System, method, and computer program product for compiling / updating geological maps

Abstract

The present invention discloses a system, method and computer program product for compiling / updating a geological map. The method comprises the following steps: receiving a compilation / updating request for a geological map; retrieving A geological basic data items from a geological database, evaluating the retrieved A geological basic data items according to usage, and selecting top N data items as candidate geological basic data items; retrieving B geological basic data items from the geological database, evaluating the retrieved B geological element class data items according to usage, and selecting top M data items as candidate geological element class data items; combining data sets (maps) corresponding to the N candidate geological basic data items as base maps with the M candidate geological element class data items respectively to obtain M*N / 2 candidate geological maps; receiving at least one geological map selected by a user from the M*N / 2 candidate geological maps, and using the selected at least one geological map as a compiled / updated geological map.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data processing, and in particular, to a system, method and computer program product for compiling / updating geological maps. Background Art

[0002] Geological maps are the scientific research results of geological surveys. Each geological map, created in different eras, employs different survey and analysis techniques, employing a wide variety of them. Furthermore, each map has varying spatial coverage and accuracy. The results expressed on these maps are iterative and repetitive, with varying content or portions of content.

[0003] In the information age, big data and artificial intelligence (AI) technologies are driving scientific and technological progress. In geology, big data and AI technologies have made it possible to construct geological big data. One aspect of geological big data involves compiling or updating geological maps using existing geological maps, basic geological data, and geological feature data. Summary of the Invention

[0004] The following description includes exemplary methods, systems, and computer program products that embody the present invention. However, it should be understood that, in one or more aspects, the described invention can be practiced without these specific details. In other cases, well-known structures and techniques are not shown in detail to avoid obscuring the present invention.

[0005] According to one aspect of the present invention, a system for compiling / updating a geological map is proposed, comprising: a user interface module configured to receive a compilation / update request for a geological map, wherein the request includes requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated; a geological basic data item acquisition module configured to retrieve A geological basic data items from a geological database storing a plurality of geological basic data items and a plurality of geological element class data items according to the requirements for the geological basic data items used in the geological map to be compiled / updated, evaluate the retrieved A geological basic data items according to usage, and select the top N geological basic data items ranked in the evaluation results as candidate geological basic data items, wherein N is a positive integer and N≤A; and a geological element class data item acquisition module configured to According to the requirements of the geological element class data items used in the geological map to be compiled / updated, B geological element class data items are retrieved from the geological database, and the retrieved B geological element class data items are evaluated according to usage, and the geological element class data items ranked top M in the evaluation results are selected as candidate geological element class data items, where M is a positive integer and M≤B; the synthesis module is configured to use the data sets (maps) corresponding to the N candidate geological basic data items as a base map and combine them with the M candidate geological element class data items respectively to obtain M*N / 2 candidate geological maps; wherein the user interface module is further configured to receive at least one geological map selected by the user from the M*N / 2 candidate geological maps, and the output module is configured to output the at least one geological map selected by the user as the compiled / updated geological map.

[0006] According to another aspect of the present invention, a method for compiling / updating a geological map is proposed, comprising: receiving a request for compiling / updating a geological map, wherein the request includes requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated; retrieving A geological basic data items from a geological database storing a plurality of geological basic data items and a plurality of geological element class data items according to the requirements for the geological basic data items used in the geological map to be compiled / updated, evaluating the retrieved A geological basic data items according to usage, and selecting the top N geological basic data items ranked in the evaluation results as candidate geological basic data items, wherein N is a positive integer and N≤A; selecting the top N geological basic data items according to the requirements for the geological basic data items used in the geological map to be compiled / updated, and selecting the top N geological basic data items ranked in the evaluation results as candidate geological basic data items. According to the requirements of geological element class data items used in the geological map to be compiled / updated, B geological element class data items are retrieved from the geological database, the retrieved B geological element class data items are evaluated according to usage, and the geological element class data items with the top M evaluation results are selected as candidate geological element class data items, where M is a positive integer and M≤B; the data sets (maps) corresponding to the N candidate geological basic data items are used as base maps and are respectively combined with the M candidate geological element class data items to obtain M*N / 2 candidate geological maps; at least one geological map selected by the user from the M*N / 2 candidate geological maps is received; and the at least one geological map selected by the user is output as the compiled / updated geological map.

[0007] According to yet another aspect of the present invention, a computer program product is provided. The computer program product includes program instructions, and the program instructions can be executed by a computing device to enable the computing device to perform the method described above.

[0008] According to yet another aspect of the present invention, a computer system is provided, comprising: a memory; and at least one processor operatively coupled to the memory and configured to execute the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The invention itself, as well as the mode of use, objects, features and advantages of its preferred embodiments, may be better understood by reading the following detailed description of illustrative embodiments with reference to the accompanying drawings in which:

[0010] Figure 1A The schematic structure of metadata included in geological basic data items in existing geological databases is shown;

[0011] Figure 1B shows exemplary geological basic data items stored in an existing geological database;

[0012] Figure 2A The schematic structure of metadata contained in geological feature class data items in existing geological databases is shown;

[0013] Figure 2B shows exemplary geological feature class data items stored in an existing geological database;

[0014] Figure 3A Parameters used to evaluate the use of geological basic data items according to an embodiment of the present invention are shown;

[0015] Figure 3B Showing a partial exemplary record of usage of geological basic data items according to an embodiment of the present invention;

[0016] Figure 4A Parameters used to evaluate the usage of geological element data items according to an embodiment of the present invention are shown;

[0017] Figure 4B Showing some exemplary records of usage of geological element data items according to an embodiment of the present invention;

[0018] Figure 5 A structural block diagram of a system for compiling / updating a geological map according to an embodiment of the present invention is shown;

[0019] Figure 6 A flowchart of a method for compiling / updating a geological map according to an embodiment of the present invention is shown;

[0020] Figure 7 The embodiment of the present invention is shown Figure 6 A flowchart of a method for evaluating the retrieved A geological basic data items according to usage conditions in the method shown;

[0021] Figure 8 The embodiment of the present invention is shown Figure 6 A flowchart of a method for evaluating the retrieved B geological feature class data items according to usage conditions in the method shown; and

[0022] Figure 9 An example of using the system and method of the present invention to compile / update a geological map is shown. DETAILED DESCRIPTION

[0023] Embodiments of the present invention are described below with reference to the accompanying drawings. In the following description, many specific details are set forth in order to provide a more complete understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be implemented without some of these specific details. Furthermore, it should be understood that the present invention is not limited to the specific embodiments described. Rather, any combination of the following features and elements may be considered to implement the present invention, regardless of whether they relate to different embodiments. Furthermore, the specific steps of the methods of different embodiments are not strictly sequential, that is, where a method includes a first step and a second step, the first step may be performed before the second step, or the second step may be performed before the first step.

[0024] As mentioned above, in the field of geology, big data and AI technologies have made it possible to construct geological big data. One aspect of geological big data includes compiling or updating geological maps using existing geological maps, basic geological data, and geological feature class data. Generally speaking, existing geological databases can store existing geological maps, basic geological data, and geological feature class data. Among the multiple geological basic data items contained in a geological database, one is the existing geological map data for a specific region, including basic geographic maps, geological maps, remote sensing images, DEM data, etc., which can serve as the base map for the geological map to be compiled or the foundation for the geological map to be updated. Each geological basic data item contains metadata that describes the relevant information of the geological basic data item for retrieval.

[0025] Figure 1A The schematic structure of the metadata contained in the geological basic data items in the existing geological database is shown. The metadata includes fields such as data number, element (set) name, subject, location, latitude and longitude range, data type, scale denominator, precision, production year, data format, coordinate system and related parameters, data version, source organization, author, and data set (map) storage location. Those skilled in the art will know that using Figure 1A The metadata structure contained in the geological basic data items represented in the table is only one representation method. Other metadata representation methods may also be used, such as text format, XML format, etc. The metadata of the geological basic data items in the geological database may be stored using relational tables in a relational database or an XML database, and the present invention is not limited to this.

[0026] Figure 1B The following shows exemplary geological basic data items stored in existing geological databases. Figure 1BThe table shown can be stored in a relational database or an XML database. Only five geological basic data items are shown schematically here. It is known to those skilled in the art that thousands of geological basic data items can be stored in a geological database. These geological basic data items can be stored in Figure 1A The metadata structure shown. When compiling / updating a geological map, you can first retrieve the required geological basic data items from the geological database and use the dataset (map) therein as the base map for compiling / updating the geological map. When retrieving, you can make requirements for the corresponding important fields of the geological basic data items, that is, give specific requirements for the subject, location, latitude and longitude range, data type, scale, and production year. It should be noted here that Figure 1A and Figure 1B The data types in the dataset are divided into two types: vector and raster. The inventors have determined that the corresponding scales are related by: raster resolution R ≈ [geological map scale denominator D / 2000]; geological map scale denominator D ≈ [2000 * raster resolution R]. Those skilled in the art can convert scales for different data types when retrieving and utilizing information related to the scale denominator.

[0027] In addition, one of the multiple geological element class data items contained in the geological database is the latest research result of a certain area obtained by geologists through field surveys or indoor research, including single or multiple elements (sets) such as strata, intrusive rocks, metamorphic rocks, faults, etc. in the area, and is the core data used to compile / update geological maps.

[0028] Figure 2A The schematic structure of the metadata contained in the geological element data items in the existing geological database is shown. The metadata includes fields such as data number, element (set) name, subject, location, latitude and longitude range, data type, scale denominator, precision, data format, coordinate system and related parameters, year, source, author, and data set (map) storage location. Those skilled in the art will know that using Figure 2A The metadata structure contained in the geological feature class data item is only one way of representation. Other ways of expressing metadata can also be used, such as text format, XML format, etc. The metadata of the geological feature class data item in the geological database can be stored using the relational table in the relational database.

[0029] An XML database may be used for storage, but the present invention is not limited thereto.

[0030] Figure 2B exemplarily geological feature class data items stored in existing geological databases are shown. Figure 2BThe table shown can be stored in a relational database or an XML database. Only seven geological element class data items are shown schematically here. It is known to those skilled in the art that thousands of geological element class data items can be stored in a geological database. These geological element class data items can be stored in Figure 2A The metadata structure shown. When compiling / updating a geological map, the required geological feature class data items can be retrieved from the geological database as the geological feature class data items to be compiled or updated. When retrieving, requirements can be made for the corresponding entries of the geological feature class data items, that is, specific requirements can be given for the subject, location, latitude and longitude range, data type, scale, accuracy, data format, coordinate system and year. It should be noted here that Figure 2A and Figure 2B The data types in the dataset are also divided into two types: vector and raster. The inventors have determined that the corresponding scales exist in the following relationship: raster resolution R ≈ [geological map scale denominator D / 2000]; geological map scale denominator D ≈ [2000 * raster resolution R]. Those skilled in the art can perform scale conversion for different data types when retrieving and utilizing scale-related information.

[0031] The retrieved geological basic data items and geological feature class data items need to have the same or similar contents in the fields "Location" and "Latitude and Longitude Range". Then, the dataset (map) in the retrieved geological basic data items is used as the base map, and the retrieved geological feature class data items are synthesized with the base map to obtain the compiled / updated geological map.

[0032] At present, the method of compiling / updating geological map data mainly relies on manpower, that is, geologists, scholars and professionals use their personal knowledge and experience to retrieve multiple geological basic data items and multiple geological element class data items, compare the different types of geographic data, geological data, data and explanatory materials already available in the area where the geological map is to be compiled / updated, and after comparison, analysis and judgment, screen out the geological basic data items that meet the mapping destination and the geological element class data items corresponding to the same area and longitude and latitude range, and then synthesize the two to compile / update the geological map.

[0033] The existing geological map compilation / updating methods rely solely on the subjective experience of geologists and technicians to screen data. On the one hand, this is inefficient and consumes a lot of time and energy of geologists and scholars. On the other hand, there are also problems such as low utilization of existing results and duplication of investment. On the other hand, the compiled / updated geological map results are related to the personal qualities of geologists and technicians in geological exploration, cartography, and map compilation, and the quality is very unstable.

[0034] In order to solve the problems existing in the prior art, the present invention considers utilizing the existing user experience in compiling / updating geological maps to assist geologists and technicians in screening data. Specifically, a system, method, and computer program product for compiling / updating geological maps are disclosed. The method comprises: receiving a request for compiling / updating a geological map, the request including requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated; based on the requirements for the geological basic data items used in the geological map to be compiled / updated, retrieving A geological basic data items from a geological database storing multiple geological basic data items and multiple geological element class data items, evaluating the retrieved A geological basic data items based on usage, and selecting the top N geological basic data items ranked by the evaluation results. , as candidate geological basic data items, where N is a positive integer and N ≤ A; based on the requirements for geological element class data items used in the geological map to be compiled / updated, retrieve B geological element class data items from the geological database, evaluate the retrieved B geological element class data items based on their usage, and select the top M geological element class data items in the evaluation results as candidate geological element class data items, where M is a positive integer and M ≤ B; use the datasets (maps) corresponding to the N candidate geological basic data items as base maps and combine them with the M candidate geological element class data items to obtain M*N / 2 candidate geological maps; receive at least one geological map selected by the user from the M*N / 2 candidate geological maps, and output the at least one geological map selected by the user as the geological map to be compiled / updated. This method can objectively, efficiently, and accurately utilize existing achievements in the geological mapping process, thereby solving the problems of low utilization rate and repeated investment in the geological mapping process, and establishing high-value and highly recognized geological maps.

[0035] Evaluation of geological basic data items based on usage requires recording usage and evaluation of usage. Figure 3A The following figure shows the parameters that can be used to evaluate the use of geological basic data items according to an embodiment of the present invention, including the institutional reputation score Eo of the geological basic data item, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used. And the percentage K1 of the number of times n1 is used in the total number of times of use of all retrieved A geological basic data items. The evaluation result can be used as the recommendation level score S of the geological basic data item. Here, the first two parameters can use fixed values, and the latter parameters are related to the specific usage and need to be calculated in combination with the specific usage. In order to obtain Figure 3A Some parameters in, such as the number of times it is used n1, the average user rating score within the number of times it is used And the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, Figure 3BFIG. 4 shows a partial exemplary record of the usage of geological basic data items according to an embodiment of the present invention. Figure 3B The records shown can be gradually added as the user's usage increases. The records can be stored in a database table, a general EXCEL table, or an XML database. Figure 3A The structure is integrated into Figure 1A In this way, other fixed information, such as the institution reputation score (Eo), the author reputation score (E1a), and Figure 3B The calculated information is integrated into the geological basic data items, in other words, the updated Figure 1B Will contain information about the usage. Figure 3A The information related to the usage of the structure is stored in a separate data table or other data form. Figure 1B The information is associated with each other using the data number as the primary key.

[0036] Similarly, evaluating geological feature data items based on usage also requires recording usage and evaluation of usage. Figure 4A The following figure shows the parameters that can be used to evaluate the use of geological element data items according to an embodiment of the present invention, including the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used. And the percentage K2 of the number of times n2 is used in the total number of times B geological basic data items are retrieved. The evaluation result can be used as the recommendation level score SS of the geological feature data item. Here, the first parameter can use a fixed value, and the following parameters are related to the specific usage and need to be calculated in combination with the specific usage. In order to obtain Figure 4A Some parameters in, such as the number of times it is used n2, the average user rating score within the number of times it is used And the percentage K2 of the number of times n2 is used in the total number of times B geological basic data items are retrieved, Figure 4B FIG. 4 shows a partial exemplary record of the usage of geological element data items according to an embodiment of the present invention. Figure 4B The records shown can also be gradually added as the user's usage increases. The records can be stored in a database table, a general EXCEL table, or an XML database. Similarly, those skilled in the art will know that Figure 4A The structure is integrated into Figure 2A In this way, other fixed information, such as author reputation score (E2a) and Figure 4B The calculated information is integrated into the geological basic data items, in other words, the updated Figure 2BWill contain information about the usage. Figure 4A The information related to the usage of the structure is stored in a separate data table or other data form. Figure 2B The information is associated with each other using the data number as the primary key.

[0037] Those skilled in the art will know that Figure 3A 、 Figure 3B 、 Figure 4A and Figure 4B The format shown is a schematic structure. Those skilled in the art may use other structures to describe this information as needed, and the present invention is not limited thereto.

[0038] Figure 5 FIG. 5 shows a structural block diagram of a system 500 for compiling / updating a geological map according to an embodiment of the present invention. Figure 5 The system 500 includes a user interface module 510, a geological basic data item acquisition module 520, a geological element class data item acquisition module 530, a synthesis module 540 and an output module 550. Figure 5As shown, the user interface module 510 is configured to receive a geological map compilation / update request from a user 502, wherein the request includes requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated. The geological basic data item acquisition module 520 is configured to retrieve A geological basic data items from a geological database 501 storing multiple geological basic data items and multiple geological element class data items based on the requirements for the geological basic data items used in the geological map to be compiled / updated, evaluate the retrieved A geological basic data items based on their usage, and select the top N geological basic data items ranked in the evaluation results as candidate geological basic data items, where N is a positive integer and N≤A. The geological element data item acquisition module 530 is configured to retrieve B geological element data items from the geological database 501 based on the geological element data item requirements for the geological map to be compiled / updated. The retrieved B geological element data items are evaluated based on usage, and the top M geological element data items ranked in the evaluation results are selected as candidate geological element data items, where M is a positive integer and M ≤ B. The synthesis module 540 is configured to combine the datasets (maps) corresponding to the N candidate geological basic data items with the M candidate geological element data items as a base map, thereby obtaining M*N / 2 candidate geological maps. The user interface module 510 is further configured to receive at least one geological map selected by the user 502 from the M*N / 2 candidate geological maps. The output module 550 is configured to output the at least one geological map selected by the user 502 as the geological map to be compiled / updated. Among the above parameters, A and B are the specific numbers of retrieved data items and are objective. N and M are parameters set by the user. For example, the user can set M=N=3 or other values.

[0039] In one embodiment, reference Figure 1A and Figure 2AThe requirements for the geological basic data items used for the geological maps to be compiled / updated include the requirements for the following fields of the metadata of the geological basic data items: subject, location area, longitude and latitude range, data type, scale denominator, accuracy, and production year; and the requirements for the geological feature class data items used for the geological maps to be compiled / updated include the requirements for the following fields of the metadata of the geological feature class data items: subject, location area, longitude and latitude range, data type, scale denominator, accuracy, and year, where the location area and longitude and latitude range of the above geological feature class data items are the same as those of the above geological basic data items. Thus, the geological basic data item acquisition module 520 and the geological feature class data item acquisition module 530 can respectively retrieve the corresponding data items from the geological database 501 according to the requirements for the respective fields of the metadata of the geological basic data items and the requirements for the respective fields of the metadata of the geological feature class data items. The retrieval by the geological basic data item acquisition module 520 and the geological feature class data item acquisition module 530 is sometimes an iterative process. For example, if the retrieved data item A < N or B < M, it may be necessary to re-enter the retrieval conditions and retrieve again; or modify the values of M and N, etc.

[0040] In one implementation, the geological basic data item acquisition module 520 needs to utilize Figure 3A the given parameter fields to evaluate the A retrieved geological basic data items according to their usage. Specifically, in the requirements for these parameters, the user can set a scoring system according to needs (for example, the user can use a percentage system, a decimal system, or even a normalized number, etc.) to set or obtain specific values. Figure 3A Among the parameters, some parameters can be directly set by the user, such as the institution reputation score (Eo) and the author reputation score (E1a). These two parameters can also be obtained through methods such as user research. Here, it is assumed that according to the scoring system set by the user, the values of these two parameters have been obtained. For other geological basic data item parameters, namely the number of times of use n1, the average user evaluation score and the percentage K1 of the number of times of use n1 of all the retrieved A geological basic data items in the total number of times of use can be statistically calculated using, for example, Figure 3B the given specific usage. Specifically, the number of times of use n1 can be obtained by counting Figure 3B the same data number or the same element (set) name. Since A data items are retrieved, it is necessary to count the number of times of use n1 of each of the A geological basic data items j (j = 1, A). For a specific geological basic data item, if the number of times of use is n1 and the user evaluation score E1 for each use i (i = 1 to n1), then the average user rating score within the number of times of use The percentage of the number of times n1 is used in the total number of times A geological basic data items are retrieved Specifically, the geological basic data item acquisition module 520 can be further configured to: first obtain the usage of each of the retrieved A geological basic data items, wherein the usage of a geological basic data item includes the number of times it has been used n1, the user evaluation score E1 for each use, and the number of times it has been used. i (i = 1 to n1); then obtain the institutional reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used for each of the retrieved A geological basic data items And the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, where Finally, based on the retrieved A geological basic data items, the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used And the percentage K1 of the number of times n1 is used in the total number of times of use of all the retrieved A geological basic data items, and the recommendation level score S of each geological basic data item of the multiple geological basic data items is obtained as the evaluation result.

[0041] There may be multiple implementations of how the geological basic data item acquisition module 520 obtains the recommendation level score S of the geological basic data item based on these parameters, because different models may be established to calculate the recommendation level score S.

[0042] In one embodiment, the recommendation level score S can be performed using a pre-trained first neural network model. In this embodiment, a pre-trained first neural network model is required. Neural network models are currently the most commonly used models in artificial intelligence (AI). AI refers to the intelligence of a machine when it is able to make decisions based on information, which maximizes the chance of success in a given topic. More specifically, AI can learn from a data set to solve problems and provide relevant recommendations. Artificial neural networks (ANNs) are models of how the nervous system operates. The basic units are called neurons, which are generally organized into layers. ANNs work by simulating a large number of interconnected processing units, which are similar to abstract versions of neurons. In an ANN, there are typically three parts, including an input layer with units representing the input domain, one or more hidden layers, and an output layer with one or more units representing the target domain. These units are connected with different connection strengths or weights. Input data is provided to the first layer, and values are propagated from each neuron to neurons in the next layer. At a basic level, each layer of a neural network includes one or more operators or functions that are operably coupled to the output and input. The output of the activation function that evaluates each neuron using the provided input is referred to herein as activation. Complex neural networks are designed to mimic how the human brain works, making it possible to train computers to solve poorly defined abstractions and problems for which training data is not readily available. Neural network models are typically trained using predefined training examples. During training, the connection weights of different layers of the neural network model are iteratively adjusted. When the results converge for all training examples or meet predetermined conditions, the neural network model is considered trained. At this point, the weights between layers are determined, and the output can be inferred for a new test example.

[0043] The first neural network model can adopt common models such as MLP, CNN, RNN, GNN, LSTM, transformer, etc. In the specific implementation of the first neural network model, first, in order to train the first neural network model, it is necessary to obtain training samples, and then use the training samples to train the first neural network model. Specifically, the experience recommendation level score of each geological basic data item in a number of geological basic data items by domain experts can be obtained first, and then the institutional reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of each geological basic data item of the several geological basic data items can be obtained. The percentage K1 of the number of times the geological basic data item is used as the input vector, and the experience recommendation level score of each geological basic data item by experts in the field is used as the output to train the first neural network model. In other words, the vector [the institutional reputation score Eo of each geological basic data item, the author's reputation score E1a, the number of times it is used n1, the average user rating score within the number of times it is used] The percentage K1 of the number of times n1 is used in the total number of times of all retrieved A geological basic data items is used, and the experience recommendation level score S of the geological basic data item by the domain experts constitutes a training sample. During the training process, using normalized data for these data will help the first neural network model to converge quickly. If the first neural network model converges or meets the predetermined conditions, the training of the first neural network model is completed and it can be used to calculate the recommendation level score S of the geological basic data item. In the calculation process, the normalized institution reputation score Eo, author reputation score E1a, number of times n1 is used, and the average user rating score within the number of times a geological basic data item is used can be used to calculate the recommendation level score S of the geological basic data item. And the percentage K1 of the number of times n1 is used in the total number of times all the retrieved A geological basic data items are used is input as an input vector to the first neural network model, and the output of the first neural network model obtained is the recommendation level score S of the geological basic data item. The normalization of the institution's reputation score Eo and the author's reputation score E1a can be directly divided by the recommendation level score S, for example, the percentage can be normalized by Eo / 100. The normalization of the number of times n1 is used can be as needed. For example, if the maximum number of times each of the retrieved A data items is n, n1 / n can be used as the normalized number of times used. Using the above-mentioned first neural network model to evaluate based on usage not only utilizes the experience of domain experts, but also utilizes the experience of users, and the evaluation results obtained are more accurate and objective.

[0044] In one embodiment, a first empirical model can be set based on the experience of domain experts to calculate the recommendation level score S. For example, in this model, for a geological basic data item, the recommendation level score S includes a recommendation score S1 and a reward score S2, and Among them, the recommendation score S1 and reward score S2 are:

[0045]

[0046] Where w11, w12, and w13 are user-defined weights, F1 is the user-defined threshold for the number of uses n1, G1, H1, and P1 are user-defined reward scores for different conditions, and K11, K12, and K13 are different thresholds for the percentage of the number of uses n1 relative to the total number of uses of all retrieved A geological basic data items. Using the first empirical model described above for evaluation based on usage not only leverages the experience of domain experts but also users. Furthermore, the model is computationally efficient, fast, and requires no pre-training. The resulting evaluation results are relatively accurate and objective.

[0047] In one embodiment, in the first empirical model, S is based on a percentage system. In the evaluation results of Eo and E1a, if the evaluation result is very good, Eo=E1a=9 points; if the evaluation result is good, Eo=E1a=6 points; if the evaluation result is average, Eo=E1a=5 points. The user evaluation score E1 for each use is i (i=1 to n1) uses a 10-point system, where the higher the score, the better the data quality of the specific geological basic data item, and wherein w11=80%, w12=10%, w13=10%, F1=50, G1=20, H1=10, P1=5, K11=50%, K12=30%, K13=10%. In this embodiment, the user needs to give a score of 0-10 for each data item, for example Figure 3B This is the scoring mechanism adopted.

[0048] Similarly, in one embodiment, the geological element data item acquisition module 530 evaluates the retrieved multiple geological element data items according to their usage, including the geological element data item acquisition module 530 being further configured to: obtain the usage of each of the retrieved B geological element data items, wherein the usage of a geological element data item includes the number of times it has been used n2, the user evaluation score E2 for each use, and the number of times it has been used. i (i = 1 to n2); obtain the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each of the B geological element data items retrieved And the number of times n2 is used accounts for all the retrieved B geological feature classes

[0049] The percentage of the total number of times a data item is used, K2, where And the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological element data item based on the retrieved B geological element data items And the percentage K2 of the number of times n2 is used in the total number of times of use of all the retrieved B geological element class data items, and the recommendation level score SS of each geological element class data item of the multiple geological element class data items is obtained as the evaluation result.

[0050] There may be multiple implementations of how the geological element data item acquisition module 530 obtains the recommendation level score SS of the geological element data item based on these parameters, because different models may be established to calculate the recommendation level score SS of the geological element data item.

[0051] In one embodiment, the recommendation level score SS of the geological element data item can be performed using a pre-trained second neural network model. The second neural network model can be trained in the following manner: obtaining the empirical recommendation level score of each geological element data item from a number of geological element data items by domain experts; then combining the institution reputation score E2o, author reputation score E2a, number of times it has been used n2, and average user rating score within the number of times it has been used for each geological element data item in the number of geological element data items. The percentage K2 of the number of times n2 is used in the total number of times all the retrieved B geological element data items are used is used as the input vector, and the experience recommendation level score of each geological element data item by experts in the field is used as the output to train the second neural network model; and when the second neural network model converges or meets the predetermined conditions, the training of the second neural network model is completed. The trained second neural network model can then be used to calculate the recommendation level score SS of the geological element data item. Specifically, the author's reputation score E2a, the number of times it is used n2, and the average user rating score within the number of times it is used can be used to calculate the recommendation level score SS of the geological element data item. The percentage K2 of the number of times n2 is used relative to the total number of times B geological feature data items are retrieved is used as an input vector and fed into the trained second neural network model. The output of the trained second neural network model is the recommendation level score SS for the geological feature data item. Similarly, the above data is preferably normalized. Using the above second neural network model to perform an evaluation based on usage not only leverages the experience of domain experts but also the experience of users, resulting in a more accurate and objective evaluation result.

[0052] Similarly, the recommendation level score SS of the geological element data item can be calculated by setting a second empirical model based on the experience of domain experts. In one embodiment, the recommendation level score SS of each geological element data item is calculated based on the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used. The recommendation level score of each of the B geological element class data items is calculated using the following second empirical model: In the second model, for a geological element class data item, the recommendation level score SS includes a recommendation score SS1 and a reward score SS2, and Among them, the recommendation score SS1 and the reward score SS2 are:

[0053]

[0054] Where w21 and w22 are user-defined weights, F2 is the user-defined threshold for the number of uses n2, G2, H2, and P2 are user-defined reward scores for different conditions, and K21, K22, and K23 are different thresholds for the percentage of the number of uses n2 relative to the total number of uses of all retrieved B geological feature data items. Using this second empirical model for evaluation based on usage not only leverages the experience of domain experts but also users. Furthermore, the model is computationally efficient, fast, and requires no pre-training. The resulting evaluation results are relatively accurate and objective.

[0055] In one embodiment, in the second empirical model, SS uses a percentage system. In the evaluation result of E2a, if the evaluation result is very good, E2a=9 points; if the evaluation result is good, E2a=6 points; if the evaluation result is average, E2a=5 points. The user evaluation score E2a for each use is i (i=1 to n2) uses a 10-point system, where the higher the score, the better the data quality of the specific geological element class data item, and among them, w21=80%, w22=20%, F2=50, G2=20, H2=10, P2=5, K21=50%, K22=30%, K23=10%.

[0056] When the synthesis module 540 uses the data sets (maps) corresponding to the N selected candidate geological basic data items as base maps and combines them with the M candidate geological element class data items to obtain M*N / 2 candidate geological maps, if the synthesis module 540 determines that a specific candidate geological basic data item among the N candidate geological basic data items contains multiple base maps with different resolutions during synthesis, the user interface module 510 receives the resolution used for compiling / updating the geological map input by the user 502, and then the synthesis module 540 converts the multiple base maps with different resolutions into multiple base maps using the resolution used for compiling / updating the geological map, and then combines them. In this way, by using the resolution provided by the user to convert maps of different resolutions, the base maps obtained can be better aligned and combined, and the obtained geological map effect is better. During the combination process, it is necessary to match the vector map with the raster data. The matching relationship between the geological map scale and the raster resolution during matching is:

[0057] Grid resolution R ≈ [geological map scale denominator D / 2000]; and

[0058] The denominator of the geological map scale D≈[2000*grid resolution R].

[0059] In one embodiment, the present invention further discloses a method for compiling / updating a geological map. Figure 6 FIG. 6 is a flow chart of a method 600 for compiling / updating a geological map according to an embodiment of the present invention. Figure 6 As shown, in step S610, a request for compiling / updating a geological map is received, the request including requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated. In step S620, based on the requirements for the geological basic data items used in the geological map to be compiled / updated, A geological basic data items are retrieved from a geological database storing multiple geological basic data items and multiple geological element class data items. The retrieved A geological basic data items are evaluated based on usage, and the geological basic data items ranked in the top N in the evaluation results are selected as candidate geological basic data items, where N is a positive integer and N≤A. In step S630, based on the requirements for the geological element class data items used in the geological map to be compiled / updated, B geological element class data items are retrieved from the geological database, and the retrieved B geological element class data items are evaluated based on usage, and the geological element class data items ranked in the top M in the evaluation results are selected as candidate geological element class data items, where M is a positive integer and M≤B. In step S640, the datasets (maps) corresponding to the N candidate geological basic data items are used as base maps and combined with the M candidate geological feature class data items to obtain M*N / 2 candidate geological maps. In step S650, at least one geological map selected by the user from the M*N / 2 candidate geological maps is received. In step S660, the at least one geological map selected by the user is output as the compiled / updated geological map.

[0060] In one embodiment of method 600, the requirements for the geological basic data items used in the geological map to be compiled / updated include requirements for the following items of metadata of the geological basic data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy, and production year; and wherein, the requirements for the geological feature class data items used in the geological map to be compiled / updated include requirements for the following fields of metadata of the geological feature class data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy, and year, wherein the geological feature class data item contains the same or similar location and longitude and latitude range as the geological basic data item.

[0061] In one embodiment, Figure 7 The embodiment of the present invention is shown Figure 6 The flowchart of the method 700 used to evaluate the retrieved A geological basic data items according to the usage conditions in the method shown. Figure 7 In step S710, the usage of each of the retrieved A geological basic data items is obtained, wherein the usage of a geological basic data item includes the number of times it is used n1, the user evaluation score E1 for each use, and the number of times it is used. i(i=1 to n1). In step S720, the institution reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of each of the retrieved A geological basic data items are obtained. And the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, where In step S730, based on the institution reputation score Eo, author reputation score E1a, number of times used n1, average user rating score within the number of times used, and the number of times the geological basic data items are retrieved, the user rating score is calculated. And the percentage K1 of the number of times n1 is used in the total number of times of all retrieved A geological basic data items, and the recommendation level score S of each geological basic data item of the multiple geological basic data items is obtained as the evaluation result

[0062] In one embodiment, Figure 7 Step S730 is executed using a pre-trained first neural network model, and the institutional reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of a geological basic data item are combined into a matrix. And the percentage K1 of the number of times n1 is used to the total number of times all the retrieved A geological basic data items are used is used as an input vector and input into the trained first neural network model. The output of the trained first neural network model is obtained as the recommendation level score S of the geological basic data item.

[0063] In one embodiment, the first neural network model is trained in the following manner: first, the experience recommendation level score of each geological basic data item in a plurality of geological basic data items is obtained by domain experts; then, the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used are calculated. The first neural network model is trained by taking the percentage K1 of the number of times n1 is used to the total number of times A geological basic data items are retrieved as input vectors, and the experience recommendation level score of each geological basic data item by experts in the field is taken as output; finally, in response to the first neural network model converging or satisfying the predetermined conditions, the training of the first neural network model is completed.

[0064] In one embodiment, Figure 7 Step S730 uses the following first empirical model to calculate: In this first empirical model, based on the institution reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of each geological basic data item retrieved A geological basic data items, The recommendation level score of each of the plurality of geological basic data items is calculated using a first empirical model: in the first empirical model, for one geological basic data item, the recommendation level score S includes a recommendation score S1 and a reward score S2, and Among them, the recommendation score S1 and reward score S2 are:

[0065]

[0066] Among them, w11, w12, and w13 are user-defined weights, F1 is the user-defined threshold for the number of uses n1, G1, H1, and P1 are the reward scores for different conditions defined by the user, and K11, K12, and K13 are different thresholds for the percentage K1 of the number of uses n1 to the total number of uses of all retrieved A geological basic data items.

[0067] In one embodiment, Figure 7 The parameters of the first empirical model used in step S730 are: S is a percentage system, and in the evaluation results of Eo and E1a, if the evaluation result is very good, Eo=E1a=9 points, if the evaluation result is good, Eo=E1a=6 points, if the evaluation result is average, Eo=E1a=5 points, and the user evaluation score E1 is used each time. i (i=1 to n1) uses a 10-point system, where the higher the score, the better the data quality of the specific geological basic data item, and among them, w11=80%, w12=10%, w13=10%, F1=50, G1=20, H1=10, P1=5, K11=50%, K12=30%, K13=10%.

[0068] In one embodiment, Figure 8 Shown Figure 6 The method shown is a flow chart of a method 800 used to evaluate the retrieved B geological element class data items according to the usage conditions. Figure 8 In step S810, the usage of each of the retrieved B geological element data items is obtained, wherein the usage of a geological element data item includes the number of times it is used n2, the user evaluation score E2 for each use, and the number of times it is used. i (i=1 to n2). In step S820, the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used are obtained for each of the retrieved B geological element data items. And the percentage K2 of the number of times it is used in all the retrieved B geological element data items, where In step S830, based on the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used, the B geological element data items retrieved are used. And the percentage K2 of the number of times n2 is used in the total number of times of use of all the retrieved B geological element class data items, and the recommendation level score SS of each geological element class data item of the multiple geological element class data items is obtained as the evaluation result.

[0069] In one embodiment, Figure 8 Step S830 is executed using a pre-trained second neural network model, and the author's reputation score E2a, the number of times it is used n2, and the average user rating score within the number of times it is used are combined into a geological element data item. And the percentage K2 of the number of times n2 is used to the total number of times B geological feature class data items are retrieved is used as an input vector and input into the trained second neural network model. The output of the trained second neural network model is the recommendation level score SS of the geological feature class data item.

[0070] In one embodiment, the second neural network model is trained by: obtaining the experience recommendation level score of each geological element data item in a plurality of geological element data items by domain experts; the institution reputation score E2o, the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological element data item in the plurality of geological element data items are combined; The second neural network model is trained using the percentage K2 of the number of times n2 is used as the total number of times all retrieved B geological element data items are used as input vectors, and the empirical recommendation level score of each geological element data item by domain experts is used as output; and in response to the second neural network model converging or satisfying a predetermined condition, the training of the second neural network model is completed.

[0071] Those skilled in the art will appreciate that the first neural network model and the second neural network model may employ the same model, such as MLP, CNN, RNN, GNN, LSTM, transformer, or the like, or they may employ different models among the above models.

[0072] In one embodiment, Figure 8 Step S830 uses the second empirical model to calculate: in the second empirical model, for a geological element data item, the recommendation level score SS includes a recommendation score SS1 and a reward score SS2, and Among them, the recommendation score SS1 and the reward score SS2 are:

[0073]

[0074] Among them, w21 and w22 are user-defined weights, F2 is the user-defined threshold of the number of uses n2, G2, H2, and P2 are the reward scores for different conditions defined by the user, and K21, K22, and K23 are different thresholds of the percentage K2 of the number of uses n2 to the total number of uses of all retrieved B geological feature class data items.

[0075] In one embodiment, Figure 8 The second empirical model parameters used in step S830 are: SS uses a percentage system, in the evaluation result of E2a, if the evaluation result is very good, E2a = 9 points, if the evaluation result is good, E2a = 6 points, if the evaluation result is average, E2a = 5 points, and the user evaluation score E2a is used for each use. i (i=1 to n2) uses a 10-point system, where the higher the score, the better the data quality of the specific geological element class data item, and among them, w21=80%, w22=20%, F2=50, G2=20, H2=10, P2=5, K21=50%, K22=30%, K23=10%.

[0076] In the process of taking the data sets (maps) corresponding to N geological basic data items as candidate base maps and combining them with M candidate geological feature class data items respectively, if it is determined that a specific candidate geological basic data item among the N candidate geological basic data items contains multiple base maps with different resolutions, then the resolution used for compiling / updating the geological map input by the user is received, and the multiple base maps with different resolutions are converted into multiple base maps using the resolution used for compiling / updating the geological map, and then combined. In the process of matching the vector map with the raster data, the matching relationship between the geological map scale and the raster resolution is: raster resolution R≈[geological map scale denominator D / 2000]; and geological map scale denominator D≈[2000*raster resolution R].

[0077] Figure 9 An example of using the system and method of the present invention to compile / update a geological map is shown. Figure 9In this example, (1) the Asian magmatic rock distribution map comes from the dataset (map) of the geological basic data item selected after evaluation, (2) the mineral deposit data and (3) the plate model data both come from the dataset (map) of the geological feature class data item selected after evaluation, and (4) the deep-time geological mineral map is the compiled geological map. In this example, if the resolution of the global (1) Asian magmatic rock distribution map is assumed to be x1, and the resolutions of (2) the mineral deposit data and (3) the plate model data are assumed to be x2, if x1 and x2 differ greatly, then the geological map obtained when combined will be very poor. In this case, the user can select an appropriate resolution x3, convert the (1) Asian magmatic rock distribution map, (2) the mineral deposit data, and (3) the plate model data into maps with a resolution of x3, and then combine the two to obtain a better geological map.

[0078] In one implementation, an embodiment of the present invention further discloses a computer system, comprising: a memory; and at least one processor operatively coupled to the memory and configured to execute the method described above.

[0079] The present invention may be a system, method, and / or computer program product. The computer program product includes a computer-readable storage medium. The computer-readable storage medium carries computer-readable program instructions for causing a processor to implement various aspects of the present invention. The method of the present invention may be executed on a standalone computer system, a distributed computing system, or a cloud platform.

[0080] A computer-readable storage medium may be a tangible device capable of retaining and storing instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination of the foregoing.

[0081] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0082] The computer-readable program instructions for performing the operations of the present invention may be assembly instructions, instruction set architecture instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages and conventional procedural programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a local area network or a wide area network, or may be connected to an external computer.

[0083] The flow chart and block diagram in the accompanying drawings have shown the possible architecture, function and operation of the system, method and computer-readable storage medium according to multiple embodiments of the present invention.In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and the part for this module, program segment or instruction comprises one or more executable instructions for realizing the logical function of regulation.In some as replacement implementations, the function marked in the box also can occur in a sequence different from that marked in the accompanying drawings.For example, two continuous boxes can actually be performed substantially in parallel, and they also can be performed in reverse order sometimes, and this depends on the function involved.

[0084] The description of the present invention is presented for the purpose of illustration and description and is not intended to be exhaustive or to limit the invention to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The embodiments are selected and described in order to best explain the principles of the invention, practical applications, and to enable others of ordinary skill in the art to understand the various embodiments of the invention with various modifications that are suitable for the specific purposes contemplated. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements existing on the market, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A system for compiling / updating a geological map, comprising: A user interface module is configured to receive a geological map compilation / update request, wherein the request includes requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated; The geological basic data item acquisition module is configured to retrieve A geological basic data items from a geological database storing multiple geological basic data items and multiple geological element class data items according to requirements for geological basic data items used in a geological map to be compiled / updated, evaluate the retrieved A geological basic data items according to usage, and select the top N geological basic data items ranked in the evaluation results as candidate geological basic data items, where N is a positive integer and N≤A. The geological basic data item acquisition module is further configured to: Obtain the usage of each of the retrieved A geological basic data items, where the usage of a geological basic data item includes the number of times it has been used n1, the user evaluation score E1 for each use i , where i = 1 to n1; Obtain the institution reputation score Eo, author reputation score E1a, number of times it has been used n1, and average user rating score within the number of times it has been used for each of the retrieved A geological basic data items And the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, where as well as Based on the retrieved A geological basic data items, each geological basic data item has the following: the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used and the percentage K1 of the number of times n1 of use to the total number of times of use of all retrieved A geological basic data items, obtaining a recommendation level score S of each geological basic data item of the multiple geological basic data items as an evaluation result; The geological element class data item acquisition module is configured to retrieve B geological element class data items from the geological database according to the requirements of the geological element class data items used in the geological map to be compiled / updated, evaluate the retrieved B geological element class data items according to usage, and select the geological element class data items ranked top M in the evaluation results as candidate geological element class data items, where M is a positive integer and M≤B. The geological element class data item acquisition module is further configured to: Get the usage of each of the retrieved B geological element data items, where the usage of a geological element data item includes the number of times it has been used n2, the user evaluation score E2 for each use i , where i = 1 to n2; Obtain the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each of the retrieved B geological element data items. And the percentage K2 of the number of times it is used in all the retrieved B geological element data items, where as well as Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items and the percentage K2 of the number of times n2 used in the total number of times of use of all the retrieved B geological element class data items, obtaining a recommendation level score SS of each geological element class data item of the multiple geological element class data items as an evaluation result; A synthesis module is configured to combine the datasets or maps corresponding to the N candidate geological basic data items as base maps with the M candidate geological feature class data items to obtain M*N / 2 candidate geological maps; The user interface module is further configured to receive at least one geological map selected by the user from M*N / 2 candidate geological maps, and The output module is configured to output at least one geological map selected by a user as a compiled / updated geological map.

2. The system according to claim 1, wherein: The requirements for the geological basic data items used in the geological map to be compiled / updated include requirements for the following fields of the metadata of the geological basic data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy and production year; and wherein, the requirements for the geological element class data items used in the geological map to be compiled / updated include requirements for the following fields of the metadata of the geological element class data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy and year, wherein the geological element class data items and the geological basic data items contain the same location and longitude and latitude range.

3. The system according to claim 1, wherein: Based on the retrieved A geological basic data items, each geological basic data item has the following: the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used The percentage K1 of the number of times n1 is used in the total number of times of all retrieved A geological basic data items is used, and the recommendation level score S of each geological basic data item of the multiple geological basic data items is obtained as the evaluation result. The first trained neural network model is used to perform the evaluation. During the execution, the institution reputation score Eo, the author reputation score E1a, the number of times n1 is used, and the average user rating score within the number of times a geological basic data item is used are combined. And the percentage K1 of the number of times n1 is used to the total number of times A geological basic data items are retrieved is used as an input vector and input into the trained first neural network model, and the output of the trained first neural network model is obtained as the recommendation level score S of the geological basic data item.

4. The system according to claim 3, wherein: The first neural network model is trained in the following manner: Obtaining the experience-recommended level score of each geological basic data item from domain experts; The institution reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of each geological basic data item are calculated. and the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, as input vectors, and the experience recommendation level score of each geological basic data item by the domain experts is used as output to train the first neural network model; as well as In response to the first neural network model converging or satisfying a predetermined condition, the training of the first neural network model is completed.

5. The system according to claim 1, wherein Based on the institutional reputation score Eo, author reputation score E1a, number of times it has been used n1, and the average user rating score within the number of times it has been used, for each geological basic data item retrieved A geological basic data items The recommendation level score of each of the plurality of geological basic data items is calculated using a first empirical model: in the first empirical model, for one geological basic data item, the recommendation level score S includes a recommendation score S1 and a reward score S2, and Among them, the recommendation score S1 and reward score S2 are: Among them, w11, w12, and w13 are user-defined weights, F1 is the user-defined threshold for the number of uses n1, G1, H1, and P1 are the reward scores for different conditions defined by the user, and K11, K12, and K13 are different thresholds for the percentage K1 of the number of uses n1 to the total number of uses of all retrieved A geological basic data items.

6. The system according to claim 5, wherein: S uses a percentage system. In the evaluation results of Eo and E1a, if the evaluation result is very good, Eo = E1a = 9 points, if the evaluation result is good, Eo = E1a = 6 points, if the evaluation result is average, Eo = E1a = 5 points, and the user evaluation score E1 for each use is i , where i=1 to n1, a 10-point system is used, and the higher the score, the better the data quality of the specific geological basic data item, and where w11=80%, w12=10%, w13=10%, F1=50, G1=20, H1=10, P1=5, K11=50%, K12=30%, K13=10%.

7. The system according to claim 1, wherein: Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items The percentage K2 of the number of times n2 is used in the total number of times of all retrieved B geological element data items is used. The recommended level score of each geological element data item of the multiple geological element data items is obtained using the trained second neural network model. During the execution, the author reputation score E2a, the number of times n2 is used, and the average user rating score within the number of times a geological element data item is used are combined. And the percentage K2 of the number of times n2 is used to the total number of times B geological element class data items are retrieved is used as an input vector and input into the trained second neural network model. The output of the trained second neural network model obtained is the recommendation level score SS of the geological element class data item.

8. The system according to claim 7, wherein: The second neural network model is trained in the following manner: Obtaining the experience-recommended level score of each geological element data item in a number of geological element data items by domain experts; The institution reputation score E2o, the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological element data item in the plurality of geological element data items are calculated. and the percentage K2 of the number of times n2 is used in the total number of times B geological element class data items are retrieved, as an input vector, and the experience recommendation level score of each geological element class data item by the domain experts is used as an output to train the second neural network model; as well as In response to the second neural network model converging or satisfying a predetermined condition, the training of the second neural network model is completed.

9. The system according to claim 1, wherein: Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items The recommendation level score of each of the B geological element class data items is calculated using the following second empirical model: In the second empirical model, for one geological element class data item, the recommendation level score SS includes a recommendation score SS1 and a reward score SS2, and Among them, the recommendation score SS1 and the reward score SS2 are: Among them, w21 and w22 are user-defined weights, F2 is the user-defined threshold of the number of uses n2, G2, H2, and P2 are the reward scores for different conditions defined by the user, and K21, K22, and K23 are different thresholds of the percentage K2 of the number of uses n2 to the total number of uses of all retrieved B geological feature class data items.

10. The system according to claim 9, wherein: SS uses a percentage system. In the evaluation results of E2a, if the evaluation result is very good, E2a = 9 points, if the evaluation result is good, E2a = 6 points, if the evaluation result is average, E2a = 5 points. The user evaluation score E2a for each use is i , where i=1 to n2, using a 10-point system, the higher the score, the better the data quality of the specific geological element class data item, and where w21=80%, w22=20%, F2=50, G2=20, H2=10, P2=5, K21=50%, K22=30%, K23=10%.

11. The system according to any one of claims 1 to 10, wherein: In response to the synthesis module determining that a specific candidate geological basic data item among the N candidate geological basic data items contains multiple base maps with different resolutions during synthesis, the synthesis module receives the resolution used for compiling / updating the geological map from the user interface module, and the synthesis module converts the multiple base maps with different resolutions into multiple base maps using the resolution used for compiling / updating the geological map, and then combines the base maps. In the process of matching the vector map with the raster data, the matching relationship between the geological map scale and the raster resolution is: Grid resolution R ≈ [geological map scale denominator D / 2000]; and The denominator of the geological map scale D≈[2000*grid resolution R].

12. A method for compiling / updating a geological map, comprising: receiving a geological map compilation / update request, wherein the request includes requirements for geological basic data items and geological element class data items used in the geological map to be compiled / updated; According to requirements for geological basic data items used in a geological map to be compiled / updated, A geological basic data items are retrieved from a geological database storing a plurality of geological basic data items and a plurality of geological element class data items, and the retrieved A geological basic data items are evaluated according to usage, and geological basic data items ranked top N in the evaluation results are selected as candidate geological basic data items, where N is a positive integer and N≤A. The evaluation of the retrieved A geological basic data items according to usage includes: Obtain the usage of each of the retrieved A geological basic data items, where the usage of a geological basic data item includes the number of times it has been used n1, the user evaluation score E1 for each use i , where i = 1 to n1; Obtain the institution reputation score Eo, author reputation score E1a, number of times it has been used n1, and average user rating score within the number of times it has been used for each of the retrieved A geological basic data items And the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, where as well as Based on the retrieved A geological basic data items, each geological basic data item has the following: the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used and the percentage K1 of the number of times n1 of use to the total number of times of use of all retrieved A geological basic data items, obtaining a recommendation level score S of each geological basic data item of the multiple geological basic data items as an evaluation result; According to requirements for geological element class data items used in a geological map to be compiled / updated, B geological element class data items are retrieved from the geological database, and the retrieved B geological element class data items are evaluated according to usage, and geological element class data items ranked top M in the evaluation results are selected as candidate geological element class data items, where M is a positive integer and M≤B. The evaluating the retrieved B geological element class data items according to usage includes: Get the usage of each of the retrieved B geological element data items, where the usage of a geological element data item includes the number of times it has been used n2, the user evaluation score E2 for each use i , where i = 1 to n2; Obtain the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each of the retrieved B geological element data items. And the percentage K2 of the number of times it is used in all the retrieved B geological element data items, where as well as Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items and the percentage K2 of the number of times n2 used in the total number of times of use of all the retrieved B geological element class data items, obtaining a recommendation level score SS of each geological element class data item of the multiple geological element class data items as an evaluation result; The datasets or maps corresponding to the N candidate geological basic data items are used as base maps, and are combined with the M candidate geological feature class data items to obtain M*N / 2 candidate geological maps; receiving at least one geological map selected by a user from M*N / 2 candidate geological maps; and At least one geological map selected by the user is output as a compiled / updated geological map.

13. The method according to claim 12, wherein: The requirements for geological basic data items used in the geological map to be compiled / updated include requirements for the following items of metadata of the geological basic data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy and production year; and wherein, the requirements for geological element class data items used in the geological map to be compiled / updated include requirements for the following fields of metadata of the geological element class data items: subject, location, longitude and latitude range, data type, scale denominator, accuracy and year, wherein the geological element class data items and the geological basic data items contain the same location and longitude and latitude range.

14. The method according to claim 12, wherein: Based on the retrieved A geological basic data items, each geological basic data item has the following: the institutional reputation score Eo, the author reputation score E1a, the number of times it has been used n1, and the average user rating score within the number of times it has been used The percentage K1 of the number of times n1 is used in the total number of times of all retrieved A geological basic data items is used, and the recommendation level score S of each geological basic data item of the multiple geological basic data items is obtained as the evaluation result. The first trained neural network model is used to perform the evaluation. During the execution, the institution reputation score Eo, the author reputation score E1a, the number of times n1 is used, and the average user rating score within the number of times a geological basic data item is used are combined. And the percentage K1 of the number of times n1 is used to the total number of times A geological basic data items are retrieved is used as an input vector and input into the trained first neural network model, and the output of the trained first neural network model is obtained as the recommendation level score S of the geological basic data item.

15. The method according to claim 14, wherein The first neural network model is trained in the following manner: Obtaining the experience-recommended level score of each geological basic data item from domain experts; The institution reputation score Eo, author reputation score E1a, number of times used n1, and average user rating score within the number of times used of each geological basic data item are calculated. and the percentage K1 of the number of times n1 is used in the total number of times A geological basic data items are retrieved, as input vectors, and the experience recommendation level score of each geological basic data item by the domain experts is used as output to train the first neural network model; as well as In response to the first neural network model converging or satisfying a predetermined condition, the training of the first neural network model is completed.

16. The method according to claim 12, wherein: Based on the institutional reputation score Eo, author reputation score E1a, number of times it has been used n1, and the average user rating score within the number of times it has been used, for each geological basic data item retrieved A geological basic data items The recommendation level score of each of the plurality of geological basic data items is calculated using a first empirical model: in the first empirical model, for one geological basic data item, the recommendation level score S includes a recommendation score S1 and a reward score S2, and Among them, the recommendation score S1 and reward score S2 are: Among them, w11, w12, and w13 are user-defined weights, F1 is the user-defined threshold for the number of uses n1, G1, H1, and P1 are the reward scores for different conditions defined by the user, and K11, K12, and K13 are different thresholds for the percentage K1 of the number of uses n1 to the total number of uses of all retrieved A geological basic data items.

17. The method according to claim 16, wherein S uses a percentage system. In the evaluation results of Eo and E1a, if the evaluation result is very good, Eo = E1a = 9 points, if the evaluation result is good, Eo = E1a = 6 points, if the evaluation result is average, Eo = E1a = 5 points, and the user evaluation score E1 for each use is i , where i=1 to n1, a 10-point system is used, and the higher the score, the better the data quality of the specific geological basic data item, and where w11=80%, w12=10%, w13=10%, F1=50, G1=20, H1=10, P1=5, K11=50%, K12=30%, K13=10%.

18. The method according to claim 12, wherein: Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items The percentage K2 of the number of times n2 is used in the total number of times of all retrieved B geological element data items is used. The recommended level score of each geological element data item of the multiple geological element data items is obtained using the trained second neural network model. During the execution, the author reputation score E2a, the number of times n2 is used, and the average user rating score within the number of times a geological element data item is used are combined. And the percentage K2 of the number of times n2 is used to the total number of times B geological element class data items are retrieved is used as an input vector and input into the trained second neural network model. The output of the trained second neural network model obtained is the recommendation level score SS of the geological element class data item.

19. The method according to claim 18, wherein The second neural network model is trained in the following manner: Obtaining the experience-recommended level score of each geological element data item in a number of geological element data items by domain experts; The institution reputation score E2o, the author reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological element data item in the plurality of geological element data items are calculated. and the percentage K2 of the number of times n2 is used in the total number of times B geological element class data items are retrieved, as an input vector, and the experience recommendation level score of each geological element class data item by the domain experts is used as an output to train the second neural network model; as well as In response to the second neural network model converging or satisfying a predetermined condition, the training of the second neural network model is completed.

20. The method according to claim 12, wherein Based on the author's reputation score E2a, the number of times it has been used n2, and the average user rating score within the number of times it has been used for each geological feature class data item retrieved B geological feature class data items The recommendation level score of each of the B geological element class data items is calculated using the following second empirical model: In the second empirical model, for one geological element class data item, the recommendation level score SS includes a recommendation score SS1 and a reward score SS2, and Among them, the recommendation score SS1 and the reward score SS2 are: Among them, w21 and w22 are user-defined weights, F2 is the user-defined threshold of the number of uses n2, G2, H2, and P2 are the reward scores for different conditions defined by the user, and K21, K22, and K23 are different thresholds of the percentage K2 of the number of uses n2 to the total number of uses of all retrieved B geological feature class data items.

21. The method according to claim 20, wherein SS uses a percentage system. In the evaluation results of E2a, if the evaluation result is very good, E2a = 9 points, if the evaluation result is good, E2a = 6 points, if the evaluation result is average, E2a = 5 points. The user evaluation score E2a for each use is i , where i=1 to n2, using a 10-point system, the higher the score, the better the data quality of the specific geological element class data item, and where w21=80%, w22=20%, F2=50, G2=20, H2=10, P2=5, K21=50%, K22=30%, K23=10%.

22. The method according to any one of claims 14 to 21, wherein In the process of combining data sets or maps corresponding to N geological basic data items as candidate base maps with M candidate geological feature class data items, in response to determining that a specific candidate geological basic data item among the N candidate geological basic data items includes multiple base maps with different resolutions, receiving a resolution used for compiling / updating a geological map input by a user, converting the multiple base maps with different resolutions into multiple base maps using the resolution used for compiling / updating the geological map, and then combining them, and wherein, in the process of matching the vector map with the raster data, the matching relationship between the geological map scale and the raster resolution is: Grid resolution R ≈ [geological map scale denominator D / 2000]; and The denominator of the geological map scale D≈[2000*grid resolution R].

23. A computer program product, comprising program instructions, wherein the program instructions are executable by a computing device to cause the computing device to perform the method according to any one of claims 12 to 22.

24. A computer system comprising: Memory; as well as At least one processor is operatively coupled to the memory and configured to execute the method according to any one of claims 12-22.

Images