, the target query request supporting a first query language, the first query language being different from the initial query language; parse the reference index information from the target query request.

21. The apparatus according to claim 13, wherein, the second acquisition module is specifically configured to: determine multiple data sources, the multiple data sources corresponding to multiple types and multiple data source addresses respectively; determine multiple mapping association relationships between the multiple data sources and the values corresponding to the keys respectively according to the multiple types; generate a query statement supporting a second query language according to the type, the data source address, and the mapping association relationship; query the multiple initial trajectories from the corresponding multiple data sources according to the multiple query statements.

22. The apparatus according to claim 20, wherein, wherein, the first acquisition module is further configured to, after parsing the reference index information from the target query request, parse a target operation type and operation parameters from the target query request; wherein the execution module is further configured to: determine a target operation corresponding to the target operation type; execute the target operation on the target trajectory according to the operation parameters.

23. The apparatus according to claim 20, wherein, the first query language is a structured query language.

24. The apparatus according to claim 21, wherein, the second query language is a structured query language.

25. A computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-12.

26. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are for causing the computer to perform the method according to any one of claims 1-12.

Images