Child safety general study street space evaluation method and system based on big language model

Abstract

The invention belongs to the technical field of urban planning, and particularly relates to a children safety general study street space evaluation method and system based on a big language model. The method comprises the following steps: 1, constructing an initial data set of child general-learning road network data; 2, performing natural language description on the streetscape pictures in the initial data set by using a large language model, and extracting evaluation indexes related to child safety; 3, performing semantic analysis on the street scene image, and identifying and classifying various elements in a street space; street space data and the extracted evaluation indexes are integrated, and quantitative analysis of street space safety is achieved; 4, based on the quantitative analysis in the step 3, performing weight distribution on the evaluation indexes by adopting a machine learning algorithm, and comparing the result of the environment monitoring sensor with the evaluation result of the large language model; and 5, according to an evaluation result, proposing a targeted improvement suggestion. The method is used for solving the problems that in the prior art, the analysis process is not complex, errors are high, and data are difficult to quantify.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban planning, and particularly relates to a method and system for evaluating the space of children's safe school-route streets based on large language models. Background Art

[0002] With the continuous acceleration of the urbanization process, the issue of children's safety has increasingly become the focus of social attention. Especially during the process of children going to school, the safety of street space directly affects children's physical and mental health and growth environment. Although certain progress has been made in the field of children's safety in China, there are still many challenges in the evaluation of street space safety. Therefore, China has formulated a series of policies and measures regarding children's safety, urban planning, and traffic management, aiming to comprehensively improve the safety of children's school-route street space through technological innovation and policy guidance.

[0003] Currently, there are mainly the following several technical means for evaluating the space of children's safe school-route streets. First, it is questionnaire surveys and on-site investigations. Through questionnaire surveys and on-site investigations, spatial, temporal, and attribute data of children's school-route roads are obtained, and a spatial analysis network for school-route roads is constructed in combination with children's walking school-route characteristics. However, this method may have the defects of strong subjectivity and large workload in data collection and processing; second, it is ArcGIS spatial analysis. Based on ArcGIS, pedestrian accessibility evaluation is carried out, and the pedestrian accessibility of school-route roads is evaluated through line segment analysis and spatial analysis. However, this method may have the defects of high technical requirements and excessive dependence on professional knowledge and software support; finally, it is methods such as the analytic hierarchy process, entropy weight method, visibility analysis, and street view data analysis. These methods have difficulties such as complex analysis processes, high requirements for data quality, and difficulty in quantification.

[0004] The technology for evaluating the space of children's safe school-route streets based on large language models is a current research and application hotspot. This technology relies on artificial intelligence and big data analysis, can comprehensively evaluate street space, identify potential safety risks, and propose corresponding improvement measures. However, due to differences in urban planning, traffic conditions, population density, and cultural background in different regions, the application and development of the technology for evaluating the space of children's safe school-route streets face the problem of imbalance, and it is difficult to form a unified evaluation standard and effective management mechanism across the country. In addition, the current development of the technology for evaluating the space of children's safe school-route streets is limited by factors such as the comprehensiveness of data collection, the accuracy of evaluation models, and the practicality of evaluation results. Summary of the Invention

[0005] The present invention provides a method for evaluating the space of children's safe school-route streets based on large language models, so as to solve the problems in the prior art that either the analysis process is complex with high errors or the data is difficult to quantify.

[0006] The present invention provides a children's safe school commuting street space evaluation system based on a large language model to implement a children's safe school commuting street space evaluation method based on a large language model.

[0007] The present invention is implemented through the following technical solutions:

[0008] A children's safe school commuting street space evaluation method based on a large language model, the method comprising the following steps:

[0009] Step 1: Construct an initial dataset of children's school commuting road network data;

[0010] Step 2: Use the large language model to perform natural language descriptions on the street view pictures in the initial dataset and extract evaluation indicators related to children's safety;

[0011] Step 3: Perform semantic analysis on the street view images, identify and classify various elements in the street space; integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the street space safety;

[0012] Step 4: Based on the quantitative analysis in Step 3, use a machine learning algorithm to assign weights to the evaluation indicators and compare the results of the environmental monitoring sensors with the evaluation results of the large language model;

[0013] Step 5: According to the evaluation results, put forward targeted improvement suggestions.

[0014] Further, the specific content of Step 1 is as follows: extract the coordinates of the sampling points according to the children's school commuting road network data; secondly, crawl the street view picture data through the coordinates to construct an initial dataset of children's school commuting road network data.

[0015] Further, determine the analysis object and research area, and obtain the key nodes on the children's school commuting paths in the research area through Baidu Map, relevant literature, and questionnaires;

[0016] Use these coordinate points to crawl the street view picture data and construct an initial dataset specifically for the children's school commuting space to provide basic data for subsequent evaluation and analysis.

[0017] Further, the specific content of Step 2 is as follows: apply the large language model to perform natural language descriptions on the collected street view pictures and extract the key information of evaluation indicators related to the sidewalk width, traffic signal clarity, greening coverage rate and children's safety.

[0018] Further, the specific content of Step 3 is as follows: combine various elements in the street view image space with GIS to integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the street space safety.

[0019] Further, step 4 specifically involves using a machine learning algorithm to assign weights to the evaluation indicators and comparing the results of the environmental monitoring sensors with the evaluation results of the large language model.

[0020] Further, step 5 specifically involves suggestions including increasing the width of the sidewalk, improving the clarity of traffic signals, or increasing the greening coverage rate.

[0021] A child-safe school street space evaluation system based on a large language model, which uses the above-mentioned child-safe school street space evaluation method based on a large language model. The system includes:

[0022] Dataset construction module: Construct an initial dataset of child school road network data;

[0023] Evaluation indicator extraction module: Use the large language model to perform natural language descriptions on the street view images in the initial dataset and extract evaluation indicators related to child safety;

[0024] Quantitative analysis module: Perform semantic analysis on the street view images, identify and classify various elements in the street space; Integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the street space safety;

[0025] Evaluation result comparison module: Based on the quantitative analysis, use a machine learning algorithm to assign weights to the evaluation indicators and compare the results of the environmental monitoring sensors with the evaluation results of the large language model to ensure the objectivity and accuracy of the evaluation results;

[0026] Suggestion proposal module: Put forward targeted improvement suggestions according to the evaluation results.

[0027] A computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method is implemented.

[0028] A computer-readable storage medium stores a computer program therein. When the computer program is executed by a processor, the above-mentioned method is implemented.

[0029] The beneficial effects of the present invention are:

[0030] The large language model of the present invention can process and understand natural language data. Combining with the street view image technology, it can analyze text and visual information simultaneously and provide a more comprehensive evaluation.

[0031] Through automated data processing, the present invention reduces the workload of manual surveys and evaluations, and improves the efficiency and accuracy of the evaluation process.

[0032] The large language model of the present invention can perform fine-grained sentiment analysis, identify the specific feelings and needs of children and parents regarding the school commute streets, and provide more accurate guidance for design.

[0033] The street view image technology of the present invention can be updated in real time, and combined with the large language model, it can dynamically monitor and evaluate the changes and impacts of children's school commute streets.

[0034] The large language model of the present invention combined with street view images can automatically process a large amount of data, process street view images in real time, conduct real-time evaluation of the street space, and quickly analyze multiple dimensions of the street space, greatly improving the evaluation efficiency compared with manual scoring.

[0035] The evaluation process of the large language model of the present invention reduces the interference of human subjective factors, making the evaluation results more objective and consistent. The automated evaluation method can be easily repeated, ensuring the repeatability of the evaluation process, while manual scoring is often affected by personal state and environment and it is difficult to ensure complete consistency.

[0036] The present invention uses the large language model to intelligently assign weights according to language instructions and the content of street view images, making the evaluation results more accurately reflect the actual situation of the children's safe school commute street space. In addition, the large language model can incorporate various external knowledge into the reasoning process, improving the positioning accuracy while promoting the reasoning ability in the geographical positioning process of street view images, which helps to more reasonably assign weights. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of the method of the present invention.

[0038] Figure 2 is a schematic diagram of the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0040] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0041] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0042] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings of the specification of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0043] Many specific details are set forth in the following description in order to fully understand this application, but this application can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of this application. Therefore, this application is not limited by the specific embodiments disclosed below.

[0044] Embodiment 1

[0045] This embodiment provides a method for evaluating the space of a children's safe school commute street based on a large language model. As Figure 1 shown, the method includes the following steps:

[0046] Step 1: Construct an initial dataset of children's school commute road network data;

[0047] Step 2: Use the large language model to perform natural language description on the street view pictures in the initial dataset, and extract evaluation indicators related to children's safety;

[0048] Step 3: Perform semantic analysis on the street view images, identify and classify various elements in the street space; integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the street space safety;

[0049] Step 4: Based on the quantitative analysis in Step 3, use a machine learning algorithm to assign weights to the evaluation indicators, and compare the results of the environmental monitoring sensors with the evaluation results of the large language model to ensure the objectivity and accuracy of the evaluation results;

[0050] Step 5: According to the evaluation results, put forward targeted improvement suggestions.

[0051] Further, the specific content of Step 1 is as follows: extract the coordinates of the sampling points according to the children's school commute road network data; secondly, crawl the street view picture data through the coordinates to construct an initial dataset of children's school commute road network data.

[0052] Furthermore, determine the analysis object and research area, and obtain the relevant data of the blocks at key nodes on the children's school commuting routes in the research area, such as schools, residential areas, main intersections, etc. from Baidu Maps, relevant literature, and questionnaires.

[0053] Using these coordinate points, crawl street view image data through the Baidu Street View API to construct an initial dataset specifically for children's school commuting space, providing basic data for subsequent evaluation and analysis.

[0054] Furthermore, the specific steps of step 2 are as follows: Apply a large language model to perform natural language descriptions on the collected street view images, and extract key information on evaluation indicators related to children's safety, such as sidewalk width, traffic signal clarity, greening coverage rate, etc.

[0055] Furthermore, the specific steps of step 3 are as follows: Integrate various elements in the street view image space with GIS to integrate street space data and the extracted evaluation indicators, and realize quantitative analysis of the safety of the street space.

[0056] The specific steps are as follows:

[0057] GIS spatial data association: Match the indicators extracted in step 2 with the geographical data (road network, POI points, traffic flow data) in the GIS system. Associate the coordinates of each street view image with the road layer in GIS to establish a spatial database.

[0058] Spatial overlay analysis: Overlay multi-source data (safety indicator layer, traffic flow layer, school distribution layer) in GIS, and identify potential safety hazard areas through heat map analysis.

[0059] Indicator quantification modeling: Combine the extracted indicators (such as the numerical value of "sidewalk width" and greening coverage rate) with the GIS attribute table, and then construct a safety scoring model to calculate the safety score of the street section.

[0060] Visualization and verification: Use the GIS map to display the safety scoring results, and verify the accuracy of the analysis results through on-site investigations or sensor data.

[0061] Furthermore, the specific steps of step 4 are as follows: Adopt a machine learning algorithm to assign weights to the evaluation indicators, and compare the results of the environmental monitoring sensors with the evaluation results of the large language model.

[0062] The specific steps are as follows:

[0063] Data preparation: First, extract multiple evaluation indicators from street view images through a large language model, including sidewalk width, traffic signal clarity, and greening coverage rate. Secondly, collect relevant environmental data through environmental monitoring sensors, including traffic flow, air quality, and noise level.

[0064] Feature selection and data preprocessing: Preprocess the extracted evaluation indicators to ensure that the data format and type are consistent, eliminate redundant information, and perform operations such as filling missing values, standardization, and normalization on the main clause tense.

[0065] Establish a machine learning model: Use the random forest learning model to assign weights to the evaluation indicators. Identify the impact degree of each indicator on the child-safe school commuting street through pre-training, and give the weight of each indicator according to the model training results.

[0066] Compare with the results of environmental monitoring sensors: Compare the results of the machine learning model with the data of environmental monitoring sensors to verify the accuracy and actual effect of the model (such as comparing the traffic flow data measured by the sensor with the traffic sign information extracted by the large language model, and matching the noise exceeding the standard measured by the sensor with the high-risk road sections predicted by the model to check whether there is a causal relationship).

[0067] Optimization and improvement: Based on the model training results, further optimize the weight assignment to ensure that the model more accurately reflects the safety of the street.

[0068] Furthermore, the specific content of step 5 is that the suggestions include increasing the width of the sidewalk, improving the clarity of traffic signals, or increasing the greening coverage rate.

[0069] The present invention can provide an evaluation tool for child-safe school commuting streets based on a large language model for urban planners, traffic management departments, and educational institutions, helping them identify and improve safety issues during children's school commuting, thereby improving the overall safety of child school commuting streets.

[0070] The difference between the evaluation index elements of child school commuting streets and ordinary streets in establishing is as follows:

[0071]

[0072] In the urban planning and design stage, the method provided by the present invention can be used to evaluate and plan child-friendly school commuting routes to ensure the safety of children during school and after-school trips. Through this method, urban planners can identify potential dangerous areas and design safer and more suitable school commuting paths for children.

[0073] In terms of policy formulation, the present invention can provide data support for the government and decision-makers to help them formulate relevant policies and standards. These policies and standards will focus on improving the safety of the child school commuting environment, thereby providing a safer growth environment for children.

[0074] In the improvement project of the school surrounding environment, the method of the present invention can be used to evaluate and optimize the school commuting environment. Through this method, potential safety hazards around the school can be identified, and corresponding measures can be taken for improvement, such as adding sidewalks, improving traffic signals, enhancing green coverage, etc., to create a safer and more comfortable educational environment.

[0075] In community development projects, the method of the present invention can also consider the school commuting needs of children and improve the overall quality of life in the community. By evaluating the school commuting routes within the community, it can be ensured that community planning fully takes into account the safety and convenience of children, thereby promoting the harmonious development of the community and improving the satisfaction and quality of life of residents.

[0076] Embodiment 2

[0077] The embodiment of the present invention provides a children's safe school commuting street space evaluation system based on a large language model. The system uses the children's safe school commuting street space evaluation method based on a large language model as described in Embodiment 1. The system includes:

[0078] Dataset construction module: Construct an initial dataset of children's school commuting road network data;

[0079] Evaluation index extraction module: Use a large language model to perform natural language description on the street view pictures in the initial dataset, and extract evaluation indexes related to children's safety;

[0080] Quantitative analysis module: Perform semantic analysis on street view images, identify and classify various elements in the street space; Integrate the street space data with the extracted evaluation indexes to achieve quantitative analysis of the safety of the street space;

[0081] Evaluation result comparison module: Based on quantitative analysis, use machine learning algorithms to assign weights to evaluation indexes, and compare the results of environmental monitoring sensors with the evaluation results of the large language model to ensure the objectivity and accuracy of the evaluation results;

[0082] Suggestion generation module: According to the evaluation results, put forward targeted improvement suggestions.

[0083] As Figure 2 shown, determine the analysis object and research area, and obtain block-related data of key nodes on the children's school commuting path in the research area through Baidu Map, relevant literature, and questionnaires, such as schools, residential areas, main intersections, etc.

[0084] Using these coordinate points, crawl street view picture data through an automated tool to construct an initial dataset specifically for children's school commuting space, providing basic data for subsequent evaluation and analysis.

[0085] Use large language models to generate natural language descriptions of the collected street view images, and extract evaluation indicators related to children's safety, such as key information like sidewalk width, traffic signal clarity, greening coverage rate, etc.

[0086] Through natural language processing technology, conduct in-depth semantic analysis of street view images, identify and classify various elements in the school commute street space, and provide support for the extraction of evaluation indicators.

[0087] Combine GIS technology to integrate street space data with the evaluation indicators extracted by large language models, realize quantitative analysis of the safety of street space, and thus evaluate the suitability of street space for children's school commute.

[0088] Adopt machine learning algorithms to assign weights to evaluation indicators to ensure the objectivity and accuracy of evaluation results. At the same time, compare the results of environmental monitoring sensors with the evaluation results of large language models to further verify the accuracy of the evaluation.

[0089] Based on the evaluation results, put forward targeted improvement suggestions to enhance the safety of children's school commute street space. These suggestions may include specific measures such as increasing sidewalk width, improving traffic signal clarity, and raising greening coverage rate.

[0090] The present invention can provide an evaluation tool for children's safe school commute street space based on large language models for urban planners, traffic management departments, and educational institutions, helping them identify and improve safety issues during children's school commute, thereby enhancing the overall safety of children's school commute streets.

[0091] As can be seen from the above, in the implementation mode of the present invention, during the urban planning and design stage, the method provided by the present invention can be used to evaluate and plan child-friendly school commute routes to ensure the safety of children during their going-to-school and coming-home journeys. Through this method, urban planners can identify potential dangerous areas and design safer and more suitable school commute paths for children.

[0092] In terms of policy formulation, the present invention can provide data support for the government and decision-makers to help them formulate relevant policies and standards. These policies and standards will focus on improving the safety of children's school commute environment, thereby providing a safer growth environment for children.

[0093] In the improvement projects of the school surrounding environment, the method of the present invention can be used to evaluate and optimize the school commute environment. Through this method, safety hazards around the school can be identified, and corresponding measures can be taken for improvement, such as increasing sidewalks, improving traffic signals, enhancing greening coverage, etc., to create a safer and more comfortable educational environment.

[0094] Embodiment 3

[0095] An embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. Among them, the memory is used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory and the processor are connected by a bus. Specifically, when the processor runs the above computer program stored in the memory, any step in the first embodiment is implemented.

[0096] It should be understood that in the embodiment of the present invention, the so-called processor may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0097] The memory may include a read-only memory, a flash memory, and a random access memory, and provide instructions and data to the processor. A part or all of the memory may also include a non-volatile random access memory.

[0098] As can be seen from the above, the electronic device provided by the embodiment of the present invention can implement the method for evaluating the safe school commuting street space based on the large language model as described in the first embodiment by running a computer program. In the urban planning and design stage, the method provided by the present invention can be used to evaluate and plan child-friendly school commuting routes to ensure the safety of children on their way to and from school. Through this method, urban planners can identify potential dangerous areas and design safer and more child-friendly school commuting paths.

[0099] It should be understood that if the above integrated modules / units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiments of the method of the present invention, it can also be completed by a computer program instructing relevant hardware. The above computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the above computer program includes computer program code, and the above computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The above computer-readable medium can include: any entity or device capable of carrying the above computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the above computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0100] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0101] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0102] It should be noted that the methods and their detailed examples provided in the above embodiments can be combined with the devices and equipment provided in the embodiments, and can be referred to each other, and will not be elaborated here.

[0103] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0104] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / equipment embodiments described above are only illustrative. For example, the above division of modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0105] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating the space of a child-safe school commuting street based on a large language model, characterized in that The method includes the following steps: Step 1: Construct an initial dataset of children's school commute road network data; Step 2: Use a large language model to perform natural language descriptions on the street view images in the initial dataset, and extract evaluation indicators related to children's safety; Step 3: Conduct semantic analysis on the street view images, identify and classify various elements in the street space; integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the safety of the street space; Step 4: Based on the quantitative analysis in Step 3, use a machine learning algorithm to assign weights to the evaluation indicators, and compare the results of the environmental monitoring sensors with the evaluation results of the large language model; Step 5: According to the evaluation results, put forward targeted improvement suggestions.

2. The method according to claim 1, wherein Specifically, for Step 1, extract the coordinates of the sampling points according to the children's school commute road network data; secondly, crawl the street view image data through the coordinates to construct an initial dataset of children's school commute road network data.

3. The method according to claim 2, wherein Determine the analysis object and research area, and obtain the key nodes on the children's school commute paths in the research area through Baidu Map, relevant literature, and questionnaires; Use these coordinate points to crawl the street view image data and construct an initial dataset specifically for the children's school commute space, providing basic data for subsequent evaluation and analysis.

4. The method according to claim 2, wherein Specifically, for Step 2, apply a large language model to perform natural language descriptions on the collected street view images, and extract the key information of evaluation indicators related to the sidewalk width, traffic signal clarity, greening coverage rate, and children's safety.

5. The method according to claim 1, wherein Specifically, for Step 3, combine various elements in the street view image space with GIS to integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the safety of the street space.

6. The method according to claim 5, characterized in that Specifically, for Step 4, use a machine learning algorithm to assign weights to the evaluation indicators, and compare the results of the environmental monitoring sensors with the evaluation results of the large language model.

7. The method according to claim 5, wherein Specifically, for Step 5, the suggestions include increasing the sidewalk width, improving traffic signal clarity, or increasing the greening coverage rate.

8. A children's safe school commuting street space evaluation system based on large language models, characterized in that, The system uses the method for evaluating the children's safe school commute street space based on a large language model as described in any one of claims 1-7. The system includes: A dataset construction module: Construct an initial dataset of children's school commute road network data; An evaluation indicator extraction module: Use a large language model to perform natural language descriptions on the street view images in the initial dataset, and extract evaluation indicators related to children's safety; A quantitative analysis module: Conduct semantic analysis on the street view images, identify and classify various elements in the street space; integrate the street space data with the extracted evaluation indicators to achieve quantitative analysis of the safety of the street space; An evaluation result comparison module: Based on the quantitative analysis, use a machine learning algorithm to assign weights to the evaluation indicators, and compare the results of the environmental monitoring sensors with the evaluation results of the large language model; A suggestion proposal module: According to the evaluation results, put forward targeted improvement suggestions.

9. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method as described in any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1-7 is implemented.

Images