Model training method and apparatus, device, storage medium, and program product

Abstract

The present disclosure provides a model training method and device, equipment, a storage medium and a program product, relating to the technical field of artificial intelligence, in particular to the technical field of deep learning. A specific embodiment of the method includes: obtaining a training sample, wherein the training sample includes sample data and a true value label; taking the sample data as input and the true value label as output, training a machine learning model integrated with feature engineering to obtain a target model, wherein the feature engineering is used for feature selection, feature extraction and feature construction on the input. This embodiment integrates feature engineering into the model training, only needs to maintain the model training part integrated with feature engineering, greatly improves the iteration efficiency of the model, and promotes the rapid development of business.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of deep learning. BACKGROUND

[0002] At present, the general process of machine learning application is composed of problem definition, sample collection, feature engineering, model training and model application. Generally, feature engineering and model training are two independent processes. The training sample is first processed by feature engineering, and then is uniformly input into the machine learning model for training. The whole model training process is loose in structure, which is not conducive to rapid iteration. SUMMARY

[0003] Embodiments of the present disclosure provide a model training method, device, equipment, storage medium and program product.

[0004] In a first aspect, embodiments of the present disclosure provide a model training method, comprising: obtaining a training sample, wherein the training sample comprises sample data and a true value label; training a machine learning model integrated with feature engineering, by taking the sample data as input and the true value label as output, to obtain a target model, wherein the feature engineering is used for feature selection, feature extraction and feature construction on the input.

[0005] In a second aspect, embodiments of the present disclosure provide a model application method, comprising: obtaining to-be-predicted data; inputting the to-be-predicted data into a pre-trained target model to obtain a prediction value of the to-be-predicted data, wherein the target model is trained by the method described in the first aspect.

[0006] In a third aspect, embodiments of the present disclosure provide a model training device, comprising: an obtaining module configured to obtain a training sample, wherein the training sample comprises sample data and a true value label; and a training module configured to train a machine learning model integrated with feature engineering, by taking the sample data as input and the true value label as output, to obtain a target model, wherein the feature engineering is used for feature selection, feature extraction and feature construction on the input.

[0007] In a fourth aspect, embodiments of the present disclosure provide a model application device, comprising: an obtaining module configured to obtain to-be-predicted data; and a prediction module configured to input the to-be-predicted data into a pre-trained target model to obtain a prediction value of the to-be-predicted data, wherein the target model is trained by the device described in the third aspect.

[0008] In a fifth aspect, an electronic device is provided, including: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any implementation manner of the first aspect or the second aspect.

[0009] In a sixth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to enable a computer to perform the method according to any implementation manner of the first aspect or the second aspect.

[0010] In a seventh aspect, a computer program product is provided, including a computer program, and the computer program, when executed by a processor, implements the method according to any implementation manner of the first aspect or the second aspect.

[0011] The model training method provided by the embodiments of the present disclosure integrates feature engineering into the model training process, and only the model training part needs to be maintained, which greatly improves the iteration efficiency of the model and promotes the rapid development of the business.

[0012] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0014] Figure 1 is a flowchart of some embodiments of the model training method according to the present disclosure;

[0015] Figure 2 is a flowchart of still some embodiments of the model training method according to the present disclosure;

[0016] Figure 3 is a flowchart of some embodiments of the model application method according to the present disclosure;

[0017] Figure 4 is a scene diagram of the model training method and the model application method that can implement the embodiments of the present disclosure;

[0018] Figure 5 is a structural schematic diagram of some embodiments of the model training device according to the present disclosure;

[0019] Figure 6is a structural schematic diagram of some embodiments of a model application device according to the present disclosure;

[0020] Figure 7 is a block diagram of an electronic device for implementing a model training method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of embodiments of the present disclosure by a person of ordinary skill in the art, and should not be construed as limiting the present disclosure. Accordingly, those of ordinary skill in the art will recognize that modifications and other equivalents can be used without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0022] It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1 Flow 100 of some embodiments of a model training method according to the present disclosure is shown. The model training method comprises the following steps:

[0024] Step 101, obtaining training samples.

[0025] In the present embodiment, the execution subject of the model training method can obtain a large number of training samples. The training samples can include sample data and true value labels. The sample data can include, but is not limited to, at least one of the following: text, audio, image, etc.

[0026] At present, the general process of machine learning application is composed of five parts: problem definition, sample collection, feature engineering, model training and model application. The problem definition can be a clear definition of the problem to be solved. Sample collection can be sample data collection and true value labeling for the problem to be solved.

[0027] Step 102, taking the sample data as input and the true value label as output, training the machine learning model with integrated feature engineering to obtain a target model.

[0028] In the present embodiment, the execution subject described above can take the sample data as input and the true value label as output, train the machine learning model with integrated feature engineering to obtain a target model.

[0029] The feature engineering can be used for feature selection, feature extraction and feature construction of the input. Here, the feature engineering is integrated into the model training, so that the sample data can be directly input into the machine learning model integrated with the feature engineering. Since the sample data input into the machine learning model integrated with the feature engineering contains all the features, there is no need to perform feature adaptation during model training. Since the model training part integrates the feature engineering, the feature processing method does not need to be additionally implemented, and only needs to maintain the model training part integrated with the feature engineering. Even if the features are changed, there is no need to re-collect samples and adjust the model structure, and only the feature corresponding method needs to be processed from the feature engineering integrated in the machine learning model.

[0030] Here, the target model can be obtained by using a machine learning method and training samples to perform supervised training on a machine learning model. In practice, each parameter (e.g., a weight parameter and a bias parameter) of the machine learning model can be initialized with some different small random numbers. The "small random numbers" are used to ensure that the model does not enter a saturated state due to excessively large weights, thereby causing training failure, and the "different" is used to ensure that the model can normally learn. The parameters of the machine learning model can be continuously adjusted during the training process until a target model with better effect is trained. For example, a BP (BackPropagation, back propagation) algorithm or an SGD (Stochastic Gradient Descent, stochastic gradient descent) algorithm can be used to adjust the parameters of the machine learning model.

[0031] The model training method provided by the embodiments of the present disclosure integrates the feature engineering into the model training, does not need to separately maintain the sample collection and feature engineering part, and only needs to maintain the model training part, which greatly reduces the workload of model iteration and maintenance, thereby greatly improving the iteration efficiency of the model, promoting the rapid development of the business, and can be applied to various machine learning recommendation and prediction services in the map travel assistant. Integrating the feature engineering into the model training part makes the originally loose two modules closely related, strengthens the cohesion of the machine learning application process, and at the same time reduces the coupling of the overall structure. The sample collection only needs to ensure that the original data is provided, and does not need to be continuously modified along with the model training.

[0032] With reference to Figure 2 which shows the flow 200 of still another embodiment of the model training method according to the present disclosure. The model training method includes the following steps:

[0033] In step 201, a training sample is obtained.

[0034] In this embodiment, the specific operation of step 201 has been described in Figure 1The step 101 in the embodiment shown is described in detail, and will not be repeated here.

[0035] Step 202, input the sample data into the machine learning model integrated with feature engineering.

[0036] In this embodiment, the model training method can input the sample data into the machine learning model integrated with feature engineering. That is, the sample data provided by the sample collection is directly input into the machine learning model integrated with feature engineering, without the need for separate feature engineering to process first.

[0037] Step 203, based on the first feature selection information of feature engineering, extract the first feature from the sample data.

[0038] In this embodiment, the above execution subject can extract the first feature from the sample data based on the first feature selection information of feature engineering.

[0039] Among them, feature selection can be performed through feature engineering to obtain the information of the selected features, that is, the first feature selection information. Then the first feature corresponding to the first feature selection information can be extracted from the sample data.

[0040] Step 204, using the feature processing method and feature construction method corresponding to the first feature in feature engineering to process and construct the first feature, to obtain the first sample feature.

[0041] In this embodiment, the above execution subject can use the feature processing method and feature construction method corresponding to the first feature in feature engineering to process and construct the first feature, to obtain the first sample feature.

[0042] Among them, the feature processing method and feature construction method corresponding to each type of feature are stored in the feature engineering. Here, the first feature can be processed using the feature processing method corresponding to the first feature. Then, using the construction method corresponding to the first feature for construction, the first sample feature in the specified format can be obtained.

[0043] Since the sample data is input into the machine learning model integrated with feature engineering, it contains all features, so there is no need to perform feature adaptation during model training. Since the model training part integrates feature engineering, the feature processing method does not need to be implemented additionally, only the feature construction needs to be performed along with the model training part, and only the model training part of the integrated feature engineering needs to be maintained. Even if the features are changed, there is no need to collect samples and adjust the model structure again, but only to select the feature processing method from the feature engineering integrated in the machine learning model.

[0044] Step 205, train the machine learning model by taking the first sample feature as input and the true value label as output, to obtain the target model.

[0045] In this embodiment, the aforementioned execution entity can use the first sample features as input and the truth label as output to train the machine learning model and obtain the target model.

[0046] Here, the target model can be obtained by supervised training of a machine learning model using machine learning methods and training samples. The parameters of the machine learning model can be continuously adjusted during training until a target model with good performance is obtained. For example, the backpropagation (BP) algorithm or the SGD algorithm can be used to adjust the parameters of the machine learning model.

[0047] Step 206: Input the sample data into the target model.

[0048] In this embodiment, the aforementioned execution entity can input sample data into the target model.

[0049] Typically, the performance of a target model deteriorates over time, necessitating optimization. Here, the collected sample data can be re-input into the target model.

[0050] Step 207: Extract the second feature from the sample data based on the second feature selection information from feature engineering.

[0051] In this embodiment, the aforementioned execution entity can extract the second feature from the sample data based on the second feature selection information of feature engineering.

[0052] Feature engineering allows for feature selection, yielding information about the desired features, known here as the second feature selection information. Then, a second feature corresponding to this second feature selection information can be extracted from the sample data. This second feature information is typically different from the first feature information; therefore, the second feature is distinct from the first feature.

[0053] Step 208: Use the feature processing method and feature construction method corresponding to the second feature in feature engineering to process and construct the second feature to obtain the second sample feature.

[0054] In this embodiment, the aforementioned execution entity can use the feature processing method and feature construction method corresponding to the second feature in feature engineering to process and construct the second feature to obtain the second sample feature.

[0055] The feature engineering section stores feature processing methods and feature construction methods corresponding to various features. Here, the feature processing method corresponding to the second feature can be used to process the second feature. Subsequently, the construction method corresponding to the second feature can be used to construct the second sample feature in the specified format.

[0056] Since the machine learning model to which the integrated feature engineering is input is sample data, it contains all features, so there is no need to perform feature adaptation when optimizing the model. Since the model training part integrates feature engineering, the feature processing method does not need to be implemented additionally, only the feature construction needs to be performed along with the model training part, and only the model training part of the integrated feature engineering needs to be maintained. Even if the features change, there is no need to collect samples and adjust the model structure again, only the feature corresponding method needs to be processed from the feature engineering integrated in the machine learning model.

[0057] Step 209, taking the second sample feature as input and the true value label as output, optimizing the target model.

[0058] In the embodiment, the execution subject described above can take the second sample feature as input and the true value label as output, optimize the target model, and improve the effect of the target model.

[0059] Here, the parameters of the target model can be continuously adjusted in the optimization process until the target model with better effect is optimized.

[0060] As can be seen from Figure 2 , compared with the embodiment corresponding to Figure 1 , the model training method in the embodiment highlights the model training step and the model optimization step. Therefore, the scheme described in the embodiment integrates feature engineering into the model training, and the machine learning model to which the integrated feature engineering is input is sample data, which contains all features. Therefore, there is no need to perform feature adaptation when training or optimizing the model, and the feature processing method does not need to be implemented additionally. Only the feature construction needs to be performed along with the model training part, and only the model training part of the integrated feature engineering needs to be maintained. Even if the features change when the model is optimized, there is no need to collect samples and adjust the model structure again, only the feature corresponding method needs to be processed from the feature engineering integrated in the machine learning model, thereby improving the model iteration efficiency.

[0061] Further referring to Figure 3 , which shows the flow 300 of some embodiments of the model application method according to the present disclosure. The model application method comprises the following steps:

[0062] Step 301, obtaining to-be-predicted data.

[0063] In the embodiment, the execution subject of the model application method can obtain to-be-predicted data.

[0064] The to-be-predicted data can be data related to information that needs to be predicted, including but not limited to at least one of the following: text, audio, image, etc. For example, if a store needs to be recommended to a user, the user's current location information and user portrait can be obtained for prediction.

[0065] Step 302, input the data to be predicted into the pre-trained target model to obtain the predicted value of the data to be predicted.

[0066] In the embodiment, the execution subject can input the data to be predicted into the pre-trained target model to obtain the predicted value of the data to be predicted.

[0067] The target model can be trained by an embodiment of the method shown in Figure 1 or Figure 2 for making relevant predictions based on data.

[0068] The model application method provided in the embodiments of the present disclosure integrates feature engineering into the target model, and applies the model to the need to update the latest version of the model, without the need to adapt to the feature processing method.

[0069] In order to facilitate understanding, Figure 4 a scene diagram of the model training method and the model application method that can implement the embodiments of the present disclosure is shown. As Figure 4 shown, first, the problem to be solved is defined; then, samples are collected for the problem to be solved; then, the machine learning model integrated with feature engineering is trained using the collected samples, and the features can be changed for model optimization during the training process; finally, the model is applied to solve the problem.

[0070] Further reference Figure 5 , as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a model training device, which device embodiments correspond to the method embodiments shown in Figure 1 , and the device can be applied in various electronic devices.

[0071] As Figure 5 shown, the model training device 500 of the embodiment can include an acquisition module 501 and a training module 502. The acquisition module 501 is configured to acquire training samples, wherein the training samples include sample data and true value labels; the training module 502 is configured to train a machine learning model integrated with feature engineering by taking the sample data as input and the true value labels as output, to obtain a target model, wherein the feature engineering is used for feature selection, feature extraction and feature construction on the input.

[0072] In the embodiment, in the model training device 500: the specific processing of the acquisition module 501 and the training module 502 and the technical effects brought by the specific processing can be respectively referred to the related descriptions of steps 101-102 in the corresponding embodiments, which will not be repeated here. Figure 1

[0073] ​In some optional implementation forms of the embodiment, the training module 502 is further configured to: input the sample data into the machine learning model integrated with the feature engineering; extract the first features from the sample data based on the first feature selection information of the feature engineering; process and construct the first features by using the feature processing method and the feature construction method corresponding to the first features in the feature engineering, to obtain first sample features; train the machine learning model by taking the first sample features as input and taking the true value label as output, to obtain the target model.

[0074] In some optional implementation forms of the embodiment, the model training apparatus 500 further comprises an optimization module configured to: input the sample data into the target model; extract the second features from the sample data based on the second feature selection information of the feature engineering; process and construct the second features by using the feature processing method and the feature construction method corresponding to the second features in the feature engineering, to obtain second sample features; optimize the target model by taking the second sample features as input and taking the true value label as output.

[0075] In some optional implementation forms of the embodiment, the sample data comprises at least one of the following: text, audio, and image.

[0076] Further referring to Figure 6 , as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a model application apparatus, which corresponds to the method embodiments shown in Figure 3 , and the apparatus can be applied in various electronic devices.

[0077] As shown in Figure 6 , the model application apparatus 600 of the embodiment can comprise an acquisition module 601 and a prediction module 602. The acquisition module 601 is configured to acquire to-be-predicted data, and the prediction module 602 is configured to input the to-be-predicted data into a pre-trained target model to obtain a prediction value of the to-be-predicted data, wherein the target model is obtained by training the apparatus shown in Figure 5 .

[0078] In the embodiment, in the model application apparatus 600: the specific processes of the acquisition module 601 and the prediction module 602 and the technical effects brought by the specific processes can be respectively referred to the related descriptions of steps 301-302 in the corresponding embodiments, which will not be repeated here. Figure 3

[0079] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution all comply with the relevant legal regulations and do not violate public order and good customs.

[0080] ​According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0081] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0082] As shown, Figure 7 the device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded into a random access memory (RAM) 703 from a storage unit 708. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0083] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; the storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0084] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the model training method. For example, in some embodiments, the model training method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the model training method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the model training method by any other appropriate means, such as by means of firmware.

[0085] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0086] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine or entirely on a remote machine or server.

[0087] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0089] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0090] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0091] It should be understood that the various forms of flow shown above can be used to reorder, add, or delete steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions provided by the present disclosure can be achieved, which is not limited herein.

[0092] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A model training method, comprising: Obtain training samples, which include sample data and ground truth labels. The sample data includes at least one of the following: text, audio, and image. The sample data is used as input and the true value label is used as output to train the machine learning model with integrated feature engineering to obtain the target model. The feature engineering is integrated into the model training and is used to perform feature selection, feature extraction and feature construction on the input. The step of using the sample data as input and the ground truth labels as output to train the integrated feature engineering machine learning model to obtain the target model includes: The sample data is input into the machine learning model of the integrated feature engineering; Based on the first feature selection information of the feature engineering, a first feature is extracted from the sample data; The first feature is processed and constructed using the feature processing method and feature construction method corresponding to the first feature in the feature engineering to obtain the first sample feature; The first sample features are used as input, and the true value label is used as output to train the machine learning model to obtain the target model; The method further includes: inputting the sample data into the target model; Based on the second feature selection information of the feature engineering, a second feature is extracted from the sample data; The second feature is processed and constructed using the feature processing method and feature construction method corresponding to the second feature in the feature engineering to obtain the second sample feature; The target model is optimized by taking the second sample features as input and the true value label as output.

2. A method for applying a model, comprising: Obtain the data to be predicted; The data to be predicted is input into a pre-trained target model to obtain a predicted value for the data to be predicted, wherein the target model is trained using the method described in claim 1.

3. A model training device, comprising: The acquisition module is configured to acquire training samples, the training samples including sample data and ground truth labels, the sample data including at least one of the following: text, audio, and image; The training module is configured to take the sample data as input and the ground truth labels as output to train the machine learning model with integrated feature engineering to obtain the target model. The feature engineering is integrated into the model training and is used to perform feature selection, feature extraction and feature construction on the input. The training module is further configured to: The sample data is input into the machine learning model of the integrated feature engineering; Based on the first feature selection information of the feature engineering, a first feature is extracted from the sample data; The first feature is processed and constructed using the feature processing method and feature construction method corresponding to the first feature in the feature engineering to obtain the first sample feature; The first sample features are used as input, and the true value label is used as output to train the machine learning model to obtain the target model; The device also includes an optimization module configured to: The sample data is input into the target model; Based on the second feature selection information of the feature engineering, a second feature is extracted from the sample data; The second feature is processed and constructed using the feature processing method and feature construction method corresponding to the second feature in the feature engineering to obtain the second sample feature; The target model is optimized by taking the second sample features as input and the true value label as output.

4. A model application device, comprising: The acquisition module is configured to acquire the data to be predicted. The prediction module is configured to input the data to be predicted into a pre-trained target model to obtain a predicted value of the data to be predicted, wherein the target model is trained using the apparatus of claim 3.

5. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the 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 of claim 1 or 2.

6. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of claim 1 or 2.

7. A computer program product comprising a computer program that, when executed by a processor, implements the method according to claim 1 or 2.

Images