Data preparation method and device for use scheme recommendation of low-code GIS (Geographic Information System)

Abstract

The invention provides a data preparation method and device for low-code GIS system use scheme recommendation, and relates to the technical field of geographic information systems. The scheme structured data generated by the method comprises the fields of scheme classification, scheme description, coded data marked with a user operation sequence, a scheme coding structure, data corresponding to a preset scheme execution efficiency index, data corresponding to a preset scheme used condition index and the like. The rich data dimensions enable a preset large model to more accurately understand user requirements when performing multiple rounds of dialogues with the user after learning training, find the most appropriate scheme under the corresponding classification according to the user requirements, and optimize and improve the scheme according to dialogue content.

Description

Technical Field

[0001] This application relates to the technical field of geographic information systems, and particularly to a data preparation method and device for recommending usage scenarios of a low-code GIS system. Background Art

[0002] With the wide application of GIS (Geographic Information System) technology, low-code GIS systems, with their "building block" style function combination mode, have greatly reduced the technical threshold for GIS application development, enabling non-professional technical personnel to also participate in the creation of GIS applications. However, many problems have emerged in practical applications. Here, a low-code GIS system is an innovative platform that combines the concept of low-code development with GIS technology. It significantly reduces the coding workload required for traditional GIS application development through a graphical interface, visual drag-and-drop operations, and pre-set function modules.

[0003] The functions of low-code GIS systems are relatively complex, consisting of multiple modules, and each module is further subdivided into numerous sub-functions. Taking the calculation module as an example, it has the calculation function of processing data in a pipeline, which includes various specific sub-functions such as generating a surface from points, judging point fences, generating attribution areas, and planning sales visits. There are also different combination methods and structures between each function. Such a complex function system undoubtedly poses a huge challenge to users' learning and use. Users often need to spend a lot of time getting familiar with the uses and interrelationships of each module and sub-function in order to build a GIS application that meets their own needs.

[0004] To reduce the usage cost for users, scenario recommendations can be made through large models. However, existing data forms (such as low-code GIS system usage tutorials or documents, etc.) are difficult for large models to fully learn the historical usage of the system, and thus cannot give efficient and accurate system usage scenarios. Therefore, in the face of the deficiencies in data preparation for usage scenario recommendations of low-code GIS systems, there is an urgent need to propose a comprehensive and innovative data preparation method, aiming to optimize the learning and training data of large models, so as to achieve efficient and accurate system usage scenario recommendations. Summary of the Invention

[0005] In view of the above problems, this application is proposed to provide a data preparation method and device, an electronic device, and a storage medium for recommending usage scenarios of a low-code GIS system that overcome the above problems or at least partially solve the above problems. The technical solutions are as follows: In a first aspect, a data preparation method for recommending usage scenarios of a low-code GIS system is provided, and the method includes: Receiving the scenario content submitted by the user, where the scenario content includes scenario classification and scenario description; In response to the user's operation on the solution editing interface of the low-code GIS system for the solution content, encode the operation on the solution editing interface of the low-code GIS system according to the pre-constructed basic coding layer and extended coding layer to generate coding data marked with the user operation sequence. Among them, the basic coding layer includes business processes, functional modules, sub-functions, and operation types, and the extended coding layer includes operation time, low-code GIS system version number, and user role; Generate a solution coding structure according to the structural relationship between the functional modules and sub-functions in the coding data marked with the user operation sequence; Use a predefined data set to test the solution, execute the solution according to the coding data marked with the user operation sequence, and during the execution process, collect data corresponding to the preset solution execution efficiency indicators according to the preset solution execution efficiency indicators; If the solution test passes, receive the solution release instruction submitted by the user, release the tested solution, and after the release, collect data corresponding to the preset solution usage situation indicators according to the preset solution usage situation indicators; Structurally store the solution classification, the solution description, the coding data marked with the user operation sequence, the solution coding structure, the data corresponding to the preset solution execution efficiency indicators, and the data corresponding to the preset solution usage situation indicators to generate solution structured data.

[0006] In a possible implementation manner, after generating the solution structured data, the method further includes: Use the solution structured data as sample training data to train a preset large model to obtain a trained low-code GIS system usage solution recommendation model; Receive the user's question about using the low-code GIS system, submit the user's question to the trained low-code GIS system usage solution recommendation model, and output the low-code GIS system usage recommendation solution corresponding to the user's question.

[0007] In a possible implementation manner, the solution description is represented by natural language.

[0008] In a possible implementation manner, the preset solution execution efficiency indicators include one or more of CPU usage rate, memory occupancy rate, and network traffic.

[0009] In a possible implementation manner, the preset solution usage situation indicators include one or more of the number of times the solution is used, the number of times the solution is liked, and the solution recommendation level.

[0010] In a possible implementation manner, if the solution test passes, the method further includes: Bind and store the collected data of the preset scheme execution efficiency indicators with the scheme classification, the scheme description, the encoded data marked with the user operation sequence, and the scheme encoding structure, and display the test results, where the test results include whether the user's scheme runs successfully and the details of each indicator.

[0011] In a possible implementation, the method further includes: If the scheme test fails, generate a prompt message indicating that there is a problem with the user's scheme, and guide the user to return to the scheme editing interface of the low-code GIS system for modification.

[0012] In a second aspect, a data preparation device for recommending a usage scheme of a low-code GIS system is provided. The device includes: A receiving unit, configured to receive the scheme content submitted by the user, where the scheme content includes a scheme classification and a scheme description; A first generating unit, configured to, in response to an operation of the user on the scheme editing interface of the low-code GIS system for the scheme content, encode the operation on the scheme editing interface of the low-code GIS system according to a pre-constructed basic coding layer and an extended coding layer, and generate encoded data marked with the user operation sequence. Among them, the basic coding layer includes a business process, a function module, a sub-function, and an operation type, and the extended coding layer includes an operation time, a low-code GIS system version number, and a user role; A second generating unit, configured to generate a scheme coding structure according to the structural relationship between the function module and the sub-function in the encoded data marked with the user operation sequence; A testing unit, configured to test the scheme using a predefined data set, execute the scheme according to the encoded data marked with the user operation sequence, and collect data corresponding to the preset scheme execution efficiency indicators according to the preset scheme execution efficiency indicators during the execution process; A publishing unit, configured to, if the scheme test passes, receive the scheme publishing instruction submitted by the user, publish the tested scheme, and collect data corresponding to the preset scheme usage situation indicators according to the preset scheme usage situation indicators after the publishing; A third generating unit, configured to structurally store the scheme classification, the scheme description, the encoded data marked with the user operation sequence, the scheme coding structure, the data corresponding to the preset scheme execution efficiency indicators, and the data corresponding to the preset scheme usage situation indicators, and generate scheme structured data.

[0013] In a third aspect, an electronic device is provided, which includes a processor and a memory. Among them, a computer program is stored in the memory, and the processor is configured to run the computer program to execute the data preparation method recommended by the low-code GIS system usage scenario described in any one of the above.

[0014] In a fourth aspect, a storage medium is provided. The storage medium stores a computer program, where the computer program is configured to execute the data preparation method recommended by the low-code GIS system usage scenario described in any one of the above when running.

[0015] With the above technical solution, the data preparation method, device, electronic device, and storage medium recommended by the low-code GIS system usage solution provided by the embodiments of the present application. For the data preparation method recommended by the low-code GIS system usage solution, first, the solution content submitted by the user is received. The solution content includes solution classification and solution description, which provides rich semantic information for the large model to understand the core meaning of the solution, enabling the large model to better grasp the overall intention of the solution during the learning and training process, rather than being limited to the implementation level of functions only. Then, in response to the user's operation on the solution editing interface of the low-code GIS system for the solution content, according to the pre-constructed basic coding layer and extended coding layer, the operation on the solution editing interface of the low-code GIS system is coded to generate coded data marked with the user's operation sequence. From the perspective of the learning efficiency and accuracy of the large model, through the coding of the operation process, the learning efficiency of the large model is greatly improved. Next, the solution is tested using a pre-defined data set. The solution is executed according to the coded data marked with the user's operation sequence, and during the execution process, according to the preset solution execution efficiency indicators, the data corresponding to the preset solution execution efficiency indicators is collected to determine whether the solution can run normally and collect various indicators related to the solution execution efficiency, such as processing speed and various resource occupancy situations, etc. Then, these indicators are bound to the coding combination. This step provides important data on the solution performance for the large model, enabling it to comprehensively consider the feasibility and efficiency of the solution when recommending solutions. After that, if the solution passes the test, the solution release instruction submitted by the user is received, and the tested solution is released. After the release, according to the preset solution usage situation indicators, the data corresponding to the preset solution usage situation indicators is collected. Only the solution that has been tested and ensured to be correct can be released, so that the collected coded data has practical significance and value, avoiding the interference of invalid or incorrect data on the large model learning, and collecting user adoption-related data such as the usage volume and the number of likes of the user's public solution. Since the solution is saved in coded form at the bottom layer, that is, the usage volume of the coding combination is collected, which helps the large model understand which coding combinations are more popular among users, so as to discover efficient and practical solution patterns.Finally, classify the solutions, description of the solutions, encoded data marked with the user operation sequence, solution encoding structure, data corresponding to the preset solution execution efficiency index, and data corresponding to the preset solution usage situation index for structured storage to generate solution structured data. In this way, the solution-related data and their encodings collected are cleaned, unified, and sorted, and saved in structured storage. The formed solution structured data includes fields such as solution classification, solution description, encoded data marked with the user operation sequence, solution encoding structure, data corresponding to the preset solution execution efficiency index, and data corresponding to the preset solution usage situation index. These rich data dimensions enable the preset large model to more accurately understand the user's needs during multi-round conversations with the user, find the most suitable solution under the corresponding classification according to the user's needs, and optimize and improve the solution based on the conversation content. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the description of the embodiments of the present application will be briefly introduced below.

[0017] Figure 1 Shows a flowchart of a data preparation method for recommending solutions for a low-code GIS system provided by an embodiment of the present application; Figure 2 Shows a schematic diagram of the solution structured data provided by an embodiment of the present application; Figure 3 Shows a structural diagram of a data preparation device for recommending solutions for a low-code GIS system provided by an embodiment of the present application; Figure 4 Shows a structural diagram of a data preparation device for recommending solutions for a low-code GIS system provided by another embodiment of the present application; Figure 5 Shows a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0019] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such use can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the term "including" and its variants should be interpreted as open-ended terms meaning "including but not limited to".

[0020] To solve the above technical problems, an embodiment of the present application provides a data preparation method for recommending a low-code GIS system usage plan, as Figure 1 shown. The data preparation method for recommending a low-code GIS system usage plan may include the following steps S101 to S106: Step S101, receiving the plan content submitted by the user, where the plan content includes a plan classification and a plan description.

[0021] In this step, both the plan classification and the plan description can be represented by natural language.

[0022] For example, on the operation interface of the low-code GIS system, a dedicated plan creation entry is provided for the user. After the user enters this entry, the system guides the user to classify the plan to be created, and the classification options can be preset as common business categories, such as "Insight Analysis", "Sales Route Planning", "Data Standardization", etc. At the same time, a text box is provided for the user to write a plan description, elaborating on the description information such as the goal and applicable scenario of the plan. For example, a user engaged in market analysis creates a plan for analyzing the market in a specific area, selects "Insight Analysis" in the classification, and writes in the description "This plan aims to plan the key areas for market promotion by analyzing data such as population density and consumption capacity in different regions of a certain city", and the system saves the plan classification and description information input by the user in real time.

[0023] Step S102, in response to the user's operation on the plan editing interface of the low-code GIS system for the plan content, encoding the operation on the plan editing interface of the low-code GIS system according to the pre-constructed basic coding layer and extended coding layer to generate coding data marked with the user operation sequence, where the basic coding layer includes business processes, functional modules, sub-functions and operation types, and the extended coding layer includes operation time, low-code GIS system version number and user role.

[0024] Step S103, generating a plan coding structure according to the structural relationship between the functional modules and sub-functions in the coding data marked with the user operation sequence.

[0025] Step S104: Test the solution using a predefined dataset. Execute the solution according to the encoded data marked with the user operation sequence. During the execution process, collect the data corresponding to the preset solution execution efficiency metrics according to the preset solution execution efficiency metrics.

[0026] In this step, the predefined dataset may include Dataset 1, Dataset 2, Dataset 3, etc. For multiple solutions in the same solution classification, the same dataset can be used for testing. For example, there are 3 solutions in solution classification a, and these 3 solutions are all tested using Dataset 1; there are 5 solutions in solution classification b, and these 5 solutions are all tested using Dataset 2. It should be noted that the examples listed here are only illustrative and do not limit this embodiment.

[0027] The preset solution execution efficiency metrics may include processing speed, CPU (Central Processing Unit) usage rate, memory occupancy rate, network traffic, etc. This embodiment does not limit this.

[0028] Step S105: If the solution passes the test, receive the solution release instruction submitted by the user, release the solution that has passed the test, and after the release, collect the data corresponding to the preset solution usage metrics according to the preset solution usage metrics.

[0029] In this step, the preset solution usage metrics may include the number of times the solution is used, the number of times the solution is liked, the solution recommendation level, etc. This embodiment does not limit this.

[0030] Step S106: Structurally store the solution classification, solution description, encoded data marked with the user operation sequence, solution encoding structure, data corresponding to the preset solution execution efficiency metrics, and data corresponding to the preset solution usage metrics to generate solution structured data.

[0031] In the data preparation method recommended by the low-code GIS system usage plan provided in this embodiment, first, the plan content submitted by the user is received. The plan content includes plan classification and plan description, which provides rich semantic information for the large model to understand the core meaning of the plan, enabling the large model to better grasp the overall intention of the plan during the learning and training process, rather than being limited to the implementation level of functions only. Then, in response to the user's operation on the plan content in the plan editing interface of the low-code GIS system, based on the pre-constructed basic coding layer and extended coding layer, the operation in the plan editing interface of the low-code GIS system is coded to generate coded data marked with the user's operation sequence. From the perspective of the learning efficiency and accuracy of the large model, through the coding of the operation process, the learning efficiency of the large model is greatly improved. Next, the plan is tested using a predefined data set. The plan is executed according to the coded data marked with the user's operation sequence, and during the execution process, according to the preset plan execution efficiency indicators, the data corresponding to the preset plan execution efficiency indicators is collected to determine whether the plan can run normally and collect various indicators related to the plan execution efficiency, such as processing speed and various resource occupancy situations, etc. Then, these indicators are bound to the coding combination. This step provides important data on the plan performance for the large model, enabling it to comprehensively consider the feasibility and efficiency of the plan when recommending plans. After that, if the plan passes the test, the plan release instruction submitted by the user is received, and the plan that passes the test is released. After the release, according to the preset plan usage situation indicators, the data corresponding to the preset plan usage situation indicators is collected. Only the plan that has been tested and ensured to be correct can be released, so that the collected coded data has practical significance and value, avoiding the interference of invalid or incorrect data on the learning of the large model, and collecting user adoption-related data such as the usage amount and the number of likes of the user's public plan. Since the plan is stored in coded form at the bottom layer, that is, the usage amount of the coding combination is collected, which helps the large model understand which coding combinations are more popular among users, so as to discover efficient and practical plan patterns. Finally, the plan classification, plan description, coded data marked with the user's operation sequence, plan coding structure, data corresponding to the preset plan execution efficiency indicators, and data corresponding to the preset plan usage situation indicators are stored in a structured manner to generate plan structured data. In this way, the collected plan-related data and its coding are cleaned, unified, and sorted, and saved in structured storage. The formed plan structured data includes fields such as plan classification, plan description, coded data marked with the user's operation sequence, plan coding structure, data corresponding to the preset plan execution efficiency indicators, and data corresponding to the preset plan usage situation indicators. These rich data dimensions enable the preset large model to more accurately understand the user's needs during multiple rounds of conversations with the user, find the most suitable plan under the corresponding classification according to the user's needs, and optimize and improve the plan according to the conversation content.

[0032] In an embodiment of the present application, a possible implementation is provided. After generating the solution structured data in step S106 above, the method further includes the following steps A1 and A2: Step A1: Use the solution structured data as sample training data to train a preset large model, and obtain a trained low-code GIS system usage solution recommendation model.

[0033] The large model (Large Model, LM) in this step, first, as the name implies, is large-scale, with network parameters reaching the scale of billions, tens of billions, hundreds of billions or even more; second, universality means that it is not limited to specific problems or fields; third, emergence means generating unexpected new capabilities.

[0034] Step A2: Receive the user's question about using the low-code GIS system, submit the user's question to the trained low-code GIS system usage solution recommendation model, and output the recommended solution for the user's question corresponding to the low-code GIS system.

[0035] In this embodiment, the solution structured data is used as sample training data to train a preset large model. Since the solution structured data includes fields such as solution classification, solution description, encoded data marked with the user operation sequence, solution encoding structure, data corresponding to the preset solution execution efficiency index, and data corresponding to the preset solution usage situation index, these rich data dimensions enable the trained low-code GIS system usage solution recommendation model to more accurately understand the user's needs during multiple rounds of conversations with the user, find the most suitable solution under the corresponding classification according to the user's needs, and optimize and improve the solution according to the conversation content.

[0036] In an embodiment of the present application, a possible implementation is provided. If the solution passes the test, the method further includes: binding and storing the collected data corresponding to the preset solution execution efficiency index with the solution classification, solution description, encoded data marked with the user operation sequence, and solution encoding structure, and displaying the test results, where the test results include whether the user's solution runs successfully and the details of each index.

[0037] In an embodiment of the present application, a possible implementation is provided. If the solution fails the test, the method further includes: generating a prompt message indicating that there are problems with the user's solution, and guiding the user to return to the solution editing interface of the low-code GIS system for modification. In this way, through the prompt and guidance, the user can more easily understand and correct the problems in the solution.

[0038] The above has introduced Figure 1 Multiple implementation methods of each link of the illustrated embodiment. Next, the data preparation method for the recommended solution of the low-code GIS system used in the embodiment of the present application will be further described through specific embodiments.

[0039] As introduced above, existing low-code GIS systems have difficulties in preparing data for usage scenario recommendations and cannot provide ideal learning data for large models, thus affecting the quality of usage scenario recommendations. For example, when using tutorials or documents of low-code GIS systems and passing them to large models, a complex semantic conversion process is required. This not only increases the difficulty of large model learning but also easily leads to inaccurate recommendation scenarios due to semantic understanding deviations. At the same time, compared with coding, written expressions are insufficient in terms of semantic clarity, information accuracy, and reflecting the abstract rules of user operations. In addition, although logs can also be used to record system content, they lack the advantages of structuring and coding and are difficult to effectively organize and analyze user operations.

[0040] In this specific embodiment, the specific framework is as follows 1) to 6): 1) Collect data on scenario classification and description information.

[0041] Users create their own scenarios and are required to classify the scenarios and write detailed descriptions and other descriptive information. This measure provides rich semantic information for large models to understand the core meaning of the scenarios, enabling large models to better grasp the overall intention of the scenarios during the learning process, rather than being limited to the implementation level of functions.

[0042] 2) Collect data on the corresponding coding structure and order of the scenarios.

[0043] Users need to complete the scenario content, specifically operate on each module and sub-function to form a complete scenario. During this process, a set of coding rules is used to assign a unique and extensible coding identifier to each module and sub-function. The coding rules cover business process coding, functional module coding, sub-function coding, and operation type coding. In addition, extension coding dimensions such as timestamp, version number, and user role are added to the coding.

[0044] 3) Collect various index data for test runs.

[0045] Users use the datasets predefined by the system to test the scenarios to determine whether the scenarios can run normally, collect various indicators related to the execution efficiency of the scenarios, such as processing speed and various resource occupancy situations, and then bind these indicators to the coding combination. This step provides important data on the performance of the scenarios for large models, enabling them to comprehensively consider the feasibility and efficiency of the scenarios when recommending scenarios.

[0046] 4) Mark the data related to the successfully published scenarios as valid.

[0047] Users can release the scope of release for the tested solutions. Only the solutions that have been tested and ensured to be correct can be released, so that the collected coding data has practical significance and value, avoiding the interference of invalid or incorrect data on the learning of the large model.

[0048] 5) Collect data during runtime.

[0049] After the solution is released, collect relevant usage data. Collect usage data such as the usage volume and the number of likes of the user's public solution. Since the solution is saved in the form of coding at the bottom layer, that is, collect the usage volume of the coding combination, which helps the large model to understand which coding combinations are more popular with users, so as to discover efficient and practical solution patterns.

[0050] 6) Organize, summarize and store the data related to the effective solutions.

[0051] Clean, unify and organize the collected solution-related data and its coding, and save it as a structured storage. The formed structured solution data includes fields such as solution classification, solution description, coding data marked with the user operation sequence, solution coding structure, data corresponding to the preset solution execution efficiency index, and data corresponding to the preset solution usage situation index. These rich data dimensions enable the preset large model to more accurately understand the user's needs during multiple rounds of conversations with the user, find the most suitable solution under the corresponding classification according to the user's needs, and optimize and improve the solution according to the conversation content.

[0052] The following is further illustrated by examples: (1) Solution creation and description: On the operation interface of the low-code GIS system, provide a dedicated solution creation entry for users. After the user enters this entry, the system guides the user to classify the solution to be created. The classification options can be preset as common business categories, such as "Insight Analysis", "Sales Route Planning", "Data Standardization", etc. At the same time, provide a text box for the user to write a solution description, elaborating on the description information such as the goal and applicable scenario of the solution. For example, a user engaged in market analysis creates a solution for analyzing the market in a specific area, selects "Insight Analysis" in the classification, and writes in the description: "This solution aims to plan the key areas for market promotion by analyzing data such as population density and consumption capacity in different regions of a certain city." The system saves the solution classification and description information input by the user in real time.

[0053] (2) Solution content completion and coding: Coding Rule Application: When the user starts to select the module and sub - function construction plan, the system background generates a code for each operation according to the established coding rules. For example, if the user, under the "Insight Analysis" business process, first selects the "Point Data" sub - function in the "Asset" module and performs a creation operation, the system generates the code "B001 - 01 - 001 - C". As the user continues to add other module and sub - function operations, such as selecting "Point to Circle" in the "Model" module and creating it, the code "B001 - 03 - 002 - C" is generated. At the same time, the system obtains the operation timestamp, such as "20250610143015", records the current system version number "V3", identifies the user role code "U015", and adds this information to the code to form the complete code "B001 - 03 - 002 -C | 20250610143015 - V3 - U015".

[0054] Structured Processing: The system monitors the user operation sequence in real - time and records the coding sequence in the form of a sequential list. For example, after the user performs the above operations in sequence, the system generates a sequential list, that is, the coding data marked with the user operation sequence. Here, the "order" records the user operation sequence: {"code": "B001 - 01 - 001 - C", "order": "1"}, {"code": "B001 - 03 - 002 - C", "order": "2"} 。

[0055] For the structural relationship of the function module and its sub - functions, the system records it in a structure. For example, if there are "Point Data" and "Surface Asset" sub - functions under the "Asset" module, the system records the structure as follows: { "id": "0eefe9a8a74245f89d81c5f3b3d4811a", / / First marker "B001 - 01": [ / / Asset module { "id": "02da7f7143554ffca59e15c6c078a448", / / Second marker "B001 - 01 - 001": { / / Point Data "desc": "Point Data description" } }, { ​"id": "a90e812843a34ef5a5ed5ed30a68ba8e", / / Third marker number "B001 - 01 - 002": { / / Surface data "desc": "Description of surface data" } } }。

[0056] (3)Scheme testing: After the user completes the scheme construction, the system automatically pops up a scheme testing prompt, informing the user to use a pre - defined data set (a fixed data set is beneficial for different performances of different schemes) for scheme testing. The system selects a suitable data set from the preset data sets according to the functions and data types involved in the scheme. For example, if the scheme involves the function of pulling LBS (Location Based Services) of the model module, the system selects a data set containing a certain number of geographical coordinates and related attribute information. After the user confirms to start the test, the system runs the scheme and monitors various performance indicators in real - time, such as the CPU usage rate, memory occupancy, network traffic, etc. of the server, as well as the running time of the scheme. After the test, the system binds and stores these performance indicator data with the coding combination of the scheme, and displays the test results on the interface, informing the user whether the scheme runs successfully and the details of each indicator.

[0057] (4)Scheme release: If the scheme passes the test, the system provides the user with a scheme release setting interface. The user can select the release scope on this interface, such as personal (visible only to oneself), team (visible to specific team members), public (visible to all users). After the user selects and clicks the release button, the system stores the scheme and its related performance indicator data in the corresponding database. If the scheme fails the test, the system prompts the user that there is a problem with the scheme and guides the user back to the scheme editing interface for modification.

[0058] (5)Scheme usage data collection: The system sets a counter in the background. Whenever a user uses (such as viewing, copying, secondary development based on the scheme, etc.) a public scheme, the usage counter of the corresponding scheme is incremented by 1 and updated to the usage record table in the database.

[0059] (6)Data cleaning and structured storage: (6.1)Data cleaning: ​Retrieve the data related to the collected solutions from the database, including encoding, performance metrics, usage volume, etc. First, perform format verification on the encoding. Check whether the business process encoding conforms to the "BPPP" format, whether the functional module encoding is two digits, etc. Correct the encoding that does not conform to the format or mark it as abnormal. For example, if it is found that the functional module encoding is three digits, prompt the administrator to perform manual confirmation and correction. Then, check the format and rationality of the extended dimensions such as timestamp, version number, user role encoding, etc. For example, whether the timestamp is a legal time, whether the version number corresponds to the actual system version, etc. Perform outlier detection on the performance metric data. For situations such as CPU usage exceeding 100% or running time being negative, mark the abnormal data and perform correction or deletion processing.

[0060] (6.2)Structured storage: The cleaned data is stored in accordance with the preset structured data format. Create a structured data table for solutions, including solution classification, solution description, encoded data marked with the user operation sequence, solution encoding structure, data corresponding to the preset solution execution efficiency metrics (extracted from the performance metric data), the number of times the solution is used, the number of times the solution is liked (can be collected by setting the user like function, with an initial value of 0), the solution recommendation level (initially can be set to the default level and adjusted later according to the preset recommendation level algorithm), etc. Fill in the data of each solution into the corresponding fields, such as Figure 2 shown.

[0061] In Figure 2 , the solution classification is "Insight Analysis", the solution description is "This solution aims to plan the key areas for market promotion by analyzing data such as population density and consumption capacity in different regions of a certain city", the encoded data marked with the user operation sequence, the solution encoding structure, the data corresponding to the preset solution execution efficiency metrics (such as CPU usage 30%, memory occupancy 512MB, running time 10s), the number of times the solution is used is 10, the number of times the solution is liked is 4, and the solution recommendation level is "Normal". It should be noted that Figure 2 the example in

[0062] is only illustrative and does not limit this embodiment.

[0062] Encoding rule description: Business processes: Such as insight analysis, sales route planning, etc.

[0063] 1.1) Adopt the "BPPP" format, where "B" represents the business process and "PPP" is three digits (001 - 999); 1.2) Example: B001 = Insight Analysis, B002 = Sales Route Planning.

[0064] Functional modules: Corresponding to the main functional modules in the system, such as maps, assets, models, etc.

[0065] 2.1) Adopt the "MM" format and use two digits (01 - 99); 2.2) Examples: 01 = Asset, 02 = Map, 03 = Model, 04 = Widget, 05 = Application.

[0066] Sub - function: Specific functional points under the module. For example, each calculation node under the model function, such as point - to - circle generation, point - fence determination, etc.

[0067] 3.1) Adopt the "SSS" format, where "SSS" is three digits representing the sub - function (001 - 999); 3.2) Example: 001 = Point data.

[0068] Operation type: Types and details of specific operations.

[0069] 4.1) Represented by a single letter: C = Create, R = Read / View, U = Update, D = Delete, E = Execute, B = Bind, etc.

[0070] This embodiment can achieve the following technical effects: First, from the perspective of the learning efficiency and accuracy of the large - model, through the encoding of the operation process, this embodiment greatly improves the learning efficiency of the large - model. The data provided to the large - model in traditional text form needs to go through complex semantic conversions, which not only takes time but also is prone to understanding deviations. In this embodiment, the encoding form is directly adopted, reducing the semantic conversion steps, enabling the large - model to learn the system historical situation more directly. For example, instead of performing complex semantic parsing on text descriptions such as "Create a point - to - circle function for insight analysis", the large - model can clearly understand the operation content through the concise encoding "B001 - 03 - 002 - C", thus significantly improving the learning efficiency, more accurately grasping the user's operation intention, and laying a foundation for generating accurate usage - plan recommendations.

[0071] Secondly, compared with text, coding has certain advantages in semantic clarity and information accuracy. The coding format is unified and standardized, with a large amount of information that is both extensive and precise, and it can reflect the abstract process of user operations in a certain pattern. Each coding combination not only clearly identifies the business process, functional module, sub-function, and operation type, but also incorporates key information such as timestamp, version number, and user role by expanding the coding dimension. This enables the large model to comprehensively and accurately understand the operation background and context relationship during the learning process. For example, through the coding "B001 - 03 - 002 - C | 20250610143015 - V3 - U015", the large model can know the specific operation performed by a specific user role at a specific time and under a specific system version, greatly reducing information ambiguity and ambiguity compared to text descriptions and improving the quality of the data learned by the large model.

[0072] In the application field of AI (Artificial Intelligence) agents, the direct mapping of the coding and functions in this embodiment brings the convenience of rapid and automatic function calls. When the agent determines the required function based on keywords and context, instead of performing complex understanding and analysis like dealing with text descriptions, it directly maps to the specific function through coding. For example, when receiving an instruction related to "Insight Analysis - Model Module - Point to Circle - Create", the agent can quickly locate and call the corresponding function by virtue of the coding "B001 - 03 - 002 - C", greatly improving the system response speed and automation level, and providing a smoother and more efficient user experience for users.

[0073] In addition, through coding in this embodiment, it is possible to continuously accumulate the usage combination methods and skills of other users and effectively integrate them. As the number of system users increases and the usage time goes by, a large amount of coding data continuously converges. By analyzing these coding combinations, various efficient and practical usage patterns and skills can be discovered. For example, it is found that in certain specific business scenarios, specific coding combinations can achieve better data analysis effects or more convenient operation processes. These valuable experiences can be integrated into general usage plans and recommended to other users, promoting knowledge sharing and improving the usage level of the entire user group for the low-code GIS system.

[0074] Furthermore, through this data accumulation, when the user has multiple rounds of conversations with the large model, the large model can understand the user's needs, thus find the solutions under the corresponding classification, give the solution that best meets the user's needs, and optimize and improve the solution according to the content of the conversation. For example, in a certain solution classification, all solutions have steps such as creating point data, point to circle, pulling LBS, and insight binding. These steps are the core steps, and according to the user's needs, steps such as creating a line chart can be added.

[0075] From the perspective of system operation analysis, the data preparation method of this embodiment is conducive to direct and in-depth analysis of various situations of system operation and use. The structuring and standardization of coding makes it very convenient to count the number, indicators, and other operations of different codes and coding combinations. For example, by counting the frequency of use of different business process codes, we can understand which business scenarios are more common in actual applications; analyzing the performance indicators of specific functional module coding combinations (such as running time, resource usage, etc.) can evaluate the efficiency and stability of each functional module. These analysis results can provide a strong basis for system optimization, help developers improve system performance and improve functional design in a targeted manner, and further enhance the overall quality and user satisfaction of low-code GIS systems.

[0076] It should be noted that the order of execution of the steps in the above embodiments does not necessarily imply a specific order of execution. The order of execution of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In practical applications, all possible implementation methods described above can be combined in any manner to form possible embodiments of the present application, and will not be described in detail here.

[0077] Based on the data preparation method for recommending the low-code GIS system usage plan provided in the above embodiments, and based on the same inventive concept, an embodiment of the present application also provides a data preparation device for recommending the low-code GIS system usage plan.

[0078] Figure 3 This is a structural diagram of the data preparation device recommended by the low-code GIS system usage solution provided in the embodiment of this application. Figure 3 As shown, the data preparation device recommended by the low-code GIS system usage plan can specifically include a receiving unit 310, a first generation unit 320, a second generation unit 330, a testing unit 340, a publishing unit 350 and a third generation unit 360.

[0079] The receiving unit 310 is configured to receive a solution content submitted by a user, wherein the solution content includes a solution classification and a solution description; The first generating unit 320 is configured to, in response to a user's operation on the solution editing interface of the low-code GIS system for the solution content, encode the operation on the solution editing interface of the low-code GIS system according to a pre-built basic coding layer and an extended coding layer, and generate coding data marked with a sequence of user operations, wherein the basic coding layer includes business processes, functional modules, sub-functions, and operation types, and the extended coding layer includes operation time, low-code GIS system version number, and user role; The second generating unit 330 is configured to generate a scheme coding structure according to the structural relationship between the functional modules and sub-functions in the coding data marked with the user operation sequence; A test unit 340 is used to test the solution using a pre - defined data set, execute the solution according to the encoded data marked with the user operation sequence, and during the execution process, collect data corresponding to the preset solution execution efficiency metrics according to the preset solution execution efficiency metrics; A publishing unit 350 is used to, if the solution test passes, receive the solution publishing instruction submitted by the user, publish the tested - passed solution, and after the publishing, collect data corresponding to the preset solution usage metrics according to the preset solution usage metrics; A third generation unit 360 is used to structurally store the solution classification, the solution description, the encoded data marked with the user operation sequence, the solution encoding structure, the data corresponding to the preset solution execution efficiency metrics, and the data corresponding to the preset solution usage metrics, and generate solution structured data.

[0080] In an embodiment of the present application, a possible implementation manner is provided, as Figure 4 shown, the device shown above Figure 3 may further include a training unit 410, which is used to use the solution structured data as sample training data to train a preset large - model, and obtain a trained low - code GIS system solution recommendation model; A recommendation unit 420 is used to receive the user's question about using the low - code GIS system, submit the user's question to the trained low - code GIS system solution recommendation model, and output a low - code GIS system usage recommendation solution corresponding to the user's question.

[0081] In an embodiment of the present application, a possible implementation manner is provided, and the solution description is represented by natural language.

[0082] In an embodiment of the present application, a possible implementation manner is provided, and the preset solution execution efficiency metrics include one or more of CPU usage rate, memory occupancy rate, and network traffic.

[0083] In an embodiment of the present application, a possible implementation manner is provided, and the preset solution usage metrics include one or more of the number of times the solution is used, the number of times the solution is liked, and the solution recommendation level.

[0084] In an embodiment of the present application, a possible implementation manner is provided, as Figure 4 shown, the above Figure 3The displayed device may further include a display unit 430, which is configured to, if the solution test passes, bind and store the data corresponding to the collected preset solution execution efficiency indicators with the solution classification, the solution description, the encoded data marked with the user operation sequence, and the solution encoding structure, and display the test results, where the test results include whether the user solution runs successfully and the details of each indicator.

[0085] In an embodiment of the present application, a possible implementation manner is provided, as Figure 4 shown above Figure 3 The displayed device may further include a prompt unit 440, which is configured to, if the solution test fails, generate a prompt message indicating that there is a problem with the user solution, and guide the user to return to the solution editing interface of the low-code GIS system for modification.

[0086] Based on the same inventive concept, an embodiment of the present application further provides an electronic device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the data preparation method for recommending the usage solution of the low-code GIS system in any one of the above embodiments.

[0087] In an exemplary embodiment, an electronic device is provided, as Figure 5 shown Figure 5 The electronic device 500 shown includes: a processor 501 and a memory 503. Among them, the processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may further include a transceiver 504. It should be noted that in practical applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation to the embodiments of the present application.

[0088] The processor 501 may be a CPU, a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in combination with the disclosure of the present application. The processor 501 may also be a combination for implementing computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0089] The bus 502 may include a path for transmitting information between the above components. The bus 502 can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 502 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 5 it is only represented by a thick line in Figure 5 , but it does not mean that there is only one bus or one type of bus.

[0090] The memory 503 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0091] The memory 503 is used to store the computer program code for executing the solution of this application, and is controlled by the processor 501 to execute. The processor 501 is used to execute the computer program code stored in the memory 503 to implement the content shown in the foregoing method embodiments.

[0092] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The illustrated electronic device is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0093] Based on the same inventive concept, the embodiments of this application also provide a storage medium, in which a computer program is stored, and the computer program is set to execute the data preparation method recommended by the low-code GIS system usage solution of any one of the above embodiments when running.

[0094] Those skilled in the art can clearly understand the specific working processes of the systems, devices, and modules described above. They can refer to the corresponding processes in the foregoing method embodiments. For the sake of brevity, they will not be elaborated herein.

[0095] Those of ordinary skill in the art can understand that the technical solution of the present application can essentially be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several program instructions for causing an electronic device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application when running the program instructions. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0096] Alternatively, all or part of the steps of implementing the foregoing method embodiments can be completed by hardware related to program instructions (such as an electronic device such as a personal computer, a server, or a network device). The program instructions can be stored in a computer-readable storage medium. When the program instructions are executed by the processor of the electronic device, the electronic device executes all or part of the steps of the methods described in the embodiments of the present application.

[0097] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that within the spirit and principle of the present application, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the corresponding technical solutions to deviate from the protection scope of the present application.

Claims

1. A data preparation method recommended for the use of a low-code GIS system, characterized in that, The method includes: Receiving the solution content submitted by the user, where the solution content includes solution classification and solution description; In response to the user's operation on the solution editing interface of the low-code GIS system for the solution content, encoding the operation on the solution editing interface of the low-code GIS system according to the pre-constructed basic coding layer and extended coding layer to generate coded data marked with the user operation sequence, where the basic coding layer includes business processes, functional modules, sub-functions, and operation types, and the extended coding layer includes operation time, low-code GIS system version number, and user role; Generating a solution coding structure according to the structural relationship between the functional modules and sub-functions in the coded data marked with the user operation sequence; Testing the solution using a predefined data set, executing the solution according to the coded data marked with the user operation sequence, and during the execution process, collecting data corresponding to the preset solution execution efficiency indicators according to the preset solution execution efficiency indicators; If the solution passes the test, receiving the solution release instruction submitted by the user, releasing the solution that has passed the test, and after the release, collecting data corresponding to the preset solution usage situation indicators according to the preset solution usage situation indicators; Structurally storing the solution classification, the solution description, the coded data marked with the user operation sequence, the solution coding structure, the data corresponding to the preset solution execution efficiency indicators, and the data corresponding to the preset solution usage situation indicators to generate solution structured data.

2. The method according to claim 1, characterized in that, After generating the solution structured data, the method further includes: Using the solution structured data as sample training data to train a preset large model to obtain a trained low-code GIS system usage solution recommendation model; Receiving the user's question about using the low-code GIS system, submitting the user's question to the trained low-code GIS system usage solution recommendation model, and outputting a recommended solution for using the low-code GIS system corresponding to the user's question.

3. The method according to claim 1, characterized in that, The solution description is represented by natural language.

4. The method according to claim 1, wherein The preset solution execution efficiency indicators include one or more of CPU usage rate, memory occupancy rate, and network traffic.

5. The method according to claim 1, wherein The preset solution usage situation indicators include one or more of the number of times the solution is used, the number of times the solution is liked, and the solution recommendation level.

6. The method according to any one of claims 1 to 5, characterized in that If the solution passes the test, the method further includes: Binding and storing the data corresponding to the preset solution execution efficiency indicators collected with the solution classification, the solution description, the coded data marked with the user operation sequence, and the solution coding structure, and displaying the test results, where the test results include whether the user solution runs successfully and the details of each indicator.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: If the solution fails the test, generating a prompt message indicating that there is a problem with the user solution and guiding the user to return to the solution editing interface of the low-code GIS system for modification.

8. A data preparation device recommended for a low-code GIS system usage scenario, characterized in that, The device includes: A receiving unit for receiving the solution content submitted by the user, where the solution content includes solution classification and solution description; A first generation unit, configured to, in response to an operation of a user on a solution editing interface of a low-code GIS system for the solution content, encode the operation on the solution editing interface of the low-code GIS system according to a pre-constructed basic coding layer and an extended coding layer, and generate coded data marked with the user operation sequence, wherein the basic coding layer includes business processes, functional modules, sub-functions, and operation types, and the extended coding layer includes operation time, low-code GIS system version number, and user roles; A second generation unit, configured to generate a solution coding structure according to the structural relationship between the functional modules and sub-functions in the coded data marked with the user operation sequence; A testing unit, configured to test the solution using a pre-defined data set, execute the solution according to the coded data marked with the user operation sequence, and during the execution process, collect data corresponding to a preset solution execution efficiency index according to the preset solution execution efficiency index; A publishing unit, configured to, if the solution passes the test, receive a solution publishing instruction submitted by the user, publish the solution that has passed the test, and after the publishing, collect data corresponding to a preset solution usage situation index according to the preset solution usage situation index; A third generation unit, configured to structurally store the solution classification, the solution description, the coded data marked with the user operation sequence, the solution coding structure, the data corresponding to the preset solution execution efficiency index, and the data corresponding to the preset solution usage situation index, and generate solution structured data.

9. An electronic device, characterized in that, It includes a processor and a memory, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the data preparation method for recommending a usage solution of the low-code GIS system according to any one of claims 1 to 7.

10. A storage medium, characterized in that, A computer program is stored in the storage medium, wherein the computer program is configured to execute the data preparation method for recommending a usage solution of the low-code GIS system according to any one of claims 1 to 7 when running.

Images