Information processing method and device and electronic equipment

Abstract

The embodiment of the invention provides an information processing method and device and electronic equipment, and the method comprises the steps: receiving model switching request information for a target function of an application, and displaying a model list which comprises one or more available models of a target user group; and receiving a target available model selected in the model list, and associating the target function with the target available model so as to realize the target function by the target available model. A channel for switching the models for the application program is provided for a user, the compatibility of the models used by the application program can be improved, and the problem that the AI function of the application program is poor in implementation flexibility can be solved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to an information processing method, device, and electronic device. Background Art

[0002] In some applications (such as applications that support video conferencing), models can be used to implement some functions of the application, which can be called AI (Artificial Intelligence) functions. For example, the model can be used to recognize and convert the received voice information in the application into text, or to generate a summary of the text content.

[0003] These functions are usually completed due to the bound model, that is, the model used by the application's functions cannot be changed on the user side, and the application cannot be combined with the model that the user expects to use, so the adaptability and compatibility of the application in using the model needs to be improved. Summary of the invention

[0004] Embodiments of the present disclosure provide an information processing method, device, and electronic device.

[0005] In a first aspect, an embodiment of the present disclosure provides 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 in the model list, associating the target function with the target available model so that the target function is implemented by the target available model.

[0006] In a second aspect, an embodiment of the present disclosure provides an information processing device, comprising: a display unit, configured to receive model switching request information for a target function of an application, and display a model list, wherein the model list includes one or more available models of a target user group; an association unit, configured to receive a target available model selected in 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] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0008] The memory stores computer-executable instructions;

[0009] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect and various possible designs of the first aspect.

[0010] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method described in the first aspect and various possible designs of the first aspect are implemented.

[0011] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect and various possible designs of the first aspect.

[0012] The information processing method, device and electronic device provided in this embodiment provide a model switching request entry for the target function in the application, and issue a model switching request through the entry. After receiving the model switching request for the target function, a model list can be displayed for the user to select. After the user selects the target available model, the target available model can be associated with the target function to implement the above function. Providing a channel for users to switch models for applications can improve the compatibility of models used by the functions of the application, and can also improve the problem of poor flexibility in implementing AI functions of the application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 Schematic flow chart of the information processing method provided in the embodiment of the present disclosure Figure 1 ;

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

[0016] Figure 3 A flowchart of configuring a custom model provided for the present 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 device provided in an embodiment of the present disclosure;

[0020] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0022] An application can be run in a user terminal device, and the application can have one or more functions, which can be implemented by a model (the functions implemented by the model can be called AI functions). For example, converting the received voice into text, summarizing the text content information, etc. These AI functions need to call a model for processing, and the model here can be a pre-trained model with language processing capabilities.

[0023] In the related art, the above-mentioned application is fixed with the above-mentioned model. For example, in the code of the above-mentioned application, the implementation of the above-mentioned functions of the application is bound with the above-mentioned model, and the user side cannot edit the used model.

[0024] In some application scenarios, users may have permission to use other models, which may be different from the models bound to the application. In these application scenarios, users cannot associate the AI ​​functions of the application with the above other models, and the capabilities of the other models cannot be applied to the above functions. In other words, the model compatibility of the AI ​​functions of the current application and the flexibility of the implementation of AI functions are both poor.

[0025] In order to improve the above problems, the solution provided by the present disclosure provides a model switching request entry for the function in the application, and a model switching request is issued through the entry. After receiving the above model switching request, a model list including one or more available models can be displayed for the user to select. After the user selects the target available model, the target available model can be associated with the function of the application to implement the above function. The user side is provided with a channel for switching models for the function of the application, which can improve the compatibility of the application function with the model use and improve the problem of poor flexibility in the implementation of the AI ​​function of the application.

[0026] Please refer to Figure 1 , Figure 1 Schematic flow of the information processing method provided by the present disclosure Figure 1 ;like Figure 1 As shown, the method comprises the following steps:

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

[0028] S102: receiving a target available model selected by a user in a model list, and associating a target function with the target available model so that the target available model realizes the function of the target application.

[0029] In this embodiment, the execution subject of the information processing method (such as a terminal device or a server) may receive model switching request information for the target function of the application. The above application may be any application that can be run on a user terminal device. The above target function may be any AI function in the application. In some application scenarios, when a model switching request is not received, the AI ​​function of the above application may be associated with a default model, and the AI ​​function of the application may call the default model.

[0030] The target user group may include one or more users. The target user group may be any one of multiple user groups that use the target application. The user group data corresponding to different user groups are not shared, that is, they are isolated from each other. One or more available models may be models that the target user group has permission to use, and the one or more models may include custom models related to the target user group.

[0031] In some embodiments, the available models may include custom models configured by members of the target user group. In these embodiments, the custom models may be trained by multiple training data suitable for the user group's business, so that the custom models obtained are more compatible with the user group's business.

[0032] The custom model can be a model that the target user group has permission to access. The model that has permission to access can be different from the model that is bound to the target function by default in the application. The model that has permission to access can come from one or more model providers. After the custom model is configured, the custom model can be used as the implementation model of the target function, thereby switching the target function from the default model to the custom model.

[0033] In some embodiments, the available models may also include a default model bound to the target function when the application is released. In these embodiments, if the target user group switches the default model associated with the target function to a custom model last time, when the preset user of the target user group initiates a model switching request again, the default model may be displayed for the preset user to select, so as to associate the default model with the target function again.

[0034] The user can select a target available model from the model list. After receiving the user's selection operation on the target available model, the execution subject can associate the target available model with the target function, so that the target function is realized by the target available model.

[0035] In this embodiment, after receiving the above-mentioned model switching request, a model list including one or more available models can be displayed for the user to select, and after the user selects the target available model, the target available model can be associated with the target function of the application. A channel is provided for the user side to configure the model of the target function of the application, so that the model used by the target function of the application can be configured by the user as needed, which can improve the compatibility of the target function with the model use, and is conducive to improving the problem of poor flexibility in the implementation of AI functions.

[0036] In some implementations, the above step S101 includes:

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

[0038] In these implementations, the model switching authority may be configured in advance for the target user group. A preset user in the target user group may send a model switching request message according to the model switching authority. Further, the model switching authority is configured by the server of the application. That is, the server of the application may configure whether the model of the application can be switched. For example, the developer of the application configures whether the function of the application can switch models on the server.

[0039] That is, the target user group needs to have the model switching authority for the application function, and the preset users of the target user group can send the above model switching request information, thereby restricting the target user group from switching the model of the target function according to the above model switching authority.

[0040] In a schematic diagram, the model switching control is displayed in a preset display interface displayed to a preset user, wherein the preset user is a user with preset permissions in the target user group, and the preset display interface is a display interface of an application. The execution subject displays the model list in response to receiving the trigger operation information executed on the model switching control.

[0041] The preset user here may be a user who manages the application used in the target user group. For example, the preset user may be an administrator of the target user group.

[0042] The preset display interface displayed to the preset user may be a model management interface of the application, and the model switching control is displayed in the model management interface, so that the preset user can manage the model used by the application according to the model switching control. The preset user can browse to the model switching control in the model management interface and perform a trigger operation on the model switching control as needed.

[0043] In one example, the preset display interface can be displayed in the terminal device of the preset user, and the model switching control can be displayed in the preset display interface. The preset user can perform a trigger operation on the model switching control, and the terminal device generates a model switching request message after receiving the trigger operation. The terminal device sends the model switching request message to the server of the target application. The server sends the model list information to the terminal device according to the model switching request message. The terminal device can display the model list, for example, display the model list in the preset display interface.

[0044] In one example, the terminal device of the preset user can display the above-mentioned model switching control in the above-mentioned preset display interface. The preset user can perform a trigger operation on the above-mentioned model switching control. When the terminal device receives the above-mentioned trigger operation on the model switching control, it can be regarded as receiving the model switching request information, and then displaying the model list. Here, the model list can be pre-stored in the terminal device, for example.

[0045] Please refer to Figure 2 , Figure 2 A schematic diagram of an application scenario is shown in FIG. Figure 2 As shown, the preset display interface (eg, model management interface) 21 of the preset user's terminal device target application can display information of the function configuration custom model. The information of the custom model may include name, description, type, etc. For example Figure 2 The preset display interface 21 displays custom model 1, description 1 corresponding to custom model 1, and type 1 of custom model 1; custom model 2, description 2 corresponding to custom model 2, and type 2 of custom model 2; and custom model 3, description 3 corresponding to custom model 3, and type 3 of custom model 3. In addition, the preset display interface 21 also displays a switching control 22. The preset user can perform a trigger operation on the switching control 22, thereby displaying a switching window 23.

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

[0047] The user can select the target available model in the model list 24, for example, select the custom model 1. After receiving the user's selection operation on the custom model 1, the above-mentioned terminal device can automatically display the custom model 1 in the selected model display window 25. In addition, the display switching window 23 can also display an "OK" control, and the user can complete the selection operation of the target function model through the above-mentioned "OK" control. The target available model is thereby associated with the target function. Through the above-mentioned process, it is preset that the user can switch the implementation model of the target function, thereby realizing the configurability of the model used by the target function. In addition, the target function can be realized by a custom model, and other models commonly used by users of the target user group can be used to realize the target function. If other models already have historical data of the target user group, the above-mentioned target function realized by the above-mentioned custom model will have a higher degree of match with the needs of the target user group.

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

[0049] The above-mentioned multiple versions of custom models can be implemented by different models provided by the model provider.

[0050] In one example, different versions of the custom model may be provided in the model list, and it is preset that the user can select which version of the custom model to use.

[0051] In these implementations, the model switching is completed by a preset user, which can ensure the stability of the model associated with the target function to a certain extent.

[0052] Please refer to Figure 3 , Figure 3 A flowchart of configuring a custom model provided for the present disclosure; Figure 3 As shown, the above information processing method also includes configuring a custom model based on the following steps:

[0053] S301: Receive a custom model configuration request from a user in a target user group; the custom model configuration request includes interface configuration information of a model provider.

[0054] The execution subject (terminal device or server) of the information processing method can receive a custom model configuration request sent by a user of the target user group. The custom model configuration request is used to configure the custom model. The user can be any user of the target user group.

[0055] As an implementation manner, the above interface configuration information may be information in a unified format input by a user.

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

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

[0058] S302: Configure a custom model according to the custom model configuration request.

[0059] The name, type, version number, model provider identifier, and interface configuration information of the above-mentioned custom model are associated with the custom model. After the configuration is completed, the custom model can realize the target function.

[0060] S303: Associating the custom model with the target user group, wherein the custom models of different user groups are isolated from each other.

[0061] The custom model corresponding to each user group is associated with the user group ID of the user group. Custom models of different user groups are not shared, so that the custom models of different user groups can be managed.

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

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

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

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

[0066] Illustratively, a first control for configuring a custom model may be displayed in a user client display interface. A user may perform a trigger operation on the first control, and a model creation interface is displayed after receiving the trigger operation on the first control. The model creation interface may include one or more configuration items.

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

[0068] After the user enters the name, description and type of the custom model in the above-mentioned first model creation interface, the user can enter the second model creation interface. The second model creation interface includes a version configuration item, a model provider configuration item, and an interface configuration editing item. The user can enter version information in the version configuration item of the second model creation interface. The model provider configuration item can provide one or more candidate model providers for the user to choose. The user can select a model provider from one or more candidate model providers. The user can enter interface configuration information in the interface configuration item.

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

[0070] The pre-configured model provider may be a model provider pre-configured for a custom model. The model provider added by the user may be any model provider different from the pre-configured model provider. The model provider may be accessible to the target user group.

[0071] By setting the above-mentioned pre-configured model provider or the user-added model provider in the custom model configuration request, the user can select the model provider to realize the free configuration of the custom model, thereby further improving the compatibility of the AI ​​function with the model.

[0072] Combine the following Figure 4 and Figure 5 , Figure 4 A schematic diagram of an application scenario. Figure 5 is a schematic diagram of an application scenario. Figure 4 As shown, the target application client of the user in the target user group can display the model management interface. The model management interface can display a control "Create Model" 411 for creating a model. The user can perform a trigger operation on the control 411 to display the first interface 42.

[0073] The first interface 42 may display a name configuration item 421, a model description configuration item 422, and a model type configuration item 423. The user may enter a name for the custom model in the name configuration item 421; enter a description of the custom model in the model description configuration item 422; and select a model type in the model type configuration item 423, for example, Figure 4 After receiving the basic information such as the name, description and type entered in the first interface, the second interface 43 may be displayed. Figure 5 The second interface 43 is used to edit the custom model version and the model passing method.

[0074] Specifically, the second interface 43 may display a version configuration item 431, a model provider configuration item 432, and an interface configuration item 433. The user may enter the version number of the custom model in the version configuration item 431. The model provider configuration item 432 may include one or more candidate model providers: model provider 1 and model provider 2, from which the user may select a candidate model provider as a model provider by clicking, touching, or other operations.

[0075] In addition, the model provider configuration item 432 may also display "other source configuration items". Users may configure other custom model sources through "other source configuration items". Other custom model sources may be, for example, other model providers that the user has permission to access. Through the above configuration, users may configure newly added model providers for custom models. By providing other source configuration items to configure newly added model providers for custom models, custom models do not have to be limited to model providers pre-bound to the application, thereby giving users greater freedom to configure custom models.

[0076] As an example, after the user selects a model provider, the interface configuration item 433 of the model provider may be displayed accordingly. That is, the interface configuration items corresponding to different model providers may be different. Schematically, when the model provider is model provider 1, the interface configuration item 433 may include an API address. The API address here may be the network address of the application programming interface of model provider 1. The access password may include an access identifier and an access password for the target user group to access the API of the above-mentioned model provider 1.

[0077] The user may submit a custom model configuration request after inputting the above information in the above second interface 43. The above execution subject may configure the custom model after receiving the above custom model configuration request.

[0078] By displaying the first interface and the second interface for configuring the custom model to the users in the target user group, it is convenient for the users to configure the custom model and simplifies the operation of the users to configure the custom model.

[0079] In some implementations, step S302 includes:

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

[0081] Second, configure the custom model according to the target interface configuration information.

[0082] In these implementations, since different model providers have different interface protocols, the formats of the parameters to be input are different. In order to facilitate users to configure custom models and make the custom models compatible with different model providers, interface compatibility is required. That is, the interface configuration information set during model configuration needs to be adapted to the interface protocol of the model provider used by the custom model.

[0083] When configuring a custom model, the user can input the interface configuration information corresponding to different model providers in the same format. The preset adapter component generates target interface configuration information matching the target model provider based on the input interface configuration information.

[0084] Due to different interface protocols, the request parameters and formats of the request parameters input to different model providers will be different when accessing different model providers. In order to simplify the user's configuration of the custom model and realize the access to different model providers, the inventor designed an intermediate adapter component, which converts the interface configuration information input by the user into request parameters and formats of request parameters that are adapted to the model provider being accessed.

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

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

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

[0088] In some embodiments, the method further comprises the steps of:

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

[0090] When the custom model receives an information processing request from a user, the custom model generates prompt information for the information processing request according to the target prompt template, and the custom model can send the prompt information to the target model provider through the above interface configuration.

[0091] By providing a target prompt template for the custom model, it is convenient for the custom model to generate prompt information so that the model provider can process the user's information processing request according to the prompt information, so that the custom model can feedback better output results to the user's information processing request.

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

[0093] First, a first prompt template is used to generate prompt information which is input into a plurality of custom models, and outputs of the plurality of custom models are 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 the 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.

[0095] The first prompt template here may include, for example, prompt words, content processing logic, examples, etc. The above content processing logic may include the steps for processing the information content input by the user, the logic of each step, etc. The example may include one or an input example and an output example corresponding to the input example, etc.

[0096] In the above-mentioned first operation process, multiple training information contents can be used, and prompt information can be generated using a prompt template according to the information content, and the prompt information can be input into multiple custom models. The output of each custom model is evaluated (for example, scored) according to the target output corresponding to the training information content. If the evaluation result does not meet the preset requirements (for example, the average score is less than the preset threshold), adjust the first prompt template, such as adjusting the prompt words, content processing logic (for example, detailing the processing steps), adding examples, etc. Generate prompt information corresponding to the training information content according to the adjusted first prompt template, input the prompt information into each custom model, and evaluate the output of each custom model. Until the evaluation result meets the preset conditions.

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

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

[0099] First, according to the offline instruction received for the custom model, it is determined whether the custom model is associated with the target function.

[0100] Secondly, if yes, keep the custom model and display a prompt to refuse offline information; if no, execute the offline operation on the custom model.

[0101] A user in the target user group can initiate an offline instruction for a custom model. The execution subject can first determine whether the custom model is associated with the target function and whether the custom model has been called by the target function. Specifically, for each custom model, the function that calls the custom model can be recorded. After receiving the offline instruction for the custom model, it can be determined whether the custom model is associated with the target function based on the above record corresponding to the custom model.

[0102] If it is determined through the above records that the custom model is not associated with the target function, the custom model can be taken offline. Otherwise, a message is issued to refuse the offline.

[0103] In these implementations, after receiving the offline instruction of the custom model, it is determined whether the custom model is associated with the target function. If not, the custom model is taken offline. Otherwise, a prompt message refusing to take the custom model offline is issued, thereby avoiding the problem that the target function cannot be achieved after the user takes the custom model offline.

[0104] Corresponding to the above Figure 1 The information processing method of the illustrated embodiment, Figure 6 A schematic structural block diagram of an information processing device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 6 , the device 60 includes: a display unit 601 and an association unit 602. Among them,

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

[0106] The associating unit 602 is used to receive the target available model selected in the model list, and associate the target function with the target available model so that the target function is realized 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 according to the model switching authority; wherein the preset user is a user with preset authority in the target user group, and the model switching authority is configured by the application server to the target user group.

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

[0110] In some embodiments, the device 60 further includes a model configuration unit (not shown in the figure), which is used to:

[0111] Receiving a custom model configuration request from a user of a target user group; the custom model configuration request includes interface configuration information of a model provider;

[0112] Configure a custom model according to a custom model configuration request;

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

[0114] In some embodiments, the custom model configuration request includes model provider information, where the model provider information indicates a pre-configured model provider or a model provider newly 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 adapter component, which converts the interface configuration information into target interface configuration information that matches the model provider interface protocol;

[0117] The custom model is configured according to the target interface configuration information. In some embodiments, the apparatus 60 further includes a prompt template configuration unit (not shown in the figure), the prompt template configuration unit is used to:

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

[0119] In some embodiments, the apparatus 60 further includes a prompt template generating unit (not shown in the figure), which is configured to determine a target prompt template based on the following first operation:

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

[0121] If the outputs of multiple custom models do 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 outputs of the multiple custom models, the adjusted prompt template is used as the first prompt template, and the first operation is repeatedly performed until the outputs of multiple custom models meet the preset conditions; the first prompt template whose outputs of multiple custom models meet the preset conditions is used as the target prompt template.

[0122] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0123] refer to Figure 7, which shows a schematic diagram of the structure of an electronic device 700 suitable for implementing the embodiment of the present disclosure, and the electronic device 700 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0124] like Figure 7 As shown, the electronic device 700 may include a processing device (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 to a random access memory (RAM) 703. Various programs and data required for the operation of the electronic device 700 are also stored in the RAM 703. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0125] Typically, the following devices may be connected to the I / O interface 705: input devices 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 708 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 709. The communication devices 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0126] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0127] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program (computer-executable instructions), which may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0128] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0129] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0130] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0132] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0133] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without 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 the like.

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

[0135] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0136] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0137] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, 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. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An information processing method, comprising: receiving a model switching request information for a target function of an application, and displaying a model list, the model list including one or more available models for a target user group; A target available model selected from the model list is received, and the target function is associated 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 model switching request information for the target function of the application includes: The model switching request information sent by a preset user according to the model switching authority is received; wherein the preset user is a user with preset authority in the target user group, and the model switching authority is configured by the server of the application 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 comprises: Receiving a custom model configuration request from a user of the target user group; the custom model configuration request includes interface configuration information of a model provider; Configuring 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, where the model provider information indicates a pre-configured model provider or a model provider newly added by the user.

6. The method according to claim 4, characterized in that Configuring the custom model according to the custom model configuration request includes: Sending the interface configuration information to a preset adapter component, which converts the interface configuration information into target interface configuration information that matches the model provider interface protocol; The custom model is configured 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 comprises: Configure a target hint 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 information and input it into multiple custom models, and obtain outputs of the multiple custom models; If the outputs of the multiple custom models do 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 outputs of the multiple custom models, the adjusted prompt template is used as the first prompt template, and the first operation is repeatedly performed until the outputs of the multiple custom models meet the preset conditions; the first prompt template whose outputs of the multiple custom models meet the preset conditions is used as the target prompt template.

9. An information processing device, comprising: A display unit, configured to receive model switching request information for a target function of an application, and display a model list, wherein the model list includes one or more available models for a target user group; The associating unit is used to receive the target available model selected in the model list, and associate the target function with the target available model so that the target function is realized by the target available model.

10. An electronic device, wherein: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer-executable instructions, and when a processor executes the computer-executable instructions, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images