Point location information determination method and device, computer equipment and readable storage medium

Abstract

The invention provides a point location information determination method and device, computer equipment and a readable storage medium. The method comprises the steps that a target point location and multiple potential point locations are determined from a designated area; wherein the target point location is provided with a convenient facility label; the potential point locations have other characteristic tags except the convenient facility tag; constructing respective characteristic variable matrixes by using the convenient facility point location information around each potential point location and the target point location; performing feature importance evaluation on the feature variable matrix of the target point location to obtain an important feature variable matrix; and performing similarity analysis on the important characteristic variable matrix of the target point location and the characteristic variable matrix of each potential point location, performing distance evaluation on a similarity analysis result, and determining a target potential point location corresponding to the target point location. The method not only improves the accuracy and scientificity of site selection decision, but also ensures the practicability and effectiveness of the selected potential point location by combining the feature similarity and the proximity of the geographic position.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method, device, computer equipment and readable storage medium for determining point information. Background Art

[0002] In the case of insufficient data resources, open data provided by OSM (OpenStreetMap) can be used as a supplement to point data. By analyzing the target point, other potential point information with high similarity can be identified, which provides valuable reference for decision-making in areas such as commercial real estate leasing, store location selection, and regional characteristics analysis.

[0003] As a map platform, OSM's real-time data updates and wide coverage make it an important resource in the field of geographic information. Through OSM open data, potential locations that meet specific conditions can be screened out to provide data support for business decisions. However, OSM data may have certain limitations, such as inaccurate point information, incomplete facility information, and information inconsistency, which may affect the accuracy of the analysis results. Therefore, when using OSM data, how to improve the accuracy and reliability of point information is a technical problem that needs to be solved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, computer equipment and readable storage medium for determining point information, which can reduce the impact of the limitations of OSM data on point information in the process of using OSM data, and improve the accuracy and reliability of the acquired point information. In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows: In a first aspect, the present invention provides a method for determining point information, the method comprising: determining a target point and multiple potential points from a designated area; wherein the target point has a convenience facility label; the potential point has other characteristic labels in addition to the convenience facility label; constructing respective characteristic variable matrices of each potential point and the target point using the convenience facility point information around each of the potential points and the target point; performing feature importance evaluation on the characteristic variable matrix of the target point to obtain an important characteristic variable matrix; performing similarity analysis on the important characteristic variable matrix of the target point and the characteristic variable matrix of each of the potential points, and performing distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point.

[0005] In a second aspect, the present invention provides a device for determining point information, including a determination module, a construction module, a feature screening module and an analysis and evaluation module; the determination module is used to determine a target point and multiple potential points from a specified area; the construction module is used to respectively use the information of each potential point and the point with the characteristics of the convenience facilities around the target point to construct respective feature variable matrices; the feature screening module is used to perform feature importance evaluation on the feature variable matrix of the target point to obtain an important feature variable matrix; the analysis and evaluation module is used to perform similarity analysis on the important feature variable matrix of the target point and the feature variable matrix of each potential point, and perform distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point.

[0006] In a third aspect, the present invention provides a computer device, comprising a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the method for determining point information described in any one of the aforementioned implementations.

[0007] In a fourth aspect, the present invention provides a readable storage medium, comprising a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the point information determination method described in any of the aforementioned implementations.

[0008] The point information determination method, device, computer equipment and readable storage medium provided by the present invention have the following advantages: first, after determining the target point and multiple potential points from the designated area, the convenience facility point information around each potential point and the target point is used to construct respective characteristic variable matrices, and the geographic spatial data is converted into numerical features that can be used for analysis, providing a structured data basis for further data processing and analysis, and the characteristic importance of the characteristic variable matrix of the target point is evaluated to obtain an important characteristic variable matrix, and the pertinence and accuracy of the analysis are improved by identifying and strengthening the characteristic variables that have the greatest impact on the target point, and the important characteristic variable matrix of the target point is analyzed for similarity with the characteristic variable matrix of each potential point, and a distance evaluation is performed on the similarity analysis results to determine the target potential point corresponding to the target point, ensuring that the selected potential point is not only similar to the target point in terms of characteristics, but also feasible in terms of geographical location. The entire method not only improves the accuracy and scientificity of site selection decisions, but also ensures the practicality and effectiveness of the selected potential point by combining feature similarity and geographical location proximity.

[0009] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic flow chart of determining point information provided by an embodiment of the present invention; Figure 2 is an example diagram of a designated area provided in an embodiment of the present invention; Figure 3 The distribution of the convenience facilities in the specified area in the embodiment of the present invention is shown; Figure 4 The distribution of potential points in the specified area in the embodiment of the present invention is shown; Figure 5 The scatter distribution of the actual and predicted values ​​of the random forest is shown; Figure 6 is an example of an inflection point diagram provided in an embodiment of the present invention; Figure 7 A schematic diagram of the geographic spatial relationship between target points and potential points in a specified area in an embodiment of the present invention is shown; Figure 8 The geospatial relationship between target points and potential points in a zoomed-in view is shown; Fig. 9 A functional module diagram of a device for determining point information provided by an embodiment of the present invention; Fig.10 A structural block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0013] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0014] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0015] Considering the inaccuracy of point information, incompleteness of facility information, and inconsistency of information in existing OSM data, which affect the accuracy of point information, the embodiment of the present invention provides a point information determination method, which can use OSM data to determine other potential point information with high similarity to the target point, and provide a reference for site selection and regional feature analysis.

[0016] See also Figure 1 , Figure 1 The schematic flow chart of determining the point information provided by the embodiment of the present invention is as follows. The execution subject of the method may be a computer device with data processing capability, and the computer device may perform the following steps: S101: Determine a target point and multiple potential points from a designated area; Among them, the target point is a point that the data analyst is interested in, that is, the point to be studied, which has a convenience facility label; the potential point is a reference point when the data analyst conducts site selection analysis on the target point, and has other characteristic labels except the convenience facility label; S102: constructing respective characteristic variable matrices using the information of the convenience facilities around each potential point and target point; S103: performing feature importance evaluation on the feature variable matrix of the target point to obtain an important feature variable matrix; S104: Performing similarity analysis on the important characteristic variable matrix of the target point and the characteristic variable matrix of each potential point, and performing distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point.

[0017] In the scheme of steps S101 to S104 provided by the embodiment of the present invention, firstly, a target point and multiple potential points are determined from a designated area, the target point has a convenience facility label; the potential point has other characteristic labels except the convenience facility label, and the convenience facility point information around each potential point and the target point is used to construct respective characteristic variable matrices, and the geographic spatial data is converted into numerical features that can be used for analysis, providing a structured data basis for further data processing and analysis, and the characteristic importance of the characteristic variable matrix of the target point is evaluated to obtain an important characteristic variable matrix, and the pertinence and accuracy of the analysis are improved by identifying and strengthening the characteristic variables that have the greatest impact on the target point, and the important characteristic variable matrix of the target point is analyzed for similarity with the characteristic variable matrix of each potential point, and a distance evaluation is performed on the similarity analysis results to determine the target potential point corresponding to the target point, ensuring that the selected potential point is not only similar to the target point in terms of characteristics, but also feasible in terms of geographical location. The entire method not only improves the accuracy and scientificity of the site selection decision, but also ensures the practicality and effectiveness of the selected potential point by combining the feature similarity and the proximity of the geographical location.

[0018] The various steps involved in the method for determining point information provided by an embodiment of the present invention will be clearly and detailedly described below in conjunction with relevant drawings.

[0019] In step S101, the designated area is the area of ​​interest where the data analyst wishes to analyze the point information. The area of ​​interest includes a district or county in a city. For example, as an example, the designated area may be District A1 in City A. The data analyst flexibly designates the area according to actual needs, which is not limited here.

[0020] In practice, data analysts can use OpenStreetMap to accurately locate specific geographic areas. Taking one possible implementation as an example, data analysts can, but are not limited to, use Python programming tools to extract data. For example, in Python code, a variable place can be defined and assigned the value "China, City A, District A1" to retrieve and obtain map data for the area. Next, data analysts can accurately mark the boundaries of the area of ​​interest on the map in order to determine the specific area required. Figure 2 As shown, Figure 2 is an example diagram of a designated area provided in an embodiment of the present invention.

[0021] There are many types of points in a given area, and these points have some specific characteristic information, such as convenience characteristics, shopping characteristics, building characteristics, railway characteristics, subway characteristics, etc. Under each characteristic information, there are many different types of points. For example, restaurants, coffee shops, and parks all belong to the category of convenience characteristics. Data analysts can, but are not limited to, use Python programming tools to retrieve point information from OpenStreetMap.

[0022] For example, data analysts can use the osmnx library in Python programming tools to access OpenStreetMap point information. The specific operations are as follows: First, a tag dictionary tags can be defined, containing the following key-value pairs: {'amenity': True, 'shop': True, 'building': True, 'railway': True, 'subway': True}. Among them, "amenity" represents points with amenities, such as "restaurant", "coffee shop", "park", etc.; "shop" represents points with shopping attributes; "building" represents points with building attributes; "railway" represents points with railway attributes; and "subway" refers to points with subway attributes. Then, the computer device obtains the corresponding point information by executing the function osmnx.geometries_from_place(place, tags).

[0023] Based on the above content, in one embodiment of the present invention, the implementation method of determining the target point and the control point may be: Step a1: Obtain a convenience facility point information table from OpenStreetMap according to the convenience facility feature tag; wherein each point information includes the convenience facility type of the point; Step a2: extracting point information corresponding to the target point name under one type of convenience facility from the convenience facility point information table to form a target point information table; Continuing with the previous example, the data analyst can first set the amenity feature tag, such as tags = {'amenity': True}, and then the computer device retrieves the point information amenity point information table by executing the code osmnx.geometries_from_place(place, tags), as shown in Table 1. Figure 1 A distribution map of the convenience facilities provided by the embodiment of the present invention within a specified area is displayed.

[0024] Data analysts can first configure a tag dictionary specifically for the characteristics of convenience facilities, such as tags = {'amenity': True}. Subsequently, the computer device can retrieve and obtain the location information of the convenience facilities by executing the code osmnx.geometries_from_place(place, tags), and then generate a data table containing these location information, which can be called the convenience facility location information table. For ease of understanding, the convenience facility location information table is shown in Table 1. In addition, Figure 3 The distribution of the convenience facility points in the specified area in the embodiment of the present invention is displayed, providing an intuitive geospatial view for data analysts.

[0025] Table 1

[0026] It can be observed from Table 1 that the computer equipment can extract various types of convenience points from OpenStreetMap using the convenience feature tags. These points cover a variety of places such as restaurants, cafes, bars, fast food restaurants, etc. In addition, the computer equipment can also obtain detailed information about these convenience points, such as their element type and unique OSMID in OpenStreetMap, and the precise geometric information of the points, which is essential for further data analysis and geospatial research.

[0027] Furthermore, after the computer device obtains the convenience facility point information table, the data analyst can specify a certain type of point under one of the convenience facility types as the target point from each convenience facility type, thereby obtaining the target point information table. In this process, the data analyst can also set a label for the selected convenience facility type, and the computer device finds each point under the convenience facility type in the convenience facility point information table based on the label and determines the target point therefrom.

[0028] For example, assuming that the amenity type selected by the data analyst is "cafe" and the point name selected is "Starbucks", then a tag can be configured as tags = {'amenity': 'cafe'}, then the computer device can obtain the target point information table with the amenity type of "cafe" and the point name of "Starbucks" from Table 1 based on the tag, as shown in Table 2. Table 2

[0029] It can be seen from Table 2 that there are multiple target points marked as "cafe" type and the point name is "Starbucks", and these points constitute the research object of the embodiment of the present invention. In addition, using the above method, the computer device can also synchronously obtain detailed information records of each target point, and each record not only contains the element type and OSMID of the target point in OpenStreetMap, geometric information, but also covers key data such as brand. These comprehensive information provides a solid data foundation for in-depth analysis and understanding of each Starbucks point.

[0030] It should be understood that Table 1 only shows some of the point information with convenience characteristics, while Table 2 shows some points and their detailed information when the convenience type is a cafe. These tables do not constitute a restriction on the type and number of convenience points. In fact, data analysts can flexibly select and extract point information according to their specific needs to meet the needs of subsequent analysis processes.

[0031] Step a3: Obtain a potential point information table with characteristic tags from OpenStreetMap according to at least one designated characteristic tag other than the convenience facility characteristic tag.

[0032] Similar to the process of determining the target point, data analysts can set specific feature tags, such as tags={'building': 'office', 'shop': True}, to identify those points with office building characteristics and shopping characteristics. The computer device can obtain the potential point information table matching these feature tags by executing osmnx.geometries_from_place(place, tags). For a more intuitive understanding, the potential point information table is shown in Table 4, and Figure 4 The distribution of potential points in the specified area in the embodiment of the present invention is shown.

[0033] Table 3

[0034] Through the above implementation, the embodiment of the present invention can quickly determine the target points and potential points in the specified area from OpenStreetMap and retrieve the point information corresponding to various points, which provides a data basis for subsequent potential point screening.

[0035] In step S102, once the target point and the potential point are determined, in order to evaluate the similarity between them and prepare for screening out the potential point that is most similar to the target point, the embodiment of the present invention first constructs the feature vectors of the target point and the potential point. To this end, the present invention provides an implementation method, the process is as follows: Step b1: for potential points and target points, determine the target amenity points within the preset radius and count the total number of each target amenity point; In an embodiment of the present invention, the preset radius range can be flexibly adjusted according to the specific needs of the data analyst. For example, if it is set to 300 meters, then for each target point and potential point, the convenience facility points within 300 meters around it and the total number of these points can be identified, providing accurate geospatial data for further similarity evaluation and point screening.

[0036] In the embodiment of the present invention, in the process of counting the total number of each target amenity point, the associated information table corresponding to the target point and the potential point can be constructed first, and then the total number can be counted. Therefore, in the embodiment of the present invention, the total number can also be counted in the following manner: First, the serial number of the target point and the serial numbers of the target convenience point corresponding to the target point and the potential point are obtained in the convenience point information table, and the serial number of the potential point is obtained in the potential point information table; Secondly, a correlation information table corresponding to the target point is constructed based on the target point and its corresponding target convenience facility serial number, and a correlation information table of the potential point is constructed based on the potential point serial number and its corresponding target convenience facility point serial number; Finally, based on the associated information tables corresponding to the target points and potential points, the total number of each corresponding target amenity point is counted.

[0037] That is to say, for the target point, the associated information table corresponding to the target point is constructed according to the serial numbers of the target point and its corresponding target convenience facility point in the convenience facility point information table, as shown in Table 4.

[0038] Table 4

[0039] In Table 4, the serial number (0, 1) represents the row number of the target point in the convenience point information table, that is, the target points corresponding to row 0 and row 1 respectively, and "Indices" refers to the row number of the target convenience point in the convenience point information table. For example, for the target point in row 0, within its preset radius, the target convenience points include row 671, row 664, row 756, row 713, row 781, row 714, row 757, row 658 and row 832 in the convenience point information table. These serial numbers can help the computer equipment quickly locate the corresponding target convenience point type in the convenience point information table, providing a reference for further analysis.

[0040] Similar to the process of constructing the target point association information table, the potential point association information table is similar to the association information table shown in Table 4, so the specific example is not repeated here. In this way, a detailed association information view can be generated for each potential point and target point, further facilitating the in-depth analysis of the similarity between the target point and the potential point.

[0041] Step b2: Take each target amenity facility point as a characteristic variable, and take the total number of target variable facility points as the eigenvalue of the characteristic variable to obtain a characteristic variable matrix.

[0042] Finally, the characteristic variable matrices constructed for the target points and potential points according to the embodiment of the present invention are shown in Table 5 and Table 6. Table 5 is an example of the characteristic variable matrix of the target point, and Table 6 is an example of the characteristic variable matrix of the potential point.

[0043] Table 5

[0044] Table 6

[0045] Each row in Table 5 shows the number of various types of convenience points within the preset radius of a target point. Correspondingly, each row in Table 6 shows the number of various types of convenience points within the preset radius of a potential point. These two tables provide a quantitative data basis for evaluating the similarity between the target point and the potential point.

[0046] Through the above implementation, the computer device obtains the characteristic variable matrices corresponding to the target points and potential points. Next, the computer device can normalize these characteristic variable matrices and adjust the values ​​of all characteristic variables to the interval [0,1]. This normalization operation helps to eliminate the influence of dimensions between different characteristic variables, making the data more consistent and convenient for subsequent analysis. After normalization is completed, the computer device can continue to execute the analysis process of the subsequent step S103 based on these standardized characteristic variable matrices.

[0047] In step S103, considering that various point information such as target points, potential points and their corresponding target convenience facility points are all derived from OSM open data, these data may have certain inaccuracies, incomplete facility information, and information inconsistency. These problems may cause the characteristic variables of the target points to contain data that is inconsistent with common sense, unclear or ambiguous, thereby affecting the accuracy of subsequent evaluation results. Therefore, in an embodiment of the present invention, it is also necessary to perform a quality assessment on each characteristic variable corresponding to the target point to ensure the reliability of the data and the accuracy of the evaluation results. Therefore, in an embodiment of the present invention, the process of implementing the feature importance assessment of the characteristic variable matrix of the target point is as follows: Step c1: preprocess the feature variable matrix; In an embodiment of the present invention, preprocessing the feature variable matrix refers to removing those feature variables whose meanings are unclear or may cause misunderstanding. For example, the feature variable "fuel" may refer to a gas station, but without context, its meaning may be unclear and therefore is considered ambiguous. It is also necessary to remove uncertain feature variables, that is, those with incomplete data or unclear status. For example, the feature variable "public_bookcase" may exist in some cases, but may not exist or its status is unknown in other cases. Removing these variables can improve the quality of the data and the accuracy of the analysis.

[0048] In actual operation, data analysts can conduct preliminary manual observations to determine whether the distribution of characteristic variables of the target points is reasonable. If it is found that the distribution of certain characteristic variables is contrary to common sense, they can be manually eliminated. For example, data analysts can perform univariate analysis through computer equipment to identify trends or patterns in the characteristic variable matrix. Through this method, it can be found that there are some specific types of convenience facilities around most target points, such as restaurants, coffee shops, fast food restaurants, banks, etc., which are commonly seen around Starbucks. This pattern may suggest that Starbucks prefers areas that already have more convenience facilities when choosing store locations, so as to attract more customers. Through such analysis, data analysts can understand the characteristics of target points more accurately and lay a solid foundation for subsequent evaluation work.

[0049] Furthermore, the computer equipment can perform PCA (principal component analysis) on the matrix of characteristic variables and present the analysis results in a graphical form. Data analysts can determine whether the linear relationship between the variables is obvious through manual observation. If no obvious interdependence or correlation is observed between the variables, this indicates that all characteristic variables are regarded as equally important, which may be impractical in practical applications. For example, if there is a library around Starbucks, which is not actually a key characteristic variable, it is given the same weight as other characteristic variables in the PCA analysis, which is inconsistent with the actual situation. Since PCA analysis may produce unreasonable results, such as equating the importance of non-key characteristic variables (such as libraries) with other variables, it is necessary to further evaluate the importance of each characteristic variable to ensure the accuracy and practicality of the analysis results.

[0050] It should be noted that the above step c1 as the first step of feature importance evaluation is only an example, and is of course executed after step c4, that is, as the last step of feature importance evaluation, which is not limited in the embodiment of the present invention.

[0051] Step c2: input the feature variable matrix into a preset feature evaluation model for processing; In the embodiment of the present invention, the feature evaluation model may be, but is not limited to, a random forest.

[0052] Step c3: Determine the evaluation index based on the difference between the predicted value and the actual value of the feature variable matrix by the feature evaluation model; Step c4: remove one characteristic variable from the characteristic variable matrix to obtain an updated characteristic variable matrix, and return to step c2 until the current evaluation index meets the convergence condition to obtain an important characteristic variable matrix.

[0053] For ease of understanding, taking the feature evaluation module as a random forest as an example, the feature importance evaluation of the random forest can identify the feature variables that have the greatest impact on the model prediction. These feature variables are more frequently used to split data in the decision tree of the random forest, which can show that some feature variables are more important than other feature variables.

[0054] In the process of using random forest to process the characteristic variable matrix, the model can use mean square error (MSE) as an evaluation index to measure the prediction accuracy. Therefore, in an embodiment of the present invention, after the characteristic variable matrix is ​​input into the random forest, the model will output an MSE value. Subsequently, a certain characteristic variable in the characteristic variable matrix can be removed one by one, and the updated characteristic variable matrix can be re-input into the model for processing. Through this iterative process, the model will calculate a new MSE value after each adjustment. Compare the current MSE value with the previous MSE value. If it is within the preset error range, for example, the MSE after the last adjustment is 0.0701±0.0115, and its mean and error are lower than the previous MSE value of 0.0784±0.0218, it can be considered that the adjustment has achieved satisfactory results. At this time, further adjustments can be stopped, and the characteristic variable matrix finally determined, that is, the matrix containing the important characteristic variables.

[0055] Of course, the computer equipment can also draw a scatter plot of actual values ​​and predicted values ​​while using random forest to evaluate the importance of the feature variable matrix, so that data analysts can intuitively understand the specific impact of each feature variable on the model's prediction ability and judge when to end the evaluation process accordingly. Figure 5 As shown, Figure 5 The scatter plot shows the actual and predicted values ​​of the random forest. Specifically, if a feature variable is critical to the model, then after removing the feature variable, the model's predicted value will deviate significantly from the actual value, resulting in more outliers on the scatter plot. When most data points are concentrated near the red dotted line, it indicates that the model fits most samples more accurately and the distribution of data points is more concentrated. Through this intuitive analysis, data analysts can more accurately evaluate the importance of feature variables and determine the end point of the evaluation.

[0056] Through the above implementation, the embodiment of the present invention obtains the important feature variable matrix corresponding to the target point and the feature vector matrix corresponding to the potential point. Before performing similarity analysis, it is necessary to ensure that the two matrices are consistent in dimension. For example, assuming that the important feature variable matrix of the target point is an N1×M1 matrix, indicating that there are N1 target points, each target point has M1 feature variables, and the feature variable matrix of the potential point is an N2×M2 matrix, indicating that there are N2 potential points, each potential point has M2 feature variables. If the dimensions of M1 and M2 are inconsistent, then it will not be feasible to directly perform similarity judgment. Therefore, the present invention adopts the following method to ensure that the two feature variable matrices have the same dimensions before comparison or analysis. The process is as follows: Step d1: Determine whether the total number of characteristic variables of the important characteristic variable matrix of the target point and the characteristic variable matrix of the potential point are the same; Step d2: If they are not the same, when the important characteristic variable matrix is ​​missing the characteristic variables in the characteristic variable matrix, add the characteristic variables to the important characteristic variable matrix and set the characteristic values ​​to zero; when the important characteristic variables in the important characteristic variable matrix are missing in the characteristic variable matrix, add the important characteristic variables to the characteristic variable matrix and set the characteristic values ​​to zero.

[0057] The above implementation ensures that the two feature variable matrices have the same dimensions before comparison or analysis. By adding missing feature variables and initializing their values ​​to zero, the two matrices are made consistent in the number of feature variables, so that subsequent similarity analysis or other data processing operations can be performed.

[0058] Furthermore, the embodiment of the present invention can perform similarity analysis and distance evaluation after dimensional alignment of the important eigenvector matrix and the eigenvector matrix, and the process is as follows: Step e1: Calculate the similarity between the important feature variable matrix and each feature variable matrix; In the embodiment of the present invention, the similarity referred to may be but is not limited to cosine similarity. In the specific calculation implementation process, each target point and all potential points may be measured for similarity, and the similarity between the target point and each potential point may be obtained by calculating the average value of the similarity between each feature vector of the target point and each feature vector of the potential point. As shown in Table 7.

[0059] Table 7

[0060] In Table 7, OSM ID represents the unique identifier of the potential point in OSM, and each potential point corresponds to an average similarity. Each target point can get a Table 7 to maintain the similarity between each potential point and the target point.

[0061] Step e2: taking the potential points with the maximum similarity and the similarity exceeding the similarity threshold as candidate potential points; In an embodiment of the present invention, in addition to selecting the potential point with the highest similarity to the target point to participate in the subsequent distance evaluation, in order to ensure that there are enough potential points to choose from, a similarity threshold can also be set to filter out potential points with similarity exceeding the threshold.

[0062] Specifically, the computer device can comprehensively consider the similarities of all potential points and draw an inflection point graph. Data analysts can observe the inflection point graph to see the number of potential points within a specific similarity interval, and then select the similarity value at the inflection point as the threshold. For example, Figure 6 , Figure 6is an example of an inflection point diagram provided in an embodiment of the present invention. Figure 6 It can be observed that although the curve is tilted downward to the right as a whole and has no obvious inflection point, the slope of the curve is gentler in the similarity range of 0.4-0.7 than in other ranges. Therefore, based on experience, 0.5 can be selected as the similarity threshold. This choice not only ensures the number of potential points, but also retains a high similarity, providing a reasonable balance point for subsequent analysis.

[0063] Step e3: determining the candidate potential points within a preset distance range of the target point as the target potential points.

[0064] In an embodiment of the present invention, after the similarity analysis is completed, a distance evaluation can be further performed to ensure the reliability of the target potential points screened out in the similarity analysis. When performing the distance evaluation, a specific distance range can be set as an evaluation criterion. The lower limit value of this distance range can be the same as the radius used to screen the target convenience facility points when constructing the characteristic variable matrix, such as 300 meters, but it can also be set to a different lower limit value. At the same time, in order to prevent the potential points from being too far away from the target points and unable to form an effective aggregation effect, an upper limit value of the distance needs to be set, such as 1500 meters. In this way, the candidate potential points within the preset distance range of the target point can be determined as the target potential points. So far, the whole process of determining the potential point information most similar to the target point is completed. This method takes into account both the similarity between points and the proximity of geographical locations, providing double protection for finding the most suitable potential points.

[0065] In addition, in order to verify the rationality of the selected target potential points, data analysts can also visually check the relative positions of the target points and potential points in geographic space through the map. Figure 7 and Figure 8 , Figure 7 The schematic diagram of the geographic spatial relationship between the target points and potential points in the specified area in the embodiment of the present invention is shown. Figure 8 The geospatial relationship between target points and potential points in the zoomed-in view is displayed. Data analysts can visually observe whether the selected potential points meet expectations on these maps, thereby providing a strong basis for the site selection decision of the target points and improving the accuracy and reliability of the site selection process.

[0066] Based on Figure 1 With the same inventive concept, the present invention also provides a device for determining point information. Fig. 9 , Fig. 9 This is a functional module diagram of a device for determining point information provided by an embodiment of the present invention. Fig. 9In the embodiment, the point information determination device 20 may include: a determination module 201, a construction module 202, a feature screening module 203 and an analysis and evaluation module 204.

[0067] A determination module 201 is used to determine a target point and multiple potential points from a specified area; A construction module 202 is used to construct respective characteristic variable matrices using information of points with convenient facilities around each potential point and target point; The feature screening module 203 is used to evaluate the feature importance of the feature variable matrix of the target point to obtain an important feature variable matrix; The analysis and evaluation module 204 is used to perform similarity analysis on the important characteristic variable matrix of the target point and the characteristic variable matrix of each potential point, and perform distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point.

[0068] It is understandable that the determination module 201, the construction module 202, the feature screening module 203 and the analysis and evaluation module 204 can be executed in a coordinated manner. Figure 1 Each step in the process is performed to achieve the corresponding technical effect.

[0069] In an optional embodiment, the feature screening module 203 is specifically used to preprocess the feature variable matrix; input the feature variable matrix into a preset feature evaluation model for processing; determine the evaluation index based on the difference between the predicted value and the actual value of the important feature variable matrix of the feature evaluation model; remove a feature variable in the feature variable matrix to obtain an updated feature variable matrix, and return to the step of inputting the feature variable matrix into the preset feature evaluation model for processing, until the current evaluation index meets the convergence condition and stops to obtain the important feature variable matrix.

[0070] In an optional embodiment, the construction module 202 is also used to determine whether the total number of characteristic variables of the important characteristic variable matrix of the target point and the characteristic variable matrix of the potential point are the same; if not, when the characteristic variables in the characteristic variable matrix are missing in the important characteristic variable matrix, the characteristic variables are added to the important characteristic variable matrix and the characteristic values ​​are set to zero; when the important characteristic variables in the important characteristic variable matrix are missing in the characteristic variable matrix, the important characteristic variables are added to the characteristic variable matrix and the characteristic values ​​are set to zero.

[0071] In an optional embodiment, the analysis and evaluation module 204 is used to calculate the similarity between the important feature variable matrix and each feature variable matrix; to use the potential points with the maximum similarity and the similarity exceeding the similarity threshold as candidate potential points; and to determine the candidate potential points within a preset distance range of the target point as target potential points.

[0072] In an optional embodiment, the determination module 201 is specifically used to obtain a convenience facility point information table from OpenStreetMap according to the convenience facility characteristic tag; wherein each point information includes the convenience facility type of the point; extract the point information corresponding to the target point name under one of the convenience facility types from the convenience facility point information table to form a target point information table; obtain a potential point information table with characteristic tags from OpenStreetMap according to at least one specified characteristic tag other than the convenience facility characteristic tag.

[0073] In an optional embodiment, the determination module 201 is also specifically used to obtain the serial number of the target point and the serial numbers of the target amenity points corresponding to the target point and the potential point in the amenity point information table, and obtain the serial number of the potential point in the potential point information table; construct an associated information table corresponding to the target point based on the target point and its corresponding target amenity serial number, and construct an associated information table for the potential point based on the potential point serial number and its corresponding target amenity point serial number; and count the total number of each corresponding target amenity point based on the associated information tables corresponding to the target point and the potential point.

[0074] It should be noted that the division of modules in the above embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0075] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program executable code.

[0076] The embodiment of the present invention further provides a computer device 30, see Fig.10 , Fig.10The computer device 30 provided in the embodiment of the present invention includes a memory 301, a processor 302 and a communication interface 303. The memory 301, the processor 302 and the communication interface 303 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0077] Optionally, the bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0078] In the embodiment of the present invention, the processor 302 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiment of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor. The software module may be located in the memory 301, and the processor 302 reads the program instructions in the memory 301 and completes the steps of the above method in combination with its hardware.

[0079] In the embodiment of the present invention, the memory 301 may be a non-volatile memory, such as a hard disk (HDD) or a solid-state drive (SSD), etc., or a volatile memory (Volatile Memory), such as RAM. The memory may also be any other medium that can be used to carry or store the desired program executable code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention may also be a circuit or any other device that can realize a storage function, for storing instructions and / or data.

[0080] The memory 301 can be used to store software programs and modules, such as the instructions / modules of the point information determination device 20 provided in the embodiment of the present invention, which can be stored in the memory 301 in the form of software or firmware (Firmware) or in the operating system (OS) of the fixed computer device 30. The processor 302 executes various functional applications and data processing by executing the software programs and modules stored in the memory 301. The communication interface 303 can be used to communicate signaling or data with other node devices.

[0081] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0082] Understandably, Fig.10 The structure shown is for illustration only. The computer device 30 may also include Fig.10 More or fewer components as shown, or with Fig.10 Different configurations are shown. Fig.10 The components shown may be implemented in hardware, software or a combination thereof.

[0083] The computer device 30 may also include a network device and / or a user device. The network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0084] Based on the above embodiments, the present application further provides a storage medium, in which a computer program is stored. When the computer program is executed by a computer, the computer executes the point information determination method provided in the above embodiments.

[0085] Based on the above embodiments, an embodiment of the present invention further provides a computer program. When the computer program is run on a computer, the computer executes the point information determination method provided in the above embodiments.

[0086] Based on the above embodiments, an embodiment of the present invention further provides a chip, which is used to read a computer program stored in a memory and to execute the point information determination method provided in the above embodiments.

[0087] A computer program product is also provided in an embodiment of the present invention, including instructions, which, when executed on a computer, enable the computer to execute the method for determining point information provided in the above embodiment.

[0088] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by instructions. These instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0091] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for determining point information, characterized in that: The method comprises: Determine a target point and multiple potential points from a designated area; wherein the target point has a convenience facility tag; and the potential point has other characteristic tags except the convenience facility tag; Using the convenience facility point information around each of the potential points and the target points, construct respective characteristic variable matrices; Performing feature importance evaluation on the feature variable matrix of the target point to obtain an important feature variable matrix; A similarity analysis is performed on the important characteristic variable matrix of the target point and the characteristic variable matrix of each potential point, and a distance evaluation is performed on the similarity analysis results to determine the target potential point corresponding to the target point.

2. The method for determining point information according to claim 1, characterized in that: Performing feature importance evaluation on the feature variable matrix of the target point to obtain an important feature variable matrix includes: Preprocessing the characteristic variable matrix; Inputting the characteristic variable matrix into a preset characteristic evaluation model for processing; Determining an evaluation index based on the difference between the predicted value and the actual value of the important feature variable matrix by the feature evaluation model; A characteristic variable in the characteristic variable matrix is ​​removed to obtain an updated characteristic variable matrix, and the step of inputting the characteristic variable matrix into a preset characteristic evaluation model for processing is returned until the current evaluation index meets the convergence condition and stops to obtain the important characteristic variable matrix.

3. The method for determining point information according to claim 1 or 2, characterized in that: After constructing respective characteristic variable matrices using the convenience facility point information around each of the potential points and the target point, the method further includes: Determine whether the total number of characteristic variables of the important characteristic variable matrix of the target point is the same as that of the characteristic variable matrix of the potential point; If they are not the same, when the characteristic variables in the characteristic variable matrix are missing in the important characteristic variable matrix, the characteristic variables are added to the important characteristic variable matrix and the characteristic values ​​are set to zero; when the important characteristic variables in the important characteristic variable matrix are missing in the characteristic variable matrix, the important characteristic variables are added to the characteristic variable matrix and the characteristic values ​​are set to zero.

4. The method for determining point information according to claim 1 or 2, characterized in that: Performing similarity analysis on the important characteristic variable matrix of the target point and the characteristic variable matrix of each potential point, and performing distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point, including: Calculating the similarity between the important feature variable matrix and each of the feature variable matrices; The potential points with the maximum similarity and the similarity exceeding the similarity threshold are taken as candidate potential points; The candidate potential points located within a preset distance range of the target point are determined as the target potential points.

5. The method for determining point information according to claim 1, characterized in that: Determine the target point and various potential points from the specified area, including: Obtaining a convenience facility point information table from OpenStreetMap according to the convenience facility feature tag; wherein each point information includes the type of convenience facility at the point; Extract point information corresponding to the target point name under one of the types of convenience facilities from the convenience facility point information table to form a target point information table; According to at least one designated characteristic tag other than the convenience facility characteristic tag, a potential point information table having the characteristic tag is obtained from the OpenStreetMap.

6. The method for determining point information according to claim 5, characterized in that: The information of the convenience facilities around each potential point and the target point is used to construct respective characteristic variable matrices, including: For the potential points and the target points, determine the target convenience facility points within the preset radius and count the total number of each target convenience facility point; Each of the target convenience facility points is used as the characteristic variable, and the total number of the target convenience facility points is used as the characteristic value of the characteristic variable, so as to obtain the characteristic variable matrix.

7. The method for determining point information according to claim 6, characterized in that: The process of counting the total number of each target amenity point includes: Obtain the serial number of the target point and the serial numbers of the target convenience facility points corresponding to the target point and the potential point in the convenience facility point information table, and obtain the serial number of the potential point in the potential point information table; Based on the target point and its corresponding target convenience facility serial number, a corresponding association information table of the target point is constructed; based on the potential point serial number and its corresponding target convenience facility point serial number, a corresponding association information table of the potential point is constructed; Based on the associated information tables corresponding to the target points and potential points respectively, the total number of each corresponding target amenity point is counted.

8. A device for determining point information, characterized in that: Determine module, build module, feature screening module and analysis and evaluation module; A determination module, used to determine a target point and multiple potential points from a specified area; wherein the target point has a convenience facility tag; and the potential point has other characteristic tags except the convenience facility tag; A construction module, used to construct respective characteristic variable matrices using the convenience facility point information around each of the potential points and the target points; A feature screening module is used to perform feature importance evaluation on the feature variable matrix of the target point to obtain an important feature variable matrix; The analysis and evaluation module is used to perform similarity analysis on the important characteristic variable matrix of the target point and the characteristic variable matrix of each potential point, and perform distance evaluation on the similarity analysis results to determine the target potential point corresponding to the target point.

9. A computer device, characterized in that: It includes a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the point information determination method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: It includes a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the point information determination method described in any one of claims 1-7.

Images