Template-based training method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure provide a template-based training method and apparatus, a device, and a storage medium. The method comprises: receiving a selection of a first training template published by a publisher; displaying a training configuration interface, the training configuration interface comprising a group of parameter configuration controls, wherein the group of parameter configuration controls is used for configuring a first group of parameters in a parameter set, and the first group of parameters is determined on the basis of a configuration operation of the publisher; acquiring, by means of the group of parameter configuration controls, first parameter information about the first group of parameters; and fine-tuning a target model at least on the basis of an acquired group of training samples and the first parameter information.

Description

Template-based training methods, apparatus, devices, and storage media

[0001] This application claims priority to Chinese Patent Application No. 202411217773.5, filed on August 30, 2024, entitled "Template-based training method, apparatus, device and storage medium", the entire contents of which are incorporated herein by reference. Technical Field

[0002] The exemplary embodiments disclosed herein relate generally to the field of computers, and more particularly to template-based training methods, apparatus, devices, and computer-readable storage media. Background Technology

[0003] With the rapid development of generative artificial intelligence technology, people can obtain the desired optimized model by fine-tuning the base model. For example, people can fine-tune the image generation model with a small number of image samples so that the image generation model can generate images of a corresponding style. Summary of the Invention

[0004] In a first aspect of this disclosure, a template-based training method is provided. The method includes: receiving a selection of a first training template published by a publisher; displaying a training configuration interface including a set of parameter configuration controls for configuring a first set of parameters in a parameter set, the first set of parameters being determined based on configuration operations by the publisher; obtaining first parameter information about the first set of parameters via the set of parameter configuration controls; and fine-tuning a target model based at least on the obtained set of training samples and the first parameter information.

[0005] In a second aspect of this disclosure, an apparatus for template-based training is provided. The apparatus includes: a receiving module configured to receive a selection of a first training template published by a publisher; a display module configured to display a training configuration interface including a set of parameter configuration controls for configuring a first set of parameters in a parameter set, the first set of parameters being determined based on a configuration operation by the publisher; an acquisition module configured to acquire first parameter information about the first set of parameters via the set of parameter configuration controls; and a fine-tuning module configured to fine-tune a target model based at least on the acquired set of training samples and the first parameter information.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 shows a schematic diagram of an interface according to some embodiments of the present disclosure;

[0013] Figures 3A and 3B show schematic diagrams of interfaces according to some embodiments of the present disclosure;

[0014] Figure 4 illustrates a flowchart of a template-based training process according to some embodiments of the present disclosure;

[0015] Figure 5 shows a schematic structural block diagram of a template-based training apparatus according to certain embodiments of the present disclosure;

[0016] Figure 6 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0020] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0021] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0022] As discussed above, image generation models can be fine-tuned using a small number of image samples to enable them to generate images in a corresponding style. However, for most users, fine-tuning the model usually requires configuring a large number of parameters, which necessitates a thorough understanding of the relevant knowledge, making it difficult for some users to independently complete the model fine-tuning process.

[0023] Embodiments of this disclosure propose a template-based training scheme. According to this scheme, the selection of a first training template published by a publisher can be received; a training configuration interface can be displayed, the training configuration interface including a set of parameter configuration controls, wherein the set of parameter configuration controls is used to configure a first set of parameters in a parameter set, the first set of parameters being determined based on the publisher's configuration operation; first parameter information about the first set of parameters can be obtained via the set of parameter configuration controls; and the target model can be fine-tuned based at least on the obtained set of training samples and the first parameter information.

[0024] In this way, embodiments of this disclosure can configure model parameters by using published training templates, thereby reducing the learning cost of the model fine-tuning process and improving model quality.

[0025] Example Environment

[0026] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0027] In this example environment 100, an application 120 is installed on an electronic device 110. A user 140 can interact with the application 120 via the electronic device 110 and / or its attached devices. The application 120 can be a template-based training application, or any other suitable application. For example, the application 120 could be a browser that provides template-based training services by accessing a website.

[0028] In environment 100 of Figure 1, if application 120 is active, application 120 can provide a display interface 150 for user 140. User 140 can perform template-based training operations based on interface 150.

[0029] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0030] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support content display in electronic devices 110.

[0031] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus, and Wi-Fi connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0033] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0034] Creating training templates

[0035] The following description of an example process for creating a training template will refer to FIG2. FIG2 illustrates a template creation interface 200 according to some embodiments of the present disclosure, which may be provided, for example, by the electronic device 110 shown in FIG1.

[0036] As shown in Figure 2, the electronic device 110 can receive the template creation request from the publisher and display the interface 200 shown in Figure 2.

[0037] As shown in the figure, the electronic device 110 can edit the name of the training template to be created via the control 205. Additionally, the electronic device 110 can also provide a cover editing control 210, which allows the publisher to configure the cover image of the template.

[0038] Additionally, the electronic device 110 may also provide a brief configuration control 215 to obtain descriptive information about the template from the publisher.

[0039] In some embodiments, the training template may be associated with an image generation model. Accordingly, the electronic device 10 may also acquire guide images uploaded by the publisher via the interface 200, such as guide image 220 and guide image 225. Such guide image 220 and guide image 225 may also be referred to as example samples.

[0040] Additionally, the electronic device 110 can also receive sample descriptions of the guide image 220 and guide image 225 from the publisher. Such sample descriptions can be used to indicate whether the corresponding guide image 220 and guide image 225 are positive or negative samples.

[0041] Additionally, such sample descriptions can also indicate other appropriate descriptive information to help users of the training template understand what kind of images should be used to effectively perform the model fine-tuning process.

[0042] Additionally, the electronic device 110 can also support users to upload training image sets via interface 200, which may include, for example, multiple image samples 230.

[0043] Furthermore, the electronic device 110 can also support user configuration of one or more template parameters associated with the training template.

[0044] In some examples, such template parameters can indicate training mode 235 to indicate training mode for small samples, such as LoRA (Low-Rank Adaptation), etc.

[0045] In some examples, such template parameters can also indicate the base model to be trained, such as a specific version of the image generation model.

[0046] Referring again to Figure 2, the electronic device 110 can, for example, allow the publisher to upload training parameters via control 245. Alternatively, the electronic device 110 can also allow the user to manually set training parameters via control 250. As an example, such training parameters may include whether to enable the ARB bucket, regularization-prior loss weights, etc.

[0047] Additionally, the template parameters can also indicate the prompt word 255 corresponding to the fine-tuned model. As an example, when the prompt word entered by the user includes this prompt word, the corresponding model will be enabled to perform the corresponding image generation task.

[0048] In some embodiments, the electronic device 110 may also support users configuring the visibility of template parameters via control 260. In some examples, the electronic device 110 may, for instance, allow the publisher to expose all parameter configurations to the template user, enabling the user to adjust the parameters. Alternatively, the electronic device 110 may expose only some parameters to the template user based on the publisher's configuration operation. As another example, the electronic device 110 may, for instance, not expose any parameters to the template user based on the publisher's configuration operation.

[0049] After the template parameters are set, the electronic device 110 can receive the publisher's selection of the publishing control 265 and create a corresponding training template. This training template can then be obtained and used by other appropriate users.

[0050] Use of training templates

[0051] The process of fine-tuning a model using a training template according to embodiments of the present disclosure will now be described with reference to Figures 3A and 3B. Figures 3A and 3B illustrate example interfaces 300A to 300B according to some embodiments of the present disclosure, which may be provided, for example, by the electronic device 110 shown in Figure 1. It should be understood that the electronic device 110 providing interfaces 300A to 300B may be the same as or different from the electronic device providing interface 200.

[0052] As shown in Figure 3A, the electronic device 110 can display a template list. This template list may include a set of training templates, such as training template 305, training template 310, and training target 315.

[0053] As shown in Figure 3A, the electronic device 110 can display identification information for each training template in the template list, such as text identifiers (titles of training templates) and / or image identifiers (cover images of training targets). Additionally, the electronic device 110 can also display descriptive information for each training template in the template list. In some embodiments, such identification and descriptive information can be configured by the corresponding publisher via the template creation interface described above.

[0054] Additionally, as shown in Figure 3A, the electronic device 110 can also display the publishing information of each training template, such as the name and avatar of the publisher, the publishing time, etc.

[0055] Furthermore, the electronic device 110 may, for example, receive a user's selection of a training template 305. This training template 305 may, for example, be created by the publisher via the creation interface 200 described above.

[0056] Accordingly, the electronic device 110 can display the training configuration interface 300B as shown in FIG3B. As shown in FIG3B, the training configuration interface 300B may include one or more parameter configuration controls, such as configuration control 320 and configuration control 325.

[0057] In some embodiments, such configuration controls 320 and 325 can be used to configure a first set of parameters in the complete set of parameters associated with the training process, such as evoked words and training modes.

[0058] In some embodiments, which parameters can be configured via the training configuration interface 300B is configured by the publisher via the template creation interface. For example, in response to the publisher setting the parameters "provocation word" and "training mode" as user-visible parameters, the training configuration interface 300B can provide configuration controls for configuring these two parameters.

[0059] Additionally, configuration controls 320 and 325 can also display initial parameter information for the parameters "provocation word" and "training mode". In some embodiments, such initial parameter information is configured by the publisher.

[0060] For example, as shown in Figure 3B, the initial trigger words and initial training modes displayed by configuration controls 320 and 325 can be the same as the parameter values ​​configured in the template creation interface shown in Figure 2.

[0061] In some embodiments, as mentioned above, the complete set of parameters associated with the training process may also include one or more other parameters, such as the base model, training parameters, etc.

[0062] In some embodiments, because the publisher sets one or more such parameters to be invisible during the template creation process, users of the target will not be able to modify such parameters through the training configuration process.

[0063] In some embodiments, the electronic device 110 can obtain first parameter information about the parameters "provocation word" and "training mode" via configuration controls 320 and 325. For example, a user can adjust the provocation word or training mode via configuration controls 320 or 325.

[0064] In some embodiments, the electronic device 110 can also acquire training samples for fine-tuning the model via the training configuration interface 300B. As an example, the electronic device 110 can acquire user-uploaded samples via the upload control 330 and display such samples 335 in the training configuration interface 300B.

[0065] In some embodiments, in order to improve the efficiency of users selecting training samples, the electronic device 110 may also display a set of example samples and corresponding sample descriptions configured by the publisher in the training configuration interface 300B.

[0066] Taking Figure 3B as an example, the electronic device 110 can display a guide diagram configured by the publisher, such as a positive guide diagram 340 and corresponding explanatory information 345, and a negative guide diagram 350 and corresponding explanatory information 355.

[0067] Therefore, the embodiments of this disclosure can help users better determine which type of image should be uploaded to achieve fine-tuning of the image generation model.

[0068] Furthermore, after obtaining the training samples and the parameter information to be configured, the electronic device 110 can receive the selection of the training button 360 to trigger fine-tuning of the target model based at least on the received training samples and the configured parameter information.

[0069] In some embodiments, for other parameters not disclosed through the training configuration interface 300B (also referred to as the second set of parameters), the electronic device 110 can obtain the second parameter information configured by the publisher. Accordingly, the electronic device 110 can fine-tune the target model (e.g., an image generation model) based on the first parameter information, the second parameter information, and the received training samples.

[0070] In this way, embodiments of this disclosure can configure model parameters by using published training templates, thereby reducing the learning cost of the model fine-tuning process and improving the quality of the optimized model.

[0071] Example process

[0072] Figure 4 shows a flowchart of a template-based training process 400 according to some embodiments of the present disclosure. Process 400 can be implemented at electronic device 110. Process 400 is described below with reference to Figure 1.

[0073] In box 410, electronic device 110 receives a selection of a first training template published by the publisher.

[0074] In box 420, electronic device 110 displays a training configuration interface, which includes a set of parameter configuration controls. The set of parameter configuration controls is used to configure the first set of parameters in the parameter set, which is determined based on the publisher's configuration operation.

[0075] In box 430, electronic device 110 obtains first parameter information about the first set of parameters via a set of parameter configuration controls.

[0076] In box 440, electronic device 110 fine-tunes the target model based at least on a set of acquired training samples and first parameter information.

[0077] In some embodiments, the parameter set also includes a second set of parameters, which are not displayed in the training configuration interface.

[0078] In some embodiments, the target model is further fine-tuned based on second parameter information of the second set of parameters, which is configured by the publisher.

[0079] In some embodiments, a set of parameter configuration controls displays initial parameter information about a first set of parameters, which is determined based on the publisher's configuration operations.

[0080] In some embodiments, process 400 further includes: in response to a received publication request, creating a second training template corresponding to the first parameter information.

[0081] In some embodiments, receiving a selection of a first training template published by a publisher includes: displaying a template list, the target list including a set of candidate training templates, the target list displaying template information of the set of candidate training templates; and receiving a selection of the first training template in the target list.

[0082] In some embodiments, the target information indicates at least one of the following: identification information of the candidate training template; description information of the candidate training template; and publication information of the candidate training template.

[0083] In some embodiments, the identification information and / or description information are determined based on the configuration operations of the corresponding publisher.

[0084] In some embodiments, process 400 further includes: displaying a set of example samples and corresponding sample descriptions configured by the publisher in the training configuration interface; and obtaining a set of training samples via the training configuration interface.

[0085] In some embodiments, the sample description is used to indicate whether the corresponding example sample is a positive sample or a negative sample.

[0086] Example devices and equipment

[0087] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 5 shows a schematic structural block diagram of a template-based training apparatus 500 according to certain embodiments of this disclosure. Apparatus 500 may be implemented as or included in the electronic device 110 discussed above. The various modules / components in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0088] As shown in Figure 5, the device 500 includes a receiving module 510 configured to receive a selection of a first training template published by a publisher; a display module 520 configured to display a training configuration interface, the training configuration interface including a set of parameter configuration controls, wherein the set of parameter configuration controls is used to configure a first set of parameters in a parameter set, the first set of parameters being determined based on the publisher's configuration operation; an acquisition module 530 configured to acquire first parameter information about the first set of parameters via the set of parameter configuration controls; and a fine-tuning module 540 configured to fine-tune the target model based at least on the acquired set of training samples and the first parameter information.

[0089] In some embodiments, the parameter set also includes a second set of parameters, which are not displayed in the training configuration interface.

[0090] In some embodiments, the target model is further fine-tuned based on second parameter information of the second set of parameters, which is configured by the publisher.

[0091] In some embodiments, a set of parameter configuration controls displays initial parameter information about a first set of parameters, which is determined based on the publisher's configuration operations.

[0092] In some embodiments, the apparatus 500 further includes a creation module configured to create a second training template corresponding to the first parameter information in response to a received publishing request.

[0093] In some embodiments, the receiving module 510 is further configured to display a template list, the target list including a set of candidate training templates, the target list displaying template information of a set of candidate training templates; and to receive a selection of a first training template in the target list.

[0094] In some embodiments, the target information indicates at least one of the following: identification information of the candidate training template; description information of the candidate training template; and publication information of the candidate training template.

[0095] In some embodiments, the identification information and / or description information are determined based on the configuration operations of the corresponding publisher.

[0096] In some embodiments, the apparatus 500 further includes a processing module configured to display a set of example samples and corresponding sample descriptions configured by the publisher in a training configuration interface; and to obtain a set of training samples via the training configuration interface.

[0097] In some embodiments, the sample description is used to indicate whether the corresponding example sample is a positive sample or a negative sample.

[0098] The units included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 500 may be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0099] Figure 6 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 600 shown in Figure 6 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 600 shown in Figure 6 can be used to implement the electronic device 110 shown in Figure 1.

[0100] As shown in Figure 6, the electronic device 600 is in the form of a general-purpose electronic device. Components of the electronic device 600 may include, but are not limited to, one or more processing units or processors 610, memory 620, storage devices 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in the memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0101] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be a removable or non-removable medium and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data (e.g., training data for training) and can be accessed within electronic device 600.

[0102] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 6, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0103] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0104] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0105] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0106] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should 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-readable program instructions.

[0107] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0108] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0109] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0110] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A template-based training method, comprising: Receive the selection of the first training template published by the publisher; The training configuration interface is displayed, which includes a set of parameter configuration controls. The set of parameter configuration controls is used to configure the first set of parameters in the parameter set. The first set of parameters is determined based on the configuration operation of the publisher. Obtain first parameter information about the first set of parameters through the set of parameter configuration controls; as well as The target model is fine-tuned based on at least one set of training samples and the first parameter information.

2. The method according to claim 1, wherein the parameter set further includes a second set of parameters, the second set of parameters not displayed in the training configuration interface.

3. The method according to claim 2, wherein the target model is further fine-tuned based on second parameter information of the second set of parameters, the second parameter information being configured by the publisher.

4. The method according to claim 1, wherein the set of parameter configuration controls displays initial parameter information about the first set of parameters, the initial parameter information being determined based on the configuration operation of the publisher.

5. The method according to claim 1, further comprising: In response to the received publication request, a second training template corresponding to the first parameter information is created.

6. The method of claim 1, wherein receiving a selection of a first training template published by the publisher comprises: Display a template list, the target list including a set of candidate training templates, the target list displaying the template information of the set of candidate training templates; as well as Receive the selection for the first training template in the target list.

7. The method of claim 6, wherein the target information indicates at least one of the following: Identification information for candidate training templates; Description information of candidate training templates; Release information for candidate training templates.

8. The method according to claim 7, wherein the identification information and / or the description information are determined based on the configuration operation of the corresponding publisher.

9. The method according to claim 1, further comprising: The training configuration interface displays a set of example samples and corresponding sample descriptions configured by the publisher. as well as The set of training samples is obtained through the training configuration interface.

10. The method of claim 9, wherein the sample description is used to indicate whether the corresponding example sample is a positive sample or a negative sample.

11. A template-based training device, comprising: The receiving module is configured to receive the selection of the first training template published by the publisher; The display module is configured to display a training configuration interface, which includes a set of parameter configuration controls. The set of parameter configuration controls is used to configure a first set of parameters in a parameter set, which is determined based on the configuration operation of the publisher. The acquisition module is configured to acquire first parameter information about the first set of parameters via the set of parameter configuration controls; as well as The fine-tuning module is configured to fine-tune the target model based on at least one set of acquired training samples and the first parameter information.

12. An electronic device, comprising: At least one processor; as well as At least one memory, coupled to the at least one processor and storing instructions for execution by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, implement the method according to any one of claims 1 to 10.

14. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 10.

Images