Information processing methods, devices and electronic equipment

Abstract

This disclosure provides an information processing method, apparatus, and electronic device. The method includes: receiving a model switching request for a target function of an application; displaying a model list, the model list including one or more available models for a target user group; receiving a target available model selected from the model list; and associating the target function with the target available model so that the target function is implemented by the target available model. This provides users with a channel to switch models for applications, which can improve the compatibility of models used by applications and also improve the problem of poor flexibility in implementing AI functions in applications.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to an information processing method, apparatus, and electronic device. Background Technology

[0002] In some applications (such as those supporting video conferencing), models can be used to implement certain functions of the application; these functions can be referred to as AI (Artificial Intelligence) functions. For example, functions such as recognizing received speech information in the application and converting it into text, or generating summaries of text content, can be implemented by calling on models.

[0003] These functions are usually accomplished by the model they are bound to, meaning that the model used by the application's functions cannot be changed on the user side. The application cannot be combined with the model that the user expects to use, which makes the application's adaptability and compatibility in the use of the model need to be improved. Summary of the Invention

[0004] This disclosure provides an information processing method, apparatus, and electronic device.

[0005] In a first aspect, embodiments of this disclosure provide an information processing method, comprising: receiving model switching request information for a target function of an application; displaying a model list, the model list including one or more available models for a target user group; receiving a target available model selected from the model list; and associating the target function with the target available model so that the target function is implemented by the target available model.

[0006] Secondly, embodiments of this disclosure provide an information processing apparatus, comprising: a display unit, configured to receive model switching request information for a target function of an application, and display a model list, the model list including one or more available models for a target user group; and an association unit, configured to receive a target available model selected from the model list, and associate the target function with the target available model so that the target function is implemented by the target available model.

[0007] Thirdly, embodiments of this disclosure provide an electronic device, including: a processor and a memory;

[0008] The memory stores computer-executed instructions;

[0009] The processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method described in the first aspect above and various possible designs of the first aspect.

[0010] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the methods described in the first aspect and various possible designs of the first aspect.

[0011] Fifthly, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect above and various possible designs of the first aspect.

[0012] The information processing method, apparatus, and electronic device provided in this embodiment provide a model switching request entry for a target function within an application. By issuing a model switching request through this entry, and upon receiving the request, a list of models can be displayed for the user to select. After the user selects a target available model, the target available model can be associated with the target function to achieve the aforementioned functionality. This provides users with a channel to switch models for the application, improving the compatibility of models used by the application's functions and addressing the issue of poor flexibility in implementing AI functions in the application. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 An illustrative flow diagram of the information processing method provided in the embodiments of this disclosure. Figure 1 ;

[0015] Figure 2 This is a schematic diagram of an application scenario;

[0016] Figure 3 This is a flowchart illustrating the process of configuring a custom model as provided in this disclosure;

[0017] Figure 4 This is a schematic diagram of an application scenario;

[0018] Figure 5 This is a schematic diagram of an application scenario;

[0019] Figure 6 A schematic structural diagram of an information processing apparatus provided in the embodiments of this disclosure;

[0020] Figure 7 This is a schematic diagram of the electronic device structure provided in an embodiment of this disclosure. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0022] Applications can run on user terminal devices, and these applications can have one or more functions. These functions can be implemented through models (functions implemented through models can be called AI functions). For example, converting received speech into text or summarizing text content. These AI functions require calling models to process the data, and these models can be pre-trained models with language processing capabilities.

[0023] In related technologies, the application is fixed to the model. For example, in the code of the application, the implementation of the above functions of the application is bound to the model, and the user cannot edit the model used.

[0024] In some application scenarios, users may have access to other models, which may be different from the models already bound to the application. In these scenarios, users cannot associate the application's AI functions with these other models, and the capabilities of those other models cannot be applied to the aforementioned functions. In other words, the model compatibility and flexibility of the application's AI functions are currently quite poor.

[0025] To address the aforementioned issues, the solution provided in this disclosure offers a model switching request entry point within the application. Users can issue model switching requests through this entry point. Upon receiving such a request, a list of one or more available models can be displayed for the user to select. After the user selects a target available model, it can be associated with the application's functionality to achieve the aforementioned effect. This provides a channel for users to switch models for application functions, improving the compatibility of application functions with model usage and mitigating the problem of poor flexibility in implementing AI functions in the application.

[0026] Please refer to Figure 1 , Figure 1 Schematic flowchart of the information processing method provided in this disclosure Figure 1 ;like Figure 1 As shown, the method includes the following steps:

[0027] S101: In response to receiving a model switching request for a target function of the application, display a model list, which includes available models for one or more target user groups.

[0028] S102: Receive the target available model selected by the user in the model list, associate the target function with the target available model, so that the target application function can be implemented by the target available model.

[0029] In this embodiment, the entity executing the information processing method (e.g., a terminal device or a server) can receive a model switching request for the target function of an application. The application can be any application that can run on a user's terminal device. The target function can be any AI function within the application. In some application scenarios, when no model switching request is received, the application's AI function can be associated with a default model, and the application's AI function can call the default model.

[0030] The target user group can include one or more users. The target user group can be any of multiple user groups using the target application. User group data is not shared between different user groups; that is, they are isolated from each other. One or more available models can be models that the target user group has the permission to use. These one or more models can include custom models associated with the target user group.

[0031] In some implementations, the available model may include a custom model configured by members of the target user group. In these implementations, the custom model may be trained using multiple training data sets suitable for the user group's business, thus resulting in a custom model that is more closely matched to the user group's business.

[0032] A custom model can be a model that the target user group has permission to access. This authorized model can differ from the model bound to the target function by default in the application. This authorized model can come from one or more model providers. After configuring a custom model, it can serve as the implementation model for the target function, thereby enabling the switching of the target function from the default model to the custom model.

[0033] In some implementations, the available models may also include the default model that was bound to the target function when the application was published. In these implementations, if the target user group previously switched the default model associated with the target function to a custom model, when a preset user in the target user group initiates a model switching request again, the default model can be displayed for the preset user to select, so as to re-associate the default model with the target function.

[0034] Users can select a target available model from the above model list. After receiving the user's selection of the target available model, the execution entity can associate the target available model with the target function, thereby enabling the target function to be implemented by the target available model.

[0035] In this embodiment, upon receiving the aforementioned model switching request, a model list including one or more available models can be displayed for the user to select. After the user selects a target available model, the target available model can be associated with the application's target function. This provides the user with a channel to configure models for the application's target function, allowing the user to configure the models used by the application's target function as needed. This improves the compatibility of the target function with model usage and helps to address the problem of poor flexibility in AI function implementation.

[0036] In some embodiments, step S101 includes:

[0037] Receive model switching request information sent by a preset user based on model switching permissions; wherein, the preset user is a user in the target user group with preset permissions, and the model switching permissions are permissions configured for switching models in the target user group, which are configured by the application's server.

[0038] In these implementations, model switching permissions can be pre-configured for the target user group. Pre-defined users within the target user group can then send model switching requests based on these permissions. Furthermore, these model switching permissions are configured by the application's server. That is, the application's server can configure whether the application's model can be switched. For example, the application's developers can configure whether the application's functionality allows model switching on the server side.

[0039] In other words, the target user group needs to have the model switching permission for the application function before the preset users of the target user group can send the above model switching request information, thereby restricting the target user group to switch the model of the target function according to the above model switching permission.

[0040] Schematic illustration: A model switching control is displayed in a preset display interface shown to a preset user; wherein the preset user is a user with preset permissions in a target user group, and the preset display interface is a display interface of the application. The aforementioned execution entity, in response to receiving trigger operation information for the model switching control, displays a list of models.

[0041] The default users here are users who manage applications used by the target user group; for example, the default users can be administrators of the target user group.

[0042] The preset display interface shown to the preset user can be the application's model management interface. This interface displays the model switching control, allowing the preset user to manage the models used by the application. The preset user can browse the model switching control within the model management interface and trigger operations on it as needed.

[0043] In one example, a preset display interface can be displayed on a user's terminal device, and this interface can display a model switching control. The user can trigger an operation on the model switching control, and upon receiving this trigger operation, the terminal device generates a model switching request. The terminal device then sends this request to the target application's server. The server sends a list of models to the terminal device based on the model switching request. The terminal device can then display the model list, for example, within the preset display interface.

[0044] In one example, a user's terminal device can display the model switching control in the aforementioned preset display interface. The user can trigger the model switching control. Upon receiving the trigger operation on the model switching control, the terminal device can be considered to have received a model switching request, and thus displays the model list. This model list can, for example, be pre-stored in the terminal device.

[0045] Please refer to Figure 2 , Figure 2 For example, a schematic diagram of an application scenario. Figure 2 As shown, the preset display interface (e.g., model management interface) 21 of the target application on the user's terminal device can display information about the custom model's function configuration. The custom model's information can include name, description, type, etc. For example... Figure 2 The preset display interface shows: Custom Model 1, its description 1, and its type 1; Custom Model 2, its description 2, and its type 2; Custom Model 3, its description 3, and its type 3. Additionally, the preset display interface 21 also displays a switching control 22. Users can trigger the switching control 22 to display a switching window 23.

[0046] Switching window 23 can display model list 24, which can include custom models that the target user group has permission to use, as well as default models. The default model here can be a model provided by the target application server, not a user-created custom model. Custom models can include Custom Model 1, Custom Model 2, and Custom Model 3.

[0047] Users can select a target available model from model list 24, such as custom model 1. After receiving the user's selection of custom model 1, the terminal device automatically displays custom model 1 in the selected model display window 25. Furthermore, the display switching window 23 can also display an "OK" control, allowing the user to complete the selection of the target function model. This associates the target available model with the target function. The above process allows users to switch the implementation model of the target function, achieving configurability of the model used by the target function. Moreover, implementing the target function using a custom model can utilize other models commonly used by the target user group. If other models already contain historical data of the target user group, the target function implemented by the custom model will have a higher degree of matching with the needs of the target user group.

[0048] In one example, if the selected custom model has multiple versions, and the user does not specify a version number, the aforementioned execution entity can associate the latest version of the custom model with the target function.

[0049] The aforementioned custom models can be implemented using different models provided by the model provider.

[0050] In one example, the above list of models can provide different versions of a custom model, with the user able to choose which version of the custom model to use.

[0051] In these implementations, having a pre-selected user perform the model switching can, to some extent, ensure the stability of the model associated with the target function.

[0052] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of configuring a custom model provided in this disclosure; such as Figure 3 As shown, the above information processing method also includes configuring a custom model based on the following steps:

[0053] S301: Receive custom model configuration requests from users of the target user group; the custom model configuration requests include interface configuration information from the model provider.

[0054] The entity executing the information processing method (terminal device or server) can receive custom model configuration requests sent by users from the target user group. These custom model configuration requests are used to configure custom models. The users mentioned above can be any user within the target user group.

[0055] As one implementation method, the above interface configuration information can be information in a uniform format input by the user.

[0056] In addition, the aforementioned custom model configuration request may also include one or more of the following: the name, type, version number, and identifier of the model provider.

[0057] To illustrate, the interface configuration information mentioned above includes the access ID of the access model provider, the access password, the API address provided by the model provider, the maximum number of tokens, etc.

[0058] S302: Configure a custom model based on a custom model configuration request.

[0059] The custom model is associated with information such as its name, type, version number, model provider identifier, and interface configuration. Once configured, this custom model can achieve the target functionality.

[0060] S303: Associate a custom model with a target user group, where the custom models for different user groups are isolated from each other.

[0061] Each user group's custom model is associated with that user group's identifier. Custom models from different user groups are not shared, in order to manage the custom models of different user groups.

[0062] After completing the configuration of the custom model, the aforementioned execution entity can register the custom model with the server corresponding to the application, so that the server can discover and use the custom model.

[0063] In some implementations, step S301 above includes the following sub-steps:

[0064] First, receive the custom model creation command and display the model creation interface;

[0065] Secondly, it receives the custom model configuration information set in the model creation interface.

[0066] Schematic illustration: A first control for configuring a custom model can be displayed on the user client interface. The user can trigger an operation on this first control; upon receiving such an operation, the model creation interface is displayed. The model creation interface may include one or more configuration items.

[0067] In one example, the model creation interface described above may include a first model creation interface, which includes a name configuration item, a model description configuration item, and a type configuration item. Users can enter the name, description, and type of a custom model in the name, model, and type configuration items, respectively. The type may, for example, include a language processing model type and a non-language processing model type.

[0068] After entering the name, description, and type of their custom model in the first model creation interface, users can proceed to the second model creation interface. The second model creation interface includes version configuration items, model provider configuration items, and interface configuration editing items. Users can enter version information in the version configuration item. The model provider configuration item provides one or more candidate model providers for the user to choose from. Users can select one model provider from the candidate providers. Users can enter interface configuration information in the interface configuration item.

[0069] In some implementations, the custom model configuration request includes model provider information, which indicates a pre-configured model provider or a model provider added by the user.

[0070] The pre-configured model providers mentioned above can be model providers pre-configured for custom models. User-added model providers can be any model provider different from the pre-configured ones. These model providers can be accessed by the target user group.

[0071] By setting the pre-configured model provider or the user-added model provider in the custom model configuration request, users can select the model provider to achieve free configuration of custom models, thereby further improving the compatibility of AI functions with models.

[0072] The following is combined Figure 4 and Figure 5 , Figure 4 This is a schematic diagram of an application scenario. Figure 5 This is a diagram illustrating an application scenario. For example... Figure 4 As shown, the target application client of the target user group can display the model management interface. The model management interface can display the "Create Model" control 411 used to create models. Users can perform a trigger operation on the above control 411 to display the first interface 42.

[0073] The first interface 42 displays the name configuration item 421, the model description configuration item 422, and the model type configuration item 423. Users can enter the name of the custom model in the name configuration item 421; enter the description of the custom model in the model description configuration item 422; and select the model type in the model type configuration item 423, for example... Figure 4 The "Language Model" type. After receiving the basic information such as name, description, and type entered in the first interface, the second interface 43 can be displayed. Please refer to [link / reference]. Figure 5 The second interface 43 is used to edit custom model versions and model approval methods.

[0074] Specifically, the second interface 43 can display version configuration item 431, model provider configuration item 432, and interface configuration item 433. Users can enter the version number of a custom model in version configuration item 431. Model provider configuration item 432 can include one or more candidate model providers: model provider 1 and model provider 2. Users can select a candidate model provider as the model provider through clicks, touches, or other operations.

[0075] Furthermore, the aforementioned model provider configuration item 432 can also display "Other Source Configuration Items." Users can configure other custom model sources through these "Other Source Configuration Items." Other custom model sources can be, for example, other model providers that the user has permission to access. Through this configuration, users can configure new model providers for their custom models. By providing "Other Source Configuration Items" to configure new model providers for custom models, custom models are not limited to the model providers pre-bound to the application, thus giving users greater freedom in configuring custom models.

[0076] As an example, after a user selects a model provider, the corresponding interface configuration item 433 for that model provider can be displayed. That is, different model providers can have different interface configuration items. Illustratively, when the model provider is model provider 1, interface configuration item 433 may include an API address. This API address can be the network address of model provider 1's application programming interface. The access password may include the access identifier and password for the target user group to access the API of model provider 1.

[0077] After entering the aforementioned information in the second interface 43, the user can submit a custom model configuration request. Upon receiving the custom model configuration request, the executing entity can configure the custom model.

[0078] By presenting users of the target user group with a first interface and a second interface for configuring custom models, the system facilitates and simplifies the process of configuring custom models for users.

[0079] In some implementations, step S302 includes:

[0080] First, the interface configuration information is sent to the preset adaptation component, which then converts the interface configuration information into target interface configuration information that matches the interface protocol of the model provider.

[0081] Secondly, configure the custom model based on the target interface configuration information.

[0082] In these implementations, different model providers use different interface protocols, resulting in different formats for the input parameters. To facilitate user configuration of custom models and ensure compatibility between different model providers, interface compatibility is required. This means that the interface configuration information set during model configuration must be compatible with the interface protocol of the model provider used by the custom model.

[0083] When configuring a custom model, users can input the corresponding interface configuration information for different model providers in the same format. A pre-defined adaptation component will then generate target interface configuration information that matches the target model provider based on the input interface configuration information.

[0084] Because different interface protocols result in different request parameters and their formats when accessing different model providers, the inventors designed an intermediate adapter component to simplify the configuration of custom models and enable access to different model providers. This intermediate adapter component converts the user-input interface configuration information into request parameters and their formats that are compatible with the accessed model provider.

[0085] As one implementation method, a mapping between user-inputted interface configuration information and interface parameters of different model providers can be set in the preset adaptation component. Through the above mapping, the user-inputted interface configuration information can be mapped to the interface parameters of different model providers.

[0086] The aforementioned preset adaptation component can parse the interface configuration information entered by the user according to different model providers, and parse it into request parameters and formats that are compatible with the target model provider being called.

[0087] In these implementations, user-inputted interface configuration information can be converted into interface configuration information and corresponding format adapted to the target model provider by using a preset adaptation component, thereby reducing the complexity of creating custom models.

[0088] In some implementations, the method further includes the following steps:

[0089] Configure a target hint template for a custom model.

[0090] When a custom model receives an information processing request from a user, it generates a prompt message based on the target prompt template. The custom model can then send the prompt message to the target model provider through the interface configuration described above.

[0091] By providing target prompt templates for custom models, it is easier for custom models to generate prompt information so that the model provider can process the user's information processing requests according to the prompt information, thereby enabling custom models to provide better output results for the user's information processing requests.

[0092] In some implementations, the information processing method further includes determining a target prompt template based on the following first operation:

[0093] First, the prompt message is generated using the first prompt template and input into multiple custom models, and the output of multiple custom models is obtained.

[0094] Secondly, if the outputs of multiple custom models do not meet the preset conditions, adjust one or more of the prompt words, content processing logic and examples in the first prompt template according to the outputs of multiple custom models, and use the adjusted prompt template as the first prompt template. Repeat the first operation until the outputs of multiple custom models meet the preset conditions; use the first prompt template whose outputs of multiple custom models meet the preset conditions as the target prompt template.

[0095] The initial prompt template here may include prompt words, content processing logic, examples, etc. The content processing logic may include the steps involved in processing the user input, and the logic for each step. Examples may include an input example and a corresponding output example.

[0096] In the first operation described above, multiple training information contents can be used. Based on these contents, prompts are generated using a prompt template, and these prompts are input into multiple custom models. The outputs of each custom model are evaluated (e.g., scored) according to the target output corresponding to the training information contents. If the evaluation results do not meet preset requirements (e.g., the average score is less than a preset threshold), the first prompt template is adjusted, for example, by adjusting the prompt words, content processing logic (e.g., refining processing steps), or adding examples. Prompts corresponding to the training information contents are then generated based on the adjusted first prompt template, and these prompts are input into each custom model. The outputs of each custom model are then evaluated. This process continues until the evaluation results meet the preset conditions.

[0097] The target prompt template obtained through the above steps can be applied to different custom models. This helps reduce the complexity of setting prompt templates for custom models.

[0098] In some implementations, the information processing method further includes:

[0099] First, based on the received offline instruction for the custom model, determine whether the custom model is associated with the target function.

[0100] Secondly, if yes, retain the custom model and display a message indicating that the offline process is refused; otherwise, perform the offline operation on the custom model.

[0101] Users in the target user group can initiate a shutdown command for a custom model. The aforementioned execution entity can first determine whether the custom model is associated with the target function and whether the custom model has been invoked by the target function. Specifically, for each custom model, the functions that invoke the custom model can be recorded. Upon receiving a shutdown command for a custom model, the entity can determine whether the custom model is associated with the target function based on the aforementioned records corresponding to that custom model.

[0102] If the above records determine that the custom model is not associated with the target function, the custom model can be taken offline. Otherwise, a message indicating that the offline process is refused should be issued.

[0103] In these implementations, after receiving a command to take a custom model offline, it is determined whether the custom model is associated with the target function. If there is no association, the custom model is taken offline; otherwise, a message indicating that offline is refused is issued. This avoids the problem that the target function cannot be implemented after the user takes the custom model offline.

[0104] Corresponding to the above text Figure 1 The information processing method of the embodiment shown, Figure 6 This is a schematic structural block diagram of an information processing apparatus provided according to an embodiment of the present disclosure. For ease of explanation, only the parts relevant to the embodiments of the present disclosure are shown. (Refer to...) Figure 6 The device 60 includes a display unit 601 and an association unit 602. Wherein,

[0105] Display unit 601 is used to receive model switching request information for the target function of the application and display a model list, which includes one or more available models for the target user group.

[0106] The association unit 602 is used to receive the target available model selected in the model list, associate the target function with the target available model, so that the target function can be implemented by the target available model.

[0107] In some embodiments, the display unit 601 is further configured to:

[0108] Receive model switching request information sent by a preset user based on model switching permissions; wherein, the preset user is a user in the target user group with preset permissions, and the model switching permissions are configured by the application's server to the target user group.

[0109] In some embodiments, the available models include custom models.

[0110] In some embodiments, the apparatus 60 further includes a model configuration unit (not shown), the model configuration unit being used for:

[0111] Receive custom model configuration requests from users of the target user group; the custom model configuration requests include the interface configuration information of the model provider;

[0112] Configure a custom model based on the custom model configuration request;

[0113] Associate custom models with target user groups, where the custom models for different user groups are isolated from each other.

[0114] In some embodiments, the custom model configuration request includes model provider information, which indicates a pre-configured model provider or a model provider added by the user.

[0115] In some embodiments, the model configuration unit is further configured to:

[0116] The interface configuration information is sent to the preset adaptation component, which then converts the interface configuration information into target interface configuration information that matches the interface protocol of the model provider.

[0117] Configure a custom model based on the target interface configuration information. In some embodiments, the device 60 further includes a prompt template configuration unit (not shown in the figure), which is used for:

[0118] Configure a target hint template for a custom model.

[0119] In some embodiments, the apparatus 60 further includes a prompt template generation unit (not shown), which determines a target prompt template based on the following first operation:

[0120] Use the first prompt template to generate prompt messages, input them into multiple custom models, and obtain the outputs of multiple custom models;

[0121] If the outputs of multiple custom models do not meet the preset conditions, adjust one or more of the prompt words, content processing logic and examples in the first prompt template according to the outputs of multiple custom models, use the adjusted prompt template as the first prompt template, and repeat the first operation until the outputs of multiple custom models meet the preset conditions; use the first prompt template whose outputs of multiple custom models meet the preset conditions as the target prompt template.

[0122] To implement the above embodiments, this disclosure also provides an electronic device.

[0123] refer to Figure 7The diagram illustrates a structural schematic of an electronic device 700 suitable for implementing embodiments of the present disclosure. The electronic device 700 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0124] like Figure 7 As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0125] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0126] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processing device 701, it performs the functions defined in the methods of embodiments of this disclosure.

[0127] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can 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 a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program (computer-executable instructions) that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0128] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0129] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0130] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] 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 code containing one or more executable instructions for implementing a specified logical function. It should also be noted that 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 consecutively indicated 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, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0133] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0134] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0135] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0136] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0137] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information processing method, comprising: Receive a model switching request for a target function of the application and display a model list, which includes one or more available models for the target user group; Receive the target available model selected from the model list, associate the target function with the target available model, so that the target function is implemented by the target available model.

2. The method according to claim 1, characterized in that, The receiving of model switching request information for the target function of the application includes: The system receives a model switching request from a preset user based on model switching permissions; wherein the preset user is a user with preset permissions in the target user group, and the model switching permissions are configured by the application's server to the target user group.

3. The method according to claim 1, characterized in that, The available models include custom models.

4. The method according to claim 3, characterized in that, The method further includes: Receive custom model configuration requests from users of the target user group; the custom model configuration requests include interface configuration information from the model provider; Configure the custom model according to the custom model configuration request; The custom model is associated with the target user group, wherein the custom models of different user groups are isolated from each other.

5. The method according to claim 4, characterized in that, The custom model configuration request includes model provider information, which indicates a pre-configured model provider or a model provider added by the user.

6. The method according to claim 4, characterized in that, The step of configuring the custom model according to the custom model configuration request includes: The interface configuration information is sent to a preset adaptation component, which then converts the interface configuration information into target interface configuration information that matches the interface protocol of the model provider. Configure the custom model according to the target interface configuration information.

7. The method according to any one of claims 4 to 6, characterized in that, The method further includes: Configure a target prompt template for the custom model.

8. The method according to claim 7, characterized in that, The method further includes determining the target prompt template based on the following first operation: Use the first prompt template to generate prompt messages, input them into multiple custom models, and obtain the outputs of multiple custom models; If the output of the multiple custom models does not meet the preset conditions, one or more of the prompt words, content processing logic and examples in the first prompt template are adjusted according to the output of the multiple custom models. The adjusted prompt template is used as the first prompt template. The first operation is repeated until the output of the multiple custom models meets the preset conditions. The first prompt template whose output of the multiple custom models meets the preset conditions is used as the target prompt template.

9. An information processing apparatus, comprising: The display unit is used to receive model switching request information for the target function of the application and display a model list, which includes one or more available models for the target user group. The association unit is configured to receive a target available model selected from the model list, associate the target function with the target available model, so that the target function is implemented by the target available model.

10. An electronic device, wherein, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method as described in any one of claims 1 to 8.

12. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 8.

Images