A service model establishment method and device, electronic equipment and storage medium

Abstract

The application discloses a business model establishment method and device, electronic equipment and storage medium, and belongs to the technical field of data mining. The method comprises the following steps: in response to a template viewing request, displaying business description information of at least one model template matched with business type information in the template viewing request; in response to a template configuration request triggered based on the business description information, displaying configuration options of various training resources available to a target model template; in response to a resource configuration request triggered based on the configuration options, configuring target training resources actually used by the target model template; in response to a model training request, performing model training based on the configured target training resources, and obtaining a business model. In this way, a business personnel can perform model training to obtain a business model by configuring various training resources of a model template, the modeling threshold is relatively low, the quality of the business model established through the model template is guaranteed, and the maintenance difficulty of the business model is also relatively low.

Description

Technical Field

[0001] This application relates to the field of data mining technology, and in particular to a method, apparatus, electronic device and storage medium for establishing a business model. Background Technology

[0002] In the field of communications, tens of thousands of business data are generated every day, and it is usually necessary to extract useful data from these business data to carry out business.

[0003] In related technologies, data mining is usually closely integrated with manual modeling. This not only requires significant manpower for feature engineering and model parameter tuning, but also demands that modelers possess specialized knowledge in data mining, making the modeling process quite demanding. The quality of the final business model depends heavily on the skill level of the professionals, making it difficult to control. Furthermore, business needs are constantly evolving, necessitating continuous updates and maintenance of the business model, which also presents considerable challenges. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for establishing a business model, in order to solve the problems of high modeling threshold, difficulty in ensuring model quality, and high difficulty in model maintenance when establishing a business model through data mining in related technologies.

[0005] Firstly, embodiments of this application provide a method for establishing a business model, comprising:

[0006] In response to a template viewing request, display the business description information of at least one model template that matches the business type information in the template viewing request;

[0007] In response to a template configuration request triggered based on the business description information, display the configuration options for various training resources that the target model template can use;

[0008] In response to a resource configuration request triggered based on the configuration options, configure the target training resources actually used by the target model template;

[0009] In response to a model training request, the model is trained based on the configured target training resources to obtain a business model.

[0010] In some embodiments, the various training resources include any combination of data sources, data features, model structures, and model algorithms.

[0011] In some embodiments, a business model is trained based on the configured target training resources to obtain a model, including:

[0012] Obtain the target data source that the target model template can use, and obtain the business annotation data of the target model template;

[0013] Determine the feature content of the target data features that the target model template in the target data source can use;

[0014] The business model is obtained by training using the feature content of the target data features, the business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

[0015] In some embodiments, if there are at least two target model algorithms, the business model is obtained by training using the feature content of the target data features, the business annotation data, and the target model structure and target model algorithm that the target model template can use, including:

[0016] A candidate business model is obtained by training using the feature content of the target data features, the business annotation data, the target model structure, and each target model algorithm.

[0017] The candidate business models are evaluated based on the algorithm evaluation metrics corresponding to the target model algorithm.

[0018] Based on the evaluation results of each alternative business model, one alternative business model is selected as the business model.

[0019] In some embodiments, after obtaining a business model, the following is also included:

[0020] Obtain business feedback information corresponding to the business model after deployment, wherein the business feedback information is used to characterize the business processing capability of the business model;

[0021] Based on the business feedback information, determine the business processing capabilities of the business model;

[0022] If it is determined that the business processing capacity exceeds the preset standard, then based on the target training resources, update the various training resources that the target model template can use.

[0023] Secondly, embodiments of this application provide a business model establishment apparatus, comprising:

[0024] The information display module is used to respond to a template viewing request and display the business description information of at least one model template that matches the business type information in the template viewing request.

[0025] The resource display module is used to respond to a template configuration request triggered based on the business description information and display the configuration options of various training resources that the target model template can use.

[0026] The configuration module is used to configure the target training resources actually used by the target model template in response to a resource configuration request triggered based on the configuration options.

[0027] The training module is used to respond to a model training request and train the model based on the configured target training resources to obtain a business model.

[0028] In some embodiments, the various training resources include any combination of data sources, data features, model structures, and model algorithms.

[0029] In some embodiments, the training module is specifically used for:

[0030] Obtain the target data source that the target model template can use, and obtain the business annotation data of the target model template;

[0031] Determine the feature content of the target data features that the target model template in the target data source can use;

[0032] The business model is obtained by training using the feature content of the target data features, the business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

[0033] In some embodiments, if there are at least two target model algorithms, the training module is specifically used for:

[0034] A candidate business model is obtained by training using the feature content of the target data features, the business annotation data, the target model structure, and each target model algorithm.

[0035] The candidate business models are evaluated based on the algorithm evaluation metrics corresponding to the target model algorithm.

[0036] Based on the evaluation results of each alternative business model, one alternative business model is selected as the business model.

[0037] In some embodiments, it also includes:

[0038] The acquisition module is used to acquire business feedback information corresponding to the business model after it is deployed, after obtaining a business model. The business feedback information is used to characterize the business processing capability of the business model.

[0039] The determination module is used to determine the business processing capability of the business model based on the business feedback information.

[0040] An update module is used to update the various training resources that the target model template can use based on the target training resources if it is determined that the business processing capacity exceeds a preset standard.

[0041] Thirdly, embodiments of this application provide an electronic device, including: at least one processor, and a memory communicatively connected to the at least one processor, wherein:

[0042] The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform the method for establishing the business model described above.

[0043] Fourthly, embodiments of this application provide a storage medium in which, when the instructions in the storage medium are executed by the processor of an electronic device, the electronic device is able to execute the above-described method for establishing a business model.

[0044] In this embodiment, in response to a template viewing request, business description information of at least one model template matching the business type information in the template viewing request is displayed. In response to a template configuration request triggered based on the business description information, configuration options for various training resources that the target model template can use are displayed. In response to a resource configuration request triggered based on the configuration options, the target training resources actually used by the target model template are configured. In response to a model training request, model training is performed based on the configured target training resources to obtain a business model. This provides a set of model templates usable by a type of business, and the various training resources of the model templates are configurable. Business personnel can train a business model by configuring the various training resources of the model templates without needing to possess professional knowledge of data mining, thus lowering the barrier to entry for developing business models. Furthermore, model templates are usually developed by experts with expertise in data mining, so the quality of business models built using model templates is relatively guaranteed. Additionally, when business requirements change, business personnel can reconfigure the various training resources of the model templates without having to re-establish complex feature engineering, thus reducing the maintenance difficulty of the business model. Attached Figure Description

[0045] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0046] Figure 1 A flowchart illustrating a method for establishing a business model as provided in an embodiment of this application;

[0047] Figure 2 A flowchart for obtaining a business model through model training is provided in an embodiment of this application;

[0048] Figure 3A schematic diagram illustrating the process of establishing a business model as provided in an embodiment of this application;

[0049] Figure 4 A schematic diagram illustrating a data filtering operation provided in an embodiment of this application;

[0050] Figure 5 A schematic diagram illustrating a data feature filtering operation provided in an embodiment of this application;

[0051] Figure 6 A schematic diagram of a business model creation apparatus provided in an embodiment of this application;

[0052] Figure 7 This is a schematic diagram of the hardware structure of an electronic device for implementing a business model establishment method, provided in an embodiment of this application. Detailed Implementation

[0053] To address the problems of high modeling threshold, difficulty in guaranteeing model quality, and high maintenance difficulty in establishing business models through data mining in related technologies, embodiments of this application provide a method, apparatus, electronic device, and storage medium for establishing a business model.

[0054] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0055] For ease of understanding, the technical terms used in this application are as follows:

[0056] A model template corresponds to a type of business and provides a general model for this type of business. With the help of this general model, different business models can be built. These different business models may use different data sources, have different data characteristics, different model structures, and different model algorithms.

[0057] Training resources refer to the resources used during training, such as data sources, data features, model structure, and model algorithms.

[0058] In this embodiment, a model template usable by various business operations is provided. The training resources of this template are configurable, allowing business personnel to train a business model simply by configuring these resources. No data mining expertise is required, thus lowering the barrier to entry for business model development. Furthermore, since model templates are typically developed by experts with data mining knowledge, the quality of business models built using these templates is generally reliable. Additionally, when business requirements change, business personnel can reconfigure the training resources of the model template without having to perform complex feature engineering again, further reducing the maintenance difficulty of the business model.

[0059] After introducing the inventive concept of this application, the following describes the solutions of the embodiments of this application in conjunction with specific flowcharts.

[0060] Figure 1 A flowchart of a method for establishing a business model provided in this application embodiment includes the following steps.

[0061] In step 101, in response to a template viewing request, business description information of at least one model template that matches the business type information in the template viewing request is displayed.

[0062] Generally, business personnel have clear business requirements before building a business model, and these requirements determine which type of business model template might be used. To enable business personnel to quickly find a suitable model template, the template viewing request can include business type information.

[0063] Among them, business type information, such as the type identifier of the business type, and business description information of the model template, such as the applicable business types, input data sources, and output results of the model template, can be used by business personnel to know what kind of business the template model can handle and what kind of business results can be obtained.

[0064] In step 102, in response to a template configuration request triggered based on business description information, configuration options for various training resources that the target model template can use are displayed.

[0065] Among them, various training resources include any combination of data sources, data features, model structures, and model algorithms.

[0066] In practice, for any of the above training resources, the configuration options for that training resource that the target model template can use can be displayed, so that business personnel can flexibly configure the target training resources actually used by the target model template.

[0067] In step 103, in response to a resource configuration request triggered based on configuration options, the target training resources actually used by the target model template are configured.

[0068] Generally, there can be more than one data source, multiple data features, one model structure, and more than one model algorithm. Therefore, target training resources include: at least one target data source, multiple target data features, one target model structure, and at least one target model algorithm.

[0069] Additionally, it should be noted that for each type of training resource, business personnel can customize it. For example, they can introduce new data sources, configure new data features, introduce new model structures, and use new model algorithms to improve the flexibility of model building and the scalability of the target model template.

[0070] In step 104, in response to the model training request, the model is trained based on the configured target training resources to obtain a business model.

[0071] In specific implementation, it can be done according to Figure 2 The process shown involves training the model to obtain a business model, and includes the following steps.

[0072] In step 201a, the target data source that the target model template can use is obtained, and the business annotation data of the target model template is obtained.

[0073] Generally, the data source can be stored in a database, and the business annotation data of the target model template is pre-annotated and can also be stored in a database. Therefore, the target data source and business annotation data can be obtained from the database.

[0074] In step 202a, the feature content of the target data features that can be used by the target model template in the target data source is determined.

[0075] Generally, target data features are fields. Therefore, determining the feature content of the target data features that the target model template can use in the target data source is equivalent to determining the field content of the corresponding field in the target data source.

[0076] In step 203a, a business model is obtained by training using the feature content of the target data features, business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

[0077] When there are at least two target model algorithms, the target data features, business-labeled data, target model structure, and each target model algorithm can be used for training to obtain a candidate business model. Based on the algorithm evaluation metrics corresponding to each target model algorithm, the prediction performance of the candidate business model is evaluated. Then, based on the evaluation results of each candidate business model, one candidate business model is selected as the actual business model. For example, the candidate business model with the best prediction performance is selected as the actual business model.

[0078] Among them, algorithm evaluation metrics include accuracy, coverage, precision, Gini coefficient, confusion matrix, Receiver Operator Characteristic (ROC) curve, Area Under Curve (AUC), KS curve, lift curve, recall, and response rate curve.

[0079] In practice, after obtaining a business model, business personnel can check whether the output of the business model matches their desired business requirements. If they do not match, they can reconfigure the target training resources actually used by the target model template and retrain the business model. If they match, they can obtain more training samples to train the business model to improve its performance and deploy the finally trained business model to the production line.

[0080] In order to improve the model building effect of the target model template, business feedback information corresponding to the business model can also be obtained after the business model is deployed. The business feedback information is used to characterize the business processing capability of the business model. Based on the business feedback information, the business processing capability of the business model is determined. If the business processing capability is determined to exceed the preset standard (such as the preset score representing the business processing capability), the various training resources that the target model template can use can also be updated based on the target training resources.

[0081] For example, add the data features defined by business users in the target training resources to the data features that the target model template can use. Or, adjust the data sources used by business users in the target training resources to the beginning of the list of data sources that the target model template can use.

[0082] In this way, by using the business processing capabilities of the business model developed by business personnel to update the various training resources available to the target model template, it is beneficial to use the updated target model template to build a better business model, thus forming a virtuous cycle of target model template - business model - target model template.

[0083] The solution of this application will be described below with reference to specific embodiments.

[0084] Figure 3 This illustration shows a business model creation process provided in an embodiment of this application. The model template is provided to business personnel. Through an interactive interface, business personnel can perform simple and quick operations such as data selection, feature selection, and algorithm selection. The system can then automatically adjust parameters to build the business model and ultimately output the result data to the address specified by the business personnel. The model template includes a data description display module, a data filtering operation module, a data feature operation module, an automatic modeling parameter tuning module, and a data export operation module. Specifically:

[0085] The data description and display module describes and displays the processed model data without requiring any operation from business personnel. It includes data source description information, statistical description information, and metadata information. Here, the data source description information includes the source of the access data source, update time, and data tags; the statistical description information includes the feature range, quintiles, mean, variance, standard deviation, and the number of records for each tag dimension; the metadata information includes feature description, storage type, update time, data type, number / percentage of missing values, and number / percentage of outliers.

[0086] The data filtering module provides business users with simple and quick self-service operations such as selecting datasets, filtering data, and choosing partitions. This includes filtering datasets by time-related features and by class label features.

[0087] The data feature operation module provides business personnel with a simple and quick way to derive new features and select input features.

[0088] The automatic modeling and parameter tuning module obtains the optimal algorithm information from the candidate algorithm set, directly calls the corresponding algorithm component and model evaluation component, and performs parameter iterative calculations on the algorithm input parameters according to predetermined rules until the optimal model parameters are obtained.

[0089] The data export module provides business personnel with the ability to specify the data output storage address.

[0090] In practice, business personnel should follow these six steps when building a business model:

[0091] The first step is to view the data. Business personnel can view the data information of the model template through the data description module, including: data source description information (such as brief database information, data source business system information, etc.), statistical description information, metadata information, etc.

[0092] The second step is data filtering. The data filtering module provides business users with a large, pre-processed dataset. Business users can quickly and easily filter data from this dataset using dropdown menus and other interactive methods. This application embodiment provides an example of a data filtering implementation. Figure 4 As shown, in Figure 4 The system filters out age and internet age features and selects records with an ARUP value greater than or equal to 60.

[0093] The third step involves data feature manipulation. Based on their business knowledge and all the features provided by the data feature manipulation module, business personnel select new features or derive new features. This application provides an example of a feature selection implementation. Figure 5 As shown, in Figure 5 In the process, business personnel added four features to the feature set: the number of minutes last month, the data traffic last month, the average number of minutes in the past 3 months, and the average data traffic in the past 3 months.

[0094] Step 4: Set the data export parameters, for example, set it to export to a specified disk location as a file.

[0095] Step 5: Automatic model calculation. Based on the parameters set in steps 2 to 4, the automatic modeling and parameter tuning module automatically performs modeling and parameter tuning to obtain a business model, and saves the data of the business model to the specified location.

[0096] Step 6: View the data. Business personnel can view the data and export it to the system's application database through the data export module. The system then provides an online data viewing method.

[0097] The modeling method provided in this application can reduce a series of problems that may occur with manual modeling, such as high manpower input, difficulty in controlling modeling quality, high threshold, and high maintenance costs. It can retain the advantages of manual modeling, such as retaining human participation in processing personalized data features and the model being closely integrated with business scenarios. It can reduce the problems that may occur with automatic modeling, such as additional investment in computing resources. It can also connect the business knowledge of business personnel with the data mining capabilities of professionals, allowing business personnel to quickly and independently build models.

[0098] When the method provided in the embodiments of this application is implemented in software, hardware, or a combination of software and hardware, the electronic device may include multiple functional modules, and each functional module may include software, hardware, or a combination thereof.

[0099] Based on the same technical concept, this application also provides a business model establishment device. The principle of the business model establishment device in solving the problem is similar to that of the above-mentioned business model establishment method. Therefore, the implementation of the business model establishment device can refer to the implementation of the business model establishment method, and the repeated parts will not be described again.

[0100] Figure 6A schematic diagram of a business model establishment device provided in this application embodiment includes an information display module 601, a resource display module 602, a configuration module 603, and a training module 604.

[0101] The information display module 601 is used to respond to a template viewing request and display the business description information of at least one model template that matches the business type information in the template viewing request.

[0102] The resource display module 602 is used to display the configuration options of various training resources that can be used by the target model template in response to a template configuration request triggered based on the business description information.

[0103] Configuration module 603 is used to configure the target training resources actually used by the target model template in response to a resource configuration request triggered based on the configuration options.

[0104] The training module 604 is used to respond to a model training request and train the model based on the configured target training resources to obtain a business model.

[0105] In some embodiments, the various training resources include any combination of data sources, data features, model structures, and model algorithms.

[0106] In some embodiments, the training module 604 is specifically used for:

[0107] Obtain the target data source that the target model template can use, and obtain the business annotation data of the target model template;

[0108] Determine the feature content of the target data features that the target model template in the target data source can use;

[0109] The business model is obtained by training using the feature content of the target data features, the business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

[0110] In some embodiments, if there are at least two target model algorithms, then the training module 604 is specifically used for:

[0111] A candidate business model is obtained by training using the feature content of the target data features, the business annotation data, the target model structure, and each target model algorithm.

[0112] The candidate business models are evaluated based on the algorithm evaluation metrics corresponding to the target model algorithm.

[0113] Based on the evaluation results of each alternative business model, one alternative business model is selected as the business model.

[0114] In some embodiments, it also includes:

[0115] The acquisition module 605 is used to acquire, after obtaining a business model, business feedback information corresponding to the business model after deployment of the business model, the business feedback information being used to characterize the business processing capability of the business model;

[0116] The determining module 606 is used to determine the business processing capability of the business model based on the business feedback information.

[0117] The update module 607 is used to update the various training resources that the target model template can use based on the target training resources if it is determined that the business processing capacity exceeds the preset standard.

[0118] The module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. Coupling between modules can be achieved through interfaces, typically electrical communication interfaces, but mechanical interfaces or other types of interfaces are also possible. Therefore, modules described as separate components may or may not be physically separate; they can be located in one place or distributed across different locations on the same or different devices. The integrated modules described above can be implemented in hardware or as software functional modules.

[0119] Having introduced the comparative learning method and apparatus of exemplary embodiments of this application, we will now introduce an electronic device according to another exemplary embodiment of this application.

[0120] The following reference Figure 7 To describe an electronic device 130 implemented according to this embodiment of the present application. Figure 7 The electronic device 130 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0121] like Figure 7 As shown, the electronic device 130 is presented in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to: at least one processor 131, at least one memory 132, and a bus 133 connecting different system components (including memory 132 and processor 131).

[0122] Bus 133 represents one or more of several bus structures, including a memory bus or memory controller, peripheral bus, processor, or local bus using any of the various bus structures.

[0123] The memory 132 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1321 and / or cache memory 1322, and may further include read-only memory (ROM) 1323.

[0124] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0125] Electronic device 130 can also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 130, and / or with any device that enables electronic device 130 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 135. Furthermore, electronic device 130 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 136. As shown, network adapter 136 communicates with other modules used in electronic device 130 via bus 133. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0126] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 132 including instructions, which can be executed by a processor 131 to complete the above-described contrastive learning method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0127] In an exemplary embodiment, the electronic device of this application may include at least one processor and at least one memory. The memory stores program code that, when executed by the processor, causes the processor to perform the steps of any of the exemplary methods provided in this application.

[0128] In an exemplary embodiment, a computer program product is also provided, which, when executed by an electronic device, enables the electronic device to implement any of the exemplary methods provided in this application.

[0129] Furthermore, computer program products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] The program product used for establishing the business model in the embodiments of this application may be a CD-ROM and include program code, and may run on a computing device. However, the program product of this application is not limited to this. In this document, the readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0131] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0132] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, radio frequency (RF), or any suitable combination thereof.

[0133] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0134] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0135] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0136] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0137] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0138] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0139] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0140] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0141] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for establishing a business model, characterized in that, include: In response to a template viewing request, business description information of at least one model template that matches the business type information in the template viewing request is displayed. The business type information is determined according to business requirements, and each model template corresponds to a type of business, which is used to provide a general model for this type of business. The business description information of the model template is used to show which type of business the model template processes and what kind of business result it obtains. In response to a template configuration request triggered based on the business description information, the system displays configuration options for various training resources that the target model template can use, including data sources, data features, model structures, and model algorithms. In response to a resource configuration request triggered based on the configuration options, the target training resources actually used by the target model template are configured, wherein each type of training resource customized by business personnel is supported; the target training resources include at least one target data source, multiple target data features, one target model structure, and at least one target model algorithm; the target data features are fields used to determine the field content of the corresponding field in the target data source; during the configuration of the target training resources, business personnel select or derive new data features from the large wide table dataset that has completed data preprocessing based on business knowledge; In response to a model training request, the model is trained based on the configured target training resources to obtain a business model; When the output of the business model does not match the business requirements, the target training resources actually used by the target model template are reconfigured and retrained. When the output of the business model matches the business requirements, more training samples are obtained for training.

2. The method as described in claim 1, characterized in that, Based on the configured target training resources, a model is trained to obtain a business model, including: Obtain the target data source that the target model template can use, and obtain the business annotation data of the target model template; Determine the feature content of the target data features that the target model template in the target data source can use; The business model is obtained by training using the feature content of the target data features, the business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

3. The method as described in claim 2, characterized in that, If there are at least two target model algorithms, then the business model is obtained by training using the feature content of the target data features, the business annotation data, and the target model structure and target model algorithm that the target model template can use, including: A candidate business model is obtained by training using the feature content of the target data features, the business annotation data, the target model structure, and each target model algorithm. The candidate business models are evaluated based on the algorithm evaluation metrics corresponding to the target model algorithm. Based on the evaluation results of each alternative business model, one alternative business model is selected as the business model.

4. The method according to any one of claims 1 to 3, characterized in that, After obtaining a business model, the following is also included: Obtain business feedback information corresponding to the business model after deployment, wherein the business feedback information is used to characterize the business processing capability of the business model; Based on the business feedback information, determine the business processing capabilities of the business model; If it is determined that the business processing capacity exceeds the preset standard, then based on the target training resources, update the various training resources that the target model template can use.

5. A business model establishment apparatus, characterized in that, include: The information display module is used to respond to a template viewing request and display the business description information of at least one model template that matches the business type information in the template viewing request. The business type information is determined according to business requirements, and each model template corresponds to a type of business, which is used to provide a general model for this type of business. The business description information of the model template is used to show which type of business the model template processes and what kind of business result it obtains. The resource display module is used to respond to a template configuration request triggered based on the business description information and display the configuration options of various training resources that the target model template can use. The various training resources include data sources, data features, model structures, and model algorithms. The configuration module is used to configure the target training resources actually used by the target model template in response to a resource configuration request triggered based on the configuration options. It supports the introduction of various training resources customized by business personnel. The target training resources include at least one target data source, multiple target data features, one target model structure, and at least one target model algorithm. The target data features are fields used to determine the content of corresponding fields in the target data source. During the configuration of the target training resources, business personnel select or derive new data features from a large, preprocessed wide-table dataset based on their business knowledge. The training module is used to respond to a model training request, train the model based on the configured target training resources, and obtain a business model. When the output of the business model does not match the business requirements, the target training resources actually used by the target model template are reconfigured and retrained. When the output of the business model matches the business requirements, more training samples are obtained for training.

6. The apparatus as claimed in claim 5, characterized in that, The training module is specifically used for: Obtain the target data source that the target model template can use, and obtain the business annotation data of the target model template; Determine the feature content of the target data features that the target model template in the target data source can use; The business model is obtained by training using the feature content of the target data features, the business labeled data, and the target model structure and target model algorithm that can be used by the target model template.

7. The apparatus as claimed in claim 6, characterized in that, If there are at least two target model algorithms, then the training module is specifically used for: A candidate business model is obtained by training using the feature content of the target data features, the business annotation data, the target model structure, and each target model algorithm. The candidate business models are evaluated based on the algorithm evaluation metrics corresponding to the target model algorithm. Based on the evaluation results of each alternative business model, one alternative business model is selected as the business model.

8. The apparatus according to any one of claims 5-7, characterized in that, Also includes: The acquisition module is used to acquire business feedback information corresponding to the business model after it is deployed, after obtaining a business model. The business feedback information is used to characterize the business processing capability of the business model. The determination module is used to determine the business processing capability of the business model based on the business feedback information. An update module is used to update the various training resources that the target model template can use based on the target training resources if it is determined that the business processing capacity exceeds a preset standard.

9. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to said at least one processor, wherein: The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1-4.

10. A storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-4.

Images