Application collaboration method, electronic equipment and storage medium
By recognizing user intent and using intelligent agents to determine target interfaces, the problem of poor data sharing and interaction between applications is solved, thereby improving the collaborative efficiency and business efficiency between applications.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- FU TAI HUA IND SHENZHEN
- Filing Date
- 2024-10-29
- Publication Date
- 2026-05-08
AI Technical Summary
Poor data sharing and interaction between applications leads to low collaboration efficiency and poor business efficiency.
By recognizing user intent in user requests, intelligent agents determine the target interface and interface information, generate call requests, and securely call the target interface through the interface management platform, thereby enabling data sharing and interaction between applications.
It enables automatic and rapid data sharing and interaction between applications, improving business efficiency and user responsiveness, reducing user waiting time, and enhancing user experience.
Smart Images
Figure CN121997314A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to an application collaboration method, electronic device, and storage medium. Background Technology
[0002] With the continuous advancement of enterprise informatization, various applications (APPs) have become important tools for improving business processing efficiency and user interaction. However, when user needs span multiple applications, the collaboration efficiency between applications is low due to poor data sharing and interaction. Therefore, it often requires manual offline methods to retrieve data from multiple applications separately, and then manually or through system tools to merge the retrieved data. This approach easily leads to fragmented business processes, resulting in poor business efficiency. Summary of the Invention
[0003] In view of the above, it is necessary to provide an application collaboration method, electronic device and storage medium that can solve the technical problem of poor business efficiency caused by poor data sharing and interaction between applications and low collaboration efficiency between applications.
[0004] On the one hand, this application provides an application collaboration method, the method comprising: responding to a user request, identifying the user intent in the user request, determining the target interface in the application corresponding to the user request and the interface information of the target interface through the intelligent agent corresponding to the user intent, generating a call request to the target interface based on the user identity information and the interface information, and calling the target interface through an interface management platform based on the call request to obtain the request result corresponding to the user request.
[0005] In some embodiments of this application, the user intent has a corresponding interface and an information template. The information template includes an information name. The method for obtaining the request result further includes: determining the target information corresponding to the information name in the user request, filling the target information into the corresponding information field in the information template, and if all information fields in the information template are filled with the corresponding target information, using the target information as a calling parameter to call the interface corresponding to the user intent to obtain the request result.
[0006] In some embodiments of this application, if the information template includes at least one unfilled information field, the method further includes: generating a request to obtain target information corresponding to the unfilled information field based on the information name corresponding to the unfilled information field, and using the user's reply information to the request as the target information corresponding to the unfilled information field.
[0007] In some embodiments of this application, determining the target interface and the interface information of the target interface in the application corresponding to the user request through the intelligent agent corresponding to the user intent includes: parsing the user request through a first language model in the intelligent agent to determine the application, determining the target interface from the interfaces of the application, and generating the interface information.
[0008] In some embodiments of this application, the method further includes: acquiring training data, the training data including interface information corresponding to the interfaces of multiple applications, description information of each application and description information of each interface of each application, and training the first language model based on the training data.
[0009] In some embodiments of this application, the step of calling the target interface through the interface management platform based on the call request to obtain the request result corresponding to the user request includes: identifying the user's access rights to the application through the interface management platform based on the identity information in the call request; if the user has the access rights, calling the target interface through the interface management platform based on the interface information in the call request to obtain the request result.
[0010] In some embodiments of this application, the method further includes: acquiring knowledge information from multiple domains, constructing an intelligent agent corresponding to each domain based on the knowledge information from each domain, acquiring user intents corresponding to each domain, and constructing a correspondence between user intents corresponding to each domain and the intelligent agent.
[0011] In some embodiments of this application, the method further includes: obtaining the request result from the interface management platform through the intelligent agent, inputting the request result into a second language model for adjustment through the intelligent agent, and sending the adjusted request result to the user's terminal device.
[0012] On the other hand, this application provides an electronic device, the electronic device comprising: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the application collaboration method.
[0013] On the other hand, this application provides a computer-readable storage medium storing at least one instruction that, when executed by a processor in an electronic device, implements the application collaboration method described above. In the application collaboration scheme provided in this application embodiment, the intelligent agent can be accurately identified by recognizing the user intent in the user request. Through the intelligent agent, the target interface and its interface information in the application corresponding to the user request can be accurately determined, providing a basis for calling the target interface. A call request to the target interface is generated based on the user's identity information and interface information, enabling the interface management platform to verify user permissions for secure and accurate calling of the target interface. The interface management platform can centrally manage and call interfaces of multiple applications. When multiple applications correspond to a user request, the target interface is automatically called based on the call request through the interface management platform, enabling smooth sharing and interaction of data and information between applications, and driving collaborative work among multiple applications. This allows for automatic and rapid acquisition of request results, thereby improving business efficiency. This method of automatically driving application operations not only ensures the collaborative efficiency between applications but also improves the automatic response capability to user requests and reduces user waiting time, thus enhancing the user experience. Attached Figure Description
[0014] Figure 1 This is a flowchart of an application collaboration method provided in an embodiment of this application.
[0015] Figure 2 This is a flowchart of a method for constructing the correspondence between user intent and intelligent agent according to an embodiment of this application.
[0016] Figure 3 This is a flowchart of an application collaboration method provided in another embodiment of this application.
[0017] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0018] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.
[0019] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. Unless otherwise specified, the following embodiments and features described herein can be combined with each other.
[0020] This application provides an application collaboration method that enables automatic response to user requests, thereby accurately and quickly obtaining the request results corresponding to the user requests, and thus improving user experience and business efficiency.
[0021] The application collaboration method provided in this application embodiment can be applied to one or more electronic devices, such as computers, mobile phones, laptops, servers, etc. The server can be a cloud server or a server cluster. This application does not limit the type of electronic device.
[0022] like Figure 1 The diagram shown is a flowchart of an application collaboration method provided in an embodiment of this application. Depending on different needs, the order of the steps in this flowchart can be adjusted according to actual requirements, and some steps can be omitted. The method is applied to electronic devices, such as… Figure 4 The electronic device 10 shown.
[0023] S11, respond to user requests and identify user intent in the user request.
[0024] In some embodiments of this application, the electronic device 10 may use various methods to receive and respond to user requests and identify user intent in user requests, which is not limited in this application.
[0025] For example, electronic device 10 can construct dialogue tools (e.g., a dialogue management assistant) using methods such as Natural Language Processing (NLP) algorithms, machine learning algorithms, deep learning algorithms, dialogue management algorithms, dialogue flow management algorithms, and dialogue management platforms (e.g., Rasa, Dialogflow) to manage user dialogues. Electronic device 10 can receive user requests and identify user intent within those requests through the dialogue tools.
[0026] For example, if a user requests: "I want to buy a movie ticket", the user's intention can be determined by recognizing the user's request through the dialogue tool; if a user requests: "I'm hungry and want to order takeout", the user's intention can be determined by recognizing the user's request through the dialogue tool.
[0027] In this embodiment, since the dialogue tool is built using technologies such as natural language processing, it is possible to quickly identify user intent.
[0028] S12, through the intelligent agent corresponding to the user intent, determine the target interface and interface information of the target interface in the application corresponding to the user request.
[0029] In some embodiments of this application, before invoking the intelligent agent, the electronic device 10 can obtain user identity information, authenticate the user based on the user identity information, and determine whether the user identity is legitimate. If the user identity is determined to be legitimate, the electronic device 10 can invoke the intelligent agent to determine the application corresponding to the user request, the target interface in the application, and the interface information. If the user identity is determined to be illegitimate, the electronic device 10 will not invoke the intelligent agent and will return a prompt message to remind the user that the identity is illegitimate.
[0030] The user identity information can be any information that indicates the user's identity, including but not limited to: facial information, account information, and fingerprint information.
[0031] For example, electronic device 10 can construct an identity authentication agent to authenticate the user based on the user's identity information. The identity authentication agent and the agent corresponding to the user's intent can be programs capable of autonomously performing tasks or achieving goals. For instance, the identity authentication agent can be a program capable of automatically performing identity authentication tasks.
[0032] For example, electronic device 10 can construct an identity authentication model to authenticate the user's identity based on the user's identity information. The identity authentication model can be a model that uses knowledge information such as account information and password for authentication, or a model that uses biometric features such as fingerprints and faces for authentication.
[0033] In this embodiment, security can be ensured by authenticating the user's identity.
[0034] In some embodiments of this application, the electronic device 10 may pre-store the correspondence between user intent and intelligent agent. Through the correspondence, the electronic device 10 can determine the intelligent agent corresponding to the user intent.
[0035] In some embodiments of this application, the electronic device 10 determines the target interface and the interface information of the target interface in the application (APP) corresponding to the user's request through the intelligent agent corresponding to the user's intent, including: parsing the user request through the first language model in the intelligent agent, determining the application, determining the target interface from the interface of the application, and generating interface information.
[0036] The first language model can be considered the "brain" of the intelligent agent, and this application does not limit the type of the first language model. For example, the first language model can be... The application can be one or more. The interface information of the target interface may include the interface name, Uniform Resource Locator (URL) or endpoint address, calling method (such as GET, POST, PUT, DELETE), calling parameters, etc. The above examples of interface information for the target interface are merely illustrative, and are not limited to these in actual applications.
[0037] For example, if a user intends to order takeout, the application for ordering takeout could be a platform that provides takeout services. In some embodiments of this application, the first language model can be trained and adjusted before being invoked, so that the first language model can determine the corresponding application and target interface information according to the user's intent.
[0038] For example, the electronic device 10 can acquire training data, which includes interface information corresponding to the interfaces of multiple applications, description information of each application, and description information of each interface of each application, and train the first language model based on the training data.
[0039] The description of the application's interface information can be referenced above for the description of the target interface's interface information, and will not be repeated here. The application's description information may include name information and functional description, etc. The interface may be an Application Programming Interface (API), and the interface's description information may include the call order, call method, functional description, etc.
[0040] In this embodiment, since the intelligent agent corresponding to the user intent is obtained through adjustment and training, the target interface and interface information of the target interface in the application corresponding to the user request can be quickly and accurately determined through the intelligent agent corresponding to the user intent, thus providing a basis for calling the target interface.
[0041] S13, Generate a call request to the target interface based on the user's identity information and interface information.
[0042] In some embodiments of this application, the electronic device 10 can use the intelligent agent corresponding to the user's intent to concatenate user identity information and interface information into a call request according to the rules of a preset protocol. The preset protocol may be HTTP, HTTPS, or similar protocols.
[0043] In this embodiment, a call request to the target interface is generated based on the user's identity information and interface information, enabling the interface management platform to verify the user's permissions so as to call the target interface securely and accurately.
[0044] In other embodiments of this application, the electronic device 10 can generate a call request for the target interface based on the interface information.
[0045] S14, based on the call request, calls the target interface through the interface management platform to obtain the request result corresponding to the user request.
[0046] In some embodiments of this application, the interface management platform is used to centrally manage the interfaces of various applications and manage the access permissions of various users to the interfaces. Before calling the target interface through the interface management platform, the interfaces of various applications can be registered and the access permissions of users to each interface can be configured.
[0047] In some embodiments of this application, the electronic device 10 can send a call request to the interface management platform through an intelligent agent, so that the electronic device 10 can call the target interface through the interface management platform and obtain the request result corresponding to the user request.
[0048] For example, the electronic device 10 can identify the user's access rights to the application through the interface management platform based on the identity information in the call request. If the user has access rights, the target interface can be called through the interface management platform based on the interface information in the call request to obtain the request result.
[0049] In this embodiment, since the interface information in the call request includes information such as the calling method, calling parameters, and calling order of the target interface, the target interface can be accurately invoked through the interface information in the call request. When multiple applications are requested by the user, the target interface is automatically invoked through the interface management platform based on the call request. This enables smooth sharing and interaction of data and information between applications, as well as driving multiple applications to work collaboratively, thereby automatically and quickly obtaining the request results and improving business efficiency.
[0050] In some embodiments of this application, the electronic device 10 can send the request result to the intelligent agent corresponding to the user's intent through an interface management platform, and then use the intelligent agent corresponding to the user's intent to send the request result to the user's client through a dialogue tool.
[0051] In other embodiments of this application, the electronic device 10 can obtain the request result from the interface management platform through an intelligent agent, input the request result into the second language model for adjustment through the intelligent agent, and send the adjusted request result to the user's client or the user's terminal device.
[0052] This application does not limit the type of the second language model. For example, the second language model can be GPT or Gemini Ultra. The terminal device can be an external device that communicates with the electronic device 10, or it can be the electronic device 10 itself.
[0053] In the application collaboration scheme provided in this application embodiment, the intelligent agent can be accurately identified by recognizing the user intent in the user request. Through the intelligent agent, the target interface and its interface information in the application corresponding to the user request can be accurately determined, providing a basis for calling the target interface. A call request to the target interface is generated based on the user's identity information and interface information, enabling the interface management platform to verify user permissions for secure and accurate calling of the target interface. The interface management platform can centrally manage and call interfaces of multiple applications. When multiple applications correspond to a user request, the target interface is automatically called based on the call request through the interface management platform, enabling smooth sharing and interaction of data and information between applications, and driving collaborative work among multiple applications. This allows for automatic and rapid acquisition of request results, thereby improving business efficiency. This method of automatically driving application operations not only ensures the collaborative efficiency between applications but also improves the automatic response capability to user requests and reduces user waiting time, thus enhancing the user experience.
[0054] like Figure 2 The diagram shown is a flowchart of a method for constructing the correspondence between user intent and intelligent agent according to an embodiment of this application.
[0055] S111, acquire knowledge and information from multiple fields.
[0056] This application does not limit the type of field. For example, multiple fields may include weather forecasting, movie ticketing, food delivery services, fault analysis, education and training, etc.
[0057] For example, in the field of weather query, knowledge information may include meteorological data, geographical location information, etc.; in the field of movie ticketing, knowledge information may include cinema information, movie schedules, ticket price rules, etc.; in the field of food delivery services, knowledge information may include restaurant information, menus, delivery rules, etc.; in the field of fault analysis, knowledge information may include equipment information, fault phenomena, repair methods, etc.
[0058] S112, Based on the knowledge information of each domain, construct the intelligent agent corresponding to each domain.
[0059] For example, the electronic device 10 can generate a training set based on the knowledge information of each domain, construct the model structure of the intelligent agent corresponding to each domain using the framework of natural language processing, machine learning, deep learning and other models, and train and optimize the model structure using the training set to obtain the intelligent agent corresponding to each domain.
[0060] Among them, domain-based knowledge information can be called domain intelligent agents.
[0061] S113, Obtain the user intent corresponding to each domain.
[0062] This application does not impose any restrictions on the method of obtaining user intent. For example, user intent can be obtained from user input.
[0063] For example, the user intent in the weather query domain could be to query the weather; the user intent in the movie ticketing domain could be to book movie tickets; the user intent in the food delivery service domain could be to order food delivery; and the user intent in the fault analysis domain could be to analyze faults.
[0064] S114, Construct the correspondence between user intents and intelligent agents for each domain.
[0065] In this embodiment, by constructing a correspondence between user intents and intelligent agents in each domain, the electronic device 10 can quickly determine the intelligent agent corresponding to the user intent based on the correspondence.
[0066] like Figure 3 The diagram shown is a flowchart of an application collaboration method provided in another embodiment of this application. S21, respond to the user request and identify the user intent in the user request.
[0067] In some embodiments of this application, the user intent has a corresponding interface and information template. The information template includes at least one information name, and each information name has a corresponding information field.
[0068] For example, if the user's intention is to book movie tickets, the corresponding interface for booking movie tickets could be the API interface of an application that provides movie ticket sales services. The information name in the information template can be customized.
[0069] For example, if a user intends to book movie tickets, the information template for booking movie tickets can be shown in the following example: Book movie tickets: {Movie title:} Cinema Name: time: quantity: Seating location:}
[0070] Among them, the movie title, cinema name, time, quantity, and seat location are all information names.
[0071] For an explanation of the method for recognizing user intent, please refer to the description of step S11, which will not be repeated here.
[0072] S22, determine the target information corresponding to the information name in the user request.
[0073] In some embodiments of this application, the electronic device 10 can use methods such as natural language recognition and keyword extraction to identify target information in a user request that matches the information name.
[0074] For example, if a user requests: "I want to buy a movie ticket named B at cinema A at 7 pm", we can determine that the movie name is B, the cinema name is A, the quantity is 1, and the time is 7 pm.
[0075] S23, fill the target information into the corresponding information field in the information template.
[0076] In some embodiments of this application, since the information template includes an information field corresponding to each information name, the electronic device 10 can write the determined target information into the corresponding information field in the information template.
[0077] For example, following the above embodiment, if the movie name is determined to be B, the cinema name to be A, the quantity to be 1, and the time to be 19:00 in the information name, then the movie name B, the cinema name A, the quantity to be 1, and the time to be 19:00 are respectively filled into the information fields of the information template. The filled information template can be referred to as the following example: Book movie tickets: {Movie title: B} Cinema Name: A Time: 19:00 Quantity: 1 Seating location:}
[0078] S24, Determine whether the information template includes unfilled information fields.
[0079] In this embodiment, if the information template includes at least one unfilled information field, step S25 is executed; if all information fields in the information template are filled with the corresponding target information, step S27 is executed.
[0080] S25, Generate a request to obtain the target information corresponding to the unfilled information field based on the information name corresponding to the unfilled information field.
[0081] In some embodiments of this application, the electronic device 10 may send the generated acquisition request to the user's client or the user's terminal device.
[0082] For example, continuing from the above embodiment, if the information field corresponding to the seat location is not filled, the electronic device 10 can generate a request based on the seat location. For example, the request could be: Please enter your desired viewing location.
[0083] In this embodiment, when the information template includes at least one unfilled information field, more information can be obtained by sending the generated retrieval request to the user's client or the user's terminal device, providing a basis for accurately calling the interface.
[0084] S26, the user's response to the request is used as the target information for the unfilled information field.
[0085] For example, if the user's reply is "Row 5, Seat 9", the electronic device 10 can fill the information field corresponding to the seat position with the reply "Row 5, Seat 9". The filled information template can be seen in the following example: Book movie tickets: {Movie title: B} Cinema Name: A Time: 19:00 Quantity: 1 Seating location: Row 5, Seat 9.
[0086] S27: Use the target information as a call parameter to call the interface corresponding to the user's intent and obtain the request result.
[0087] For example, following the above embodiments, target information such as B, A, 19:00, 1, and 5th row, 9th seat can be used as calling parameters to call the movie ticket booking interface and obtain the request result. The request result may include information such as booking status, order number, payment link, booking confirmation information, and seat details.
[0088] In the application collaboration scheme provided in this application embodiment, since the target information includes comprehensive information of the interface call, by using the target information as a call parameter to call the interface corresponding to the user intent and obtain the request result, the response efficiency of the user request and the efficiency of obtaining the request result can be improved. Through the intelligent information capture and filling mechanism, the user's operation process can be simplified and the user's waiting time can be reduced, thereby improving the user experience.
[0089] like Figure 4 The diagram shown is a structural schematic of an electronic device 10 provided in an embodiment of this application. The electronic device 10 can be a computer, mobile phone, tablet computer, laptop computer, server, or other similar device. This application embodiment does not impose any restrictions on the specific type of the electronic device 10.
[0090] exist Figure 4The electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the input / output interface 104 via the bus 105.
[0091] Communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as Universal Serial Bus (USB) and Controller Area Network (CAN). The wireless communication module may provide one or more wireless communication solutions such as Wireless Fidelity (Wi-Fi), Bluetooth (BT), mobile communication networks, frequency modulation (FM), near field communication (NFC), and infrared (IR).
[0092] Memory 102 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM can be directly read and written by the processor 103, and can be used to store executable programs (e.g., machine instructions) of other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.
[0093] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 103. Non-volatile memory can include disk storage devices and flash memory.
[0094] Memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 103. The one or more computer programs include multiple instructions that, when executed by processor 103, enable an application coordination method to be executed on electronic device 10.
[0095] In other embodiments, such as Figure 4 The electronic device 10 shown also includes an external memory interface for connecting to an external memory to expand the storage capacity of the electronic device 10.
[0096] Processor 103 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.
[0097] The processor 103 provides computing and control capabilities, for example, the processor 103 is used to execute computer programs stored in the memory 102 to implement the application collaboration method described above.
[0098] The input / output interface 104 is used to provide a channel for user input or output. For example, the input / output interface 104 can be used to connect various input / output devices, such as a mouse, keyboard, touch device, display screen, etc., so that users can enter information or visualize information.
[0099] Bus 105 is used at least to provide a channel for communication between communication modules 101, memory 102, processor 103, and input / output interface 104 in electronic device 10.
[0100] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 10. In other embodiments of this application, the electronic device 10 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0101] This application also provides a computer-readable storage medium storing a computer program, which includes program instructions. When the program instructions are executed, the method implemented can refer to the methods in the above embodiments of this application.
[0102] The computer-readable storage medium can be the internal memory of the electronic device described in the above embodiments, such as the hard disk or memory of the electronic device. Alternatively, the computer-readable storage medium can be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., installed on the electronic device.
[0103] In some embodiments, a computer-readable storage medium may include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of the electronic device, etc.
[0104] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.
[0105] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0106] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.
[0107] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No appended diagram markings in the claims should be construed as limiting the scope of the claims.
[0108] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this application may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.
[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.
Claims
1. A collaborative application method, characterized in that, The method includes: Respond to user requests and identify the user intent in the user requests; The target interface and its interface information in the application corresponding to the user's request are determined by the intelligent agent corresponding to the user's intent. A request to invoke the target interface is generated based on the user's identity information and the interface information. Based on the call request, the target interface is called through the interface management platform to obtain the request result corresponding to the user request.
2. The application collaboration method as described in claim 1, characterized in that, The user intent has a corresponding interface and information template, the information template includes an information name, and the method for obtaining the request result further includes: Determine the target information corresponding to the information name in the user request; Fill the target information into the corresponding information field in the information template; If all information fields in the information template are filled with the corresponding target information, the target information is used as a calling parameter to call the interface corresponding to the user intent and obtain the request result.
3. The application collaboration method as described in claim 2, characterized in that, If the information template includes at least one unfilled information field, the method further includes: Generate a request to retrieve the target information corresponding to the unfilled information field based on the information name corresponding to the unfilled information field. The user's response to the request is used as the target information corresponding to the unfilled information field.
4. The application collaboration method as described in claim 1, characterized in that, The step of determining the target interface in the application corresponding to the user request and the interface information of the target interface through the intelligent agent corresponding to the user intent includes: The application is determined by parsing the user request using the first language model in the intelligent agent, the target interface is determined from the interface of the application, and the interface information is generated.
5. The application collaboration method as described in claim 4, characterized in that, The method further includes: Acquire training data, which includes interface information corresponding to the interfaces of multiple applications, description information of each application, and description information of each interface of each application. The first language model is trained based on the training data.
6. The application collaboration method as described in claim 1, characterized in that, The step of obtaining the request result corresponding to the user request by calling the target interface through the interface management platform based on the call request includes: Based on the identity information in the call request, the interface management platform identifies the user's access permissions to the application; If the user has the access permission, the target interface is invoked through the interface management platform based on the interface information in the call request to obtain the request result.
7. The application collaboration method as described in claim 1, characterized in that, The method further includes: Acquire knowledge and information from multiple fields; Based on the knowledge information of each domain, construct the intelligent agent corresponding to each domain; Obtain the user intent corresponding to each of the aforementioned domains; Construct a correspondence between the user intent and the intelligent agent for each domain.
8. The application collaboration method as described in claim 1, characterized in that, The method further includes: The intelligent agent obtains the request result from the interface management platform. The intelligent agent inputs the request result into the second language model for adjustment, and then sends the adjusted request result to the user's terminal device.
9. An electronic device, characterized in that, The electronic device includes: Memory, storing at least one instruction; and The processor executes the at least one instruction to implement the application collaboration method as described in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction that, when executed by a processor in an electronic device, implements the application collaboration method as described in any one of claims 1 to 8.