Mineral product monitoring method and device based on big data and cloud platform

Abstract

The invention discloses a mineral product monitoring method based on big data, and relates to the technical field of data monitoring, and the method comprises the steps: building a traceability chain of a target region, and obtaining process node information on the traceability chain; a block chain data processing step is adopted to carry out data processing on the flow node information on the traceability chain, and the flow node information is uploaded to the chain; public information of the process nodes is collected; according to the price data and a pre-constructed prediction model, price prediction data is obtained, and the prediction model comprises an input layer, an embedded layer, a feature fusion layer, a time sequence processing layer, a feature extraction layer, a prediction layer and an output layer; obtaining a mineral product price linkage trend chart through price prediction data and public information; obtaining user query information, and determining mineral product data based on the user query information; and based on the mineral product data and mineral product price linkage trend chart, generating a mineral product query report and displaying the mineral product query report to the user. The problem that mineral information is not updated in time can be effectively solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data monitoring technology, and in particular to a mineral monitoring method, equipment and cloud platform based on big data. Background Art

[0002] With the acceleration of social and economic development and industrial informatization, higher requirements are placed on the monitoring and management of minerals. Effective monitoring of mineral information can not only provide a more scientific and authoritative decision-making reference for government price supervision and regulation.

[0003] At present, the existing mineral monitoring mainly collects statistics on mineral information such as mineral prices and reserves, and publishes them on the mineral information announcement platform. Since the statistics and announcement of mineral information are usually done manually, and the statistical work of mineral information involves multiple links, including data collection, collation, review, and reporting, each link requires time and effort. Therefore, there is a time delay between the collection and reporting of mineral information, which leads to the untimely update of mineral information on the mineral information announcement platform.

[0004] Based on the above problems, the lag of mineral information such as price and type will cause market participants to be unable to accurately judge the real demand and supply of the market, which is not conducive to the healthy development of the mineral market. Therefore, there is an urgent need for a method to monitor mineral information in a timely manner to ensure the healthy development of the mineral industry market. Summary of the invention

[0005] The embodiment of the present application provides a mineral monitoring method based on big data, which is used to solve the problem of untimely updating of mineral information.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In a first aspect, a mineral monitoring method based on big data is provided, which is applied to a mineral monitoring platform, wherein the monitoring platform is used to monitor a mineral process, wherein the mineral process includes at least two process nodes, and the method includes: Building a traceability chain for the target region based on all the process nodes, and obtaining information on all process nodes on the traceability chain; Using blockchain data processing steps, data processing is performed on all the process node information on the traceability chain, and the process node information includes public information and private information. Collecting the public information of all the process nodes, wherein the public information includes price data and mineral product category data; Obtain price prediction data according to the price data, the mineral product type data and the pre-built prediction model; Obtaining a mineral product price linkage trend chart based on the price forecast data and the public information of the target area; In response to a query instruction, obtaining user query information, and determining mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; Based on the mineral product data and the mineral product price linkage trend chart, a mineral query report is generated and displayed to the user; Among them, the prediction model includes an input layer, an embedding layer, a feature fusion layer, a time series processing layer, a feature extraction layer, a prediction layer and an output layer. The embedding layer includes at least two embedding vectors, each of which corresponds to a feature category. The embedding layer is used to convert the mineral product type data into a low-dimensional dense vector. The time series processing layer includes at least one layer of LSTM units for processing the price data. The prediction layer is a fully connected layer.

[0007] In a possible implementation of the first aspect, the step of using blockchain data processing includes: Classify all the node information on the traceability chain to obtain public information and private information; The private information is encrypted by a preset encryption algorithm to obtain encrypted mineral data; Using all the process nodes of the traceability chain and based on the blockchain consensus mechanism preset by the traceability chain, consensus verification is performed on the public information and the private information; If the consensus verification is passed, the public information and private information are broadcast to all the process nodes; The public information and private information are stored in the traceability chain blockchain account book in the form of blocks.

[0008] In a possible implementation manner of the first aspect, obtaining price prediction data according to the price data and a pre-built prediction model includes: When the consensus verification of the public information and the private information is passed, extracting features from the price data to obtain a price feature vector; and Extracting features from the mineral product category data to obtain a mineral product category feature vector; The price feature vector and the mineral product type feature vector are input into a pre-built prediction model to obtain price prediction data.

[0009] In a possible implementation manner of the first aspect, the public information further includes regional production data of mineral products, mineral reserves data, and mineral demand data, and obtaining a mineral product price linkage trend chart based on the price forecast data of the target area and the public information includes: Generating a price forecast trend line of mineral products in the target area according to the price forecast data of the target area; Inputting the public information into the prediction model to obtain prediction data, wherein the prediction data includes regional production prediction data, reserve prediction data and demand prediction data of all regions in the target area; Determining a first impact factor of the regional output forecast data on the price forecast data; and determining a second impact factor of the reserve forecast data on the price forecast data; and Determining a third influencing factor of the demand forecast data on the price forecast data; Fitting the first influencing factor, the second influencing factor and the third influencing factor to the mineral product price forecast trend line to obtain a mineral product price linkage trend graph; Wherein, in response to a first click instruction, a regional output forecast trend graph of a target area is displayed in the mineral product price linkage trend graph, and the first click instruction is used to indicate a target area in the mineral product price linkage trend graph; In response to a second click instruction, a mineral product reserve forecast trend chart and a mineral product demand forecast trend chart are displayed in the mineral product price linkage trend chart, and the second click instruction is used to indicate the mineral product reserves or the mineral product demand in the mineral product price linkage trend chart.

[0010] In a possible implementation manner of the first aspect, determining a first impact factor of the regional output forecast data on the price forecast data includes: Taking the set of regional output forecast data as a first data set, and taking the set of price forecast data as a second data set; Performing standardization processing on the first data set and the second data set so that the time dimensions of the first data set and the second data set are consistent; Merging the first data set and the second data set to obtain a first integrated data set; Clustering the first comprehensive data set using a preset time series clustering algorithm to obtain m first clusters, wherein each of the first clusters includes regional production forecast data and price forecast data, and m is a positive integer; For each of the first clusters, combining all of the regional production forecast data into a first vector, combining all of the price forecast data into a second vector, and calculating a first correlation coefficient between the first vector and the second vector; The sum of all the first correlation coefficients is used as the first influencing factor of the regional output forecast data on the price forecast data; The determining of the second impact factor of the reserve forecast data on the price forecast data includes: taking the set of reserve prediction data as a third data set, and performing standardization processing on the third data set so that the time dimension of the third data set is consistent with that of the second data set; Combining the third data set and the second data set to obtain a second integrated data set; Clustering the second comprehensive data set using the time series clustering algorithm to obtain n second clusters, wherein each of the second clusters includes reserve prediction data and price prediction data, and n is a positive integer; For each of the second clusters, combining all the reserve prediction data into a third vector, combining all the price prediction data into a fourth vector, and calculating a second correlation coefficient between the third vector and the fourth vector; taking the sum of all the second correlation coefficients as a second influencing factor of the reserve forecast data on the price forecast data; The determining of a third influencing factor of the demand forecast data on the price forecast data includes: The set of demand forecast data is used as a fourth data set, and the fourth data set is standardized so that the time dimension of the fourth data set is consistent with that of the second data set; Combining the fourth data set and the second data set to obtain a third integrated data set; Clustering the third comprehensive data set using the time series clustering algorithm to obtain p third clusters, wherein each of the third clusters includes demand forecast data and price forecast data, and p is a positive integer; For each of the third clusters, combining all of the demand quantity forecast data into a fifth vector, combining all of the price forecast data into a sixth vector, and calculating a third correlation coefficient between the fifth vector and the sixth vector; The sum of all the third correlation coefficients is used as the third influencing factor of the demand forecast data on the price forecast data.

[0011] In a possible implementation of the first aspect, fitting the first influencing factor, the second influencing factor, and the third influencing factor with the mineral product price forecast trend line to obtain a mineral product price linkage trend graph includes: Obtain the function for predicting the price trend of mineral products; The first influencing factor, the second influencing factor, the third influencing factor and the price prediction trend function are combined to obtain an adjustment function, and a mineral product price linkage trend chart is generated based on the adjustment function.

[0012] In a possible implementation manner of the first aspect, determining the mineral product data based on the user query information includes: In response to the query instruction, determine user information according to the user query information, the user information including a unique identity identifier and an account authority level; The user information is authenticated by the unique identity identifier. When the unique identity identifier and the real-name mobile phone number corresponding to the number identifier are consistent, the user account information is verified; After the verification is passed, the user's account level is generated based on the number of visits and the number of successful product transactions corresponding to the user information, wherein the user's account level includes primary account level, intermediate account level and advanced account level; Determine in public information the first mineral product data corresponding to the primary account level, the second mineral product data corresponding to the intermediate account level, and the third mineral product data corresponding to the senior account level, wherein the first preset time period of the first mineral product data is less than the second preset time period of the second mineral product data, and the second preset time period of the second mineral product data is less than the third preset time period of the third mineral product data.

[0013] In a possible implementation of the first aspect, the mineral query report includes a trend forecast result report and a mineral regulation report, and the mineral query report is generated based on the mineral product data and the mineral product price linkage trend chart, including: By querying mineral product data by the user, determining the product data of the mineral product that the user is querying, the product data includes type, price, output, and regional information; Extract the trend change of product data of the mineral product in the trend graph to obtain a trend prediction result report of the mineral product; Obtain trend forecast result reports of product data of multiple mineral products, generate a mineral regulation report based on the trend forecast result reports of multiple user queries on mineral products, and the trend forecast result reports of the mineral products and the mineral regulation report are used to characterize the mineral query report.

[0014] In a second aspect, the embodiment of the present application further provides a mineral monitoring cloud platform, including: An information acquisition module builds a traceability chain of the target area based on all the process nodes and acquires information of all process nodes on the traceability chain; The information processing module uses blockchain data processing steps to process all the process node information on the traceability chain and upload it to the chain, where the process node information includes public information and private information; An information collection module, which collects the public information of all the process nodes, wherein the public information includes price data; A forecast data determination module, which obtains price forecast data based on the price data and a pre-built forecast model; A linkage trend chart construction module, which obtains a linkage trend chart of mineral product prices based on the price forecast data and the public information of the target area; A query data determination module, in response to a query instruction, obtains user query information and determines mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; The query report generation module generates a mineral query report based on the mineral product data and the mineral product price linkage trend chart and displays the mineral query report to the user.

[0015] In a third aspect, an embodiment of the present application further provides an electronic device, including: a memory configured to store instructions; and A processor is configured to call instructions from a memory and to implement a mineral monitoring method based on big data according to any one of claims 1 to 8 when executing the instructions.

[0016] Through the above technical solution, firstly, a traceability chain is built for all process nodes in the mining industry and data is obtained. After the processed data is uploaded to the chain, the privacy information in the node information is encrypted, so that the process node information of the mining industry can be fully grasped and the security of the information of the mining industry can be guaranteed, which significantly improves the security of information; secondly, the price data in the public information is obtained, and the price forecast data is obtained through the price data and the pre-built forecast model. The mineral query report is generated through the price forecast data and the trend chart of the mineral product price linkage, which can clearly show the impact of the type, output and region of mineral products on the price of mineral products, so that users can obtain the query information in time, which can effectively solve the problem of untimely information update in the mining industry.

[0017] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a process of a mineral monitoring method based on big data provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a regional monitoring center provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a blockchain module provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a mineral monitoring cloud platform based on big data provided in an embodiment of the present application; Figure 5A block diagram of the layer structure of a prediction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0021] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0022] Figure 1 The following schematically shows a flow chart of a mineral monitoring method based on big data according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a mineral monitoring method based on big data, which is applied to a mineral monitoring platform. The monitoring platform is used to monitor the mineral process. The mineral process includes at least two process nodes. The method may include the following steps.

[0023] S110. Build a traceability chain in the target area based on all process nodes, and obtain information on all process nodes on the traceability chain; S120. Using blockchain data processing steps, perform data processing on all process node information on the traceability chain and upload it to the chain. The process node information includes public information and private information. S130, collecting public information of all process nodes, including price data and mineral product category data; S140, obtaining price forecast data according to the price data, mineral product type data and the pre-built forecast model; S150, obtaining a mineral product price linkage trend chart based on price forecast data and public information of the target area; S160, in response to a query instruction, obtaining user query information, and determining mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; S170. Generate a mineral query report based on the mineral product data and the mineral product price linkage trend chart and display the mineral query report to the user.

[0024] Among them, the prediction model includes an input layer, an embedding layer, a feature fusion layer, a time series processing layer, a feature extraction layer, a prediction layer and an output layer. The embedding layer includes at least two embedding vectors, each of which corresponds to a feature category. The embedding layer is used to convert the mineral product type data into a low-dimensional dense vector. The time series processing layer includes at least one layer of LSTM units for processing the price data. The prediction layer is a fully connected layer.

[0025] Figure 3 A schematic diagram of the structure of a blockchain module provided according to an embodiment of the present application is shown schematically. Figure 3 As shown, a traceability chain for the target area is built based on the process nodes of all mineral industries. All process nodes in the mineral industry are mineral exploration and mining nodes, mineral product processing nodes, mineral product sales nodes, mineral management and maintenance nodes, and regulatory department nodes. The traceability chain process nodes correspond to the exploration and mining information of the relevant mineral exploration and mining nodes, the processing information of the mineral product processing nodes, the sales price information of the mineral product sales nodes, the planning, management, and maintenance information of the mineral management and maintenance nodes, and the sales price supervision information and mineral management supervision information of the regulatory department nodes.

[0026] Based on all process nodes, a traceability chain is built in the target area, and all process node information on the traceability chain is obtained. In other words, all process nodes on the traceability chain of the mineral industry in the target area are obtained, and a traceability chain for the mineral industry is built. The traceability chain is a solution based on blockchain technology. In order to solve the information traceability, anti-counterfeiting and mobile marketing problems of enterprises in the process of commodity production, circulation, distribution, and terminal consumption, in this embodiment, the target area can be determined according to the actual situation. For example, the area queried by the user can be used as the target area. All nodes on the traceability chain include mineral exploration and mining nodes, mineral product processing nodes, mineral product sales nodes, mineral management and maintenance nodes, and regulatory department nodes.

[0027] Building a traceability chain for the target area based on all process nodes specifically means, first, obtaining all process nodes in the target area in the mineral industry, and building a traceability chain for the process nodes. For example, all process nodes in the mineral industry in the area that the user wants to query are mineral exploration and mining nodes, mineral product processing nodes, mineral product sales nodes, mineral management and maintenance nodes, and regulatory department nodes. All process nodes acquired in the mineral industry are built into a traceability chain, that is, the mineral exploration and mining nodes, mineral product processing nodes, mineral product sales nodes, mineral management and maintenance nodes, and regulatory department nodes are respectively built through transportation processes, quality inspection and transportation processes, management and maintenance processes, and regulatory processes. Obtaining all process node information on the traceability chain, in this embodiment, means obtaining the exploration and mining information on the mineral exploration and mining nodes corresponding to the target node of the traceability chain, the processing information of the mineral product processing nodes, the sales price information of the mineral product sales nodes, the planning, management, and maintenance information of the mineral management and maintenance nodes, and the sales price supervision information and mineral management supervision information of the regulatory department nodes.

[0028] After obtaining all process node information on the traceability chain, the blockchain data processing steps are used to process all node information on all traceability chains. Blockchain is a decentralized distributed ledger technology that records transactions and information through a growing data block chain to ensure data security and transparency. The blockchain data processing steps are used. Specifically, all node information on the traceability chain of the mining industry is first classified to obtain public information and private information. Public information refers to data and information that should be publicly provided to market entities, market operating institutions and the public. Private information refers to data and information that are not publicly provided to market entities, market operating institutions and the public. The standard for dividing all node information on the traceability chain is determined according to actual conditions. After obtaining public information and private information, the private information is encrypted through a preset encryption algorithm to obtain encrypted mineral data, and the public information and private information are verified by consensus through a consensus mechanism to determine whether the public information and private information have passed the consensus verification. The consensus verification can be determined by preset rules to determine the subject of the accounting right and verify the validity of the accounting. In this embodiment, the consensus verification adopts the preset non-Byzantine fault tolerance, which refers to a fault-tolerant technology that specifically handles non-Byzantine errors that occur in distributed systems. If the consensus verification is passed, the public information and private information will be broadcast to all nodes on the traceability chain of the mining industry and uploaded to the chain. In this embodiment, the upload to the chain means storing the public information and private information in the form of blocks in the blockchain of the mining industry.

[0029] According to the price data, mineral product type data and the pre-built prediction model, the price prediction data is obtained. That is to say, after the public information and private information are verified by consensus and uploaded to the chain, the price data is feature extracted to obtain the price feature vector, and the mineral product type data is feature extracted to obtain the mineral product type feature vector. Specifically, in one embodiment, the mineral product price data is obtained from the public information. After the data is obtained, the price data is feature extracted. The similarity between the price data and the benchmark data can be calculated by cosine similarity, and the price data is feature analyzed to extract the characteristics of the price data. In this embodiment, the benchmark data can be the average value of the price data. For example, the user account level is the primary account level. The primary account level can query data for five years. The benchmark data is determined to be the average value of the price data within five years. The cosine similarity is used to calculate the similarity between the public information and the benchmark information, and obtain the characteristics of the price data. The price feature vector and the mineral product type feature vector are input into the pre-built prediction model to obtain the price prediction data. Specifically, the price feature vector and the mineral product type feature vector are input into the prediction model, and the prediction model can output the price prediction result. The prediction model can be a preset neural network model. The neural network model is a machine learning model based on artificial neural networks. It can capture the complex relationship between response variables and explanatory variables, and learn the input data and generate prediction results by constructing a network structure composed of multiple neurons connected to each other. The neural network model is used to predict price data to obtain price prediction data.

[0030] In another embodiment, Figure 5 A layer structure block diagram of a prediction model provided by an embodiment of the present application is shown, such as Figure 5 As shown, the prediction model provided by the embodiment of the present application includes: input layer 1, embedding layer 2, feature fusion layer 3, time series processing layer 4, feature extraction layer 5, prediction layer and output layer 6. After the price feature vector and the mineral product type feature vector are input into the prediction model, the model will be processed by each layer and finally output the prediction result. The following is the processing process of the input data by each layer of the prediction model: Input layer: The input layer is used to receive the price feature vector and the mineral product type feature vector, and pass the received data to the next layer, namely the embedding layer.

[0031] Embedding layer: The embedding layer contains at least two embedding vectors, each of which corresponds to a feature category. In this embodiment, one embedding vector corresponds to the price feature and the other corresponds to the mineral product type feature. The main function of the embedding layer is to convert the high-dimensional sparse feature vector into a low-dimensional dense vector representation. This can be achieved by learning a preset function that maps the original data points to a new feature space. For the price feature vector, the embedding layer converts it into a low-dimensional price feature vector representation, which contains the main information and patterns of the price feature. For the mineral product type feature vector, since it is a high-dimensional sparse feature, the embedding layer can convert it into a low-dimensional mineral product type feature vector representation to capture the similarities and differences between different mineral product types.

[0032] Feature fusion layer: The feature fusion layer is used to fuse feature vectors from different embedding layers. In this embodiment, the feature fusion layer fuses the price feature vector and the mineral product type feature vector. Feature fusion can be achieved by splicing. The fused feature vector will contain both price information and mineral product type information to integrate feature information from multiple different sources so that subsequent layers can better use this information for prediction.

[0033] Time series processing layer: The time series processing layer includes at least one layer of LSTM units (Long Short-Term Memory Network) for processing time series data. In this embodiment, it mainly processes the time series information in the price feature vector. LSTM is a special recurrent neural network (RNN) that can capture long-term dependencies in sequence data. The time series processing layer iterates the price feature vector, and each iteration considers the input of the current time step and the hidden state of the previous time step. In this way, the model can capture the trend and pattern of price changes over time.

[0034] Feature extraction layer: The feature extraction layer is used to extract useful information from the fused feature vector. This layer can be implemented by a fully connected layer. The feature extraction layer further processes and transforms the fused feature vector to extract feature information that is useful for the prediction task. This feature information will be passed to the next layer, the prediction layer.

[0035] Prediction layer: The prediction layer is a fully connected layer used to make predictions based on the extracted feature information. In this embodiment, the prediction layer predicts future price data based on the fused feature vector and the feature information extracted by the time series processing layer.

[0036] Output layer: The output layer is the last layer of the prediction model and is used to output the prediction results.

[0037] In this example, the output layer will output predicted price data. This data can be future price points expressed in numerical form or future price ranges expressed in the form of probability distribution. The results of the output layer can directly reflect the model's understanding and prediction ability of the input data.

[0038] In summary, the prediction model receives data through the input layer, and then processes it through the embedding layer, feature fusion layer, time series processing layer, feature extraction layer, and prediction layer, and finally outputs the prediction result at the output layer. The purpose is to extract useful information from the input data and make accurate predictions.

[0039] According to the price forecast data and public information of the target area, a mineral product price linkage trend chart is obtained. Specifically, first, according to the price forecast data of the target area, a mineral product price forecast trend chart of the target area is generated. In this embodiment, the price forecast data of the target area can be obtained through a neural network model. The neural network model is a machine learning model based on an artificial neural network. It can capture the complex relationship between the response variable and the explanatory variable, and learn the input data and generate a prediction result by building a network structure composed of multiple neurons connected to each other. The price data is predicted using the neural network model to obtain price forecast data. According to the price forecast data of the target area, a mineral product price forecast trend line of the target area is generated. For example, the target area is the iron ore information of the Shanxi area queried by the user. According to the Shanxi area queried by the user, an iron ore price forecast trend line of the Shanxi area is generated. The public information is input into the prediction model to obtain the prediction data, which can be obtained through the neural network model. In this embodiment, the prediction data includes the regional production forecast data, reserve forecast data and demand forecast data of all areas of the target area. That is to say, the prediction data of the target area queried by the user includes the prediction data of regional production, reserves and demand. Secondly, by determining the first influencing factor of regional production forecast data on price forecast data, the second influencing factor of reserve forecast data on price forecast data, and the third influencing factor of demand forecast data on price forecast data, and fitting the first influencing factor, the second influencing factor and the third influencing factor with the mineral product price forecast trend line, a mineral product price linkage trend chart is obtained. In this embodiment, the first influencing factor refers to the influence of regional production forecast data on price forecast data, the second influencing factor refers to the influence of reserve forecast data on price forecast data, and the third influencing factor refers to the influence of demand forecast data on price forecast data. Specifically, through the Pearson correlation The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are calculated. The Pearson correlation coefficient, also known as the Pearson product-moment correlation coefficient, is used to calculate the linear correlation between two variables X and Y. The first correlation coefficient refers to the correlation coefficient between regional production forecast data and price forecast data, the second correlation coefficient refers to the correlation coefficient between reserve forecast data and price forecast data, and the third correlation coefficient refers to the correlation coefficient between demand forecast data and price forecast data. The first correlation coefficient is the first influencing factor, the second correlation coefficient is the second influencing factor, and the third correlation coefficient is the third influencing factor, thereby obtaining the first influencing factor, the second influencing factor and the third influencing factor.The first influencing factor, the second influencing factor and the third influencing factor are fitted with the mineral product price forecast trend line to obtain a mineral product price linkage trend chart. By obtaining the mineral product price forecast trend function, an adjustment function is obtained through the first influencing factor, the second influencing factor, the third influencing factor and the mineral product price forecast trend function. The mineral product price linkage trend chart is generated based on the adjustment function. Specifically, after obtaining the mineral product price forecast data, the computer will automatically generate a price forecast trend function. At this time, this function is displayed on the monitor in the form of a trend chart. For example, the original forecast trend function displayed on the computer:. Adjustment function: Among them, w1+w2+w3=1, F1 is the first influencing factor, F2 is the second influencing factor, F3 is the third influencing factor, a and b are coefficients, a is used to control the overall impact of the influencing factor on the adjusted price, and b is used to ensure Not greater than 1, b is actually This formula is rounded, for example, if is 3.4, then b is 3.

[0040] The adjustment function can also be described as follows: By adjusting the function, a trend chart of mineral product price linkage can be generated.

[0041] In response to the query instruction, the user query information is obtained, and the mineral product data is determined based on the user query information. The query instruction is used to query the mineral product data. In this embodiment, the query instruction refers to the user's operation instruction on the platform for the data to be queried, such as the type, price, and mineral output of the mineral product. Specifically, the user information is determined based on the user query data and the user query information. In this embodiment, determining the user information is to determine the user's unique identity identifier and account authority level. The user's account information is authenticated through the unique identity identifier of the user account information, and it is determined whether the user's unique identity identifier is consistent with the applied real-name mobile phone number. If they are consistent, it can be determined that the account information verification has passed; when the user's account After the user information is verified, the account authority level is verified, specifically, the user's account level is generated through the number of visits to the user account and the number of successful product transactions. For example, when the number of visits to the user account and the number of successful product transactions exceed the preset number, the user's account level is determined. The number of visits and the number of successful product transactions exceeding the preset number can be determined according to actual conditions. For example, the primary account level can be set to more than 100 visits and more than 150 successful transactions, the intermediate account level can be set to more than 150 visits and more than 200 successful transactions, and the senior account level can be set to more than 200 visits and more than 300 successful transactions. After obtaining the user's account level, the first mineral product data corresponding to the primary account level, the second mineral product data corresponding to the intermediate account level, and the third mineral product data corresponding to the senior account level are determined in the public information. In this embodiment, the first mineral product data is the data that the primary account can view, the second mineral product data is the data that the intermediate account can view, and the third mineral product data is the data that the senior account can view. The specific data of the first mineral product data, the second mineral product data, and the third mineral product data can be determined according to actual conditions. Among them, the first preset time period of the first mineral product data is smaller than the second preset time period of the second mineral product data, and the second preset time period of the second mineral product data is smaller than the third preset time period of the third mineral product data. For example, the first preset time period of the first mineral product data may be five years, the second preset time period of the second mineral product data may be seven years, and the third preset time period of the third mineral product data may be nine years.

[0042] Based on the trend chart of mineral product data and mineral product price linkage, a mineral query report is generated. Specifically, by obtaining the mineral product data queried by the user, the product data of the mineral product queried by the user is determined in the public information. The product data includes type, price, output, and regional information, and the corresponding mineral query report is generated according to the trend chart of the mineral product data queried by the user. For example, when the mineral product queried by the user is pyrite, the user enters the keyword of pyrite, and the price, output, and origin of pyrite are obtained. The year that the user can view is determined according to the user's level. The trend chart of the price, output, and region of pyrite is extracted, and the user's exclusive query report is generated according to the user's query mineral product data and the trend chart of the mineral product price linkage. In addition, all user query reports for pyrite are obtained on the monitoring platform, so as to obtain the demand for pyrite in different regions. According to the demand for pyrite, the control quantity can be generated, and a mineral control report is generated. The mineral control report and the mineral query report can provide users with more detailed mineral information.

[0043] Figure 2 A schematic diagram of the structure of a regional monitoring center according to an embodiment of the present application is shown schematically. Figure 2 As shown, the mineral node information is obtained through the information collection module, and the collected data is processed by the data processing module. The future trend of the data is predicted by the trend prediction module. At the same time, all mineral industry process nodes are obtained, and a mineral traceability chain is built according to the mineral industry process nodes and stored in the blockchain module. The process nodes on the traceability chain are processed to obtain public information and private information, and the public information is stored in the public key data center.

[0044] Through the above technical solution, firstly, a traceability chain is built for all process nodes in the mining industry and data is obtained. After the processed data is uploaded to the chain, the privacy information in the node information is encrypted, so that the process node information of the mining industry can be fully grasped and the security of the information of the mining industry can be guaranteed, which significantly improves the security of information; secondly, the price data in the public information is obtained, and the price forecast data is obtained through the price data and the pre-built forecast model. The mineral query report is generated through the price forecast data and the trend chart of the mineral product price linkage, which can clearly show the impact of the mineral product type, output, and region on the price of mineral products, so that users can clearly obtain the query information, which can effectively solve the problem of information asymmetry in the mining industry.

[0045] In one implementation of this embodiment, a blockchain data processing step is adopted, including the following steps: S210, classify all node information on the traceability chain to obtain public information and private information; S220, encrypting the private information using a preset encryption algorithm to obtain encrypted mineral data; S230. Use all process nodes of the traceability chain and based on the blockchain consensus mechanism preset by the traceability chain to conduct consensus verification on public information and private information; S240. If the consensus verification is passed, the public information and private information will be broadcast to all nodes in the mining industry; S250, storing the public information and private information in the form of blocks in the traceability chain blockchain ledger.

[0046] Public information includes data that can be disclosed publicly, such as company name, type of mineral products, production scale, transaction date, etc.; private information involves sensitive information such as specific production processes, customer information, detailed financial data, mining locations, and scarce mineral information.

[0047] In one embodiment, all node information on the traceability chain is classified to obtain public information and private information. Specifically, all node information on the traceability chain of the mineral industry is classified. The classification standard is determined by the actual situation, wherein the node information includes mineral exploration and mining node information, mineral product processing node information, mineral product sales node information, mineral management and maintenance node information, and regulatory department node information. Classifying the node information obtains public information and private information. For example, for very scarce minerals, such as uranium and ionic rare earth element mineral reserves, which are relatively confidential information in the mineral industry, the relevant information of scarce minerals is used as private information. Public information refers to data and information that should be publicly provided to market entities, market operating institutions and the public, and private information refers to data and information that is not publicly provided to market entities, market operating institutions and the public.

[0048] The privacy information is encrypted by a preset encryption algorithm. The preset encryption algorithm may be an RSA algorithm among asymmetric encryption algorithms. The RSA algorithm is an asymmetric encryption algorithm. Unlike the symmetric encryption algorithm, the RSA algorithm has two different keys, one is a public key and the other is a private key. The RSA algorithm is used to encrypt the privacy information. In this embodiment, the privacy information depends on the actual situation and may be mineral product data that the enterprise has not disclosed to the public. The privacy information is encrypted to obtain encrypted mineral data.

[0049] After obtaining the encrypted mineral data, the blockchain consensus mechanism preset by the traceability chain is used to perform consensus verification on public information and private information using all process nodes on the traceability chain. The preset blockchain consensus mechanism can be Byzantine fault tolerance. The Byzantine fault tolerance consensus mechanism is a mechanism for achieving fault tolerance in a distributed system, which aims to ensure that the system can still operate normally in the presence of malicious or faulty nodes. The Byzantine fault tolerance consensus mechanism is used to complete consensus verification on public information and private information, and consensus verification is performed on public information and private information.

[0050] After public information and private information pass the Byzantine fault-tolerant consensus mechanism, they will be broadcast to all nodes in the mining industry. Specifically, if all process nodes in the traceability chain of the mineral participate in the consensus verification and give a result that passes the consensus verification, the regional platform server will broadcast the public information and private information to all nodes in the mining industry. Among them, the regional platform server is the server of the blockchain platform, which refers to the server used to store and run the blockchain network. The server of the blockchain platform is an important part of the blockchain network. It is used to maintain the normal operation of the entire network, ensure that nodes synchronize data through mutual communication, and reach consensus to ensure consistency.

[0051] The public information and private information in the target node are stored in the traceability chain blockchain ledger in the form of blocks. The blockchain ledger is a decentralized distributed ledger that records transactions and information through a growing data block chain to ensure data security and transparency.

[0052] In another embodiment, natural language processing (NLP) technology can be used to classify node information by using a pre-trained model to classify text information. For example, a deep learning model can be used to train a text classifier that can automatically determine whether the information belongs to a public or private category based on the text content.

[0053] For structured data, this embodiment can predefine field attributes and automatically classify different fields as public or private. In actual implementation, the granularity and relevance of data can also be considered. Since some information may be public when viewed alone, but may leak privacy when combined with other information, it is necessary to establish an association analysis mechanism. Specifically, a graph database can be used to store the relationship between information, and potential sensitive information combinations can be identified through graph analysis algorithms. The classification results are stored in a structured form to facilitate subsequent encryption and processing. The classified data structure is represented in JSON or XML format, including data ID (used to uniquely identify each piece of data), data type (indicating whether it is public or private), data content (original data or encrypted data), classification confidence (indicating the credibility of automatic classification, which can be used to mark data that requires manual review), etc. In this way, sensitive information can be protected while maximizing the transparency of publicly available information, which is conducive to balancing the needs of information sharing and privacy protection.

[0054] Specifically, in a graph database, each piece of data can be represented as a node, and the relationship between nodes is represented by an edge. For example, a mining record may be connected to multiple transportation records, and transportation records are connected to sales records. In this way, a complete data relationship network can be constructed. Then, a graph analysis algorithm is used to identify potential sensitive information combinations. The logic of the graph analysis algorithm is: if there is a path shorter than a certain length from a public information node (such as mining volume) to a private information node (such as customer information), then the public information needs to reconsider its classification. In the specific implementation, a breadth-first search (BFS) or depth-first search (DFS) algorithm is used to find all paths, and then the sensitivity is judged based on the path length and the attributes of the nodes passed through, where the length of the path can be represented by the number of nodes passed through.

[0055] In order to convert information classified as private into an unreadable ciphertext form, and considering the performance requirements and security requirements in the blockchain environment, this embodiment adopts a hybrid encryption scheme: the data itself is encrypted using AES-256, and then the AES key is encrypted using the RSA algorithm. This not only ensures the efficiency of data encryption, but also increases the security of key management. The specific steps of the encryption process are as follows: First, a random AES-256 key is generated for each piece of private information. A cryptographically secure random number generator can be used. Then, the private data is encrypted using the AES key. Next, the AES key is encrypted using the RSA public key pre-assigned to the data owner. In this way, only users with the corresponding RSA private key can decrypt the AES key and then decrypt the data. In order to enhance security, salt and initialization vector (IV) can be added to the encryption process. Salt can prevent the same plaintext from generating the same ciphertext, increasing the difficulty of cracking; IV is used for initialization in CBC mode to ensure that the same plaintext will generate different ciphertexts even if the same key is used. The encrypted data structure should contain the following parts: the encrypted data itself, the encrypted AES key, the encryption algorithm used, IV, salt value, the data owner's identifier, etc. Through the above hybrid encryption method, sensitive mineral data can be converted into a secure encrypted form. It not only protects the security of data during storage and transmission, but also provides a basis for implementing fine-grained access control. Through reasonable key management, differentiated information access control for different users and different roles can be achieved, which not only ensures the security of data, but also meets the needs of information sharing.

[0056] This embodiment verifies and confirms the information to be put on the chain through a distributed consensus mechanism. First, since the mineral traceability chain is a permissioned blockchain, Practical Byzantine Fault Tolerance (PBFT) can be selected as the consensus algorithm. While ensuring security, it can provide higher transaction throughput and lower confirmation delay. The specific steps of the consensus process of this embodiment are as follows: When there is new information that needs to be put on the chain, the initiating node (which can be any process node) packages the information to be verified into a proposal. The proposal contains the original text of the public information, the encrypted form of the private information, the hash value of the information, the timestamp, etc. Then, the initiating node broadcasts this proposal to all verification nodes in the network. After receiving the proposal, the verification node first checks whether the format of the proposal is correct and whether the information is complete. Then, the verification node will review the public information to check whether it complies with the predetermined rules and standards. For private information, although the verification node cannot see the plain text, it can verify whether its encryption process is correct, such as checking whether the encryption algorithm is a pre-agreed algorithm and whether the encrypted data structure complies with the specification. The verification node also needs to check the consistency of the information, such as ensuring that the total amount of data in the public information is consistent with the quantity reported in each link. In the PBFT type consensus mechanism, the verification process includes the following stages: pre-preparation, preparation, and confirmation. In the pre-preparation stage, the master node broadcasts the received proposal to all verification nodes. In the preparation stage, each verification node verifies the proposal, and if the verification passes, it broadcasts the preparation message to other nodes. When a node receives the preparation message from more than 2 / 3 of the verification nodes, it enters the confirmation stage. In the confirmation stage, the node broadcasts the confirmation message. When more than 2 / 3 of the confirmation messages are received, the proposal is considered to have reached a consensus. In order to improve efficiency, a multi-layer consensus mechanism can be adopted. For example, the verification nodes can be divided into several groups, each group first reaches a local consensus, and then the groups reach a global consensus. This method can significantly improve the consensus efficiency of large-scale networks. In addition, for nodes that provide false information multiple times, they can be temporarily or permanently excluded from the consensus process. Through distributed consensus, single-point fraud and data tampering are effectively prevented, and the credibility of the entire traceability chain is improved.

[0057] If the consensus verification is passed, the public information and private information will be broadcast to all process nodes. First of all, since the mineral traceability chain involves a large number of nodes and data, a hierarchical broadcast strategy can be adopted. The specific process of broadcasting is as follows: After the consensus is completed, the master node (or any node that reaches consensus) starts the broadcast process. The content of the broadcast includes the original text of the public information, the encrypted form of the private information, the proof of consensus (such as the signature set), the timestamp, etc. In order to ensure the integrity and authenticity of the broadcast, the Merkle tree structure can be used to organize the broadcast content. The root hash of the Merkle tree can be used as the unique identifier of the entire broadcast content. The node can quickly check whether the received information is complete and has not been tampered with by verifying the Merkle root. During the transmission process, breakpoint resumption and data compression technology can be used to improve transmission efficiency and reliability. For example, a large amount of transaction information can be packaged into a compressed file and transmitted in pieces using a protocol similar to BitTorrent. In this way, even in the case of unstable network, the complete transmission of data can be guaranteed. In addition, access control information can be added to the broadcast content to specify nodes that have the authority to receive and store specific private information. If the verification is passed, the node stores the received information in the local database.

[0058] Finally, the public information and private information are stored in the traceability chain blockchain account book in the form of blocks. The information that has been verified by consensus and broadcast to the entire network is permanently recorded on the blockchain to form an unalterable distributed account book. The block structure of the mineral traceability scenario in this embodiment includes the following parts: block header (containing the hash, timestamp, Merkle root, etc. of the previous block), transaction list (containing all information recorded in this block), consensus proof (such as the signature set of the verification node). Since mineral traceability may involve a large number of small, high-frequency transactions, sharding technology can be used to improve processing capabilities. For example, transactions can be assigned to different shards for processing according to the type of mineral or geographical location. When storing public information, the original text can be written directly into the block. For private information, its encrypted form is stored. In order to improve storage efficiency, data compression technology can be used to compress public information.

[0059] By classifying all node information on the traceability chain, public information and private information, and encrypting private information, the security of private data in the mining industry can be effectively guaranteed. Storing public information and private information in the form of blocks in the blockchain ledger of the traceability chain can ensure that the data cannot be tampered with, providing effective security for data in the mining industry.

[0060] In one implementation of this embodiment, obtaining price prediction data according to price data and a pre-built prediction model includes the following steps: S310, when the consensus verification of the public information and the private information is passed, extracting features from the price data to obtain a price feature vector; and; S320, extracting features from the mineral product category data to obtain a mineral product category feature vector; S330: Input the price feature vector and the mineral product type feature vector into a pre-built prediction model to obtain price prediction data.

[0061] When the consensus verification of public information and private information is passed, feature extraction is performed on price data to obtain a price feature vector. Specifically, when the public information and private information in the process node have passed the Byzantine fault tolerance mechanism, feature extraction is performed on price data, and the similarity between price data and benchmark data can be calculated by cosine similarity. Cosine similarity is a method for calculating the similarity between two data. In this embodiment, benchmark data refers to the average value of all process node data in the mineral traceability chain. For example, when the account level is the primary account level, the data age of the user's query is obtained according to the account level, and the average value of the query data within the data age is calculated. The public information and the benchmark data are calculated using cosine similarity to calculate the similarity between the two data. If the calculated similarity is greater than a preset value, the preset value can be determined by the actual situation, and the data greater than the preset value is excluded to obtain a price feature vector.

[0062] Principal component analysis can be used to extract features from mineral product type data and obtain mineral product type feature vectors. Principal component analysis is a commonly used dimensionality reduction method that can reduce high-dimensional data to low-dimensional data while retaining as much information as possible. Through principal component analysis, the characteristics of mineral product types can be extracted from mineral product type data to obtain mineral product type feature vectors.

[0063] The price feature vector is input into a pre-built prediction model to obtain price prediction data, specifically, the features of the obtained mineral product price data are input into the prediction model, wherein the prediction model includes an input layer, an embedding layer, a feature fusion layer, a time series processing layer, a feature extraction layer, a prediction layer and an output layer, the embedding layer includes at least two embedding vectors, each embedding vector corresponds to a feature category, the embedding layer is used to convert the mineral product type data into a low-dimensional dense vector, the time series processing layer includes at least one layer of LSTM units for processing price data, the prediction layer is a fully connected layer, and the prediction model can be a neural network model, which is a machine learning model based on an artificial neural network, which can capture the complex relationship between the response variable and the explanatory variable, and learn the input data and generate prediction results by constructing a network structure composed of multiple neurons connected to each other, and use the neural network model to predict the price data to obtain price prediction data.

[0064] By obtaining the price feature vector and the mineral product type feature vector and inputting the price feature vector and the mineral product type feature vector into the pre-built prediction model to obtain the price prediction data, the key information in the price data and the mineral product type data can be effectively captured, the prediction accuracy can be improved and the market stability can be enhanced.

[0065] In one implementation of this embodiment, the public information also includes regional production data of mineral products, mineral product reserve data and mineral product demand data. According to the price forecast data of the target area and the public information, a mineral product price linkage trend chart is obtained, including the following steps: S410, generating a price forecast trend line of mineral products in the target area according to the price forecast data of the target area; S420, inputting the public information into the prediction model to obtain prediction data, wherein the prediction data includes regional production prediction data, reserve prediction data and demand prediction data of all regions in the target area; S430, determining the first influencing factor of the regional output forecast data on the price forecast data; and S440, determining a second influencing factor of the reserve forecast data on the price forecast data; and S450, determining a third influencing factor of the demand forecast data on the price forecast data; S460, fitting the first influencing factor, the second influencing factor and the third influencing factor to the mineral product price forecast trend line to obtain a mineral product price linkage trend graph; S470, wherein, in response to the first click instruction, a regional output forecast trend chart of the target area is displayed in the mineral product price linkage trend chart, and the first click instruction is used to indicate the target area in the mineral product price linkage trend chart; S480. In response to a second click instruction, a mineral product reserve forecast trend chart and a mineral product demand forecast trend chart are displayed in the mineral product price linkage trend chart, and the second click instruction is used to indicate the mineral product reserves or the mineral product demand in the mineral product price linkage trend chart.

[0066] According to the price prediction data of the target area, a price prediction trend line of the mineral products in the target area is generated. In this embodiment, the target area can be determined according to the actual situation. For example, the area queried by the user can be used as the target area. That is to say, the price prediction data of the target area is used to generate the price prediction trend line of the mineral products in the target area. For example, the user obtains the price prediction data of the target area and generates the price prediction trend line of the mineral products in the target area from the price prediction data. The public information is input into the prediction model to obtain prediction data. In this embodiment, the prediction model can be a neural network model. The neural network model is a machine learning model based on an artificial neural network. It can capture the complex relationship between the response variable and the explanatory variable, and learn the input data and generate prediction results by constructing a network structure composed of multiple neurons connected to each other. The neural network model predicts the public information to obtain prediction data, wherein the prediction data includes regional production prediction data, reserve prediction data and demand prediction data of all areas in the target area.

[0067] After obtaining the forecast data, determine the first influencing factor of the regional output forecast data on the price forecast data. In this embodiment, the first influencing factor refers to the degree of influence of the regional output forecast data on the price forecast data. Specifically, first, take the set of regional output forecast data as the first data set, and take the set of price forecast data as the second data set. After obtaining the first data set and the second data set, standardize the first data set and the second data set to make the time dimension of the first data set consistent with that of the second data set. In this embodiment, the first data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the first data set and the second data set are merged to obtain a first comprehensive data set, and a preset time series clustering algorithm is used to cluster the first comprehensive data set to obtain m first clusters, wherein each first cluster includes regional production forecast data and price forecast data, and m is a positive integer. The preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, and then randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining m first clusters, for each first cluster, all regional yield forecast data are combined into a first vector, all price forecast data are combined into a second vector, and a first correlation coefficient between the first vector and the second vector is calculated, wherein the first correlation coefficient between the first vector and the second vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the first correlation coefficient refers to the correlation coefficient between the regional yield forecast data and the price forecast data, and the sum of all first correlation coefficients is taken as the first influencing factor of the regional yield forecast data on the price forecast data.

[0068] Similarly, the second influencing factor of the reserve prediction data on the price prediction data is determined. In this embodiment, the second influencing factor refers to the degree of influence of the reserve prediction data on the price prediction data. Specifically, first, the set of price prediction data is used as the second data set, and the set of reserve prediction data is used as the third data set, and the third data set is standardized so that the time dimension of the third data set is consistent with that of the second data set. In this embodiment, the third data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the third data set and the second data set are merged to obtain a second comprehensive data set, and the first comprehensive data set is clustered using a preset time series clustering algorithm to obtain n second clusters, wherein each second cluster includes reserve prediction data and price prediction data, and n is a positive integer. The preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining n first clusters, for each second cluster, all regional production forecast data are combined into a third vector, all price forecast data are combined into a fourth vector, and the second correlation coefficient between the third vector and the fourth vector is calculated, wherein the second correlation coefficient between the third vector and the fourth vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the second correlation coefficient refers to the correlation coefficient between the regional production forecast data and the price forecast data, and the sum of all second correlation coefficients is used as the second influencing factor of the reserve forecast data on the price forecast data.

[0069] Determine the third influencing factor of the demand forecast data on the price forecast data. In this embodiment, the third influencing factor refers to the degree of influence of the demand forecast data on the price forecast data. Specifically, first, the set of price forecast data is used as the second data set, and the set of demand forecast data is used as the fourth data set, and the fourth data set is standardized so that the time dimension of the fourth data set is consistent with that of the second data set. In this embodiment, the fourth data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the fourth data set and the second data set are merged to obtain a third comprehensive data set, and the third comprehensive data set is clustered using a preset time series clustering algorithm to obtain p first clusters, wherein each third cluster includes demand forecast data and price forecast data, p is a positive integer, and the preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, then randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining p third clusters, for each third cluster, all demand forecast data are combined into a fourth vector, all price forecast data are combined into a fifth vector, and the second correlation coefficient between the third vector and the fourth vector is calculated, wherein the third correlation coefficient between the fourth vector and the fifth vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the third correlation coefficient refers to the correlation coefficient between the demand forecast data and the price forecast data, and the sum of all third correlation coefficients is taken as the third influencing factor of the reserve forecast data on the price forecast data.

[0070] The first influencing factor, the second influencing factor and the third influencing factor are fitted to the mineral product price forecast trend line to obtain a mineral product price linkage trend chart. Specifically, a mineral product price forecast trend function is obtained, and an adjustment function is obtained based on the first influencing factor, the second influencing factor, the third influencing factor and the price forecast trend function, and a mineral product price linkage trend chart is generated based on the adjustment function.

[0071] In response to the first click instruction, the regional output forecast trend chart of the target area is displayed in the mineral product price linkage trend chart. The first click instruction is used to indicate the target area in the mineral product price linkage trend chart. In response to the first click instruction, the target area is indicated in the mineral product price linkage trend chart. For example, when the user selects Datong City, Shanxi Province as the target area on the mineral monitoring platform, in response to the first click, the mineral product price and output forecast linkage trend chart of Datong City, Shanxi Province is displayed on the monitoring platform interface.

[0072] In response to the second click instruction, the mineral reserve forecast trend chart and the mineral demand forecast trend chart are displayed in the mineral price linkage trend chart. The second click instruction is used to indicate the mineral reserves or the mineral demand in the mineral price linkage trend chart. For example, when the user selects Datong City, Shanxi Province as the target area on the mineral monitoring platform, in response to the second click, the mineral price and mineral reserve forecast linkage trend chart of Datong City, Shanxi Province is displayed on the monitoring platform interface.

[0073] By taking the regional output data, reserve data and demand data of mineral products as the first, second and third influencing factors, and fitting the first, second and third influencing factors with the mineral price forecast trend line, we can obtain the mineral price linkage trend chart, which can more intuitively show the dynamic relationship between price and regional output, reserves and demand, and help improve the accuracy of price forecasts.

[0074] In one implementation of this embodiment, determining the first influencing factor of regional output forecast data on price forecast data includes the following steps: S501, taking a set of regional output forecast data as a first data set, and taking a set of price forecast data as a second data set; S502, performing standardization processing on the first data set and the second data set so that the time dimensions of the first data set and the second data set are consistent; S503, merging the first data set and the second data set to obtain a first comprehensive data set; S504, clustering the first comprehensive data set using a preset time series clustering algorithm to obtain m first clusters, wherein each first cluster includes regional output forecast data and price forecast data, and m is a positive integer; S505: for each first cluster, combine all regional output forecast data into a first vector, combine all price forecast data into a second vector, and calculate a first correlation coefficient between the first vector and the second vector; S506. The sum of all first correlation coefficients is taken as the first influencing factor of the regional output forecast data on the price forecast data; Determine the second factor that affects the reserve forecast data on the price forecast data, including: S507, taking the set of reserve prediction data as a third data set, and performing standardization processing on the third data set so that the time dimension of the third data set is consistent with that of the second data set; S508, merging the third data set and the second data set to obtain a second comprehensive data set; S509, clustering the second comprehensive data set using a time series clustering algorithm to obtain n second clusters, wherein each second cluster includes reserve prediction data and price prediction data, and n is a positive integer; S510: for each second cluster, combine all reserve prediction data into a third vector, combine all price prediction data into a fourth vector, and calculate a second correlation coefficient between the third vector and the fourth vector; S511. The sum of all second correlation coefficients is taken as the second influencing factor of the reserve prediction data on the price prediction data; Determine the third factor that affects the demand forecast data on the price forecast data, including: S512, taking the set of demand forecast data as a fourth data set, and performing standardization processing on the fourth data set so that the time dimension of the fourth data set is consistent with that of the second data set; S513, combining the fourth data set and the second data set to obtain a third comprehensive data set; S514, clustering the third comprehensive data set using a time series clustering algorithm to obtain p third clusters, wherein each third cluster includes demand forecast data and price forecast data, and p is a positive integer; S515, for each third cluster, combining all demand quantity forecast data into a fifth vector, combining all price forecast data into a sixth vector, and calculating a third correlation coefficient between the fifth vector and the sixth vector; S516. The sum of all third correlation coefficients is taken as the third influencing factor of the demand forecast data on the price forecast data.

[0075] After obtaining the forecast data, determine the first influencing factor of the regional output forecast data on the price forecast data. In this embodiment, the first influencing factor refers to the degree of influence of the regional output forecast data on the price forecast data. Specifically, first, take the set of regional output forecast data as the first data set, and take the set of price forecast data as the second data set. After obtaining the first data set and the second data set, standardize the first data set and the second data set to make the time dimension of the first data set consistent with that of the second data set. In this embodiment, the first data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the first data set and the second data set are merged to obtain a first comprehensive data set, and a preset time series clustering algorithm is used to cluster the first comprehensive data set to obtain m first clusters, wherein each first cluster includes regional production forecast data and price forecast data, and m is a positive integer. The preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, and then randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining m first clusters, for each first cluster, all regional yield forecast data are combined into a first vector, all price forecast data are combined into a second vector, and a first correlation coefficient between the first vector and the second vector is calculated, wherein the first correlation coefficient between the first vector and the second vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the first correlation coefficient refers to the correlation coefficient between the regional yield forecast data and the price forecast data, and the sum of all first correlation coefficients is taken as the first influencing factor of the regional yield forecast data on the price forecast data.

[0076] Similarly, the second influencing factor of the reserve prediction data on the price prediction data is determined. In this embodiment, the second influencing factor refers to the degree of influence of the reserve prediction data on the price prediction data. Specifically, first, the set of price prediction data is used as the second data set, and the set of reserve prediction data is used as the third data set, and the third data set is standardized so that the time dimension of the third data set is consistent with that of the second data set. In this embodiment, the third data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the third data set and the second data set are merged to obtain a second comprehensive data set, and the first comprehensive data set is clustered using a preset time series clustering algorithm to obtain n second clusters, wherein each second cluster includes reserve prediction data and price prediction data, and n is a positive integer. The preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining n first clusters, for each second cluster, all regional production forecast data are combined into a third vector, all price forecast data are combined into a fourth vector, and the second correlation coefficient between the third vector and the fourth vector is calculated, wherein the second correlation coefficient between the third vector and the fourth vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the second correlation coefficient refers to the correlation coefficient between the regional production forecast data and the price forecast data, and the sum of all second correlation coefficients is used as the second influencing factor of the reserve forecast data on the price forecast data.

[0077] Determine the third influencing factor of the demand forecast data on the price forecast data. In this embodiment, the third influencing factor refers to the degree of influence of the demand forecast data on the price forecast data. Specifically, first, the set of price forecast data is used as the second data set, and the set of demand forecast data is used as the fourth data set, and the fourth data set is standardized so that the time dimension of the fourth data set is consistent with that of the second data set. In this embodiment, the fourth data set and the second data set are standardized by the Z-score standardization method, which adjusts the data to conform to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. This method is suitable for situations where the data obeys or approximately obeys the normal distribution. By converting the original data into a distribution with a mean of 0 and a standard deviation of 1, the standardized processing of data of different time dimensions can be achieved, so that the data of the time dimension has a consistent basis for comparison. Secondly, the fourth data set and the second data set are merged to obtain a third comprehensive data set, and the third comprehensive data set is clustered using a preset time series clustering algorithm to obtain p first clusters, wherein each third cluster includes demand forecast data and price forecast data, p is a positive integer, and the preset time series clustering algorithm refers to an unsupervised learning method used in time series analysis, which is used to group data together according to the similarity between time series data. In this embodiment, the k-means clustering algorithm is used. The k-means clustering algorithm is an iterative clustering analysis algorithm, and its steps are to pre-divide the data into K groups, then randomly select K objects as initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it. After obtaining p third clusters, for each third cluster, all demand forecast data are combined into a fourth vector, all price forecast data are combined into a fifth vector, and the second correlation coefficient between the third vector and the fourth vector is calculated, wherein the third correlation coefficient between the fourth vector and the fifth vector is calculated by the Pearson correlation coefficient, which is also called the Pearson product-moment correlation coefficient and is used to calculate the linear correlation between two variables X and Y, wherein the third correlation coefficient refers to the correlation coefficient between the demand forecast data and the price forecast data, and the sum of all third correlation coefficients is taken as the third influencing factor of the reserve forecast data on the price forecast data.

[0078] By calculating the impact factors of regional production forecast data, reserve forecast data and demand forecast data on price forecast data, we can more accurately quantify the impact of regional production, reserves and demand on prices, which will help to further improve the accuracy of price forecasts.

[0079] In one implementation of this embodiment, fitting the first influencing factor, the second influencing factor and the third influencing factor with the mineral product price forecast trend line to obtain a mineral product price linkage trend graph includes the following steps: S610, obtaining a mineral product price prediction trend function; S620. Combining the first influencing factor, the second influencing factor, the third influencing factor and the price prediction trend function, obtain an adjustment function, and generate a mineral product price linkage trend chart based on the adjustment function.

[0080] After obtaining the price forecast data of the mineral products, the computer will automatically generate a price forecast trend function. At this time, the price forecast trend function is displayed on the display in the form of a trend chart. For example, the original forecast trend function generated on the computer is: Combining the first influencing factor, the second influencing factor, the third influencing factor and the price forecast trend function, the adjustment function is obtained, and the mineral product price linkage trend chart is generated based on the adjustment function. That is to say, the original forecast trend function is adjusted to obtain the adjustment function: Among them, w1+w2+w3=1, F1 is the first influencing factor, F2 is the second influencing factor, F3 is the third influencing factor, a and b are coefficients, a is used to control the overall impact of the influencing factor on the adjusted price, and b is used to ensure Not greater than 1, b is actually This formula is rounded, for example, if is 3.4, then b is 3.

[0081] Therefore, the adjustment function can be described as follows: The above formula still has certain limitations, that is, the adjusted price is at most twice the original predicted price. Therefore, the adjustment function can also be described as follows: Among them, the range of the sin function is [-1,1]; therefore, The value range of is also [-1,1].

[0082] The adjustment factor is:

[0083] Since the range of the sin term is [-1,1], the range of the adjustment factor is [0,2].

[0084] The relationship between the adjusted price and the original predicted price: Minimum value: When the sin term is -1, the adjusted price = f(time) 0=0; Maximum value: When the sin term is 1, the adjusted price = f(time) 2; Intermediate value: When the sin term is 0, the adjusted price = f(time), which is equal to the original predicted price. Therefore, the range of the adjusted price is: [0,2 f(time)]. Normally, the mineral price after adding the influencing factors will not exceed twice the predicted value. If the actual mineral price exceeds twice the predicted value, an alarm message will be issued.

[0085] The first influencing factor, the second influencing factor and the third influencing factor are fitted with the mineral product price forecast trend line to obtain the mineral product price linkage trend chart. Specifically, by obtaining the mineral product price forecast trend function, and then combining these influencing factors to obtain the adjustment function, the mineral product price linkage trend chart is finally generated. This can display market information in a more detailed and accurate manner, which will help companies better grasp market dynamics and formulate more effective market strategies.

[0086] In one implementation of this embodiment, determining mineral product data based on user query information includes: S710, in response to the query instruction, determining user information according to the user query information, where the user information includes a unique identity identifier and an account authority level; S720, authenticate the user information through the unique identity identifier, and if the identity information and the corresponding number identifier real-name mobile phone number are consistent, the user account information is verified; S730. After the verification is passed, based on the number of visits and the number of successful product transactions corresponding to the user information, generate the user's account level, where the user's account level includes primary account level, intermediate account level and advanced account level; S740. Determine in the public information the first mineral product data corresponding to the primary account level, the second mineral product data corresponding to the intermediate account level, and the third mineral product data corresponding to the senior account level, wherein the first preset time period of the first mineral product data is less than the second preset time period of the second mineral product data, and the second preset time period of the second mineral product data is less than the third preset time period of the third mineral product data.

[0087] In response to the query instruction, the user information is determined according to the user query information. In this embodiment, the query instruction refers to the operation instruction of the user on the platform for the data to be queried, such as the type, price, and mineral output of mineral products. The user information is determined according to the user query information. In this embodiment, the user's unique identity identifier and account authority level are determined through the user query information. In response to the query instruction, the user information is determined according to the user query information. That is, when the user starts to query mineral data, the user's unique identity identifier and account authority level are determined according to the user's query information.

[0088] The user information is authenticated by the unique identity identifier. In this embodiment, the authentication of the user information is to determine whether the unique identity identifier is consistent with the real-name mobile phone number applied by the user. If they are consistent, it can be determined that the account information verification has passed. After the verification is passed, the user's account level is generated based on the number of visits and the number of successful product transactions corresponding to the user information, wherein the user's account level includes a primary account level, an intermediate account level and a senior account level. That is to say, when the user's account information passes the verification, the account authority level is verified, specifically, the user's account level is generated by the number of visits and the number of successful product transactions of the user account. For example, when the number of visits and the number of successful product transactions of the user's account exceed the preset number, the user's account level is determined. The number of visits and the number of successful product transactions exceeding the preset number can be determined according to the actual situation. For example, the primary account level can be set to more than 100 visits and more than 150 successful transactions, the intermediate account level can be set to more than 150 visits and more than 200 successful transactions, and the senior account level can be set to more than 200 visits and more than 300 successful transactions.

[0089] After obtaining the user's account level, the first mineral product data corresponding to the primary account level, the second mineral product data corresponding to the intermediate account level, and the third mineral product data corresponding to the senior account level are determined in the public information. In this embodiment, the first mineral product data is data that can be viewed by the primary account, the second mineral product data is data that can be viewed by the intermediate account, and the third mineral product data is data that can be viewed by the senior account. The specific data of the first mineral product data, the second mineral product data, and the third mineral product data can be determined according to the actual situation. Among them, the first preset time period of the first mineral product data is less than the second preset time period of the second mineral product data, and the second preset time period of the second mineral product data is less than the third preset time period of the third mineral product data. For example, the first preset time period of the first mineral product data can be five years, the second preset time period of the second mineral product data can be seven years, and the third preset time period of the third mineral product data can be nine years.

[0090] By determining mineral product data through user query information, and through identity authentication, account level division, and providing mineral product data of different time periods according to account level, the security of user access to mineral product data can be ensured, thereby enhancing data security, providing users with personalized service experience, and improving user satisfaction.

[0091] In one implementation of this embodiment, the mineral query report includes a trend forecast result report and a mineral regulation report. Based on the mineral product data and the mineral product price linkage trend chart, the mineral query report is generated, including the following steps: S810, determining, through the user querying mineral product data, product data of the mineral product the user is querying, the product data including type, price, output, and regional information; S820, extracting the trend change of product data of the mineral product in the trend chart, and obtaining a trend prediction result report of the mineral product; S830, obtaining a trend forecast result report of product data of multiple mineral products, generating a mineral regulation report based on multiple users querying the trend forecast result report of the mineral products, and the trend forecast result report of the mineral products and the mineral regulation report are used to characterize the mineral query report.

[0092] Through the user's query of mineral product data, the product data of the mineral product queried by the user is determined. In this embodiment, the product data includes type, price, output, and regional information. Through the user's query of mineral product data, the product data of the mineral product queried by the user is determined. For example, the user's query of mineral product is copper mine information, all mineral product data is obtained, and the copper mine price, output, and regional information are obtained in the mineral product data.

[0093] The trend change of the product data of the mineral product is extracted from the trend chart to obtain a trend forecast result report of the mineral product. In this embodiment, the trend forecast result report is a forecast report of the future trend of the price data change of the mineral product with the change of other data. The trend change of the product data of the mineral product is extracted from the trend chart to obtain a trend forecast result report of the mineral product. For example, the user inquires about the mineral product information of copper mine, and the trend change of the copper mine data is extracted from the trend chart to obtain a trend forecast result report of the copper mine. In this embodiment, the trend forecast result report can be the changing trend of the type, price, output, and region of the mineral product in the future time period.

[0094] After obtaining the trend forecast result report of the mineral products, the trend forecast result report of the product data of multiple mineral products is obtained, and a mineral regulation report is generated based on the trend forecast result report of the mineral products queried by multiple users. For example, when it is determined that the type of mineral product queried by the user is copper ore, the output of copper ore required in different regions can be determined through the regions searched by multiple users, and the output of copper ore required in different regions can be generated according to the output of copper ore required in different regions, so as to obtain the mineral regulation report. In this embodiment, the mineral regulation report is based on the output of mineral products in different regions, and the mineral products in the areas with higher output of mineral products are allocated to the areas with higher demand for mineral products and lower output of mineral products.

[0095] By linking mineral product data with mineral product price trend charts, mineral query reports, including trend forecast result reports and mineral regulation reports, can more clearly display comprehensive market information of the mineral industry, help improve the accuracy and scientific nature of mineral industry decision-making, and ensure the healthy development of the mineral industry.

[0096] Figure 4 The structure diagram of a mineral monitoring cloud platform based on big data provided by the embodiment of the present application is shown as follows: Figure 4 As shown, the embodiment of the present application also provides a mineral monitoring cloud platform based on big data, including: The information acquisition module 10 builds a traceability chain of the target area based on all process nodes and obtains information of all process nodes on the traceability chain; The information processing module 20 uses the blockchain data processing steps to process all process node information on the traceability chain and upload it to the chain. The process node information includes public information and private information. Information collection module 30, collects public information of all process nodes, including price data; The forecast data determination module 40 obtains price forecast data according to the price data and the pre-built forecast model; A linkage trend graph building module 50 obtains a linkage trend graph of mineral product prices based on price forecast data and public information of the target area; A query data determination module 60, in response to a query instruction, obtains user query information and determines mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; The query report generation module 70 generates a mineral query report based on the mineral product data and the mineral product price linkage trend chart and displays the mineral query report to the user.

[0097] The present application also provides an electronic device, including: a memory configured to store instructions; and The processor is configured to call instructions from the memory and implement the above-mentioned mineral monitoring method based on big data when executing the instructions.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0104] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0106] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A mineral monitoring method based on big data, characterized in that: Applied to a mineral monitoring platform, the monitoring platform is used to monitor a mineral process, the mineral process includes at least two process nodes, and the method includes: Building a traceability chain for the target region based on all the process nodes, and obtaining information on all process nodes on the traceability chain; Using blockchain data processing steps, data processing is performed on all the process node information on the traceability chain, and the process node information includes public information and private information. Collecting the public information of all the process nodes, wherein the public information includes price data and mineral product category data; Obtain price prediction data according to the price data, the mineral product type data and the pre-built prediction model; Obtaining a mineral product price linkage trend chart based on the price forecast data and the public information of the target area; In response to a query instruction, obtaining user query information, and determining mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; Based on the mineral product data and the mineral product price linkage trend chart, a mineral query report is generated and displayed to the user; Among them, the prediction model includes an input layer, an embedding layer, a feature fusion layer, a time series processing layer, a feature extraction layer, a prediction layer and an output layer. The embedding layer includes at least two embedding vectors, each of which corresponds to a feature category. The embedding layer is used to convert the mineral product type data into a low-dimensional dense vector. The time series processing layer includes at least one layer of LSTM units for processing the price data. The prediction layer is a fully connected layer.

2. The method according to claim 1, characterized in that The blockchain data processing steps include: Classify all the node information on the traceability chain to obtain public information and private information; The private information is encrypted by a preset encryption algorithm to obtain encrypted mineral data; Using all the process nodes of the traceability chain and based on the blockchain consensus mechanism preset by the traceability chain, consensus verification is performed on the public information and the private information; If the consensus verification is passed, the public information and private information are broadcast to all the process nodes; The public information and private information are stored in the traceability chain blockchain account book in the form of blocks.

3. The method according to claim 2, characterized in that The step of obtaining price prediction data according to the price data and the pre-built prediction model includes: When the consensus verification of the public information and the private information is passed, extracting features from the price data to obtain a price feature vector; and Extracting features from the mineral product category data to obtain a mineral product category feature vector; The price feature vector and the mineral product type feature vector are input into a pre-built prediction model to obtain price prediction data.

4. The method according to claim 1, characterized in that The public information also includes regional production data of mineral products, mineral product reserves data and mineral product demand data. The price linkage trend chart of mineral products is obtained based on the price forecast data of the target area and the public information, including: Generating a forecast trend line of mineral product prices in the target area according to the forecast price data in the target area; Inputting the public information into the prediction model to obtain prediction data, wherein the prediction data includes regional production prediction data, reserve prediction data and demand prediction data of all regions in the target area; Determining a first impact factor of the regional output forecast data on the price forecast data; and determining a second impact factor of the reserve forecast data on the price forecast data; and Determining a third influencing factor of the demand forecast data on the price forecast data; Fitting the first influencing factor, the second influencing factor and the third influencing factor to the mineral product price forecast trend line to obtain a mineral product price linkage trend graph; Wherein, in response to a first click instruction, a regional output forecast trend graph of a target area is displayed in the mineral product price linkage trend graph, and the first click instruction is used to indicate a target area in the mineral product price linkage trend graph; In response to a second click instruction, a mineral product reserve forecast trend chart and a mineral product demand forecast trend chart are displayed in the mineral product price linkage trend chart, and the second click instruction is used to indicate the mineral product reserves or the mineral product demand in the mineral product price linkage trend chart.

5. The method according to claim 4, characterized in that The determining of a first influencing factor of the regional output forecast data on the price forecast data comprises: Taking the set of regional output forecast data as a first data set, and taking the set of price forecast data as a second data set; Performing standardization processing on the first data set and the second data set so that the time dimensions of the first data set and the second data set are consistent; Merging the first data set and the second data set to obtain a first integrated data set; Clustering the first comprehensive data set using a preset time series clustering algorithm to obtain m first clusters, wherein each of the first clusters includes regional production forecast data and price forecast data, and m is a positive integer; For each of the first clusters, combining all of the regional production forecast data into a first vector, combining all of the price forecast data into a second vector, and calculating a first correlation coefficient between the first vector and the second vector; The sum of all the first correlation coefficients is used as the first influencing factor of the regional output forecast data on the price forecast data; The determining of the second impact factor of the reserve forecast data on the price forecast data includes: taking the set of reserve prediction data as a third data set, and performing standardization processing on the third data set so that the time dimension of the third data set is consistent with that of the second data set; Combining the third data set and the second data set to obtain a second integrated data set; Clustering the second comprehensive data set using the time series clustering algorithm to obtain n second clusters, wherein each of the second clusters includes reserve prediction data and price prediction data, and n is a positive integer; For each of the second clusters, combining all the reserve prediction data into a third vector, combining all the price prediction data into a fourth vector, and calculating a second correlation coefficient between the third vector and the fourth vector; taking the sum of all the second correlation coefficients as a second influencing factor of the reserve forecast data on the price forecast data; The determining of a third influencing factor of the demand forecast data on the price forecast data includes: The set of demand forecast data is used as a fourth data set, and the fourth data set is standardized so that the time dimension of the fourth data set is consistent with that of the second data set; Combining the fourth data set and the second data set to obtain a third integrated data set; Clustering the third comprehensive data set using the time series clustering algorithm to obtain p third clusters, wherein each of the third clusters includes demand forecast data and price forecast data, and p is a positive integer; For each of the third clusters, combining all of the demand quantity forecast data into a fifth vector, combining all of the price forecast data into a sixth vector, and calculating a third correlation coefficient between the fifth vector and the sixth vector; The sum of all the third correlation coefficients is used as the third influencing factor of the demand forecast data on the price forecast data.

6. The method according to claim 5, characterized in that The step of fitting the first influencing factor, the second influencing factor and the third influencing factor to the mineral product price forecast trend line to obtain a mineral product price linkage trend graph includes: Obtain the function for predicting the price trend of mineral products; The first influencing factor, the second influencing factor, the third influencing factor and the price prediction trend function are combined to obtain an adjustment function, and a mineral product price linkage trend chart is generated based on the adjustment function.

7. The method according to claim 1, characterized in that Determining mineral product data based on user query information includes: In response to the query instruction, determine user information according to the user query information, the user information including a unique identity identifier and an account authority level; The user information is authenticated by the unique identity identifier. When the unique identity identifier and the real-name mobile phone number corresponding to the number identifier are consistent, the user account information is verified; After the verification is passed, the user's account level is generated based on the number of visits and the number of successful product transactions corresponding to the user information, wherein the user's account level includes primary account level, intermediate account level and advanced account level; Determine in public information the first mineral product data corresponding to the primary account level, the second mineral product data corresponding to the intermediate account level, and the third mineral product data corresponding to the senior account level, wherein the first preset time period of the first mineral product data is less than the second preset time period of the second mineral product data, and the second preset time period of the second mineral product data is less than the third preset time period of the third mineral product data.

8. The method according to claim 1, characterized in that The mineral query report includes a trend forecast result report and a mineral regulation report. Based on the mineral product data and the mineral product price linkage trend chart, a mineral query report is generated, including: By querying mineral product data by the user, determining the product data of the mineral product that the user is querying, the product data includes type, price, output, and regional information; Extract the trend change of product data of the mineral product in the trend graph to obtain a trend prediction result report of the mineral product; Obtain trend forecast result reports of product data of multiple mineral products, generate a mineral regulation report based on the trend forecast result reports of multiple user queries on mineral products, and the trend forecast result reports of the mineral products and the mineral regulation report are used to characterize the mineral query report.

9. A mineral monitoring cloud platform, characterized in that: include: An information acquisition module builds a traceability chain of the target area based on all the process nodes and acquires information of all process nodes on the traceability chain; The information processing module uses blockchain data processing steps to process all the process node information on the traceability chain and upload it to the chain, where the process node information includes public information and private information; An information collection module, which collects the public information of all the process nodes, wherein the public information includes price data; A forecast data determination module, which obtains price forecast data based on the price data and a pre-built forecast model; A linkage trend chart construction module, which obtains a linkage trend chart of mineral product prices based on the price forecast data and the public information of the target area; A query data determination module, in response to a query instruction, obtains user query information and determines mineral product data based on the user query information, wherein the query instruction is used to query the mineral product data; The query report generation module generates a mineral query report based on the mineral product data and the mineral product price linkage trend chart and displays the mineral query report to the user.

10. An electronic device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call instructions from a memory and to implement a mineral monitoring method based on big data according to any one of claims 1 to 8 when executing the instructions.

Images