Prediction method and device, equipment, storage medium and program product

Abstract

The invention relates to a prediction method and device, equipment, a storage medium and a program product, and the method comprises the steps: obtaining the industrial data of a to-be-transformed industry and a preset mapping relation, inputting the industrial data of the to-be-transformed industry and the preset mapping relation into a trend prediction model, and carrying out the prediction of an industrial development trend, thereby obtaining a prediction result. According to the method, the preset mapping relation can reflect the corresponding relation between different types of industrial data and the industrial development trend, so that the industrial data of the to-be-transformed industry is classified, and then the industrial development trend of the to-be-transformed industry can be accurately predicted through the classification result and the preset mapping relation. Meanwhile, compared with the problem that prediction is inaccurate due to the fact that prediction depends on artificial experience in the prior art, the industrial development trend is predicted through the trend prediction model, the prediction accuracy can be improved to a great extent, and meanwhile the prediction efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a prediction method, device, equipment, storage medium and program product. Background Art

[0002] With the development of network information, big data analysis has the advantages of high efficiency, accuracy and real-time, and has been applied to many fields, especially building models through big data to achieve information prediction.

[0003] At present, the pace of integration between advanced manufacturing and modern service industries is accelerating, and the industrial operation management system of an enterprise usually realizes the prediction of the industrial operation situation based on the prediction model.

[0004] However, the above-mentioned forecasting method for industrial operation situation has the problem of inaccurate forecasting. Summary of the invention

[0005] Based on this, it is necessary to provide a prediction method, device, equipment, storage medium and program product that can improve prediction accuracy in response to the above technical problems.

[0006] In a first aspect, the present application provides a prediction method, the method comprising:

[0007] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0008] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0009] The prediction method provided in the embodiment of the present application obtains the industrial data and preset mapping relationship of the industry to be transformed, and then inputs the industrial data and preset mapping relationship of the industry to be transformed into a trend prediction model to predict the industrial development trend and obtain a prediction result. Among them, the preset mapping relationship is used to characterize the correspondence between industrial data of different categories and industrial development trends. In the above method, since the preset mapping relationship can reflect the correspondence between industrial data of different categories and industrial development trends, the industrial data of the industry to be transformed is classified, and then the industrial development trend of the industry to be transformed can be accurately predicted through the classification results and the preset mapping relationship. At the same time, compared with the existing problem of inaccurate prediction caused by relying on manual experience for prediction, the above method predicts the industrial development trend through the trend prediction model, which can greatly improve the prediction accuracy and improve the prediction efficiency.

[0010] In one embodiment, the trend prediction model includes a weight allocation sub-model and a prediction sub-model. The industry data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industry development trend, and the prediction results are obtained, including:

[0011] Input the industrial data of the industries to be transformed into the weight allocation sub-model for weight allocation, and obtain the weights corresponding to different categories of industrial data;

[0012] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the prediction sub-model for prediction to obtain the prediction results.

[0013] The method described in the embodiments of the present application can accurately predict the development trend of the industry by assigning weights to different categories of industrial data, as the weights can reflect the degree of influence of different categories of industrial data on the development trend of the industry. Therefore, by assigning weights to different categories of industrial data, and then determining the industrial development trend of the industry to be transformed based on the size of the weights and the preset mapping relationship, the development trend of the industry can be accurately predicted.

[0014] In one embodiment, the weight allocation sub-model includes a statistical module and an allocation module, and the industrial data of the industry to be transformed is input into the weight allocation sub-model for weight allocation to obtain weights corresponding to different categories of industrial data, including:

[0015] Input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of different categories of industrial data;

[0016] The data volume of different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0017] In one embodiment, the prediction sub-model includes a calculation module and a screening module, and the weights and preset mapping relationships corresponding to different categories of industrial data are input into the prediction sub-model for prediction to obtain prediction results, including:

[0018] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the calculation module to obtain the total weights corresponding to the development trends of each industry in the preset mapping relationship;

[0019] The total weights corresponding to the development trends of various industries are input into the screening module to obtain the forecast results of the development trends of the industries corresponding to the total weights with the largest weight values.

[0020] In one embodiment, the trend prediction model further includes a classification sub-model, and the method further includes:

[0021] Input the industrial data of the industries to be transformed into the classification sub-model for classification to obtain industrial data of different categories;

[0022] The industrial data of the industries to be transformed are input into the weight allocation sub-model for weight allocation, and the weights corresponding to different categories of industrial data are obtained, including:

[0023] Different categories of industrial data are input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0024] The method described in the embodiments of the present application can clarify the priority and focus of various industries in the transformation process through the classification and weight allocation of industrial data, avoid waste of resources and ineffective investment, and thus improve the prediction efficiency of industrial transformation.

[0025] In one embodiment, the trend prediction model further includes a feature extraction sub-model, and the method further includes:

[0026] Input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain the feature data of the industrial data;

[0027] The industrial data of the industries to be transformed are input into the classification sub-model for classification to obtain industrial data of different categories, including:

[0028] The characteristic data of the industrial data is input into the classification sub-model for classification to obtain industrial data of different categories.

[0029] The method described in the embodiment of the present application first extracts features of industrial data through a feature extraction sub-model, which can improve classification accuracy and efficiency when subsequently classifying based on the extracted data features, thereby improving prediction accuracy and prediction efficiency.

[0030] In a second aspect, the present application further provides a prediction device, the device comprising:

[0031] An acquisition module is used to acquire the industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between different categories of industrial data and industrial development trends;

[0032] The prediction module is used to input the industrial data and preset mapping relationship of the industry to be transformed into the trend prediction model to predict the industrial development trend and obtain the prediction result.

[0033] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0034] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0035] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0038] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0039] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0041] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0042] The above-mentioned prediction method, device, equipment, storage medium and program product, the method obtains the industrial data and preset mapping relationship of the industry to be transformed, and then inputs the industrial data and preset mapping relationship of the industry to be transformed into the trend prediction model to predict the industrial development trend and obtain the prediction result. Among them, the preset mapping relationship is used to characterize the correspondence between different categories of industrial data and industrial development trends. In the above method, since the preset mapping relationship can reflect the correspondence between different categories of industrial data and industrial development trends, the industrial data of the industry to be transformed is classified, and then the industrial development trend of the industry to be transformed can be accurately predicted through the classification results and the preset mapping relationship. At the same time, compared with the existing problem of inaccurate prediction caused by relying on manual experience for prediction, the above method predicts the industrial development trend through the trend prediction model, which can greatly improve the prediction accuracy and improve the prediction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0044] Figure 2 A schematic diagram of a prediction method in one embodiment;

[0045] Figure 3 is a flow chart of a prediction method in another embodiment;

[0046] Figure 4 This is the target weight distribution diagram corresponding to each category of industrial data;

[0047] Figure 5 Heatmap of confusion matrix for sub-models with initial weight assignments;

[0048] Figure 6 is a flow chart of a prediction method in another embodiment;

[0049] Figure 7 It is a statistical chart of the data volume of different categories of industrial data;

[0050] Figure 8 is a flow chart of a prediction method in another embodiment;

[0051] Fig. 9 is a flow chart of a prediction method in another embodiment;

[0052] Fig.10 A schematic diagram of a preset mapping relationship in an embodiment;

[0053] Fig.11 is a flow chart of a prediction method in another embodiment;

[0054] Fig.12 is a flow chart of a prediction method in another embodiment;

[0055] Fig.13 FIG. 4 is a structural block diagram of a prediction device in an embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] With the development of network information, big data analysis has the advantages of high efficiency, accuracy and real-time, and has been applied to many fields, especially building models through big data to achieve information prediction. At present, the integration of advanced manufacturing and modern service industries is accelerating, and the industrial operation management system of an enterprise usually predicts the industrial operation situation based on a prediction model. However, the above-mentioned prediction method of the industrial operation situation has the problem of inaccurate prediction. The present application provides a prediction method, which aims to solve the above-mentioned technical problems. The following embodiments will specifically illustrate the prediction method described in the present application.

[0058] The prediction method provided in the embodiment of the present application can be applied to Figure 1 In the computer device shown in the figure, the computer device can be a terminal or a server, and its internal structure diagram can be as shown in FIG. Figure 1 As shown, the computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a prediction method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0059] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0060] In one embodiment, Figure 2 As shown, a prediction method is provided, which can be applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0061] S201, obtaining the industry data and preset mapping relationship of the industry to be transformed.

[0062] Among them, the industrial data of the industries to be transformed include at least one of internal data, external data, environmental data and policy data. Internal data include various statistical data generated by the industries to be transformed in various fields such as industry, commerce, and agriculture; for example, industrial value-added data, sales revenue and profit data, industrial structure data, industrial chain data, market and consumption capacity data, etc. External data include business data of the industries to be transformed; for example, basic information of enterprises in the industries to be transformed, enterprise tax information, enterprise energy consumption information, enterprise registration and cancellation data, etc. Environmental data is data from data sources such as public financing event disclosure, enterprise industrial and commercial change information sorting, and institutional information provision. Policy data is the layout data of the industries to be transformed in local and regional areas under the leadership of local policies; for example, data of advantageous industries, data of new industries, and data of key industries. The preset mapping relationship is used to characterize the corresponding relationship between different categories of industrial data and industrial development trends. Specifically, each industrial development trend can correspond to multiple categories of industrial data. Industrial development trends include at least one of technology-driven development trends, demand-driven development trends, policy-guided development trends, and social transformation development trends.

[0063] In the embodiment of the present application, a preset mapping relationship can be determined in advance based on different categories of industrial data and industrial development trends. Specifically, different industrial development trends can be determined first, and then the influencing factors corresponding to the industrial development trends of each industry can be determined, and then the industrial data of the industry to be transformed can be classified based on the influencing factors corresponding to the industrial development trends of each industry, and different categories of industrial data can be obtained. Finally, the preset mapping relationship is determined according to the industrial data and industrial development trends of different categories. For example, the industrial development trends include trends A, B and C, the industrial data of the category corresponding to trend A includes a1 and a2, the industrial data of the category corresponding to trend B includes b1, b2 and b3, and the industrial data of the category corresponding to trend C includes c1, then a preset mapping relationship can be constructed according to a1 and a2 corresponding to trend A, b1, b2 and b3 corresponding to trend B, and c1 corresponding to trend C, and the preset mapping relationship is stored under the preset path. When it is necessary to predict the industrial development trend of the industry to be transformed, the computer device can obtain the industrial data of the industry to be transformed through the data management system of the industry to be transformed, and obtain the preset mapping relationship through the preset path.

[0064] S202, inputting the industry data and preset mapping relationship of the industry to be transformed into the trend prediction model to predict the industry development trend and obtain the prediction result.

[0065] Among them, the trend prediction model is used to predict the industrial development trend of the industry to be transformed. The trend prediction model is obtained by training the initial trend prediction model with industrial sample data of multiple historical transformation units. The initial trend prediction model can adopt the gradient boosting tree (GBDT) model. The prediction results include industrial development trends.

[0066] In the embodiment of the present application, the computer device can pre-train the initial trend prediction model based on the industrial sample data of multiple historical transformation units to obtain a trend prediction model. Specifically, the computer device can obtain the industrial sample data of multiple historical transformation units by means of network crawling or other suitable methods, and then annotate the industrial sample data of multiple historical transformation units by means of preset mapping relationships, annotate the target industry development trends corresponding to all industrial sample data, so as to obtain multiple sample pairs consisting of each industrial sample data and the corresponding target industry development trends, and then input each industrial sample data into the initial trend prediction model for prediction, obtain the predicted industry development trend, and then adjust the hyperparameters in the initial trend prediction model according to the predicted industry development trend and the target industry development trend in the corresponding sample pair, obtain the adjusted initial trend prediction model, and determine the adjusted initial trend prediction model as the trend prediction model. After the computer device obtains the industrial data and preset mapping relationship of the industry to be transformed based on the above steps, the industrial data and preset mapping relationship of the industry to be transformed can be input into the trend prediction model to predict the industrial development trend, predict the industrial development trend corresponding to the industrial data of the industry to be transformed, that is, obtain the prediction result, and then the industry with transformation can make corresponding improvements according to the industrial development trend in the prediction result to achieve better transformation.

[0067] Optionally, after obtaining the industrial data of the industry to be transformed, the computer equipment can pre-process the industrial data of the industry to be transformed, for example, perform data integration, data standardization and data dimensionality reduction to obtain the pre-processed industrial data of the industry to be transformed, and then input the pre-processed industrial data of the industry to be transformed and the preset mapping relationship into the trend prediction model to predict the industrial development trend and obtain the prediction result.

[0068] The prediction method provided in the embodiment of the present application obtains the industrial data and preset mapping relationship of the industry to be transformed, and then inputs the industrial data and preset mapping relationship of the industry to be transformed into a trend prediction model to predict the industrial development trend and obtain a prediction result. Among them, the preset mapping relationship is used to characterize the correspondence between industrial data of different categories and industrial development trends. In the above method, since the preset mapping relationship can reflect the correspondence between industrial data of different categories and industrial development trends, the industrial data of the industry to be transformed is classified, and then the industrial development trend of the industry to be transformed can be accurately predicted through the classification results and the preset mapping relationship. At the same time, compared with the existing problem of inaccurate prediction caused by relying on manual experience for prediction, the above method predicts the industrial development trend through the trend prediction model, which can greatly improve the prediction accuracy and improve the prediction efficiency.

[0069] In one embodiment, the trend prediction model includes a weight allocation sub-model and a prediction sub-model. On this basis, a specific implementation method for predicting the industrial development trend of the industry data of the industry to be transformed and the preset mapping relationship is also provided, such as Figure 3 As shown, the above step S202 of "inputting the industry data and the preset mapping relationship of the industry to be transformed into the trend prediction model to predict the industry development trend and obtain the prediction result" includes:

[0070] S301, inputting the industrial data of the industries to be transformed into the weight allocation sub-model for weight allocation, and obtaining the weights corresponding to different categories of industrial data.

[0071] The trend prediction model includes a weight allocation sub-model and a prediction sub-model. The weight allocation sub-model is used to allocate weights to different categories of industrial data in the industrial data of the industry to be transformed. The weight allocation sub-model is obtained by training the initial weight allocation sub-model with industrial sample data of multiple historical transformation units. The initial weight allocation sub-model can adopt a gradient boosting tree (GBDT) model.

[0072] In an embodiment of the present application, the computer device can pre-train the initial weight allocation sub-model based on the industrial sample data of multiple historical transformation units to obtain the weight allocation sub-model. Specifically, the computer device can first classify the industrial sample data of each historical transformation unit to obtain different categories of industrial data, and then can perform target weight allocation according to the data volume of different categories of industrial data, or perform target weight allocation according to the degree of influence of different categories of industrial data on industrial development trends, and obtain multiple sample pairs consisting of different categories of industrial data and corresponding target weights, and then input the different categories of industrial data into the initial weight allocation sub-model for weight allocation, and obtain the prediction weights corresponding to each category of industrial data, and then adjust the hyperparameters in the initial weight allocation sub-model according to the prediction weight and the target weight in the corresponding sample pair, and obtain the adjusted initial weight allocation sub-model, and determine the adjusted initial weight allocation sub-model as the weight allocation sub-model.

[0073] The initial weight allocation sub-model is trained based on the industrial sample data of multiple historical transformation units. The process of obtaining the weight allocation sub-model can be as follows:

[0074] (1) Preprocess the industrial sample data of multiple historical transformation units to obtain preprocessed industrial sample data.

[0075] First, the data sets of industrial sample data of multiple historical transformation units are integrated to obtain integrated data, so as to realize the aggregation, processing, governance and extraction of industry-related internal data, external data, environmental data, policy data, etc. in terms of work technology, and realize the perception, interconnection, integration and efficient application of diverse and comprehensive data in business. Then, the integrated data is cleaned according to the unified data format and structure, the data is compared with the unified code set, the data is converted into numerical type, the noise data and redundant data are removed, and the data with the same meaning but different expressions are standardized to obtain the standardized data.

[0076] (2) Annotate the preprocessed industrial sample data to obtain multiple sample pairs consisting of different categories of industrial data and corresponding target weights, and construct a sample training set.

[0077] (3) Set the parameters of the gradient boosting tree model according to the model parameters in the table below and use it as the initial weight allocation submodel.

[0078]

[0079]

[0080] (3) Input different categories of industrial data into the initial weight allocation sub-model to obtain the target weights corresponding to each category of industrial data. For details, see Figure 4 The target weight distribution diagram corresponding to each category of industry data is shown, where each category of industry data includes category data on demand diversification, category data on industry core technology, category data on the impact of social structure on industry, category data on promoting development of specific industries, category data on changes in the cost and quality of substitutes due to inventions and innovations, category data on policy guidance, category data on the impact of social values ​​on industry, and category data on industry added value.

[0081] (4) Based on the verification results, the parameters of the initial weight allocation sub-model are adjusted to obtain the weight allocation sub-model.

[0082] The computer device can determine the predicted industry development trend based on the weights corresponding to each category of industry data and the preset mapping relationship, and obtain the following by comparing the predicted industry development trend with the target industry development trend: Figure 5 The confusion matrix heat map is shown in the figure, and the initial weight allocation sub-model is evaluated based on the confusion matrix heat map to obtain the evaluation results. As shown in the following table, the evaluation results include accuracy, recall, precision and F1 index.

[0083]

[0084] The above table shows the prediction evaluation indicators of the cross-validation set, training set, and test set, and uses quantitative indicators to measure the prediction effect of GBDT. Among them, the evaluation indicators of the cross-validation set can continuously adjust the hyperparameters to obtain a reliable and stable model. Accuracy: The proportion of correctly predicted samples to the total samples. The higher the accuracy, the better. Recall: The proportion of predicted positive samples among the results that are actually positive samples. The higher the recall, the better. Precision: The proportion of actually positive samples among the results predicted to be positive samples. The higher the precision, the better. F1: The harmonic mean of precision and recall. Precision and recall affect each other. Although both are high is an ideal situation, in reality, it is often the case that the precision is high and the recall is low, or the recall is low but the precision is high. If you need to take both into account, you can use the F1 indicator.

[0085] If the evaluation result does not meet the expected requirements, the model parameters in the initial weight allocation sub-model are adjusted to obtain new prediction weights until the evaluation result determined based on the new prediction weights meets the expected requirements, and the weight allocation sub-model is obtained. Specifically, when adjusting the model parameters, the data segmentation, the minimum number of samples of leaf nodes, the maximum depth of the tree, and the threshold of node partition impurity in the model parameters can be adjusted.

[0086] After obtaining the industrial data of the industry to be transformed, the computer device can input the industrial data of the industry to be transformed into the weight allocation sub-model for weight allocation. The weight allocation sub-model can allocate weights according to the frequency of occurrence of different categories of industrial data to obtain weights corresponding to different categories of industrial data. Optionally, the weight allocation sub-model can also allocate weights according to the degree of influence of different categories of industrial data to obtain weights corresponding to different categories of industrial data.

[0087] Optional, 3Optional, such as Figure 6 As shown, the above step S301 of "inputting the industrial data of the industry to be transformed into the weight allocation sub-model for weight allocation to obtain weights corresponding to different categories of industrial data" includes:

[0088] S3011, input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of industrial data of different categories.

[0089] The weight distribution sub-model includes a statistical module and a distribution module. The statistical module is used to count the data volume of different categories of industrial data.

[0090] In the embodiment of the present application, after the computer device obtains the industrial data of the industry to be transformed, the industrial data of the industry to be transformed can be input into the statistical module. The statistical module can count the data volume of different categories of industrial data to obtain the data volume of different categories of industrial data. For details, see Figure 7 The data volume statistics of different categories of industrial data are shown.

[0091] S3012, input the data volume of different categories of industrial data into the allocation module for weight allocation, and obtain the weights corresponding to the different categories of industrial data.

[0092] Among them, the allocation module is used to perform weight allocation based on the amount of data.

[0093] In the embodiment of the present application, after the computer device obtains the data volume of different categories of industrial data, the data volume of different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to the different categories of industrial data.

[0094] S302, inputting the weights and preset mapping relationships corresponding to different categories of industrial data into the prediction sub-model for prediction to obtain prediction results.

[0095] Among them, the prediction sub-model is used to predict the industrial development trends of industries to be transformed.

[0096] In the embodiment of the present application, the computer device can be pre-trained based on the industrial sample data of multiple historical transformation units, using the method of training the weight allocation sub-model and training the prediction model in the above embodiment, to train the initial prediction sub-model to obtain the prediction sub-model. Optionally, the computer device can also directly obtain an existing neural network model that can predict the industrial development trend based on weights and preset mapping relationships as a prediction sub-model. After obtaining the weights and preset mapping relationships corresponding to different categories of industrial data, the computer device can input the weights and preset mapping relationships corresponding to different categories of industrial data into the prediction sub-model for prediction to obtain a prediction result. Specifically, the category of industrial data with the largest weight value can be determined from the weights corresponding to different categories of industrial data, and then the industrial development trend corresponding to the category of industrial data with the largest weight value can be found in the preset mapping relationship as the prediction result. For example, the weight value corresponding to b1 is the largest, so the category of industrial data with the largest weight value is b1, and then the industrial development trend corresponding to b1 is found in the preset mapping relationship as trend B, and trend B is used as the prediction result.

[0097] Optional, such as Figure 8 As shown, the above step S302 of "inputting the weights and preset mapping relationships corresponding to different categories of industrial data into the prediction sub-model for prediction to obtain prediction results" includes:

[0098] S3021, input the weights and preset mapping relationships corresponding to different categories of industrial data into the calculation module to obtain the total weights corresponding to the development trends of various industries in the preset mapping relationships.

[0099] The prediction sub-model includes a calculation module and a screening module. The calculation module is used to calculate the total weight corresponding to the development trend of each industry.

[0100] In the embodiment of the present application, after the computer device obtains the weights and preset mapping relationships corresponding to different categories of industrial data, the weights and preset mapping relationships corresponding to different categories of industrial data can be input into the calculation module. The calculation module can first determine the categories of industrial data corresponding to the development trends of each industry in the preset mapping relationship, and then respectively calculate the sum of the weights of the categories of industrial data corresponding to the development trends of each industry, and obtain the total weights corresponding to the development trends of each industry in the preset mapping relationship. For example, it is determined from the preset relationship that the categories of industrial data corresponding to trend A include a1 and a2, the categories of industrial data corresponding to trend B include b1, b2 and b3, and the categories of industrial data corresponding to trend C include c1, then the total weight corresponding to trend A is the sum of the weights of a1 and a2, the total weight corresponding to trend B is the sum of the weights of b1, b2 and b3, and the total weight corresponding to trend C is the weight of c1.

[0101] S3022, input the total weight corresponding to each industry development trend into the screening module to obtain the forecast result of the industry development trend corresponding to the total weight with the largest weight value.

[0102] Among them, the screening module is used to screen out the total weight with the largest value from multiple total weights.

[0103] In the embodiment of the present application, after obtaining the total weight corresponding to the development trend of each industry, the computer device can input the total weight corresponding to the development trend of each industry into the screening module, and the screening module screens out the total weight with the largest value from multiple total weights, and then obtains the industry development trend corresponding to the maximum total weight value, and the computer device can output it as a prediction result. For example, the screening module screens out the sum of the weights of a1 and a2, the sum of the weights of b1, b2 and b3, and the total weight c1 corresponding to trend C, and the prediction result is trend A.

[0104] The method described in the embodiments of the present application can accurately predict the development trend of the industry by assigning weights to different categories of industrial data, as the weights can reflect the degree of influence of different categories of industrial data on the development trend of the industry. Therefore, by assigning weights to different categories of industrial data, and then determining the industrial development trend of the industry to be transformed based on the size of the weights and the preset mapping relationship, the development trend of the industry can be accurately predicted.

[0105] In one embodiment, the trend prediction model further includes a classification sub-model and provides a method for classifying the industrial data of the industry to be transformed. Before step S301, Fig. 9 As shown, the method includes:

[0106] S303, inputting the industrial data of the industries to be transformed into the classification sub-model for classification to obtain industrial data of different categories.

[0107] Among them, different categories of industrial data include data on changes in the cost and quality of substitutes due to invention and innovation, data on core industrial technologies, data on demand diversification, data on industrial added value, data on policy guidance, data on the promotion of development of specific industries, data on the impact of social structure on industries, and data on the impact of social values ​​on industries. The classification sub-model is used to classify industrial data for industries to be transformed.

[0108] In an embodiment of the present application, the computer device may pre-train the initial classification sub-model based on the industrial sample data of multiple historical transformation units, using the method of training the weight allocation sub-model and training the prediction model in the above embodiment to obtain a classification sub-model. Optionally, the computer device may also directly obtain an existing neural network model that can accurately classify data as a classification sub-model. After obtaining the industrial data of the industry to be transformed, the computer device may input the industrial data of the industry to be transformed into the classification sub-model for classification to obtain industrial data of different categories. Specifically, the correspondence between different categories of industrial data and industrial development trends can be seen in the following. Fig.10 A schematic diagram of the preset mapping relationship is shown.

[0109] Optionally, after obtaining the industrial data of the industry to be transformed, the computer equipment can pre-process the industrial data of the industry to be transformed, for example, perform data integration, data standardization and data dimensionality reduction to obtain the pre-processed industrial data of the industry to be transformed, and then input the pre-processed industrial data of the industry to be transformed into the classification sub-model for classification to obtain industrial data of different categories.

[0110] Correspondingly, it is predicted that when executing step S301 "inputting the industrial data of the industry to be transformed into the weight allocation sub-model for weight allocation, and obtaining weights corresponding to different categories of industrial data", the specific execution steps are: inputting different categories of industrial data into the weight allocation sub-model for weight allocation, and obtaining weights corresponding to different categories of industrial data.

[0111] In an embodiment of the present application, after obtaining different categories of industrial data based on the above steps, the computer device can input the different categories of industrial data into the weight allocation sub-model for weight allocation to obtain weights corresponding to the different categories of industrial data.

[0112] The method described in the embodiments of the present application can clarify the priority and focus of various industries in the transformation process through the classification and weight allocation of industrial data, avoid waste of resources and ineffective investment, and thus improve the prediction efficiency of industrial transformation.

[0113] In one embodiment, the trend prediction model further includes a feature extraction sub-model. Before step S303, a method for extracting features from the industrial data of the industry to be transformed is also provided, such as Fig.11 As shown, the method includes:

[0114] S304, inputting the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain feature data of the industrial data.

[0115] Among them, the feature extraction sub-model is used to extract features from the industrial data of the industries to be transformed.

[0116] In an embodiment of the present application, the computer device can pre-train the initial feature extraction sub-model based on the industrial sample data of multiple historical transformation units, using the method of training the weight allocation sub-model and training the prediction model in the above embodiment to obtain the feature extraction sub-model. Optionally, the computer device can also directly obtain an existing neural network model that can accurately extract features from data as a feature extraction sub-model. After obtaining the industrial data of the industry to be transformed, the computer device can input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain feature data of the industrial data.

[0117] Correspondingly, it is predicted that when executing step S303 "inputting the industrial data of the industry to be transformed into the classification sub-model for classification to obtain industrial data of different categories", the specific execution steps are: inputting the characteristic data of the industrial data into the classification sub-model for classification to obtain industrial data of different categories.

[0118] In an embodiment of the present application, after the computer device obtains the characteristic data of the industrial data based on the above steps, it can input the characteristic data of the industrial data into a classification sub-model for classification to obtain industrial data of different categories.

[0119] The method described in the embodiment of the present application first extracts features of industrial data through a feature extraction sub-model, which can improve classification accuracy and efficiency when subsequently classifying based on the extracted data features, thereby improving prediction accuracy and prediction efficiency.

[0120] Based on all the above embodiments, a prediction method is also provided. Fig.12 As shown, the method includes:

[0121] S401, obtaining industry data and preset mapping relationships of industries to be transformed, wherein the preset mapping relationships are used to represent the corresponding relationships between different types of industry data and industry development trends.

[0122] S402, inputting the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain feature data of the industrial data.

[0123] S403, inputting the characteristic data of the industrial data into the classification sub-model for classification to obtain industrial data of different categories.

[0124] S404, inputting different categories of industrial data into the statistical module to obtain the data volume of different categories of industrial data.

[0125] S405, inputting the data volume of different categories of industrial data into the allocation module for weight allocation, and obtaining the weights corresponding to the different categories of industrial data.

[0126] S406, inputting the weights corresponding to different categories of industrial data and the preset mapping relationship into the calculation module to obtain the total weight corresponding to the development trend of each industry in the preset mapping relationship.

[0127] S407, inputting the total weight corresponding to each industry development trend into the screening module to obtain a prediction result of the industry development trend corresponding to the total weight with the largest weight value.

[0128] The method described in the embodiments of the present application can flexibly process various types of data, including continuous values ​​and discrete values, because the prediction model is trained using a gradient boosting tree model. Features that have a greater impact on the prediction results can be selected through feature importance evaluation, thereby improving the explanatory power and generalization ability of the model. Therefore, the prediction model used to predict industrial development trends has a high prediction accuracy.

[0129] The methods described in the above steps are all described in the above embodiments. Please refer to the above description for details and will not be repeated here.

[0130] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0131] Based on the same inventive concept, the embodiment of the present application also provides a prediction device for implementing the prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more prediction device embodiments provided below can refer to the limitations of the prediction method above, and will not be repeated here.

[0132] In one embodiment, Fig.13 As shown, a prediction device is provided, comprising:

[0133] The acquisition module 10 is used to acquire the industrial data of the industry to be transformed and the preset mapping relationship; the preset mapping relationship is used to characterize the correspondence between different categories of industrial data and industrial development trends.

[0134] The prediction module 11 is used to input the industrial data of the industry to be transformed and the preset mapping relationship into the trend prediction model to predict the industrial development trend and obtain the prediction result.

[0135] In one embodiment, the prediction module includes:

[0136] The allocation unit is used to input the industrial data of the industry to be transformed into the weight allocation sub-model for weight allocation, so as to obtain the weights corresponding to different categories of industrial data.

[0137] The prediction unit is used to input the weights and preset mapping relationships corresponding to different categories of industrial data into the prediction sub-model for prediction to obtain the prediction results.

[0138] In one embodiment, the allocation unit comprises:

[0139] The statistical sub-unit is used to input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of different categories of industrial data.

[0140] The allocation subunit is used to input the data volume of different categories of industrial data into the allocation module for weight allocation, so as to obtain the weights corresponding to the different categories of industrial data.

[0141] In one embodiment, the prediction unit includes:

[0142] The calculation subunit is used to input the weights and preset mapping relationships corresponding to different categories of industrial data into the calculation module to obtain the total weights corresponding to the development trends of various industries in the preset mapping relationships.

[0143] The screening subunit is used to input the total weights corresponding to the development trends of various industries into the screening module to obtain the forecast results of the development trends of the industries corresponding to the total weights with the largest weight values.

[0144] In one embodiment, the prediction module further includes:

[0145] The classification unit is used to input the industrial data of the industry to be transformed into the classification sub-model for classification to obtain industrial data of different categories.

[0146] Correspondingly, the above allocation unit is specifically used to input different categories of industrial data into the weight allocation sub-model for weight allocation, so as to obtain weights corresponding to different categories of industrial data.

[0147] In one embodiment, the prediction module further includes:

[0148] The extraction unit is used to input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain feature data of the industrial data.

[0149] Correspondingly, the above-mentioned classification unit is specifically used to input the characteristic data of the industrial data into the classification sub-model for classification to obtain industrial data of different categories.

[0150] Each module in the above prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0152] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0153] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0154] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0155] Input the industrial data of the industries to be transformed into the weight allocation sub-model for weight allocation, and obtain the weights corresponding to different categories of industrial data;

[0156] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the prediction sub-model for prediction to obtain the prediction results.

[0157] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0158] Input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of different categories of industrial data;

[0159] The data volume of different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the calculation module to obtain the total weights corresponding to the development trends of each industry in the preset mapping relationship;

[0162] The total weights corresponding to the development trends of various industries are input into the screening module to obtain the forecast results of the development trends of the industries corresponding to the total weights with the largest weight values.

[0163] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0164] Input the industrial data of the industries to be transformed into the classification sub-model for classification to obtain industrial data of different categories;

[0165] The industrial data of the industries to be transformed are input into the weight allocation sub-model for weight allocation, and the weights corresponding to different categories of industrial data are obtained, including:

[0166] Different categories of industrial data are input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0167] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0168] Input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain the feature data of the industrial data;

[0169] The industrial data of the industries to be transformed are input into the classification sub-model for classification to obtain industrial data of different categories, including:

[0170] The characteristic data of the industrial data is input into the classification sub-model for classification to obtain industrial data of different categories.

[0171] The above embodiment provides a computer device, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0172] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0173] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0174] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] Input the industrial data of the industries to be transformed into the weight allocation sub-model for weight allocation, and obtain the weights corresponding to different categories of industrial data;

[0177] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the prediction sub-model for prediction to obtain the prediction results.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0179] Input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of different categories of industrial data;

[0180] The data volume of different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the calculation module to obtain the total weights corresponding to the development trends of each industry in the preset mapping relationship;

[0183] The total weights corresponding to the development trends of various industries are input into the screening module to obtain the forecast results of the development trends of the industries corresponding to the total weights with the largest weight values.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0185] Input the industrial data of the industries to be transformed into the classification sub-model for classification to obtain industrial data of different categories;

[0186] The industrial data of the industries to be transformed are input into the weight allocation sub-model for weight allocation, and the weights corresponding to different categories of industrial data are obtained, including:

[0187] Different categories of industrial data are input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain the feature data of the industrial data;

[0190] The industrial data of the industries to be transformed are input into the classification sub-model for classification to obtain industrial data of different categories, including:

[0191] The characteristic data of the industrial data is input into the classification sub-model for classification to obtain industrial data of different categories.

[0192] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0193] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0194] Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends;

[0195] The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction results.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0197] Input the industrial data of the industries to be transformed into the weight allocation sub-model for weight allocation, and obtain the weights corresponding to different categories of industrial data;

[0198] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the prediction sub-model for prediction to obtain the prediction results.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0200] Input the industrial data of the industries to be transformed into the statistical module to obtain the data volume of different categories of industrial data;

[0201] The data volume of different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] The weights and preset mapping relationships corresponding to different categories of industrial data are input into the calculation module to obtain the total weights corresponding to the development trends of each industry in the preset mapping relationship;

[0204] The total weights corresponding to the development trends of various industries are input into the screening module to obtain the forecast results of the development trends of the industries corresponding to the total weights with the largest weight values.

[0205] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0206] Input the industrial data of the industries to be transformed into the classification sub-model for classification to obtain industrial data of different categories;

[0207] The industrial data of the industries to be transformed are input into the weight allocation sub-model for weight allocation, and the weights corresponding to different categories of industrial data are obtained, including:

[0208] Different categories of industrial data are input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to different categories of industrial data.

[0209] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0210] Input the industrial data of the industry to be transformed into the feature extraction sub-model for feature extraction to obtain the feature data of the industrial data;

[0211] The industrial data of the industries to be transformed are input into the classification sub-model for classification to obtain industrial data of different categories, including:

[0212] The characteristic data of the industrial data is input into the classification sub-model for classification to obtain industrial data of different categories.

[0213] The above embodiment provides a computer program product, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0214] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0215] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0216] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A prediction method, characterized in that: The method comprises: Obtaining industrial data and preset mapping relationships of the industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends; The industrial data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industrial development trend and obtain the prediction result.

2. The method according to claim 1, characterized in that The trend prediction model includes a weight allocation sub-model and a prediction sub-model. The industry data of the industry to be transformed and the preset mapping relationship are input into the trend prediction model to predict the industry development trend, and the prediction results are obtained, including: Inputting the industrial data of the to-be-transformed industry into the weight allocation sub-model for weight allocation, and obtaining the weights corresponding to the industrial data of different categories; The weights corresponding to the different categories of industrial data and the preset mapping relationship are input into the prediction sub-model for prediction to obtain the prediction result.

3. The method according to claim 2, characterized in that The weight allocation sub-model includes a statistical module and an allocation module. The industrial data of the industry to be transformed is input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to the industrial data of different categories, including: Inputting the industrial data of the to-be-transformed industry into the statistical module to obtain the data volume of industrial data of different categories; The data volume of the different categories of industrial data is input into the allocation module for weight allocation to obtain the weights corresponding to the different categories of industrial data.

4. The method according to claim 2, characterized in that: The prediction sub-model includes a calculation module and a screening module. The weights corresponding to the different categories of industrial data and the preset mapping relationship are input into the prediction sub-model for prediction to obtain the prediction result, including: Inputting the weights corresponding to the different categories of industrial data and the preset mapping relationship into the calculation module to obtain the total weight corresponding to the development trend of each industry in the preset mapping relationship; The total weights corresponding to the development trends of the industries are input into the screening module to obtain a prediction result of the development trend of the industry corresponding to the total weight with the largest weight value.

5. The method according to claim 2, characterized in that: The trend prediction model also includes a classification sub-model, and the method also includes: Inputting the industrial data of the to-be-transformed industry into the classification sub-model for classification to obtain the industrial data of different categories; The step of inputting the industrial data of the to-be-transformed industry into the weight allocation sub-model for weight allocation to obtain weights corresponding to the industrial data of different categories includes: The different categories of industrial data are input into the weight allocation sub-model for weight allocation to obtain the weights corresponding to the different categories of industrial data.

6. The method according to claim 5, characterized in that The trend prediction model also includes a feature extraction sub-model, and the method further includes: Inputting the industrial data of the industry to be transformed into the feature extraction sub-model to extract features, thereby obtaining feature data of the industrial data; The industrial data of the industry to be transformed is input into the classification sub-model for classification to obtain the industrial data of different categories, including: The characteristic data of the industrial data is input into the classification sub-model for classification to obtain the industrial data of different categories.

7. A prediction device, characterized in that: The device comprises: An acquisition module, used to acquire industrial data and preset mapping relationships of industries to be transformed; the preset mapping relationships are used to characterize the corresponding relationships between industrial data of different categories and industrial development trends; The prediction module is used to input the industrial data of the industry to be transformed and the preset mapping relationship into the trend prediction model to predict the industrial development trend and obtain the prediction result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images