Data processing method and device, computer device, and storage medium

Abstract

Embodiments of the present application disclose a data processing method and device, computer equipment and a storage medium, and belong to the field of artificial intelligence. The method comprises the following steps: displaying a data interface, the data interface displays at least two modules, each module comprises a group of data; in response to a first interaction operation, displaying an artificial intelligence (AI) receiving slot based on the data interface, the AI receiving slot is used for storing a module to be processed; storing at least one module in the data interface into the AI receiving slot; in response to a second interaction operation, processing data of the at least one module, and displaying a data processing result. The present application simplifies user operation, saves operation time, and improves data processing efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a data processing method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the rapid development of AI (Artificial Intelligence) technology, data processing technology based on AI models has been gradually applied to various applications. AI models have stronger understanding and learning capabilities, and data processing based on AI models can significantly reduce labor costs and improve data processing efficiency.

[0003] To use an AI model to analyze data, users can manually take a screenshot of the data interface, open an application with AI data processing capabilities, display the AI ​​interactive interface, select the screenshot, and input the image into the AI ​​interactive interface to obtain the data processing results returned by the AI ​​model.

[0004] However, the data processing described above involves cumbersome and time-consuming operations for users. Summary of the Invention

[0005] This application provides a data processing method, apparatus, computer equipment, and storage medium, which simplifies user operations, saves operation time, and improves data processing efficiency. The technical solution is as follows: On the one hand, a data processing method is provided, the method comprising: The data display interface has at least two modules, each module including a set of data; In response to the first interactive operation, an AI receiving slot is displayed, which is used to store modules to be processed; Store at least one module of the data interface into the AI ​​receiving slot; In response to the second interactive operation, the data of the at least one module is processed and the data processing result is displayed.

[0006] Optionally, the method further includes: If the pulling operation ends before the specified ratio reaches the first specified ratio, a bounce animation will be displayed on the data interface.

[0007] Optionally, the step of displaying the artificial intelligence (AI) receiver slot in response to a first interactive operation on the data interface includes: In response to a pull operation on the data interface, the AI ​​receiving slot is displayed in the area between the current position and the original position of the edge of the data interface that has been pulled.

[0008] Optionally, the method further includes: dynamically displaying each module in the data interface during the display of the AI ​​receiving slot.

[0009] Optionally, the method further includes: dynamically displaying each module icon in the AI ​​receiving slot during data processing.

[0010] Optionally, the method further includes at least one of the following: When the AI ​​receiver slot is first displayed, each module in the data interface is set to a draggable state; When the AI ​​receiver slot is first displayed, a drag-and-drop operation is initiated to detect each module in the data interface.

[0011] On the other hand, a data processing method is provided, the method comprising: The receiving terminal sends a data processing request, which carries structured data. The structured data includes data of various target types. The structured data is obtained by converting data from at least one module, screenshots of the at least one module, and question text. The at least one module is a module that stores data from the data interface displayed on the terminal into the AI ​​receiving slot. In response to the data processing request, the structured data is processed using an AI model to obtain the data processing result; The data processing result is sent to the terminal.

[0012] Optionally, the data of the multiple target types further includes at least one module identifier, which is used to represent a module in the data interface; The method further includes: Query the second knowledge data corresponding to the module identifier; The creation of prompt words that match the question text includes: Create prompt words that match the question text and the second knowledge data. The prompt words are used to instruct the AI ​​model to answer the question text based on the multiple target types of data and with reference to the second knowledge data.

[0013] On the other hand, a data processing apparatus is provided, the apparatus comprising: A display unit is used to display a data interface, wherein the data interface displays at least two modules, and each module includes a set of data. The display unit is also configured to respond to the first interactive operation by displaying an artificial intelligence (AI) receiving slot, which is used to store modules to be processed. A module storage unit is used to store at least one module from the data interface into the AI ​​receiving slot; A data processing unit is configured to process the data of the at least one module in response to a second interactive operation and display the data processing results.

[0014] Optionally, the display unit is configured to, in response to a pull operation on the data interface, obtain the ratio between the pull distance and the height of the display screen; and, if the ratio reaches a first ratio, display the AI ​​receiving slot based on the data interface.

[0015] Optionally, the display unit is further configured to: If the specified ratio does not reach the second ratio, a first prompt message is displayed on the data interface; the first prompt message is used to suggest releasing the data interface and then refreshing it; or... If the ratio reaches the second ratio but has not yet reached the first ratio, a second prompt message is displayed on the data interface; the second prompt message is used to prompt the user to continue dragging the data interface to process the data. The second ratio is smaller than the first ratio.

[0016] Optionally, the display unit is further configured to display a bounce animation of the data interface when the pulling operation ends if the ratio does not reach the first ratio.

[0017] Optionally, the display unit is configured to display the AI ​​receiving slot in the area between the current position and the original position of the edge of the data interface that is being pulled, in response to a pull operation on the data interface.

[0018] Optionally, the display unit is used to dynamically display each module in the data interface during the process of displaying the AI ​​receiving slot.

[0019] Optionally, the display unit is used to dynamically display each module icon in the AI ​​receiving slot during data processing.

[0020] Optionally, the display unit is used for at least one of the following: When the AI ​​receiver slot is first displayed, each module in the data interface is set to a draggable state; When the AI ​​receiver slot is first displayed, a drag-and-drop operation is initiated to detect each module in the data interface.

[0021] Optionally, the module storage unit is used to drag and drop the first module to the AI ​​receiving slot and then release it, displaying the first module icon corresponding to the first module in the AI ​​receiving slot; the first module is any module in the data interface.

[0022] Optionally, the module storage unit is configured to, in response to a touch operation on the first module, display a screenshot of the first module at the location of the first module; in response to a movement of the touch position of the touch operation, display the screenshot moving with the touch position of the touch operation; if the screenshot is located in the AI ​​receiving slot when the touch operation ends, display the screenshot disappearing after moving to the target position in the AI ​​receiving slot, and display the first module icon at the target position.

[0023] Optionally, the display unit is further configured to display that if the screenshot is located outside the AI ​​receiving slot when the touch operation ends, the screenshot will move to the location of the first module and then disappear.

[0024] Optionally, the module storage unit is used to obtain the current position of the first module during the dragging process; perform collision detection on the first module and the AI ​​receiving slot based on the position; highlight the AI ​​receiving slot when the first module collides with the AI ​​receiving slot; and display the first module icon in the AI ​​receiving slot when the dragging of the first module ends.

[0025] Optionally, a virtual character is displayed in the AI ​​receiving slot. The virtual character is used to refer to the AI ​​model that performs data processing. The module storage unit is used to highlight the virtual character when the first module collides with the AI ​​receiving slot.

[0026] Optionally, the data processing unit is configured to display the data processing result in an AI interactive interface located above the data interface; or, display the data processing result in the AI ​​receiving slot or in an adjacent area of ​​the AI ​​receiving slot; or, jump to the AI ​​interactive interface and display the data processing result in the AI ​​interactive interface.

[0027] Optionally, the display unit is further configured to display a text input box corresponding to the AI ​​receiving slot, and display recommended question text in the text input box, wherein the recommended question text matches the data of the at least one module; The data processing unit is configured to respond to the second interactive operation, process the data of the at least one module based on the question text in the text input box, and display the data processing result.

[0028] Optionally, the data processing unit is configured to, in response to the second interactive operation, convert the data of the at least one module, the text encoding corresponding to the screenshot of the at least one module, and the question text into structured data, wherein the structured data includes data of various target types; process the structured data through an AI model to obtain the data processing result, and display the data processing result.

[0029] Optionally, the data processing unit is configured to call the server's application programming interface to send a data processing request to the server, the data processing request carrying the structured data; the server is configured to respond to the data processing request by processing the structured data through the AI ​​model to obtain a data block representing the data processing result; and display the data block whenever it receives the data block sent by the server.

[0030] On the other hand, a data processing apparatus is provided, the apparatus comprising: A receiving unit is used to receive a data processing request sent by a terminal. The data processing request carries structured data, which includes data of various target types. The structured data is obtained by converting data from at least one module, screenshots of the at least one module, and question text. The at least one module is a module that stores data from the data interface displayed on the terminal into an artificial intelligence (AI) receiving slot. A data processing unit is configured to respond to the data processing request by processing the structured data using an AI model to obtain the data processing result. A sending unit is used to send the data processing result to the terminal.

[0031] Optionally, the data processing unit is configured to, in response to the data processing request, parse the structured data to obtain data of the multiple target types, the multiple target types including question text; create prompt words matching the question text, the prompt words being used to instruct the AI ​​model to answer the question text based on the multiple target types of data; and process the multiple target types of data based on the prompt words through the AI ​​model to obtain the data processing result.

[0032] Optionally, the data processing unit is configured to acquire the preference features of the terminal, the preference features representing the user preferences of the terminal; query first knowledge data in the database matching the preference features; and create the prompt word matching the question text, the preference features, and the first knowledge data, the prompt word instructing the AI ​​model to answer the question text based on the multiple target types of data and with reference to the preference features and the first knowledge data.

[0033] Optionally, the data of the multiple target types further includes at least one module identifier, which is used to represent a module in the data interface; The data processing unit is used to query the second knowledge data corresponding to the module identifier; create the prompt word that matches the question text and the second knowledge data, and the prompt word is used to instruct the AI ​​model to answer the question text based on the data of the multiple target types and with reference to the second knowledge data.

[0034] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to perform the operations performed by the data processing method as described above.

[0035] On the other hand, a computer-readable storage medium is provided that stores at least one computer program, which is loaded and executed by a processor to perform the operations performed by the data processing method described above.

[0036] In another aspect, a computer program product is provided, comprising a computer program that, when executed by a processor, performs the operations performed by the data processing method described above.

[0037] In this embodiment, when displaying a modular data interface, the AI ​​receiving slot can be activated by performing a first interactive operation. The user can then store any module from the data interface into the AI ​​receiving slot and perform a second interactive operation to process the data of the stored module and display the processing results. This embodiment allows users to initiate a data processing flow without leaving the data interface by performing simple first and second interactive operations, simplifying user operations, saving operation time, improving data processing efficiency, and ensuring that users can personalize the selection of the modules they need to process, providing ample flexibility. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application.

[0040] Figure 2 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application.

[0041] Figure 3 This is a schematic diagram of the structure of a server provided in an embodiment of this application.

[0042] Figure 4 This is a flowchart of a data processing method provided in an embodiment of this application.

[0043] Figure 5 This is a schematic diagram of a data interface provided in an embodiment of this application.

[0044] Figure 6 This is a flowchart of a method for displaying an AI receiving slot provided in an embodiment of this application.

[0045] Figure 7 This is a schematic diagram of the structure of a data interface provided in an embodiment of this application.

[0046] Figure 8 This is a schematic diagram of a first prompt message provided in an embodiment of this application.

[0047] Figure 9 This is a schematic diagram of a second prompt message provided in an embodiment of this application.

[0048] Figure 10 This is a schematic diagram of an AI receiving slot provided in an embodiment of this application.

[0049] Figure 11 This is a schematic diagram of the response flow of a pull operation provided in an embodiment of this application.

[0050] Figure 12 This is an operational schematic diagram of a module provided in an embodiment of this application.

[0051] Figure 13 This is a flowchart of another data processing method provided in the embodiments of this application.

[0052] Figure 14 This is a schematic diagram of a screenshot provided in an embodiment of this application.

[0053] Figure 15 This is a schematic diagram of a module icon provided in an embodiment of this application.

[0054] Figure 16 This is a schematic diagram of a process for creating a screenshot provided in an embodiment of this application.

[0055] Figure 17 This is a schematic diagram of a screenshot processing flow provided in an embodiment of this application.

[0056] Figure 18 This is a schematic diagram of another screenshot provided in an embodiment of this application.

[0057] Figure 19 This is a schematic diagram of another module icon provided in an embodiment of this application.

[0058] Figure 20 This is a schematic diagram of a drag-and-drop process provided in an embodiment of this application.

[0059] Figure 21 This is a schematic diagram of the processing flow of a terminal provided in an embodiment of this application.

[0060] Figure 22 This is a schematic diagram of the interaction process between a terminal and a server provided in an embodiment of this application.

[0061] Figure 23 This is a schematic diagram of an AI interactive interface provided in an embodiment of this application.

[0062] Figure 24 This is a schematic diagram of the state switching process of an AI receiving slot provided in an embodiment of this application.

[0063] Figure 25 This is a flowchart of another data processing method provided in the embodiments of this application.

[0064] Figure 26 This is a schematic diagram of the preference features and preference feature matching database provided in the embodiments of this application.

[0065] Figure 27 This is a schematic diagram of another interaction process between a terminal and a server provided in an embodiment of this application.

[0066] Figure 28 This is a schematic diagram of a server processing flow provided in an embodiment of this application.

[0067] Figure 29 This is a schematic diagram illustrating the service capabilities of a server provided in an embodiment of this application.

[0068] Figure 30 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application.

[0069] Figure 31 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application.

[0070] Figure 32 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application.

[0071] Figure 33This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0073] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0074] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0075] It is understood that the terms "first," "second," etc., used in this application may be used to describe various concepts herein, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of this application, the first module may be referred to as the second module, and similarly, the second module may be referred to as the first module.

[0076] "At least one" refers to one or more modules. For example, at least one module can be one module, two modules, three modules, or any integer number of modules greater than or equal to one. "Multiple" refers to two or more modules. For example, multiple modules can be two modules, three modules, or any integer number of modules greater than or equal to two. "Each" refers to each of the at least one modules. For example, each module refers to each of the multiple modules. If the multiple modules are three modules, then each module refers to each of the three modules.

[0077] It should be noted that the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals (including but not limited to signals transmitted between user terminals and other devices) involved in this application have all been fully authorized by the user or relevant parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0078] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application. The implementation environment includes a terminal 110 and a server 120. The terminal 110 is connected to the server 120 via a wireless network or a wired network.

[0079] Optionally, the terminal 110 may be a smartphone, tablet, laptop, desktop computer, virtual reality device, augmented reality device, etc., but is not limited to these.

[0080] Optionally, server 120 may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0081] Optionally, server 120 undertakes the main computing work and terminal 110 undertakes the secondary computing work; or, server 120 undertakes the secondary computing work and terminal 110 undertakes the main computing work; or, server 120 and terminal 110 use a distributed computing architecture for collaborative computing.

[0082] Server 120 is used to provide data to terminal 110. Terminal 110 displays a data interface with at least two modules, each of which includes a set of data provided by server 120.

[0083] Optionally, terminal 110 runs an application associated with server 120, through which a data interface is displayed. This application can be a standalone application or a mini-program within an application. Alternatively, the data interface can be a webpage provided by server 120, such as an HTML5 (Hypertext Markup Language 5) page. In other words, server 120 is a web server, and terminal 110 displays webpages provided by server 120.

[0084] Optionally, the data interface is used to display data of the target object; that is, at least one module in the data interface contains data of the target object, used to introduce the target object. In addition to data belonging to the target object, the data interface may also include other data, such as data belonging to other objects, public data published by server 120, or data recommended to the user.

[0085] During the display of the data interface on terminal 110, the user of terminal 110 can browse the data in the data interface, or interact with the target object of the data interface through the interactive controls displayed in the data interface. If the user needs to process the data in the data interface, they can perform a first interactive operation in the data interface. In response to the first interactive operation, terminal 110 displays an AI receiving slot, which is used to store modules to be processed. The user can drag at least one module from the data interface to the AI ​​receiving slot, thereby storing at least one module in the AI ​​receiving slot. Subsequently, the user triggers a second interactive operation. In response to the second interactive operation, terminal 110 processes the data of the module currently stored in the AI ​​receiving slot, obtains the data processing result, and displays the data processing result.

[0086] Optionally, server 120 is equipped with an AI model for data processing. In response to the second interaction, terminal 110 retrieves the data currently stored in the AI ​​receiving slot and sends a data processing request to server 120, carrying the data. Server 120 responds to the data processing request, processes the data based on the AI ​​model, obtains the processing result, and returns it to terminal 110. Terminal 110 receives the processing result and displays it on the data interface.

[0087] Those skilled in the art will understand that the number of terminals described above can be more or less. For example, there may be only one terminal (such as the management terminal of server 120), or there may be 10 or more terminals. This application does not limit the number of terminals.

[0088] Optionally, see Figure 2 Terminal 110 includes a view layer 111, a state management layer 112, a business logic layer 113, and a data service layer 114.

[0089] The view layer 111 is used to display the data interface and respond to interactive operations within the data interface. The view layer 111 includes a pull gesture detection unit, an interface dragging unit, and a result display unit. The pull gesture detection unit detects pull gestures on the data interface, the interface dragging unit allows dragging modules within the data interface, and the result display unit displays the data processing results based on the data interface.

[0090] The state management layer 112 manages various state changes of the data interface during interaction and updates the display based on these changes. For example, as the data interface is dragged, the state and display style change accordingly with different drag distances. The state management layer 112 includes a gesture state management unit, a module state management unit, and an AI state management unit. The gesture state management unit manages the state of gesture operations, such as dividing drag operations into different states based on the drag distance. The data interface state differs depending on the drag operation state. The module state management unit manages the state of modules in the data interface. Module states can include non-draggable, draggable, and dragging states. The interactive operations that can be performed on the module may differ in different states, and the module's display style may also differ. The AI ​​state management unit manages the state of the AI ​​receiving slot. The AI ​​receiving slot states include no module stored, module stored, data processing in progress, and data processing completed. The AI ​​receiving slot's display style may differ in different states.

[0091] The business logic layer 113 performs background calculations based on the data interface, updating the gesture state, module state, and AI receiver slot state in the state management layer 112 based on the calculation results. The business logic layer 113 includes a gesture calculation engine, a collision detection engine, and a data processing engine. The gesture calculation engine calculates various parameters of gesture operations, such as the dragging distance for a pull operation and the coordinates of the touch position for a touch operation. The collision detection engine detects whether a dragged module in the data interface collides with the AI ​​receiver slot. The data processing engine performs background calculations based on the detected parameters to obtain the calculation results.

[0092] The data service layer 114 interacts with the server 120, including: transmitting data to be processed from the data interface to the server 120 for processing, and displaying the data processing results returned by the server 120 on the terminal 110. The data service layer 114 includes a data service unit, an image generation service unit, and an AI invocation service unit. The data service unit extracts data from one or more modules in the data interface, the image generation service unit generates images based on the data in the data interface, and the AI ​​invocation service unit requests the server 120 to invoke an AI model for data processing.

[0093] Optionally, see Figure 3 Server 120 includes access layer 121, service layer 122 and infrastructure 123.

[0094] Access layer 121 is the entry point for interaction between terminal 110 and server 120.

[0095] Service layer 122 provides at least one service for data processing. The services provided by service layer 122 include: multimodal parsing service, prompt word generation service, and AI processing service. The multimodal parsing service parses the data sent by terminal 110, converting it into structured data. The prompt word generation service generates personalized matching prompt words based on the structured data and other information from terminal 110 (including account information, user-inputted question text, etc.). The AI ​​processing service uses the structured data and prompt words to call the underlying AI model, obtains the data processing result output by the AI ​​model, and then returns it to terminal 110 through access layer 121.

[0096] Infrastructure 123 includes OCR (Optical Character Recognition), underlying AI models, cloud storage services, MySQL (My Structured Query Language, a relational database), Redis (Remote Dictionary Server), and Kafka (a distributed message queue). OCR is used to automatically recognize text from images. The underlying AI models possess text understanding, multimodal perception, and logical reasoning capabilities, enabling data processing based on input structured data and prompts to obtain data processing results. Cloud storage services are used to store data such as images, documents, time-frequency data, logs, and model files. MySQL is used to store structured data and supports data query operations. Redis is a database capable of high-speed read and write operations based on memory and can be used for data caching. Kafka, based on a publish-subscribe model, enables asynchronous message transmission and can be used to report data processing requests, OCR recognition requests, etc.

[0097] It should be noted that the above implementation environment is only an example, and other implementation environments can also be used in the embodiments of this application, which will not be described in detail here.

[0098] Figure 4 This is a flowchart of a data processing method provided in an embodiment of this application. The execution subject of this embodiment is a terminal, which can be, for example, Figure 1 The terminal 110 shown or other terminals. For example... Figure 4 As shown, the method includes: 401. The terminal displays a data interface, which has at least two modules, each of which includes a set of data.

[0099] Each module can be a GUI (Graphical User Interface) control in the data interface that allows for independent operation. The data in each module can include multiple fields.

[0100] Optionally, the data interface is used to display data about the target object; that is, at least one module in the data interface contains data about the target object, used to introduce the target object. In addition to data belonging to the target object, the data interface may also include other data, such as data belonging to other objects, publicly available data published by the server, or data recommended to the user.

[0101] For example, the data interface is an interface for introducing the target object, and at least two modules in the data interface are used to introduce the target object from different dimensions.

[0102] For example, see Figure 5 This data interface serves as an introduction to the target product. It displays at least two modules, each containing a set of data for the target product. These modules include: a price quote module 501, a candlestick chart module 502, a record module 503, and an information module 504. The price quote module 501 displays the target product's name, code, and other attribute information, as well as its current price, percentage change, opening price, highest price, and lowest price. The candlestick chart module 502 displays the target product's candlestick chart. The record module 503 displays records of buy, sell, and order cancellations related to the target product, along with statistical data derived from these records, such as the percentage of different user types. The information module 504 displays news headlines, research reports, announcements, and other information.

[0103] For example, this data interface might be an introduction screen for the target video. This interface displays at least two modules, each containing a set of data for the target video. These at least two modules could include an attribute module, a playback history module, and an interaction statistics module. The attribute module includes the target video's attribute information, such as author, publication time, and genre. The playback history module includes the target video's playback history, such as the number of plays and completion rate. The interaction statistics module includes the target video's interaction history, such as the number of likes, comments, and shares.

[0104] For example, this data interface is an interaction interface between the currently logged-in account and associated accounts on the terminal. This interaction interface displays at least two modules, each of which includes a set of interaction messages between the currently logged-in account and associated accounts. The interaction messages may include text or images, etc.

[0105] 402. The terminal responds to the first interactive operation and displays the AI ​​receiving slot, which is used to store modules to be processed.

[0106] The first interactive operation is used to wake up the AI ​​receiver slot. This first interactive operation can be clicking on the AI ​​control in the data interface, dragging the data interface, inputting a wake-up command via voice, or shaking the terminal. When the terminal detects the first interactive operation, it displays the AI ​​receiver slot.

[0107] Optionally, the terminal displays the AI ​​receiver slot in the data interface, and the AI ​​receiver slot occupies a portion of the data interface. Alternatively, while maintaining the data interface display state, the terminal displays the AI ​​receiver slot on top of the data interface, where the AI ​​receiver slot does not occupy any area of ​​the data interface, but may obscure a portion of the data interface.

[0108] The AI ​​receiving slot is used to store modules to be processed. When the data processing flow is initiated later, the data from the modules stored in the AI ​​receiving slot will be processed by the AI ​​model. Therefore, the AI ​​receiving slot can also be called the "data feeding area" of the AI ​​model.

[0109] 403. The terminal stores at least one module from the data interface into the AI ​​receiving slot.

[0110] Since the AI ​​receiving slot is used to store modules to be processed, if a user needs to process a certain module in the data interface, they can store that module in the AI ​​receiving slot.

[0111] The terminal may store modules in the AI ​​receiving slot by dragging or dropping modules into the AI ​​receiving slot, or, in response to a triggering operation of adding controls in the AI ​​receiving slot, displaying a selection marker for each module in the data interface, and storing the selected module in the AI ​​receiving slot when the selection marker for any one or more modules is selected.

[0112] It should be noted that after the module is stored in the AI ​​receiving slot, the module can still be displayed normally in the data interface and still support the original interactive operations. That is, storing the module in the AI ​​receiving slot will not affect the original function of the module in the data interface.

[0113] 404. The terminal responds to the second interactive operation, processes the data of at least one module, and displays the data processing results.

[0114] After storing at least one module to be processed into the AI ​​receiving slot, the user can trigger a second interactive operation. The second interactive operation indicates that the AI ​​receiving slot has finished storing the module and the data processing flow can be started. The terminal responds to the second interactive operation, processes the data of the module currently stored in the AI ​​receiving slot, obtains the data processing result, and displays the data processing result on the data interface.

[0115] Optionally, a confirmation control is displayed in the AI ​​receiving slot to indicate that the storage module has been completed. The second interactive operation can be triggering the confirmation control in the AI ​​receiving slot. Alternatively, an AI control is displayed in the data interface to initiate queries to the AI ​​model. This AI control can be displayed in the AI ​​receiving slot or below it, etc., and the second interactive operation can be triggering the AI ​​control. Furthermore, the second interactive operation can be, if the module is already stored in the AI ​​receiving slot, voice input of keywords or shaking the terminal, etc.

[0116] In related technologies, if a user wants to use an AI model to analyze data, they need to manually take a screenshot of the data interface, open an application with AI data processing capabilities, display an AI interactive interface within the application, select the screenshot, and input the image into the AI ​​interactive interface to obtain the data processing results returned by the AI ​​model. The entire operation path involves 5-7 steps and takes 25-40 seconds.

[0117] In this embodiment, when displaying a modular data interface, the AI ​​receiving slot can be activated by performing a first interactive operation. The user can then store any module from the data interface into the AI ​​receiving slot and perform a second interactive operation to process the data of the stored module and display the processing results. This embodiment allows users to initiate a data processing flow without leaving the data interface by performing simple first and second interactive operations, simplifying user operations, saving operation time, improving data processing efficiency, and ensuring that users can personalize the selection of the modules they need to process, providing ample flexibility.

[0118] In related technologies, if a user needs to process different data, they must input different question texts, asking questions about different data separately. The AI ​​model then answers each question based on its specific text. However, this separate questioning and answering approach leads to a loss of context, making it impossible to connect different data points and resulting in a lack of correlation between them in the processed data. In this embodiment, however, by storing multiple modules in the AI ​​receiving slot, data from multiple modules can be processed uniformly at once. This not only processes the data from each module individually but also comprehensively considers the correlation between the data from different modules, ensuring that the processed data includes the relationships between different data points and is more accurate.

[0119] Based on the above embodiments, Figure 6 This is a flowchart illustrating a method for displaying an AI receiving slot according to an embodiment of this application. The execution subject of this method is a terminal, which can be, for example, Figure 1The terminal 110 shown or other terminals. For example... Figure 6 As shown, the method includes: 601. The terminal displays a data interface with at least two modules, each module containing a set of data.

[0120] Figure 7 This is a schematic diagram of the structure of a data interface provided in an embodiment of this application. Taking the data interface as an example, the five modules are arranged in the data interface in sequence.

[0121] Each module's data includes the following data items: 1. Module Identifier: This is a unique identifier for a module. Different modules within the same data interface have different module identifiers. Therefore, the module identifier is used to distinguish different modules within the same data interface. For example, in the product introduction interface, the quotation module, candlestick chart module, record module, and information module each have their own module identifier. However, in data interfaces of the same type but belonging to different target objects, modules of the same type have the same module identifier. For example, the quotation module for Product 1 and the quotation module for Product 2 have the same module identifier.

[0122] 2. Module Type: Used to indicate the type of module, such as quotation module, candlestick chart module, record module, and information module.

[0123] 3. Module Source Data: This is the module's raw data, used by the terminal when displaying the module. It can be the same as the data displayed in the module, or it can contain more information. Module data can be obtained by the terminal from the server hosting the data interface.

[0124] For example, the candlestick chart module displays candlestick charts. The source data of the candlestick chart module must include data such as the transaction price and transaction time of each transaction of the target product in order to display statistical data such as the real-time transaction price, the average price of the day, and the intraday transaction price of the target product in the candlestick chart.

[0125] 4. Module position: This indicates the position of the module in the data interface. It is represented by coordinates, which can be the coordinates of a vertex in the module, such as the x and y coordinates of the top left vertex.

[0126] The terminal abstracts each component in the data interface into a module, assigns a module identifier and module type to each module, uses the data source in the component as module data, and records the module's position in the data interface as the module location. The data of each module in the data interface is configured in the above standardized format, and the data of the modules to be processed can subsequently be transmitted to the backend server in the same standardized format for use by the server when calling the AI ​​model.

[0127] 602. The terminal responds to the drag operation on the data interface and obtains the ratio between the drag distance and the height of the display screen.

[0128] The drag operation on the data interface refers to sliding along any edge of the data interface in the direction of the opposite side after the interface has been displayed. The drag distance is the distance slid along any edge in the direction of the opposite side. This edge can be the entire edge of the data interface, or it can be the edge of a draggable area within the data interface. For example, if the data interface includes a title bar that cannot be dragged and a draggable data area, the drag operation refers to dragging the data area within the data interface, and the dragged edge is the edge of the data area.

[0129] For example, if the top edge of the data interface is already displayed, swiping down on the data interface is a pull-down operation; if the bottom edge of the data interface is already displayed, swiping up on the data interface is a pull-up operation; if the left edge of the data interface is already displayed, swiping right on the data interface is a pull-right operation; and if the right edge of the data interface is already displayed, swiping left on the data interface is a pull-left operation.

[0130] The height of the display screen refers to the height of the display screen in the direction in which the data interface is dragged. For example, if the dragging operation is to slide the data interface down or up, the height of the display screen refers to the height of the display screen in the vertical direction. If the dragging operation is to slide the data interface left or right, the height of the display screen refers to the height of the display screen in the horizontal direction.

[0131] 603. If the terminal does not reach the second ratio, it displays a first prompt message on the data interface. The first prompt message is used to prompt the user to release the data interface and refresh it.

[0132] The terminal is configured with a first ratio and a second ratio, where the second ratio is smaller than the first ratio. For example, the first ratio is 10%, and the second ratio is 25%. The second ratio represents the ratio between the pulling distance required to display the second prompt message and the height of the display screen; that is, the second prompt message is displayed when the ratio between the pulling distance and the height of the display screen reaches the second ratio. The first ratio represents the ratio between the pulling distance required to display the AI ​​receiver slot and the height of the display screen; that is, the AI ​​receiver slot can be displayed when the ratio between the pulling distance and the height of the display screen reaches the first ratio.

[0133] In the initial stage of the pull operation, the pull distance is short and the ratio between the pull distance and the height of the display screen is small, not yet reaching the second ratio. At this time, the first prompt message is displayed to prompt the user to stop the pull operation. After releasing the data interface, the data interface can be refreshed.

[0134] Optionally, in response to a drag operation on the data interface, the terminal moves the data interface following the drag operation and displays a first prompt message in the area between the current position and the original position of the dragged edge of the data interface.

[0135] See Figure 8 When the terminal detects a pull-down operation, if the ratio between the pull-down distance and the height of the display screen does not reach the second ratio, the data interface moves down following the pull-down operation and displays the first prompt message 802 "Refresh after releasing" in the empty area 801 at the top of the data interface.

[0136] 604. If the terminal reaches the second ratio but has not yet reached the first ratio, it displays a second prompt message on the data interface; the second prompt message is used to prompt the user to continue dragging the data interface to process the data.

[0137] As the drag operation is executed, the drag distance gradually increases, and the ratio between the drag distance and the height of the display screen gradually increases until it reaches a second ratio, but has not yet reached the first ratio. At this point, a second prompt message is displayed, prompting the user to continue dragging. AI technology can be used to process the data in the data interface.

[0138] Optionally, if the first prompt message is displayed in the area between the current position and the original position of the edge of the data interface that is being dragged, then when the ratio reaches the second ratio, the first prompt message in that area is replaced with the second prompt message.

[0139] Optionally, the terminal adjusts the size of the area between the current position and the original position of the edge of the data interface being pulled based on the ratio between the current pulling distance and the height of the display screen, so that the area increases as the pulling distance increases and decreases as the pulling distance decreases.

[0140] See Figure 9 If the ratio reaches the second ratio but has not yet reached the first ratio, a second prompt message 803, "Continue scrolling down, AI will help you analyze market advantages," will be displayed in the empty area 801 at the top of the data interface. See also... Figure 8 and Figure 9 The area 801 when displaying the first prompt message is smaller than the area 801 when displaying the second prompt message.

[0141] 605. When the terminal reaches the first ratio, it displays the AI ​​receiving slot.

[0142] As the pulling operation is executed, the pulling distance gradually increases, and the ratio between the pulling distance and the height of the display screen gradually increases until the ratio reaches the first ratio, at which point the AI ​​receiving slot is displayed.

[0143] Optionally, displaying the AI ​​receiver slot includes: displaying the AI ​​receiver slot in the area between the current position and the original position of the edge of the data interface that is being pulled.

[0144] See Figure 10 When the drag operation is a pull-down operation, the AI ​​receiving slot 1001 is displayed on the outer edge of the top edge of the data interface, above the existing data. When the drag operation is a pull-up operation, the AI ​​receiving slot is displayed on the outer edge of the bottom edge of the data interface, below the existing data. When the drag operation is a pull-left operation, the AI ​​receiving slot is displayed on the outer edge of the right edge of the data interface, to the right of the existing data. When the drag operation is a pull-right operation, the AI ​​receiving slot is displayed on the outer edge of the left edge of the data interface, to the left of the existing data.

[0145] Optionally, after the terminal displays the AI ​​receiver slot, it locks the AI ​​receiver slot. Thereafter, even if the terminal detects operations such as swiping on the data interface, it will not automatically de-display the AI ​​receiver slot. Furthermore, while the AI ​​receiver slot is displayed, the data interface still supports responsiveness to swiping or other interactive operations. That is, while the AI ​​receiver slot is displayed, in response to swiping on the data interface, the terminal will swipe the data interface while maintaining the AI ​​receiver slot's display state, thereby displaying different modules within the data interface. Similarly, in response to interactive operations on the data interface (such as clicking on interactive controls), the terminal will also respond to the interactive operation while maintaining the AI ​​receiver slot's display state.

[0146] Optionally, during the display of the AI ​​receiving slot, the terminal can respond to the interface jump operation and maintain the display state of the AI ​​receiving slot when jumping from the current data interface to another data interface, so as to store the modules in the data interface after the jump to the AI ​​receiving slot.

[0147] Optionally, see Figure 10The AI ​​receiving slot 1001 displays a third prompt message 1002, which indicates that data to be processed is stored in the AI ​​receiving slot 1001. Optionally, the AI ​​receiving slot 1001 may also display a virtual character 1003 representing the AI ​​model, indicating that the data will be processed by the virtual character 1003. Optionally, the AI ​​receiving slot 1001 may also display controls such as a close control 1004 and a jump entry point 1005 for the AI ​​interactive interface. Users can trigger the close control 1004 to close the AI ​​receiving slot and restore the data interface to its original state, or they can trigger the jump entry point 1005 for the AI ​​interactive interface to jump to the AI ​​interactive interface and interact with the AI ​​model in the AI ​​interactive interface.

[0148] In another embodiment, the method further includes: if the pulling operation ends before the first ratio is reached, then a bounce animation of the data interface is displayed. This bounce animation shows the edge of the data interface that was pulled moving back to its original position before the pulling operation, and the data interface also bounces back to its position before the pulling operation. The first or second prompt information displayed on the outer area of ​​this edge is then canceled.

[0149] Figure 11 This is a schematic diagram of the response flow of a pull operation provided in an embodiment of this application. See also... Figure 11 The response process for a pull operation includes: 1101. When a drag operation on the data interface is detected, record the initial coordinates and timestamp of the data interface.

[0150] The initial coordinates represent the position of the data interface at the start of the drag operation. These initial coordinates can be the coordinates of any vertex in the data interface, such as the top-left or top-right vertex.

[0151] 1102. Determine the current coordinates of the data interface in real time. The distance between the current coordinates and the initial coordinates is the drag distance.

[0152] The coordinates on the data interface can be the coordinates on the coordinate axis corresponding to the direction of the pull. For example, if the pull operation is a pull-down operation, then the coordinates on the data interface are the vertical coordinates, excluding the horizontal coordinates.

[0153] 1103. Determine the pulling ratio based on the pulling distance and the height of the display screen.

[0154] The drag ratio is (current Y - start Y) / Height, where current Y represents the current coordinate, start Y represents the initial coordinate, and Height represents the height of the display screen.

[0155] 1104. Determine whether the pull ratio has reached the first or second ratio, and respond based on the determination result.

[0156] Different judgment results lead to different response methods and different visual feedback effects on the data interface. If the drag ratio does not reach the second ratio, the first prompt message is displayed; if the drag ratio reaches the second ratio but does not reach the first ratio, the second prompt message is displayed; if the drag ratio reaches the first ratio, the AI ​​receiving slot is locked, the modules in the data interface are separated, and they are displayed dynamically.

[0157] Optionally, the terminal is equipped with a state machine to manage various states of the data interface and the switching conditions between these states. Initially, the data interface is in standby mode, displaying data normally. Then, a pull operation begins. If the pull percentage is less than a first percentage, the data interface switches to a pull-down prompt state, displaying a prompt message. As the pull percentage gradually increases, reaching the first percentage, the data interface switches to a receiver slot locked state, displaying the AI ​​receiver slot and locking it. Alternatively, if the pull operation ends before reaching the first percentage, a data interface bounce animation is displayed, and the data interface returns to standby mode.

[0158] 1105. Pulling operation completed.

[0159] Optionally, during the display of the AI ​​receiver slot, the terminal dynamically displays each module in the data interface separately. By dynamically displaying each module separately, the user's attention can be attracted, making it easier for the user to distinguish between different modules, and actively guiding the user to store the modules in the AI ​​receiver slot, thereby increasing the probability of the user using the AI ​​receiver slot.

[0160] Optionally, dynamically displaying the module includes at least one of the following: displaying a jittering animation of the module, adding dynamic effects to the module, and adding dynamic markers to the display area of ​​the module.

[0161] Optionally, the method further includes at least one of the following: When the AI ​​receiver slot is first displayed, make each module in the data interface draggable; When the AI ​​receiver slot is first displayed, initiate drag-and-drop operations for each module in the detection data interface.

[0162] See Figure 12When the terminal reaches the first drag ratio and begins displaying the AI ​​receiving slot, it iterates through each module in the data interface. For each module, it initiates drag operation detection and sets the module to a draggable state so that users can drag the module subsequently. Furthermore, it starts a shaking animation for the module to visually represent the module shaking.

[0163] Additionally, in draggable mode, each module displays its own boundary line, allowing users to clearly view the boundaries of each module within the data interface. Draggable mode can also be considered a detached state, where different modules are separated from each other.

[0164] For example, see Figure 9 and Figure 10 Before the AI ​​receiver slot is displayed on the terminal, each module in the data interface does not show all its boundary lines, and the boundaries between different modules are not obvious. This makes it easy for users to browse the data of different modules in a focused manner without creating a strong sense of fragmentation. After the AI ​​receiver slot is displayed on the terminal, each module in the data interface shows its own boundary lines, and the boundaries between different modules are clear. This makes it easy for users to select the module they want to drag to the AI ​​receiver slot and avoids dragging the wrong module.

[0165] Optionally, the module can be set to a draggable state by setting it to absolute positioning, so that the module is freed from the layout constraints of the data interface and its position is completely controlled by the module's own coordinates. In this way, during the dragging process, the module's coordinates can be adjusted accordingly based on the position of the drag operation to change the module's position in the data interface and achieve the effect of dragging the module.

[0166] After displaying the AI ​​receiving slot, the terminal can store the data interface module in the AI ​​receiving slot, thereby processing the data from the module. See the following embodiment for details of the processing procedure.

[0167] In this embodiment, when displaying a modular data interface, the AI ​​receiving slot can be activated by dragging the data interface. The user can drag any module from the data interface into the AI ​​receiving slot and perform a second interactive operation to process the module's data and display the processing results. This embodiment allows users to initiate a data processing flow without leaving the data interface through simple interactive operations, simplifying user operations, saving operation time, improving data processing efficiency, and ensuring that users can personalize the selection of the modules they need to process, providing ample flexibility.

[0168] This embodiment divides the data interface into multiple stages based on the ratio between the dragging distance and the height of the display screen. In the initial stage, a first prompt message is displayed, instructing the user to release the data interface to refresh it. In the middle stage, a second prompt message is displayed, prompting the user to continue dragging the data interface for data processing. In the later stage, the AI ​​receiving slot is activated, allowing the user to store modules that need processing within the data interface. This avoids displaying the AI ​​receiving slot when the dragging distance is too short, reducing the probability of accidental operation and preventing unnecessary waste of processing resources, while also ensuring the smoothness of the user's normal use of the data interface. Furthermore, it comprehensively considers different user needs, distinguishing between refreshing the data interface and displaying the AI ​​receiving slot as two different operations, achieving layered control of operational resources.

[0169] Based on the above embodiments, Figure 13 This is a flowchart of a data processing method provided in an embodiment of this application. The execution subject of this embodiment is a terminal, which can be, for example, Figure 1 The terminal 110 shown or other terminals. For example... Figure 13 As shown, the method includes: 1301. The terminal displays a data interface with at least two modules, each containing a set of data.

[0170] 1302. The terminal responds to the first interactive operation and displays the AI ​​receiving slot, which is used to store modules to be processed.

[0171] Steps 1301-1302 are similar to steps 401-402 and 601-605, and will not be repeated here.

[0172] 1303. After the terminal drags the first module to the AI ​​receiving slot and releases it, the first module icon corresponding to the first module will be displayed in the AI ​​receiving slot; the first module can be any module in the data interface.

[0173] In this embodiment, modules can be stored in the AI ​​receiving slot by dragging and dropping them. Taking the first module as an example, when a user drags and drops the first module into the AI ​​receiving slot and then releases it, the terminal detects that the first module has been released into the AI ​​receiving slot and displays the first module icon in the AI ​​receiving slot to indicate that the first module is stored there.

[0174] The process of determining whether the first module is released in the AI ​​receiving slot includes: when the drag operation on the first module ends, obtaining the current position of the center point of the first module, determining whether the position is located in the AI ​​receiving slot, if so, determining to release the first module in the AI ​​receiving slot, if not, determining to release the first module outside the AI ​​receiving slot.

[0175] In this embodiment, when displaying a modular data interface, after waking up the AI ​​receiving slot, the user can drag any module from the data interface into the AI ​​receiving slot and perform a second interactive operation to process the data of the module in the AI ​​receiving slot and display the data processing results. The drag-and-drop operation is simple, convenient, and easy to implement, enabling rapid storage of modules in the AI ​​receiving slot and improving storage efficiency. Furthermore, displaying module icons in the AI ​​receiving slot clearly presents the stored modules, providing timely feedback to the user without needing to display the module's raw data, saving display space and facilitating the display of multiple module icons in the AI ​​receiving slot, thus improving organization.

[0176] Optionally, in response to a touch operation on the first module, the terminal displays a screenshot of the first module at the location of the first module; in response to the movement of the touch position of the touch operation, the displayed screenshot moves with the touch position of the touch operation; if the screenshot is located in the AI ​​receiving slot when the touch operation ends, the displayed screenshot moves to the target position in the AI ​​receiving slot and then disappears, and the first module icon is displayed at the target position.

[0177] When a user performs a touch operation on the first module but hasn't yet moved the touch location, the terminal creates a screenshot of the first module and displays it at the module's location. Since the screenshot's size is the same as the first module's size, it sits on top of the first module, covering it, but isn't displayed simultaneously. The user can only see the screenshot identical to the first module in the data interface. If the user then moves the touch location while maintaining the touch operation, the screenshot moves with the touch location, while the first module remains in its original position. When the touch operation ends, the screenshot of the first module is released, indicating the first module has been released. If the screenshot is currently in the AI ​​receiver slot, it is moved to the target location and then its display is canceled, with the first module's icon appearing at the target location, creating the visual effect of the screenshot transforming into the first module's icon.

[0178] See Figure 14 When a user presses the quotation module 1401 in the data interface, a screenshot 1402 of the quotation module 1401 is created and displayed. The screenshot 1402 is then moved to follow the touch position and released into the AI ​​receiving slot 1403. See [link / description]. Figure 15 The quotation module icon 1404 is displayed in the AI ​​receiving slot 1403. At this time, the quotation module 1401 is displayed normally, and the screenshot 1402 has disappeared.

[0179] Figure 16 This is a flowchart illustrating a screenshot creation process provided in an embodiment of this application. See also... Figure 16 The process of creating a screenshot includes: 1601. For any module A in the data interface, detect touch events on module A, record the coordinates of the touch point, the position and size of module A, and determine whether the touch point is located within the draggable area.

[0180] 1602. If the touch point is located within the draggable area, create screenshot A of module A. ’ Module A remains unchanged.

[0181] 1603. Set screenshot A ’ Information such as display style, position, and shadow effects.

[0182] 1604. Screenshot A is displayed. ’ And start following the touch point, dragging screenshot A ’ .

[0183] For example, after the terminal creates a screenshot of the first module, it converts the screenshot into the corresponding text encoding and caches the text encoding. When processing the data of the first module subsequently, the cached text encoding can be extracted and processed along with the data. This text encoding is used to describe the information contained in the screenshot in text form, and can be either Base64 encoding (a method of representing binary data based on 64 printable characters) or other encodings.

[0184] In this embodiment of the application, during the drag-and-drop process, a screenshot of the module is used to replace the module. The content displayed in the module and the screenshot are the same. Dragging the screenshot can simulate the effect of dragging the module, and it will not affect the normal display state of the module itself in the data interface, thus taking into account the dual needs of dragging the module and displaying the module normally.

[0185] Optionally, the target location can be any available location in the AI ​​receiving slot, or the terminal can pre-set multiple target locations in the AI ​​receiving slot, and arbitrarily select one of the target locations each time a module needs to be stored. Alternatively, the terminal can use a location selection algorithm to select one of the multiple target locations each time a module needs to be stored, so as to ensure that the distribution of used target locations in the AI ​​receiving slot is as even as possible.

[0186] For example, the AI ​​receiving slot displays a circular marker with multiple target positions set on it. These target positions are arranged sequentially. Each time a module needs to be stored, one of the remaining target positions on the circular marker is selected to minimize the sum of the distances between that target position and all the already occupied target positions. After the module icon corresponding to the currently stored module is displayed at that target position, the module icon can be evenly distributed among the other module icons, avoiding the situation where some areas display more module icons than others, thus improving the display effect of the AI ​​receiving slot.

[0187] In another embodiment, the method further includes: if the screenshot is outside the AI ​​receiving slot when the touch operation ends, then the screenshot is shown to disappear after moving to the location of the first module.

[0188] Although the touch position was moved during the touch operation, the screenshot was not located in the AI ​​receiving slot when the touch operation ended, but outside the AI ​​receiving slot. This indicates that the user did not drag the first module to the AI ​​receiving slot, but dragged it to another location. Therefore, the first module icon will not be displayed in the AI ​​receiving slot, and the screenshot will bounce back, simulating the effect of the module returning to its original position after dragging. This provides timely visual feedback to the user's operation, and lets the user know that the module was not successfully stored, enhancing interactivity, avoiding user misoperation, and improving the smoothness of human-computer interaction and user trust.

[0189] The process of determining whether the screenshot is located in the AI ​​receiving slot at the end of the touch operation includes: at the end of the touch operation, obtaining the current position of the center point of the screenshot, determining whether the position is located in the AI ​​receiving slot, if yes, determining that the screenshot is located in the AI ​​receiving slot at the end of the touch operation, if no, determining that the screenshot is located outside the AI ​​receiving slot at the end of the touch operation.

[0190] Figure 17 This is a schematic diagram of a screenshot processing flow provided in an embodiment of this application. See also... Figure 17 The screenshot processing workflow includes: 1701. Touch operation released.

[0191] 1702. Determine whether the release position of the touch operation is located in the AI ​​receiving slot. If yes, proceed to step 1703; otherwise, proceed to step 1704.

[0192] 1703. Move the screenshot to the target location in the AI ​​receiver slot and remove the screenshot.

[0193] 1704. Redirect the screenshot to its original position and remove the screenshot.

[0194] During the display process of the AI ​​receiving slot, the terminal can execute step 507 for one or more modules in the data interface respectively. Then, one or more module icons can be displayed in the AI ​​receiving slot to indicate that the AI ​​receiving slot stores the data of the module to which these module icons belong.

[0195] See Figure 18If the price quote module 1401 is already stored in the AI ​​receiver slot, and the user touches the candlestick chart module 1407 in the data interface, a screenshot 1408 of the candlestick chart module 1407 will be created and displayed. Then, the screenshot 1408 will move with the touch position and be released from the AI ​​receiver slot 1403. See [link to relevant documentation]. Figure 19 The AI ​​receiver slot 1403 displays the quotation module icon 1404 and the candlestick module icon 1409.

[0196] Optionally, during the process of dragging the first module, the terminal obtains the current position of the first module; based on the position, it performs collision detection between the first module and the AI ​​receiving slot; when the first module collides with the AI ​​receiving slot, the AI ​​receiving slot is highlighted; and when the dragging of the first module ends, the icon of the first module is displayed in the AI ​​receiving slot.

[0197] The current position of the first module can be the current position of its center point, or, when dragging a screenshot of the first module, the current position of the center point of the screenshot. This position updates accordingly as the dragging operation progresses. A collision between the first module and the AI ​​receiver slot occurs when the first module's current position is at the edge of the AI ​​receiver slot, or when its position changes from outside the AI ​​receiver slot to inside it. Once a collision is detected, the AI ​​receiver slot is highlighted, increasing its visibility and providing timely visual feedback to the user. This indicates that the first module has entered the AI ​​receiver slot, allowing the user to end the dragging operation. This enhances interactivity, prevents accidental user actions, and improves the smoothness of human-computer interaction and user trust.

[0198] For example, highlighting the AI ​​receiving slot when the first module collides with it includes changing the AI ​​receiving slot from a static display to a dynamic display. For instance, if each module icon and other elements in the AI ​​receiving slot are originally statically displayed, then upon collision, each element in the AI ​​receiving slot is displayed with a jittering motion, or each module icon in the AI ​​receiving slot is moved clockwise or counterclockwise on a circular marker.

[0199] For example, a virtual character is displayed in the AI ​​receiving slot. This virtual character represents the AI ​​model performing data processing, enabling the AI ​​model to be personified or objectified, thus displaying it intuitively and increasing the user's sense of familiarity with the AI ​​model. Highlighting the AI ​​receiving slot when the first module collides with it includes: highlighting the virtual character when the first module collides with the AI ​​receiving slot. Examples include changing the virtual character's color to a more prominent color, adding virtual decorations, enlarging the virtual character's size, or dynamically displaying the virtual character.

[0200] When the first module collides with the AI ​​receiving slot, the virtual character is highlighted instead of using rigid text prompts. This provides immediate feedback to the user's actions, reduces the difficulty of understanding, and enhances vividness and fun. It also brings the user closer to the virtual character, increases the user's trust in the AI ​​function, and thus increases the probability of the user using the AI ​​model.

[0201] For example, see Figure 14 and Figure 18 The virtual character originally displayed in the AI ​​receiving slot was small in size, and other areas were used to display module icons. However, when the screenshot 1408 of the K-line module 1407 collided with the AI ​​receiving slot 1403, the size of the virtual character was enlarged, and the module icons were temporarily canceled from display.

[0202] While highlighting the virtual character, the display style of other elements in the AI ​​receiver slot can remain unchanged, or one or more other elements in the AI ​​receiver slot can be temporarily hidden, using the freed-up area to display the virtual character. After dragging and dropping the first module, restore the AI ​​receiver slot and each element in the AI ​​receiver slot to their original display style.

[0203] Figure 20 This is a schematic diagram of a drag-and-drop process provided in an embodiment of this application. See also... Figure 20 The drag-and-drop process includes: 2001. Begin dragging and dropping modules.

[0204] 2002. The module enters drag-and-drop mode and records the module's initial position.

[0205] 2003. During the drag-and-drop process, the latest position of the module is recorded in real time.

[0206] 2004. Collision detection is performed on the module and the AI ​​receiver slot.

[0207] 2005. Based on the collision detection results, determine whether the module has entered the AI ​​receiving slot. If yes, proceed to step 2006; otherwise, proceed to step 2008.

[0208] 2006. Highlight the AI ​​receiver slot, including highlighting the AI ​​receiver slot and vibrating the terminal.

[0209] 2007. Once the drag-and-drop operation on the module is complete and the module is located in the AI ​​receiving slot, the module will be snapped to the target location and disappear. The corresponding module icon will then be displayed at the target location.

[0210] 2008, the AI ​​receiver slot remains in its normal display state.

[0211] 2009. When the drag-and-drop operation on the module is completed and the module is outside the AI ​​receiving slot, the module will be bounced back to its original position and disappear.

[0212] Optionally, the AI ​​receiver slot supports continuous storage of modules. That is, when a module is stored in the AI ​​receiver slot, the terminal caches the data of that module. Even if the AI ​​receiver slot is closed later, the cached data will not be lost. When the terminal redisplays the AI ​​receiver slot, the module icon corresponding to that module will still be displayed in the AI ​​receiver slot.

[0213] Optionally, the AI ​​receiver slot supports deleting stored modules. If a user wants to delete a module from the AI ​​receiver slot, they can trigger a deletion operation on the module icon corresponding to that module. The terminal will then remove the module icon from the AI ​​receiver slot and delete the data corresponding to that module icon from the cache.

[0214] Optionally, in response to a touch operation on the first module, the terminal creates a snapshot based on the current data of the first module and caches the snapshot. Subsequently, if the screenshot of the first module is in the AI ​​receiving slot when the touch operation ends, the cached snapshot is retained; if the screenshot of the first module is not in the AI ​​receiving slot when the touch operation ends, the cached snapshot is deleted. Alternatively, if the screenshot of the first module is in the AI ​​receiving slot when the touch operation on the first module ends, a snapshot is created based on the current data of the first module.

[0215] The data in the snapshot is identical to the current data in the first module; the snapshot can be considered a copy of the first module. Subsequent processing of the data in the first module actually refers to processing the data in the cached snapshot. Furthermore, the data in the first module is updated in real time and may change, while the data in the snapshot remains unchanged.

[0216] 1304. The terminal responds to the second interactive operation, processes the data corresponding to each module icon displayed in the AI ​​receiving slot, and displays the data processing results.

[0217] The second interactive operation is used to instruct the start of the data processing process. The terminal then obtains the data corresponding to each module icon displayed in the AI ​​receiving slot, processes the obtained data, obtains the data processing result, and displays the data processing result.

[0218] Optionally, when storing the module in the AI ​​receiving slot, the terminal caches the module's data in the form of a snapshot. In response to the second interactive operation, the terminal retrieves the snapshot of the module from the cache and processes the data in the snapshot.

[0219] Optionally, the method further includes: the terminal displaying a text input box corresponding to the AI ​​receiving slot in the data interface, displaying recommended question text in the text input box, and the recommended question text matching the data of at least one module currently stored in the AI ​​receiving slot. Accordingly, step 1304 includes: the terminal responding to the second interactive operation, processing the data of the at least one module based on the question text in the text input box, and displaying the data processing result.

[0220] The text input box is used to input the question text, which is used when the AI ​​model is invoked later. This question text represents the user's question to the AI ​​model regarding the data from at least one module, requesting the AI ​​model to provide an answer. Therefore, the data processing results output by the AI ​​model will include the answer text to this question.

[0221] Since the modules stored in the AI ​​receiving slot can be considered as the modules that the user will process, recommending matching question text based on the data of these modules and automatically inputting it into the text input box can increase the probability that the user will use the question text, reduce the user's burden of thinking about the question text and manually inputting the question text, and improve user satisfaction.

[0222] For example, if the AI ​​receiver slot does not yet contain a module, the text input box is not displayed initially. Once the AI ​​receiver slot contains a module, the text input box is displayed, and the recommended question text is shown in the text input box. Alternatively, the text input box is displayed in the data interface. If the AI ​​receiver slot does not yet contain a module, no text is entered in the text input box. Once the AI ​​receiver slot contains a module, the recommended question text is displayed in the text input box.

[0223] For example, the terminal pre-sets multiple recommended question texts and determines the module type corresponding to each recommended question text. From the multiple recommended question texts, it selects the recommended question text that matches the module type corresponding to the module currently stored in the AI ​​receiving slot and displays it in the text input box.

[0224] For example, the terminal obtains data from the modules currently stored in the AI ​​receiving slot and determines the recommended question text that matches the data. For instance, the terminal uses a pre-set text generation algorithm to extract the required data items from the data and constructs the recommended question text based on the extracted data items. Alternatively, the terminal inputs the data into an AI model, which then generates the recommended question text.

[0225] The terminal displays recommended question text in the text input box by default. Users can use the recommended question text or edit it.

[0226] Optionally, the method further includes: when the AI ​​receiving slot already contains modules, the terminal displays a text input box and an AI control corresponding to the AI ​​receiving slot in the data interface. The AI ​​control is used to initiate a data processing flow. When the user confirms the question text in the text input box, the user triggers the AI ​​control. The terminal responds to the trigger operation of the AI ​​control, processes the data corresponding to each module icon displayed in the AI ​​receiving slot based on the question text, and displays the data processing result. During the data processing, the AI ​​model processes the data according to the instructions of the question text, thereby ensuring that the data processing result output by the AI ​​model meets the requirements of the question text.

[0227] See Figure 15 When the quotation module icon 1404 is displayed in the AI ​​receiving slot 1403, the recommended question text "Analyze today's stock price changes and predict future trends" is displayed in the text input box 1404, and the AI ​​control 1405 "Ask AI" is also displayed. See also Figure 19 When the K-line module icon 1409 is displayed in the AI ​​receiving slot 1403, the text input box 1404, the recommended question text in the text input box 1404, and the AI ​​control 1405 "Ask AI" are also displayed.

[0228] Optionally, step 1304 includes: in response to the second interactive operation, converting the data of at least one module currently stored in the AI ​​receiving slot, the text encoding corresponding to the screenshot of the at least one module, and the question text in the text input box into structured data; processing the structured data through an AI model to obtain data processing results; and displaying the data processing results. The structured data includes at least one target type of data, meaning the structured data has a fixed format and is stored in the form of "target type - data".

[0229] In related technologies, screenshots of the data interface are taken and then processed by an AI model. However, the AI ​​model can only recognize the screenshot, extract the data displayed, and process that data; it cannot process other related data. In contrast, this application's embodiment can acquire raw data from the module, screenshots of the module, question text, and other data, increasing the data volume, avoiding the loss of high-precision data, and ensuring the comprehensiveness and accuracy of the data, thereby improving the comprehensiveness and accuracy of the data processing results. Furthermore, the server, based on structured data, can extract multimodal data according to its different types. Because the format of structured data is fixed, the parsing operation is simple and convenient, avoiding data parsing errors on the server and improving server stability.

[0230] For example, Figure 21 This is a schematic diagram of the processing flow of a terminal provided in an embodiment of this application. See also... Figure 21 The terminal extracts structured data, and after obtaining the structured data, it calls the API (Application Programming Interface) of the backend server, which then processes the structured data.

[0231] For example, the AI ​​model is deployed on a server, and the server provides an API to the terminal. This API is used to call the AI ​​model on the server. The AI ​​model processes the structured data to obtain the data processing results, including: the terminal calling the server's API to send a data processing request to the server, the data processing request carrying structured data; the server responding to the data processing request, processing the structured data through the AI ​​model to obtain data blocks, and sending them to the terminal; the terminal displays the data blocks whenever it receives them from the server.

[0232] In this system, data blocks represent the data processing results. After processing the structured data, the AI ​​model streams data blocks, and the server also streams data blocks to the terminal. The terminal receives and displays these data blocks sequentially, creating a streaming display of the data processing results. This process continues until the terminal displays the last data block, indicating that the data processing is complete. By using a streaming data block output method from the AI ​​model and a streaming data block display method from the terminal, users do not need to wait for extended periods. This allows for instant display and real-time feedback of the data processing results, improving display smoothness, reducing user anxiety, and making the interaction between the user and the AI ​​model more like a real-life interaction.

[0233] For example, the data to be processed includes data from at least one module, text encoding corresponding to screenshots of at least one module, question text, and may also include related data such as the terminal's login account. The data is diverse and belongs to multimodal data. The terminal encapsulates the multimodal data according to the target protocol agreed upon with the server to obtain structured data. Each piece of data in the structured data is assigned a corresponding target type and stored as key-value pairs. The data processing request sent by the terminal to the server carries the encapsulated structured data, so that the server can decapsulate it according to the target protocol to obtain data of various target types.

[0234] Figure 22 This is a schematic diagram of the interaction process between a terminal and a server provided in an embodiment of this application. See also... Figure 22 The terminal encapsulates the text encoding corresponding to the screenshot, the question text in the text input box, and at least one set of module data according to the target protocol. Then, it calls the server's API to send the encapsulated structured data, which is processed by the server. The server then returns the data processing result to the terminal through the SSE (Server-Sent Events) communication connection established between the server and the terminal.

[0235] In addition, the server's data processing procedures are detailed below. Figure 24 The embodiments shown are not described here.

[0236] Optionally, the method further includes: during data processing, the terminal dynamically displays the module icon in the AI ​​receiving slot. Compared with statically displaying the module icon, dynamically displaying the module icon can improve the visibility of the AI ​​receiving slot, attract user attention, and inform the user that data is currently being processed, thus providing the user with intuitive feedback.

[0237] For example, if the AI ​​receiving slot displays a circular marker and each module icon is located on the circular marker, then in response to the second interactive operation, the terminal moves each module icon on the circular marker in a clockwise or counterclockwise direction until the data processing result is obtained and the AI ​​receiving slot is dedisplayed.

[0238] Optionally, the terminal displays the data processing results by displaying the data processing results in an AI interactive interface located above the data interface.

[0239] The AI ​​interactive interface allows users to interact with the AI ​​model. Users can ask questions to the AI ​​model, which will then provide answers. Since the terminal has already initiated a data processing flow through the AI ​​receiving slot, it automatically sends an interactive message in the AI ​​interactive interface. This message includes the question text in the text input box and displays the data processing result returned by the AI ​​model as the answer to the question text in the AI ​​interactive interface, thus simulating the dialogue effect of the AI ​​model responding to a user's question.

[0240] For example, see Figure 23 While maintaining the data display interface 2301, an AI interaction interface 2302 is displayed on the upper layer. In the AI ​​interaction interface 2302, the user sends an interaction message 2303, which includes the question text "Analyze today's K-line market and predict future trends", and the AI ​​model returns the answer 2304.

[0241] By displaying the data processing results in the AI ​​interactive interface on top of the data interface, the data processing results can be displayed in an independent display space, ensuring sufficient display space and making it easy for users to browse the data processing results. This also avoids affecting the data interface itself and saves the processing resources required to adjust the data interface.

[0242] Optionally, the terminal displays the data processing results by: displaying the data processing results in the AI ​​receiving slot or in an adjacent area of ​​the AI ​​receiving slot. The existing data on the data interface will be moved accordingly to provide sufficient display space for the data processing results. Since the data processing results are initiated through the AI ​​receiving slot, displaying them in the AI ​​receiving slot or in an adjacent area enhances the correlation between the two, making it easier for users to understand that the data processing results are the result of the processing flow initiated by the AI ​​receiving slot. It also avoids requiring users to shift their visual focus, reducing the operational burden on users to view the data processing results. Alternatively, the terminal can jump from the current interface to the AI ​​interaction interface, displaying the data processing results in the AI ​​interaction interface. In the AI ​​interaction interface, users can continue to input question text, which the AI ​​model will answer, allowing for one or more rounds of interaction with the AI ​​model. Additionally, the AI ​​interaction interface displays a back button; users can trigger the back button to exit the AI ​​interaction interface and redisplay the previous data interface, allowing users to continue browsing the data interface. Displaying the data processing interface within the AI ​​interactive interface not only provides a dedicated display space for the data processing results, ensuring ample space for users to browse the results and interact more with the AI ​​model, but also avoids impacting the data interface itself, saving the processing resources needed to adjust the data interface. Furthermore, it provides an exit point from the AI ​​interactive interface, meeting diverse user needs.

[0243] Optionally, the data processing results may include answer text, which is used to respond to the question text, and the terminal can directly display the answer text. Additionally, the data processing results may include reference data, which is external data referenced during the data processing, such as knowledge data, industry information data, news hotspot data, etc., related to the data to be processed. When displaying the data processing results, the terminal may directly display the reference data, or it may first display brief reference guidance information and corresponding expansion controls, such as the title of the reference data or a prompt message prompting the user to view the reference data, and then display the reference data after triggering the expansion control corresponding to the reference guidance information. Furthermore, the data processing results may include inference steps, which are the inference steps performed by the AI ​​model in the process of obtaining the answer text, and can demonstrate the AI ​​model's thinking process. When displaying the data processing results, the terminal may directly display the inference steps, or it may first display inference guidance information and corresponding expansion controls, such as a brief introduction to the inference steps or a prompt message prompting the user to view the inference steps, and then display the inference steps after triggering the expansion control corresponding to the inference guidance information.

[0244] Based on the above embodiments, the state switching process of the AI ​​receiving slot will be described below.

[0245] Figure 24 This is a schematic diagram of the state switching process of an AI receiving slot provided in an embodiment of this application. See also... Figure 24 The state switching process of the AI ​​receiver slot includes: 2401. The AI ​​receiver slot is in a hidden state.

[0246] 2402. When the pull-down ratio of the data interface reaches the first ratio, the AI ​​receiving slot is in the normal display state.

[0247] 2403. The module is dragged into the AI ​​receiver slot, and the AI ​​receiver slot is highlighted (e.g., highlighted).

[0248] 2404. After the drag-and-drop operation of the module is completed, the AI ​​receiving slot is in the module storage state, and the module icon corresponding to the stored module is displayed inside the AI ​​receiving slot.

[0249] 2405. When the user triggers the AI ​​control, the AI ​​receiving slot is in data processing state, during which data processing is performed through the AI ​​model.

[0250] Furthermore, in data processing mode, the module icons in the AI ​​receiving slot can change their display style to present a different visual effect than when the modules are stored. For example, in data processing mode, the transparency of the module icons can be increased to make them transparent. Alternatively, the module icons can be switched from a static display to a dynamic display.

[0251] 2406. The AI ​​module returns the data processing result. Data processing is complete, and the AI ​​receiving slot returns to its hidden state.

[0252] Based on the above embodiments, Figure 25 This is a flowchart of another data processing method provided in this application embodiment. The execution subject of this application embodiment is a server, which can be, for example, Figure 1 The server shown is 120 or another server. For example... Figure 25 As shown, the method includes: 2501. The server receives a data processing request sent by the terminal, and the data processing request carries structured data.

[0253] The structured data includes data of at least one target type. The structured data is obtained by converting data from at least one module, screenshots from at least one module, and question text. At least one module is the module that stores data from the terminal's displayed interface into the AI ​​receiving slot. The specific process for acquiring the structured data is detailed in the above embodiments and will not be repeated here.

[0254] 2502. The server responds to the data processing request by processing the structured data using an AI model to obtain the data processing result.

[0255] The AI ​​model can be a large language model, a deep learning model, a convolutional neural network model, or other types of models. The server can deploy only one AI model to process data, or it can deploy multiple AI models, including a primary model and a backup model. Normally, the server uses the primary model, but in case of failure, data processing failure, or timeout, the server uses the backup model. This ensures the stability of the model call chain and maximizes the return of valid data processing results.

[0256] In response to a data processing request, the server creates a prompt word, inputs the prompt word and the data to be processed into the AI ​​model, and processes the data through the AI ​​model to obtain the data processing result.

[0257] Optionally, in response to a data processing request, the terminal parses the structured data to obtain data of various target types.

[0258] For example, the terminal encapsulates multiple data items to be processed based on the target protocol between the terminal and the server to obtain structured data. After receiving the data processing request, the server parses the structured data based on the target protocol to obtain data of various target types, which means that the target types to which the multiple data items belong are determined.

[0259] The data of various target types can include question text, terminal login account, module source data, module identifier, module type, and text code corresponding to screenshots. Module source data refers to the original data of the module in the data interface displayed on the terminal; the module identifier is the unique identifier of the module; the module type refers to the type to which the module belongs; and the text code corresponding to the screenshot is used to represent the content contained in the module's screenshot.

[0260] Optionally, the data of various target types includes question text, which is the text entered in the text input box displayed on the data interface. This question text represents a question posed by the user regarding the data on the data interface, requiring an answer from the AI ​​model. The server creates prompt words that match the question text. These prompt words instruct the AI ​​model to answer the question text based on the various target types of data. The AI ​​model then processes the data of various target types based on these prompt words to obtain the data processing results.

[0261] Optionally, the method further includes: obtaining the terminal's preference features, which represent the terminal's user preferences; querying first knowledge data in a database that matches the preference features; and accordingly, creating prompt words that match the question text, including: creating prompt words that match the question text, preference features, and first knowledge data, whereby the prompt words instruct the AI ​​model to answer the question text based on data of various target types and with reference to preference features and first knowledge data.

[0262] The preference features can be set by the user on the terminal or determined by the server based on the user's operating habits. For example, preference features can represent the user's preferred data processing dimensions, preferred data evaluation angles, or the types of data the user focuses on. The server sets up a matching database for each preference feature, storing knowledge data. This knowledge data can be considered as data that users with that preference feature focus on, and it can play an auxiliary role in answering user questions. Therefore, prompt words matching the preference feature and the first knowledge data are created. These prompt words instruct the AI ​​model to process data according to the preference feature and refer to the first knowledge data for analysis, in order to obtain an accurate answer to the question text.

[0263] See Figure 26In a scenario where the data interface is an introduction screen for the target product, the server sets various preference features, including: basic data parsing preference, graphical data parsing preference, message event parsing preference, and balanced parsing preference. Basic data parsing preference refers to the user's preference for parsing the product's basic data; graphical data parsing preference refers to the user's preference for parsing the product's graphical data; message event parsing preference refers to the user's preference for parsing product-related message events; and balanced parsing preference refers to the user's preference for comprehensively parsing all aspects of the product's data, with no significant difference between the parsing of each aspect.

[0264] The server sets up a matching database for each preference trait. See also Figure 26 The server's databases include: a basic data database, a graph database, and a message / event database. The basic data database stores knowledge data related to basic data, the graph database stores knowledge data related to graph data, and the message / event database stores knowledge data related to message events. Specifically, the basic data parsing preference matches the basic data database, the graph parsing preference matches the graph database, the message / event parsing preference matches the message / event database, and the balanced parsing preference matches all three databases.

[0265] Optionally, the data of multiple target types also includes at least one module identifier, which is used to represent a module in the data interface displayed on the terminal. The method further includes: querying the second knowledge data corresponding to the module identifier, and accordingly, creating a prompt word matching the question text, including: creating a prompt word matching the question text and the second knowledge data, the prompt word being used to prompt the AI ​​model to answer the question text based on the data of multiple target types and with reference to the second knowledge data.

[0266] The server can set corresponding knowledge data for different module identifiers. This knowledge data can serve as supplementary data to the module data and may include industry news data, professional knowledge data, announcement data, research report data, etc. The knowledge data corresponding to different module identifiers may include the same data or different data. The server creates prompt words that match the second knowledge data. These prompt words instruct the AI ​​model to refer to the second knowledge data during data processing to analyze the data and obtain an accurate answer to the question text.

[0267] 2503. The server sends the data processing results to the terminal.

[0268] Optionally, the data processing results of the AI ​​model are returned in the form of streaming data blocks. The server will sequentially obtain the data blocks returned by the AI ​​model and send the data blocks to the terminal for display.

[0269] The method provided in this application embodiment stores modules of the data processing interface on the terminal via an AI receiving slot. When a data processing flow is initiated, the server calls an AI model to process the data of the aforementioned modules. Throughout the process, the terminal is responsible for the foreground display, and the server is responsible for the background processing. The terminal and server cooperate to ensure smooth interface display, timely feedback to user operations, and high operational efficiency, avoiding lag. During processing, the method can also consider the terminal user's preference characteristics, knowledge data matching these preferences, or knowledge data corresponding to module identifiers, increasing the data volume and improving the accuracy and richness of the data processing results.

[0270] Figure 27 This is a schematic diagram illustrating the interaction process between a terminal and a server according to an embodiment of this application. See also... Figure 27 The interaction process includes: 2701. The terminal sends a data processing request to the server.

[0271] 2702. The server calls the large language model.

[0272] 2703. Establish an SSE connection between the server and the terminal.

[0273] 2704. During the data processing of the large language model, a data block is returned.

[0274] 2705. After receiving the data block, the server sends an SSE event to the terminal. The SSE event carries a data block returned by the large language model.

[0275] 2706. The terminal displays data blocks in the AI ​​interactive interface based on the received SSE events.

[0276] The AI ​​interactive interface is presented in the form of a semi-pop-up layer, and the data blocks are rendered in markdown (a lightweight markup language).

[0277] Then, repeat steps 2704-2706 above.

[0278] 2707. After the large language model has finished processing the data, it returns a processing completion flag after returning the last data block.

[0279] 2708. After receiving the processing completion flag, the server sends a communication end flag to the terminal.

[0280] 2709. The server closes the SSE connection with the terminal.

[0281] In the SSE streaming push architecture described above, the server maintains a long-term connection with the terminal, and asynchronous processing occurs between the server and the AI ​​model. The data processing results from the AI ​​model are returned to the terminal via the long-term connection. Compared to WebSocket (a full-duplex communication protocol), SSE is simpler to implement, natively supported by browsers or mini-programs, supports mechanisms such as automatic reconnection, and has lower costs.

[0282] exist Figure 3 The server architecture shown and Figure 27 Based on the interactive flow shown, Figure 28 This is a schematic diagram of a server processing flow provided in an embodiment of this application. See also... Figure 28 The processing flow includes: 2801. The terminal sends a data processing request to the server, and an SSE connection is established between the terminal and the server.

[0283] 2802. Access layer 121 requests the multimodal parsing service. Through the multimodal parsing service, it parses the module identifier, terminal login account, user-inputted question text, module screenshot, announcement, research report, and other data from the structured data carried in the data processing request and returns them to access layer 121.

[0284] 2803. Based on the terminal login account, module identifier, and question text, the access layer 121 requests the prompt word generation service. Through the prompt word generation service, it generates personalized prompt words for the user's question and returns them to the access layer 121.

[0285] 2804. Access layer 121 requests the AI ​​processing service to transmit structured data, module screenshots, announcements, research reports, and other data to the AI ​​processing service. The AI ​​processing service processes the data and returns the data processing results to access layer 121.

[0286] 2805. The access layer 121 performs security checks on the data processing results. After the checks are passed, the data processing results are returned to the terminal.

[0287] Security checks can include sensitive word detection and violation detection. The server can be configured with a sensitive word database, matching the processed data against this database to identify, block, delete, or replace sensitive words. It can also detect violations in the processed data, such as recommending non-compliant information or using inappropriate language. If a violation is detected, the data processing result fails the detection, is canceled, and a violation record is generated.

[0288] In addition, after the data processing result passes the test, the server can directly return the data processing result to the terminal, or add supplementary explanations to the data processing result before returning it to the terminal. These supplementary explanations may include disclaimers, test pass statements, or information prompting the user to report any violations found in the data processing result.

[0289] Figure 29 This is a schematic diagram illustrating the service capabilities of a server provided in an embodiment of this application. See also... Figure 29 The server's business capabilities are as follows: 1. Supports multimodal data: The AI ​​model is a multimodal large language model, which supports processing various types of data such as source data of modules, screenshots of modules, and user-input question text.

[0290] 2. Supports business data management: It can update the data of the target object in real time based on the actual situation of the target object. For example, when the target object is a target product, it can update data such as the price and transaction status of the target product in real time.

[0291] 3. Adapt to user question scenarios: Supports users to ask personalized questions. Users only need to input or edit the question text, and the AI ​​model will answer the question text.

[0292] 4. Personalized processing: Supports data processing based on user preferences and knowledge data that match those preferences, and outputs personalized data processing results.

[0293] 5. Multimodal encapsulation: Supports encapsulating various types of data in a standardized format, providing it to the AI ​​model, and requiring the AI ​​model to return structured data processing results.

[0294] 6. Follow these principles: Based on facts: Data processing results must be based on facts and must not contain false information; Risk warning: This section warns of potential risks in the data processing results. Multi-dimensional judgment: Make full judgments based on multi-dimensional data to ensure the accuracy of data processing results; Multiple models: Deploy multiple models to ensure the stability of the model call chain.

[0295] Figure 30 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application, as shown below. Figure 30 As shown, the device includes: Display unit 3001 is used to display a data interface. The data interface displays at least two modules, and each module includes a set of data. The display unit 3001 is also used to respond to the first interactive operation by displaying the artificial intelligence (AI) receiving slot, which is used to store modules to be processed. The module storage unit 3002 is used to store at least one module in the data interface into the AI ​​receiving slot; The data processing unit 3003 is used to process data from at least one module in response to a second interactive operation and display the data processing results.

[0296] Optionally, the display unit 3001 is used to obtain the ratio between the pulling distance and the height of the display screen in response to the pulling operation of the data interface; when the ratio reaches a first ratio, the AI ​​receiving slot is displayed based on the data interface.

[0297] Optionally, the display unit 3001 is also used for: If the ratio does not reach the second ratio, a first prompt message will be displayed on the data interface; the first prompt message is used to remind users to refresh the data interface after releasing it; or... If the ratio reaches the second ratio but has not yet reached the first ratio, a second prompt message is displayed on the data interface; the second prompt message is used to prompt the user to continue dragging the data interface to process the data. The second proportion is smaller than the first proportion.

[0298] Optionally, the display unit 3001 is also used to display a bounce animation of the data interface when the drag operation ends if the ratio has not reached the first ratio.

[0299] Optionally, the display unit 3001 is configured to display the AI ​​receiving slot in the area between the current position and the original position of the edge of the data interface being pulled, in response to a pull operation on the data interface.

[0300] Optionally, the display unit 3001 is used to dynamically display each module in the data interface during the display of the AI ​​receiving slot.

[0301] Optionally, the display unit 3001 is used to dynamically display the icon of each module in the AI ​​receiving slot during data processing.

[0302] Optionally, the display unit 3001 is used for at least one of the following: When the AI ​​receiver slot is first displayed, make each module in the data interface draggable; When the AI ​​receiver slot is first displayed, initiate drag-and-drop operations for each module in the detection data interface.

[0303] Optionally, the module storage unit 3002 is used to drag and drop the first module into the AI ​​receiving slot and then release it, displaying the first module icon corresponding to the first module in the AI ​​receiving slot; the first module is any module in the data interface.

[0304] Optionally, the module storage unit 3002 is used to display a screenshot of the first module at the location of the first module in response to a touch operation on the first module; in response to the movement of the touch position of the touch operation, the displayed screenshot moves with the touch position of the touch operation; if the screenshot is located in the AI ​​receiving slot when the touch operation ends, the displayed screenshot moves to the target position in the AI ​​receiving slot and disappears, and the first module icon is displayed at the target position.

[0305] Optionally, the display unit 3001 is also configured to display that if the screenshot is located outside the AI ​​receiving slot when the touch operation ends, the screenshot will disappear after moving to the location of the first module.

[0306] Optionally, the module storage unit 3002 is used to obtain the current position of the first module during the dragging process; perform collision detection between the first module and the AI ​​receiving slot based on the position; highlight the AI ​​receiving slot when the first module collides with the AI ​​receiving slot; and display the first module icon in the AI ​​receiving slot when the dragging of the first module ends.

[0307] Optionally, a virtual character is displayed in the AI ​​receiving slot. The virtual character is used to refer to the AI ​​model that performs data processing. The module storage unit 3002 is used to highlight the virtual character when the first module collides with the AI ​​receiving slot.

[0308] Optionally, the data processing unit 3003 is used to display the data processing results in the AI ​​interactive interface located above the data interface; or, to display the data processing results in the AI ​​receiving slot or in an adjacent area of ​​the AI ​​receiving slot; or, to jump to the AI ​​interactive interface and display the data processing results in the AI ​​interactive interface.

[0309] Optionally, the display unit 3001 is also used to display a text input box corresponding to the AI ​​receiving slot, and to display recommended question text in the text input box, wherein the recommended question text matches the data of at least one module; The data processing unit 3003 is used to respond to the second interactive operation, process the data of at least one module based on the question text in the text input box, and display the data processing results.

[0310] Optionally, the data processing unit 3003 is configured to, in response to the second interactive operation, convert the data of at least one module, the text encoding corresponding to the screenshot of at least one module, and the question text into structured data, the structured data including data of various target types; process the structured data through an AI model to obtain data processing results, and display the data processing results.

[0311] Optionally, the data processing unit 3003 is used to call the server's application programming interface to send a data processing request to the server, the data processing request carrying structured data; the server is used to respond to the data processing request, process the structured data through an AI model, and obtain a data block to represent the data processing result; whenever a data block is received from the server, the data block is displayed.

[0312] Figure 31 This is a schematic diagram of another data processing device provided in the embodiments of this application, such as... Figure 31 As shown, the device includes: The receiving unit 3101 is used to receive a data processing request sent by the terminal. The data processing request carries structured data, which includes data of various target types. The structured data is obtained by converting data from at least one module, screenshots from at least one module, and question text. At least one module is a module that stores data from the data interface displayed on the terminal into the AI ​​receiving slot. The data processing unit 3102 is used to respond to a data processing request, process structured data through an AI model, and obtain data processing results; The sending unit 3103 is used to send the data processing results to the terminal.

[0313] Optionally, the data processing unit 3102 is configured to, in response to a data processing request, parse the structured data to obtain data of multiple target types, including question text; create prompt words that match the question text, the prompt words being used to instruct the AI ​​model to answer the question text based on the data of multiple target types; and process the data of multiple target types based on the prompt words through the AI ​​model to obtain data processing results.

[0314] Optionally, the data processing unit 3102 is used to acquire the terminal's preference features, which represent the terminal's user preferences; query first knowledge data in a database that matches the preference features; and create prompt words that match the question text, preference features, and first knowledge data, which instruct the AI ​​model to answer the question text based on data of various target types and with reference to preference features and first knowledge data.

[0315] Optionally, the data of multiple target types also includes at least one module identifier, which is used to represent a module in the data interface; The data processing unit 3102 is used to query the second knowledge data corresponding to the module identifier; and to create prompt words that match the question text and the second knowledge data. The prompt words are used to instruct the AI ​​model to answer the question text based on data of various target types and with reference to the second knowledge data.

[0316] It should be noted that the data processing apparatus provided in the above embodiments is only illustrated by the division of the above modules. In actual applications, the above functions can be assigned to different modules as needed, that is, the internal structure of the terminal and the server can be divided into different modules to complete all or part of the functions described above. In addition, the data processing apparatus and data processing method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0317] This application also provides a computer device, which includes a processor and a memory. The memory stores at least one computer program, which is loaded and executed by the processor to perform the operations performed by the data processing method of the above embodiments.

[0318] Optionally, the computer device is provided as a terminal. Figure 32 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. The terminal 3200 can be a smartphone, tablet computer, laptop computer, desktop computer, etc. The terminal 3200 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0319] The terminal 3200 includes a processor 3201 and a memory 3202.

[0320] Processor 3201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 3201 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 3201 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 3201 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 3201 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0321] The memory 3202 may include one or more computer-readable storage media, which may be non-transitory. The memory 3202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 3202 are used to store at least one computer program, which is executed by the processor 3201 to implement the data processing method provided in the method embodiments of this application.

[0322] In some embodiments, the terminal 3200 may also optionally include a peripheral device interface 3203 and at least one peripheral device. The processor 3201, memory 3202, and peripheral device interface 3203 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 3203 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: radio frequency circuitry 3204, display screen 3205, camera assembly 3206, audio circuitry 3207, and power supply 3208.

[0323] Peripheral device interface 3203 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 3201 and memory 3202. In some embodiments, processor 3201, memory 3202 and peripheral device interface 3203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 3201, memory 3202 and peripheral device interface 3203 can be implemented on separate chips or circuit boards, and this application embodiment does not limit this.

[0324] The radio frequency (RF) circuit 3204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 3204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 3204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 3204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 3204 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 3204 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0325] Display screen 3205 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 3205 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 3201 for processing. In this case, display screen 3205 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 3205, disposed on the front panel of terminal 3200; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 3200 or in a folded design; in still other embodiments, display screen 3205 may be a flexible display screen, disposed on a curved or folded surface of terminal 3200. Furthermore, display screen 3205 may also be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 3205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0326] The camera assembly 3206 is used to acquire images or videos. Optionally, the camera assembly 3206 includes a front-facing camera and a rear-facing camera. The front-facing camera is disposed on the front panel of the terminal, and the rear-facing camera is disposed on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 3206 may also include a flash. The flash may be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0327] The audio circuit 3207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 3201 for processing, or to the radio frequency circuit 3204 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 3200. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 3201 or the radio frequency circuit 3204 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 3207 may also include a headphone jack.

[0328] Power supply 3208 is used to power the various components in terminal 3200. Power supply 3208 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 3208 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0329] In some embodiments, the terminal 3200 further includes one or more sensors 3209. The one or more sensors 3209 include, but are not limited to: an accelerometer 3210, a gyroscope 3211, a pressure sensor 3212, an optical sensor 3213, and a proximity sensor 3214.

[0330] Accelerometer 3210 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by terminal 3200. For example, accelerometer 3210 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 3201 can control display screen 3205 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 3210. Accelerometer 3210 can also be used for games or for acquiring user motion data.

[0331] The gyroscope sensor 3211 can detect the orientation and rotation angle of the terminal 3200. The gyroscope sensor 3211 can work in conjunction with the accelerometer sensor 3210 to collect the user's 3D movements on the terminal 3200. Based on the data collected by the gyroscope sensor 3211, the processor 3201 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0332] The pressure sensor 3212 can be disposed on the side bezel of the terminal 3200 and / or the lower layer of the display screen 3205. When the pressure sensor 3212 is disposed on the side bezel of the terminal 3200, it can detect the user's grip signal on the terminal 3200, and the processor 3201 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 3212. When the pressure sensor 3212 is disposed on the lower layer of the display screen 3205, the processor 3201 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 3205. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0333] The optical sensor 3213 is used to collect ambient light intensity. In one embodiment, the processor 3201 can control the display brightness of the display screen 3205 based on the ambient light intensity collected by the optical sensor 3213. Specifically, when the ambient light intensity is high, the display brightness of the display screen 3205 is increased; when the ambient light intensity is low, the display brightness of the display screen 3205 is decreased. In another embodiment, the processor 3201 can also dynamically adjust the shooting parameters of the camera assembly 3206 based on the ambient light intensity collected by the optical sensor 3213.

[0334] The proximity sensor 3214, also known as a distance sensor, is installed on the front panel of the terminal 3200. The proximity sensor 3214 is used to detect the distance between the user and the front of the terminal 3200. In one embodiment, when the proximity sensor 3214 detects that the distance between the user and the front of the terminal 3200 is gradually decreasing, the processor 3201 controls the display screen 3205 to switch from a screen-on state to a screen-off state; when the proximity sensor 3214 detects that the distance between the user and the front of the terminal 3200 is gradually increasing, the processor 3201 controls the display screen 3205 to switch from a screen-off state to a screen-on state.

[0335] Those skilled in the art will understand that Figure 32 The structure shown does not constitute a limitation on terminal 3200 and may include more or fewer components than shown, or combine certain components, or use different component placements.

[0336] Optionally, the computer device is provided as a server. Figure 33This is a schematic diagram of a server structure provided in an embodiment of this application. The server 3300 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 3301 and one or more memories 3302. The memories 3302 store at least one computer program, which is loaded and executed by the processor 3301 to implement the methods provided in the above-described method embodiments. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated upon here.

[0337] This application also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the operations performed by the data processing method of the above embodiments.

[0338] This application also provides a computer program product, including a computer program that, when executed by a processor, performs the operations performed by the data processing method described above.

[0339] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0340] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present application should be included within the protection scope of the present application.

Claims

1. A data processing method, characterized in that, The method includes: The data display interface has at least two modules, each module including a set of data; In response to the first interactive operation, an AI receiving slot is displayed, which is used to store modules to be processed; Store at least one module of the data interface into the AI ​​receiving slot; In response to the second interactive operation, the data of the at least one module is processed and the data processing result is displayed.

2. The method according to claim 1, characterized in that, The AI ​​receiver slot, displayed in response to the first interactive operation, includes: In response to a drag operation on the data interface, the ratio between the drag distance and the height of the display screen is obtained; When the ratio reaches the first ratio, the AI ​​receiving slot is displayed based on the data interface.

3. The method according to claim 2, characterized in that, The method further includes: If the specified ratio does not reach the second ratio, a first prompt message is displayed on the data interface; the first prompt message is used to suggest releasing the data interface and then refreshing it; or... If the ratio reaches the second ratio but has not yet reached the first ratio, a second prompt message is displayed on the data interface; the second prompt message is used to prompt the user to continue dragging the data interface to process the data. The second ratio is smaller than the first ratio.

4. The method according to any one of claims 1-3, characterized in that, The step of storing at least one module from the data interface into the AI ​​receiving slot includes: After dragging and dropping the first module into the AI ​​receiving slot, release it. The first module icon corresponding to the first module will be displayed in the AI ​​receiving slot. The first module can be any module in the data interface.

5. The method according to claim 4, characterized in that, The step of dragging and releasing the first module to the AI ​​receiving slot, and then displaying the first module icon corresponding to the first module in the AI ​​receiving slot, includes: In response to a touch operation on the first module, a screenshot of the first module is displayed at the location of the first module; In response to the movement of the touch position in response to the touch operation, the screenshot is displayed to move along with the touch position of the touch operation; If the screenshot is located in the AI ​​receiving slot when the touch operation ends, the screenshot will disappear after moving to the target position in the AI ​​receiving slot, and the first module icon will be displayed at the target position.

6. The method according to claim 5, characterized in that, The method further includes: If the screenshot is outside the AI ​​receiving slot when the touch operation ends, the screenshot will be displayed and then disappear after moving to the location of the first module.

7. The method according to claim 4, characterized in that, The step of dragging and releasing the first module to the AI ​​receiving slot, and then displaying the first module icon corresponding to the first module in the AI ​​receiving slot, includes: During the dragging and dropping of the first module, the current position of the first module is obtained; Based on the location, collision detection is performed between the first module and the AI ​​receiving slot; When the first module collides with the AI ​​receiving slot, the AI ​​receiving slot is highlighted. When the dragging of the first module is finished, the icon of the first module is displayed in the AI ​​receiving slot.

8. The method according to claim 7, characterized in that, The AI ​​receiving slot displays a virtual character, which refers to the AI ​​model performing data processing. The step of highlighting the AI ​​receiving slot when the first module collides with it includes: When the first module collides with the AI ​​receiving slot, the virtual character is highlighted.

9. The method according to any one of claims 1-8, characterized in that, The displayed data processing results include: The data processing results are displayed in the AI ​​interactive interface located above the data interface; or, The data processing results are displayed in the AI ​​receiving slot or in an adjacent area of ​​the AI ​​receiving slot; or, The user is redirected to the AI ​​interactive interface, where the data processing results are displayed.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Display the text input box corresponding to the AI ​​receiving slot, and display recommended question text in the text input box, wherein the recommended question text matches the data of the at least one module; The process of responding to the second interactive operation, processing the data of the at least one module, and displaying the data processing results includes: In response to the second interactive operation, the data of the at least one module is processed based on the question text in the text input box, and the data processing result is displayed.

11. The method according to any one of claims 1-10, characterized in that, The process of responding to the second interactive operation, processing the data of the at least one module, and displaying the data processing results includes: In response to the second interactive operation, the data of the at least one module, the text encoding corresponding to the screenshot of the at least one module, and the question text are converted into structured data, which includes data of multiple target types; The structured data is processed using an AI model to obtain the data processing results, which are then displayed.

12. The method according to claim 11, characterized in that, The process of processing the structured data using an AI model to obtain and display the data processing results includes: The application programming interface of the server is invoked to send a data processing request to the server, the data processing request carrying the structured data; the server is used to respond to the data processing request, and process the structured data through the AI ​​model to obtain a data block representing the data processing result; Whenever a data block is received from the server, the data block is displayed.

13. A data processing method, characterized in that, The method includes: The receiving terminal sends a data processing request, which carries structured data. The structured data includes data of various target types. The structured data is obtained by converting data from at least one module, screenshots of the at least one module, and question text. The at least one module is a module that stores data from the data interface displayed on the terminal into the AI ​​receiving slot. In response to the data processing request, the structured data is processed using an AI model to obtain the data processing result; The data processing result is sent to the terminal.

14. The method according to claim 13, characterized in that, In response to the data processing request, the structured data is processed using an AI model to obtain the data processing result, including: In response to the data processing request, the structured data is parsed to obtain data of various target types, including question text; Create prompt words that match the question text, the prompt words being used to instruct the AI ​​model to answer the question text based on the data of the multiple target types; The AI ​​model processes the data of the various target types based on the prompt words to obtain the data processing results.

15. The method according to claim 14, characterized in that, The method further includes: Obtain the preference features of the terminal, which are used to represent the user preferences of the terminal; Query the first knowledge data in the database that matches the preference features; The creation of prompt words that match the question text includes: Create prompt words that match the question text, the preference features, and the first knowledge data. The prompt words are used to instruct the AI ​​model to answer the question text based on the multiple target types of data and with reference to the preference features and the first knowledge data.

16. A data processing apparatus, characterized in that, The device includes: A display unit is used to display a data interface, wherein the data interface displays at least two modules, and each module includes a set of data. The display unit is also configured to respond to the first interactive operation by displaying an artificial intelligence (AI) receiving slot, which is used to store modules to be processed. A module storage unit is used to store at least one module from the data interface into the AI ​​receiving slot; A data processing unit is configured to process the data of the at least one module in response to a second interactive operation and display the data processing results.

17. A data processing apparatus, characterized in that, The device includes: A receiving unit is used to receive a data processing request sent by a terminal. The data processing request carries structured data, which includes data of various target types. The structured data is obtained by converting data from at least one module, screenshots of the at least one module, and question text. The at least one module is a module that stores data from the data interface displayed on the terminal into an artificial intelligence (AI) receiving slot. A data processing unit is configured to respond to the data processing request by processing the structured data using an AI model to obtain the data processing result. A sending unit is used to send the data processing result to the terminal.

18. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to perform the operations performed by the data processing method as claimed in any one of claims 1 to 12; or, to perform the operations performed by the data processing method as claimed in any one of claims 13 to 15.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to implement the operations performed by the data processing method as claimed in any one of claims 1 to 12; or to implement the operations performed by the data processing method as claimed in any one of claims 13 to 15.

20. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it performs the operations performed by the data processing method as described in any one of claims 1 to 12; or, it performs the operations performed by the data processing method as described in any one of claims 13 to 15.

Images