Crowdsourcing collection and freshness maintenance system for self-updating spatial database

Abstract

The present application relates to the technical field of data updating, in particular to a crowd-sourcing collection and freshness maintenance system for self-updating spatial database. The system comprises: the present application takes the candidate update node corresponding to the maximum position matching characteristic value as the update node; calculates the track change characteristic value between the historical road track and the road track, and judges whether to update the historical road condition information based on the track change characteristic value; carries out interactive comparison processing on the update image feature and the historical image feature to obtain a building change index, and judges whether to update the historical building image information based on the building change index; updates the historical road condition information and the historical building image information in the spatial database, which can improve the updating efficiency of the data in the spatial database and reduce the updating lag.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data updating, in particular to a crowdsourcing collection and freshness maintenance system for self-updating spatial database. BACKGROUND

[0002] As the core infrastructure of digital city, intelligent transportation, environmental monitoring and location-based services, the accuracy and freshness of spatial database directly determine the service quality and reliability of upper application. Crowdsourcing data collection mode is a data collection mode that outsources data collection tasks traditionally performed by internal staff to a large, undefined group in the form of public recruitment.

[0003] Limitations of existing spatial data updating mode: on the one hand, the cost of professional collection is high, relying on professional surveying and mapping team to collect data, which is time-consuming and laborious, with high economic cost and long updating cycle, which cannot meet the real-time requirements of modern applications, on the other hand, the data updating is lagging behind, and the road condition information and building image information are not updated in time.

[0004] Therefore, it is urgent to provide a crowdsourcing collection and freshness maintenance system for self-updating spatial database to solve the above problems. SUMMARY

[0005] The purpose of the present application is to provide a crowdsourcing collection and freshness maintenance system for self-updating spatial database: to solve the technical problems of high data updating cost and high data updating lag in the existing spatial data updating mode.

[0006] The crowdsourcing collection and freshness maintenance system for self-updating spatial database comprises:

[0007] The crowdsourcing collection unit is used for collecting the uploaded data to be updated by the selected participants who have passed the legal authentication based on the crowdsourcing platform, wherein the data to be updated includes the location information of the selected participants, road condition information and building image information;

[0008] The data matching unit is used for calculating the location matching feature value of the location information of the selected participants and each candidate updating node in the spatial database, and taking the candidate updating node corresponding to the maximum location matching feature value as the updating node;

[0009] The road analysis unit is used for determining the historical road condition information of the updating node based on the road condition information and the updating node corresponding to the road condition information, respectively tracking the road trajectory of the historical road condition information and the road condition information to obtain the historical road trajectory and the road trajectory, calculating the trajectory change feature value between the historical road trajectory and the road trajectory, and judging whether to update the historical road condition information based on the trajectory change feature value;

[0010] The building analysis unit is configured to respectively extract features from the building image information and the historical building image information in the spatial database to obtain updated image features and historical image features, and to perform interactive comparison processing on the updated image features and the historical image features to obtain a building change index, and to determine whether to update the historical building image information based on the building change index.

[0011] The data updating unit is configured to update the historical road condition information and the historical building image information in the spatial database.

[0012] Further, the position matching feature value of the location information of the selected participant and each candidate update node in the spatial database specifically includes the following processes:

[0013] Based on the location information of the selected participant, the coordinates of the mobile terminal of the selected participant are obtained ;

[0014] Based on the coordinates , the azimuth of the selected participant pointing to the candidate update node is calculated using an arctangent function : The calculated azimuth is converted into degrees , wherein the coordinates of the candidate update node ;

[0015] Based on the coordinates , the distance between the selected participant and the candidate update node is calculated using the Euclidean distance formula ;

[0016] The position proximity between the location information of the selected participant and the candidate update node is calculated

[0017] The degrees corresponding to the azimuth , the distance , and the position proximity are dimensionless, and their numerical values are substituted into the position matching feature value calculation formula to calculate the position matching feature value WZT, wherein the position matching feature value calculation formula is as follows: ; wherein the value of c is , the number of candidate update nodes in the spatial database.

[0018] Further, the position matching feature value of the location information of the selected participant and each candidate update node in the spatial database specifically includes the following processes: Position proximity of the selected participant to the candidate update node Specifically, the method comprises the following processes:

[0019] Based on the location information of the selected participant, the IP address information of the selected participant, the node encoding information of the selected participant and the geographical location information of the selected participant, the CRF (Conditional Random Field) model is used to perform entity mention extraction on the IP address information, the node encoding information and the geographical location information, and the entity mention is converted into a vector matrix based on the bag-of-words model;

[0020] Calculate the vector matrix and the candidate update node Modularity vector between the corresponding node vector matrices :

[0021] ;

[0022] wherein K is the number of vectors in the vector matrix, denotes the adjacency matrix of the vector matrix and the node vector matrix, denotes the node number of the adjacency matrix, and 2P denotes the sum of all edge numbers in the adjacency matrix , denotes the degree of i, denotes the degree of j, denotes the community in which the node i exists, denotes the community in which the node j exists, is a conditional restriction coefficient, if the vector matrix and the candidate update node corresponding node vector matrices are different in node encoding length, then is 0, if the vector matrix and the candidate update node corresponding node vector matrices are the same in node encoding length, then is 1;

[0023] Modularity vector The modulus of the modularity vector is denoted as the position proximity of the selected participant to the candidate update node . .

[0024] Further, the historical road condition information of the update node is determined based on the road condition information and the update node corresponding to the road condition information, and the historical road condition information of the update node comprises the following processes:

[0025] The road condition information and the update node corresponding to the road condition information are input into a deep convolutional neural network model, and the historical road condition information of the update node is output.

[0026] Further, the historical road condition information and the road condition information are respectively subjected to road trajectory tracking to obtain the historical road trajectory and the road trajectory, which specifically includes the following processes:

[0027] Step one: based on the historical road condition information or the road condition information, a corresponding historical road route or a road route is obtained, and a set of sampling points is set For the combined parameters, the historical road route or the road route is set with the same sampling points, and each sampling point is combined according to the sampling order of the sampling interval value to obtain a plurality of combined groups;

[0028] Step two: the first sampling point and the second sampling point of each combined group are combined to form a reference vector m, and the remaining z-th sampling point and the z-1-th sampling point are combined to form a vector , wherein , the angle between is calculated , wherein the calculation formula of the angle is as follows: ;

[0029] Step three: the angle is compared with a threshold angle , if the angle of the z-th point is greater than the threshold angle , the sampling points arranged in front of the z-th sampling point are subdivided into a group, and the sampling points arranged in front of the z-th point are repeated step two and step three to complete the subdivision of the combined group, and the sampling points in each subdivided group are connected to obtain the historical road trajectory and the road trajectory.

[0030] Further, the calculation of the trajectory change characteristic value between the historical road trajectory and the road trajectory specifically includes the following processes:

[0031] The length of the trajectory segment curve that coincides with the historical road trajectory and the road trajectory is counted, and the lengths of the trajectory curves corresponding to the historical road trajectory and the road trajectory are counted respectively, the maximum trajectory curve length is determined, and the ratio between the length of the trajectory segment curve that coincides and the maximum trajectory curve length is calculated, and the ratio is recorded as the trajectory change characteristic value.

[0032] Further, the judgment of whether to update the historical road condition information based on the trajectory change characteristic value specifically includes the following processes:

[0033] The trajectory change characteristic value threshold is loaded, and it is judged whether the trajectory change characteristic value exceeds the trajectory change characteristic value threshold, if yes, it is determined that the historical road condition information needs to be updated, if not, it is determined that the historical road condition information does not need to be updated, wherein the trajectory change characteristic value threshold is set by the system and stored in the system.

[0034] Further, the feature extraction of the building image information and the historical building image information in the spatial database is carried out to obtain the updated image feature and the historical image feature, and the specific process includes the following steps:

[0035] The building image information and the historical building image information are respectively input into the Transformer encoding layer for feature extraction to obtain the updated image feature and the historical image feature , wherein, is the length of the feature, is the dimension of the feature, and R is the real number set.

[0036] Further, the updated image feature and the historical image feature are interactively compared to obtain the building change index, and the specific process includes the following steps:

[0037] Based on , a graph structure is generated , wherein V is a node set representing the target building feature information in the updated image feature, the node set , is the number of nodes, E is an edge set representing the target building feature information in the historical image feature, , the number of edges is A, wherein two adjacent nodes constitute an edge ;

[0038] The edge centrality is defined as the average value of the centrality scores of two adjacent nodes as follows:

[0039] ;

[0040] , wherein, is the centrality of the edge , which is used to represent the importance influence between two connected nodes, represents the node centrality measure;

[0041] According to the centrality of each edge, the probability of each edge is calculated: set to reduce the influence of dense nodes, and after normalization processing, the interaction probability of the two is calculated:

[0042] ;

[0043] , wherein, is a hyperparameter, which is used to control the overall probability of interaction; is the maximum value of , is an average value of the probability, a maximum value for limiting the probability;

[0044] calculating a building change index: wherein the greater the interaction probability, the more similar the updated image feature and the historical image feature prove to be, and the smaller the change in the building.

[0045] Further, judging whether to update the historical building image information based on the building change index specifically includes the following process:

[0046] loading a building change index threshold, judging whether the building change index exceeds the building change index threshold, if yes, determining that the historical building image information needs to be updated, and if no, determining that the historical building image information does not need to be updated, wherein the building change index threshold is set by the system and stored in the system.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] On the one hand, the present application calculates accurate position matching feature values through the data matching unit, can intelligently and automatically accurately associate the crowd-sourced data with the most relevant candidate update nodes in the database, avoids data mismatch from the source, ensures the correctness of the subsequent analysis processing object, greatly reduces the cost of manual review and error correction, and improves the update efficiency and accuracy.

[0049] On the other hand, the road analysis unit can sensitively capture substantial changes in road topology and direction (such as new road opening, one-way adjustment, road closure, etc.) by comparing real-time road trajectories with historical trajectories and calculating trajectory change feature values; the building analysis unit can effectively identify complex changes such as building construction, demolition, and facade reconstruction by generating a building change index through deep feature extraction and interaction comparison, and based on the freshness judgment mechanism of multi-dimensional feature analysis, the system can accurately identify which building information needs to be updated, greatly improving the purpose and value density of the update.

[0050] Finally, updating the spatial database based on the crowd-sourcing platform can reduce the cost and lag of data updating. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0052] Figure 1is a system block diagram of a crowd-sourcing collection and freshness maintenance system of a self-updating spatial database according to an embodiment of the present application;

[0053] Figure 2 is a workflow diagram of a crowd-sourcing collection and freshness maintenance system of a self-updating spatial database according to an embodiment of the present application;

[0054] Figure 3 is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0056] In addition, the described features, structures, or characteristics can be combined in any suitable way in one or more example embodiments. In the following description, numerous specific details are provided to give a thorough understanding of example embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the techniques disclosed can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.

[0057] The present embodiment provides a crowd-sourcing collection and freshness maintenance system of a self-updating spatial database, Figure 1 is a system block diagram of a crowd-sourcing collection and freshness maintenance system of a self-updating spatial database according to an embodiment of the present application, as Figure 1 shown, the system comprises:

[0058] The crowd-sourcing collection unit is configured to collect the to-be-updated data uploaded by the selected participants who have passed the legal authentication based on the crowd-sourcing platform, wherein the to-be-updated data comprises the location information, the road condition information and the building image information of the selected participants;

[0059] It is worth noting that the selected participants who have passed the legal authentication can upload the to-be-updated data to the crowd-sourcing platform through a mobile terminal or a computer terminal, wherein the crowd-sourcing platform is a digital intermediary or an online market, which decomposes, distributes and outsources the tasks or projects of an organization (the party giving the order) to a large, undefined network group (contributors or "the public") to complete through an open call form, and coordinates the work, management and payment of rewards.

[0060] The data matching unit is configured to calculate a position matching feature value of the position information of the selected participant and each candidate update node in the spatial database, and take the candidate update node corresponding to the maximum position matching feature value as the update node.

[0061] The road analysis unit is configured to determine historical road condition information of the update node based on the road condition information and the update node corresponding to the road condition information, perform road track tracking on the historical road condition information and the road condition information respectively to obtain a historical road track and a road track, calculate a track change feature value between the historical road track and the road track, and determine whether to update the historical road condition information based on the track change feature value.

[0062] The building analysis unit is configured to perform feature extraction on the building image information and historical building image information in the spatial database respectively to obtain update image features and historical image features, perform interactive comparison processing on the update image features and the historical image features to obtain a building change index, and determine whether to update the historical building image information based on the building change index.

[0063] The data updating unit is configured to update the historical road condition information and the historical building image information in the spatial database.

[0064] In summary, the data matching unit can intelligently and automatically accurately associate the crowd-sourced data with the most relevant candidate update node in the database by calculating accurate position matching feature values, thereby avoiding data mismatch from the source, ensuring the correctness of the subsequent analysis processing object, greatly reducing the cost of manual review and error correction, and improving the update efficiency and accuracy. The road analysis unit can sensitively capture substantial changes in road topology and direction (such as new road opening, one-way adjustment, road closure, etc.) by comparing real-time road tracks with historical tracks and calculating track change feature values. The building analysis unit can effectively identify complex changes such as building construction, demolition, and facade reconstruction by generating a building change index through deep feature extraction and interactive comparison. Based on the freshness judgment mechanism of multi-dimensional feature analysis, the system can accurately identify which building information needs to be updated, greatly improving the purpose and value density of the update. Based on the crowd-sourcing platform, the data updating of the spatial database can reduce the data updating cost and data updating lag.

[0065] In some embodiments, the calculation of the position matching feature value of the position information of the selected participant and each candidate update node in the spatial database specifically includes the following processes:

[0066] The coordinate of the mobile terminal of the selected participant is obtained based on the position information of the selected participant.

[0067] ​Among them, the location information of the selected participants is collected through the positioning system, and the coordinates of the selected participants' mobile devices are obtained;

[0068] Based on coordinates Use the arctangent function to calculate the selected participant's pointer to the candidate update node. azimuth : The calculated azimuth angle Convert to degrees Among them, candidate update nodes coordinates It is worth noting that, within a specific range, the selected participant points to the candidate update node. azimuth The larger the value, the more likely it is that the selected participants and the candidate update nodes are... The closer the distance, the higher the match.

[0069] Based on coordinates The selected participants and candidate update nodes are calculated using the Euclidean distance formula. distance : It is worth noting that the selection of participants and candidate update nodes... distance The larger the value, the more likely it is that the selected participants and the candidate update nodes are... The greater the distance, the lower the match rate;

[0070] Calculate the location information of the selected participant and the candidate update node. proximity ;

[0071] Specifically, based on the selected participants' location information, IP address information, node encoding information, and geographical location information, the CRF model is used to extract entity references from the IP address information, node encoding information, and geographical location information. The entity references are then transformed into vector matrices based on the bag-of-words model. The Conditional Random Field (CRF) model is a statistical modeling method that is very suitable for sequence labeling tasks. It can well consider contextual features and determine which words in the text belong to specific entity references.

[0072] The bag-of-words model converts entity mentions into a matrix of vectors, and builds a vocabulary: collect all extracted entity values (such as all different IP, node ID, place names) to form a vocabulary, each word corresponds to a unique index. Generate vectors: for a data sample (such as a log record), create a vector according to the entity it contains. The length of the vector is equal to the size of the vocabulary. If a certain word appears in the sample, set the corresponding index position of the vector to 1 (or the number of occurrences), otherwise set it to 0. Form a matrix: stack all sample vectors to form a huge, sparse vector matrix. Each row represents a sample, and each column represents an entity word.

[0073] Computing vector matrix and candidate update node Modularity vector between corresponding node vector matrices

[0074]

[0075] where K is the number of vectors in the vector matrix, denotes the adjacency matrix of the vector matrix and the node vector matrix, denotes the node number of the adjacency matrix, and 2P denotes the sum of all edges in the adjacency matrix , denotes the degree of i, denotes the degree of j, denotes the community in which node i exists, denotes the community in which node j exists, is a conditional restriction coefficient, if the vector matrix and the candidate update node corresponding node vector matrix have different node encoding lengths, then is 0, if the vector matrix and the candidate update node corresponding node vector matrix have the same node encoding length, then is 1.

[0076] Modularity vector The modulus of is the proximity of the location information of the selected participant to the location of the candidate update node .

[0077] Further, the azimuth corresponding degree , distance and location proximity are de-dimensioned to obtain their numerical values, which are substituted into the position matching characteristic value calculation formula to calculate the position matching characteristic value WZT. The position matching characteristic value calculation formula is: ; wherein the value of c is ,​​​​ This represents the number of candidate update nodes in the spatial database.

[0078] In some embodiments, determining the historical road condition information of an update node based on road condition information and the corresponding update node specifically includes the following process:

[0079] The road condition information and the corresponding update nodes are input into a deep convolutional neural network model, which outputs the historical road condition information of the update nodes.

[0080] The training process of a deep convolutional neural network model is as follows:

[0081] A deep convolutional neural network model consists of several cells, and each cell contains N nodes. This represents the node parameters for each cell. Represents a node. Values ;

[0082] Obtain the historical road condition information of all candidate roads for the update node. Each different road in the update node corresponds to a specific historical road condition information. Combine all candidate historical road condition information into a dataset X. Training a deep convolutional neural network model is equivalent to determining the computational operations for each neural network. The process:

[0083] make Between nodes i and j, by A parameterized probability distribution of a neural network operation. This represents a joint distribution, where each cell consists of N operations, given a dataset X and a set of candidate operations. Calculate an operation distribution conditional entropy :

[0084] ;

[0085] in, Let X be the probability distribution of the dataset. It is a set of neural network operations;

[0086] Conditional entropy of all operations in the entire neural network cell for:

[0087] ;

[0088] Calculating the log-likelihood function based on conditional entropy :

[0089] ;

[0090] wherein, is a discrete feature indicator function, if is less than a preset threshold value, then is 1, otherwise, is 0, is the Euclidean distance between node i and node j;

[0091] wherein, ;

[0092] By solving the maximum , the maximum entropy constraint condition is added to update .

[0093] In some embodiments, the road trajectory tracking is respectively performed on the historical road condition information and the road condition information to obtain the historical road trajectory and the road trajectory, which specifically includes the following processes:

[0094] Step one: based on the historical road condition information or the road condition information, the corresponding historical road route or road route is obtained, and is set as a combination parameter, the historical road route or the road route is set with the same sampling points, and each sampling point is combined according to the sampling order of the sampling interval value to obtain a plurality of combination groups;

[0095] Step two: the first sampling point and the second sampling point of each combination group are combined to form a reference vector m, and the remaining z-th sampling point and the z-1-th sampling point are combined to form a vector , wherein, , the angle between and m is calculated, wherein the calculation formula of the angle is as follows: ;

[0096] Step three: the is compared with a threshold angle , if the of the z-th point is greater than the threshold angle , the sampling points arranged in front of the z-th sampling point are subdivided into a group, the sampling points arranged in front of the z-th point are repeated step two and step three to complete the subdivision of the combination group, and the sampling points in each subdivided group are connected to obtain the historical road trajectory and the road trajectory.

[0097] In some embodiments, Figure 2 is a workflow diagram of a crowdsourcing collection and freshness maintenance system of a self-updating spatial database according to an embodiment of the present application, as shown in Figure 2As shown, the steps of calculating the trajectory change feature value between the historical road trajectory and the road trajectory specifically include the following steps:

[0098] Step one, count the trajectory segment curve length of the historical road trajectory and the road trajectory, and count the corresponding trajectory curve length of the historical road trajectory and the road trajectory respectively;

[0099] Step two, determine the maximum trajectory curve length of the two;

[0100] Step three, calculate the ratio between the trajectory segment curve length and the maximum trajectory curve length, and record the ratio as the trajectory change feature value.

[0101] In some embodiments, the process of determining whether to update the historical road condition information based on the trajectory change feature value specifically includes the following process:

[0102] Load the trajectory change feature value threshold, determine whether the trajectory change feature value exceeds the trajectory change feature value threshold, if yes, determine that the historical road condition information needs to be updated, if no, determine that the historical road condition information does not need to be updated, wherein the trajectory change feature value threshold is set by the system and stored in the system. As an optional embodiment, the setting process of the trajectory change feature value threshold is as follows: in the early stage of system operation, a large number of trajectory change feature values under the scene of "no need to update" (i.e. the feature value change caused by normal factors such as GPS error, different driving lanes, etc. when the road does not change substantially) are collected, and the statistical quantities are calculated: the mean value of the trajectory change feature value calculated from this batch of historical data: the central tendency of normal fluctuations. Standard deviation: the degree of dispersion of normal fluctuations. Set threshold: a common and effective method is to use the mean value plus several times the standard deviation.

[0103] In some embodiments, the process of extracting features from the building image information and the historical building image information in the spatial database to obtain the update image feature and the historical image feature specifically includes the following process:

[0104] The building image information and the historical building image information are respectively input into the Transformer encoding layer for feature extraction, and the update image feature and the historical image feature are respectively obtained, wherein, is the length of the feature respectively, is the dimension of the feature, and R is the real number set.

[0105] Further, the process of interactive comparison of the update image feature and the historical image feature to obtain the building change index specifically includes the following process:

[0106] Based on generate a graph structure wherein V is a node set representing target building feature information in the updated image feature, the node set V = {v1, v2, v3,..., vn}, n is the number of nodes, E is an edge set representing target building feature information in the historical image feature, the edge set E = {e1, e2, e3,..., eA}, A is the number of edges, wherein two adjacent nodes vi and vj form an edge ej, and the edge center is defined as the average of the center scores of the two adjacent nodes as follows: , wherein n is the number of nodes, A is the number of edges, and the edge center is defined as the average of the center scores of the two adjacent nodes as follows: ;

[0107] wherein the edge center is defined as the average of the center scores of the two adjacent nodes as follows:

[0108] ; wherein the edge center is defined as the average of the center scores of the two adjacent nodes as follows:

[0109] The probability of each edge is calculated according to the center of each edge: set to reduce the influence of dense nodes, and after normalization, the interaction probability of the two is calculated as follows:

[0110] ;

[0111] wherein a is a hyperparameter, which aims to control the overall probability of interaction; is the maximum value of a, is the average value of a, and a is used to limit the maximum value of the probability; , which is used to limit the maximum value of the probability;

[0112] The building change index is calculated as follows: ; wherein the greater the interaction probability, the more similar the updated image feature and the historical image feature, and the smaller the change of the building.

[0113] In some embodiments, determining whether to update the historical building image information based on the building change index specifically includes the following process:

[0114] loading a building change index threshold, determining whether the building change index exceeds the building change index threshold, if yes, determining that the historical building image information needs to be updated, and if no, determining that the historical building image information does not need to be updated, wherein the building change index threshold is set by the system and stored in the system. Wherein the building change index threshold refers to the setting process of the trajectory change feature value threshold.

[0115] ​​​​​​​​​​In some embodiments, updating the historical road condition information and the historical building image information in the spatial database comprises replacing the to-be-updated data uploaded by the selected participant with the spatial data corresponding to the node in the spatial database.

[0116] The above formulas are all dimensionless values calculated, and the preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0117] The embodiment also provides an electronic device, Figure 3 is a structural block diagram of an electronic device according to an embodiment of the present application, as Figure 3 As shown in the figure, the electronic device comprises a memory 301 and a processor 302, the memory 301 stores a computer program; the computer program is executed by the processor 302, so that the processor 302 executes the update process of the crowd-sourcing collection and freshness maintenance system of the self-updating spatial database according to any one of the above embodiments.

[0118] The memory 301 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 301 has a storage space 303 for program codes 313 for executing any method steps in the above method. For example, the storage space 303 for program codes can include respective program codes 313 for implementing various steps in the above method. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program codes can be compressed in an appropriate form, for example. These codes, when executed by a computing processing device, cause the computing processing device to perform various steps in the above-described method. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program codes can be compressed in an appropriate form, for example. These codes, when executed by a computing processing device, cause the computing processing device to perform various steps in the above-described update process of the crowd-sourcing collection and freshness maintenance system of the self-updating spatial database.

[0119] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0120] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0122] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0124] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A crowd-sourced collection and freshness maintenance system for a self-updating spatial database, characterized in that, The system comprises: A crowdsourcing collection unit configured to collect data to be updated uploaded by selected participants who have passed legal authentication based on a crowdsourcing platform, wherein the data to be updated comprises location information of the selected participants, road condition information, and building image information; A data matching unit configured to calculate a location matching feature value of the location information of the selected participants and each candidate update node in a spatial database, and take the candidate update node corresponding to the maximum location matching feature value as an update node; wherein the calculation of the location matching feature value of the location information of the selected participants and each candidate update node in the spatial database comprises the following process: acquiring coordinates of the mobile terminal of the selected participant based on location information of the selected participant ; Based on coordinates Calculating the azimuth of the selected participant to the candidate update node using an arctangent function : Converting the calculated azimuth to degrees where the coordinates of the candidate update node ;​​​ Based on coordinates Using the Euclidean distance formula to calculate the distance of the selected participant and the candidate update node : ;​ computing a proximity of a location information of a selected participant to a location of a candidate update node ;​ azimuth angle corresponding degrees , distance and location proximity , and the location matching characteristic value WZT is calculated by substituting the value of the dimensionless quantity into the location matching characteristic value calculation formula, and the location matching characteristic value calculation formula is: ; wherein the value of c is , the number of to-be-selected update nodes in the spatial database; computing a proximity of the location information of the selected participant to the location of the candidate update node and specifically includes the following processes:​ Based on the location information of the selected participants, the IP address information of the selected participants, the node coding information of the selected participants, and the geographic location information of the selected participants, a CRF model is used to perform entity reference extraction on the IP address information, the node coding information, and the geographic location information, and the entity reference is converted into a vector matrix based on a bag-of-words model; Computing vector matrix and candidate update nodes Modularity vector between corresponding node vector matrices : ； wherein, is the number of vectors in the vector matrix, denotes the adjacency matrix of the vector matrix and the node vector matrix, denotes the node number of the adjacency matrix, denotes the adjacency matrix the sum of all edges in the matrix, denotes the degree of denotes the degree of denotes the community in which the node exists, denotes the community in which the node exists, is the conditional restriction coefficient, if the node coding length of the corresponding node vector matrix of the vector matrix and the candidate updating node are not the same, then is 0, if the node coding length of the corresponding node vector matrix of the vector matrix and the candidate updating node are the same, then is 1;​​ Modularity vector The modulus value of the modularity vector is recorded as the proximity of the location information of the selected participant to the location of the candidate update node ;​ A road analysis unit configured to determine historical road condition information of the update node based on the road condition information and the update node corresponding to the road condition information, perform road trajectory tracking on the historical road condition information and the road condition information respectively, obtain historical road trajectory and road trajectory, calculate a trajectory change feature value between the historical road trajectory and the road trajectory, and determine whether to update the historical road condition information based on the trajectory change feature value; Wherein, the road trajectory tracking on the historical road condition information and the road condition information respectively, obtaining the historical road trajectory and the road trajectory, comprises the following process: Step one: based on historical road condition information or road condition information, set corresponding historical road route or road route For combined parameters, the same sampling points are set for the historical road route or road route, and each sampling point is combined according to the sampling order of the sampling interval value to obtain a plurality of combination groups; Step 2: Combine the first and second sampling points of each combination group to form a reference vector. , and the remaining first The sampling point and the first A vector is formed from each sampling point. ,in, Calculate separately and Angle between Among them, angle The calculation formula is as follows: ; Step 3: Put With threshold angle Compare, if the first points greater than the threshold angle Then it will be arranged in the th order. The sampling points preceding the first sampling point are subdivided into groups, and the points arranged in the order of the first sampling point are... Repeat steps two and three to subdivide the combined group, and connect the sampling points in each subdivided group to obtain the historical road trajectory and the road trajectory. A building analysis unit configured to perform feature extraction on the building image information and historical building image information in the spatial database respectively, obtain update image features and historical image features, perform interactive comparison processing on the update image features and the historical image features, obtain a building change index, and determine whether to update the historical building image information based on the building change index; The interactive comparison processing on the update image features and the historical image features to obtain the building change index comprises the following process: Based on And Generate graph structure Wherein, For updating the node set representing the target building feature information in the image feature, the node set , The number of nodes is For the edge set representing the target building feature information in the historical image feature, The number of edges is Wherein, two adjacent nodes Form an edge ; The edge centrality is defined as the average of the centrality scores of two adjacent nodes as follows: ; wherein, is the edge betweenness centrality, which measures the influence of a node on the communication between two other nodes, denotes the node centrality measure; According to the centrality of each edge, the probability of each edge is calculated: set to mitigate the impact of dense nodes, after normalization, the interaction probability of the two is calculated : ； wherein, is a hyperparameter, whose purpose is to control the overall probability of interaction; is the maximum value of , is the average value of , is used to limit the maximum value of the probability; Computing a building change index: ; wherein the greater the interaction probability, the more similar the updated image features and the historical image features prove to be, the less change in the building. A data update unit configured to update the historical road condition information and the historical building image information in the spatial database.

2. The crowd-sourced collection and freshness maintenance system of a self-updating spatial database of claim 1, wherein, The determination of the historical road condition information of the update node based on the road condition information and the update node corresponding to the road condition information comprises the following process: The road condition information and the update node corresponding to the road condition information are input into a deep convolutional neural network model, and the historical road condition information of the update node is output. The calculation of the trajectory change feature value between the historical road trajectory and the road trajectory comprises the following process:

3. The crowd-sourced collection and freshness maintenance system of a self-updating spatial database of claim 1, wherein, The length of the trajectory segment curve that coincides between the historical road trajectory and the road trajectory is counted, and the lengths of the trajectory curves corresponding to the historical road trajectory and the road trajectory are counted respectively, the maximum trajectory curve length is determined, and the ratio between the length of the trajectory segment curve that coincides and the maximum trajectory curve length is calculated as the trajectory change feature value. ​ 4. The crowd-sourced collection and freshness maintenance system of a self-updating spatial database of claim 1, wherein, The judging whether to update the historical road condition information based on the trajectory change characteristic value specifically includes the following processes: loading the trajectory change characteristic value threshold, judging whether the trajectory change characteristic value exceeds the trajectory change characteristic value threshold, if yes, determining that the historical road condition information needs to be updated, if no, determining that the historical road condition information does not need to be updated, wherein the trajectory change characteristic value threshold is set by the system and stored in the system.

5. The crowd-sourced collection and freshness maintenance system of a self-updating spatial database of claim 1, wherein, The feature extraction is performed on the building image information and the historical building image information in the spatial database to obtain updated image features and historical image features, which specifically includes the following processes: The judging whether to update the historical building image information based on the building change index specifically includes the following processes: The building image information and the historical building image information are respectively input into a Transformer encoding layer for feature extraction, to obtain updated image features and historical image features wherein, is a length of the features, respectively, is a dimension of the features, is a set of real numbers.

6. The crowd-sourced collection and freshness maintenance system of a self-updating spatial database of claim 1, wherein, loading the building change index threshold, judging whether the building change index exceeds the building change index threshold, if yes, determining that the historical building image information needs to be updated, if no, determining that the historical building image information does not need to be updated, wherein the building change index threshold is set by the system and stored in the system. ​

Images