Micro map evaluation method based on user perception

Abstract

The invention discloses a micro-map evaluation method based on user perception. The micro-map evaluation method comprises the following steps: establishing a five-dimensional integrated evaluation index system of a micro-map; an evaluation data set of each index based on user perception is constructed, the evaluation data set comprises a comparison evaluation data set and a direct scoring data set, and the direct scoring data set is constructed according to a comparison evaluation result; constructing a neural network model for micro map evaluation, and training an evaluation model by using the constructed data set; and evaluating the micro-map by using the trained evaluation model to obtain an evaluation result of the micro-map. According to the method provided by the invention, the self-media characteristic of the micro map is fully considered, and the method has relatively high efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of map evaluation, and more specifically to a micro-map evaluation method based on user perception, which is used to implement micro-map evaluation in the era of self-media. Background Art

[0002] The advent of the we-media era has stimulated the public's urgent desire to participate in map making, which has also led to the transformation of the main body of map making from professional cartographers to the general public. As a product of the we-media era, micro-maps effectively make up for the shortcomings of traditional maps in meeting the needs of the public. As a popular map product, the micro-map platform can well realize the general public's beautiful hope of making maps, disseminating maps, and using maps. Its core is the low threshold of the mapping group and the we-media nature of map dissemination, which enables the general public to easily make, disseminate and use maps just like creating and sharing we-media content (such as Weibo, Douyin, etc.).

[0003] However, in the dissemination and application of micro-maps, it is necessary to consider whether the map can accurately reflect spatial information and whether it can provide clear and easy-to-understand visual expressions. Only when the map has good accuracy, functionality and readability can it be more widely disseminated and used. Therefore, in order to improve the quality of user mapping, dissemination efficiency and user experience, and ensure the effectiveness of maps in various scenarios, it is necessary to conduct a comprehensive and accurate evaluation of the map.

[0004] The existing map evaluation mainly involves three categories: the first is to evaluate the map objectively, such as the mathematical accuracy, quality of main elements and correctness of structure, geographic accuracy and finishing quality of the map, such as the evaluation of high-impact vector maps. In addition, there is also an objective evaluation of map information. This method can well evaluate the professional quality of the map itself, but ignores the user participation in mapping, map use and map transmission in the context of mass mapping; the second is the map quality evaluation based on users, that is, considering the user's subjective feelings to conduct subjective evaluation of their maps, such as establishing an evaluation system for network maps from different angles in the evaluation system, and evaluating map information based on user perception. This type of method can well adapt to the needs of the current mass mapping background. However, for micro-maps in the era of self-media, the existing map evaluation system and methods cannot meet the evaluation needs of micro-maps, and a complete micro-map evaluation system and evaluation method need to be established.

[0005] Therefore, how to provide a micro-map evaluation method that fully considers user perception is an urgent problem that technicians in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a micro-map evaluation method based on user perception. Taking into account the overall user perception, the user's map perception characteristics of the micro-map are extracted from five aspects: functionality, reliability, aesthetics, illustrativeness, and satisfaction. The evaluation results of the micro-map under different evaluation dimensions are obtained, which solves the problem of the lack of micro-map evaluation methods in the era of self-media, so as to better serve the production and dissemination of micro-maps.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A method for evaluating a micro map based on user perception, comprising:

[0009] S 1: Based on Maslow's life needs, a five-dimensional evaluation index system for micro-maps is constructed;

[0010] S2: Based on the above micro-map evaluation index system, a micro-map evaluation dataset is constructed;

[0011] S3: Construct a micro-map evaluation neural network model and use the constructed micro-map evaluation dataset to train the model;

[0012] S4: Use the trained micro-map evaluation model to evaluate the micro-map and output the evaluation results.

[0013] Step S2 further comprises:

[0014] S21: Perform micro-map comparison and evaluation, determine the comparison results, and construct a micro-map comparison and evaluation data set; S22: Construct a micro-map comparison and evaluation network model, and use the micro-map comparison and evaluation data set constructed in S21 to train the micro-map comparison and rating network model;

[0015] S23: Use the trained micro-map comparison and evaluation network model to conduct comparative evaluation on all micro-map comparison groups;

[0016] S24: performing group statistics and normalization processing on the results of the micro-map comparative evaluation in S23 to obtain a micro-map evaluation data set.

[0017] Step S21 further comprises:

[0018] Step 1: Determine the comparison sequence of the data set

[0019] Using the deep clustering method, the map data is divided into 20 categories; in the ratio of 8:2, the comparison sequences of different categories and the same category are randomly selected.

[0020] Step 2: Data labeling

[0021] Before the labeling started, the volunteers were given a detailed explanation of the indicators for the micro-map evaluation to ensure the accuracy of data collection. The following prompts were given before each indicator started:

[0022] Thank you for participating in this micro-map evaluation experiment. Your participation is crucial to the research of micro-maps! Next, you will see multiple groups of map comparisons. Please make an intuitive choice based on your subjective feelings. If you think that map A has more certain characteristics, please choose A; if you think that map B has more certain characteristics, please choose B; if you think that map A and map B have the same characteristics or cannot be distinguished, please choose AB. Now start the map functionality selection.

[0023] After the volunteers fully understood the background of micro-map evaluation, these map comparison sequences were displayed one by one, allowing each volunteer to make a choice based on their own cognition. A warm-up mechanism was adopted, that is, before the formal selection began, 5 groups of comparison sequences were randomly selected for volunteers to conduct experiments, but no records were made.

[0024] Step 3: Data Processing

[0025] Use weighted method to select result statistics, Label i To compare the labels of sequence i, the calculation formula is as follows:

[0026]

[0027] Where P(A i )、P(B i )、P(AB i ), are the weighted values ​​of selecting A, B or AB for map comparison sequence i:

[0028]

[0029] Where W i (t A )、W i (t B )、W i (t AB ) represent the weighted values ​​of the selected time, and the calculation formula is as follows:

[0030]

[0031] Finally, the final label is determined through weighted statistics.

[0032] Step S24 further comprises:

[0033] Step 1: Weighted statistics

[0034] Count the number of times each micromap has been fully confirmed N A , confirmed as the same number of times as other map indicators N AB According to the statistical selection situation, the weighted selection times are calculated, and the calculation formula is shown in Formula 4.

[0035] N i =N A ×2+N AB ×1 (Formula 4)

[0036] Step 2: Normalization

[0037] The weighted selection times N are normalized to the range of 0-10, with two decimal places retained, as the final evaluation score of map i. The calculation formula is shown in Formula 5.

[0038]

[0039] Furthermore, the functionality of the micro map in the evaluation indicators of the micro map refers to the practicality of the map, including the accuracy of the map information, ease of use, and whether it can effectively help users achieve their search, navigation or analysis purposes; reliability refers to whether users can trust the map and which map they are more willing to believe that the information represented is true; aesthetics refers to the visual appeal of the map, including the harmony of color matching, element layout and overall design; illustrativeness refers to whether different users can understand the map more directly and clearly during the process of communicating using the map; satisfaction refers to whether users are satisfied with the overall evaluation of the map after combining other dimensions.

[0040] Furthermore, the micro-map comparative evaluation network model refers to a twin VMamba (visual state space network structure) composed of weight-shared twins.

[0041] Furthermore, the micro-map evaluation network model is composed of a KAN-Vmamba (Kolmogorov-Arnold visual state space network structure) network.

[0042] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses a micro-map evaluation method based on user perception, which is easy to implement and can accurately and efficiently evaluate micro-maps while fully considering user perception, thereby solving the problem that the existing map evaluation system and method cannot meet the evaluation needs of micro-maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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 in the following description are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0044] Figure 1 A flowchart of a micro-map evaluation method based on user perception provided by the present invention;

[0045] Figure 2 A schematic diagram of a micro-map comparison and evaluation network model provided by the present invention;

[0046] Figure 3 A schematic diagram of a micro-map evaluation network model provided by the present invention;

[0047] Figure 4 This is an effect diagram of the micro-map evaluation provided by the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] See attached Figure 1 The embodiment of the present invention discloses a micro-map evaluation method based on user perception, comprising:

[0050] The present invention is further described below in conjunction with the accompanying drawings and specific operating examples.

[0051] like Figure 1 As shown, in one example, a method for evaluating a mini-map based on user perception is provided. The evaluation method specifically includes the following steps S1 to S4.

[0052] S 1: Based on Maslow's life needs, a five-dimensional evaluation index system for micro-maps is constructed;

[0053] Specifically, the five-dimensional micro-map rating index system constructed in S1 includes the functionality, reliability, aesthetics, descriptiveness, and satisfaction of micro-maps.

[0054] S2: Based on the above micro-map evaluation index system, a micro-map evaluation dataset is constructed;

[0055] Specifically, S2 includes S21 to S24.

[0056] S21: Perform micro-map comparison and evaluation, determine the comparison results, and construct a micro-map comparison and evaluation data set;

[0057] S22: Construct a micro-map comparison and evaluation network model, and use the micro-map comparison and evaluation dataset constructed in S21 to train the micro-map comparison and rating network model;

[0058] S23: Use the trained micro-map comparison and evaluation network model to conduct comparative evaluation on all micro-map comparison groups;

[0059] S24: performing group statistics and normalization processing on the results of the micro-map comparative evaluation in S23 to obtain a micro-map evaluation data set.

[0060] S3: Construct a micro-map evaluation neural network model and use the constructed micro-map evaluation dataset to train the model;

[0061] S4: Use the trained micro-map evaluation model to evaluate the micro-map and output the evaluation results.

[0062] The method involved in the present invention is further explained.

[0063] The micro-map comparison evaluation model constructed for the comparison evaluation of micro-maps in S22 of the present invention is composed of two weight-sharing VMamba feature extraction layers, followed by MLP (multi-layer perception), and its structure is as follows: Figure 2 As shown in the figure, a set of maps that need to be compared and evaluated are extracted by VMamba, the features are spliced, and then the results of the comparative evaluation are obtained through MLP.

[0064] The micro-map evaluation model constructed for micro-map evaluation in S3 of the present invention is composed of KAN-VMamba, and its structure is as follows: Figure 3 That is, VMamba extracts features for micro-map evaluation, uses the extracted features as the input of the KAN network, performs evaluation regression, and finally obtains the evaluation results.

[0065] The results of the micro-map evaluation by the method provided by the present invention are shown in the attached Figure 4 .

[0066] 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.

[0067] 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 micro-map evaluation method based on user perception, characterized in that: include: S1: Based on Maslow's life needs, a five-dimensional evaluation index system for micro-maps is constructed; S2: Based on the above micro-map evaluation index system, a micro-map evaluation dataset is constructed; S3: Construct a micro-map evaluation neural network model and use the constructed micro-map evaluation dataset to train the model; S4: Use the trained micro-map evaluation model to evaluate the micro-map and output the evaluation results. Step S2 further comprises: S21: Perform micro-map comparison and evaluation, determine the comparison results, and construct a micro-map comparison and evaluation data set; S22: Construct a micro-map comparison and evaluation network model, and use the micro-map comparison and evaluation dataset constructed in S21 to train the micro-map comparison and rating network model; S23: Use the trained micro-map comparison and evaluation network model to conduct comparative evaluation on all micro-map comparison groups; S24: performing group statistics and normalization processing on the results of the micro-map comparative evaluation in S23 to obtain a micro-map evaluation data set.

2. A method for evaluating a micro map based on user perception according to claim 1, characterized in that: The five-dimensional evaluation index system of micromaps includes the functionality, reliability, aesthetics, explanation and safety of micromaps.

3. A method for evaluating a micro map based on user perception according to claim 2, characterized in that: In steps S2, S3 and S4, relevant evaluation is performed for each micro-map evaluation index.

4. The micro-map evaluation method based on user perception according to claim 1, characterized in that: The micromap evaluation dataset is constructed based on the evaluation of the micromap comparative evaluation model.

5. The micro-map evaluation method based on user perception according to claim 4 is characterized in that: The micro-map comparison and evaluation model uses a weight-shared twin VMamba network to extract micro-map comparison features, followed by feature splicing and fusion.

6. The method for evaluating a micro map based on user perception according to claim 1, characterized in that: The micro-map evaluation model uses VMamba for feature extraction, and KAN is used for feature regression.

Images