Regional economic difficulty influence factor analysis method, model training method, device and equipment

Abstract

The invention relates to a regional economic difficulty influence factor analysis method, a model training method, devices and equipment. The method comprises the following steps: establishing a multi-dimensional economic difficulty influence factor index system, and quantifying each economic difficulty influence factor in the multi-dimensional economic difficulty influence factor index system based on elevation data, traffic data and remote sensing data; the multi-dimensional economic difficulty influence factor index system comprises a traffic level index, an economic level index, an ecological condition index, a population condition index, a welfare level index and a geographic location index, and each index comprises a plurality of economic difficulty influence factors; calculating the contribution degree of each economic difficulty influence factor in the multi-dimensional economic difficulty influence factor index system, and analyzing each economic difficulty influence factor according to the relation graph of each economic difficulty influence factor and the economic difficulty probability and the contribution degree of each economic difficulty influence factor to obtain a multi-dimensional economic difficulty influence factor index system; and the difference of economic difficulty influence factors between different economic difficulty regions can be considered.

Description

Technical Field

[0001] The present disclosure relates to the technical field of economic difficulty analysis, and in particular to a method for analyzing factors affecting regional economic difficulties, a model training method, a device and equipment. Background Art

[0002] The factors affecting economic difficulties in different economically difficult areas are also different. Influenced by many factors such as geographical location and economic development level, the degree of economic difficulties and factors causing difficulties vary greatly among economically difficult areas.

[0003] In the prior art, due to the lack of methods for analyzing factors affecting economic difficulties, it is impossible to explore the causes of regional economic difficulties and effectively analyze the factors affecting economic difficulties, resulting in the inability to take effective measures to improve economically distressed areas. As a result, the improvements for economically distressed areas cannot take into account the differences in factors affecting economic difficulties between economically distressed areas, and the accuracy of the improvements is poor. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method for analyzing factors affecting regional economic difficulties, a model training method, a device and equipment.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for analyzing factors affecting regional economic difficulties, including:

[0006] Establish a multi-dimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multi-dimensional economic hardship influencing factor index system includes traffic level indicators, economic level indicators, ecological status indicators, population status indicators, welfare level indicators, and geographical location indicators, and each indicator includes multiple economic hardship influencing factors;

[0007] Calculating the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system;

[0008] Construct a relationship diagram between each factor affecting economic difficulties and the probability of economic difficulties;

[0009] Based on the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, as well as the contribution of each economic difficulty influencing factor, each economic difficulty influencing factor is analyzed.

[0010] In a second aspect, the present disclosure provides a model training method, including:

[0011] Construct an analysis model of factors affecting economic difficulties;

[0012] Acquire multiple sets of training sample data and actual economic hardship attributes corresponding to each set of training sample data, wherein each set of training sample data includes values ​​of various economic hardship influencing factors;

[0013] Based on each set of training sample data, the economic hardship influencing factor analysis model to be trained is trained to obtain the importance score of each economic hardship influencing factor;

[0014] Based on the importance scores of the economic hardship influencing factors and the values ​​of the economic hardship influencing factors, the economic hardship attribute of each group of training sample data is predicted to obtain the predicted economic hardship attribute of each group of training sample data;

[0015] Performing loss calculation on the actual economic hardship attribute corresponding to each group of training sample data based on the predicted economic hardship attribute of each group of training sample data, to obtain a loss calculation result of the economic hardship influencing factor analysis model;

[0016] Based on the loss calculation result of the economic hardship influencing factor analysis model, the model parameters of the economic hardship influencing factor analysis model are updated.

[0017] In some embodiments, after updating the model parameters of the economic hardship influencing factor analysis model based on the loss calculation result of the economic hardship influencing factor analysis model, the method further includes:

[0018] Determining whether the predicted economic hardship attribute of each set of training sample data converges to the actual economic hardship attribute corresponding to each set of training sample data;

[0019] If the predicted economic hardship attribute of each set of training sample data has converged to the actual economic hardship attribute corresponding to each set of training sample data, it is determined that the training of the economic hardship influencing factor analysis model is completed.

[0020] In a third aspect, an embodiment of the present disclosure provides a device for analyzing factors affecting regional economic difficulties, including:

[0021] Establish a module for establishing a multidimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic hardship influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index, and a geographical location index, and each index includes multiple economic hardship influencing factors;

[0022] A calculation module, used to calculate the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system;

[0023] A construction module is used to construct a relationship diagram between various economic hardship influencing factors and the probability of economic hardship;

[0024] The analysis module is used to analyze each economic difficulty influencing factor according to a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty and a contribution degree of each economic difficulty influencing factor.

[0025] In a fourth aspect, an embodiment of the present disclosure provides a model training device, including:

[0026] A construction module for constructing an analysis model of factors affecting economic difficulties;

[0027] An acquisition module, used to acquire multiple sets of training sample data and actual economic hardship attributes corresponding to each set of training sample data, wherein each set of training sample data includes a value of each economic hardship influencing factor;

[0028] The first obtaining module is used to train the economic hardship influencing factor analysis model to be trained based on each group of training sample data to obtain the importance score of each economic hardship influencing factor;

[0029] A second obtaining module is used to predict the economic hardship attribute of each group of training sample data based on the importance score of each economic hardship influencing factor and the value of each economic hardship influencing factor to obtain the predicted economic hardship attribute of each group of training sample data;

[0030] A loss calculation module, configured to perform loss calculation on the actual economic hardship attribute corresponding to each group of training sample data based on the predicted economic hardship attribute of each group of training sample data, and obtain a loss calculation result of the economic hardship influencing factor analysis model;

[0031] An updating module is used to update the model parameters of the economic hardship influencing factor analysis model based on the loss calculation result of the economic hardship influencing factor analysis model.

[0032] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0033] Memory;

[0034] Processor; and

[0035] Computer programs;

[0036] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect or the second aspect.

[0037] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method as described in the first aspect or the second aspect.

[0038] In a seventh aspect, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the method for analyzing factors affecting regional economic difficulties as described above is implemented.

[0039] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0040] In the regional economic difficulties influencing factor analysis method, model training method, device and equipment provided in the embodiments of the present disclosure, a multidimensional economic difficulties influencing factor index system is established, and each economic difficulties influencing factor in the multidimensional economic difficulties influencing factor index system is quantified based on elevation data, traffic data and remote sensing data. The multidimensional economic difficulties influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index and a geographical location index, and each index includes multiple economic difficulties influencing factors. The contribution of each economic difficulties influencing factor in the multidimensional economic difficulties influencing factor index system is calculated, and a relationship diagram between each economic difficulties influencing factor and the economic difficulties probability is constructed. Then, according to the relationship diagram between each economic difficulties influencing factor and the economic difficulties probability, and the contribution of each economic difficulties influencing factor, each economic difficulties influencing factor is analyzed. Compared with the prior art, the present disclosure establishes a multidimensional economic difficulties influencing factor index system, and quantifies each economic difficulties influencing factor in the multidimensional economic difficulties influencing factor index system based on elevation data, traffic data and remote sensing data. Furthermore, the contribution of each economic difficulty influencing factor in the multi-dimensional economic difficulty influencing factor index system is calculated, and a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty is constructed. Then, according to the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty and the contribution of each economic difficulty influencing factor, each economic difficulty influencing factor is analyzed, the causes of regional economic difficulties can be explored, the economic difficulty influencing factors can be effectively analyzed, the differences in economic difficulty influencing factors between different economic difficulty regions can be taken into account, and effective measures can be taken to improve the economic difficulty regions and improve the accuracy of the improvement, so that transportation construction can be accurately planned, the comprehensive transportation system can be improved, and the pertinence and effectiveness of transportation planning and transportation investment policies for economic difficulty regions can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 It is a flow chart of a method for analyzing factors affecting regional economic difficulties provided by an embodiment of the present disclosure;

[0044] Figure 2 is a flow chart of a method for analyzing factors affecting regional economic difficulties provided by another embodiment of the present disclosure;

[0045] Figure 3 It is a schematic diagram of the overall process of a method for analyzing factors affecting regional economic difficulties provided by an embodiment of the present disclosure;

[0046] Figure 4 is a flow chart of a model training method provided by an embodiment of the present disclosure;

[0047] Figure 5 A schematic diagram of the structure of a device for analyzing factors affecting regional economic difficulties provided by an embodiment of the present disclosure;

[0048] Figure 6 A schematic diagram of the structure of a model training device provided in an embodiment of the present disclosure;

[0049] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0050] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0052] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0053] The factors affecting economic difficulties in different economically difficult areas are also different. Influenced by many factors such as geographical location and economic development level, the degree of economic difficulties and factors causing difficulties vary greatly among economically difficult areas.

[0054] In the prior art, due to the lack of methods for analyzing factors affecting economic difficulties, it is impossible to explore the causes of regional economic difficulties and effectively analyze the factors affecting economic difficulties, resulting in the inability to take effective measures to improve economically distressed areas. As a result, the improvements for economically distressed areas cannot take into account the differences in factors affecting economic difficulties between economically distressed areas, and the accuracy of the improvements is poor.

[0055] To address this problem, an embodiment of the present disclosure provides a method for analyzing factors affecting regional economic difficulties, which will be introduced below in conjunction with specific embodiments.

[0056] Figure 1 A flow chart of the method for analyzing factors affecting regional economic difficulties provided in the embodiment of the present disclosure. The method can be applied to electronic devices, which may be portable mobile devices such as smart phones, tablet computers, laptops, in-vehicle navigation devices, and smart sports equipment; they may also be fixed devices such as personal computers and smart home appliances. The method can be applied to scenarios for identifying factors affecting economic difficulties, and can also be applied to scenarios for analyzing factors affecting economic difficulties. The causes of regional economic difficulties can be explored, and the factors affecting economic difficulties can be effectively analyzed. The differences in factors affecting economic difficulties between different economically difficult areas can be taken into account, and effective measures can be taken to improve the economically difficult areas, improve the accuracy of the improvements, and accurately plan transportation construction. It can be understood that the method for analyzing factors affecting regional economic difficulties provided in the embodiment of the present disclosure can also be applied in other scenarios.

[0057] Below Figure 1 The method for analyzing the factors affecting regional economic difficulties is introduced in detail. The specific steps of this method are as follows:

[0058] S101. Establish a multidimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic hardship influencing factor index system includes traffic level indicators, economic level indicators, ecological status indicators, population status indicators, welfare level indicators, and geographical location indicators, and each indicator includes multiple economic hardship influencing factors.

[0059] In this step, the electronic device establishes a multi-dimensional economic hardship influencing factor index system, and quantifies each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. In some embodiments, each economic hardship influencing factor can also be quantified based on multi-source data (including remote sensing data, DEM elevation data), statistical yearbooks, traffic data (such as spatial geographic data of traffic line types, railway and airline timetables), medical facility accessibility data, and application software interface call data. In some embodiments, Figure 3 As shown, the multi-dimensional economic hardship influencing factor index system includes multiple indicators, and the multiple indicators include economic level indicators, ecological status indicators, population status indicators, transportation level indicators, welfare level indicators, and geographical location indicators; each indicator includes multiple economic hardship influencing factors.

[0060] As shown in Table 1, 1) The economic level index includes three economic difficulty influencing factors, namely, per capita regional gross domestic product (regional GDP), urbanization level, and economic development differences. Among them, per capita regional GDP comes from the statistical data of each region. The urbanization level is calculated using remote sensing monitoring data. The economic development difference is measured using the coefficient of variation of the night light intensity distribution of the grid within the region.

[0061] 2) Ecological status indicators include the regional average altitude and surface undulation calculated based on elevation data, the proportion of ecologically fragile areas and per capita cultivated land area calculated based on land use remote sensing data.

[0062] 3) Population status indicators select factors affecting economic difficulties from three aspects: total population, population structure and population quality.

[0063] 4) Traffic level indicators mainly include the following economic difficulties influencing factors: ① Line type spatial geographic data of expressways, grade roads, railways, and high-speed railways; ② Point type spatial geographic data of high-speed railway stations, railway stations, airports, and highway entrances and exits, obtained by calling the map interface (API) location retrieval service; ③ Railway train schedule data; ④ Flight schedule data; ⑤ Proximity indicators of various types of transportation, obtained by calling the map interface (API) path planning service; ⑥ Highway demonstration area.

[0064] 5) The welfare level index is measured using the POI data of education and medical care at different levels.

[0065] 6) The geographic location index is a measure of the spatial distance between the seat of each regional government and the nearest prefecture-level city or large city government seat calculated using the ArcGIS nearest neighbor analysis tool.

[0066] Table 1 Index system and meaning of multi-dimensional economic difficulties influencing factors

[0067]

[0068]

[0069]

[0070] S102: Calculate the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system.

[0071] After quantifying each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system, the electronic device can calculate the contribution of each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system. Specifically, the contribution of each economic difficulty influencing factor can be obtained based on a grid search-cross validation-extreme gradient boosting tree analysis framework.

[0072] As shown in Table 2, the importance scores of each economic difficulty influencing factor and the contribution of each economic difficulty influencing factor are calculated based on the values ​​of each economic difficulty influencing factor corresponding to the economic difficulty areas identified by the three economic difficulty area identification mechanisms, and the values ​​of each economic difficulty influencing factor corresponding to the non-economic difficulty areas.

[0073] Table 2 Contribution and importance score ranking of various economic difficulties influencing factors

[0074]

[0075]

[0076] S103. Construct a relationship diagram between various economic hardship influencing factors and the probability of economic hardship.

[0077] In this step, the electronic device constructs a relationship diagram between each economic difficulty influencing factor and the economic difficulty probability. By constructing the relationship diagram, the optimal value range of each economic difficulty influencing factor can be accurately understood, and the nonlinear relationship between the economic difficulty probability and each economic difficulty influencing factor can be explored.

[0078] S104. Analyze each economic difficulty influencing factor based on the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability and the contribution of each economic difficulty influencing factor.

[0079] In this step, the electronic device analyzes each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability, and the contribution of each economic difficulty influencing factor. The greater the contribution, the higher the importance of the economic difficulty influencing factor, and the stronger the decisive role of the economic difficulty degree. In addition, by analyzing each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability, the optimal numerical range of each economic difficulty influencing factor can be accurately understood, and the nonlinear relationship between the economic difficulty degree and each economic difficulty influencing factor can be explored, so as to effectively support the implementation of policies such as transportation investment, and has the advantages of accurate identification and strong operability.

[0080] The embodiment of the present disclosure establishes a multidimensional economic difficulty influencing factor index system, and quantifies each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic difficulty influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index, and a geographical location index. Each index includes multiple economic difficulty influencing factors, calculates the contribution of each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system, constructs a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, and analyzes each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty and the contribution of each economic difficulty influencing factor. Compared with the prior art, the present disclosure establishes a multidimensional economic difficulty influencing factor index system, and quantifies each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system. Further, the contribution of each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system is calculated, and a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty is constructed. Then, based on the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, as well as the contribution of each economic difficulty influencing factor, each economic difficulty influencing factor can be analyzed, the causes of regional economic difficulties can be explored, the economic difficulty influencing factors can be effectively analyzed, the differences in economic difficulty influencing factors between different economically difficult areas can be taken into account, and then effective measures can be taken to improve the economically difficult areas and improve the accuracy of the improvement. It is possible to accurately plan transportation construction, improve the comprehensive transportation system, and improve the pertinence and effectiveness of transportation planning and transportation investment policies for economically difficult areas.

[0081] Figure 2 A flowchart of a method for analyzing factors affecting regional economic difficulties provided by another embodiment of the present disclosure, the method includes the following specific steps:

[0082] S201. Establish a multidimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic hardship influencing factor index system includes traffic level indicators, economic level indicators, ecological status indicators, population status indicators, welfare level indicators, and geographical location indicators, and each indicator includes multiple economic hardship influencing factors.

[0083] Specifically, the implementation process and principle of S201 and S101 are the same, and will not be repeated here.

[0084] S202: Identify factors to be eliminated from various economic hardship influencing factors, and eliminate the factors to be eliminated from various economic hardship influencing factors.

[0085] After quantifying each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system, the electronic device identifies the factors to be eliminated from each economic difficulty influencing factor, and eliminates the factors to be eliminated from each economic difficulty influencing factor. Optionally, the factors to be eliminated are multicollinearity factors, and there are multicollinearity factors in each economic difficulty influencing factor. The electronic device identifies the multicollinearity factors from each economic difficulty influencing factor, eliminates the multicollinearity factors in each economic difficulty influencing factor, and obtains each economic difficulty influencing factor after elimination. In some embodiments, the variance inflation factor (VIF) test method can be used to identify multicollinearity factors.

[0086] In some embodiments, S202 includes but is not limited to S2021 and S2022:

[0087] S2021. For any economic difficulty influencing factor among various economic difficulty influencing factors, calculate the variance inflation coefficient of the economic difficulty influencing factor;

[0088] In this step, the electronic device calculates the variance inflation coefficient of any economic difficulty influencing factor among the various economic difficulty influencing factors. The variance inflation coefficient is an indicator reflecting the degree of linear correlation between independent variables. The calculation method is: for each independent variable, it is regressed with other independent variables, and then the residual sum of squares is taken, and finally VIF=1 / (1-R^2), where R^2 represents the degree of linear correlation between the independent variable and other independent variables. Generally, if the VIF value is greater than 10, multicollinearity exists.

[0089] S2022. If the variance inflation coefficient of the economic hardship factor is greater than a preset threshold, the economic hardship factor is determined to be a factor to be eliminated;

[0090] In this step, it is determined whether the variance inflation coefficient of the economic hardship factor is greater than a preset threshold. If the variance inflation coefficient of the economic hardship factor is greater than the preset threshold, the economic hardship factor is determined to be a factor to be eliminated. Optionally, the preset threshold may be 10. If the VIF value of the economic hardship factor is greater than 10, there is multicollinearity, and the economic hardship factor is a factor to be eliminated.

[0091] S203. Calculate the importance score of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system by using the economic hardship influencing factor analysis model.

[0092] In this step, the electronic device obtains the values ​​of each economic difficulty influencing factor in the economic difficulty area and the non-economic difficulty area, inputs the values ​​of each economic difficulty influencing factor in the economic difficulty area and the non-economic difficulty area into the economic difficulty influencing factor analysis model, and calculates the importance score of each economic difficulty influencing factor through the economic difficulty influencing factor analysis model. Figure 3 As shown in the figure, the economic hardship influencing factor analysis model is based on the XGBoost machine learning model. The extreme gradient boosting tree (eXtreme Gradient Boosting Decision Tree, XGBoost) is a classification regression tree (CARTS) that adds a regular term to the gradient boosting tree (GBDT) function to prevent the model from overfitting and improve the generalization performance of the model.

[0093] S204. Calculate the contribution of each economic difficulty influencing factor based on the importance score of each economic difficulty influencing factor.

[0094] After obtaining the importance scores of various economic difficulties influencing factors, such as Figure 3 As shown, the electronic device can calculate the contribution of each economic difficulty influencing factor. Specifically, the quotient obtained by dividing the importance score of each economic difficulty influencing factor by the sum of the importance scores of each economic difficulty influencing factor is determined as the contribution of each economic difficulty influencing factor.

[0095] S205. Generate a relationship diagram between each economic difficulty influencing factor and the economic difficulty probability according to the numerical value of each economic difficulty influencing factor and the corresponding economic difficulty probability.

[0096] In this step, after calculating the contribution of each economic difficulty influencing factor, the electronic device can generate a relationship diagram between each economic difficulty influencing factor and the economic difficulty probability according to the value of each economic difficulty influencing factor and the corresponding economic difficulty probability. Optionally, the relationship diagram can be a partial dependency plot (PDP) used to characterize the relationship between each economic difficulty influencing factor and the economic difficulty probability (or economic difficulty degree), with the horizontal axis being the value of each economic difficulty influencing factor and the vertical axis being the economic difficulty probability (or economic difficulty degree).

[0097] S206. Analyze each economic difficulty influencing factor based on the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability and the contribution of each economic difficulty influencing factor.

[0098] In this step, the electronic device analyzes each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability, and the contribution of each economic difficulty influencing factor. The greater the contribution, the higher the importance of the economic difficulty influencing factor, and the stronger the decisive role of the economic difficulty degree. In addition, by analyzing each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability, the optimal numerical range of each economic difficulty influencing factor can be accurately understood, and the nonlinear relationship between the economic difficulty degree and each economic difficulty influencing factor can be explored, so as to effectively support the implementation of policies such as transportation investment, and has the advantages of accurate identification and strong operability.

[0099] The disclosed embodiment establishes a multidimensional economic difficulty influencing factor index system, and quantifies each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic difficulty influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index, and a geographical location index. Each index includes multiple economic difficulty influencing factors, and the factors to be eliminated are identified from each economic difficulty influencing factor, and the factors to be eliminated in each economic difficulty influencing factor are eliminated. Further, the importance score of each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system is calculated using an economic difficulty influencing factor analysis model, and the contribution of each economic difficulty influencing factor is calculated based on the importance score of each economic difficulty influencing factor. Then, according to the numerical value of each economic difficulty influencing factor and the corresponding economic difficulty probability, a relationship diagram between each economic difficulty influencing factor and the economic difficulty probability is generated, and each economic difficulty influencing factor is analyzed according to the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability and the contribution of each economic difficulty influencing factor. Compared with the prior art, the embodiments of the present disclosure can explore the causes of regional economic difficulties, can effectively analyze the factors affecting economic difficulties, can take into account the differences in factors affecting economic difficulties between different economically difficult areas, and then can take effective measures to improve the economically difficult areas and improve the accuracy of the improvements. It can accurately plan transportation construction and improve the pertinence and effectiveness of transportation planning and transportation investment policies for economically difficult areas.

[0100] Figure 4 A flow chart of the model training method provided in the embodiment of the present disclosure, such as Figure 4 As shown, the method includes the following steps:

[0101] S301. Construct an analysis model of factors affecting economic difficulties.

[0102] In this step, the electronic device constructs an analysis model of factors affecting economic difficulties. Specifically, the analysis model of factors affecting economic difficulties can be a machine learning model based on XGBoost. The extreme gradient boosting tree (eXtreme GradientBoosting Decision Tree, XGBoost) is a classification regression tree (CARTS) that adds a regularization term to the gradient boosting tree (GBDT) function to prevent the model from overfitting and improve the generalization performance of the model.

[0103] S302: Acquire multiple sets of training sample data and actual economic hardship attributes corresponding to each set of training sample data, wherein each set of training sample data includes values ​​of various economic hardship influencing factors.

[0104] In this step, the electronic device obtains multiple sets of training sample data and the actual economic hardship attribute corresponding to each set of training sample data, wherein each set of training sample data includes the value of each economic hardship influencing factor. Optionally, the multiple sets of training sample data and the actual economic hardship attribute corresponding to each set of training sample data can be data stored locally in the electronic device, or can be from data stored in a server.

[0105] In some embodiments, the multiple sets of training sample data are the values ​​of various economic hardship influencing factors corresponding to economically hardship areas determined by light intensity data and population grid data, and the values ​​of various economic hardship influencing factors corresponding to non-economically hardship areas.

[0106] S303: Train the economic hardship influencing factor analysis model to be trained based on each set of training sample data to obtain the importance score of each economic hardship influencing factor and the predicted economic hardship attribute of each set of training sample data.

[0107] In this step, the electronic device trains the economic hardship influencing factor analysis model to be trained based on each set of training sample data, and obtains the importance score of each economic hardship influencing factor and the predicted economic hardship attribute of each set of training sample data. Since the parameters of the model are not optimal, the predicted economic hardship attribute during the training process may not be close to the actual economic hardship attribute. Training the model based on sufficient training sample data can improve the accuracy of the economic hardship influencing factor analysis model in analyzing the economic hardship influencing factors.

[0108] S304: Perform loss calculation on the actual economic hardship attribute corresponding to each group of training sample data based on the predicted economic hardship attribute of each group of training sample data to obtain a loss calculation result of the economic hardship influencing factor analysis model.

[0109] After obtaining the predicted economic hardship attribute of each set of training sample data, a loss calculation is performed on the actual economic hardship attribute corresponding to each set of training sample data based on the predicted economic hardship attribute of each set of training sample data to obtain the loss calculation result of the economic hardship influencing factor analysis model. The smaller the loss calculation result, the closer the predicted economic hardship attribute is to the actual economic hardship attribute, the more accurate the analysis of economic hardship influencing factors is, and the higher the current accuracy of the model is. Specifically, the loss calculation can be performed through a loss function.

[0110] S305: Based on the loss calculation result of the economic hardship influencing factor analysis model, update the model parameters of the economic hardship influencing factor analysis model.

[0111] In this step, the model parameters of the economic hardship influencing factor analysis model are updated according to the loss calculation results of the economic hardship influencing factor analysis model, thereby improving the analysis accuracy of the economic hardship influencing factor analysis model. As the number of training times increases, the parameters of the model are continuously adjusted so that the predicted economic hardship attributes are closer and closer to the actual economic hardship attributes.

[0112] In some embodiments, the model parameters of the economic hardship influencing factor analysis model are updated by grid search-cross validation. Specifically, a numerical range is set for each parameter, the parameters are continuously adjusted during the training process, the optimal value of each parameter is verified from the numerical range of each parameter, and the model parameters are adjusted to the optimal value of each parameter.

[0113] In some embodiments, S305 may also include but is not limited to S306 and S307:

[0114] S306: Determine whether the predicted economic hardship attribute of each set of training sample data converges to the actual economic hardship attribute corresponding to each set of training sample data.

[0115] The electronic device determines whether the predicted economic hardship attribute of each set of training sample data converges to the actual economic hardship attribute corresponding to each set of training sample data. If the predicted economic hardship attribute is close to the actual economic hardship attribute, it means that the predicted economic hardship attribute converges to the actual economic hardship attribute.

[0116] S307: If the predicted economic hardship attribute of each set of training sample data has converged to the actual economic hardship attribute corresponding to each set of training sample data, it is determined that the training of the economic hardship influencing factor analysis model is completed.

[0117] When the predicted economic hardship attributes of each set of training sample data have converged to the actual economic hardship attributes corresponding to each set of training sample data, the training of the economic hardship influencing factor analysis model is completed, and the economic hardship influencing factor analysis model can be used to analyze the economic hardship influencing factors of economically difficult areas.

[0118] The disclosed embodiment constructs an analysis model of economic difficulties influencing factors, obtains multiple groups of training sample data and actual economic difficulties attributes corresponding to each group of training sample data, and each group of training sample data includes the numerical values ​​of each economic difficulties influencing factor. Then, the economic difficulties influencing factor analysis model to be trained is trained based on each group of training sample data to obtain the importance score of each economic difficulties influencing factor and the predicted economic difficulties attributes of each group of training sample data, and the loss calculation of the actual economic difficulties attributes corresponding to each group of training sample data is performed based on the predicted economic difficulties attributes of each group of training sample data to obtain the loss calculation result of the economic difficulties influencing factor analysis model. Further, based on the loss calculation result of the economic difficulties influencing factor analysis model, the model parameters of the economic difficulties influencing factor analysis model are updated to determine whether the predicted economic difficulties attributes of each group of training sample data converge to the actual economic difficulties attributes corresponding to each group of training sample data. Furthermore, if the predicted economic difficulties attributes of each group of training sample data have converged to the actual economic difficulties attributes corresponding to each group of training sample data, it is determined that the training of the economic difficulties influencing factor analysis model is completed. Since the economic hardship influencing factors analysis model is trained, loss calculation is performed on the actual economic hardship attributes corresponding to each group of training sample data based on the predicted economic hardship attributes of each group of training sample data, and the loss calculation results of the economic hardship influencing factors analysis model are obtained. Through the loss calculation results, the model parameters are continuously updated to improve the accuracy of the economic hardship influencing factors analysis model, thereby improving the economic hardship influencing factors analysis performance, effectively analyzing the economic hardship influencing factors, taking into account the differences in economic hardship influencing factors between different economically difficult areas, so that effective measures can be taken to improve the economically difficult areas and improve the accuracy of the improvements. The transportation construction can be accurately planned, and the pertinence and effectiveness of transportation planning and transportation investment policies for economically difficult areas can be improved.

[0119] Figure 5 The schematic diagram of the structure of the device for analyzing factors affecting regional economic difficulties provided by the embodiment of the present disclosure. The device for analyzing factors affecting regional economic difficulties may be the electronic device as described in the above embodiment, or the device for analyzing factors affecting regional economic difficulties may be a component or assembly in the electronic device. The device for analyzing factors affecting regional economic difficulties provided by the embodiment of the present disclosure may execute the processing flow provided by the method for analyzing factors affecting regional economic difficulties, such as Figure 5As shown, the regional economic difficulty influencing factor analysis device 50 includes: an establishment module 51, a calculation module 52, a construction module 53, and an analysis module 54; wherein the establishment module 51 is used to establish a multidimensional economic difficulty influencing factor index system, and quantify each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system based on elevation data, traffic data, and remote sensing data, wherein the multidimensional economic difficulty influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index, and a geographical location index, and each indicator includes multiple economic difficulty influencing factors; the calculation module 52 is used to calculate the contribution of each economic difficulty influencing factor in the multidimensional economic difficulty influencing factor index system; the construction module 53 is used to construct a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty; the analysis module 54 is used to analyze each economic difficulty influencing factor according to the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, and the contribution of each economic difficulty influencing factor.

[0120] Optionally, before calculating the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system, the device 50 also includes: an elimination module 55; the elimination module 55 is used to identify factors to be eliminated from each economic hardship influencing factor, and eliminate the factors to be eliminated from each economic hardship influencing factor.

[0121] Optionally, when the elimination module 55 identifies the target influencing factor from various economic hardship influencing factors, it is specifically used to: calculate the variance inflation coefficient of any economic hardship influencing factor among the various economic hardship influencing factors; if the variance inflation coefficient of the economic hardship influencing factor is greater than a preset threshold, determine that the economic hardship influencing factor is a factor to be eliminated.

[0122] Optionally, when the calculation module 52 calculates the contribution of each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system, it is specifically used to: use the economic hardship influencing factor analysis model to calculate the importance score of each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system; based on the importance score of each economic hardship influencing factor, calculate the contribution of each economic hardship influencing factor.

[0123] Optionally, when constructing the relationship graph between each economic difficulty influencing factor and the economic difficulty probability, the construction module 53 is specifically used to: generate a relationship graph between each economic difficulty influencing factor and the economic difficulty probability according to the numerical value of each economic difficulty influencing factor and the corresponding economic difficulty probability.

[0124] Figure 5The device for analyzing factors affecting regional economic difficulties in the illustrated embodiment can be used to implement the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0125] Figure 6 The schematic diagram of the structure of the model training device provided in the embodiment of the present disclosure. The model training device may be the electronic device as described in the above embodiment, or the model training device may be a component or assembly in the electronic device. The model training device provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the model training method, such as Figure 6 As shown, the model training device 60 includes: a construction module 61, an acquisition module 62, a obtaining module 63, a loss calculation module 64, and an updating module 65; wherein the construction module 61 is used to construct an economic hardship influencing factor analysis model; the acquisition module 62 is used to obtain multiple groups of training sample data and actual economic hardship attributes corresponding to each group of training sample data, and each group of training sample data includes the numerical values ​​of each economic hardship influencing factor; the obtaining module 63 is used to train the economic hardship influencing factor analysis model to be trained based on each group of training sample data, and obtain the importance score of each economic hardship influencing factor and the predicted economic hardship attributes of each group of training sample data; the loss calculation module 64 is used to perform loss calculation on the actual economic hardship attributes corresponding to each group of training sample data based on the predicted economic hardship attributes of each group of training sample data, and obtain the loss calculation result of the economic hardship influencing factor analysis model; the updating module 65 is used to update the model parameters of the economic hardship influencing factor analysis model based on the loss calculation result of the economic hardship influencing factor analysis model.

[0126] Optionally, the model training device 60 also includes: a judgment module 66 and a determination module 67; the judgment module 66 is used to judge whether the predicted economic hardship attribute of each group of training sample data converges to the actual economic hardship attribute corresponding to each group of training sample data; the determination module 67 is used to determine that the training of the economic hardship influencing factor analysis model is completed if the predicted economic hardship attribute of each group of training sample data has converged to the actual economic hardship attribute corresponding to each group of training sample data.

[0127] Figure 6 The model training device of the illustrated embodiment can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0128] Figure 7 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 7 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 7The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0129] like Figure 7 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503 to implement the regional economic difficulties influencing factor analysis method of the embodiment described in the present disclosure. In RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0130] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0131] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the regional economic hardship influencing factor analysis method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0132] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0133] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0134] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0135] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0136] Establish a multi-dimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multi-dimensional economic hardship influencing factor index system includes traffic level indicators, economic level indicators, ecological status indicators, population status indicators, welfare level indicators, and geographical location indicators, and each indicator includes multiple economic hardship influencing factors;

[0137] Calculating the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system;

[0138] Construct a relationship diagram between each factor affecting economic difficulties and the probability of economic difficulties;

[0139] Based on the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, as well as the contribution of each economic difficulty influencing factor, each economic difficulty influencing factor is analyzed.

[0140] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0141] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0142] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0144] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0145] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0146] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0147] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for analyzing factors affecting regional economic difficulties, characterized in that: The method comprises: Establish a multi-dimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multi-dimensional economic hardship influencing factor index system includes traffic level indicators, economic level indicators, ecological status indicators, population status indicators, welfare level indicators, and geographical location indicators, and each indicator includes multiple economic hardship influencing factors; Calculating the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system; Construct a relationship diagram between each factor affecting economic difficulties and the probability of economic difficulties; Based on the relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty, as well as the contribution of each economic difficulty influencing factor, each economic difficulty influencing factor is analyzed.

2. The method according to claim 1, characterized in that Before calculating the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system, the method further includes: Identify factors to be eliminated from various economic hardship influencing factors, and eliminate the factors to be eliminated from various economic hardship influencing factors.

3. The method according to claim 2, characterized in that The target influencing factors are identified from various economic hardship influencing factors, including: For any economic hardship influencing factor among various economic hardship influencing factors, calculate the variance inflation coefficient of the economic hardship influencing factor; If the variance inflation coefficient of the economic hardship influencing factor is greater than the preset threshold, the economic hardship influencing factor is determined to be a factor to be eliminated.

4. The method according to claim 1, characterized in that: The calculating of the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system includes: Calculate the importance score of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system by using the economic hardship influencing factor analysis model; Based on the importance score of each economic hardship influencing factor, the contribution of each economic hardship influencing factor is calculated.

5. The method according to claim 1, characterized in that: The construction of the relationship diagram between each economic difficulty influencing factor and the economic difficulty probability includes: According to the values ​​of various economic hardship influencing factors and the corresponding economic hardship probabilities, a relationship diagram between various economic hardship influencing factors and economic hardship probabilities is generated.

6. A model training method, characterized in that: The method comprises: Construct an analysis model of factors affecting economic difficulties; Acquire multiple sets of training sample data and actual economic hardship attributes corresponding to each set of training sample data, wherein each set of training sample data includes values ​​of various economic hardship influencing factors; Based on each set of training sample data, the economic hardship influencing factor analysis model to be trained is trained to obtain the importance score of each economic hardship influencing factor and the predicted economic hardship attribute of each set of training sample data; Performing loss calculation on the actual economic hardship attribute corresponding to each group of training sample data based on the predicted economic hardship attribute of each group of training sample data, to obtain a loss calculation result of the economic hardship influencing factor analysis model; Based on the loss calculation result of the economic hardship influencing factor analysis model, the model parameters of the economic hardship influencing factor analysis model are updated.

7. The method according to claim 6, characterized in that After updating the model parameters of the economic hardship influencing factor analysis model based on the loss calculation result of the economic hardship influencing factor analysis model, the method further includes: Determining whether the predicted economic hardship attribute of each set of training sample data converges to the actual economic hardship attribute corresponding to each set of training sample data; If the predicted economic hardship attribute of each set of training sample data has converged to the actual economic hardship attribute corresponding to each set of training sample data, it is determined that the training of the economic hardship influencing factor analysis model is completed.

8. A device for analyzing factors affecting regional economic difficulties, characterized in that: include: Establish a module for establishing a multidimensional economic hardship influencing factor index system, and quantify each economic hardship influencing factor in the multidimensional economic hardship influencing factor index system based on elevation data, traffic data, and remote sensing data. The multidimensional economic hardship influencing factor index system includes a traffic level index, an economic level index, an ecological status index, a population status index, a welfare level index, and a geographical location index, and each index includes multiple economic hardship influencing factors; A calculation module, used to calculate the contribution of each economic hardship influencing factor in the multi-dimensional economic hardship influencing factor index system; A construction module is used to construct a relationship diagram between various economic hardship influencing factors and the probability of economic hardship; The analysis module is used to analyze each economic difficulty influencing factor according to a relationship diagram between each economic difficulty influencing factor and the probability of economic difficulty and a contribution degree of each economic difficulty influencing factor.

9. A model training device, characterized in that: include: A construction module for constructing an analysis model of factors affecting economic difficulties; An acquisition module, used to acquire multiple sets of training sample data and actual economic hardship attributes corresponding to each set of training sample data, wherein each set of training sample data includes a value of each economic hardship influencing factor; An obtaining module is used to train the economic hardship influencing factor analysis model to be trained based on each set of training sample data, and obtain the importance score of each economic hardship influencing factor and the predicted economic hardship attribute of each set of training sample data; A loss calculation module, configured to perform loss calculation on the actual economic hardship attribute corresponding to each group of training sample data based on the predicted economic hardship attribute of each group of training sample data, and obtain a loss calculation result of the economic hardship influencing factor analysis model; An updating module is used to update the model parameters of the economic hardship influencing factor analysis model based on the loss calculation result of the economic hardship influencing factor analysis model.

10. An electronic device, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 7.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images