Automatic modeling method, system, computing device and storage medium

Abstract

The embodiments of the present application provide an automatic modeling method, system, computing device and storage medium. In the embodiments of the present application, a modeling interface is provided, based on which data for modeling is obtained; modeling is performed according to the data and the preset modeling method to generate a corresponding model; and the output result of the model is determined according to the model and the input data, and the output result is displayed. This allows users to automatically and quickly create models without having to create models or model algorithms themselves, and to determine the output results according to the input data of the model, helping users complete modeling and model prediction at one time, greatly increasing the user experience, especially for users who are not familiar with model construction.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an automatic modeling method, system, computing device and storage medium. Background Art

[0002] With the rapid development of computer technology and the Internet, the application scope of computers has become more and more extensive, and has penetrated deeper into people's daily lives, and is gradually moving towards the direction of information intelligence. Among them, machine learning is the main reason for making computer applications more and more intelligent.

[0003] Machine Learning (ML) is a multi-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. It is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence, especially through machine learning algorithm modeling for prediction, etc. However, machine learning is a very complex subject, and it is very difficult for users who do not understand algorithms to build algorithms through machine learning. Summary of the invention

[0004] Multiple aspects of the present application provide an automatic modeling method, system, computing device and storage medium to help users automatically and quickly perform modeling and make predictions based on the modeled model.

[0005] An embodiment of the present application provides an automatic modeling method, including: providing a modeling interface, and obtaining data used for modeling based on the modeling interface; performing modeling according to the data and a preset modeling method to generate a corresponding model; obtaining input data corresponding to the model, and determining an output result of the model based on the model, and displaying the output result of the model.

[0006] An embodiment of the present application also provides an automatic modeling method, including: providing a modeling interface, displaying a data selection area, a modeling area, and a modeling result area on the modeling interface; in the data selection area, in response to a data selection operation and a data acquisition operation, acquiring data used for modeling; in the modeling area, in response to a modeling operation, performing modeling according to the data and a preset modeling method to generate a corresponding model; acquiring input data corresponding to the model, and determining an output result of the model based on the model, and displaying the model output result in the modeling result area.

[0007] The application embodiment also provides an automatic modeling method, including: receiving a source of data, and obtaining data for modeling based on the source; performing modeling based on the data and a preset modeling method to generate a corresponding model; receiving input data corresponding to the model, and determining an output result of the model based on the model, and sending the output result to a display end for display.

[0008] The application embodiment also provides an automatic modeling system, including: a first device and a second device; the first device is used to provide a modeling interface, and in the modeling interface, in response to a data acquisition operation, sends an acquisition request to the second device; the second device is used to obtain data used for modeling in response to the acquisition request; modeling is performed according to the data and a preset modeling method to generate a corresponding model; input data corresponding to the model sent by the first device is received, and based on the model, the output result of the model is determined, and the output result is sent to the first device for display.

[0009] An embodiment of the present application also provides a computing device, including: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program, so as to: provide a modeling interface, and based on the modeling interface, obtain data used for modeling; perform modeling according to the data and a preset modeling method to generate a corresponding model; obtain input data corresponding to the model, and determine the output result of the model based on the model, and display the output result of the model.

[0010] An embodiment of the present application also provides a computing device, comprising: a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program, so as to: provide a modeling interface, in which a data selection area, a modeling area and a modeling result area are displayed; in the data selection area, in response to a data selection operation and a data acquisition operation, data used for modeling are acquired; in the modeling area, in response to a modeling operation, modeling is performed according to the data and a preset modeling method to generate a corresponding model; the input data corresponding to the model is acquired, and based on the model, the output result of the model is determined, and the model output result is displayed in the modeling result area.

[0011] An embodiment of the present application also provides a computing device, including: a memory, a processor and a communication component; the memory is used to store a computer program; the processor is used to execute the computer program to: obtain data for modeling according to the source; perform modeling according to the data and a preset modeling method to generate a corresponding model; receive input data corresponding to the model, and determine the output result of the model according to the model; the communication component is used to receive the source of the data; and send the output result to a display terminal for display.

[0012] An embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by one or more processors, the one or more processors implement the steps in the above method.

[0013] In the embodiment of the present application, a modeling interface is provided. Based on the modeling interface, data for modeling is obtained; modeling is performed according to the data and the preset modeling method to generate a corresponding model; and the output result of the model is determined according to the model and the input data, and the output result is displayed. This allows users to automatically and quickly create models without having to create models or model algorithms themselves, and to determine the output result according to the model input data, helping users complete modeling and model prediction at one time, greatly increasing the user experience, especially for users who are not familiar with model construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1 A schematic diagram of the structure of an automatic modeling system according to an exemplary embodiment of the present application;

[0016] Figure 2 A schematic flow chart of an automatic modeling method according to an exemplary embodiment of the present application;

[0017] Figure 3 A schematic diagram of a modeling interface for another exemplary implementation of the present application;

[0018] Figure 4A This is a schematic diagram of a data selection interface for another exemplary implementation of the present application;

[0019] Figure 4B This is a schematic diagram of a data selection interface for another exemplary implementation of the present application;

[0020] Figure 5AA schematic diagram of a data selection interface of an exemplary embodiment of the present application;

[0021] Figure 5B A schematic diagram of a data selection interface of an exemplary embodiment of the present application;

[0022] Figure 6 A schematic diagram of a modeling area interface of an exemplary embodiment of the present application;

[0023] Figure 7 A schematic diagram of a modeling result interface of an exemplary embodiment of the present application;

[0024] Figure 8 A schematic diagram of a modeling result interface of an exemplary embodiment of the present application;

[0025] Fig. 9 A schematic flow chart of an automatic modeling method according to an exemplary embodiment of the present application;

[0026] Fig.10 A schematic flow chart of an automatic modeling method according to an exemplary embodiment of the present application;

[0027] Fig.11 A schematic structural diagram of an automatic modeling device provided for another exemplary embodiment of the present application;

[0028] Fig.12 A schematic structural diagram of an automatic modeling device provided for another exemplary embodiment of the present application;

[0029] Fig.13 A schematic structural diagram of an automatic modeling device provided for another exemplary embodiment of the present application;

[0030] Fig.14 A schematic diagram of the structure of a computing device provided for an exemplary embodiment of the present application;

[0031] Fig.15 A schematic diagram of the structure of a computing device provided for an exemplary embodiment of the present application;

[0032] Fig.16 A schematic diagram of the structure of a computing device provided for an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0034] In machine learning, time series forecasting (also known as time series forecasting) is to predict future trends through historical data to help users prepare for future situations in advance. It is very difficult to accurately predict trends, and it is necessary to consider a large number of influencing factors and have a keen intuition.

[0035] In order to solve this problem, an embodiment of the present application provides an automatic modeling method. Although the scenarios are diverse, the time granularity and historical data conditions are different, the method allows users to easily and quickly perform modeling and thus predict future trends.

[0036] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0037] Figure 1 The following is a schematic diagram of the structure of an automatic modeling system provided by an exemplary embodiment of the present application. Figure 1 As shown, the system 100 may include: a first device 101 and a second device 102 .

[0038] Among them, the first device 101 can be a device with certain computing capabilities, which can realize the function of sending a request to the second device 102 and obtain response data from the second device 102. The basic structure of the first device 101 may include: at least one processor. The number of processors may depend on the configuration and type of the device with certain computing capabilities. The device with certain computing capabilities may also include a memory, which may be volatile, such as RAM (Random Access Memory), or non-volatile, such as Read-Only Memory (ROM), flash memory, etc., or may include both types. The memory usually stores an operating system (OS), one or more application programs, and may also store program data, etc. In addition to the processing unit and the memory, the device with certain computing capabilities also includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices, etc. Optionally, some peripheral devices may include, for example, a keyboard, an input pen, etc. Other peripheral devices are well known in the art and will not be described in detail here. Optionally, the first device 101 may be an intelligent terminal, such as a mobile phone, a desktop computer, a notebook, a tablet computer, etc.

[0039] The second device 102 refers to a device that can provide computing and processing services in a network virtual environment, and can refer to a device that uses the network to acquire data and model. In physical implementation, the second device 102 can be anything that can provide computing services, respond to service requests, and return data processing results, such as a cloud server, cloud host, virtual center, conventional server, etc. The second device 102 mainly includes a processor, a hard disk, a memory, a system bus, etc., which is similar to a general computer architecture.

[0040] In an embodiment of the present application, the first device 101 provides a modeling interface, in which, in response to a data acquisition operation, an acquisition request is sent to the second device 102, and the acquisition request may carry the data source. The second device 102 receives the request and acquires data for modeling according to the data source carried in the request. The second device 102 may directly perform modeling based on the acquired data and a preset modeling method to generate a corresponding model. The second device 102 also receives input data corresponding to the model sent by the first device 101, and the input data may be carried by the acquisition request. The second device 102 determines the output result of the model based on the model and the input data, and sends the output result to the first device 101 for display.

[0041] In addition, after the second device 102 obtains the data for modeling according to the acquisition request, it returns the data to the first device 101 for display. After the user confirms the data and determines the above input data, the user can create the model. In response to the user's modeling operation, the first device 101 sends a modeling request to the second device 102, and the modeling request can carry the above input data. After receiving the modeling request, the second device 102 can perform modeling according to the acquired data, and after modeling, determine the output result of the model according to the input data carried in the modeling request.

[0042] In the application scenario of the embodiment of the present application, the user sends a request to obtain data from the second device 102, such as a cloud server, through the first device 101, such as a computer. The user can send the request through the browser installed on the first device 101. The second device 102 receives the request, which can carry the data source, such as the b table in the A database. The second device 102 can obtain the b table in the A database, thereby obtaining the data in the b table. It should be understood that this acquisition is that the second device 102 is connected to the data source through a data interface, so that it can be obtained. The second device 102 can use the acquired data as data for modeling, and return it to the first device 101 for display for user confirmation. If the data is a type of data, such as historical temperature, and can be data at the same time every day in history, such as the temperature at the same time every day in the past two years, then the user can directly model and enter the predicted time, such as the next year. In response to the user's input operation of the predicted time, the first device 101 obtains the predicted time, and in response to the modeling operation, sends a modeling request to the second device 102, which can carry the predicted time. After receiving the modeling request, the second device 102 performs modeling based on the acquired data, such as modeling a default model, which may be a prediction model, such as an exponential smoothing model. After modeling, the second device 102 may input the prediction time into the modeled exponential smoothing model to perform a prediction, such as predicting the temperature within the next year. At the same time, the second device 102 returns the predicted temperature to the first device 101 for the user to view.

[0043] It should be noted that in addition to the above-mentioned temperature prediction, data in many different scenarios can also be predicted, such as the passenger flow of scenic spots, the outpatient volume of hospitals, the incidence of epidemics, the prediction, analysis, and judgment of future tax trends for local and foreign trade enterprises, and the impact of the epidemic on imports and exports, etc. It can also be used to predict the registration volume of local and foreign trade enterprises. The prediction of geological changes in a region, the analysis of the economic situation of land resources, etc.

[0044] Among them, the threat of traditional epidemics continues to exist, and new epidemics continue to emerge. Early warning and prevention of epidemics are very important. For example, as a disease controlled globally, influenza always has the risk of large-scale epidemics. Accurately predicting the outbreak of influenza in advance can provide predictive and proactive early warning and prevention of influenza, minimizing the harm.

[0045] In addition, the embodiments of the present application are also applicable to image recognition, speech recognition, text recognition, etc. The corresponding recognition model is directly constructed through the embodiments of the present application, and the information to be tested, such as images and speech, is recognized.

[0046] Since the prediction scenario has been described above, the multiple scenario applications mentioned above will not be elaborated here. It is only explained that for different prediction data, the data types obtained for modeling are different and correspond to the prediction data. For example, if the passenger flow is predicted, the data type used for modeling is the historical passenger flow of a scenic spot, so as to predict the future passenger flow. For example, for the prediction of epidemics, the data type used for modeling can be the historical occurrence cycle of an epidemic and the outbreak data after the historical occurrence cycle, and a time series prediction model can be established to predict the future incidence trend of the epidemic. In addition, if the future tax trend of local enterprises and foreign trade enterprises is predicted, the data type used for modeling can be the historical tax data of local enterprises and the historical tax data of foreign trade enterprises, and a time series model can be established to predict the future tax trend of local enterprises and foreign trade enterprises. For speech recognition, the data type used for modeling can be the existing speech and the corresponding semantics, and modeling can be performed according to the neural network model to perform semantic recognition of speech.

[0047] In the above embodiment, the first device 101 and the second device 102 are connected to a network, and the network connection may be a wireless connection. If the first device 101 and the second device 102 are connected by communication, the network standard of the mobile network may be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), WiMax, 5G, etc.

[0048] The automatic modeling process is described in detail below in conjunction with the method embodiment.

[0049] Figure 2 This is a flowchart of an automatic modeling method according to an exemplary embodiment of the present application. The method 200 provided in the embodiment of the present application is executed by a smart terminal, such as a computer, a mobile phone, etc. The method 200 includes the following steps:

[0050] 201: Provide a modeling interface, and obtain data used for modeling based on the modeling interface.

[0051] 202: Modeling is performed according to the data and the preset modeling method to generate a corresponding model.

[0052] 203: Obtain input data corresponding to the model, determine the output result of the model based on the model, and display the output result of the model.

[0053] The following is a detailed description of the above steps:

[0054] 201: Provide a modeling interface, and obtain data used for modeling based on the modeling interface.

[0055] The modeling interface is a display interface for modeling, which can be displayed through a smart terminal.

[0056] For example, a user accesses a web interface (i.e., a modeling interface) provided by a cloud server through a browser installed on a computer. The user can perform a data acquisition operation on the modeling interface, and the computer responds to the acquisition operation and acquires the data from the cloud server and displays it on the interface, thereby acquiring data for modeling.

[0057] in, Figure 3 The modeling interface 300 is shown. A data selection area 301 (i.e. Figure 3 The user can perform a data acquisition operation on the data selection area 301 on the interface 300 , so that the acquired data can be displayed in the data selection area 301 .

[0058] In addition, the modeling interface includes not only the data selection area 301, but also a modeling area 302 (i.e. Figure 3 The modeling area in the figure) and the modeling result area 302 (i.e. Figure 3 The user can operate in different areas to complete the entire modeling process. The operation process of other areas will be described in detail below.

[0059] Specifically, based on the modeling interface, data for modeling is obtained, including: determining the source of the data in response to an input operation of the data source; and obtaining data according to the source as the data for modeling.

[0060] The source of data (also called data origin) refers to the source of the data, that is, the place where the data is stored, such as a database or other data storage platform, data storage server, etc.

[0061] For example, according to the above description, the user performs an acquisition operation on the interface 300. The user can use the mouse and keyboard to input the data source on the interface 300. The user can input in the input box corresponding to the data source in the data selection area 301, such as the "cloud computing resource" input box 3012 and the "table name" input box 3013.

[0062] in, Figure 4AThe interface 400A of the specific data selection area 301 is shown. The computer displays the data entered in the above input box on the interface 400A. The user enters "A" in the cloud computing resource input box 3012, indicating database A, and the user enters "b" in the table name input box 3013. At this time, the computer responds to the user's input operation, obtains the input data, and can send a request to the cloud server, which can carry the input data. After receiving the request, the cloud server goes to the source of the corresponding data to obtain the corresponding data according to the input data it carries. For example, the cloud server obtains the data in the b table from database A through the data interface. The cloud server returns the obtained data to the user's computer and displays it through the interface 400A. That is, the user can see the obtained data, which can be used as data for modeling.

[0063] In addition, the computer can also be used as an independent execution end. After obtaining the source of data, it can directly obtain the data in table b from database A through the data interface without obtaining it through the server. The obtained data is displayed on the interface 400A and can be used as data for modeling.

[0064] The data in this table belongs to the same type of data, such as historical temperature, and can be data at the same time every day in history, such as the temperature at the same time every day in the past two years. Users can directly use the acquired data as data for modeling.

[0065] It should be noted that the cloud computing resources mentioned above refer to data resources, that is, the source of data. The data resources may be databases, data storage platforms, etc. connected to the cloud server through a data interface, and are not specifically limited here.

[0066] In addition, whether it is a cloud server or a computer itself, when obtaining data, the data can be automatically detected, that is, the data that does not conform to the data format can be deleted or filtered, and finally the data that conforms to the data format can be retained for display, or sent to the computer for display.

[0067] It should be understood that the modeling interface is not limited to Figure 3 As long as it is an interface, users can obtain the corresponding data from the cloud server through the acquisition operation.

[0068] In addition, after a smart terminal, such as a computer, obtains data, it needs to be made known to the user through a display form so that the user can view what kind of data is currently obtained and enhance the user experience.

[0069] Specifically, the method 200 may further include: after acquiring the data according to the source, displaying the data corresponding to the source, the occurrence time of the data, and the data type of the data on the modeling interface.

[0070] The occurrence time of the data refers to the time when the data is generated, which can be displayed and queried through time fields, such as data date and running date.

[0071] Data type refers to the classification of data, such as temperature, price, etc. It can be displayed and queried through test fields, such as field name, temperature, etc.

[0072] For example, according to the above description, after the computer obtains the data, the interface 400A may display a list 401 of the obtained data. The list 401 may include multiple data columns. For illustration only, the list 401 may display the product number "001", the product name "Product 1", the data date "201x-01-03", the running date "201x-01-04" and the field name "3 million", etc.

[0073] When the user has other requirements for data, such as other conditions for filtering data, or when there are many types of data obtained and filtering is required for better modeling, the modeling interface, such as the interface 300, can also provide other conditions for data filtering to the user, so that the user can filter data on the modeling interface.

[0074] Specifically, the method 200 may also include: determining the occurrence time in response to an input operation of the occurrence time of the data; determining the data type in response to an input operation of the data type; and obtaining target data from the acquired data according to the occurrence time and the data type as data for modeling.

[0075] For example, as described above, when the user operates on the interface 300, in addition to inputting the input box for the source of the data, he can also input the "time field" input box 3014 and the "test field" input box 3015 to perform input filtering.

[0076] in, Figure 4BThe specific interface 400B of the data selection area 301 is shown. The data selection area 301 is displayed on the interface 400B, and the user operates on the data selection area 301, and enters "Date" in the "time field" input box 3014 and "Temp" in the "test field" input box 3015. Among them, Date represents the date, that is, the time of generation, and Temp represents the temperature. After the input is completed, the user can directly click the "Get Data" button 3011 to obtain data. The computer responds to the acquisition operation and can obtain data through the cloud server, or directly obtain data by itself. The acquisition process is similar to the previous text, and it will not be repeated here. It is only explained that when acquiring data, in addition to obtaining data from the source of the corresponding data, it is also necessary to filter these data according to the time field and the test field, and select data that meets the time field and the test field. Here, the time field can also be entered as 9 o'clock every morning, etc. At the same time, the acquired data is displayed on the interface 400B, which can be used as data for modeling, such as the data list 402.

[0077] In order to allow users to more directly see the changes and trends of various data, they can also be displayed in the following graphical form:

[0078] Specifically, the method 200 also includes: displaying the acquired data for modeling, the occurrence time of the data, and the data type of the data on the modeling interface; and displaying a detailed data graph corresponding to the data according to the occurrence time sequence.

[0079] Among them, the occurrence time series refers to the sequence composed of occurrence time. The data detailed graph refers to the graph that can show each data.

[0080] For example, according to the above, if Figure 4B As shown, the computer displays a data list 402 on the interface 400B, and also displays the data according to the data list 402, with the occurrence time series as the horizontal axis and the vertical axis as the temperature, that is, the data detailed graph 403. In the data detailed graph 403, the user can see the value of each data and the temperature corresponding to each date. For example, in the graph 403, the user can hover the mouse over the data 4031, that is, the data 4031 can be displayed as (1989-09-21, 10), which means that the temperature on September 21, 1989 is 10 degrees Celsius. In addition, the user can also enlarge the graph 403 with the mouse to view the data.

[0081] In addition, the method 200 may also include: displaying an overall data change trend graph corresponding to the data according to the occurrence time series.

[0082] For example, according to the above, in addition to displaying the data detailed graph 403, the data change trend graph 404 of the data can be displayed according to the above data list 402, with the occurrence time series as the horizontal axis and the vertical axis as the temperature, so that the user can view the change trend of the data as a whole. When you want to see the details, you can view the data detailed graph 403.

[0083] Since the embodiment of the present application provides a data detail graph 403 and a data change trend graph 404, that is, the time series data is analyzed and displayed from multiple dimensions, the user can view all the data or take a closer look at the local data.

[0084] In addition, in addition to filtering data based on the above conditions, the user can also filter data based on an aggregation method, which may include determining the unit time of the data and how to determine the data per unit time.

[0085] Specifically, the method 200 also includes: determining the unit time in response to an input operation of the unit time of the data; determining the determination method in response to an input operation of a determination method of the data corresponding to the unit time; and determining the corresponding data from the acquired data according to the unit time and the determination method as data for modeling.

[0086] The unit time can also be called the aggregation time scale, and the aggregation time scale can be year, month, week, day, hour, minute, second, etc.

[0087] The determination method, which may also be called the aggregation method, may include sum, maximum value, minimum value, first value (i.e., the first value in the time interval (aggregation time scale)) and last value (i.e., the last value in the time interval (aggregation time scale)).

[0088] For example, as described above, when the user operates on the interface 300, in addition to inputting into the above input boxes, he can also input into the "aggregation time scale" input box 3016 and the "aggregation method" input box 3017 to perform data screening and processing.

[0089] in, Figure 5AA more specific interface 500A of the data selection area 301 is shown. In the interface 500A, the user can use the mouse to input "day" in the "aggregation time scale" input box 3016 and input "average value" in the "aggregation method" input box 3017. That is, for the daily average temperature, when there are multiple temperatures at the same historical time on the same day, it is necessary to calculate the average value of the historical temperatures for that day as the historical temperature for that day, or the maximum or minimum value of the day can be selected as required. The user clicks the "Get Data" button 3011 to acquire data. The acquisition process will not be described in detail. It is only explained that after acquiring the data, both the computer and the cloud server will process the data according to the aggregation method and aggregation time scale, and display the processed data through the computer, which can be used as data for modeling. Figure 5A The data list 501, data detailed graph 502 and data change trend graph 503 are shown. In addition, the user can also move the two axes 504 in the data change trend graph 503, and can focus on viewing the data change trend before the two axes 504. It should be understood that for different data types, the aggregation method corresponding to the aggregation time scale can be different, so the user can make an independent choice to determine. At the same time, since the embodiment of the present application provides a variety of aggregation time scales and aggregation methods, the user can quickly preview and explore data at multiple aggregation time scales.

[0090] Since the acquired data may have missing data values, in order to reduce the impact of modeling, the missing data values ​​can be supplemented as follows:

[0091] The method 200 may further include: determining a corresponding processing method in response to a determination operation of a processing method for missing data values; determining the missing data value from data corresponding to the source; and processing the missing data value according to the processing method.

[0092] Among them, missing data values ​​can also become default values, such as the date 1981.05.05, the temperature data value is missing.

[0093] The processing method of missing data values ​​refers to the method of supplementing the missing data values, such as supplementing 0 or performing linear interpolation. Supplementing 0 can be used as the default processing method, and the supplementing 0 processing can be directly performed when the user does not make a selection.

[0094] For example, according to the above, when the user operates on the interface 300, in addition to entering the above input boxes, he can also enter the default value of the "processing method" input box 3018 or select "add 0" to filter and process the data. The acquisition and aggregation of data will not be described here. It is only explained that the computer or cloud server can first detect each acquired data, add 0 to the missing data value, and then perform aggregation processing. The processed data can be displayed on the computer and used as data for modeling. Figure 5B Shown are a data list 501 , a data detail graph 502 , and a data change trend graph 503 .

[0095] It should be noted that in addition to manual input by the user, the above input boxes can also be manually selected. Clicking each input box can provide a corresponding drop-down interface for the user to manually select. For example, clicking the "aggregation time scale" input box 3016 provides a drop-down interface that can include years, months, weeks, days, hours, minutes, seconds, etc.

[0096] 202: Modeling is performed according to the data and the preset modeling method to generate a corresponding model.

[0097] Among them, the preset modeling method refers to the process of establishing a corresponding model. The preset modeling method has been stored in the intelligent terminal or the server, and can be directly run to perform modeling. Each model can correspond to a modeling method. The model can include a neural network model and a time series prediction model. Among them, the time series prediction model can include an exponential smoothing model (ETS) and a Light GBM (Light Gradient Boosting Machine, referred to as LGBM), which is a variant of the Gradient Boosting Machine (GBM) model and is based on a decision tree model. The exponential smoothing model is a time series analysis and prediction method developed on the moving average method. It calculates the exponential smoothing value and predicts the future with a certain time series prediction model. The exponential smoothing model can provide multiple common cycles, perform cycle scanning, and select the most appropriate cycle. LGBM establishes time-related statistical features based on training data to predict future trends. For different aggregation time scales, there are corresponding statistical feature calculations, and optimized model parameters can also be provided.

[0098] For example, according to the foregoing, after the computer obtains the above data, the computer can directly perform modeling through the preset modeling method stored locally. At this time, the computer can randomly select a model to create, or select the default model to create, and generate the corresponding model.

[0099] The cloud server can also directly perform modeling according to the preset modeling method stored locally to generate the corresponding model.

[0100] Among them, modeling is performed according to data and a preset modeling method to generate a corresponding model, including: determining data within a preset range from the data, and displaying the data within the preset range on a modeling interface; displaying preset model information on the modeling interface; in response to a modeling operation, modeling is performed according to the data within the preset range and a preset modeling method corresponding to the preset model to generate a model.

[0101] In order to better carry out modeling, the computer can select a part of the acquired data as the preset range of data for modeling, and display this part of the data for user confirmation and selection.

[0102] For example, according to the foregoing, after the computer or cloud server obtains the data, that is, the data used for modeling, it selects data within a preset range, such as temperature history data within a year. And the temperature history data within a year is displayed on the modeling interface. At the same time, the model information of the modeling, such as the model name, etc., can also be displayed, so that the user can select the model to be created. When the user confirms the currently displayed content and performs a modeling operation, the computer responds to the modeling operation, performs modeling according to the above method, and generates a corresponding model. Or the computer responds to the modeling operation and sends a modeling request to the cloud server, so that the cloud server performs modeling according to the above method and generates a corresponding model.

[0103] in, Figure 6 The interface 600 of the modeling area 302 is shown. The computer displays the data within the preset range "Training time history 1000 to 199 days" on the interface 600. A graph 601 corresponding to the data can also be displayed. The training time area 602, that is, the temperature corresponding to the historical 1000 to 199 days is displayed in the graph 601. The model selection area (i.e., model selection) 605 is also displayed on the interface 600, which includes an exponential smoothing model and a Light GBM. In the model selection area 605, the exponential smoothing model is selected. The user can switch to select Light GBM by checking or filling in the option 606 of Light GBM. And cancel the option 607 of the exponential smoothing model. After confirming that everything is correct, the user can click the "Run" button 3021, that is, the modeling operation, and the computer responds to the operation and performs modeling.

[0104] In addition, the user can modify the training time zone on the diagram 601 in the interface 600, so that the user can independently select the training time zone, thereby enhancing the user's experience.

[0105] Specifically, the method 200 also includes: in response to a modification operation of a preset range, determining data corresponding to the modified range; in response to a modeling operation, performing modeling according to the data corresponding to the modified range and a preset modeling method corresponding to the preset model to generate a model.

[0106] For example, according to the foregoing, the user can modify the training time in the interface 600 by using the mouse. That is, the user modifies the "historical initial date" input box "3022" and the "historical end date" input box "3023" by using the mouse. The computer responds to the modification operation, thereby modifying the historical date, that is, modifying the training time, which can be modified to: historical 2000 to 100 days. Modeling is thereby performed, and the modeling process has been explained in the foregoing text and will not be repeated here. Since the embodiments of the present application can provide at least two types of time series prediction models, which respectively support time series data with obvious periodic trends and time series data without obvious periodic trends. Data with obvious cycles can be predicted by an exponential smoothing model, and data without obvious cycles can be predicted by establishing time-related statistical features and a Light GBM model.

[0107] In order to allow users to independently select the model to be created and enhance the user experience, multiple model selection options are provided for users to select the model to be created.

[0108] Specifically, the method 200 also includes: in response to a selection operation of a preset model, determining a target model from at least two models; in response to a modeling operation, performing modeling according to data in a preset range and a preset modeling method corresponding to the target model to generate a model.

[0109] Since it has been explained in the previous article, I will not repeat it here.

[0110] In order to enhance the user's understanding of the data, the training time can also be displayed in the form of a graph, so that the user can clearly and clearly know the training time, and the final training time can also be directly determined by modifying the data range in the graph. Specifically, the method 200 also includes: displaying data in a time series in the form of a graph; dividing the data in the graph by an axis to generate data in a preset range; and determining the data corresponding to the modified range in response to the movement operation of the axis.

[0111] For example, according to the foregoing, the computer displays a graph 601 corresponding to the data "Training time history 1000 to 199 days" 3025 within the preset range in the interface 600. The graph 601 is displayed with the occurrence time series as the horizontal axis and the temperature as the vertical axis. In the graph 601, the data in the graph 601 is divided by multiple axes, such as axis 6011 and axis 6012. Among them, the area between axis 6011 and axis 6012 is the training time area 602. The user can slide the axis 6011 and / or axis 6012 with the mouse to expand or reduce the data in the training time area 602, thereby modifying the corresponding data range. In response to the moving operation, the computer determines that the data corresponding to the modified range can be used as the data for the training model. After determining the corresponding training time, the corresponding training data, that is, the data used for modeling, can be determined. In addition, the user can also select or input the parameters for modeling to meet the user's modeling needs, and the generated model can better meet the model the user wants. The method 200 may further include: determining the target model parameters in response to a target model parameter selection operation; and generating a model by performing modeling according to data in a preset range, a preset modeling method corresponding to the target model, and the target model parameters in response to a modeling operation.

[0112] Among them, the model parameters are different for different models and are used to determine the model. For example, for an exponential smoothing model, its parameters can be a period, such as 7 days, etc. For LGBM, its parameters are learning rate, maximum number of iterations, etc.

[0113] For example, according to the above, if Figure 6 As shown, after selecting the exponential smoothing model, the user can customize its parameters. For example, the user can first select option 6052 of the "custom parameter" input box 6051, and then click the "custom parameter" input box 6051. The computer will pop up a drop-down interface, select its parameters in the drop-down interface, or directly enter its parameters in the "custom parameter" input box 6051, such as 7 days. When selecting parameters, the drop-down interface can provide multiple parameters for the user to choose. For the exponential smoothing model, 7, 14, 52, 365, etc. can be provided. The computer responds to the operation, determines the parameters, and performs modeling according to the user's modeling operation. The process of modeling has been explained in the previous text, and it will not be repeated here. It is only explained that in the process of modeling, the user-defined parameters will be used for modeling. When the user does not define the parameters, the default parameters of the model are used for modeling.

[0114] 203: Obtain input data corresponding to the model, determine the output result of the model based on the model, and display the output result of the model.

[0115] Among them, input data refers to the data input into the model to obtain the model results. For time series prediction models, it can be the prediction time or prediction time range, such as a time period in the future.

[0116] It should be noted that, whether it is an intelligent terminal or a server, after the model is created, when obtaining input data, the default input data can be directly used as the current input data. For example, for a time series prediction model, the intelligent terminal or server can set the next year as the default input data, obtain the default data, and input it into the model as the current input data to obtain the prediction results, such as the temperature of each day in the next year.

[0117] In addition, the method of obtaining input data corresponding to the model may also include: when there is a time series prediction model in the preset model, displaying the preset prediction time range (or prediction time); in response to the modification operation of the prediction time range (or prediction time), using the modified prediction time range (or prediction time) as input data.

[0118] In addition, in addition to responding to the modification operation, a modeling operation may also be responded to. Specifically, obtaining input data corresponding to the model includes: in response to the modeling operation, obtaining a predicted time within a preset range as input data;

[0119] For example, according to the above, if Figure 6 As shown, the computer can display the forecast time range "forecast time in the next 30 days" 3026 in the interface 600, and the model selected here is the exponential smoothing model. The user can modify the "future days" input box 3024 by mouse, and can modify it to 100 days. In response to the modification operation, the computer determines the modified forecast time range, such as the next 100 days. After the user clicks the "Run" button 3021, the computer responds to the modeling operation and obtains the modified forecast time range as input data.

[0120] For cloud server modeling, the computer can send a modeling request to it, and the modeling request can carry the above input data. After the modeling is completed, the cloud server can directly input the input data into the model for prediction. For computer modeling, the computer can directly input the input data into the model for prediction.

[0121] It should be noted that for other models, input data can also be obtained in the above manner, and the preset prediction time range can be directly displayed on the modeling interface, and an input box can be provided for the user to make modifications.

[0122] Similarly, the predicted time can also be displayed through a graph. The method 200 also includes: displaying data and the predicted time (or predicted time range) in the form of a graph in a time series; dividing the data and the predicted time (or predicted time range) in the graph through multiple axes to generate multiple preset ranges of data and preset ranges of predicted time; the multiple preset ranges of data include training data for training the model and test data for testing the model; in response to the modeling operation, obtaining the test data of the preset range; and testing the generated model based on the test data.

[0123] Among them, the data in the graph refers to the data used for modeling, that is, the data obtained for modeling can be divided into training data and test data. The training data is used to train the model and model, and the test data refers to the data used to test the accuracy of the model. It should be understood that the data obtained for modeling can be directly used as training data to train the model without dividing out the test data. However, the embodiment of the present application divides the test data so that the user can view the accuracy of the model and improve the user experience. The user can repeatedly modify the modeling parameters according to the accuracy, so that the final model meets the user's needs. At the same time, the computer or cloud server can also adjust and upgrade the preset modeling method according to the accuracy.

[0124] For example, according to the above, if Figure 6 As shown, the computer can display a graph 601 in the interface 600, and the graph 601 is displayed with the horizontal axis being the occurrence time series and the vertical axis being the temperature. In the graph 601, the data in the graph 601 is divided by multiple axes, such as axis 6011, axis 6012, axis 6013 and axis 6014, wherein axis 6011 and axis 6012 divide the training time zone, and axis 6012 and axis 6013 divide the test time zone 603, that is, the data in the time zone 603 can be used to test the model. Axis 6013 and axis 6014 divide the prediction time zone 604, and the data in the time zone 604 can be used as the above-mentioned input data for prediction. When the user confirms the current default displayed figure 601, that is, the user agrees to the training data in the current training time zone, the test data in the test time zone, and the prediction data in the prediction time zone, he can directly click the "Run" button 3021. The computer responds to the modeling operation, obtains the corresponding training data for model training (i.e., modeling), obtains the corresponding test data for model testing, and obtains the corresponding prediction data for prediction.

[0125] In addition, the user can also modify the above time zone. Specifically, the method 200 can also include: in response to the movement operation of the axis, determining the data corresponding to the modified range (that is, including training data and test data) and / or the predicted time corresponding to the modified range.

[0126] The method of obtaining the input data corresponding to the model may include: when determining the prediction time corresponding to the modified range, in response to the modeling operation, obtaining the prediction time corresponding to the modified range as input data. And the method 200 may also include: when determining the test data corresponding to the modified range, in response to the modeling operation, obtaining the test data corresponding to the modified range; and testing the generated model according to the test data corresponding to the modified range.

[0127] For example, according to the above, if Figure 6 As described above, the user can modify the corresponding time zone and thus the corresponding data range by moving any axis with the mouse. At the same time, the computer can determine the data range corresponding to each time zone in response to the moving operation, thereby modifying the data in "Training time history 1000 to 199 days" 3025 and / or "Prediction time next 30 days" 3026 in the interface 600. In addition, each axis can correspond to a specific time point, and the time unit can support years, months, weeks, days, hours, minutes, seconds, etc. Figure 6 The time unit in the figure is day. At the same time, the horizontal axis time series can be extended, and the rightmost boundary in Figure 601 can be extended to any time in the future. After the user clicks the "Run" button 3021, the computer responds to the modeling operation, obtains the prediction time corresponding to the modified prediction time zone as input data, and performs prediction. At the same time, it obtains the training data corresponding to the modified training time zone for model training (i.e., modeling) and the test data corresponding to the modified test time zone. Or the computer sends these data to the cloud server through a modeling request, so that the cloud server performs model training and prediction.

[0128] It should be noted that the test time can also be displayed on the interface 600 as needed, and its display format is similar to "Training time history 1000 to 199 days" 3025 or "Forecast time next 30 days" 3026. After modifying the test time zone in Figure 601, the test time in the interface 600 can also be modified accordingly, which will not be explained in detail here.

[0129] After the modeling is completed, the modeling results will be displayed on the modeling interface so that users can know the final prediction results and the specific situation of the modeling.

[0130] Specifically, the method 200 also includes: displaying modeling error data on the modeling interface; displaying the test results of the model on the modeling interface, the test results indicating the comparison result between the test value obtained by the model according to the input data corresponding to the test data and the actual value corresponding to the test data; and displaying the information of the model on the modeling interface.

[0131] Among them, the error data refers to the error of the model after modeling, which can refer to the error after modeling or the error of the model determined by test data. The error can include the root mean square error RMSE (root mean squared error) and the mean absolute error MAE (mean absolute error). These errors can be determined directly by a computer or by a cloud server. The specific determination process belongs to the prior art and will not be repeated here.

[0132] The above comparison results can be presented through data or through graphics.

[0133] The model information refers to the information of the model after modeling, which may refer to the introduction information of the model, the training time corresponding to the training data, the test time corresponding to the test data, and the model parameters.

[0134] For example, according to the foregoing, the computer can display the error data of the model after modeling on the modeling interface, which may include the root mean square error RMSE and mean absolute error MAE of the model itself, as well as the root mean square error RMSE and mean absolute error MAE of the model obtained by testing the model with the test data. At the same time, the modeling interface can also display the comparison results of the test values ​​obtained by the model based on the test data and the actual values ​​corresponding to the test data. For example, the test data is the temperature of each day in March 1990. March 1990 is used as the input data of the model to determine the temperature of each day, and the determined temperature is compared with the actual temperature of each day in March 1990.

[0135] in, Figure 7The interface 700 of the modeling result area 303 is shown. In the interface 700, the error data 3031 of the model ID "LGBM-01" is displayed. Among them, in the error data 3031, the error data of the training set refers to the root mean square error RMSE and the mean absolute error MAE of the model itself obtained by modeling the training data. The error data of the test set refers to the root mean square error RMSE and the mean absolute error MAE of the model obtained by testing the model with the test data. At the same time, the interface 700 also shows a graph 701, which belongs to the comparison result displayed when the "prediction result" icon 7011 is selected. In the graph 701, the solid line represents the actual value, that is, the actual value 7014, such as the actual value of temperature. In the graph 701, the dotted line represents the test value, that is, the test value 7015, such as the test value of temperature. The user can intuitively understand the error between the actual value and the test value from the graph 701, and can also understand the accuracy of the model after the current modeling.

[0136] In addition, the computer can also display the model information after modeling on the modeling interface. Figure 7 As shown, the user can click the "model information" icon 7012 on the interface 700 with the mouse, and the computer responds to the switching operation, or the clicking operation, to switch the current diagram 701 to the model information. Figure 8 An interface 800 of the modeling result area 303 is shown, in which model information is displayed, such as a data interval 801, which indicates the training time corresponding to the training data, including the training start time and the training end time, and can also indicate the test time corresponding to the test data, that is, from the current time to a certain time in the future.

[0137] In addition, the interface 800 also displays a model introduction 802 (i.e., model introduction information), which may include introduction information of the LGBM model, such as "LGBM is a variant of the Gradient Boosting Machine (GBM) model, which is based on a decision tree model." Parameters 803, i.e., model parameters, are also displayed, which may include a learning rate of 100, a maximum number of iterations of 500, a number of leaf nodes of 10, a sampling ratio of 0.7, an L1 regularization parameter of 0, and an L2 regularization parameter of 0.

[0138] It should be noted that users can understand the performance of the model and its prediction results for the future through the rich data displayed in the modeling results.

[0139] In addition, in the embodiments of the present application, users can directly implement functions such as data acquisition, data processing, prediction parameters and model selection through simple operations such as selection, input and moving axis lines, and complete the whole process of data analysis and modeling by clicking the mouse.

[0140] In order to help users gain a more intuitive understanding of the modeling process, each execution stage of the modeling process can also be displayed on the interface.

[0141] Specifically, the method 200 further includes: during the modeling process, displaying each execution stage of the process on the modeling interface, and displaying the current execution stage.

[0142] Among them, the execution phase refers to the various sub-processes in the modeling process, such as feature calculation, modeling, prediction, and completion.

[0143] For example, according to the above, during the modeling process, the computer determines each execution stage in the process, displays each execution stage on the modeling interface, and indicates the current execution stage. It should be noted that each execution stage can be preset for each preset model. That is, each preset model corresponds to a set of execution stages, which may include multiple execution stages. And the execution stages corresponding to each preset model may be the same or different.

[0144] Among them, Figure 7 As shown, the model operation status 702 is displayed in the interface 700, indicating the modeling process of the model. The model is LGBM-01, and its corresponding execution stages include: feature calculation, modeling, prediction, and completion. The completion mark 7021 of the execution stage can be used to clearly indicate whether the corresponding execution stage has been completed. When the completion mark 7021 is checked or selected, Figure 7 If it is in medium black, the execution stage has been completed, and it can be determined that the current execution stage of the current model is modeling.

[0145] It should be noted that for a server, such as a cloud server, during the modeling process, each stage will also be sent to a computer so that the computer can display each stage through an interface and provide it to the user.

[0146] In addition, the modeling interface also provides a download function, which can download the prediction results and model information, so that users can view them locally at any time.

[0147] Specifically, the method 200 further includes: in response to the information download operation, obtaining error data, comparison results and model information, and storing them locally.

[0148] For example, according to the above, if Figure 7 As shown, the user can click the "Download" button 7013 with the mouse, and the computer can respond to the download operation by sending the graph 701 and the error data 3031 in the prediction result to the corresponding storage area of ​​the computer for storage to facilitate user viewing.

[0149] In addition, if Figure 8 As shown, the user can click the "Download" button 7013 with the mouse, and the computer can respond to the download operation by sending the model information, including the data interval 801, model introduction 802 and parameters 803, to the corresponding storage area of ​​the computer for storage to facilitate user viewing.

[0150] It should be noted that if the model is built through a server, such as a cloud server, the cloud server can send the above data after modeling to a computer for display on the computer, such as Figure 7 as well as Figure 8 The data shown.

[0151] Based on the same inventive concept as above, Fig. 9 1 shows a flow chart of an automatic modeling method provided by another exemplary embodiment of the present application. The method 900 provided in the embodiment of the present application is executed by the above-mentioned intelligent terminal, such as a computer, such as Fig. 9 As shown, the method 900 includes the following steps:

[0152] 901: Provide a modeling interface, which displays a data selection area, a modeling area, and a modeling result area.

[0153] 902: In the data selection area, in response to a data selection operation and a data acquisition operation, data for modeling is acquired.

[0154] 903: In the modeling area, in response to the modeling operation, modeling is performed according to the data and the preset modeling method to generate a corresponding model.

[0155] 904: Obtain input data corresponding to the model, determine the output result of the model according to the model, and display the model output result in the modeling result area.

[0156] Since the specific implementation of steps 901-904 has been described in detail above, they will not be repeated here.

[0157] In addition, for the contents not described in detail in the method 900, reference may also be made to the various steps in the above method 200.

[0158] Based on the same inventive concept as above, Fig.10 A flow chart of an automatic modeling method provided by another exemplary embodiment of the present application is shown. The method 1000 provided by the embodiment of the present application is executed by the above-mentioned server, such as a cloud server, and the method 1000 includes the following steps:

[0159] 1001: receiving the source of data, and obtaining data for modeling according to the source.

[0160] 1002: Modeling is performed according to the data and the preset modeling method to generate a corresponding model.

[0161] 1003: Receive input data corresponding to the model, determine the output result of the model according to the model, and send the output result to the display end for display.

[0162] Since the specific implementation of steps 1001-1003 has been described in detail above, they will not be repeated here. It is only explained that the display terminal can be an intelligent terminal with a display component, such as a computer.

[0163] In addition, the method 1000 also includes: sending the data used for modeling to the display end for display; receiving the modeling request sent by the display end, executing the modeling according to the data and the preset modeling method, and generating the corresponding model.

[0164] Among them, obtaining data for modeling according to the source includes: obtaining source data according to the source and sending the source data to the display end; receiving the occurrence time of the data and the data type of the data, and obtaining corresponding data from the source data according to the occurrence time and the data type; receiving the unit time of the data and the determination method of the corresponding data per unit time, and determining the data for modeling from the corresponding data according to the unit time and the determination method.

[0165] Since the above content has been explained in the previous article, it will not be repeated here.

[0166] In addition, for the contents not described in detail in the method 1000 , reference can also be made to the various steps in the above method 200 .

[0167] Fig.11 A schematic diagram of the structure framework of an automatic modeling device provided for an exemplary embodiment of the present application. The device 1100 can be applied to an intelligent terminal, such as a computer. The device 1100 includes a providing module 1101, a modeling module 1102, and a determining module 1103; the functions of each module are described in detail below:

[0168] A module 1101 is provided, which is used to provide a modeling interface, and obtain data used for modeling based on the modeling interface.

[0169] The modeling module 1102 is used to perform modeling according to data and a preset modeling method to generate a corresponding model.

[0170] The determination module 1103 is used to obtain input data corresponding to the model, determine the output result of the model according to the model, and display the output result of the model.

[0171] The determination module 1103 includes: a determination unit, which is used to determine the source of data in response to an input operation of the data source; and an acquisition unit, which is used to acquire data according to the source as data for modeling.

[0172] In addition, the device 1103 also includes: a display module, which is used to display the data corresponding to the source, the occurrence time of the data, and the data type of the data on the modeling interface after the data is acquired according to the source.

[0173] In addition, the determination module 1103 is also used to determine the occurrence time in response to the input operation of the occurrence time of the data; determine the data type in response to the input operation of the data type; and obtain target data from the acquired data according to the occurrence time and the data type as data for modeling.

[0174] In addition, the determination module 1103 is also used to determine the unit time in response to an input operation of the unit time of the data; determine the determination method in response to an input operation of a determination method of the data corresponding to the unit time; and determine the corresponding data from the acquired data according to the unit time and the determination method as data for modeling.

[0175] In addition, the determination module 1103 is also used to determine the corresponding processing method in response to the determination operation of the processing method of the missing data value; determine the missing data value from the data corresponding to the source; and process the missing data value according to the processing method.

[0176] In addition, the display module is also used to display the acquired data used for modeling, the time when the data occurred, and the data type on the modeling interface; according to the occurrence time sequence, the detailed data graph corresponding to the data is displayed.

[0177] In addition, the display module is also used to display the overall data change trend graph corresponding to the data based on the occurrence time series.

[0178] Among them, the modeling module 1102 includes: a display unit, which is used to determine data within a preset range from the data and display the data within the preset range on the modeling interface; display preset model information on the modeling interface; and a generation unit, which is used to respond to the modeling operation, perform modeling according to the data within the preset range and the preset modeling method corresponding to the preset model, and generate a model.

[0179] In addition, the determination module 1103 is also used to respond to the modification operation of the preset range and determine the data corresponding to the modified range; the modeling module 1102 is also used to respond to the modeling operation and generate a model according to the data corresponding to the modified range and the preset modeling method corresponding to the preset model.

[0180] In addition, the determination module 1103 is also used to determine the target model from at least two models in response to the selection operation of the preset model; the modeling module 1102 is also used to generate a model in response to the modeling operation by performing modeling according to the data in the preset range and the preset modeling method corresponding to the target model.

[0181] In addition, the display module is also used to display data in a time series in the form of a graph; the device 1100 also includes: a division module, which is used to divide the data in the graph through an axis line to generate data in a preset range; the determination module 1103 is also used to determine the data corresponding to the modified range in response to the movement operation of the axis line.

[0182] In addition, the determination module 1103 is also used to determine the target model parameters in response to the selection operation of the target model parameters; the modeling module 1102 is also used to respond to the modeling operation, and generate a model according to the data in the preset range, the preset modeling method corresponding to the target model, and the target model parameters.

[0183] Among them, the determination module 1103 is also used to display the preset prediction time range when there is a time series prediction model in the preset model; in response to the modification operation of the prediction time range, the modified prediction time range is used as input data.

[0184] In addition, the display module is also used to display data and predicted time in the form of a graph in a time series; the data and predicted time in the graph are divided by multiple axes to generate multiple preset ranges of data and predicted time in the preset ranges; the multiple preset ranges of data include training data for training the model and test data for testing the model; wherein the determination module 1103 is also used to obtain the predicted time in the preset range as input data in response to the modeling operation; wherein the device 1100 also includes: a testing module, which is used to obtain the test data in the preset range in response to the modeling operation; and the generated model is tested according to the test data.

[0185] In addition, the determination module 1103 is also used to determine the data corresponding to the modified range and / or the predicted time corresponding to the modified range in response to the movement operation of the axis; when the predicted time corresponding to the modified range is determined, the predicted time corresponding to the modified range is obtained as input data in response to the modeling operation; wherein the device 1100 also includes: an acquisition module, which is used to obtain the test data corresponding to the modified range in response to the modeling operation when the test data corresponding to the modified range is determined; and a testing module, which is also used to test the generated model according to the test data corresponding to the modified range.

[0186] In addition, the display module is also used to display each execution stage of the process on the modeling interface during the modeling process, and display the current execution stage.

[0187] In addition, the display module is also used to display the modeling error data on the modeling interface; display the test results of the model on the modeling interface, which test results show the comparison results between the test values ​​obtained by the model according to the input data corresponding to the test data and the actual values ​​corresponding to the test data; and display the model information on the modeling interface.

[0188] In addition, the acquisition module is also used to obtain error data, comparison results and model information in response to the information download operation, and store them locally.

[0189] Fig.12 A schematic diagram of the structure framework of an automatic modeling device provided for an exemplary embodiment of the present application. The device 1200 can be applied to an intelligent terminal, such as a computer. The device 1200 includes a providing module 1201, an acquiring module 1202, a modeling module 1203, and a determining module 1204; the functions of each module are described in detail below:

[0190] A module 1201 is provided for providing a modeling interface, in which a data selection area, a modeling area and a modeling result area are displayed.

[0191] The acquisition module 1202 is used to acquire data for modeling in response to a data selection operation and a data acquisition operation in the data selection area.

[0192] The modeling module 1203 is used to perform modeling in the modeling area in response to the modeling operation according to the data and the preset modeling method to generate a corresponding model.

[0193] The determination module 1204 is used to obtain input data corresponding to the model, determine the output result of the model according to the model, and display the model output result in the modeling result area.

[0194] It should be noted that for some contents not mentioned in the device 1200 , reference may be made to the contents of the above-mentioned device 1100 .

[0195] Fig.13 A schematic diagram of the structure framework of an automatic modeling device provided for an exemplary embodiment of the present application. The device 1300 can be applied to a server. The device 1300 includes a receiving module 1301, a modeling module 1302, and a determining module 1303; the functions of each module are described in detail below:

[0196] The receiving module 1301 is used to receive the source of data and obtain data for modeling according to the source.

[0197] The modeling module 1302 is used to perform modeling according to data and a preset modeling method to generate a corresponding model.

[0198] The determination module 1303 is used to receive input data corresponding to the model, determine the output result of the model according to the model, and send the output result to the display end for display.

[0199] In addition, the device 1300 also includes: a sending module for sending data used for modeling to a display end for display; a receiving module 1301 for receiving a modeling request sent by the display end, executing modeling according to the data and a preset modeling method, and generating a corresponding model.

[0200] Among them, the receiving module 1301 includes: a sending unit, used to obtain source data according to the source, and send the source data to the display end; an obtaining unit, used to receive the occurrence time of the data and the data type of the data, and obtain corresponding data from the source data according to the occurrence time and the data type; a determining unit, used to receive the unit time of the data and the determination method of the corresponding data per unit time, and determine the data used for modeling from the corresponding data according to the unit time and the determination method.

[0201] It should be noted that for some contents not mentioned in the device 1300 , reference may be made to the contents of the above-mentioned device 1100 .

[0202] The above describes Fig.11 The internal functions and structure of the device 1100 shown, in one possible design, Fig.11 The structure of the device 1100 shown can be implemented as a computing device, such as a computer. Fig.14 As shown, the device 1400 may include: a memory 1401 and a processor 1402;

[0203] The memory 1401 is used to store computer programs.

[0204] Processor 1402 is used to execute a computer program to: provide a modeling interface, and based on the modeling interface, obtain data used for modeling; perform modeling according to the data and a preset modeling method to generate a corresponding model; obtain input data corresponding to the model, and based on the model, determine the output result of the model, and display the output result of the model.

[0205] The processor 1402 is specifically used to: determine the source of the data in response to an input operation of the data source; and obtain data according to the source as data for modeling.

[0206] In addition, the processor 1402 is also used to: after acquiring data according to the source, display the data corresponding to the source, the time when the data occurred, and the data type of the data on the modeling interface.

[0207] In addition, processor 1402 is also used to: determine the occurrence time in response to an input operation of the occurrence time of the data; determine the data type in response to an input operation of the data type; and obtain target data from the acquired data based on the occurrence time and the data type as data for modeling.

[0208] In addition, processor 1402 is also used to: determine the unit time in response to an input operation of the unit time of the data; determine the determination method in response to an input operation of the determination method of the unit time corresponding to the data, and determine the corresponding data from the acquired data according to the unit time and the determination method as data for modeling.

[0209] In addition, the processor 1402 is further used to: determine the corresponding processing method in response to the determination operation of the processing method of the missing data value; determine the missing data value from the data corresponding to the source; and process the missing data value according to the processing method.

[0210] In addition, the processor 1402 is also used to: display the acquired data used for modeling, the occurrence time of the data, and the data type of the data on the modeling interface; and display detailed data graphs corresponding to the data according to the occurrence time sequence.

[0211] In addition, the processor 1402 is also used to: display the overall data change trend graph corresponding to the data according to the occurrence time series.

[0212] Among them, processor 1402 is specifically used to: determine data within a preset range from the data, and display the data within the preset range on the modeling interface; display preset model information on the modeling interface; in response to the modeling operation, perform modeling according to the data within the preset range and the preset modeling method corresponding to the preset model to generate a model.

[0213] In addition, the processor 1402 is also used to: in response to a modification operation of a preset range, determine data corresponding to the modified range; in response to a modeling operation, perform modeling according to the data corresponding to the modified range and a preset modeling method corresponding to the preset model to generate a model.

[0214] In addition, the processor 1402 is also used to: determine a target model from at least two models in response to a preset model selection operation; and generate a model by performing modeling according to data in a preset range and a preset modeling method corresponding to the target model in response to a modeling operation.

[0215] In addition, processor 1402 is also used to: display data in a time series in the form of a graph; divide the data in the graph by an axis to generate data in a preset range; and determine the data corresponding to the modified range in response to the movement operation of the axis.

[0216] In addition, the processor 1402 is also used to: determine the target model parameters in response to the target model parameter selection operation; and generate a model in response to the modeling operation by performing modeling according to the data in the preset range, the preset modeling method corresponding to the target model, and the target model parameters.

[0217] The processor 1402 is further used for: when there is a time series prediction model in the preset models, displaying the preset prediction time range; and in response to a modification operation of the prediction time range, using the modified prediction time range as input data.

[0218] In addition, the display module is also used to display data and predicted time in the form of graphics in the form of occurrence time series; divide the data and predicted time in the graphics through multiple axes to generate multiple preset ranges of data and preset ranges of predicted time; the multiple preset ranges of data include training data for training models and test data for testing models; wherein the processor 1402 is also used to: in response to modeling operations, obtain the predicted time of the preset range as input data; wherein the processor 1402 is also used to: in response to modeling operations, obtain the test data of the preset range; according to the test data, test the generated model.

[0219] In addition, processor 1402 is also used to: determine the data corresponding to the modified range and / or the predicted time corresponding to the modified range in response to the movement operation of the axis; when determining the predicted time corresponding to the modified range, in response to the modeling operation, obtain the predicted time corresponding to the modified range as input data; wherein processor 1402 is also used to: when determining the test data corresponding to the modified range, in response to the modeling operation, obtain the test data corresponding to the modified range; and test the generated model according to the test data corresponding to the modified range.

[0220] In addition, the processor 1402 is further configured to: during the modeling process, display each execution stage of the process on the modeling interface, and display the current execution stage.

[0221] In addition, processor 1402 is also used to: display modeling error data on the modeling interface; display the test results of the model on the modeling interface, the test results showing the comparison results between the test values ​​obtained by the model based on the input data corresponding to the test data and the actual values ​​corresponding to the test data; and display the information of the model on the modeling interface.

[0222] In addition, the processor 1402 is also used to: in response to the information download operation, obtain error data, comparison results and model information, and store them locally.

[0223] In addition, an embodiment of the present invention provides a computer storage medium, when the computer program is executed by one or more processors, causing the one or more processors to implement Figure 2 The steps of an automatic modeling method in a method embodiment.

[0224] The above describes Fig.12 The internal functions and structure of the device 1200 shown, in one possible design, Fig.12 The structure of the device 1200 shown can be implemented as a computing device, such as a computer. Fig.15 As shown, the device 1500 may include: a memory 1501 and a processor 1502;

[0225] Memory 1501, used for storing computer programs;

[0226] Processor 1502 is used to execute a computer program to: provide a modeling interface, displaying a data selection area, a modeling area, and a modeling result area on the modeling interface; in the data selection area, in response to a data selection operation and a data acquisition operation, acquiring data used for modeling; in the modeling area, in response to a modeling operation, performing modeling according to the data and a preset modeling method to generate a corresponding model; acquiring input data corresponding to the model, and determining an output result of the model based on the model, and displaying the model output result in the modeling result area.

[0227] It should be noted that for some contents not mentioned in the device 1500 , reference may be made to the contents of the above-mentioned device 1400 .

[0228] In addition, an embodiment of the present invention provides a computer storage medium, when the computer program is executed by one or more processors, causing the one or more processors to implement Fig. 9 The steps of an automatic modeling method in a method embodiment.

[0229] The above describes Fig.13 The internal functions and structure of the device 1300 shown, in one possible design, Fig.13 The structure of the device 1300 shown may be implemented as a computing device, such as a server. Fig.16 As shown, the device 1600 may include: a memory 1601, a processor 1602, and a communication component 1603;

[0230] Memory 1601, used for storing computer programs;

[0231] Processor 1602 is used to execute a computer program to: obtain data for modeling according to a source; perform modeling according to the data and a preset modeling method to generate a corresponding model; receive input data corresponding to the model, and determine an output result of the model according to the model.

[0232] The communication component 1603 is used to receive the source of data and send the output result to the display end for display.

[0233] In addition, the communication component 1603 is also used to: send the data used for modeling to the display end for display; receive the modeling request sent by the display end, execute the modeling according to the data and the preset modeling method, and generate the corresponding model step.

[0234] Among them, the processor 1602 is specifically used to: obtain source data according to the source, and send the source data to the display end; receive the occurrence time of the data and the data type of the data, and obtain corresponding data from the source data according to the occurrence time and the data type; receive the unit time of the data and the determination method of the corresponding data per unit time, and determine the data used for modeling from the corresponding data according to the unit time and the determination method.

[0235] It should be noted that for some contents not mentioned in the device 1600 , reference may be made to the contents of the above-mentioned device 1400 .

[0236] In addition, an embodiment of the present invention provides a computer storage medium, when the computer program is executed by one or more processors, causing the one or more processors to implement Fig.10 The steps of an automatic modeling method in a method embodiment.

[0237] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 201, 202, 203, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0238] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0239] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0240] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable multimedia data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable multimedia data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0241] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable multimedia data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0242] These computer program instructions may also be loaded onto a computer or other programmable multimedia data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0243] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0244] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0245] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0246] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic modeling method, characterized in that: include: Providing a modeling interface, and acquiring data used for modeling based on the modeling interface; Determine data of a preset range from the data, and display the data of the preset range on the modeling interface; in response to a modification operation of the preset range, determine data corresponding to the modified range; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; The input data corresponding to the model is obtained, and based on the model, the output result of the model is determined, and the output result of the model is displayed.

2. The method according to claim 1, characterized in that The step of acquiring data for modeling based on the modeling interface includes: In response to an input operation of a data source, determining a source of the data; The data is acquired from the source as data for modeling.

3. The method according to claim 2, characterized in that The method further comprises: After the data is acquired according to the source, the data corresponding to the source, the occurrence time of the data, and the data type of the data are displayed on the modeling interface.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: In response to an input operation of an occurrence time of data, determining the occurrence time; In response to an input operation of a data type, determining the data type; According to the occurrence time and data type, target data is acquired from the acquired data as data for modeling.

5. The method according to claim 2 or 3, characterized in that: The method further comprises: In response to an input operation of a unit time of data, determining the unit time; In response to an input operation of a determination method of unit time corresponding data, determining the determination method; According to the unit time and the determination method, corresponding data is determined from the acquired data as data for modeling.

6. The method according to claim 2 or 3, characterized in that: The method further comprises: In response to the operation of determining a processing method for missing data values, determining a corresponding processing method; Determine missing data values ​​from the data corresponding to the source; The missing data value is processed according to the processing method.

7. The method according to claim 1, characterized in that The method further comprises: Displaying the acquired data used for modeling, the occurrence time of the data, and the data type of the data on the modeling interface; According to the occurrence time series, detailed data graphs corresponding to the data are displayed.

8. The method according to claim 7, characterized in that The method further comprises: According to the occurrence time series, the overall data change trend graph corresponding to the data is displayed.

9. The method according to claim 1, characterized in that: The method further comprises: Present the data in a time series in the form of a graph; Divide the data in the graph by the axis to generate data in a preset range; In response to the movement operation of the axis, data corresponding to the modified range is determined.

10. The method according to claim 1, characterized in that The obtaining of input data corresponding to the model includes: When there is a time series prediction model among the preset models, the preset prediction time range is displayed; In response to the modification operation of the prediction time range, the modified prediction time range is used as the input data.

11. The method according to claim 1, characterized in that: The method further comprises: Display the data in a time series and the forecast time in a graphical form; The data and the predicted time in the graph are divided by multiple axes to generate data in multiple preset ranges and predicted time in the preset ranges; the data in the multiple preset ranges include training data for training the model and test data for testing the model; Wherein, the obtaining of input data corresponding to the model includes: In response to the modeling operation, a preset range of predicted time is obtained as input data; Wherein, the method further comprises: In response to the modeling operation, obtaining test data of a preset range; The generated model is tested according to the test data.

12. The method according to claim 11, characterized in that The method further comprises: In response to the movement operation of the axis, determining data corresponding to the modified range and / or a predicted time corresponding to the modified range; Wherein, the obtaining of input data corresponding to the model includes: When determining the forecast time corresponding to the modified range, in response to the modeling operation, obtaining the forecast time corresponding to the modified range as input data; Wherein, the method further comprises: When the test data corresponding to the modified range is determined, in response to the modeling operation, the test data corresponding to the modified range is obtained; The generated model is tested according to the test data corresponding to the modified range.

13. The method according to claim 1, characterized in that The method further comprises: During the modeling process, each execution stage in the process is displayed on the modeling interface, and the current execution stage is displayed.

14. The method according to claim 1, characterized in that The method further comprises: Displaying modeled error data on the modeling interface; Displaying the test result of the model on the modeling interface, the test result indicating the comparison result between the test value obtained by the model according to the input data corresponding to the test data and the actual value corresponding to the test data; The model information is displayed on the modeling interface.

15. The method according to claim 14, characterized in that The method further comprises: In response to the information downloading operation, the error data, comparison results and model information are acquired and stored locally.

16. An automatic modeling method, characterized in that: include: Providing a modeling interface, wherein a data selection area, a modeling area, and a modeling result area are displayed on the modeling interface; In response to a data selection operation and a data acquisition operation, acquiring data for modeling in the data selection area; In response to a modeling operation, on the modeling area, data of a preset range is determined from the data, and the data of the preset range is displayed on the modeling interface; in response to a modification operation of the preset range, data corresponding to the modified range is determined; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; The input data corresponding to the model is obtained, and the output result of the model is determined according to the model, and the output result of the model is displayed in the modeling result area.

17. An automatic modeling method, characterized in that: include: receiving a source of data, and obtaining data for modeling according to the source; Determine data of a preset range from the data, and display the data of the preset range on the modeling interface; in response to a modification operation of the preset range, determine data corresponding to the modified range; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; Receive input data corresponding to the model, determine the output result of the model according to the model, and send the output result to the display end for display.

18. The method according to claim 17, characterized in that The method further comprises: Sending the data used for modeling to the display end for display; The modeling request sent by the display terminal is received, and the modeling is performed according to the data and the preset modeling method to generate the corresponding model.

19. The method according to claim 17, characterized in that The step of acquiring data for modeling from the source includes: According to the source, source data is obtained, and the source data is sent to the display end; Receive the occurrence time of data and the data type of the data, and obtain corresponding data from the source data according to the occurrence time and the data type; The unit time of the data and the method for determining the data corresponding to the unit time are received, and the data used for modeling are determined from the corresponding data according to the unit time and the method for determining.

20. An automatic modeling system, characterized in that: include: a first device and a second device; The first device is used to provide a modeling interface, and in the modeling interface, in response to a data acquisition operation, sends an acquisition request to the second device; The second device is used to obtain data for modeling in response to the acquisition request; Determine data of a preset range from the data, and display the data of the preset range on the modeling interface; in response to a modification operation of the preset range, determine data corresponding to the modified range; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; Receive input data corresponding to the model sent by the first device, determine the output result of the model based on the model, and send the output result to the first device for display.

21. A computing device comprising: Memory and processor; The memory is used to store computer programs; The processor is configured to execute the computer program to: Providing a modeling interface, and acquiring data used for modeling based on the modeling interface; Determine data of a preset range from the data, and display the data of the preset range on the modeling interface; in response to a modification operation of the preset range, determine data corresponding to the modified range; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; The input data corresponding to the model is obtained, and based on the model, the output result of the model is determined, and the output result of the model is displayed.

22. A computing device comprising: Memory and processor; The memory is used to store computer programs; The processor is configured to execute the computer program to: Providing a modeling interface, wherein a data selection area, a modeling area, and a modeling result area are displayed on the modeling interface; In response to a data selection operation and a data acquisition operation, acquiring data for modeling in the data selection area; In response to a modeling operation, on the modeling area, data of a preset range is determined from the data, and the data of the preset range is displayed on the modeling interface; in response to a modification operation of the preset range, data corresponding to the modified range is determined; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; The input data corresponding to the model is obtained, and the output result of the model is determined according to the model, and the output result of the model is displayed in the modeling result area.

23. A computing device comprising: Memory, processor, and communication components; The memory is used to store computer programs; The processor is configured to execute the computer program to: Obtain data for modeling based on sources; Determine data of a preset range from the data, and display the data of the preset range on the modeling interface; in response to a modification operation of the preset range, determine data corresponding to the modified range; In response to a selection operation of a preset model, determining a target model from at least two models; in response to a selection operation of the target model parameters, determining the target model parameters; In response to the modeling operation, modeling is performed according to the data corresponding to the modified range, the preset modeling mode corresponding to the target model, and the target model parameters to generate the model; Receiving input data corresponding to the model, and determining an output result of the model according to the model; The communication component is used to receive the source of data; The output result is sent to the display terminal for display.

24. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by one or more processors, the one or more processors are caused to implement the steps of the method according to any one of claims 1 to 19.

Images