Natural resource inspector question extraction and classification method and system based on artificial intelligence

Abstract

This invention discloses an artificial intelligence-based method and system for extracting and classifying issues in natural resource supervision. The method includes: acquiring preset terms; obtaining several online clues based on the preset terms using a web crawler; acquiring preset keywords and a database; creating at least one set of issue data based on the preset keywords and each online clue; determining whether a problem database with the same regional attributes as the issue data exists in the database, based on the regional attributes of the issue data and the database; creating another problem database if it does not exist; and moving the issue data into the problem database if it does exist, and sending a notification when the quantity of issues in the problem database changes. This invention leverages existing web crawlers to integrate online reports, breaking down information barriers and achieving deep fusion of multi-source data. By monitoring the quantity of issue data in the database, it reduces the cost of manual intervention, ensures comprehensive coverage of illegal issues, and enables efficient and rapid implementation of natural resource supervision.

Description

Technical Field

[0001] This invention relates to the field of natural resource supervision technology, and is applicable to all scenarios of natural resource supervision, including land use, national spatial planning, mineral resource development, and ecological protection red line management. In particular, it relates to a method and system for extracting and classifying natural resource supervision issues based on artificial intelligence. Background Technology

[0002] Natural resource supervision, based on legal authorization, supported by smart technology, centered on a closed-loop process, and guaranteed by rigid accountability, has achieved a transformation from "passive investigation and punishment" to "proactive prevention and control," and from "single supervision" to "systematic governance." Through multiple mechanisms including technological authenticity assurance, procedural fairness, internal and external supervision, rigid accountability, and long-term governance, it ensures that supervision results are authentic and reliable, rectification is thorough, and effects are lasting. It has become a key institutional tool for safeguarding national resource security and ecological security, and promoting the modernization of local governance and green development.

[0003] Currently, the scope of natural resource supervision work is limited to processing single business data, lacking the ability to effectively integrate external clues such as media exposure, and relying on manual problem extraction and classification, which is inefficient. It also relies too much on the subjectivity of staff, making it easy to miss clues, resulting in low efficiency in the conduct of natural resource supervision work and the inability to discover problems in a timely and rapid manner. Summary of the Invention

[0004] The main objective of this invention is to provide a method and system for extracting and classifying problems in natural resource supervision based on artificial intelligence, aiming to solve the problem of low efficiency in the conduct of natural resource supervision work and the inability to discover problems in a timely and rapid manner.

[0005] To achieve the above objectives, this invention proposes an artificial intelligence-based method for extracting and classifying natural resource supervision issues, comprising: Obtain preset terms, and based on the preset terms, obtain several online clues through web crawlers; Obtain preset keywords and a database, wherein the preset keywords include regional attributes; Create at least one set of question data based on preset keywords and the aforementioned online clues; Based on the regional attributes of the problem data and the database, determine whether there exists a problem database in the database that has the same regional attributes as the problem data; When there is no problem database in the database that has the same regional attributes as the problem data, another problem database is created in the database according to the regional attributes of the problem data, and then the step of determining whether there is a problem database with the same regional attributes as the problem data in the database is executed based on the regional attributes of the problem data and the database. When a problem database with the same regional attribute as the problem data exists in the database, the problem data is moved into the problem database. The quantity attribute of the problem database is adjusted according to the quantity of each problem data in the problem database, and a reminder message is sent when the quantity attribute of the problem database changes.

[0006] Preferably, after the steps of moving the problem data into the problem database when the database contains a problem database with the same regional attribute as the problem data, adjusting the quantity attribute of the problem database according to the quantity of each problem data in the problem database, and sending a reminder message when the quantity attribute of the problem database changes, the method further includes: Determine whether the quantity attribute of the problem database is greater than a first preset quantity; When the quantity attribute of the question database is less than the first preset quantity, the steps of obtaining preset terms and obtaining several network clues through web crawlers based on the preset terms are executed. When the quantity attribute of the problem database is greater than or equal to the first preset quantity, an early warning message is sent at a preset time point.

[0007] Preferably, the step of sending an early warning message when the quantity attribute of the problem database is greater than or equal to the first preset quantity includes: When the quantity attribute of the question database is greater than or equal to the first preset quantity, it is determined whether the quantity attribute of the question database is greater than the second preset quantity, wherein the first preset quantity is less than the second preset quantity; When the quantity attribute of the problem database is less than the second preset quantity, the step of sending a warning message at a preset time point is executed; When the quantity attribute of the question database is greater than or equal to the second preset quantity, the excess quantity is determined according to the quantity attribute of the question database and the second preset quantity; Based on the quantity exceeding the limit, identify and send an alert message.

[0008] Preferably, after the step of sending a warning message when the quantity attribute of the problem database is greater than or equal to the preset quantity, the method includes: Obtain first selection information, delete at least one of the problem data in the problem database according to the first selection information, and perform the step of determining whether the quantity attribute of the problem database is greater than a preset quantity.

[0009] Preferably, the step of obtaining preset terms and acquiring several network clues through a web crawler based on the preset terms when the quantity attribute of the question database is less than the first preset quantity includes: When the quantity attribute of the question database is less than the first preset quantity, the target term is obtained; Based on the target term and the question database, determine the number of times the target term appears in the question database; Determine whether the number of times the target term appears in the question database is greater than a preset number; When the number of times the target term appears in the question database is less than the preset number, the steps of obtaining the preset term and obtaining several network clues through web crawler based on the preset term are executed. When the number of times the target term appears in the question database is greater than or equal to the preset number, the step of sending a warning message at a preset time point is executed.

[0010] Preferably, the step of sending a warning message at a preset time point when the number of occurrences of the target term in the question database is greater than or equal to the preset number includes: When the number of times the target term appears in the question database is greater than or equal to the preset number, based on the target term and the question database, a number of question data containing the target term are determined. Obtain information about the second option; Based on the second selection information and the question data for each of the target terms, determine the true information; Determine whether the quantity of the real information is greater than a third preset quantity; When the quantity of real information is less than the third preset quantity, the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms is executed. When the quantity of the real information is greater than or equal to the third preset quantity, the step of sending a warning message at a preset time point is executed.

[0011] Preferably, the step of sending a warning message at a preset time point when the number of occurrences of the target term in the question database is greater than or equal to the preset number includes: When the number of occurrences of the target term in the question database is greater than or equal to the preset number, a term with a preset unit of measurement is obtained: Based on the preset unit of measurement terms and the question database, determine a number of question data that contain the preset unit of measurement terms; Based on a number of problem data entries containing the preset unit of measurement, determine the first total quantity; Determine whether the total quantity of the first quantity is greater than the first preset total quantity; When the total first quantity is less than the first preset total quantity, the step of obtaining preset terms and obtaining several network clues through a web crawler based on the preset terms is executed. When the total quantity of the first quantity is greater than or equal to the first preset total quantity, the step of sending a warning message at a preset time point is executed.

[0012] Preferably, the step of determining the first total quantity based on a plurality of the problem data containing the preset unit of measurement entries includes: Based on a number of problem data containing the preset unit of measurement term, determine whether the data volume of the preset unit of measurement term in each problem data is correct; When the data volume of each of the preset unit of measurement entries in the problem data is correct, the data volumes are added together to determine the total data volume; When the amount of data for the preset unit of measurement term in any of the aforementioned problem data is incorrect, obtain third selection information; Based on the third selection information, the problematic data with incorrect data volume is modified, and the original record is retained. Then, the step of determining whether the data volume of the preset unit of measurement term in each of the problematic data is correct is performed based on the several problematic data containing the preset unit of measurement term.

[0013] To achieve the above objectives, an artificial intelligence-based natural resource supervision problem extraction and classification system applies the artificial intelligence-based natural resource supervision problem extraction and classification method described in any of the above-mentioned embodiments, including an execution module, a judgment module, and a calculation module; The execution module is used to obtain preset terms, obtain several online clues through web crawlers based on the preset terms, obtain preset keywords and a database, and create at least one set of question data based on the preset keywords and each of the online clues. The judgment module is used to determine, based on the regional attributes of the problem data and the database, whether there exists a problem database in the database that has the same regional attributes as the problem data; The calculation module is used to create another problem database in the database based on the regional attributes of the problem data when there is no problem database in the database with the same regional attributes as the problem data; then, it performs the step of determining whether there is a problem database with the same regional attributes as the problem data in the database based on the regional attributes of the problem data and the database; when there is a problem database with the same regional attributes as the problem data in the database, it moves the problem data into the problem database, adjusts the quantity attribute of the problem database according to the quantity of each problem data in the problem database, and sends a reminder message when the quantity attribute of the problem database changes.

[0014] Compared with the prior art, the present invention has at least the following beneficial effects: By setting preset keywords and leveraging existing web crawlers, the system integrates online reports, breaking down information barriers and achieving deep fusion of multi-source data. A database is built based on preset keywords and various online clues, providing targeted support for "key inspections" and strengthening the authority and deterrent effect of the inspection work. Furthermore, by monitoring the quantity of problematic data within the database, the system significantly reduces the cost of manual intervention, avoids omissions in manual verification and non-standard classification, ensures comprehensive coverage of illegal activity clues, supports routine monitoring needs, and enables the efficient and rapid implementation of natural resource inspections. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating an embodiment of an artificial intelligence-based method for extracting and classifying problems in natural resource supervision.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0019] The following describes, with reference to the accompanying drawings, an artificial intelligence-based method and system for extracting and classifying natural resource supervision issues according to embodiments of the present invention.

[0020] Figure 1 This is a flowchart illustrating an embodiment of an artificial intelligence-based method for extracting and classifying problems in natural resource supervision.

[0021] Please see Figure 1 To achieve the above objectives, the first embodiment of the present invention provides an artificial intelligence-based method for extracting and classifying natural resource supervision issues, comprising: Step S10: Obtain preset terms and use web crawlers to obtain several online clues based on the preset terms; Step S20: Obtain preset keywords and database; Step S30: Create at least one question data based on preset keywords and various online clues; Step S40: Based on the regional attributes of the problem data and the database, determine whether there exists a problem database with the same regional attributes as the problem data. Step S50: When there is no problem database in the database that has the same regional attribute as the problem data, create another problem database in the database according to the regional attribute of the problem data, and then execute the step of determining whether there is a problem database in the database that has the same regional attribute as the problem data based on the regional attribute of the problem data and the database. Step S60: When there is a problem database in the database with the same region attribute as the problem data, move the problem data into the problem database, adjust the quantity attribute of the problem database according to the quantity of each problem data in the problem database, and send a reminder message when the quantity attribute of the problem database changes.

[0022] By setting preset keywords and leveraging existing web crawlers, the system integrates online reports, breaking down information barriers and achieving deep fusion of multi-source data. A database is built based on preset keywords and various online clues, providing targeted support for "key inspections" and strengthening the authority and deterrent effect of the inspection work. Furthermore, by monitoring the quantity of problematic data within the database, the system significantly reduces the cost of manual intervention, avoids omissions in manual verification and non-standard classification, ensures comprehensive coverage of illegal activity clues, supports routine monitoring needs, and enables the efficient and rapid implementation of natural resource inspections.

[0023] Specifically, the preset terms are manually set vocabulary, such as illegal land use, illegal mining, and destruction of ecological red lines. These preset terms are iteratively upgraded based on policy adjustments and business feedback, supporting the supervisory needs of multiple fields including land, minerals, and ecology. They are adaptable to use by natural resource supervision agencies at all levels and have a wide range of applications.

[0024] The preset keywords are manually entered information. The preset keywords must include regional attributes, such as a certain district. The preset keywords can also include names, such as Wang Moumou. Generally, the names of administrative personnel are used for identification.

[0025] The preset keywords are set according to the area to be monitored. For example, if you are monitoring a certain city, the preset keywords will include all districts of that city, as well as all townships and towns under the jurisdiction of that city.

[0026] The issue data includes online leads, as well as name and / or region information tagged into the issue data based on the online leads.

[0027] The regional attribute in the problem data is one of the regional attributes within the preset keywords. The database is set up separately according to a certain city (usually further divided according to different districts, excluding the lower-level units of the city), a certain town, and a certain township, so that staff can quickly determine the specific area where the problem data occurred.

[0028] Specifically, after step S20, the following steps are included: Step S21: Based on preset keywords and online clues, determine whether the online clues have regional attributes; Step S22: When the network clue has a regional attribute, proceed to step S30; Step S23: When the network clue does not have a regional attribute, obtain the IP address of the person who sent the network clue from the platform where the network clue is located; Step S24: Determine the regional attribute of the network clue based on the IP address, and then proceed to step S30.

[0029] Based on preset keywords, the regional attributes of online leads are identified, and then the regional attributes are determined by obtaining the IP address from the platform, thereby completing the data of online leads and improving the utilization rate of online leads.

[0030] Specifically, step S23 includes: Step S25: If the network clue does not have a regional attribute, send a request to the platform where the network clue is located to obtain the IP address of the person who issued the network clue; Step S26: Obtain the reply information and determine whether there is an IP address in the reply information; Step S27: If the reply information contains an IP address, proceed to step S24; Step S28: When the IP address is not present in the reply information, mark the area data of the network clue as incomplete; Step S29: Create a problem database with incomplete regional attributes in the database, and then execute S24.

[0031] The issue database with incomplete regional attributes includes all issue data lacking regional attributes, ensuring maximum data collection and providing some data support for investigators.

[0032] In the second embodiment of the present invention, based on the first embodiment, after step S60, the following is included: Step S70: Determine whether the number of questions in the question bank is greater than the first preset number; Step S71: When the number of questions in the question database is less than the first preset number, execute the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms. Step S72: When the number of questions in the question database is greater than or equal to the first preset number, send an early warning message at a preset time point.

[0033] Different initial preset quantities can be designed for different problem databases. For example, a higher initial preset quantity can be set for areas with more arable land and mineral resources. Since more violations occur in these areas, the initial preset data can be adjusted to avoid excessive warning information affecting the daily work of staff.

[0034] Specifically, the quantity attribute is the total number of all problem data in the problem database.

[0035] In the third embodiment of the present invention, based on the second embodiment, step S72 includes: Step S73: When the quantity attribute of the question library is greater than or equal to the first preset quantity, determine whether the quantity attribute of the question library is greater than the second preset quantity, and the first preset quantity is less than the second preset quantity; Step S74: When the number of questions in the question bank is less than the second preset number, execute the step of sending a warning message at a preset time point; Step S75: When the quantity attribute of the question library is greater than or equal to the second preset quantity, determine the excess quantity based on the quantity attribute of the question library and the second preset quantity; Based on the quantity exceeding the limit, identify and send an alert message.

[0036] By setting multiple levels of preset quantities (first and second preset quantities), staff can be better supervised in handling high-incidence events.

[0037] In the fourth embodiment of the present invention, based on the third embodiment, after step S75, the following is included: Step S76: Obtain first selection information, delete at least one problem data in the problem database according to the first selection information, and execute the step of judging whether the quantity attribute of the problem database is greater than the preset quantity.

[0038] The first selection information is manually entered information. Duplicate or incorrect information is deleted based on the first selection information to avoid the database becoming bloated and accumulating too much junk data.

[0039] In the fifth embodiment of the present invention, based on any one of the second to fourth embodiments, step S71 includes: Step S80: When the number of questions in the question bank is less than the first preset number, obtain the target term; Step S81: Determine the number of times the target term appears in the question database based on the target term and the question database; Step S82: Determine whether the number of times the target term appears in the question database is greater than the preset number; Step S83: When the number of times the target term appears in the question database is less than the preset number, execute the step of obtaining the preset term and obtaining several network clues through web crawler based on the preset term; Step S84: When the number of times the target term appears in the question database is greater than or equal to the preset number, execute the step of sending a warning message at a preset time point.

[0040] Specifically, the target terms are manually set terms, such as the name: Wang Moumou.

[0041] Since the regional attributes of all the problem data in the problem database are consistent, when a certain target term appears frequently, it means that the target term has been publicly disclosed and restricted online multiple times in the region where the problem data is located. Therefore, an early warning message is sent to the staff to facilitate the handling of the violation in its initial stage and prevent the violation from escalating.

[0042] In the sixth embodiment of the present invention, based on the fifth embodiment, step S84 includes: Step S85: When the number of times the target term appears in the question database is greater than or equal to the preset number, determine a number of question data containing the target term based on the target term and the question database; Step S86: Obtain the second selection information; Step S87: Determine the true information based on the second selection information and the question data of each question containing the target term; Step S88: Determine whether the number of real information is greater than the third preset number; Step S89: When the number of real information is less than the third preset number, execute the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms. Step S810: When the number of real information is greater than or equal to the third preset number, execute the step of sending a warning message at a preset time point.

[0043] The second option is similar to the first option, both involving manually entered information. Both methods involve manual intervention to further filter the problematic data containing the target terms. By deleting erroneous problematic data, the remaining problematic data is confirmed as genuine, ensuring the authenticity of the problematic data while significantly reducing the cost of manual intervention.

[0044] In the seventh embodiment of the present invention, based on the fifth embodiment, step S84 includes: Step S90: When the number of occurrences of the target term in the question database is greater than or equal to a preset number, obtain the term with a preset unit of measurement. Step S91: Based on the preset unit of measurement terms and the question database, determine several question data that contain preset unit of measurement terms; Step S92: Determine the first total quantity based on several problem data entries with preset units of measurement. Step S93: Determine whether the total quantity of the first quantity is greater than the first preset quantity; Step S94: When the total first quantity is less than the first preset total quantity, execute the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms. Step S95: When the first quantity is greater than or equal to the first preset quantity, execute the step of sending a warning message at a preset time point.

[0045] The preset units of measurement for the entries are mu (a Chinese unit of area), yuan (a Chinese unit of currency), and square meters. The system calculates the total number of the first quantity of the target entry in the question database (for example, if question A has 10 mu, question B has 2 mu, and question C has 5 mu, the total number of the first quantity is 17 mu) to provide prompts, enabling multi-faceted review and ensuring timely review.

[0046] Specifically, after step S91, the following steps are included: Step S101: Based on the preset terms and several problem data with preset units of measurement, determine the complaint type in each problem data with preset units of measurement. Step S102: Determine the second total quantity of each problem data of the same complaint type based on the complaint type of each problem data. Step S103: Determine whether the total second quantity is greater than the second preset total quantity; Step S104: When the total second quantity is less than the second preset quantity, execute the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms; Step S105: When the second total quantity is greater than or equal to the second preset total quantity, determine the management department and data packet according to the complaint type of each problem data corresponding to the second total quantity. Step S106: Obtain the fourth selection information, and send a data packet to the management department based on the fourth selection information and the management department.

[0047] The complaint types for each issue data are determined based on preset terms (e.g., illegal land use, illegal mining, destruction of ecological red lines, etc.). Then, by judging the total amount of the second data in the complaint type (e.g., illegal land use of 5 mu in issue A1, 3 mu in issue A2, and 6 mu in issue A3, the total amount of the second data belonging to the same complaint type A1+A2+A3 is 14 mu), a more accurate data problem data package is summarized and sent to the corresponding management department (e.g., the Natural Resources Bureau).

[0048] The data package includes all the issue data involving the second total quantity, such as issue data A1 containing 5 mu of illegal land use, issue data A2 containing 3 mu of illegal land use, and issue data A3 containing 6 mu of illegal land use. The data package includes three data packages: A1, A2, and A3.

[0049] In the eighth embodiment of the present invention, based on the seventh embodiment, step S92 includes: Step S96: Based on several problem data with preset unit of measurement entries, determine whether the data volume of preset unit of measurement entries in each problem data is correct; Step S97: When the data volume of the preset unit of measurement terms in each problem data is correct, add up the data volume to determine the total data volume; Step S98: When the amount of data for a preset unit of measurement term in any problem data is incorrect, obtain third selection information; Step S99: Modify the problematic data with incorrect data volume according to the third selection information, retain the original record, and then execute the step of determining whether the data volume of the preset unit of measurement term in each problematic data is correct based on the several problematic data with preset unit of measurement terms.

[0050] The third option is manually entered information. This information is used to correct any errors or inaccuracies in the problem data, and the original record is retained to ensure the accuracy of the initial total quantity. The retained original record facilitates further tracking during actual investigation and case handling.

[0051] To achieve the above objectives, an AI-based natural resource supervision problem extraction and classification system applies any of the AI-based natural resource supervision problem extraction and classification methods described above, including an execution module, a judgment module, and a calculation module. The execution module is used to obtain preset terms, retrieve several online clues based on the preset terms using a web crawler, obtain preset keywords and a database, and create at least one question based on the preset keywords and each online clue. The judgment module is used to determine whether a problem database with the same regional attributes as the problem data exists in the database, based on the regional attributes of the problem data and the database. The calculation module is used to create another problem database based on the regional attributes of the problem data when there is no problem database in the database that has the same regional attributes as the problem data. Then, it performs the step of determining whether there is a problem database with the same regional attributes as the problem data based on the regional attributes of the problem data and the database. When there is a problem database with the same regional attributes as the problem data in the database, the problem data is moved into the problem database. The quantity attribute of the problem database is adjusted according to the quantity of each problem data in the problem database. When the quantity attribute of the problem database changes, an alert message is sent.

[0052] In the description of this specification, references are made to the terms "one embodiment", "another embodiment", "other embodiments" Descriptions such as "example" or "first embodiment to Xth embodiment" refer to descriptions in conjunction with that embodiment or example. Specific features, structures, materials, or characteristics are included in at least one embodiment or example of the present invention.

[0053] In this specification, the illustrative expressions of the terms used above do not necessarily refer to the same embodiments or examples.

[0054] Furthermore, the specific features, structures, materials, method steps, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0055] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to... This encompasses non-exclusivity inclusion, thereby allowing a process, method, article, or device to include a range of elements. The setting includes not only those elements, but also other elements not explicitly listed, or may also include... Elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0056] The sequence numbers of the above embodiments of the present invention are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0057] The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited thereto. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art, guided by the teachings of this invention, will apply the principles and claims of this invention without departing from its spirit and scope. Within the scope of protection, many other forms can be made, all of which fall within the protection scope of this invention.

Claims

1. A method for extracting and classifying problems in natural resource supervision based on artificial intelligence, characterized in that, include: Obtain preset terms, and based on the preset terms, obtain several online clues through web crawlers; Obtain preset keywords and a database, wherein the preset keywords include regional attributes; Create at least one set of question data based on preset keywords and the aforementioned online clues; Based on the regional attributes of the problem data and the database, determine whether there exists a problem database in the database that has the same regional attributes as the problem data; When there is no problem database in the database that has the same regional attributes as the problem data, another problem database is created in the database according to the regional attributes of the problem data, and then the step of determining whether there is a problem database with the same regional attributes as the problem data in the database is executed based on the regional attributes of the problem data and the database. When a problem database with the same regional attribute as the problem data exists in the database, the problem data is moved into the problem database. The quantity attribute of the problem database is adjusted according to the quantity of each problem data in the problem database, and a reminder message is sent when the quantity attribute of the problem database changes.

2. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 1, characterized in that, After the steps of moving the problem data into the problem database when a problem database with the same regional attribute as the problem data exists in the database, adjusting the quantity attribute of the problem database according to the quantity of each problem data in the problem database, and sending a reminder message when the quantity attribute of the problem database changes, the method includes: Determine whether the quantity attribute of the problem database is greater than a first preset quantity; When the quantity attribute of the question database is less than the first preset quantity, the steps of obtaining preset terms and obtaining several network clues through web crawlers based on the preset terms are executed. When the quantity attribute of the problem database is greater than or equal to the first preset quantity, an early warning message is sent at a preset time point.

3. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 2, characterized in that, The step of sending an early warning message when the quantity attribute of the problem database is greater than or equal to the first preset quantity includes: When the quantity attribute of the question database is greater than or equal to the first preset quantity, it is determined whether the quantity attribute of the question database is greater than the second preset quantity, wherein the first preset quantity is less than the second preset quantity; When the quantity attribute of the problem database is less than the second preset quantity, the step of sending a warning message at a preset time point is executed; When the quantity attribute of the question database is greater than or equal to the second preset quantity, the excess quantity is determined according to the quantity attribute of the question database and the second preset quantity; Based on the quantity exceeding the limit, identify and send an alert message.

4. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 3, characterized in that, After the step of sending a warning message when the quantity attribute of the problem database is greater than or equal to the preset quantity, the following steps are included: Obtain first selection information, delete at least one of the problem data in the problem database according to the first selection information, and perform the step of determining whether the quantity attribute of the problem database is greater than a preset quantity.

5. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in any one of claims 2-4, characterized in that, When the quantity attribute of the question database is less than the first preset quantity, the step of obtaining preset terms and obtaining several network clues through a web crawler based on the preset terms includes: When the quantity attribute of the question database is less than the first preset quantity, the target term is obtained; Based on the target term and the question database, determine the number of times the target term appears in the question database; Determine whether the number of times the target term appears in the question database is greater than a preset number; When the number of times the target term appears in the question database is less than the preset number, the steps of obtaining the preset term and obtaining several network clues through web crawler based on the preset term are executed. When the number of times the target term appears in the question database is greater than or equal to the preset number, the step of sending a warning message at a preset time point is executed.

6. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 5, characterized in that, The step of sending a warning message at a preset time point when the number of occurrences of the target term in the question database is greater than or equal to the preset number includes: When the number of times the target term appears in the question database is greater than or equal to the preset number, based on the target term and the question database, a number of question data containing the target term are determined. Obtain information about the second option; Based on the second selection information and the question data for each of the target terms, determine the true information; Determine whether the quantity of the real information is greater than a third preset quantity; When the quantity of real information is less than the third preset quantity, the step of obtaining preset terms and obtaining several network clues through web crawler based on the preset terms is executed. When the quantity of the real information is greater than or equal to the third preset quantity, the step of sending a warning message at a preset time point is executed.

7. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 5, characterized in that, The step of sending a warning message at a preset time point when the number of occurrences of the target term in the question database is greater than or equal to the preset number includes: When the number of occurrences of the target term in the question database is greater than or equal to the preset number, a term with a preset unit of measurement is obtained: Based on the preset unit of measurement terms and the question database, determine a number of question data that contain the preset unit of measurement terms; Based on a number of problem data entries containing the preset unit of measurement, determine the first total quantity; Determine whether the total quantity of the first quantity is greater than the first preset total quantity; When the total first quantity is less than the first preset total quantity, the step of obtaining preset terms and obtaining several network clues through a web crawler based on the preset terms is executed. When the total quantity of the first quantity is greater than or equal to the first preset total quantity, the step of sending a warning message at a preset time point is executed.

8. The artificial intelligence-based method for extracting and classifying natural resource supervision issues as described in claim 7, characterized in that, The step of determining the first total quantity based on a plurality of question data containing the preset unit of measurement entries includes: Based on a number of problem data containing the preset unit of measurement term, determine whether the data volume of the preset unit of measurement term in each problem data is correct; When the data volume of each of the preset unit of measurement entries in the problem data is correct, the data volumes are added together to determine the total data volume; When the amount of data for the preset unit of measurement term in any of the aforementioned problem data is incorrect, obtain third selection information; Based on the third selection information, the problematic data with incorrect data volume is modified, and the original record is retained. Then, the step of determining whether the data volume of the preset unit of measurement term in each of the problematic data is correct is performed based on the several problematic data containing the preset unit of measurement term.

9. An artificial intelligence-based system for extracting and classifying problems in natural resource supervision, characterized in that: The method for extracting and classifying natural resource supervision issues based on artificial intelligence as described in any one of claims 1-8 includes an execution module, a judgment module, and a calculation module; The execution module is used to obtain preset terms, obtain several online clues through web crawlers based on the preset terms, obtain preset keywords and a database, and create at least one set of question data based on the preset keywords and each of the online clues. The judgment module is used to determine, based on the regional attributes of the problem data and the database, whether there exists a problem database in the database that has the same regional attributes as the problem data; The calculation module is used to create another problem database in the database based on the regional attributes of the problem data when there is no problem database in the database with the same regional attributes as the problem data; then, it performs the step of determining whether there is a problem database with the same regional attributes as the problem data in the database based on the regional attributes of the problem data and the database; when there is a problem database with the same regional attributes as the problem data in the database, it moves the problem data into the problem database, adjusts the quantity attribute of the problem database according to the quantity of each problem data in the problem database, and sends a reminder message when the quantity attribute of the problem database changes.

Images