Interaction card generation method and device based on large model, equipment and intelligent agent

Abstract

The invention provides an interaction card generation method and device based on a large model, electronic equipment and a storage medium, and relates to the technical fields of computer vision, large models, artificial intelligence and the like. The specific implementation scheme is as follows: acquiring a request of a user; calling a corresponding application program interface based on the request of the user, and obtaining return information of the application program interface; and based on the return information of the application program interface, generating an interaction card by adopting a generative large model. According to the technology disclosed by the invention, the generation efficiency of the interaction card in the front end can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the technical fields of computer vision, large models, artificial intelligence, and more particularly to a method, device, equipment, and intelligent agent for generating an interactive card based on a large model. Background Art

[0002] With the advent of the information age, internal communication and collaboration in enterprises are increasingly dependent on digital tools. Among them, smart office systems are widely used as an important means to improve work efficiency.

[0003] In the smart office system, the interactive card, also called the work card, is an important component, which is usually used to display various information such as employee's task list, project progress, meeting schedule, etc. In the prior art, the interactive card is set by manual design and coding. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and intelligent agent for generating an interactive card based on a large model.

[0005] According to one aspect of the present disclosure, a method for generating a medium interaction card based on a large model is provided, comprising:

[0006] Get the user's request;

[0007] Based on the user's request, calling a corresponding application program interface to obtain return information of the application program interface;

[0008] Based on the return information of the application program interface, a generative large model is adopted to generate code snippets of the interactive card.

[0009] According to another aspect of the present disclosure, there is provided a device for generating an interactive card based on a large model, comprising:

[0010] Request acquisition module, used to obtain user requests;

[0011] An information acquisition module, used to call a corresponding application program interface based on the user's request and obtain the return information of the application program interface;

[0012] A generation module is used to generate code snippets of an interactive card based on the return information of the application program interface and using a generative large model.

[0013] According to another aspect of the present disclosure, there is provided an intelligent agent, comprising:

[0014] An input module, used for receiving an input user's request;

[0015] A processing module, configured to determine a task for generating an interactive card based on the user's request received by the input module, determine a generative big model based on the task for generating the interactive card, and generate a code snippet for the interactive card by calling the generative big model to execute the method of the above aspects and any possible implementation manner;

[0016] The output module is used to output the code fragment of the interactive card generated by the processing module.

[0017] According to another aspect of the present disclosure, there is provided an electronic device, including:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0021] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method of the above-mentioned aspects and any possible implementation manner.

[0022] According to yet another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the method of the above-mentioned aspect and any possible implementation manner.

[0023] According to the technology disclosed in the present invention, the generation efficiency of the interaction card in the front end can be effectively improved.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0026] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0027] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0028] Figure 3 is a schematic diagram according to a third embodiment of the present disclosure;

[0029] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0030] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0031] Figure 6 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] Obviously, the described embodiments are only part of the embodiments of the present disclosure, but not all of them. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present disclosure.

[0034] It should be noted that the terminal devices involved in the embodiments of the present disclosure may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0035] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0036] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; Figure 1 As shown, this embodiment provides a method for generating an interaction card based on a large model, which may specifically include the following steps:

[0037] S101, obtaining a user's request;

[0038] S102, based on the user's request, calling the corresponding application programming interface (Application Programming Interface; API) to obtain the return information of the API;

[0039] S103. Based on the return information of the API, a generative big model is used to generate a code snippet of the interactive card.

[0040] The execution subject of the method for generating an interactive card based on a large model in this embodiment is a device for generating an interactive card based on a large model, and the device can be used as a plug-in and set in the front end.

[0041] Specifically, the technical solution of this embodiment can be applied in an intelligent office system. Specifically, the device for generating interactive cards based on the large model can be implanted in the front end with plug-in technology. The device can realize intelligent and automatic generation of interactive cards in the front end.

[0042] The interactive card of this embodiment, which can also be called Work Card, is mainly used to display various task information of employees, including employee leave information, employee meeting arrangement information, employee participation or follow-up project information, and other task lists. Since the interactive card can be clicked by the user to trigger the interaction, it is called an interactive card.

[0043] In this embodiment, the user's request is a query request initiated by the user, and the query request may be a request of various intentions initiated by the user, such as a leave approval request when the user wants to take a leave, or a financial reimbursement request when the user wants to apply for reimbursement, or a meeting reservation request when the user wants to reserve a meeting, etc.

[0044] In this embodiment, based on the user's request, the corresponding API is called, which does not initiate a request to the system corresponding to the API, but standardizes the user's request with the help of the API to obtain all the field information that the API can adapt. Therefore, the return information of the API includes the field information that the API adapts. Finally, based on the return information of the API, the generative large model is used to generate the code snippet of the interactive card. Subsequently, the code snippet based on the interactive card can realize the rendering and display of the interactive card.

[0045] In this embodiment, the generative large model used can also be called a generative language model (General Language Model; GLM), or a generative large language model.

[0046] The method for generating an interactive card based on a big model of this embodiment, by adopting the above-mentioned scheme, can call an API to obtain return information based on a user's request, and use a generative big model to intelligently and automatically generate code snippets for the interactive card. This can overcome the problem in the prior art that it takes a long time to manually design and code the interactive card, and can effectively improve the generation efficiency of the interactive card in the front end.

[0047] Furthermore, in the prior art, when services are frequently changed, the maintenance cost of the interaction card is very high. However, the technical solution of this embodiment can decouple the generation of the interaction card from the service, and can effectively reduce the maintenance cost of the interaction card.

[0048] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure; the method for generating an interactive card based on a large model in this embodiment, in the above Figure 1 Based on the technical solutions of the embodiments shown in the figure, the technical solutions of the present disclosure are further described in more detail. Figure 2 As shown, the method for generating an interactive card based on a large model in this embodiment may specifically include the following steps:

[0049] S201, obtaining a user's request;

[0050] S202, identifying a corresponding request category based on a user's request;

[0051] S203, based on the request type, calling the corresponding API to obtain the return information of the API;

[0052] Since different users' requests include different contents, the corresponding systems for processing the users' requests are different, so the APIs called are different.

[0053] For example, in this embodiment, the request categories of user requests may include: leave approval request, financial reimbursement request or conference reservation request, etc. Leave approval request corresponds to the API of the leave approval system, financial reimbursement request corresponds to the API of the financial reimbursement system, and conference reservation request corresponds to the API of the conference reservation system.

[0054] In this embodiment, only the API corresponding to the request category is called to obtain the return information after the API processes the user's request, and the user's request is not sent to the corresponding system through the API. The processing of the user's request by the API is equivalent to performing standardized adaptation processing on the user's request based on multiple fields defined by the API, and obtaining the field information of the user's request that is adapted and the field information that is not adapted.

[0055] For example, user A initiates a request to reserve a meeting with user B at time C. At this time, based on the user's request, the API of the meeting reservation system is called, and the returned information may include multiple field information, such as the name field, the field value of which may be: the meeting between user A and user B; the time field, the field value of which may be: time C; the participant field: user A and user B; it may also include other fields that the user's request is not adapted to but are defined in the API, such as the meeting address field. Since the value of this field is not in the user's request, it can be temporarily set to empty, and the user can subsequently supplement it through interaction; similarly, it may also include other fields, which will not be listed one by one here.

[0056] That is to say, the APIs of various categories of systems define multiple fields required by the system in that category. The user's request can include the values ​​of all the fields defined in the API, or only the values ​​of some of the fields. The return information of the API must include all the fields required by the system in that category. However, since the user's request can only include the values ​​of some of the fields, when the return information of the API includes multiple fields, it can include the value of each field, or only include the values ​​of some of the fields, while the values ​​of other fields can be empty and can be supplemented in subsequent user interactions.

[0057] Based on the above, it can be known that the return information of the API in this embodiment may include the identifier of the field adapted by the user's request and the value of the field; and the identifier of the field not adapted by the user's request.

[0058] Steps S202-S203 are as above Figure 1 An implementation of step S102 is shown in real time. By this method, the return information of the API corresponding to the user's request can be accurately obtained.

[0059] S204, based on the returned information of the API, using a generative large model to generate a code snippet of the interactive card;

[0060] Specifically, in this embodiment, with the help of a generative big model, based on the return information of the API, the code snippet of the interactive card is intelligently generated without manual design and coding, which can effectively improve the generation efficiency of the interactive card.

[0061] Specifically, the implementation of step S204 may include the following two methods:

[0062] The first method, a method of pre-configuring multiple card templates, may specifically include the following steps:

[0063] (1) Based on the returned information from the API, a generative large language model is used to obtain a matching target card template from multiple pre-configured card templates;

[0064] In this embodiment, multiple card templates may be preconfigured, and different card templates may include different field information. Specifically, the matching target card template may be obtained based on the identifiers of all fields included in the returned information of the API.

[0065] (2) A generative big model is used to generate code snippets for interactive cards based on the API return information and target card templates.

[0066] For example, specifically, a generative big model is used to identify field identifiers and corresponding field values ​​from the return information of the API; here, it is necessary to identify the identifiers of all fields included in the return information of the API and the corresponding field values. It should be noted that the field values ​​of some fields can be empty. Then, a generative big model is used to generate a code snippet for an interactive card based on the target card template, field identifiers and corresponding field values. In other words, the automatically generated code snippet for an interactive card needs to include information about the target card template, field identifiers and corresponding field values. The field identifier of this embodiment may also refer to a field name.

[0067] This implementation method can utilize the natural language understanding and generation capabilities of the generative big model, automatically select the adapted target card template and fill in the relevant information based on the API's return information request, and efficiently and accurately generate the code snippet of the interactive card, thereby effectively improving the efficiency and flexibility of generating interactive cards.

[0068] The second method is to use a generative large model to directly generate, which can specifically include the following steps:

[0069] (a) Based on the API return information, a generative large language model is used to identify field identifiers and corresponding field values;

[0070] (b) Generate code snippets for interactive cards based on field identifiers and field values ​​using a generative big model.

[0071] Compared with the first method mentioned above, in this implementation method, no pre-configured card template is used, but the generative large model is used to automatically generate it directly according to the identified field identifiers and corresponding field values.

[0072] No matter which of the above methods is adopted, the code snippets of the interactive card can be generated intelligently and automatically. Moreover, since the generative large model is very powerful, the accuracy of the code snippets of the generated interactive card can also be effectively ensured.

[0073] S205, sending the code snippet of the interaction card to the front end, so that the front end renders and displays the interaction card based on the code snippet of the interaction card;

[0074] In this step, the user renders and displays the interactive card for the user to view. Moreover, the user can also trigger the update of the content of the interactive card based on the displayed interactive card. That is, the interactive card has an interactive function.

[0075] S206, obtaining update information of the interaction card, where the update information is an update triggered by the user based on the interaction card displayed on the front end;

[0076] The update information of this embodiment includes supplementary information. For example, as mentioned in the above embodiment, when generating an interactive card, the field values ​​of some fields are empty, and the field values ​​of these fields can be supplemented. In addition, the supplementary information here can also include modification information, which can modify the existing field values, such as modifying the meeting time or participants in the above example.

[0077] S207, based on the update information of the interaction card, using a generative large language model to generate an update code snippet of the interaction card;

[0078] S208: Send the updated code snippet of the interactive card to the front end, so that the front end renders and updates the displayed interactive card based on the updated code snippet of the interactive card.

[0079] Through steps S206-S208, the content of the interactive card can be updated, further effectively improving the accuracy of the interactive card. Moreover, the modification of the interactive card content is very convenient and efficient.

[0080] Furthermore, after the interaction card is generated, a create button may be provided on the interaction card. After the user confirms the interaction card information, the create button may be clicked to initiate a corresponding task creation request to the corresponding system, so that the corresponding system may create a corresponding task, such as a meeting reservation task, a request for approval task, a financial reimbursement task, etc. For the specific system creation of the corresponding task, reference may be made to the relevant existing task creation implementation plan, which will not be described in detail here.

[0081] The method for generating interactive cards based on a large model in this embodiment can automatically generate interactive cards based on the drive of a generative large model. This function is based on a plug-in mechanism and can automatically call the corresponding API and generate the corresponding interactive card according to the user's query. Specifically, it can be applied to the front end of the intelligent office system, and can realize more intelligent and flexible generation of front-end interactive cards to meet the needs of modern enterprises for office automation and rapid information transmission.

[0082] The method for generating interactive cards based on a large model of this embodiment can generate interactive cards in the front end accurately, efficiently and intelligently by adopting the above technical solution, thereby effectively improving the speed and quality of generating interactive cards.

[0083] The disclosed method for generating interactive cards based on large models can also greatly improve the user experience, allowing users to complete tasks more efficiently, such as appointments, meeting arrangements, etc., without having to deeply understand the specific background operation details.

[0084] Second, because interactive cards are often designed with simplicity and intuitiveness in mind, this helps reduce users’ cognitive load, allowing them to understand and take action faster.

[0085] Compared with the traditional method of manually filling out forms or relying on email communication, the technical solution disclosed in the present invention no longer requires users to manually fill out forms or wait for manual responses, greatly shortening the processing time. Automatic processing through generative large models can effectively reduce errors caused by human factors and significantly improve the speed and accuracy of information processing. In short, since the links involved in human participation are reduced, the possibility of data entry errors caused by misunderstandings or negligence is also reduced accordingly. In addition, the automated process also means that services can be provided around the clock, without being restricted by working hours, further increasing the availability and reliability of the service.

[0086] Finally, the method for generating interactive cards based on large models disclosed in the present invention can effectively enhance users' trust in brands by providing a unified and easy-to-use interface, because users will feel that they are interacting with a modern and user-friendly system. For enterprises, this not only improves customer satisfaction, but also enhances brand image. Moreover, the visual design of the interactive card makes it easier for users to understand information, enhancing the friendliness of human-computer interaction.

[0087] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure; Figure 3 As shown, this embodiment provides a large model-based interactive card generation device 300, including:

[0088] The request acquisition module 301 is used to acquire the user's request;

[0089] The information acquisition module 302 is used to call the corresponding application program interface based on the user's request and obtain the return information of the application program interface;

[0090] The generation module 303 is used to generate the code snippet of the interactive card based on the return information of the application program interface and using the generative large model.

[0091] The large-model-based interactive card generation device 300 of this embodiment implements the implementation principle and technical effect of large-model-based interactive card generation by adopting the above-mentioned modules, which is the same as the implementation of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0092] Figure 4 is a schematic diagram of a fourth embodiment of the present disclosure; this embodiment provides a large model-based interactive card generation device 400, in the above Figure 3 Based on the illustrated embodiment, the technical solution of the present disclosure is further described in more detail. Figure 4 As shown, the generation device 400 of the interactive card based on the large model of this embodiment includes the above Figure 3 Modules with the same name and function are shown as follows: a request acquisition module 401 , an information acquisition module 402 , and a generation module 403 .

[0093] like Figure 4 As shown, the large model-based interactive card generation device 400 of this embodiment further includes:

[0094] The sending module 404 is used to send the code fragment of the interaction card to the front end, so that the front end can render and display the interaction card based on the code fragment of the interaction card.

[0095] Specifically, in this embodiment, the information acquisition module 402 is used to:

[0096] Based on the user's request, identifying a corresponding request category;

[0097] Based on the request category, calling a corresponding application program interface to obtain return information of the application program interface;

[0098] Further optionally, in one embodiment of the present disclosure, the generating module 403 is used to:

[0099] Based on the returned information of the application program interface, a generative large language model is used to obtain a matching target card template from a plurality of pre-configured card templates;

[0100] The generative large model is used to generate the code snippet of the interactive card based on the return information of the application program interface and the target card template.

[0101] Further optionally, in one embodiment of the present disclosure, the generating module 403 is used to:

[0102] Using the generative big model, identifying field identifiers and corresponding field values ​​from the return information of the application program interface;

[0103] The generative large model is used to generate a code snippet of the interactive card based on the target card template, the field identifier and the corresponding field value.

[0104] Further optionally, in one embodiment of the present disclosure, the generating module 403 is used to:

[0105] Based on the return information of the application program interface, the generative large language model is used to identify the field identifier and the corresponding field value;

[0106] The generative big model is used to generate the code snippet of the interactive card based on the field identifier and the field value.

[0107] Further optionally, in one embodiment of the present disclosure:

[0108] The information acquisition module 402 is further used to acquire update information of the interaction card, where the update information is an update triggered by the user based on the interaction card displayed on the front end;

[0109] The generating module 403 is further used to generate an update code snippet of the interactive card based on the update information of the interactive card and using the generative large language model;

[0110] The sending module 404 is further configured to send the updated code fragment of the interaction card to the front end, so that the front end can render and update the interaction card based on the updated code fragment of the interaction card.

[0111] The large-model-based interactive card generation device 400 of this embodiment implements the implementation principle and technical effect of large-model-based interactive card generation by adopting the above-mentioned modules, which is the same as the implementation of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0112] Figure 5 is a schematic diagram according to a fifth embodiment of the present disclosure; this embodiment provides an intelligent agent 500, including:

[0113] An input module 501 is used to receive a user's request;

[0114] The processing module 502 is used to determine the generation task of the interactive card based on the user's request received by the input module, determine the generative model based on the generation task of the interactive card, and execute the above by calling the generative model. Figure 1 or Figure 2 The method described generates a code snippet for an interactive card;

[0115] The output module 503 is used to output the code fragment of the interactive card generated by the processing module.

[0116] The intelligent agent 500 of this embodiment realizes the realization principle and technical effect of generating interactive cards based on large models by adopting the above-mentioned modules, which is the same as the realization of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0117] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0118] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0119] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0120] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0121] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0122] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the above-mentioned methods of the present disclosure. For example, in some embodiments, the above-mentioned methods of the present disclosure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the above-mentioned methods of the present disclosure described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the above-mentioned methods of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0123] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0125] 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.

[0126] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0127] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0128] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0129] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0130] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating an interactive card based on a large model, comprising: Get the user's request; Based on the user's request, calling a corresponding application program interface to obtain return information of the application program interface; Based on the return information of the application program interface, a generative large model is adopted to generate code snippets of the interactive card.

2. The method according to claim 1, wherein: After generating the code snippet of the interactive card based on the return information of the application program interface and using a generative large model, the method further includes: The code snippet of the interaction card is sent to the front end, so that the front end renders and displays the interaction card based on the code snippet of the interaction card.

3. The method according to claim 2, wherein: Based on the user's request, calling a corresponding application program interface to obtain return information of the application program interface; including: Based on the user's request, identifying a corresponding request category; Based on the request category, a corresponding application program interface is called to obtain return information of the application program interface.

4. The method according to claim 2, wherein: Based on the return information of the application program interface, the generative large model is used to generate a code fragment of an interactive card, including: Based on the returned information of the application program interface, a generative large language model is used to obtain a matching target card template from a plurality of pre-configured card templates; The generative large model is used to generate the code snippet of the interactive card based on the return information of the application program interface and the target card template.

5. The method according to claim 4, wherein: The generative large model is used to generate the code snippet of the interactive card based on the return information of the application program interface and the target card template, including: Using the generative big model, identifying field identifiers and corresponding field values ​​from the return information of the application program interface; The generative large model is used to generate a code snippet of the interactive card based on the target card template, the field identifier and the corresponding field value.

6. The method according to claim 2, wherein: Based on the return information of the application program interface, the generative large model is used to generate a code fragment of an interactive card, including: Based on the return information of the application program interface, the generative large language model is used to identify the field identifier and the corresponding field value; The generative big model is used to generate the code snippet of the interactive card based on the field identifier and the field value.

7. The method according to any one of claims 2 to 6, wherein: After sending the code snippet of the interaction card to the front end so that the front end renders and displays the interaction card based on the code snippet of the interaction card, the method further includes: Acquire update information of the interaction card, where the update information is an update triggered by the user based on the interaction card displayed on the front end; Based on the update information of the interaction card, using the generative large language model, generating an update code snippet of the interaction card; The updated code fragment of the interaction card is sent to the front end, so that the front end renders and updates and displays the interaction card based on the updated code fragment of the interaction card.

8. A device for generating an interactive card based on a large model, comprising: Request acquisition module, used to obtain user requests; An information acquisition module, used to call a corresponding application program interface based on the user's request and obtain the return information of the application program interface; A generation module is used to generate code snippets of an interactive card based on the return information of the application program interface and using a generative large model.

9. The device according to claim 8, wherein: The device also includes: The sending module is used to send the code fragment of the interaction card to the front end, so that the front end can render and display the interaction card based on the code fragment of the interaction card.

10. The device according to claim 9, wherein: The information acquisition module is used to: Based on the user's request, identifying a corresponding request category; Based on the request category, a corresponding application program interface is called to obtain return information of the application program interface.

11. The device according to claim 9, wherein: The generating module is used for: Based on the returned information of the application program interface, a generative large language model is used to obtain a matching target card template from a plurality of pre-configured card templates; The generative large model is used to generate the code snippet of the interactive card based on the return information of the application program interface and the target card template.

12. The device according to claim 11, wherein: The generating module is used for: Using the generative big model, identifying field identifiers and corresponding field values ​​from the return information of the application program interface; The generative large model is used to generate a code snippet of the interactive card based on the target card template, the field identifier and the corresponding field value.

13. The device according to claim 9, wherein: The generating module is used for: Based on the return information of the application program interface, the generative large language model is used to identify the field identifier and the corresponding field value; The generative big model is used to generate the code snippet of the interactive card based on the field identifier and the field value.

14. The device according to any one of claims 9 to 13, wherein: The information acquisition module is further used to acquire update information of the interaction card, where the update information is an update triggered by the user based on the interaction card displayed on the front end; The generating module is further used to generate an update code snippet of the interactive card based on the update information of the interactive card and using the generative large language model; The sending module is further used to send the updated code fragment of the interaction card to the front end, so that the front end can render and update the interaction card based on the updated code fragment of the interaction card.

15. An intelligent agent, comprising: An input module, used for receiving an input user's request; a processing module, configured to determine a task for generating an interactive card based on the user's request received by the input module, determine a generative big model based on the task for generating the interactive card, and generate a code fragment for generating an interactive card by calling the generative big model to execute the method according to any one of claims 1 to 7; The output module is used to output the code fragment of the interactive card generated by the processing module.

16. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

17. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

18. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images