Investment information processing method and device, storage medium and electronic equipment

Abstract

The invention discloses an investment information processing method and device, a storage medium and electronic equipment. Relates to the technical field of data processing, the field of financial science and technology and other related technical fields, and comprises the steps of obtaining an investment recommendation request, and determining a first remote sensing image corresponding to a land to be invested according to the investment recommendation request; acquiring a second remote sensing image in a target range with the area to which the land to be invested belongs as the center; processing the first remote sensing image and the second remote sensing image according to a target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested; performing risk calculation on the plurality of predicted investment projects to obtain a plurality of investment risk values; and determining a to-be-recommended target investment project according to the plurality of investment risk values. Through the method and the device, the problem that the accuracy of the investment decision is relatively low due to the fact that the investment decision of the land to be invested is determined through similar land investment cases in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the fields of data processing technology, financial technology and other related technical fields, and specifically to a method and device for processing investment information, a storage medium and an electronic device. Background Art

[0002] Currently, when financial institutions provide investment advice to the outside world, they mainly rely on a large number of historical investment cases of similar land, operating information of the invested enterprises, and the investors' own knowledge structure, industry experience, corporate intelligence and other information to make investment decisions. However, the actual characteristics and potential risks of similar lands, such as geological conditions, land ownership, and land use, may vary greatly. At the same time, each investor's own knowledge structure, industry experience, corporate intelligence and other information are highly subjective, and the investors' information processing speed is limited, resulting in investors being unable to identify the risk characteristics of the land to be invested in from a large number of historical investment cases of similar land, and thus unable to make high-quality investment decisions.

[0003] Currently, no effective solution has been proposed to address the problem that in related technologies, investment decisions for land to be invested are determined by using similar land investment cases, resulting in a relatively low accuracy rate of investment decisions. Summary of the invention

[0004] The main purpose of this application is to provide a method and device for processing investment information, a storage medium and an electronic device to solve the problem in the related art that the investment decision for the land to be invested is determined by similar land investment cases, resulting in a relatively low accuracy rate of investment decisions.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for processing investment information is provided. The method includes: obtaining an investment recommendation request, and determining a first remote sensing image corresponding to the land to be invested based on the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; obtaining a second remote sensing image within a target range centered on the area to which the land to be invested belongs; processing the first remote sensing image and the second remote sensing image based on a target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested; performing risk calculations on the multiple predicted investment projects respectively to obtain multiple investment risk values; and determining a target investment project to be recommended based on the multiple investment risk values.

[0006] Furthermore, the first remote sensing image and the second remote sensing image are processed according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested, including: extracting features of the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; extracting features of the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; performing dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; performing dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; determining target feature data of the land to be invested based on the third feature data and the fourth feature data; processing the target feature data according to the output layer of the target neural network model to obtain the multiple predicted investment projects.

[0007] Furthermore, determining the target characteristic data of the land to be invested based on the third characteristic data and the fourth characteristic data includes: performing calculations based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; normalizing the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and determining the target characteristic data of the land to be invested based on the sixth characteristic data.

[0008] Furthermore, based on the sixth characteristic data, determining the target characteristic data of the land to be invested in includes: performing correlation calculation on any two characteristic data in the sixth characteristic data to obtain multiple correlation coefficients; judging whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; if the judgment result indicates that the target correlation coefficient exists among the multiple correlation coefficients, then determining the two characteristic data corresponding to the target correlation coefficient as candidate characteristic data of the target characteristic data; and determining the target characteristic data of the land to be invested in based on the multiple candidate characteristic data.

[0009] Furthermore, performing risk calculations on the multiple predicted investment projects respectively to obtain multiple investment risk values ​​includes: obtaining the investment type corresponding to each predicted investment project; determining a target risk indicator from multiple risk indicators based on the investment type; and performing risk calculations on the multiple predicted investment projects respectively based on the target risk indicator to obtain the multiple investment risk values.

[0010] Furthermore, based on the multiple investment risk values, determining the target investment project to be recommended includes: sorting the multiple investment risk values ​​to obtain a sorted investment risk list; obtaining the first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and determining the investment project corresponding to the first risk value as the target investment project.

[0011] Furthermore, based on the investment recommendation request, determining the first remote sensing image corresponding to the land to be invested includes: based on the investment recommendation request, collecting an initial remote sensing image corresponding to the land to be invested; denoising and correcting the initial remote sensing image to obtain a processed initial remote sensing image; and enhancing the processed initial remote sensing image to obtain the first remote sensing image.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for processing investment information is provided. The device includes: a first acquisition unit, used to acquire an investment recommendation request, and determine a first remote sensing image corresponding to the land to be invested based on the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; a second acquisition unit, used to acquire a second remote sensing image within a target range centered on the area to which the land to be invested belongs; a processing unit, used to process the first remote sensing image and the second remote sensing image based on a target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested; a calculation unit, used to perform risk calculations on the multiple predicted investment projects respectively to obtain multiple investment risk values; and a determination unit, used to determine the target investment project to be recommended based on the multiple investment risk values.

[0013] Furthermore, the processing unit includes: a first feature extraction module, used to perform feature extraction on the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; a second feature extraction module, used to perform feature extraction on the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; a first dimension reduction module, used to perform dimension reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; a second dimension reduction module, used to perform dimension reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; a first determination module, used to determine the target feature data of the land to be invested based on the third feature data and the fourth feature data; a first processing module, used to process the target feature data according to the output layer of the target neural network model to obtain the multiple predicted investment projects.

[0014] Furthermore, the determination module includes: a calculation submodule, used to perform calculations based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; a processing submodule, used to normalize the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and a determination submodule, used to determine the target characteristic data of the land to be invested based on the sixth characteristic data.

[0015] Furthermore, the determination submodule includes: a calculation submodule, used to perform correlation calculation on any two feature data in the sixth feature data to obtain multiple correlation coefficients; a judgment submodule, used to judge whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; a first determination submodule, used to determine the two feature data corresponding to the target correlation coefficient as candidate feature data of the target feature data if the judgment result indicates that the target correlation coefficient exists among the multiple correlation coefficients; and a second determination submodule, used to determine the target feature data of the land to be invested in based on multiple candidate feature data.

[0016] Furthermore, the calculation unit includes: a first acquisition module, used to obtain the investment type corresponding to each predicted investment project; a second determination module, used to determine the target risk indicator from multiple risk indicators based on the investment type; and a calculation module, used to perform risk calculations on the multiple predicted investment projects respectively based on the target risk indicator to obtain the multiple investment risk values.

[0017] Furthermore, the determination unit includes: a sorting module, used to sort the multiple investment risk values ​​to obtain a sorted investment risk list; a second acquisition module, used to obtain a first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and a third determination module, used to determine the investment project corresponding to the first risk value as the target investment project.

[0018] Furthermore, the first acquisition unit includes: an acquisition module, which is used to acquire the initial remote sensing image corresponding to the land to be invested in according to the investment recommendation request; a second processing module, which is used to denoise and correct the initial remote sensing image to obtain a processed initial remote sensing image; and an enhancement module, which is used to enhance the processed initial remote sensing image to obtain the first remote sensing image.

[0019] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned investment information processing methods.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is also provided, the electronic device includes one or more processors and a memory, and the memory is used to store the one or more processors to implement the investment information processing method described in any one of the above.

[0021] Through this application, the following steps are adopted: obtaining an investment recommendation request, and determining the first remote sensing image corresponding to the land to be invested according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; obtaining a second remote sensing image within a target range centered on the area to which the land to be invested belongs; processing the first remote sensing image and the second remote sensing image according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested; performing risk calculations on multiple predicted investment projects respectively to obtain multiple investment risk values; determining the target investment project to be recommended according to the multiple investment risk values, through this application, the problem that the investment decision of the land to be invested is determined by similar land investment cases in the related technology, resulting in a relatively low accuracy of the investment decision. In this scheme, firstly, an investment recommendation request is received from an investment customer, and according to the investment recommendation request, the location and range of the land to be invested are determined, the first remote sensing image of the area is obtained, and the second remote sensing image including the characteristics of a wider area is obtained at the same time. Then, the target neural network model is used to perform image recognition and analysis on the first remote sensing image and the second remote sensing image, identify the land characteristics of the land to be invested, and then obtain multiple predicted investment projects corresponding to the land to be invested. Finally, a risk assessment is conducted on each predicted investment project, and the investment risk value corresponding to each predicted investment project is calculated. Based on multiple investment risk values, the target investment project to be recommended is determined. The target neural network model is used to conduct a comprehensive analysis of the first remote sensing image corresponding to the land to be invested and the second remote sensing image containing wider regional features, accurately identifying multiple predicted investment projects suitable for the land to be invested, and a risk assessment is conducted on each predicted investment project. The predicted investment project with the smallest risk value is determined as the target investment project, avoiding the subjective decision-making caused by the traditional method in which the investment client relies on similar land investment cases and his own investment experience to determine the investment decision for the land to be invested, thereby achieving the effect of improving the accuracy of investment decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 is a flow chart of a method for processing investment information provided in an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of a method for processing investment information provided according to an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of a device for processing investment information provided according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution 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. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0031] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a method for processing investment information provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0032] Step S101, obtaining an investment recommendation request, and determining a first remote sensing image corresponding to the land to be invested in according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution.

[0033] Optionally, the financial institution receives an investment recommendation request from an investment client, including information on investment purpose, land location, investment scale, expected return, etc. According to the land location provided in the investment recommendation request, the specific geographic coordinates or boundary range of the land to be invested are determined. A first remote sensing image corresponding to the land to be invested is obtained through a geographic information system (GIS).

[0034] Step S102, obtaining a second remote sensing image within a target range centered on the area where the land to be invested belongs.

[0035] Optionally, taking the geographical location of the area where the land to be invested is located as the center, a second remote sensing image within the target range is acquired through a geographic information system (GIS), and the acquired second remote sensing image is preprocessed, including: image correction, image cropping, denoising, mosaicking and multi-temporal analysis, so as to obtain more comprehensive geographical and environmental characteristics of the land to be invested.

[0036] Step S103, processing the first remote sensing image and the second remote sensing image according to the target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested.

[0037] Optionally, a convolutional neural network model (CNN), i.e., a target neural network model, is used to perform feature extraction, iterative training and result prediction on the first remote sensing image and the second remote sensing image respectively, and output a plurality of predicted investment projects corresponding to the land to be invested.

[0038] Step S104, performing risk calculations on a plurality of predicted investment projects respectively to obtain a plurality of investment risk values.

[0039] Optionally, the investment risk of each predicted investment project is analyzed and compared to obtain multiple investment risk values ​​to assess the risk level of each investment project and provide a reference for decision-making.

[0040] Step S105, determining target investment projects to be recommended based on multiple investment risk values.

[0041] Optionally, the obtained multiple investment risk values ​​are comprehensively considered, and the predicted investment project with the lowest investment risk value is selected as the target investment project to be recommended.

[0042] In summary, first, an investment recommendation request is received from an investment client, and according to the investment recommendation request, the location and scope of the land to be invested are determined, and a first remote sensing image of the area is obtained, and a second remote sensing image including wider regional features is obtained at the same time. Then, the target neural network model is used to perform image recognition and analysis on the first remote sensing image and the second remote sensing image, and the land features of the land to be invested are identified, and then multiple predicted investment projects corresponding to the land to be invested are obtained. Finally, a risk assessment is performed on each predicted investment project, and the investment risk value corresponding to each predicted investment project is calculated, and the target investment project to be recommended is determined based on the multiple investment risk values. The target neural network model is used to perform a comprehensive analysis on the first remote sensing image corresponding to the land to be invested and the second remote sensing image including wider regional features, accurately identify multiple predicted investment projects suitable for the land to be invested, and perform a risk assessment on each predicted investment project, and determine the predicted investment project with the smallest risk value as the target investment project, thereby avoiding the problem that the investment client in the traditional method relies on similar land investment cases and his own investment experience to determine the investment decision of the land to be invested, resulting in subjective decisions, and thus achieving the effect of improving the accuracy of investment decisions.

[0043] Optionally, in the method for processing investment information provided in the embodiment of the present application, the first remote sensing image and the second remote sensing image are processed according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested, including: extracting features of the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; extracting features of the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; performing dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; performing dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; determining target feature data of the land to be invested based on the third feature data and the fourth feature data; processing the target feature data according to the output layer of the target neural network model to obtain multiple predicted investment projects.

[0044] In an optional embodiment, firstly, the convolution layer of the convolution neural network model (CNN) is used to extract features from the first remote sensing image of the land to be invested and the second remote sensing image of the surrounding area of ​​the land to be invested, and the first feature data (including: the feature data of the terrain, soil conditions and existing buildings of the land to be invested) and the second feature data (including: the feature data of the surrounding infrastructure, transportation network and human flow data of the area to which the land to be invested belongs). Then, the first feature data and the second feature data are respectively subjected to dimensionality reduction processing by the pooling layer of the convolution neural network model (CNN) to reduce the dimension of the feature data and extract important features, and the third set of feature data and the fourth feature data of the land to be invested are obtained. According to a specific feature fusion strategy, the third feature data and the fourth feature data are combined to obtain the target feature data of the land to be invested. Finally, the target feature data is passed to the output layer of the convolution neural network model (CNN) for prediction and processing, and multiple predicted investment projects suitable for the land to be invested are output.

[0045] It should be noted that the output layer of a convolutional neural network model (CNN) usually includes one or more fully connected layers, which are used to map the extracted high-level features to the final prediction results.

[0046] Through the convolutional layer of the convolutional neural network model, high-level features can be accurately extracted from the original image of the land to be invested, and the features can be input into the output layer of the model for prediction and processing, thereby quickly obtaining multiple predicted investment projects corresponding to the land to be invested.

[0047] Optionally, in the method for processing investment information provided in the embodiment of the present application, determining the target characteristic data of the land to be invested based on the third characteristic data and the fourth characteristic data includes: calculating based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; normalizing the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and determining the target characteristic data of the land to be invested based on the sixth characteristic data.

[0048] In an optional embodiment, the third feature data and the fourth feature data are firstly subjected to feature combination, feature comparison, and feature aggregation calculations to obtain the fifth feature data of the land to be invested. Then, the fifth feature data is normalized to eliminate the dimensional influence between different feature data to obtain the sixth feature data. Common normalization methods include: Min-Max normalization method, Z-Score normalization method, and linear normalization method. Finally, the normalized sixth feature data is subjected to feature screening to obtain the target feature data of the land to be invested.

[0049] It should be noted that feature combination is the mathematical combination of related features in two data sets, such as weighted sum, ratio or product; feature comparison is the calculation of feature differences or similarity measures between two data sets; feature aggregation is the aggregation operation of multiple features, such as sum, average, maximum or minimum value.

[0050] By performing feature combination, feature comparison and feature aggregation calculations on the third feature data and the fourth feature data, the fifth feature data of the land to be invested in can be quickly obtained. By normalizing the fifth feature data, the sixth feature data of the land to be invested in can be accurately obtained, and then the target feature data can be determined based on the sixth feature data.

[0051] Optionally, in the method for processing investment information provided in the embodiment of the present application, determining the target characteristic data of the land to be invested in based on the sixth characteristic data includes: performing correlation calculation on any two characteristic data in the sixth characteristic data to obtain multiple correlation coefficients; judging whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; if the judgment result indicates that there is a target correlation coefficient among the multiple correlation coefficients, then determining the two characteristic data corresponding to the target correlation coefficient as candidate characteristic data of the target characteristic data; and determining the target characteristic data of the land to be invested based on the multiple candidate characteristic data.

[0052] In an optional embodiment, according to the data characteristics and data distribution in the sixth feature data, the correlation coefficient (for example: Pearson correlation coefficient, Spearman correlation coefficient or Kendall correlation coefficient) of any two feature data is calculated to achieve feature screening and ensure that each feature data has a substantial contribution to the prediction task. First, a correlation matrix is ​​constructed, in which each element represents the correlation coefficient between a pair of features, and a preset value is used to determine whether the correlation between the two features is significant. Then, the correlation matrix is ​​traversed to determine whether there is a target correlation coefficient greater than or equal to the preset value. If the judgment result shows that there is a target correlation coefficient, the corresponding two feature data are determined as candidate feature data for the target feature data. Finally, for multiple candidate feature data, a multicollinearity test is performed to remove duplicate feature data to avoid collinearity problems in subsequent analysis to obtain the target feature data for the land to be invested.

[0053] By performing correlation calculation on the sixth characteristic data, the key characteristic data of the land to be invested can be effectively determined, and then the predicted investment projects suitable for the land to be invested can be accurately predicted.

[0054] Optionally, in the method for processing investment information provided in the embodiment of the present application, risk calculations are performed on multiple predicted investment projects respectively to obtain multiple investment risk values, including: obtaining the investment type corresponding to each predicted investment project; determining a target risk indicator from multiple risk indicators based on the investment type; and performing risk calculations on multiple predicted investment projects respectively based on the target risk indicator to obtain multiple investment risk values.

[0055] In an optional embodiment, multiple forecast investment projects are first analyzed to determine the investment type of each forecast investment project, such as residential development, commercial real estate, industrial projects, agricultural investment, etc. Then, according to the investment type of each forecast investment project, the target risk indicator is determined in the risk indicator library. For example, for residential development projects, market demand and price fluctuations are focused on; while for commercial real estate, rental income and vacancy rate are focused on. Finally, according to the characteristics of the target risk indicator, an appropriate risk calculation method is selected, including statistical analysis, financial modeling, stress testing, Monte Carlo simulation, etc., and risk calculation is performed on multiple forecast investment projects to obtain multiple investment risk values.

[0056] It should be noted that the risk indicator library contains multiple risk indicators applicable to different investment types, including: market risk, credit risk, liquidity risk, operational risk, exchange rate risk, etc.

[0057] By predicting the investment type of an investment project, we can quickly determine the target risk indicator suitable for each predicted investment project. By calculating and evaluating the risks of the predicted investment project based on the target risk indicator, we can accurately obtain the investment risk value corresponding to each predicted investment project, thereby helping investment clients to better manage investment projects.

[0058] Optionally, in the method for processing investment information provided in the embodiment of the present application, determining the target investment project to be recommended based on multiple investment risk values ​​includes: sorting the multiple investment risk values ​​to obtain a sorted investment risk list; obtaining the first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and determining the investment project corresponding to the first risk value as the target investment project.

[0059] In an optional embodiment, the investment risk values ​​corresponding to the predicted investment projects are sorted in ascending order to form a sorted investment risk list. A first risk value at the first position is obtained from the sorted investment risk list. The investment project corresponding to the first risk value represents the investment project with the lowest risk among the multiple predicted investment projects, and the investment project corresponding to the first risk value is determined as the target investment project.

[0060] By arranging multiple investment risk values ​​in ascending order, the predicted investment project with the smallest risk value can be quickly determined, and then the target investment project can be accurately determined.

[0061] Optionally, in the method for processing investment information provided in the embodiment of the present application, determining the first remote sensing image corresponding to the land to be invested based on the investment recommendation request includes: collecting an initial remote sensing image corresponding to the land to be invested based on the investment recommendation request; denoising and correcting the initial remote sensing image to obtain a processed initial remote sensing image; and performing image enhancement on the processed initial remote sensing image to obtain a first remote sensing image.

[0062] In an optional embodiment, after receiving an investment recommendation request from an investment client, the location, scope and specific requirements of the land to be invested are clarified according to the request information in the investment recommendation request. Then, the initial remote sensing image of the land to be invested is collected through a geographic information system (GIS). Filtering technology is used to remove noise in the initial remote sensing image to improve the image quality. At the same time, the initial remote sensing image is subjected to radiation correction and geometric correction to eliminate the effects of sensor errors and earth curvature, terrain undulations, etc., to obtain a processed initial remote sensing image. Finally, the processed initial remote sensing image is subjected to contrast enhancement, edge enhancement and color enhancement to highlight features useful for investment analysis.

[0063] It should be noted that contrast enhancement is to adjust the contrast of the image to make the differences between different features more obvious; edge enhancement is to highlight the edges in the image, which helps to identify terrain, structures and natural features; color enhancement is to adjust the color of the image to better distinguish different land types.

[0064] By performing preprocessing operations such as denoising, correction and image enhancement on the initial remote sensing image of the land to be invested, the first remote sensing image corresponding to the land to be invested can be obtained quickly and accurately.

[0065] It should be noted that Figure 2 FIG. 1 is a schematic diagram of a method for processing investment information provided in an embodiment of the present application. Figure 2 As shown, firstly, according to the investment recommendation request of the investment client, a first remote sensing image corresponding to the land to be invested and a second remote sensing image within a target range centered on the area to which the land to be invested belongs are determined.

[0066] Then, according to the convolution layer of the target neural network model, the first remote sensing image and the second remote sensing image are respectively feature extracted to obtain the first feature data and the second feature data. According to the pooling layer of the target neural network model, the first feature data and the second feature data are respectively dimensionally reduced to obtain the third feature data and the fourth feature data of the land to be invested. The third feature data and the fourth feature data are subjected to feature combination, feature comparison and feature aggregation calculations to obtain the fifth feature data of the land to be invested. By normalizing the fifth feature data, the dimensional influence between different features can be eliminated to obtain the sixth feature data of the land to be invested. The sixth feature data is feature screened to ensure that each feature data has a substantial contribution to the prediction task to obtain the target feature data of the land to be invested. The target feature data is predicted and processed through the output layer of the target neural network model to obtain multiple predicted investment projects.

[0067] Finally, according to the investment type of each predicted investment project, the corresponding target risk indicator is determined from the risk indicator library, and the risks of multiple predicted investment projects are calculated according to the target risk indicator to obtain multiple investment risk values, and the investment project with the smallest investment risk value is selected as the target investment project.

[0068] The method for processing investment information provided by the embodiment of the present application obtains an investment recommendation request, and determines the first remote sensing image corresponding to the land to be invested according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; obtains a second remote sensing image within a target range centered on the area to which the land to be invested belongs; processes the first remote sensing image and the second remote sensing image according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested; performs risk calculations on multiple predicted investment projects respectively to obtain multiple investment risk values; determines the target investment project to be recommended according to the multiple investment risk values, and solves the problem that the investment decision of the land to be invested is determined by similar land investment cases in the related art, resulting in a relatively low accuracy rate of investment decisions. In summary, in this solution, firstly, an investment recommendation request is received from an investment client, and according to the investment recommendation request, the location and range of the land to be invested are determined, and the first remote sensing image of the area is obtained, and the second remote sensing image including the characteristics of a wider area is obtained at the same time. Then, the target neural network model is used to perform image recognition and analysis on the first remote sensing image and the second remote sensing image to identify the land characteristics of the land to be invested, and then obtain multiple predicted investment projects corresponding to the land to be invested. Finally, a risk assessment is conducted on each predicted investment project, and the investment risk value corresponding to each predicted investment project is calculated. Based on multiple investment risk values, the target investment project to be recommended is determined. The target neural network model is used to conduct a comprehensive analysis of the first remote sensing image corresponding to the land to be invested and the second remote sensing image containing wider regional features, accurately identifying multiple predicted investment projects suitable for the land to be invested, and a risk assessment is conducted on each predicted investment project. The predicted investment project with the smallest risk value is determined as the target investment project, avoiding the subjective decision-making caused by the traditional method in which the investment client relies on similar land investment cases and his own investment experience to determine the investment decision for the land to be invested, thereby achieving the effect of improving the accuracy of investment decisions.

[0069] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0070] The embodiment of the present application also provides an investment information processing device. It should be noted that the investment information processing device of the embodiment of the present application can be used to execute the investment information processing method provided in the embodiment of the present application. The investment information processing device provided in the embodiment of the present application is introduced below.

[0071] Figure 3 Schematic diagram of an investment information processing device according to an embodiment of the present application. Figure 3As shown, the device includes: a first acquisition unit 301, a second acquisition unit 302, a processing unit 303, a calculation unit 304, and a determination unit 305.

[0072] The first acquisition unit 301 is used to acquire an investment recommendation request, and determine a first remote sensing image corresponding to the land to be invested in according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution;

[0073] The second determining unit 302 is used to obtain a second remote sensing image within a target range centered on the area where the land to be invested belongs;

[0074] The processing unit 303 is used to process the first remote sensing image and the second remote sensing image according to the target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested;

[0075] The calculation unit 304 is used to perform risk calculation on a plurality of forecast investment projects respectively to obtain a plurality of investment risk values;

[0076] The determination unit 305 is used to determine the target investment project to be recommended according to multiple investment risk values.

[0077] The investment information processing device provided by the embodiment of the present application comprises: a first acquisition unit 301 acquires an investment recommendation request, and determines a first remote sensing image corresponding to the land to be invested according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; a second determination unit 302 acquires a second remote sensing image within a target range centered on the area to which the land to be invested belongs; a processing unit 303 processes the first remote sensing image and the second remote sensing image according to a target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested; a calculation unit 304 calculates the risk of the plurality of predicted investment projects respectively to obtain a plurality of investment risk values; a determination unit 305 determines the target investment project to be recommended according to the plurality of investment risk values, thereby solving the problem in the related art that the investment decision of the land to be invested is determined by similar land investment cases, resulting in a relatively low accuracy rate of the investment decision. In this solution, an investment recommendation request is first received from an investment client, and according to the investment recommendation request, the location and range of the land to be invested are determined, a first remote sensing image of the area is acquired, and a second remote sensing image including wider regional features is acquired at the same time. Then, the target neural network model is used to perform image recognition and analysis on the first remote sensing image and the second remote sensing image, identify the land features of the land to be invested, and then obtain multiple predicted investment projects corresponding to the land to be invested. Finally, a risk assessment is performed on each predicted investment project, and the investment risk value corresponding to each predicted investment project is calculated. According to the multiple investment risk values, the target investment project to be recommended is determined. The target neural network model is used to perform a comprehensive analysis on the first remote sensing image corresponding to the land to be invested and the second remote sensing image containing wider regional features, accurately identify multiple predicted investment projects suitable for the land to be invested, and perform risk assessment on each predicted investment project, and determine the predicted investment project with the smallest risk value as the target investment project, avoiding the subjective decision-making caused by the traditional method that the investment client relies on similar land investment cases and his own investment experience to determine the investment decision of the land to be invested, thereby achieving the effect of improving the accuracy of investment decisions.

[0078] Optionally, in the investment information processing device provided in the embodiment of the present application, the processing unit includes: a first feature extraction module, used to perform feature extraction on the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; a second feature extraction module, used to perform feature extraction on the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; a first dimensionality reduction module, used to perform dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; a second dimensionality reduction module, used to perform dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; a first determination module, used to determine the target feature data of the land to be invested based on the third feature data and the fourth feature data; a first processing module, used to process the target feature data according to the output layer of the target neural network model to obtain multiple predicted investment projects.

[0079] Optionally, in the investment information processing device provided in the embodiment of the present application, the determination module includes: a calculation submodule, used to calculate based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; a processing submodule, used to normalize the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and a determination submodule, used to determine the target characteristic data of the land to be invested based on the sixth characteristic data.

[0080] Optionally, in the investment information processing device provided in the embodiment of the present application, the determination submodule includes: a calculation submodule, used to perform correlation calculation on any two feature data in the sixth feature data to obtain multiple correlation coefficients; a judgment submodule, used to judge whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; a first determination submodule, used to determine the two feature data corresponding to the target correlation coefficient as candidate feature data of the target feature data if the judgment result indicates that there is a target correlation coefficient among the multiple correlation coefficients; and a second determination submodule, used to determine the target feature data of the land to be invested in based on the multiple candidate feature data.

[0081] Optionally, in the investment information processing device provided in the embodiment of the present application, the calculation unit includes: a first acquisition module, used to obtain the investment type corresponding to each predicted investment project; a second determination module, used to determine the target risk indicator from multiple risk indicators based on the investment type; and a calculation module, used to perform risk calculations on multiple predicted investment projects respectively according to the target risk indicator to obtain multiple investment risk values.

[0082] Optionally, in the investment information processing device provided in the embodiment of the present application, the determination unit includes: a sorting module, used to sort multiple investment risk values ​​to obtain a sorted investment risk list; a second acquisition module, used to obtain a first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and a third determination module, used to determine the investment project corresponding to the first risk value as a target investment project.

[0083] Optionally, in the investment information processing device provided in the embodiment of the present application, the first acquisition unit includes: an acquisition module, used to acquire an initial remote sensing image corresponding to the land to be invested in according to the investment recommendation request; a second processing module, used to denoise and correct the initial remote sensing image to obtain a processed initial remote sensing image; an enhancement module, used to perform image enhancement on the processed initial remote sensing image to obtain a first remote sensing image.

[0084] The device for processing investment information includes a processor and a memory. The above-mentioned first acquisition unit 301, second acquisition unit 302, processing unit 303, calculation unit 304, determination unit 305, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize accurate processing of investment information.

[0085] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and accurate processing of investment information can be achieved by adjusting kernel parameters.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0087] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a method for processing investment information is implemented.

[0088] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes a method for processing investment information when it is run.

[0089] like Figure 4As shown, an embodiment of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: obtaining an investment recommendation request, and determining a first remote sensing image corresponding to the land to be invested based on the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; obtaining a second remote sensing image within a target range centered on the area to which the land to be invested belongs; processing the first remote sensing image and the second remote sensing image based on a target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested; performing risk calculations on the plurality of predicted investment projects respectively to obtain a plurality of investment risk values; and determining a target investment project to be recommended based on the plurality of investment risk values.

[0090] Optionally, the first remote sensing image and the second remote sensing image are processed according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested, including: extracting features of the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; extracting features of the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; performing dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; performing dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; determining target feature data of the land to be invested based on the third feature data and the fourth feature data; processing the target feature data according to the output layer of the target neural network model to obtain multiple predicted investment projects.

[0091] Optionally, determining the target characteristic data of the land to be invested based on the third characteristic data and the fourth characteristic data includes: calculating based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; normalizing the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and determining the target characteristic data of the land to be invested based on the sixth characteristic data.

[0092] Optionally, based on the sixth characteristic data, determining the target characteristic data of the land to be invested includes: performing correlation calculation on any two characteristic data in the sixth characteristic data to obtain multiple correlation coefficients; judging whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; if the judgment result indicates that there is a target correlation coefficient among the multiple correlation coefficients, then determining the two characteristic data corresponding to the target correlation coefficient as candidate characteristic data of the target characteristic data; and determining the target characteristic data of the land to be invested based on the multiple candidate characteristic data.

[0093] Optionally, performing risk calculations on multiple predicted investment projects separately to obtain multiple investment risk values ​​includes: obtaining the investment type corresponding to each predicted investment project; determining a target risk indicator from multiple risk indicators based on the investment type; and performing risk calculations on multiple predicted investment projects separately based on the target risk indicator to obtain multiple investment risk values.

[0094] Optionally, determining the target investment project to be recommended based on multiple investment risk values ​​includes: sorting the multiple investment risk values ​​to obtain a sorted investment risk list; obtaining the first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and determining the investment project corresponding to the first risk value as the target investment project.

[0095] Optionally, based on the investment recommendation request, determining the first remote sensing image corresponding to the land to be invested includes: based on the investment recommendation request, collecting an initial remote sensing image corresponding to the land to be invested; denoising and correcting the initial remote sensing image to obtain a processed initial remote sensing image; and enhancing the processed initial remote sensing image to obtain a first remote sensing image.

[0096] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0097] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining an investment recommendation request, and determining a first remote sensing image corresponding to the land to be invested based on the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; obtaining a second remote sensing image within a target range centered on the area to which the land to be invested belongs; processing the first remote sensing image and the second remote sensing image based on a target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested; performing risk calculations on the multiple predicted investment projects respectively to obtain multiple investment risk values; and determining a target investment project to be recommended based on the multiple investment risk values.

[0098] Optionally, the first remote sensing image and the second remote sensing image are processed according to the target neural network model to obtain multiple predicted investment projects corresponding to the land to be invested, including: extracting features of the first remote sensing image according to the convolution layer of the target neural network model to obtain first feature data; extracting features of the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; performing dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; performing dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; determining target feature data of the land to be invested based on the third feature data and the fourth feature data; processing the target feature data according to the output layer of the target neural network model to obtain multiple predicted investment projects.

[0099] Optionally, determining the target characteristic data of the land to be invested based on the third characteristic data and the fourth characteristic data includes: calculating based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; normalizing the fifth characteristic data to obtain the sixth characteristic data of the land to be invested; and determining the target characteristic data of the land to be invested based on the sixth characteristic data.

[0100] Optionally, based on the sixth characteristic data, determining the target characteristic data of the land to be invested includes: performing correlation calculation on any two characteristic data in the sixth characteristic data to obtain multiple correlation coefficients; judging whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients to obtain a judgment result; if the judgment result indicates that there is a target correlation coefficient among the multiple correlation coefficients, then determining the two characteristic data corresponding to the target correlation coefficient as candidate characteristic data of the target characteristic data; and determining the target characteristic data of the land to be invested based on the multiple candidate characteristic data.

[0101] Optionally, performing risk calculations on multiple predicted investment projects separately to obtain multiple investment risk values ​​includes: obtaining the investment type corresponding to each predicted investment project; determining a target risk indicator from multiple risk indicators based on the investment type; and performing risk calculations on multiple predicted investment projects separately based on the target risk indicator to obtain multiple investment risk values.

[0102] Optionally, determining the target investment project to be recommended based on multiple investment risk values ​​includes: sorting the multiple investment risk values ​​to obtain a sorted investment risk list; obtaining the first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; and determining the investment project corresponding to the first risk value as the target investment project.

[0103] Optionally, based on the investment recommendation request, determining the first remote sensing image corresponding to the land to be invested includes: based on the investment recommendation request, collecting an initial remote sensing image corresponding to the land to be invested; denoising and correcting the initial remote sensing image to obtain a processed initial remote sensing image; and enhancing the processed initial remote sensing image to obtain a first remote sensing image.

[0104] 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 adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0105] 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 box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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.

[0106] 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 comprising 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.

[0107] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0108] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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 adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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.) that contain computer-usable program code.

[0113] 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 method for processing investment information, characterized in that: include: Obtaining an investment recommendation request, and determining a first remote sensing image corresponding to the land to be invested in according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; Acquire a second remote sensing image within a target range centered on the area where the land to be invested belongs; Processing the first remote sensing image and the second remote sensing image according to the target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested; Performing risk calculations on the multiple predicted investment projects respectively to obtain multiple investment risk values; According to the multiple investment risk values, target investment projects to be recommended are determined.

2. The method according to claim 1, characterized in that: The first remote sensing image and the second remote sensing image are processed according to the target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested, including: Extracting features of the first remote sensing image according to the convolutional layer of the target neural network model to obtain first feature data; Performing feature extraction on the second remote sensing image according to the convolution layer of the target neural network model to obtain second feature data; Performing dimensionality reduction processing on the first feature data according to the pooling layer of the target neural network model to obtain third feature data of the land to be invested; Performing dimensionality reduction processing on the second feature data according to the pooling layer of the target neural network model to obtain fourth feature data of the land to be invested; Determining target characteristic data of the land to be invested in based on the third characteristic data and the fourth characteristic data; The target feature data is processed according to the output layer of the target neural network model to obtain the multiple predicted investment projects.

3. The method according to claim 2, characterized in that Determining the target characteristic data of the land to be invested in based on the third characteristic data and the fourth characteristic data includes: Calculating based on the third characteristic data and the fourth characteristic data to obtain the fifth characteristic data of the land to be invested; Normalizing the fifth characteristic data to obtain sixth characteristic data of the land to be invested; The target characteristic data of the land to be invested in is determined based on the sixth characteristic data.

4. The method according to claim 3, characterized in that Determining the target characteristic data of the land to be invested based on the sixth characteristic data includes: Performing correlation calculation on any two of the sixth characteristic data to obtain a plurality of correlation coefficients; Determine whether there is a target correlation coefficient greater than or equal to a preset value among the multiple correlation coefficients, and obtain a determination result; If the judgment result indicates that the target correlation coefficient exists in the multiple correlation coefficients, two feature data corresponding to the target correlation coefficient are determined as candidate feature data for the target feature data; The target characteristic data of the land to be invested is determined based on a plurality of candidate characteristic data.

5. The method according to claim 1, characterized in that Risk calculations are performed on the multiple predicted investment projects respectively to obtain multiple investment risk values ​​including: Get the investment type corresponding to each predicted investment project; Determining a target risk indicator among a plurality of risk indicators based on the investment type; The risk calculations are performed on the multiple predicted investment projects respectively according to the target risk index to obtain the multiple investment risk values.

6. The method according to claim 1, characterized in that Determining the target investment project to be recommended based on the multiple investment risk values ​​includes: Sorting the multiple investment risk values ​​to obtain a sorted investment risk list; Obtaining a first risk value in the sorted investment risk list, wherein the order of the first risk value in the sorted investment risk list is less than the order of the remaining risk values ​​in the sorted investment risk list; The investment project corresponding to the first risk value is determined as the target investment project.

7. The method according to claim 1, characterized in that Determining, according to the investment recommendation request, a first remote sensing image corresponding to the land to be invested in comprises: According to the investment recommendation request, collecting an initial remote sensing image corresponding to the land to be invested; De-noising and correcting the initial remote sensing image to obtain a processed initial remote sensing image; The processed initial remote sensing image is enhanced to obtain the first remote sensing image.

8. An investment information processing device, characterized in that: include: A first acquisition unit is used to acquire an investment recommendation request, and determine a first remote sensing image corresponding to the land to be invested in according to the investment recommendation request, wherein the investment recommendation request is used to request investment advice from a financial institution; A second acquisition unit is used to acquire a second remote sensing image within a target range centered on the area where the land to be invested belongs; A processing unit, configured to process the first remote sensing image and the second remote sensing image according to a target neural network model to obtain a plurality of predicted investment projects corresponding to the land to be invested; A calculation unit, used to perform risk calculation on the multiple predicted investment projects respectively to obtain multiple investment risk values; The determination unit is used to determine the target investment project to be recommended according to the multiple investment risk values.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the storage medium is controlled to execute the method for processing investment information according to any one of claims 1 to 7 on a device.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the investment information processing method described in any one of claims 1 to 7.

Images