Spatial text site selection method and device, equipment, storage medium and program product

Abstract

The invention relates to a spatial text site selection method and device, equipment, a storage medium and a program product, and particularly relates to the technical field of spatial big data. Comprising the steps that a road index grid of a geographic area is constructed, and each grid unit of the road index grid comprises position information and attribute information of all object points in a corresponding geographic sub-area; wherein the object points comprise facility points and user points; calculating spatial text correlation parameters between the user point and different facility points based on the road index grid; determining facility points to be selected from different facility points according to the spatial text correlation parameters; calculating competitiveness scores of the facility points to be selected based on a competition scoring model; and selecting a target facility point from the facility points to be selected according to the competitiveness score. According to the method, competition between similar facilities is considered, and the accuracy and effectiveness of space text site selection can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of terminals, and particularly to a method, device, equipment, storage medium and program product for spatial text site selection. Background Art

[0002] Spatial text site selection is a process of combining geospatial information and text description information to determine a suitable location. It involves comprehensive analysis of geospatial areas (such as regions on a map, city blocks, etc.) and related text data (such as user reviews, land use descriptions, policy and regulation texts, etc.) to find a site selection location that meets specific requirements.

[0003] Currently, there are mainly two text site selection methods: preference-based spatial text location recommendation and spatial text location recommendation with time attributes added. However, competition is prevalent in the market economy, and existing spatial text location recommendation models only consider the influence of the facility itself, while ignoring the competitive ability of other similar facilities. The selected address lacks competitiveness and is not the most suitable site selection location. Summary of the Invention

[0004] To solve the above technical problems or at least partially solve the above technical problems, the present application provides a method, device, equipment, storage medium and program product for spatial text site selection, which can improve the accuracy and effectiveness of spatial text site selection considering the competition among similar facilities.

[0005] To achieve the above object, the technical solutions provided by the embodiments of the present application are as follows:

[0006] In a first aspect, the present application provides a method for spatial text site selection, including: constructing a road index grid for a geographical area, where each grid unit of the road index grid includes the position information and attribute information of all object points in the corresponding geographical sub-region; wherein, the object points include facility points and user points; calculating a spatial text correlation parameter between a user point and different facility points based on the road index grid; determining candidate facility points from different facility points according to the spatial text correlation parameter; calculating a competitiveness score of the candidate facility points based on a competition scoring model; and selecting a target facility point from the candidate facility points according to the competitiveness score.

[0007] As an optional implementation manner of an embodiment of the present application, the attribute information includes text description information. Based on the road index grid, calculate the spatial text correlation parameter between the user point and different facility points, including: calculating the spatial similarity parameter between the user point and different facility points according to the location information of the user point and the location information of different facility points; calculating the text similarity parameter between the user point and different facility points according to the text description information of the user point and the text description information of different facility points; calculating the spatial text correlation parameter according to the spatial similarity parameter and the text similarity parameter.

[0008] As an optional implementation manner of an embodiment of the present application, according to the spatial text correlation parameter, determine the candidate facility points from different facility points, including: determining whether the spatial text correlation parameter is greater than the expected influence threshold; if so, using the facility points with the spatial text correlation parameter greater than the expected influence threshold as the candidate facility points.

[0009] As an optional implementation manner of an embodiment of the present application, the attribute information includes user ratings. After determining the candidate facility points from different facility points according to the spatial text correlation parameter, it further includes: performing normalization processing on the user ratings of the candidate facility points to obtain the competition weights.

[0010] As an optional implementation manner of an embodiment of the present application, calculate the competitiveness score of the candidate facility points based on the competition scoring model, including: substituting the competition weights into the competition scoring model to calculate the competitiveness score of the candidate facility points.

[0011] As an optional implementation manner of an embodiment of the present application, according to the competitiveness score, select the target facility point from the candidate facility points, including: calculating the actual road network distance between the candidate facility points and the user point according to the road index grid; calculating the influence score of the candidate facility points according to the competitiveness score and the actual road network distance; selecting the target facility point from the candidate facility points according to the influence score.

[0012] In a second aspect, the present application provides a spatial text location device, which includes:

[0013] A construction module for constructing a road index grid of a geographical area, and each grid unit includes the location information and attribute information of all object points in the corresponding geographical sub-area; wherein, the object points include facility points and user points;

[0014] A spatial text correlation calculation module for calculating the spatial text correlation parameter between the user point and different facility points based on the road index grid;

[0015] A determination module for determining candidate facility points from different facility points according to the spatial text correlation parameter;

[0016] A competitiveness calculation module for calculating the competitiveness score of candidate facility points based on a competition scoring model;

[0017] A selection module for selecting target facility points from the candidate facility points according to the competitiveness scores.

[0018] As an optional implementation manner of an embodiment of the present application, the attribute information includes text description information. The spatial text relevance calculation module is specifically used for: calculating the spatial similarity parameter between the user point and different facility points according to the location information of the user point and the location information of different facility points; calculating the text similarity parameter between the user point and different facility points according to the text description information of the user point and the text description information of different facility points; calculating the spatial text relevance parameter according to the spatial similarity parameter and the text similarity parameter.

[0019] As an optional implementation manner of an embodiment of the present application, the determination module is specifically used for: determining whether the spatial text relevance parameter is greater than the expected influence threshold; if so, using the facility points whose spatial text relevance parameter is greater than the expected influence threshold as candidate facility points.

[0020] As an optional implementation manner of an embodiment of the present application, the attribute information includes user ratings. The competitiveness calculation module is further used for: performing normalization processing on the user ratings of the candidate facility points to obtain competition weights.

[0021] As an optional implementation manner of an embodiment of the present application, the competitiveness calculation module is specifically used for: substituting the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

[0022] As an optional implementation manner of an embodiment of the present application, the selection module is specifically used for: calculating the actual road network distance between the candidate facility points and the user point according to the road index grid; calculating the influence score of the candidate facility points according to the competitiveness scores and the actual road network distance; selecting target facility points from the candidate facility points according to the influence scores.

[0023] In a third aspect, the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the spatial text location method as described in the first aspect or any one of its optional implementation manners.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, including: a computer program stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the spatial text location method as described in the first aspect or any one of its optional implementation manners.

[0025] Fifth aspect, the present application provides a computer program product, including: the computer program product includes a computer program, when the computer program runs on a computer, it enables the computer to implement the spatial text location method as described in the first aspect or any of its alternative embodiments.

[0026] The technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art:

[0027] The embodiments of the present disclosure provide a spatial text location method, device, equipment, storage medium and program product. The method first constructs a road index grid for a geographical area. Each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-area. The object points include facility points and user points. Then, based on the road index grid, the spatial text correlation parameters between user points and different facility points are calculated to determine candidate facility points from different facility points according to the spatial text correlation parameters. Then, the competitiveness scores of the candidate facility points are calculated based on a competition scoring model, and thus the target facility point is selected according to the competitiveness scores of the candidate facility points as the final location address. In this way, by constructing a road index grid for the geographical area, covering the location information and attribute information of all object points in the entire geographical area, and then calculating the control text similarity parameters based on this information to measure the influence of each facility point on the user point, some facility points are screened out. To select a more suitable target facility point, the competitiveness scores of these facility points are quantified based on a competition scoring model, and selection is made according to these competitiveness scores, improving the accuracy and effectiveness of spatial text location. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0029] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0030] Figure 1 It is a flowchart showing a spatial text location method provided by an embodiment of the present application;

[0031] Figure 2 It is a schematic diagram of a road index grid provided by an embodiment of the present application;

[0032] Figure 3 It is a schematic diagram of a TaR-tree provided by an embodiment of the present application;

[0033] Figure 4 A structural schematic diagram of a spatial text location selection device provided by an embodiment of the present application;

[0034] Figure 5 A structural schematic diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0035] In order to be able to more clearly understand the above objects, features, and advantages of the present application, the solutions of the present application will be further described below. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

[0036] Many specific details are set forth in the following description in order to fully understand the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present application, rather than all of the embodiments.

[0037] To solve some or all of the technical problems existing in the related art, an embodiment of the present application provides a spatial text location selection method, device, equipment, storage medium, and program product. The method first constructs a road index grid of a geographical area. Each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-area. The object points include facility points and user points. Then, based on the road index grid, the spatial text correlation parameter between the user point and different facility points is calculated, so as to determine the candidate facility points from different facility points according to the spatial text correlation parameter. Then, the competitiveness score of the candidate facility points is calculated based on the competition scoring model, and thus the target facility point is selected according to the competitiveness score of the candidate facility points as the final location selection address. In this way, by constructing a road index grid of a geographical area, covering the location information and attribute information of all object points in the entire geographical area, and then calculating the control text similarity parameter based on this information to measure the influence of each facility point on the user point, so as to screen out some facility points. To select a more suitable target facility point, the competitiveness score of this part of the facility points is quantified based on the competition scoring model, and selection is made according to these competitiveness scores, improving the accuracy and effectiveness of spatial text location selection.

[0038] A spatial text location method provided in an embodiment of the present application can be implemented by a spatial text location device or an electronic device. The electronic device includes but is not limited to a personal computer, a laptop computer, a tablet computer, a smart phone, etc. The operating system of the electronic device can include Android, iOS developed by Apple Inc., Windows developed by Microsoft Corporation in the United States, etc. The embodiments of the present application do not limit this. The electronic device can run alone to implement the present application, or can be connected to a network and implement the present application through interactive operations with other computer devices in the network. Among them, the network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a Virtual Private Network (VPN) network, etc.

[0039] It should be noted that the protection scope of a spatial text location method described in an embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding or subtracting steps of the prior art and replacing steps according to the principle of the present application is included in the protection scope of the present application.

[0040] As Figure 1 shown, Figure 1 is a schematic flowchart of a spatial text location method according to an embodiment of the present application. This method can be executed by a spatial text location device, where the device can be implemented by software and / or hardware and is generally integrated in. This method mainly includes the following steps S101 to S105:

[0041] S101. Construct a road index grid for a geographical area.

[0042] Among them, each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-area.

[0043] In some embodiments, during the process of constructing a road index grid for a geographical area, the geographical area is divided into one geographical sub-area after another. Each geographical sub-area is correspondingly provided with a grid unit, and there are roads and object points in each geographical sub-area. The object points include facility points and user points, and each grid unit includes the location information and attribute information of all object points in the corresponding geographical sub-area.

[0044] The geographical area can be an urban area, etc. The present application does not make specific limitations on the location, size, etc. of the geographical area. Optionally, the geographical area is divided according to a preset distance, so that each grid unit has a side length equal to the preset distance. Achieving a reasonable division of the geographical area is beneficial to the construction of the road index grid.

[0045] The facility points may include merchants, restaurants, hotels, vehicles, etc. The location information of the object points may be longitude and latitude coordinates. The attribute information includes text description information, user ratings, etc.

[0046] Exemplarily, as Figure 2 shown, Figure 2 FIG. is a schematic diagram of a road index grid provided by an embodiment of the present application. The illustrated circular area is a geographical area, including criss-crossing roads and multiple object points. The object points include user points and facility points. The geographical area is divided into one geographical sub-area after another, in a grid pattern. Each geographical sub-area corresponds to a grid cell, and each grid cell includes the location and attribute information of the object points in the corresponding geographical sub-area.

[0047] In some embodiments, a tree index structure is correspondingly constructed for each grid cell. The tree index structure is used to organize the location information and attribute information of all object points. Exemplarily, the grid cell organizes the location information and attribute information of all object points based on TaR-tree.

[0048] The TaR-tree structure includes leaf nodes and non-leaf nodes. Each leaf node (nodeLeaf) contains an object point entry <nodeLeaf.MBR, nodeLeaf.text>. Among them, nodeLeaf.MBR represents the location information of the object point, usually the Minimum Bounding Rectangle of the object point; the attribute information of nodeLeaf.text, usually the text description information. Each non-leaf node contains a parent leaf entry <parentLeaf.MBR, parentLeaf.text>. parentLeaf.MBR represents the location information of all child nodes. The minimum bounding rectangle of the parent leaf node contains the minimum bounding rectangles of all child nodes. parentLeaf.text represents the location information of all child nodes, and parentLeaf.text = ∪ nodeLeft∈parentLeaf nodeLeft.text.

[0049] In addition to spatial partitioning, TaR-tree also incorporates aggregated information in the time dimension. In each node (including leaf nodes and non-leaf nodes), data related to time is recorded, such as the range of time intervals, the distribution of timestamps, etc. In this way, it can effectively handle time-based queries.

[0050] For ease of understanding the relationship between leaf nodes and non-leaf nodes, refer to Figure 3 shown, Figure 3 FIG. is a schematic diagram of TaR-tree provided by an embodiment of the present application. In TaR-tree, the leaf nodes include R1 to R8, and the non-leaf nodes include R9 to R14 Each leaf node contains corresponding text description information. R1 corresponds to "tea", R2 corresponds to "barbecue", R3 corresponds to "milk", R4 corresponds to "wine", R5 corresponds to "coffee", R6 corresponds to "sandwich", R7 corresponds to "sushi", and R8 corresponds to "chicken". At the same time, each leaf node also includes corresponding location information, which is not shown in the figure. Taking the non-leaf node R9 as an example, the text description information corresponding to the non-leaf node R9 is "tea" and "barbecue", aggregating the text description information of the leaf nodes R1 and R2.

[0051] The above embodiments combine the grid index with the tree index, which complement each other, give full play to their respective advantages, and improve the site selection efficiency.

[0052] S102. Calculate the spatial text correlation parameters between different facility points and the user point based on the road index grid.

[0053] In some embodiments, step S102 includes the following steps S1021 to S1023:

[0054] S1021. Calculate the spatial correlation parameters between the user point and different facility points according to the location information of the user point and the location information of different facility points.

[0055] Optionally, calculate the spatial correlation parameter between the user point and any facility point according to the following formula (1):

[0056]

[0057] In formula (1), S(u, o) represents the spatial correlation parameter between the user point u and the facility point o, u.loc represents the location information of the user point u, o.loc represents the location information of the facility point o; d(u.loc, o.loc) represents the Euclidean distance between the user point u and the facility point o; D max is the maximum distance between two points in the space where the user point and the facility point are located. The location information can be represented by longitude and latitude coordinates.

[0058] Optionally, the distance between two points is calculated using the A* algorithm. The A* algorithm is a heuristic search algorithm that guides the search direction through a heuristic function to find the optimal path from the starting point to the target point.

[0059] S1022. Calculate the text similarity parameters between the user point and different facility points according to the text description information of the user point and the text description information of different facility points.

[0060] Optionally, calculate the text similarity parameter between the user point and any facility point according to the following formula (2):

[0061]

[0062] In formula (2), T(u, o) represents the spatial correlation parameter between the user point u and the facility point o; u.des represents the text description information of the user point u, and o.des represents the text description information of the facility point o; u.des ∩ o.des represents the intersection of the text description information of the user point u and the text description information of the facility point o; u.des ∪ o.des represents the union of the text description information of the user point u and the text description information of the facility point o.

[0063] S1023. Calculate the spatial-text correlation parameter between the user and different facility points according to the above spatial similarity parameter and text similarity parameter.

[0064] Optionally, calculate the spatial-text correlation parameter between the user point and any facility point according to the following formula (3):

[0065] P(u, o) = αS(u, o) + (1 - α)T(u, o) (3)

[0066] In formula (3), P(u, o) represents the spatial-text correlation parameter between the user point u and the facility point o; α is the spatial-text adjustment parameter, which is used to balance the importance of the spatial similarity parameter and the text similarity parameter to the influence of the facility point, and α ∈ [0, 1].[[]]

[0067] In the above embodiments, the spatial correlation parameter and the text correlation parameter between the user point and the facility point are calculated step by step, and then the spatial-text correlation parameter is calculated to quantify the influence of the facility point on the user point.

[0068] S103. Determine the candidate facility points from different facility points according to the spatial-text correlation parameter.

[0069] In some embodiments, when performing step S103, first determine whether the spatial-text correlation is greater than the expected influence threshold. If so, use the facility points with the spatial-text correlation parameter greater than the expected influence threshold as the candidate facility points. It can be understood that select the facility points with the spatial-text correlation parameter greater than the expected influence threshold from different facility points. Among them, the expected influence threshold τ is a preset spatial-text correlation threshold. If the spatial-text correlation parameter corresponding to a certain facility point is greater than the expected influence threshold, it means that the influence of this facility point on the user point is stronger. There is competition among multiple facility points with a spatial-text correlation parameter greater than the expected influence threshold.

[0070] Assume that different facility points include facility point o a and facility point ob , the facility point o is calculated through the above steps a and the spatial similarity parameter P(u, o a ) between the facility point o b and the user point u, as well as the spatial similarity parameter P(u, o b ) between the facility point o a and the user point u. If τ = 0.73, P(u, o b ) = 0.75, P(u, o a ) = 0.72, then the candidate facility points include the facility point o

[0071] . a ) > τ indicates that the facility point o a will affect the user point u. If P(u, o b ) > τ, the facility point o a will also affect the user point u. Then there is competition between the facility point o a and the facility point o b . Exemplarily, assume τ = 0.7, P(u, o a ) = 0.75, P(u, o b ) = 0.72. Then both the facility point o a and the facility point o b will affect the user point u, and there is competition between the facility point o a and the facility point o b .

[0072] In the above embodiments, by setting the expected influence threshold, candidate facility points that affect the user point and compete with each other are screened out from different facility points, so as to consider the peer competition factor during spatial text site selection, which is beneficial to selecting a more suitable address.

[0073] S104. Calculate the competitiveness scores of the candidate facility points based on the competition scoring model.

[0074] Among them, the competition scoring model is a model including multiple evaluation indicators, which is used to quantitatively score the facility points, so as to clearly show the advantages and disadvantages between each facility point and provide a basis for site selection.

[0075] In some embodiments, each grid cell includes the location information and attribute information of all object points in the corresponding geographical sub-region, and the attribute information includes user ratings, specifically the user ratings of the facility points. After performing step S103, the user ratings of the candidate facility points are normalized to obtain the competition weights.

[0076] Among them, the user rating can be a star rating standard, for example, from 1 star to 5 stars, indicating that the level of the facility point ranges from poor to excellent. Normalize the user rating of the candidate facility point into a discrete value, and use this discrete value as the weight to combine with the competition scoring model paradigm to obtain the competitiveness score of the candidate facility point.

[0077] Exemplarily, as shown in Table 1, the discrete values (weights) corresponding to the user ratings.

[0078] Table 1

[0079] User rating Weight 1 star 0.2 2 stars 0.4 3 stars s0.6 4 stars 0.8 5 stars 1

[0080] During the execution of step S104, substitute the competition weight into the competition scoring model to calculate the competitiveness score of the candidate facility point.

[0081] The above embodiment takes into account that peer competition is widespread. By normalizing the user rating as the weight to quantify the competitiveness, it is beneficial to select the optimal address.

[0082] S105. Select a target facility point from the candidate facility points according to the competitiveness score.

[0083] In some embodiments, when executing step S105, first calculate the actual road network distance between the candidate facility point and the user point according to the road index grid constructed in step S101, and then calculate the influence score of the candidate facility point according to the competitiveness score and the actual road network distance; further, select a target facility point from the candidate facility points according to the influence score. Among them, the smaller the actual road network distance between the candidate facility point and the user point, the higher the influence score.

[0084] In some embodiments, when calculating the actual road network distance between the candidate facility point and the user point in the road index grid, add a time parameter to calculate the actual road network distance between the candidate facility point and the user point corresponding to this time parameter, so as to find an available path at a certain time. This enables the user to query the facilities that meet the requirements when time permits. It should be noted that TaR-tree will first query according to the spatial range to find the nodes that may contain the target area (by comparing the query area with the MBR of the node), and then further filter out the data objects that meet the time interval requirements using the time information among these nodes. This can greatly reduce the amount of data to be traversed and improve the query efficiency.

[0085] TaR-tree can handle queries in both spatial and temporal dimensions simultaneously, greatly improving the query efficiency of spatio-temporal data.

[0086] Optionally, based on the A* algorithm, calculate the actual road network distance between the candidate facility point and the user point in the road index grid. The actual road network distance is the shortest distance from the user point to the candidate facility point that conforms to the actual road conditions, which is different from the straight-line distance between two points.

[0087] In the above embodiments, it is considered that people's travel in real life is often restricted by the road network conditions and they need to travel on the established paved roads. The straight-line distance between the starting point and the ending point is often not the actual distance in the road network environment. Therefore, in this application, the road index grid of the geographical area is first constructed, and then the actual road network distance between the user point and the facility point is calculated based on this road index grid.

[0088] In summary, the embodiments of this application provide a spatial text site selection method. This method first constructs a road index grid of the geographical area. Each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-region. The object points include facility points and user points. Then, based on this road index grid, calculate the spatial text correlation parameters between the user point and different facility points, and determine the candidate facility points from different facility points according to these spatial text correlation parameters. Then, calculate the competitiveness scores of the candidate facility points based on the competition scoring model, and thus select the target facility point according to the competitiveness scores of the candidate facility points as the final site selection address. In this way, this application constructs a road index grid of the geographical area, covering the location information and attribute information of all object points in the entire geographical area, and then calculates the control text similarity parameters based on this information to measure the influence of each facility point on the user point, so as to screen out some facility points. To select a more suitable target facility point, quantify the competitiveness scores of these facility points based on the competition scoring model and select according to these competitiveness scores, which improves the accuracy and effectiveness of spatial text site selection.

[0089] The embodiments of this application provide a spatial text site selection method, which includes the following steps S201 to S210:

[0090] S201. Construct a road index grid of the geographical area.

[0091] Each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-region. Each grid unit corresponds to a tree index structure TaR-tree, and the tree index structure TaR-tree is used to organize the location information and attribute information of all object points. The attribute information includes text description information, user ratings, etc. The attribute information may also include time attributes.

[0092] The construction of the road index grid in step S201 can refer to the implementation manner of the foregoing step S101, and this application will not elaborate here.

[0093] S202. Calculate the spatial correlation parameters between the user point and different facility points based on the location information of the user point and the location information of different facility points.

[0094] S203. Calculate the text similarity parameters between the user point and different facility points according to the text description information of the user point and the text description information of different facility points.

[0095] S204. Calculate the spatial - text correlation parameters between the user and different facility points based on the above - mentioned spatial similarity parameters and text similarity parameters.

[0096] For the specific calculations of the above steps S202 - S204, reference can be made to the aforementioned steps S1021 - S1023, and details are not elaborated herein in this application.

[0097] S205. Select candidate facility points from different facility points whose spatial - text correlation parameters are greater than the expected influence threshold.

[0098] Among them, the expected influence threshold τ is a preset spatial - text correlation threshold. If the spatial - text correlation parameter corresponding to a certain facility point is greater than the expected influence threshold, it indicates that this facility point has a strong influence on the user point. There is competition among multiple facility points with spatial - text correlation parameters greater than the expected influence threshold.

[0099] S206. Normalize the user ratings of the candidate facility points to obtain the competition weights.

[0100] S207. Substitute the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

[0101] S208. Based on the road index grid, calculate the actual road network distance between the candidate facility points and the user point.

[0102] Optionally, calculate the actual road network distance between the candidate facility points and the user point based on the A* algorithm.

[0103] S209. Calculate the influence scores of the candidate facility points according to the competitiveness scores and the actual road network distances.

[0104] Among them, the smaller the actual road network distance between the candidate facility point and the user point, the higher the influence score.

[0105] S210. Select the target facility point from the candidate facility points according to the influence scores.

[0106] The ideal target facility point is the one that has an impact on the user point, has the strongest competitiveness among its peers, and has the shortest actual road network distance from the user point.

[0107] The above steps construct a road index grid for a geographical area. Considering that the travel distance is not simply the straight-line distance, the actual road network distance between the user point and the facility point is calculated, making the final target facility point more reasonable. Considering the peer competition among facilities, by normalizing the user ratings as competition weights and introducing them into the competition scoring model, the competition capabilities of each facility point are quantified, and thus incorporated into the calculation of the influence of the facility point on the user, and the facility points with better competition capabilities are selected.

[0108] As Figure 4 shown, Figure 4 FIG. is a schematic structural diagram of a spatial text location device provided by an embodiment of the present application. The device includes:

[0109] A construction module 401, configured to construct a road index grid for a geographical area. Each grid unit includes the location information and attribute information of all object points in the corresponding geographical sub-area; wherein, the object points include facility points and user points;

[0110] A spatial text correlation calculation module 402, configured to calculate spatial text correlation parameters between the user point and different facility points based on the road index grid;

[0111] A determination module 403, configured to determine candidate facility points from different facility points according to the spatial text correlation parameters;

[0112] A competitiveness calculation module 404, configured to calculate the competitiveness scores of the candidate facility points based on the competition scoring model;

[0113] A selection module 405, configured to select target facility points from the candidate facility points according to the competitiveness scores.

[0114] As an optional implementation manner of an embodiment of the present application, the attribute information includes text description information. The spatial text correlation calculation module 402 is specifically configured to: calculate spatial similarity parameters between the user point and different facility points according to the location information of the user point and the location information of different facility points; calculate text similarity parameters between the user point and different facility points according to the text description information of the user point and the text description information of different facility points; calculate spatial text correlation parameters according to the spatial similarity parameters and the text similarity parameters.

[0115] As an optional implementation manner of an embodiment of the present application, the determination module 403 is specifically configured to: determine whether the spatial text correlation parameter is greater than an expected influence threshold; if so, use the facility points with the spatial text correlation parameter greater than the expected influence threshold as candidate facility points.

[0116] As an optional implementation manner of the embodiment of the present application, the attribute information includes user ratings, and the competitiveness calculation module 404 is further configured to: perform normalization processing on the user ratings of the candidate facility points to obtain competition weights.

[0117] As an optional implementation manner of the embodiment of the present application, the competitiveness calculation module 404 is specifically configured to: substitute the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

[0118] As an optional implementation manner of the embodiment of the present application, the selection module 405 is specifically configured to: calculate the actual road network distance between the candidate facility points and the user points according to the road index grid; calculate the influence scores of the candidate facility points according to the competitiveness scores and the actual road network distance; select the target facility points from the candidate facility points according to the influence scores.

[0119] In summary, the embodiment of the present application provides a spatial text location device. The device first constructs a road index grid of a geographical area. Each grid unit of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-area. The object points include facility points and user points. Then, based on this road index grid, calculate the spatial text correlation parameters between the user points and different facility points, so as to determine the candidate facility points from different facility points according to the spatial text correlation parameters, and then calculate the competitiveness scores of the candidate facility points based on the competition scoring model, so as to select the target facility points according to the competitiveness scores of the candidate facility points as the final location address. In this way, the present application constructs a road index grid of a geographical area, covering the location information and attribute information of all object points in the entire geographical area, and then calculates the control text similarity parameters based on this information to measure the influence of each facility point on the user point, so as to screen out some facility points. To select a more suitable target facility point, the competitiveness scores of these facility points are quantified based on the competition scoring model, and selection is made according to these competitiveness scores, which improves the accuracy and effectiveness of spatial text location.

[0120] For the specific limitations on the spatial text location device, reference may be made to the limitations on the spatial text location method in the foregoing text, which will not be elaborated here. Each module in the above-mentioned spatial text location device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0121] In one embodiment, the present application provides an electronic device. The electronic device can be a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a spatial text location method. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the electronic device, or an external keyboard, touchpad, or mouse, etc.

[0122] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0123] In one embodiment, the spatial text location device provided by the present application can be implemented in the form of a computer program, and the computer program can run on an electronic device such as Figure 5 shown in the figure. Each program module constituting the spatial text location device can be stored in the memory of the electronic device. For example, Figure 4 the construction module 401, the spatial text relevance calculation module 402, the determination module 403, the competitiveness calculation module 404, and the selection module 405 shown in the figure. The computer program composed of each program module enables the processor to execute the steps in the spatial text location method of each embodiment of the present application described in this specification.

[0124] For example, Figure 5 the electronic device shown in the figure can be through such as Figure 4The construction module 401 in the spatial text location device shown constructs a road index grid of a geographical area, and each grid cell of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub - area; wherein, the object points include facility points and user points; the electronic device can execute, through the spatial text correlation calculation module 402, calculating the spatial text correlation parameters between the user point and different facility points based on the road index grid; the electronic device can execute, through the determination module 403, determining candidate facility points from different facility points according to the spatial text correlation parameters; the electronic device can execute, through the competitiveness calculation module 404, calculating the competitiveness scores of the candidate facility points based on a competition scoring model; the electronic device can execute, through the selection module 405, selecting a target facility point from the candidate facility points according to the competitiveness scores.

[0125] In one embodiment, the present application provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0126] Construct a road index grid of a geographical area, and each grid cell of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub - area; wherein, the object points include facility points and user points; calculate the spatial text correlation parameters between the user point and different facility points based on the road index grid; determine candidate facility points from different facility points according to the spatial text correlation parameters; calculate the competitiveness scores of the candidate facility points based on a competition scoring model; select a target facility point from the candidate facility points according to the competitiveness scores.

[0127] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The attribute information includes text description information. Calculating the spatial text correlation parameters between the user point and different facility points based on the road index grid includes: calculating the spatial similarity parameters between the user point and different facility points according to the location information of the user point and the location information of different facility points; calculating the text similarity parameters between the user point and different facility points according to the text description information of the user point and the text description information of different facility points; calculating the spatial text correlation parameters according to the spatial similarity parameters and the text similarity parameters.

[0128] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Determining candidate facility points from different facility points according to the spatial text correlation parameters includes: judging whether the spatial text correlation parameters are greater than the expected influence threshold; if so, taking the facility points with spatial text correlation parameters greater than the expected influence threshold as candidate facility points.

[0129] In one embodiment, when the processor executes the computer program, the following steps are further implemented: The attribute information includes user ratings. After determining candidate facility points from different facility points according to the spatial text correlation parameter, the following steps are further included: Normalizing the user ratings of the candidate facility points to obtain competition weights.

[0130] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Calculating the competitiveness scores of the candidate facility points based on the competition scoring model, including: Substituting the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

[0131] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Selecting a target facility point from the candidate facility points according to the competitiveness scores, including: Calculating the actual road network distance between the candidate facility points and the user point according to the road index grid; Calculating the influence score of the candidate facility points according to the competitiveness scores and the actual road network distance; Selecting a target facility point from the candidate facility points according to the influence score.

[0132] When the processor in the electronic device provided in this application executes the computer program, first, a road index grid of the geographical area is constructed. Each grid unit of the road index grid includes the position information and attribute information of all object points in the corresponding geographical sub-area. The object points include facility points and user points; Then, based on this road index grid, the spatial text correlation parameter between the user point and different facility points is calculated to determine candidate facility points from different facility points according to this spatial text correlation parameter, and then the competitiveness scores of the candidate facility points are calculated based on the competition scoring model, so as to select a target facility point according to the competitiveness scores of the candidate facility points as the final site selection address. In this way, this application constructs a road index grid of the geographical area, covering the position information and attribute information of all object points in the entire geographical area, and then calculates the control text similarity parameter based on these information to measure the influence of each facility point on the user point, so as to screen out some facility points. To select a more suitable target facility point, the competitiveness scores of these facility points are quantified based on the competition scoring model, and selection is made according to these competitiveness scores, which improves the accuracy and effectiveness of spatial text site selection.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the following steps are implemented:

[0134] Construct a road index grid for a geographical area. Each grid cell of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub - area. Among them, the object points include facility points and user points. Based on the road index grid, calculate the spatial - text correlation parameters between user points and different facility points. Determine candidate facility points from different facility points according to the spatial - text correlation parameters. Calculate the competitiveness scores of the candidate facility points based on a competition scoring model. Select a target facility point from the candidate facility points according to the competitiveness scores.

[0135] In one embodiment, when the computer program executes, it also implements the following steps: The attribute information includes text description information. Based on the road index grid, calculating the spatial - text correlation parameters between the user point and different facility points includes: According to the location information of the user point and the location information of different facility points, calculate the spatial similarity parameter between the user point and different facility points; According to the text description information of the user point and the text description information of different facility points, calculate the text similarity parameter between the user point and different facility points; Calculate the spatial - text correlation parameter according to the spatial similarity parameter and the text similarity parameter.

[0136] In one embodiment, when the computer program executes, it also implements the following steps: According to the spatial - text correlation parameters, determining candidate facility points from different facility points includes: Judging whether the spatial - text correlation parameter is greater than the expected influence threshold; If so, use the facility points whose spatial - text correlation parameters are greater than the expected influence threshold as candidate facility points.

[0137] In one embodiment, when the computer program executes, it also implements the following steps: The attribute information includes user ratings. After determining candidate facility points from different facility points according to the spatial - text correlation parameters, it further includes: Normalize the user ratings of the candidate facility points to obtain competition weights.

[0138] In one embodiment, when the computer program executes, it also implements the following steps: Calculating the competitiveness scores of the candidate facility points based on a competition scoring model includes: Substitute the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

[0139] In one embodiment, when the computer program executes, it also implements the following steps: Selecting a target facility point from the candidate facility points according to the competitiveness scores includes: According to the road index grid, calculate the actual road network distance between the candidate facility points and the user point; According to the competitiveness scores and the actual road network distance, calculate the influence scores of the candidate facility points; Select a target facility point from the candidate facility points according to the influence scores.

[0140] When the computer program in the computer-readable storage medium provided by this application executes the computer program, it first constructs a road index grid for the geographical area. Each grid cell of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub-area. The object points include facility points and user points. Then, based on this road index grid, the spatial text correlation parameters between user points and different facility points are calculated to determine candidate facility points from different facility points according to these spatial text correlation parameters. Next, the competitiveness scores of the candidate facility points are calculated based on the competition scoring model, so as to select the target facility point according to the competitiveness scores of the candidate facility points as the final site selection address. In this way, by constructing a road index grid for the geographical area, covering the location information and attribute information of all object points in the entire geographical area, and then calculating the control text similarity parameters based on this information to measure the influence of each facility point on the user point, some facility points are screened out. To select a more suitable target facility point, the competitiveness scores of these facility points are quantified based on the competition scoring model, and selection is made according to these competitiveness scores, improving the accuracy and effectiveness of spatial text site selection.

[0141] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0142] In several embodiments provided by this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0143] In this application, the processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0144] In this application, the memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0145] In this application, computer-readable media includes permanent and non-permanent, removable and non-removable storage media. The storage media can implement information storage by any method or technology, and the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, Phase Change Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other memory technologies, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0146] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0147] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A spatial text location method, characterized in that, Including: Construct a road index grid for a geographical area, where each grid cell of the road index grid includes the location information and attribute information of all object points in the corresponding geographical sub - area; wherein, the object points include facility points and user points; Based on the road index grid, calculate the spatial - text correlation parameters between the user points and different facility points; According to the spatial - text correlation parameters, determine candidate facility points from different facility points; Calculate the competitiveness scores of the candidate facility points based on a competition scoring model; According to the competitiveness scores, select a target facility point from the candidate facility points.

2. The method according to claim 1, characterized in that, The attribute information includes text description information. The calculating the spatial - text correlation parameters between the user points and different facility points based on the road index grid includes: According to the location information of the user points and the location information of the different facility points, calculate the spatial similarity parameters between the user points and the different facility points; According to the text description information of the user points and the text description information of the different facility points, calculate the text similarity parameters between the user points and the different facility points; According to the spatial similarity parameters and the text similarity parameters, calculate the spatial - text correlation parameters.

3. The method according to claim 1, characterized in that The determining candidate facility points from different facility points according to the spatial - text correlation parameters includes: Judge whether the spatial - text correlation parameters are greater than the expected influence threshold; If so, use the facility points whose spatial - text correlation parameters are greater than the expected influence threshold as the candidate facility points.

4. The method according to claim 1, wherein The attribute information includes user ratings. After determining candidate facility points from different facility points according to the spatial - text correlation parameters, it further includes: performing normalization processing on the user ratings of the candidate facility points to obtain competition weights.

5. The method according to claim 4, wherein The calculating the competitiveness scores of the candidate facility points based on a competition scoring model includes: substituting the competition weights into the competition scoring model to calculate the competitiveness scores of the candidate facility points.

6. The method according to claim 1, characterized in that The selecting a target facility point from the candidate facility points according to the competitiveness scores includes: According to the road index grid, calculate the actual road network distance between the candidate facility points and the user points; According to the competitiveness scores and the actual road network distance, calculate the influence scores of the candidate facility points; According to the influence scores, select the target facility point from the candidate facility points.

7. A spatial text location device, characterized in that, Including: A construction module for constructing a road index grid for a geographical area, where each grid cell includes the location information and attribute information of all object points in the corresponding geographical sub - area; wherein, the object points include facility points and user points; A spatial - text correlation calculation module for calculating the spatial - text correlation parameters between the user points and different facility points based on the road index grid; A determination module for determining candidate facility points from different facility points according to the spatial - text correlation parameters; A competitiveness calculation module for calculating the competitiveness scores of the candidate facility points based on a competition scoring model; A selection module for selecting a target facility point from the candidate facility points according to the competitiveness scores.

8. An electronic device, characterized in that, Including: A processor, a memory, and a computer program stored on the memory and executable on the processor, wherein when the computer program is executed by the processor, it implements the spatial text location method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Comprising: A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the spatial text location method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Comprising: The computer program product includes a computer program, and when the computer program runs on a computer, it causes the computer to implement the spatial text location method according to any one of claims 1 to 6.

Images