Natural resource asset checking and evaluating system based on AI technology

Abstract

The invention discloses a natural resource asset checking and evaluating system based on an AI technology, relates to the technical field of resource asset checking, and solves the technical problem of low efficiency caused by difficulty in reasonable arrangement according to the actual condition of each checking area in the existing means. Comprising a data acquisition module for acquiring influence events in a plurality of to-be-checked areas through a network platform and acquiring material object checking data of each to-be-checked area through an acquisition client; the region rating module is used for generating a checking difficulty coefficient and a checking priority coefficient corresponding to the to-be-checked region according to the influence event; the checking evaluation module is used for generating a checking scheme according to the checking difficulty coefficient and the checking priority coefficient of the to-be-checked area, and performing value evaluation on the corresponding to-be-checked area according to the material object checking data to obtain a corresponding natural resource asset value; and constructing a natural resource asset source checking database according to the real object checking data and the natural resource asset value of the to-be-checked area. And the checking efficiency of the natural resource assets is improved.

Description

Technical Field

[0001] This application belongs to the field of resource asset inventory technology, and relates to resource asset inventory technology, specifically a natural resource asset inventory and evaluation system based on AI technology. Background Art

[0002] The main work of the natural resource asset inventory project is to obtain the required data and information based on the special survey data that have been carried out on land, oceans, minerals, forests, grasslands, wetlands, etc., and calculate the asset prices on this basis.

[0003] Most of the existing natural resource asset inventory systems manually arrange the inventory work in a predetermined order and use computers to calculate the natural resource assets. However, the amount of data involved in the natural resource asset inventory process is extremely large; the inventory work cycle is also relatively long, and the situation in each inventory area is changing in real time. At the same time, since the natural resource assets in each inventory area are different, the requirements for the inventory are also different. Arranging the inventory work in a predetermined order will lead to unreasonable arrangements of the inventory work, which in turn leads to low efficiency of the inventory work. Therefore, a natural resource asset inventory and evaluation system based on AI technology is needed. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a natural resource asset inventory and evaluation system based on AI technology, which is used to solve the technical problem that the existing natural resource asset inventory is difficult to make reasonable arrangements according to the actual conditions of each inventory area, resulting in low efficiency.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a natural resource asset inventory and evaluation system based on AI technology, including: a data collection module, a regional rating module, an inventory and evaluation module, a database, and a natural resource asset inventory database;

[0006] The data acquisition module: acquires several influencing events in several areas to be checked through the network platform connected thereto; and acquires physical inventory data of each area to be checked through the acquisition client;

[0007] The regional rating module: obtains a number of influencing events in the area to be checked, and generates a check difficulty coefficient and a check priority coefficient for the area to be checked according to the influencing events;

[0008] The inventory assessment module generates an inventory plan based on the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried, and conducts a natural resource asset inventory on the corresponding area to be inventoried according to the inventory plan to obtain physical inventory data; and obtains physical inventory data, conducts a value assessment on the corresponding area to be inventoried based on the physical inventory data to obtain the corresponding natural resource asset value, and constructs a natural resource asset inventory database based on the physical inventory data and natural resource asset value of each area to be inventoried.

[0009] The present application evaluates each area to be investigated according to the influencing events in each area to be investigated to obtain the investigation difficulty coefficient and investigation priority coefficient of each area to be investigated; generates a corresponding investigation plan according to the investigation difficulty coefficient and investigation priority coefficient of each area to be investigated; conducts a natural resource asset investigation on the corresponding area to be investigated according to the investigation plan to obtain physical investigation data; conducts a value assessment on the corresponding area to be investigated according to the physical investigation data to obtain the corresponding natural resource asset value, and constructs a natural resource asset investigation database according to the physical investigation data and the natural resource asset value of each area to be investigated; arranges appropriate investigation personnel according to the characteristics of each area to be investigated, and conducts a natural resource asset investigation at appropriate events; and uses artificial intelligence in conjunction with the above process to greatly improve the investigation efficiency of natural resource assets.

[0010] Preferably, generating the inspection difficulty coefficient of the corresponding area to be inspected according to the influencing event includes:

[0011] Obtain a number of natural resource asset types in the area to be inventoried;

[0012] Input the impact event and the natural resource asset type of the corresponding inventory area into the impact scoring model to obtain the impact score of the corresponding impact event on the corresponding natural resource asset type; the impact scoring model is obtained through artificial intelligence model training;

[0013] The basic regional data of each area to be checked is obtained through the database; the inventory difficulty coefficient is generated according to the impact score and the basic regional data of the area to be checked; and the inventory priority coefficient is generated according to the impact event and its corresponding impact score.

[0014] Preferably, the impact scoring model is obtained by training an artificial intelligence model, including:

[0015] Obtain through the database a number of areas to be inventoried and their corresponding impact events, as well as the impact scores of the impact events on the natural resource asset types in the areas to be inventoried;

[0016] Integrate a number of impact events, natural resource asset types and impact scores into a number of training data and test data, use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model; specifically, input the impact events and natural resource asset types in the test data into the trained artificial intelligence model, and output the corresponding impact score; when the difference between the output impact score and the impact score recorded in the test data is within an acceptable range, perform the next set of test data for testing; when the difference between the output impact score and the impact score recorded in the test data is not within an acceptable range, adjust the relevant parameters of the artificial intelligence model, and re-use the current set of test data for testing until a set proportion of the test data passes the test; finally, an impact scoring model is obtained, whose input is the impact event and the natural resource asset type, and whose output is the corresponding impact score, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0017] Preferably, generating the inventory difficulty coefficient according to the impact score and the basic area data of the area to be inspected includes:

[0018] Obtain the impact score corresponding to each impact event and mark it as YPij; where i is the number of the impact event, and j is the number of the natural resource asset type in the area to be checked;

[0019] Extract the regional area score, geographical condition score and climate condition score from the regional basic data and mark them as QM, DP and QP respectively;

[0020] By formula The inventory difficulty coefficient of the corresponding area to be inventoried is calculated; wherein α1, α2, α3 and α4 are proportional coefficients, and the specific values ​​are set according to experience; i = 1, 2, ..., I; I is the total number of impact event numbers, j = 1, 2, ..., J; J is the total number of natural resource asset type numbers.

[0021] Preferably, generating the inventory priority coefficient according to the impact event and its corresponding impact score includes:

[0022] Obtain the impact score of each natural resource asset type in the inventory area for the impact event, and sum up each impact score to obtain the total impact score ZYP of the corresponding impact event;

[0023] Obtain the occurrence time of each impact event; fit the event impact curve ZYP(t) according to the total impact score and its corresponding occurrence time;

[0024] By formula The inventory priority coefficient YD is calculated, where β1 and β2 are proportional coefficients, and t1 and t2 are set time nodes.

[0025] Preferably, the generation of an inventory plan according to the inventory difficulty coefficient and the inventory priority coefficient of each area to be inspected includes:

[0026] Obtain the inspection priority coefficient of each area to be inspected; set the inspection time of each area to be inspected according to the inspection priority coefficient;

[0027] Obtain the difficulty coefficient of each area to be checked, and set the number of checkers for each area according to the difficulty coefficient; integrate the check time and number of checkers for each area to be checked into an check plan for the area to be checked.

[0028] Preferably, the method of conducting a value assessment on the corresponding area to be investigated based on the physical investigation data to obtain the corresponding natural resource asset value includes:

[0029] Obtain the price system table corresponding to the area to be checked through the database;

[0030] Extract physical inventory data and several inventory data; extract natural resource asset types and resource assets in the inventory data; obtain price evaluation standards corresponding to natural resource asset types in the price system table, and obtain natural resource asset values ​​corresponding to natural resource asset types based on the price evaluation standards and corresponding resource assets.

[0031] Preferably, the natural resource asset inventory database is constructed based on the physical inventory data and the natural resource asset value of each area to be inventoried, including:

[0032] Extract the distribution areas of each type of natural resource assets in the physical inventory data, and construct a natural resource asset distribution base map based on the distribution areas and the areas to be inventoried;

[0033] Extract the property owners of each natural resource asset type in the physical inventory data, and construct a property distribution layer based on the natural resource asset type, its corresponding distribution area and property owner;

[0034] Extract the natural resource asset value corresponding to each natural resource asset type, and construct a natural resource asset value layer based on the natural resource asset type, its corresponding distribution area and natural resource asset value;

[0035] Construct the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of each area to be inventoried in turn; integrate the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of the same area to be inventoried into its corresponding natural resource asset inventory map; store the physical inventory data, natural resource asset value and natural resource asset inventory map of the same area to be inventoried in the storage unit of the corresponding area to be inventoried, and construct the storage units of each area to be inventoried into a natural resource asset inventory database.

[0036] Preferably, the inventory assessment module is also used to obtain resource assets corresponding to each natural resource asset type in the physical inventory data corresponding to the area to be inventoried; and to obtain historical resource assets corresponding to each natural resource asset type in the historical physical inventory data corresponding to the last inventory of the same area to be inventoried through a database; and to perform a subtraction between resource assets of the same natural resource asset type and historical resource assets to obtain corresponding resource asset difference values;

[0037] Obtain the sum of the impact scores of each impact event on the same natural resource asset type and mark it as the total event impact score of the corresponding natural resource asset type; input the natural resource asset type and the total event impact score into the resource asset difference estimation model to obtain the estimated resource asset difference;

[0038] Determine whether the difference between the resource asset difference and the estimated resource asset difference is within the set difference threshold; if so, mark the inventory result of the corresponding natural resource asset type as normal; if not, mark the inventory result of the corresponding natural resource asset type as abnormal, and generate a re-inventory signal for the corresponding natural resource asset type.

[0039] Preferably, the resource asset difference estimation model is obtained by training an artificial intelligence model, including:

[0040] Acquire several historical physical inventory data through the database; extract the historical resource assets corresponding to each natural resource asset type in each historical inventory physical data; mark the difference between historical resource assets of the same natural resource asset type in adjacent historical inventory data as the resource asset difference of the corresponding natural resource asset type, and obtain the total event impact score of each historical impact event corresponding to the next inventory on the same natural resource asset type; integrate several natural resource asset types corresponding to each natural resource asset type, as well as the resource asset difference and the corresponding total event impact score into several groups of training data and test data;

[0041] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; ultimately, a resource asset difference estimation model is obtained, whose input is the natural resource asset type and the total event impact score, and whose output is the estimated resource asset difference, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0042] Compared with the prior art, the beneficial effects of this application are:

[0043] 1. This application evaluates each area to be investigated according to the influencing events in each area to be investigated to obtain the investigation difficulty coefficient and investigation priority coefficient of each area to be investigated; and generates a corresponding investigation plan according to the investigation difficulty coefficient and investigation priority coefficient of each area to be investigated; conducts a natural resource asset investigation on the corresponding area to be investigated according to the investigation plan to obtain physical investigation data; conducts a value assessment on the corresponding area to be investigated according to the physical investigation data to obtain the corresponding natural resource asset value, and constructs a natural resource asset investigation database according to the physical investigation data and the natural resource asset value of each area to be investigated; arranges appropriate investigation personnel according to the characteristics of each area to be investigated, and conducts a natural resource asset investigation at appropriate events; and uses artificial intelligence in conjunction with the above process to greatly improve the efficiency of natural resource asset investigation.

[0044] 2. This application uses historical resource asset differences to make abnormal judgments on current resource asset differences, which can promptly discover and correct inventory results and improve the accuracy of the final inventory data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is a schematic diagram of the principle of the natural resource asset inventory and evaluation system in this application;

[0047] Figure 2 Schematic diagram of the steps of the natural resource asset inventory and assessment method in this application. DETAILED DESCRIPTION

[0048] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0049] See also Figure 1-Figure 2 , the first aspect of the present application provides a natural resource asset inventory and evaluation system based on AI technology, including: a data acquisition module, a regional rating module, an inventory and evaluation module, a database, and a natural resource asset inventory database;

[0050] Data collection module: obtain several impact events in several areas to be investigated through the network platform connected to it; the network platform can be a computer or a cloud platform, which is used to record events related to the areas to be investigated; and obtain physical inventory data of each area to be investigated through the collection client; the collection client is a client used by staff, including smart phones, smart computers and other devices; the area to be investigated is the area where the natural resource asset inventory is required this time, and the impact event is the event related to each type of natural resource asset in the area to be investigated. It can be understood that the impact time obtained here is the impact event recorded from the end of the last inventory to the beginning of this inventory, and the inventory data is the relevant inventory data in the corresponding area to be investigated obtained by the staff; the specific data is determined according to the type of natural resource assets. For example, when investigating the forests owned by the whole people, the corresponding physical inventory data includes tree species, quantity, tree crown width and tree breast diameter;

[0051] Regional rating module: obtains several influencing events in the area to be checked, and generates the corresponding inventory difficulty coefficient and inventory priority coefficient of the area to be checked according to the influencing events; the inventory difficulty coefficient is an evaluation of the inventory difficulty of the area to be checked, and the higher the inventory difficulty coefficient, the greater the inventory difficulty of the area to be checked; the inventory priority coefficient is an evaluation of the current status of the area to be checked, and the higher the inventory priority coefficient, the more suitable the current area to be checked is for inventory work;

[0052] Inventory and evaluation module: Generate an inventory plan based on the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried. The inventory plan is to arrange the number of people and time for inventory work in the area to be inventoried based on the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; conduct a natural resource asset inventory of the corresponding area to be inventoried according to the inventory plan; and obtain physical inventory data, and conduct a value assessment of the corresponding area to be inventoried based on the physical inventory data to obtain the corresponding natural resource asset value. The natural resource asset value is the value after assessment of the corresponding natural resource asset type in the area to be inventoried; construct a natural resource asset inventory database based on the physical inventory data and natural resource asset value of each area to be inventoried; the natural resource asset inventory database is used to store relevant data generated during the inventory.

[0053] This embodiment evaluates each area to be inventoried according to the influencing events in each area to be inventoried to obtain the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; and generates a corresponding inventory plan according to the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; according to the inventory plan, a natural resource asset inventory is conducted on the corresponding area to be inventoried to obtain physical inventory data; based on the physical inventory data, a value assessment is conducted on the corresponding area to be inventoried to obtain the corresponding natural resource asset value, and a natural resource asset inventory database is constructed based on the physical inventory data and natural resource asset value of each area to be inventoried; according to the characteristics of each area to be inventoried, suitable inventory personnel are arranged to conduct natural resource asset inventories at suitable events; during this process, artificial intelligence is used in conjunction to greatly improve the efficiency of natural resource asset inventories.

[0054] Generate the inventory difficulty coefficient of the corresponding area to be inspected based on the impact event, including:

[0055] Obtain several types of natural resource assets in the area to be investigated, including forests owned by the whole people, grasslands owned by the whole people, wetlands owned by the whole people, water owned by the whole people, agricultural land, construction land, unused land and minerals, etc.; the above-mentioned natural resource asset types can be further subdivided; the higher the degree of subdivision, the more accurate the subsequent corresponding results will be.

[0056] Input the impact event and the natural resource asset type of the corresponding inventory area into the impact scoring model to score the impact of the corresponding impact event on the corresponding natural resource asset type; the impact scoring model is obtained through artificial intelligence model training;

[0057] The basic regional data of each area to be checked is obtained through the database; the inventory difficulty coefficient is generated according to the impact score and the basic regional data of the area to be checked; and the inventory priority coefficient is generated according to the impact event and its corresponding impact score.

[0058] The impact scoring model is obtained through artificial intelligence model training, including: obtaining a number of areas to be investigated and their corresponding impact events through the database, as well as the impact scores of the impact events on the natural resource asset types in the areas to be investigated; the impact score is the score given by experts based on the impact degree of the impact event on each natural resource asset type. The greater the impact degree, the higher the corresponding impact score; for example, the larger the degradation and desertification area corresponding to the event of forest land degradation and forest land desertification, the greater its impact on the forest resources in the corresponding area, and the higher the corresponding impact score;

[0059] Integrate a number of impact events, natural resource asset types and impact scores into a number of training data and test data, use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model; specifically, input the impact events and natural resource asset types in the test data into the trained artificial intelligence model, and output the corresponding impact score; when the difference between the output impact score and the impact score recorded in the test data is within an acceptable range, perform the next set of test data for testing; when the difference between the output impact score and the impact score recorded in the test data is not within an acceptable range, adjust the relevant parameters of the artificial intelligence model, and re-use the current set of test data for testing until a set proportion of the test data passes the test; finally, an impact scoring model is obtained, whose input is the impact event and the natural resource asset type, and whose output is the corresponding impact score, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0060] Generate an inventory difficulty factor based on the impact score and basic area data of the area to be inventoried, including:

[0061] Obtain the impact score corresponding to each impact event and mark it as YPij; where i is the number of the impact event, and j is the number of the natural resource asset type in the area to be checked;

[0062] The regional area score, geographical condition score and climate condition score in the regional basic data are extracted and marked as QM, DP and QP respectively; the regional area score is the score given by experts based on the total area of ​​the area to be inventoried. The larger the regional area, the greater the workload during the inventory process, and the larger the corresponding regional area score; the geographical condition score is the score given by experts to the inventory area based on the topographic and geomorphic features of the area to be inventoried. The more complex the topographic and geomorphic features of the area to be inventoried, the greater the difficulty in conducting the natural resource asset inventory, and the higher the corresponding geographical condition score; the climate condition score is the score given by experts based on the impact of the climate conditions of the corresponding area to be inventoried on the inventory work. The more diverse and severe the climate conditions in the area to be inventoried, the higher the difficulty in conducting the natural resource asset inventory, and the higher the corresponding climate condition score; it can be understood that the above-mentioned regional area score, geographical condition score and Climate condition scores can be obtained by training artificial intelligence models; for example, training a geographical condition scoring model for geographical condition scores; obtaining geographical feature data of the area to be investigated and inputting it into the geographical condition scoring model to obtain a geographical condition score; specifically, obtaining geographical feature data of several areas to be investigated and their corresponding geographical condition scores through a database, integrating the geographical feature data and the geographical condition scores into several training data and test data; using the training data to train the artificial intelligence model, and using the test data to test the trained artificial intelligence model; finally obtaining a geographical condition scoring model whose input is geographical feature data and output is the corresponding geographical condition score, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model; the regional area score and the climate condition score can also be obtained by training the corresponding models in a process similar to that of training the geographical condition scoring model.

[0063] By formula The inventory difficulty coefficient of the corresponding area to be inventoried is calculated; wherein α1, α2, α3 and α4 are proportional coefficients, and the specific values ​​are set according to experience; i = 1, 2, ..., I; I is the total number of impact event numbers, j = 1, 2, ..., J; J is the total number of natural resource asset type numbers.

[0064] This embodiment calculates the inventory difficulty coefficient of each area to be inventoried through the above formula; the more natural resource asset types there are in the area to be inventoried, the greater the corresponding inventory difficulty; the more impact events related to the natural resource asset types occur within the set period, the greater the corresponding inventory difficulty; the larger the regional area score, geographical condition score and climate condition score, the greater the impact on the natural resource asset inventory, and the greater the difficulty of natural resource asset inventory; therefore, the larger the inventory difficulty coefficient is set.

[0065] Generate an inventory priority coefficient based on the impact event and its corresponding impact scores, including: obtaining the impact score of each natural resource asset type of the impact event in the inventory area, and summing up each impact score to obtain the total impact score ZYP of the corresponding impact event;

[0066] Obtain the occurrence time of each impact event; fit the event impact curve ZYP(t) according to the total impact score and its corresponding occurrence time;

[0067] By formula The inventory priority coefficient YD is calculated; wherein β1 and β2 are proportional coefficients, and the specific values ​​are set according to experience; t1 and t2 are set time nodes. In this embodiment, the closer the time node is to the current time, the better; the inventory priority coefficients of each area to be inventoried are calculated by the above formula; the first term of the above formula represents the fluctuation of the impact of various influencing events in the recent area to be inventoried on the inventory of natural resource assets, and the second term represents the average impact of various influencing events in the recent area to be inventoried; the smaller the impact of the influencing event on the corresponding area to be inventoried, and the more stable the impact of the recent influencing event on the area to be inventoried; it means that the changes in the types of natural resource assets in the area to be inventoried at this time are relatively stable, and the inventory results obtained by the inventory of natural resource assets at this time are more accurate; the more suitable it is for the inventory of natural resource assets, and the accuracy of the inventory results of natural resource assets can be effectively guaranteed; therefore, the corresponding inventory priority coefficient is set larger.

[0068] Generate an inventory plan based on the inventory difficulty coefficient and inventory priority coefficient of each area to be inspected, including:

[0069] Obtain the inventory priority coefficient of each area to be inventoried; set the inventory time of each area to be inventoried according to the inventory priority coefficient. The larger the inventory priority coefficient, the earlier the corresponding inventory time. Specifically, the inventory time is the time when the inventory of the area to be inventoried begins. The higher the inventory priority coefficient, that is, the larger the value of the inventory priority coefficient, the more suitable the area to be inventoried is for natural resource asset inventory. The earlier the corresponding inventory time is. When there are enough staff, multiple areas to be inventoried can be considered for inventory at the same time according to the order of inventory priority coefficients from high to low. If there are not enough staff, after the inventory of the area to be inventoried is completed, the inventory priority coefficients of the remaining areas to be inventoried will be recalculated, and the area to be inventoried with the largest inventory priority coefficient will be used as the next inventory area, and the corresponding inventory time will be set.

[0070] Get the difficulty coefficient of each area to be checked, and set the number of checkers for each area according to the difficulty coefficient. Specifically, the formula The corresponding number of personnel for inspection YS is calculated, where BND is the set standard difficulty coefficient threshold; BZR is the standard number of personnel corresponding to the standard difficulty coefficient threshold; γ is the set condition coefficient, and the specific value is set according to experience; the larger the inspection difficulty coefficient, the greater the workload and difficulty of the corresponding area to be inspected, and a large number of staff are required to conduct the inspection while ensuring efficiency. Therefore, the corresponding number of inspection personnel is larger; the inspection time and number of inspection personnel of each area to be inspected are integrated into the inspection plan for the corresponding area to be inspected.

[0071] It is worth noting that in this embodiment, the inventory direction of each staff member is scored and statistically obtained to obtain the staff member's comprehensive efficiency score for each natural resource asset type; the higher the comprehensive efficiency score, the higher the work efficiency of the corresponding staff member in the inventory of that natural resource asset type; when determining the number of inventory personnel, selecting from high to low according to the comprehensive efficiency score of each staff member corresponding to the corresponding natural resource asset type can further improve the efficiency of the inventory.

[0072] According to the physical inventory data, the corresponding area to be inspected is evaluated for value to obtain the corresponding natural resource asset value, including: obtaining the price system table of the corresponding area to be inspected through the database;

[0073] Extract physical inventory data and several inventory data; extract natural resource asset types and resource assets in the inventory data; obtain price evaluation standards corresponding to natural resource asset types in the price system table, and obtain natural resource asset values ​​corresponding to natural resource asset types based on the price evaluation standards and corresponding resource assets.

[0074] The price system table is established based on the price system of the corresponding inventory area. It includes the types of natural resource assets and their corresponding price evaluation standards. The price evaluation standards are the unit values ​​of the corresponding natural resource assets, such as the price of one square meter of construction land; the resource assets are the quantity of the inventory results of the corresponding natural resource assets, such as 10,000 square meters of construction land.

[0075] A natural resource asset inventory database is constructed based on the physical inventory data and natural resource asset values ​​of each area to be inventoried, including: extracting the distribution areas of each type of natural resource asset in the physical inventory data, and constructing a natural resource asset distribution base map based on the distribution areas and the areas to be inventoried; the distribution areas are the distribution positions of natural resource assets in the areas to be inventoried; the natural resource asset distribution base map can reflect what kind of natural resource assets are in the areas to be inventoried, as well as the distribution of each natural resource asset.

[0076] Extract the property owners of each natural resource asset type in the physical inventory data, and construct a property distribution layer based on the natural resource asset type, the corresponding distribution area and the property owner; the property owner is the property owner of the natural resource asset type in the corresponding distribution area; the property distribution layer can reflect the ownership of the natural resource assets in each part of the area to be inventoried;

[0077] Extract the natural resource asset value corresponding to each natural resource asset type, and construct a natural resource asset value layer based on the natural resource asset type, the corresponding distribution area and the natural resource asset value; the natural resource asset value layer can reflect the asset status of each natural resource asset in the area to be checked;

[0078] Construct the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of each area to be inventoried in turn; integrate the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of the same area to be inventoried into its corresponding natural resource asset inventory map; store the physical inventory data, natural resource asset value and natural resource asset inventory map of the same area to be inventoried in the storage unit of the corresponding area to be inventoried, and construct the storage units of each area to be inventoried into a natural resource asset inventory database.

[0079] The inventory assessment module is also used to obtain resource assets corresponding to each natural resource asset type in the physical inventory data corresponding to the area to be inventoried; and to obtain historical resource assets corresponding to each natural resource asset type in the historical physical inventory data corresponding to the last inventory of the same area to be inventoried through the database; and to perform a subtraction between resource assets of the same natural resource asset type and historical resource assets to obtain the corresponding resource asset difference;

[0080] Obtain the sum of the impact scores of each impact event on the same natural resource asset type and mark it as the total event impact score of the corresponding natural resource asset type; input the natural resource asset type and the total event impact score into the resource asset difference estimation model to obtain the estimated resource asset difference;

[0081] Determine whether the difference between the resource asset difference and the estimated resource asset difference is within the set difference threshold; if so, mark the inventory result of the corresponding natural resource asset type as normal; if not, mark the inventory result of the corresponding natural resource asset type as abnormal, and generate a re-inventory signal for the corresponding natural resource asset type.

[0082] This embodiment uses historical resource asset differences to make abnormal judgments on current resource asset differences, and can timely discover and correct inventory results, thereby improving the accuracy of final inventory data.

[0083] The resource asset difference estimation model is obtained through artificial intelligence model training, including: obtaining a number of historical physical inventory data through a database; extracting the historical resource assets corresponding to each natural resource asset type in each historical inventory physical data; marking the difference between historical resource assets of the same natural resource asset type in adjacent historical inventory data as the resource asset difference of the corresponding natural resource asset type, and obtaining the total event impact score of each historical impact event corresponding to the next inventory on the same natural resource asset type; integrating a number of natural resource asset types corresponding to each natural resource asset type, as well as the resource asset difference and the corresponding total event impact score into several groups of training data and test data;

[0084] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; ultimately, a resource asset difference estimation model is obtained, whose input is the natural resource asset type and the total event impact score, and whose output is the estimated resource asset difference, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0085] It is understandable that after the completion of this inventory, that is, when the inventory results corresponding to each natural resource asset type are normal, the relevant data of the corresponding area to be inventoried will be integrated into historical inventory data.

[0086] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0087] How this application works:

[0088] The present application evaluates each area to be inventoried according to the influencing events in each area to be inventoried to obtain the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; and generates a corresponding inventory plan according to the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; conducts a natural resource asset inventory on the corresponding area to be inventoried according to the inventory plan to obtain physical inventory data; conducts a value assessment on the corresponding area to be inventoried according to the physical inventory data to obtain the corresponding natural resource asset value, and constructs a natural resource asset inventory database according to the physical inventory data and natural resource asset value of each area to be inventoried; arranges appropriate inventory personnel according to the characteristics of each area to be inventoried, and conducts a natural resource asset inventory at appropriate events; during this process, artificial intelligence is used to greatly improve the efficiency of natural resource asset inventory, and at the same time, abnormalities are judged on the current resource asset difference through historical resource asset difference, so that the inventory results can be discovered and corrected in time, thereby improving the accuracy of the final inventory data.

[0089] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. Natural resource asset inventory and evaluation system based on AI technology, including: Data collection module, regional rating module, inventory assessment module, database and natural resource asset inventory database; characterized in that, The data acquisition module: acquires several influencing events in several areas to be checked through the network platform connected thereto; and acquires physical inventory data of each area to be checked through the acquisition client; The regional rating module: obtains a number of influencing events in the area to be checked, and generates a check difficulty coefficient and a check priority coefficient for the area to be checked according to the influencing events; The inventory assessment module generates an inventory plan based on the inventory difficulty coefficient and inventory priority coefficient of each area to be inventoried; and obtains physical inventory data, conducts value assessment on the corresponding area to be inventoried based on the physical inventory data to obtain the corresponding natural resource asset value, and constructs a natural resource asset inventory database based on the physical inventory data and natural resource asset value of each area to be inventoried.

2. The natural resource asset inventory and evaluation system based on AI technology according to claim 1 is characterized in that: The generating of the inventory difficulty coefficient of the corresponding area to be inspected according to the influencing event includes: Obtain a number of natural resource asset types in the area to be inventoried; Input the impact event and the natural resource asset type of the corresponding inventory area into the impact scoring model to obtain the impact score of the corresponding impact event on the corresponding natural resource asset type; the impact scoring model is obtained through artificial intelligence model training; The basic regional data of each area to be checked is obtained through the database; the inventory difficulty coefficient is generated according to the impact score and the basic regional data of the area to be checked; and the inventory priority coefficient is generated according to the impact event and its corresponding impact score.

3. The natural resource asset inventory and evaluation system based on AI technology according to claim 2 is characterized in that: The impact scoring model is obtained through artificial intelligence model training, including: Obtaining from the database a number of areas to be investigated and a number of impact events corresponding thereto, as well as impact scores of the impact events on the natural resource asset types in the areas to be investigated; the impact scores are scores made by experts based on the degree of impact of the impact events on each type of natural resource asset; Integrate a number of impact events, natural resource asset types and impact scores into a number of training data and test data, use the training data to train the artificial intelligence model, and use the test data to test the trained artificial intelligence model; finally, obtain an impact scoring model whose input is the impact event and natural resource asset type, and whose output is the corresponding impact score, wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

4. The natural resource asset inventory and evaluation system based on AI technology according to claim 2 is characterized in that: The generation of the inventory difficulty coefficient according to the impact score and the basic area data of the area to be inspected includes: Obtain the impact score corresponding to each impact event and mark it as YPij; where i is the number of the impact event, and j is the number of the natural resource asset type in the area to be checked; Extract the regional area score, geographical condition score and climate condition score from the regional basic data and mark them as QM, DP and QP respectively; By formula The inventory difficulty coefficient of the corresponding area to be inventoried is calculated; wherein α1, α2, α3 and α4 are proportional coefficients; i=1, 2, ..., I; I is the total number of impact event numbers, j=1, 2, ..., J; J is the total number of natural resource asset type numbers.

5. The natural resource asset inventory and evaluation system based on AI technology according to claim 2 is characterized in that: The generation of the inventory priority coefficient according to the impact event and its corresponding impact score includes: Obtain the impact score of each natural resource asset type in the inventory area for the impact event, and sum up each impact score to obtain the total impact score ZYP of the corresponding impact event; Obtain the occurrence time of each impact event; fit the event impact curve ZYP(t) according to the total impact score and its corresponding occurrence time; By formula The inventory priority coefficient YD is calculated, where β1 and β2 are proportional coefficients, and t1 and t2 are set time nodes.

6. The natural resource asset inventory and evaluation system based on AI technology according to claim 1 is characterized in that: The generation of an inventory plan according to the inventory difficulty coefficient and the inventory priority coefficient of each area to be inspected includes: Obtain the inspection priority coefficient of each area to be inspected; set the inspection time of each area to be inspected according to the inspection priority coefficient; Obtain the difficulty coefficient of each area to be checked, and set the number of checkers for each area according to the difficulty coefficient; integrate the check time and number of checkers for each area to be checked into an check plan for the area to be checked.

7. The natural resource asset inventory and evaluation system based on AI technology according to claim 1 is characterized in that: The value of the corresponding natural resource assets is obtained by conducting a value assessment on the corresponding area to be investigated based on the physical inventory data, including: Obtain the price system table corresponding to the area to be checked through the database; Extract physical inventory data and several inventory data; extract natural resource asset types and resource assets in the inventory data; obtain price evaluation standards corresponding to natural resource asset types in the price system table, and obtain natural resource asset values ​​corresponding to natural resource asset types based on the price evaluation standards and corresponding resource assets.

8. The natural resource asset inventory and evaluation system based on AI technology according to claim 1 is characterized in that: The natural resource asset inventory database is constructed based on the physical inventory data and natural resource asset value of each area to be inventoried, including: Extract the distribution areas of each type of natural resource assets in the physical inventory data, and construct a natural resource asset distribution base map based on the distribution areas and the areas to be inventoried; Extract the property owners of each natural resource asset type in the physical inventory data, and construct a property distribution layer based on the natural resource asset type, its corresponding distribution area and property owner; Extract the natural resource asset value corresponding to each natural resource asset type, and construct a natural resource asset value layer based on the natural resource asset type, its corresponding distribution area and natural resource asset value; Construct the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of each area to be inventoried in turn; integrate the natural resource asset distribution base map, property distribution layer and natural resource asset value layer of the same area to be inventoried into its corresponding natural resource asset inventory map; store the physical inventory data, natural resource asset value and natural resource asset inventory map of the same area to be inventoried in the storage unit of the corresponding area to be inventoried, and construct the storage units of each area to be inventoried into a natural resource asset inventory database.

9. The natural resource asset inventory and evaluation system based on AI technology according to claim 1 is characterized in that: The inventory assessment module is also used to obtain resource assets corresponding to each natural resource asset type in the physical inventory data corresponding to the area to be inventoried; and to obtain historical resource assets corresponding to each natural resource asset type in the historical physical inventory data corresponding to the last inventory of the same area to be inventoried through the database; and to perform a subtraction between resource assets of the same natural resource asset type and historical resource assets to obtain the corresponding resource asset difference; Obtain the sum of the impact scores of each impact event on the same natural resource asset type and mark it as the total event impact score of the corresponding natural resource asset type; Input the natural resource asset type and the total score of the event impact into the resource asset difference estimation model to obtain the estimated resource asset difference; Determine whether the difference between the resource asset difference and the estimated resource asset difference is within a set difference threshold; If yes, the inventory result of the corresponding natural resource asset type will be marked as normal; If not, the inventory result of the corresponding natural resource asset type will be marked as abnormal, and a re-inventory signal for the corresponding natural resource asset type will be generated.

10. The natural resource asset inventory and evaluation system based on AI technology according to claim 9 is characterized in that: The resource asset difference estimation model is obtained through artificial intelligence model training, including: Acquire several historical physical inventory data through the database; extract the historical resource assets corresponding to each natural resource asset type in each historical inventory physical data; mark the difference between historical resource assets of the same natural resource asset type in adjacent historical inventory data as the resource asset difference of the corresponding natural resource asset type, and obtain the total event impact score of each historical impact event corresponding to the next inventory on the same natural resource asset type; integrate several natural resource asset types corresponding to each natural resource asset type, as well as the resource asset difference and the corresponding total event impact score into several groups of training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data; ultimately, a resource asset difference estimation model is obtained, whose input is the natural resource asset type and the total event impact score, and whose output is the estimated resource asset difference, wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

Images