Micro-map personalized layout information mining method

Abstract

The invention provides a micro-map personalized layout information mining method, relates to related professional knowledge of image processing and map making, and solves the problem that common people are difficult to make maps due to lack of professional map knowledge. The method comprises the following steps: acquiring combination features and position features of map layout elements, and acquiring relation feature information among the layout elements so as to construct a micro-map layout knowledge base; according to the method for mining the personalized layout information of the map components, the distribution characteristics of the map components in the map can be effectively obtained, help is provided for common people lacking a map making basis, and the map making efficiency and the map quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of map making and image processing, and in particular to a method for mining personalized layout information of a micro map. Background Art

[0002] Maps are one of the important tools for transmitting information in addition to text and language. Traditional maps are drawn by professional cartographers using professional mapping tools after they understand the mapping needs. However, most map users are ordinary people, which makes it difficult for cartographers to fully understand the needs of users, let alone draw the ideal map in the eyes of users. Micro-maps (We-Map) are the expansion of traditional maps in the era of self-media, providing the possibility for ordinary people to make their own maps. As a "grassroots" map for the general public, it has the characteristics of micro content, low threshold, fast production and personalization, which means that cartographers do not need professional training and can draw and publish maps through personal electronic devices anytime and anywhere to complete information transmission.

[0003] Layout is a key factor affecting information transmission. High-quality map layout can effectively improve the communication efficiency of maps and enhance visual appeal. For the general public who lack professional map knowledge, it is a very difficult task to select and layout map elements under the premise of comprehensively considering the readability of the map, the transmission of information, and the aesthetics of the layout. However, since micro-maps provide cartographers with a low-threshold production method, cartographers can delete map components and adjust the element layout structure according to their personal wishes, resulting in a negative impact on the map's theme expression, content readability, and spatial information transmission. However, providing users with a reasonable layout framework or guiding suggestions has not been considered. Therefore, it is an urgent problem to build a knowledge base of micro-map element layout to assist the general public in drawing maps.

[0004] National invention patent CN202310098622.1 discloses an emergency map making method based on a mapping scheme set. In view of the large demand for emergency map making types and the high threshold for mapping, it proposes to make corresponding mapping schemes for different emergency mapping scenarios and form a mapping scheme set. The system can complete the automatic mapping method by selecting the mapping scheme that matches the mapping scenario, thereby improving the efficiency and timeliness of emergency map making. Although the method proposes map decoration rules, it only involves the fonts and styles of the decoration elements, and does not analyze the position characteristics of each element in the drawing and the spatial relationship between the elements. At the same time, the method proposes to count the frequency of use of each material in various mapping scenarios, but only includes various mapping scenarios in emergencies and does not analyze the combination of different materials in different scenarios. From this point of view, the automatic emergency map making method proposed by the invention cannot effectively lower the threshold for the general public who lack map expertise to draw personalized maps.

[0005] National invention patent CN202310183001.3 discloses a method and system for the decoration of thematic map outlines, which aims to automatically draw the standard map outlines of certain specific thematic maps, avoid multiple modifications to the outline decoration effects, and improve the professional and automated level of map production. However, its production process is only for the standard styles of certain specific thematic maps, such as clearly specifying the content of the annotations in the lower left and right corners, which does not reduce the personalized map production technology and cannot meet the needs of the general public for personalized map production technology. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method for mining personalized layout information of a micro-map, so as to overcome the technical defect that the general public needs to spend a lot of energy on layout adjustment when making maps due to lack of professional knowledge background.

[0007] To solve the above problems, the present invention provides a method for mining personalized layout information of micro-maps, which is used to reduce the difficulty of micro-map making, solve the technical problem that the drawn maps lack readability and aesthetics due to lack of mapping knowledge, fill the gap in the rules of personalized map layout elements in micro-map making, provide scientific layout strategies for mass mapping, and thus improve mapping efficiency and map quality.

[0008] To achieve the above objectives, the present invention adopts the following technical solutions:

[0009] A method for mining personalized layout information of micro-maps is characterized by including three parts: data screening, layout feature analysis and layout knowledge extraction. It aims to condense a set of micro-map element layout rules suitable for the general public based on the analysis of map cases that satisfy the public, so as to improve the effect of conveying information and enhancing design.

[0010] Preferably, the data screening includes map data screening and layout element screening to solve the problems of data not meeting the requirements and data duplication, and provide basic data for layout element analysis;

[0011] The map data screening refers to selecting a set of personalized map data for feature analysis of map layout elements;

[0012] The layout element screening refers to selecting elements that have an impact on map readability as objects of layout analysis and constructing layout element sample data.

[0013] Preferably, the layout feature analysis includes a layout element extraction and recognition module, a basic feature analysis module and a spatial relationship analysis module, which detects and classifies the basic components of all maps based on the layout element sample data, constructs a basic feature analysis model, and then mines the relationship features between elements;

[0014] The layout element extraction and identification module refers to automatically extracting layout elements in the map using layout element sample data and classifying the layout elements;

[0015] The basic feature analysis module is used to obtain element combination features and position features;

[0016] The spatial relationship analysis module understands the potential positions of layout elements by calculating the orientation, distance and overlapping relationship between elements.

[0017] Preferably, the layout knowledge extraction module specifically includes feature screening and cluster analysis;

[0018] The feature screening refers to selecting layout features with high public recognition based on user satisfaction evaluation results;

[0019] The cluster analysis refers to counting the frequency of occurrence of each layout feature. The higher the frequency, the higher the recognition. They are sorted according to the frequency and stored in the knowledge base.

[0020] Preferably, the map data screening specifically includes a personalized map data set and a sample data set;

[0021] The personalized map data set refers to a map data set that selects a personalized map other than a standard map and a map set as a map data set for mining layout information based on map readability;

[0022] The sample data set refers to some representative maps selected as sample data sets to reduce the cost of manual annotation and improve the accuracy of automatic standards to support layout element screening.

[0023] Preferably, the layout element extraction and identification module specifically includes layout element extraction and category identification, which is used to automatically extract layout elements in the map, aiming to improve annotation efficiency and reduce annotation costs;

[0024] The layout element extraction refers to automatically segmenting map entities according to layout element samples;

[0025] The layout element category recognition refers to realizing element classification by recognizing text information in layout elements.

[0026] Preferably, the basic feature analysis module specifically includes type structure analysis and spatial structure analysis of layout elements, so as to obtain element combination features and position features;

[0027] The type structure analysis of the layout elements refers to a method for calculating the combination characteristics of element types contained in each map;

[0028] The spatial structure analysis of the layout elements refers to a method for calculating the position characteristic value of each layout element in the map, and a description of the parameters involved in the calculation method.

[0029] Preferably, the spatial relationship analysis module specifically includes three submodules: orientation relationship, distance relationship and overlapping relationship, so as to solve the problem that cartographers without professional knowledge have difficulty in understanding the spatial layout of the map and the depth sorting of map elements;

[0030] The layout element distance relationship refers to a method for calculating the Euclidean distance between elements;

[0031] The layout element orientation relationship refers to a method for calculating the eight orientation relationships of elements;

[0032] The layout element overlapping relationship refers to selecting overlapping area, overlapping rate and IoU as factors for analyzing element overlapping relationship, and a calculation method of the two factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0034] Figure 1 A schematic diagram of the structure of the method for mining personalized layout information of micro-maps provided by the present invention;

[0035] Figure 2 A method for calculating the position characteristic value of a layout element provided by the present invention and a description diagram thereof;

[0036] Figure 3 A schematic diagram of the position characteristic values ​​of layout elements provided by the present invention;

[0037] Figure 4 A schematic diagram of an eight-direction cone model provided by the present invention;

[0038] Figure 5 This is an IoU example diagram provided by the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] The embodiment of the present invention discloses a method for mining personalized layout information of a micro map, which is characterized by comprising three parts: data screening, layout feature analysis, and layout knowledge extraction (such as Figure 1 As shown in the figure, it aims to condense a set of micro-map element layout rules suitable for the general public based on the analysis of map cases that satisfy the public, so as to improve the effect of conveying information and enhancing the design.

[0041] In order to further optimize the above technical solution, the data screening includes map data screening and layout element screening to solve the problems of data not meeting the requirements and data duplication, and provide basic data for layout element analysis;

[0042] The map data screening refers to selecting a set of personalized map data for feature analysis of map layout elements;

[0043] The layout element screening refers to selecting elements that have an impact on map readability as objects of layout analysis and constructing layout element sample data.

[0044] In order to further optimize the above technical solution, the layout feature analysis includes a layout element extraction and recognition module, a basic feature analysis module and a spatial relationship analysis module. Based on the layout element sample data, the basic components of all maps are detected and classified, a basic feature analysis model is constructed, and then the relationship features between elements are mined;

[0045] The layout element extraction and identification module refers to automatically extracting layout elements in the map using layout element sample data and classifying the layout elements;

[0046] The basic feature analysis module is used to obtain element combination features and position features;

[0047] The spatial relationship analysis module understands the potential positions of layout elements by calculating the orientation, distance and overlapping relationship between elements.

[0048] In order to further optimize the above technical solution, the layout knowledge extraction module specifically selects layout features with high public acceptance as layout knowledge, and constructs a layout knowledge base based on them.

[0049] In order to further optimize the above technical solution, the map data screening specifically includes a personalized map data set and a sample data set;

[0050] The personalized map data set refers to a map data set that selects a personalized map other than a standard map and a map set as a map data set for mining layout information based on map readability;

[0051] The sample data set refers to some representative maps selected as sample data sets to reduce the cost of manual annotation and improve the accuracy of automatic standards, so as to support the screening of layout elements;

[0052] More specifically, the sample data set selection method refers to selecting the 150 maps with the highest scores from the scoring results of satisfaction S, functionality F, explanatory E, aesthetics A, authenticity R, and comprehensiveness I according to the user satisfaction evaluation results, and eliminating the data that do not meet the requirements such as atlases, incomplete maps, and duplicate maps, and finally retaining 400 maps as sample data;

[0053] Furthermore, the user satisfaction evaluation only includes five evaluation indicators: satisfaction S, functionality F, explanatory E, aesthetics A, and authenticity R. According to the requirements of map readability, a comprehensive indicator is added. Comprehensiveness I is described as ;

[0054] More specifically, the layout elements in the layout element screening include the map body, map name, legend, compass, scale, description information and other elements.

[0055] In order to further optimize the above technical solution, the layout element extraction and identification module specifically includes layout element extraction and category identification, which is used to automatically extract layout elements in the map, aiming to improve annotation efficiency and reduce annotation costs;

[0056] The layout element extraction refers to automatically segmenting map entities according to layout element samples, and automatically extracting layout elements in all maps based on manually annotated element sample data;

[0057] More specifically, the main body of the map is the instance segmentation result, and the map name, legend, compass, scale, description information, and others are the target detection results (i.e., the minimum bounding box of the feature);

[0058] The layout element category recognition refers to realizing element classification by recognizing text information in the layout elements, using OCR technology to recognize text information in the layout elements and classify the elements;

[0059] In order to further optimize the above technical solution, the basic feature analysis module specifically includes type structure analysis and spatial structure analysis of layout elements to obtain element combination features and position features;

[0060] The type structure analysis of the layout elements refers to a method for calculating the combination characteristics of element types contained in each map, and obtaining the number and type of elements contained in each map by statistics;

[0061] The spatial structure analysis of the layout elements refers to the calculation method of the position characteristic value of each layout element in the map and the description of the parameters in the calculation method, such as Figure 2 , Figure 3 As shown, the feature values ​​involved include the minimum bounding box, the center point, and the distance from the edge of the image.

[0062] In order to further optimize the above technical solution, the spatial relationship analysis module specifically includes three sub-modules: distance relationship, orientation relationship and overlapping relationship. Considering that the map layout element is not a single individual, but a group composed of many individuals, the center point of the layout element is used for calculation when calculating the distance and orientation relationship. At the same time, considering that the map has the characteristics that the main body of the map is located in the middle of the map sheet and the remaining layout elements are located at the edge of the map sheet, when calculating the distance, orientation and overlapping relationship, the relationship between the remaining layout elements and the main body of the map is calculated;

[0063] The layout element distance relationship refers to the method of calculating the Euclidean distance between elements. The Euclidean distance D between two elements is described as

[0064] (1)

[0065] Among them, the center coordinates of the map body are , the center coordinates of the remaining elements 1 are ;

[0066] The layout element orientation relationship refers to a method for calculating the eight orientation relationships of elements, using an eight-direction cone model to obtain the orientation relationship between the remaining layout elements and the map body;

[0067] More specifically, the angle between the map body and the remaining layout elements is calculated based on the map body, and the orientation relationship of the elements is obtained according to the eight-direction cone model. The angle between the map body and the remaining layout elements is described as

[0068] (2)

[0069] Among them, the center coordinates of the map body are , the center coordinates of the remaining feature 2 are ;

[0070] like Figure 4 As shown, combined with the public's habit of describing the relationship between the figures, the eight directions of the eight-direction cone model are {right, upper right, upper, upper left, left, lower left, lower, lower right};

[0071] The overlapping relationship of the layout elements is designed to include characteristic values ​​including overlapping area, overlapping rate and IoU;

[0072] The overlapping area is described as

[0073] (3)

[0074] Among them, there are two sets 𝐴 and 𝐵, which are the main graphic area of ​​the map and the graphic area of ​​some other elements respectively;

[0075] The overlap ratio is described as

[0076] (4)

[0077] Among them, there are two sets 𝐴 and 𝐵, which are the main graphic area of ​​the map and the graphic area of ​​some other elements respectively;

[0078] like Figure 5 As shown, IoU is described as

[0079] (3)

[0080] Among them, there are two sets 𝐴 and 𝐵, which are the main graphic area of ​​the map and some other element graphic area respectively.

[0081] In order to further optimize the above technical solution, the layout knowledge extraction module specifically includes feature screening and cluster analysis;

[0082] The feature screening refers to selecting layout features corresponding to 1,000 maps with higher comprehensiveness based on the user satisfaction evaluation results;

[0083] The cluster analysis refers to performing cluster analysis on the screened layout features, counting the frequency of occurrence of each type of knowledge, sorting them according to the frequency of occurrence, and storing them in the knowledge base.

[0084] The micro-map intelligent production system and device provided by the present invention have the following characteristics:

[0085] (1) It overcomes the technical defect that the general public needs to spend a lot of energy on layout adjustment when making maps due to lack of professional knowledge background, thereby reducing the professional requirements for cartographers in micro-map production;

[0086] (2) It solves the time-consuming and laborious problem of manually annotating map layout elements, providing basic support for layout analysis;

[0087] (3) The influence of subjectivity in the knowledge extraction process is reduced. The layout knowledge is sorted according to satisfaction evaluation results and usage frequency, which effectively improves the universality of knowledge.

[0088] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0089] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for mining personalized layout information of a micro-map, characterized in that: include: The method for mining personalized layout information of micro-maps is used to solve the technical problem that micro-maps can be intelligently produced on mobile terminals in a self-media environment, and to solve the technical problem that the drawn maps lack readability and aesthetics due to lack of cartographic knowledge. The method is composed of data screening, layout feature analysis, and layout knowledge extraction. The data screening includes map data screening and layout element screening to solve the problems of data not meeting the requirements and data duplication, and provide basic data for layout element analysis; The layout feature analysis includes a layout element extraction and recognition module, a basic feature analysis module and a spatial relationship analysis module. Based on the layout element sample data, the basic components of all maps are detected and classified, a basic feature analysis model is constructed, and then the relationship features between elements are mined; The layout knowledge extraction module specifically selects layout features with high public acceptance as layout knowledge, and constructs a layout knowledge base based on them.

2. A method for mining personalized layout information of a micro map according to claim 1, characterized in that: The data screening includes: The map data screening refers to selecting a set of personalized map data for feature analysis of map layout elements; The layout element screening refers to selecting elements that have an impact on map readability as objects of layout analysis and constructing layout element sample data.

3. A method for mining personalized layout information of a micro map according to claim 1, characterized in that: The layout feature analysis includes: The layout element extraction and identification module refers to automatically extracting layout elements in the map using layout element sample data and classifying the layout elements; The basic feature analysis module is used to obtain element combination features and position features; The spatial relationship analysis module understands the potential positions of layout elements by calculating the orientation, distance and overlapping relationship between elements.

4. A method for mining personalized layout information of a micro map according to claim 1, characterized in that: The layout knowledge extraction module includes: The feature screening refers to selecting layout features with high public recognition based on user satisfaction evaluation results; The cluster analysis refers to counting the frequency of occurrence of each layout feature. The higher the frequency, the higher the recognition. They are sorted according to the frequency and stored in the knowledge base.

5. According to the method for mining personalized layout information of a micro map in claim 1 or 2, the map data screening specifically comprises: The personalized map data set refers to a map data set that selects personalized maps other than standard maps and atlases as map data sets for mining layout information based on map readability; The sample data set refers to some representative maps selected as sample data sets to reduce the cost of manual annotation and improve the accuracy of automatic standards, so as to support the screening of layout elements.

6. According to the method for mining personalized layout information of a micromap according to claim 1 or 3, the layout element extraction and recognition module specifically comprises: The layout element extraction refers to automatically segmenting map entities according to layout element samples; The layout element category recognition refers to realizing element classification by recognizing text information in layout elements.

7. According to the method for mining personalized layout information of a micromap according to claim 1 or 3, the basic feature analysis module specifically comprises: The type structure analysis of the layout elements refers to a method for calculating the combination characteristics of element types contained in each map; The spatial structure analysis of the layout elements refers to a method for calculating the position characteristic value of each layout element in the map, and a description of the parameters involved in the calculation method.

8. According to the method for mining personalized layout information of a micromap according to claim 1 or 3, the spatial relationship analysis module specifically comprises: The layout element distance relationship refers to a method for calculating the Euclidean distance between elements; The layout element orientation relationship refers to a method for calculating the eight orientation relationships of elements; The layout element overlapping relationship refers to selecting overlapping area, overlapping rate and IoU as factors for analyzing element overlapping relationship, and a calculation method of the two factors.

Images