Method, device and equipment for generating interactive card based on large model and agent

Abstract

The present disclosure provides a large model-based interactive card generation method and device, electronic equipment and storage medium, which relates to the technical fields of computer vision, large model and artificial intelligence. The specific implementation scheme is: obtaining a request of a user; based on the request of the user, calling a corresponding application programming interface to obtain return information of the application programming interface; based on the return information of the application programming interface, using a generative large model to generate an interactive card. The technology of the present disclosure can effectively improve the generation efficiency of the interactive card in the front end.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to the technical field of computer vision, large model and artificial intelligence, and more particularly to a large model-based interactive card generation method and device, equipment and agent. BACKGROUND

[0002] With the advent of the information age, the communication and cooperation within enterprises increasingly rely on digital tools. Among them, intelligent office systems, as an important means to improve work efficiency, are widely used.

[0003] In the intelligent office system, the interactive card, also known as the work card, as an important component, is usually used to display various information such as the task list of employees, project progress, meeting arrangement, etc. In the prior art, the interactive card is set by manual design and coding implementation. SUMMARY

[0004] The present disclosure provides a large model-based interactive card generation method, device, equipment and agent.

[0005] According to an aspect of the present disclosure, a large model-based interactive card generation method is provided, comprising:

[0006] obtaining a request of a user;

[0007] based on the request of the user, calling a corresponding application program interface, and obtaining return information of the application program interface;

[0008] based on the return information of the application program interface, generating a code segment of the interactive card by using a generative large model.

[0009] According to another aspect of the present disclosure, a large model-based interactive card generation device is provided, comprising:

[0010] a request obtaining module configured to obtain a request of a user;

[0011] an information obtaining module configured to, based on the request of the user, call a corresponding application program interface, and obtain return information of the application program interface;

[0012] a generating module configured to, based on the return information of the application program interface, generate a code segment of the interactive card by using a generative large model.

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

[0014] an input module configured to receive an inputted request of a user;

[0015] The processing module is configured to determine a generation task of an interactive card based on the request of the user received by the input module, determine a generative large model based on the generation task of the interactive card, and generate a code snippet of the interactive card by invoking the generative large model to execute the method of any possible implementation manner of the aspect described above.

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

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

[0018] at least one processor; and

[0019] a memory connected with the at least one processor; wherein

[0020] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any possible implementation manner of the aspect described above.

[0021] According to still another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to cause the computer to execute the method of any possible implementation manner of the aspect described above.

[0022] According to still another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any possible implementation manner of the aspect described above.

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

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

[0025] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

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

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

[0028] Figure 3 is a schematic diagram according to the 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 is a block diagram of an electronic device for implementing the method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Thus, those skilled in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0033] It is obvious that 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 those skilled in the art without creative labor are within the scope of protection of the present disclosure.

[0034] It should be noted that the terminal device involved in the embodiments of the present disclosure can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and the like. The display device can include, but is not limited to, a personal computer, a television, and the like.

[0035] In addition, the term "and / or" in this paper is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects before and after it.

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

[0037] S101, obtaining a request of a user;

[0038] S102, based on the request of the user, call the corresponding application programming interface (API), obtain the return information of the API;

[0039] S103, based on the return information of the API, generate the code segment of the interactive card by using the generative large model.

[0040] The execution subject of the generation method of the interactive card based on the large model in the embodiment is a generation device of the interactive card based on the large model. The device can be set in the front end as a plug-in.

[0041] Specifically, the technical scheme of the embodiment can be applied in an intelligent office system. The generation device of the interactive card based on the large model can be implanted in the front end as a plug-in technology. The device can automatically generate the interactive card intelligently in the front end.

[0042] The interactive card in the embodiment can also be called a Work Card. The Work Card is mainly used to display various task information of employees, including leave information of employees, meeting arrangement information of employees, project information participated or followed by employees, and other task list information. Since the interactive card can be clicked to trigger interaction, it is called an interactive card.

[0043] In the embodiment, the request of the user is a query request initiated by the user. The query request can be various intent requests initiated by the user. For example, 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, and the like.

[0044] In the embodiment, based on the request of the user, the corresponding API is called. Instead of initiating a request to the system corresponding to the API, the request of the user is standardized by means of the API to obtain all field information that can be adapted by the API. Therefore, the return information of the API includes the field information adapted by the API. Finally, based on the return information of the API, the generative large model is used to generate the code segment of the interactive card. Subsequently, the rendering and display of the interactive card can be realized based on the code segment of the interactive card.

[0045] The generative large model used in the embodiment can also be called a generative language model (GLM) or a generative large language model.

[0046] The generation method of the interactive card based on the large model in the embodiment can obtain return information by calling an API based on the request of the user, and intelligently generate a code segment of the interactive card by using a generative large model, so as to overcome the problem that it takes a long time to manually design and code to generate the interactive card in the prior art, and effectively improve the generation efficiency of the interactive card in the front end.

[0047] Moreover, in the prior art, the maintenance cost of the interactive card is very high when the business is frequently changed, and the technical solution in the embodiment can decouple the generation of the interactive card from the business, thereby effectively reducing the maintenance cost of the interactive card.

[0048] Figure 2 is a schematic diagram according to the second embodiment of the disclosure; the generation method of the interactive card based on the large model in the embodiment can further more specifically describe the technical solution of the disclosure based on the technical solution of the embodiment shown in Figure 1 As shown in the embodiment, the generation method of the interactive card based on the large model in the embodiment can specifically include the following steps: Figure 2

[0049] S201, obtaining a request of a user;

[0050] S202, identifying a corresponding request category based on the request of the user;

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

[0052] Because the requests of different users include different contents and the systems for processing the requests of the users are different, the called APIs are different.

[0053] For example, in the embodiment, the request categories of the user requests can include leave approval requests, financial reimbursement requests, or meeting reservation requests, and the like. The leave approval requests correspond to the API of the leave approval system, the financial reimbursement requests correspond to the API of the financial reimbursement system, and the meeting reservation requests correspond to the API of the meeting reservation system.

[0054] In the embodiment, only the API corresponding to the request category is called to obtain the return information of the API after processing the request of the user, and the request of the user is not sent to the corresponding system through the API. The processing of the request of the user by the API is equivalent to the standardized adaptive processing of the request of the user based on a plurality of fields defined by the API, to obtain field information adapted to the request of the user and field information not adapted to the request of the user.

[0055] ​For example, user A initiates a meeting reservation request 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 can include multiple field information, such as the name field, the field value of which can be: the meeting of user A and user B; the time field, the field value of which can be: time C; the participant field: user A and user B; and can also include other fields defined in the API that are not adapted to the user's request, such as the meeting address field, which is temporarily set to empty because the value of this field is not in the user's request. Subsequently, the user can supplement it through interaction. Similarly, other fields can also be included, which will not be listed one by one here.

[0056] That is, the API of various types of systems defines multiple fields required by the system of that type. The user's request can include the values of all fields defined in the API, or only include the values of some fields. The return information of the API must include all fields required by the system of that type, but since the user's request can only include the values of some fields. Therefore, when the return information of the API includes multiple fields, it can include the values of each field, or only include the values of some fields, and the values of the other fields can be empty and can be supplemented later through user interaction.

[0057] Based on the above, it can be seen that the return information of the API in this embodiment can include the identification of the fields adapted to the user's request and the values of the fields; and the identification of the fields not adapted to the user's request.

[0058] Steps S202-S203 are an implementation of the above Figure 1 real-time step S102. Through this way, the return information of the API corresponding to the user's request can be accurately obtained.

[0059] S204, based on the return 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 large model, based on the return information of the API, a code snippet of the interactive card is intelligently generated, without manual design and code writing, which can effectively improve the generation efficiency of the interactive card.

[0061] Specifically, the step S204 can include the following two ways when implemented:

[0062] The first way is to pre-configure multiple card templates, which can include the following steps:

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

[0064] In this embodiment, a plurality of card templates can be pre-configured, and different card templates include different field information. Specifically, the target card template can be obtained according to the identification of all fields included in the return information of the API.

[0065] (2) A generative large model is used to generate a code segment of the interactive card based on the return information of the API and the target card template.

[0066] For example, specifically, a generative large model is used to identify the field identification and the corresponding field value from the return information of the API. Here, the identification of all fields included in the return information of the API and the corresponding field value need to be identified. It should be noted that the field value of some fields can be empty. Then, a generative large model is used to generate a code segment of the interactive card based on the target card template, the field identification and the corresponding field value. That is, the information of the target card template, the field identification and the corresponding field value information need to be included in the automatically generated code segment of the interactive card. The field identification in this embodiment can also refer to the field name.

[0067] This implementation mode can use the natural language understanding and generation capability of the generative large model to automatically select the target card template and fill in the relevant information based on the return information of the API, efficiently and accurately generate a code segment of the interactive card, and thus effectively improve the efficiency and flexibility of generating the interactive card.

[0068] The second way, the direct generation way of the generative large model, can specifically include the following steps:

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

[0070] (b) A generative large model is used to generate a code segment of the interactive card based on the field identification and the field value.

[0071] Compared with the first way described above, in this implementation mode, the pre-configured card template is not used, but the generative large model directly generates it according to the identified field identification and the corresponding field value.

[0072] No matter which way is used, the code segment of the interactive card can be intelligently and automatically generated. Moreover, since the generative large model has very strong functionality, it can also effectively ensure the accuracy of the generated code segment of the interactive card.

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

[0074] The step renders and displays the interactive card for the user to view the interactive card. 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, obtain the update information of the interactive card, which is triggered by the user based on the interactive card displayed by the front end;

[0076] The update information of the embodiment includes supplementary information, for example, as mentioned in the above embodiment, when generating the interactive card, the field values of some fields are empty, at this time, 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 the participants in the above example.

[0077] S207, based on the update information of the interactive card, using the generative large language model, generating an update code segment of the interactive card;

[0078] S208, sending the update code segment of the interactive card to the front end, so that the front end renders and updates the display of the interactive card based on the update code segment 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 content of the interactive card is very convenient and efficient.

[0080] Further, after the generation of the interactive card, a create button can also be set on the interactive card. After the user confirms the interactive card information, clicking the create button can initiate a corresponding task creation request to the corresponding system, so that the corresponding system creates a corresponding task, such as a meeting reservation task, a request for approval task, a financial reimbursement task, etc. Specifically, the system creates a corresponding task, which can refer to the related existing task creation implementation scheme, which is not described here.

[0081] The generation method of the interactive card based on the large model of the embodiment can automatically generate the interactive card based on the driving of the generative large model. This function is based on the 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, which can realize more intelligent and flexible generation of the interactive card of the front end to meet the needs of modern enterprises for office automation and fast information transmission.

[0082] The generation method of the interactive card based on the large model of the embodiment can accurately, efficiently and intelligently generate the interactive card in the front end, effectively improving the speed and quality of generating the interactive card.

[0083] The generation method of the interactive card based on the large model of the present disclosure can also greatly improve the user experience, so that users can more efficiently complete tasks such as appointments, meeting arrangements, etc., without the need to understand the specific details of the background operation.

[0084] Secondly, since the design of the interactive card usually focuses on simplicity and intuitiveness, it helps to reduce the cognitive load of the user, so that they can understand and take action faster.

[0085] Compared with the traditional way of manually filling out forms or relying on email communication, the technical solution of the present disclosure no longer requires users to manually fill out forms or wait for manual replies, greatly shortening the processing time. Through automatic processing by the generative large model, errors caused by human factors can be effectively reduced, and the speed and accuracy of information processing can be significantly improved. In summary, since the human participation link is reduced, the possibility of data entry errors caused by misunderstanding or negligence is also correspondingly reduced. In addition, the automated process also means that services can be provided around the clock without being limited by working hours, further increasing the availability and reliability of services.

[0086] Finally, the generation method of the interactive card based on the large model of the present disclosure can also effectively enhance the user's trust in the brand by providing a unified and easy-to-use interface, as users will feel that they are interacting with a modern and user-friendly system. This not only improves customer satisfaction for businesses, but also enhances the brand image. Moreover, the visual design of the interactive card makes it easier for users to understand the information, enhancing the friendliness of human-computer interaction.

[0087] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure; as Figure 3 shown, the present embodiment provides a generation device 300 of an interactive card based on a large model, which comprises:

[0088] The request acquisition module 301 is configured to acquire the request of the user.

[0089] The information acquisition module 302 is configured to call the corresponding application program interface based on the request of the user, and acquire the return information of the application program interface.

[0090] The generation module 303 is configured to generate a code segment of the interactive card based on the return information of the application program interface by using a generative large model.

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

[0092] Figure 4 is a schematic diagram according to a fourth embodiment of the present disclosure; the fourth embodiment provides a large model-based interactive card generation apparatus 400, which is based on the above-mentioned Figure 3 The technical solutions of the present disclosure are described in further detail based on the above-mentioned embodiments. As shown in Figure 4 The large model-based interactive card generation apparatus 400 of the present embodiment includes the same function modules as shown in the above-mentioned Figure 3 The same function modules as shown in the above-mentioned

[0093] As shown in Figure 4 The large model-based interactive card generation apparatus 400 of the present embodiment further includes:

[0094] The sending module 404 is configured to send the code snippet of the interactive card to the front end, so that the front end renders and displays the interactive card based on the code snippet of the interactive card.

[0095] Specifically, in the present embodiment, the information acquisition module 402 is configured to:

[0096] identify the corresponding request category based on the request of the user;

[0097] invoke the corresponding application program interface based on the request category, and acquire the return information of the application program interface;

[0098] Further optionally, in an embodiment of the present disclosure, the generation module 403 is configured to:

[0099] acquire a target card template that matches from a plurality of card templates pre-configured based on the return information of the application program interface using a generative large language model;

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

[0101] Further optionally, in an embodiment of the present disclosure, the generation module 403 is configured to:

[0102] identify a field identifier and a corresponding field value from the return information of the application program interface using the generative large model;

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

[0104] Further optionally, in an embodiment of the present disclosure, the generation module 403 is configured to:

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

[0106] Based on the field identifier and the field value, the generative large model is used to generate a code segment of the interactive card.

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

[0108] The information acquisition module 402 is also configured to acquire update information of the interactive card, the update information being triggered by the user based on the interactive card displayed on the front end;

[0109] The generation module 403 is also configured to use the generative large language model to generate an update code segment of the interactive card based on the update information of the interactive card.

[0110] The sending module 404 is also configured to send the update code segment of the interactive card to the front end, so that the front end renders and updates the display of the interactive card based on the update code segment of the interactive card.

[0111] The generation apparatus 400 of the interactive card based on the large model of the present embodiment realizes the implementation principle and technical effects of the generation of the interactive card based on the large model by using the above modules, which are the same as the implementation of the above related method embodiments. For details, refer to the description of the above related method embodiments, which will not be repeated here.

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

[0113] The input module 501 is configured to receive an input user request.

[0114] The processing module 502 is configured to determine a generation task of an interactive card based on the user request received by the input module, determine a generative large model based on the generation task of the interactive card, and execute the above Figure 1 Or Figure 2 The method generates a code segment of the interactive card.

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

[0116] The agent 500 of the present embodiment realizes the implementation principle and technical effects of the generation of the interactive card based on the large model by using the above modules, which are the same as the implementation of the above related method embodiments. For details, refer to the description of the above related method embodiments, which will not be repeated here.

[0117] In the technical solutions of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0118] According to embodiments 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 embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

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

[0121] Various 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, a speaker, etc., a storage unit 608, such as a magnetic 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 can be various general-purpose and / or special-purpose 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 specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The computing unit 601 performs various methods and processes described above, such as the above-described methods of the present disclosure. For example, in some embodiments, the above-described methods of the present disclosure can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the computing unit 601, one or more steps of the above-described methods of the present disclosure described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the above-described methods of the present disclosure by any other suitable means, such as by means of firmware.

[0123] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0124] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0125] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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

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

[0128] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0129] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology described in the present disclosure are achieved.

[0130] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating interactive cards based on a large model, comprising: Obtain the user's request; Based on the user's request, the corresponding application programming interface (API) is invoked, and the return information of the API is obtained. The purpose of calling the application programming interface (API) is to perform standardized adaptation processing of the user's request based on multiple fields defined by the API, without sending the user's request to the system corresponding to the API. The return information of the API includes the identifiers and values ​​of the fields in the user's request that can be adapted to the multiple fields, as well as the identifiers of the fields in the multiple fields that the user's request cannot be adapted to. Based on the return information from the application interface, a generative large model is used to generate code snippets for the interactive card.

2. The method according to claim 1, wherein, Based on the return information from the application programming interface, and using a generative large model to generate the code snippet for the interactive card, the method further includes: Send the code snippet of the interactive card to the front end so that the front end can render and display the interactive card based on the code snippet.

3. The method according to claim 2, wherein, Based on the user's request, the corresponding application programming interface (API) is invoked, and the return information of the API is obtained; including: Based on the user's request, identify the corresponding request category; Based on the request category, the corresponding application interface is invoked to obtain the return information of the application interface.

4. The method according to claim 2, wherein, Based on the return information from the application programming interface, and using the generative large model, code snippets for the interactive card are generated, including: Based on the information returned by the application interface, a generative large language model is used to obtain a matching target card template from multiple pre-configured card templates; Using the generative large model, code snippets for the interactive card are generated based on the return information from the application interface and the target card template.

5. The method according to claim 4, wherein, Using the generative large model, based on the return information of the application programming interface and the target card template, code snippets for generating the interactive card are generated, including: Using the generative large model, field identifiers and corresponding field values ​​are identified from the information returned by the application interface; Using the generative large model, code snippets for the interactive card are generated 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 from the application programming interface, and using the generative large model, code snippets for the interactive card are generated, including: Based on the information returned by the application interface, the generative large language model is used to identify field identifiers and corresponding field values. Using the generative large model, code snippets for the interactive card are generated based on the field identifiers and field values.

7. The method according to any one of claims 2-6, wherein, After sending the code snippet of the interactive card to the front end so that the front end can render and display the interactive card based on the code snippet, the method further includes: Obtain the update information of the interactive card, wherein the update information is an update triggered by the user based on the interactive card displayed on the front end; Based on the update information of the interactive card, the generative large language model is used to generate the update code snippet for the interactive card; Send the updated code snippet of the interactive card to the front end, so that the front end can render and update the interactive card based on the updated code snippet.

8. A device for generating interactive cards based on a large model, comprising: The request retrieval module is used to retrieve user requests; The information acquisition module is used to call the corresponding application interface based on the user's request and obtain the return information of the application interface; The purpose of calling the application programming interface (API) is to perform standardized adaptation processing of the user's request based on multiple fields defined by the API, without sending the user's request to the system corresponding to the API. The return information of the API includes the identifiers and values ​​of the fields in the user's request that can be adapted to the multiple fields, as well as the identifiers of the fields in the multiple fields that the user's request cannot be adapted to. The generation module is used to generate code snippets for the interactive card based on the return information from the application interface and using a generative large model.

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

10. The apparatus according to claim 9, wherein, The information acquisition module is used for: Based on the user's request, identify the corresponding request category; Based on the request category, the corresponding application interface is invoked to obtain the return information of the application interface.

11. The apparatus according to claim 9, wherein, The generation module is used for: Based on the information returned by the application interface, a generative large language model is used to obtain a matching target card template from multiple pre-configured card templates; Using the generative large model, code snippets for the interactive card are generated based on the return information from the application interface and the target card template.

12. The apparatus according to claim 11, wherein, The generation module is used for: Using the generative large model, field identifiers and corresponding field values ​​are identified from the information returned by the application interface; Using the generative large model, code snippets for the interactive card are generated based on the target card template, the field identifier, and the corresponding field value.

13. The apparatus according to claim 9, wherein, The generation module is used for: Based on the information returned by the application interface, the generative large language model is used to identify field identifiers and corresponding field values. Using the generative large model, code snippets for the interactive card are generated based on the field identifiers and field values.

14. The apparatus according to any one of claims 9-13, wherein: The information acquisition module is also used to acquire the update information of the interactive card, wherein the update information is an update triggered by the user based on the interactive card displayed on the front end; The generation module is also used to generate update code snippets for the interactive card based on the update information of the interactive card and using the generative large language model. The sending module is also used to send the update code snippet of the interactive card to the front end, so that the front end can render and update the interactive card based on the update code snippet of the interactive card.

15. An intelligent agent, comprising: The input module is used to receive user requests for input. The processing module is configured to determine the generation task of the interactive card based on the user's request received by the input module, determine the generative large model based on the generation task of the interactive card, and generate the code fragment of the interactive card by calling the generative large model to execute the method described in any one of claims 1-7 above. The output module is used to output the code snippets 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 to enable the at least one processor to perform the method of any one of claims 1-7.

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

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

Images