Intelligent interaction method and device

Abstract

The embodiment of the invention provides an intelligent interaction method, and the method comprises the steps: obtaining a user portrait of a user under the condition of user authorization; obtaining the current operation of the user on the current page of the application program; predicting a next operation of the user based on the user portrait and the current operation, and generating an operation prompt based on the next operation; and displaying the operation prompt on the current page. According to the technical scheme provided by the embodiment of the invention, the behavior of the user can be predicted to generate the operation prompt, so that the user can directly enter the page which the user wants to enter by skipping a complex path, and the user experience is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to an intelligent interaction method, device, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] As the functions and content of application programs become more and more, the pages of application programs become more and more complex. When a user wants to enter a certain page on the current page, it may be necessary to go through a very complex operation path to enter, which causes a lot of inconvenience to the user and the user experience is poor.

[0003] It should be noted that the above content is not necessarily prior art and is not used to limit the patent protection scope of the present application. Summary of the Invention

[0004] Embodiments of the present application provide an intelligent interaction method, device, computer device, computer-readable storage medium, and computer program product to solve or alleviate one or more of the above-mentioned technical problems.

[0005] One aspect of the embodiments of the present application provides an intelligent interaction method, and the method includes: Obtaining the user portrait of the user under the condition of user authorization; Obtaining the current operation of the user on the current page of the application program; Predicting the next operation of the user based on the user portrait and the current operation, and generating an operation prompt based on the next operation; Displaying the operation prompt on the current page.

[0006] Optionally, the predicting the next operation of the user based on the user portrait and the current operation, and generating an operation prompt based on the next operation includes: Predicting the target page corresponding to the next operation of the user based on the user portrait and the current operation by using an artificial intelligence assistant, and generating an operation prompt for the target page, where the artificial intelligence assistant is located in the application program.

[0007] Optionally, the artificial intelligence assistant includes a lightweight model deployed on the client; Correspondingly, the predicting the target page corresponding to the next operation of the user based on the user portrait and the current operation by using an artificial intelligence assistant, and generating an operation prompt for the target page includes: Converting the user portrait and the current operation to obtain the input token of the lightweight model; Input the input token into the lightweight model, and use the lightweight model to predict the target page corresponding to the user's next operation based on the input token, and generate an operation prompt for the target page.

[0008] Optionally, the method further includes: Use the AI assistant to obtain the user's query keywords; Use the AI assistant to obtain query results based on the query keywords; Display the query results on the current page.

[0009] Optionally, the AI assistant further includes a large model deployed in the cloud; Correspondingly, the steps of using the AI assistant to obtain the user's query keywords, using the AI assistant to obtain query results based on the query keywords, and displaying the query results on the current page include: When the AI assistant receives a target instruction, obtain the user's query keywords, and display the chat page of the large model on the current page; Send the query keywords to the large model to use the large model to obtain query results; Display the query results in the chat page.

[0010] Optionally, the step of using the AI assistant to obtain the user's query keywords includes: In response to a copy operation on the current page, use the AI assistant to identify the keyword corresponding to the copy operation; Use the identified keyword as the query keyword.

[0011] Another aspect of the embodiments of the present application provides an intelligent interaction device, the device includes: A first acquisition module, configured to acquire the user portrait of the user with the user's authorization; A second acquisition module, configured to acquire the current operation of the user on the current page of the application; A prediction module, configured to predict the user's next operation based on the user portrait and the current operation, and generate an operation prompt based on the next operation; A display module, configured to display the operation prompt on the current page.

[0012] Another aspect of the embodiments of the present application provides a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein: the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method as described above.

[0013] Another aspect of the embodiments of the present application provides a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are executed by a processor, the method as described above is implemented.

[0014] Another aspect of the embodiments of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method as described above is implemented.

[0015] The embodiments of the present application adopting the above technical solutions may include the following advantages: By obtaining the user portrait of the user under the condition of user authorization, obtaining the current operation of the user on the current page of the application program, predicting the next operation of the user based on the user portrait and the current operation, and generating an operation prompt based on the next operation and displaying the operation prompt on the current page, an operation prompt can be generated according to the user portrait and the current operation of the user, enabling the user to quickly perform the desired operation according to the operation prompt on the current page, thereby avoiding having to go through a complex path to enter the desired page and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings exemplarily show the embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments. The shown embodiments are only for illustrative purposes and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0017] Figure 1 Schematically shows an operating environment diagram of the intelligent interaction method according to Embodiment 1 of the present application; Figure 2 Schematically shows a flowchart of the intelligent interaction method according to Embodiment 1 of the present application; Figure 3 Schematically shows an artificial intelligence assistant; Figure 4 Schematically shows Figure 2 a sub-step flowchart of step S204 in; Figure 5 Schematically shows an additional process of the intelligent interaction method according to Embodiment 1 of the present application; Figure 6 Schematically showsFigure 4 Flowcharts of sub-steps for each step in Figure 7 Schematically shows Figure 4 Another flowchart of sub-steps for step S400 in Figure 8 Schematically shows a block diagram of an intelligent interaction device according to Embodiment 2 of the present application; and Figure 9 Schematically shows a schematic diagram of the hardware architecture of a computer device according to Embodiment 3 of the present application. Detailed implementation manners

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts fall within the scope of protection of the present application.

[0019] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions appears to be contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0020] In the description of the present application, it should be understood that the numerical labels before the steps do not identify the order of execution of the steps, but are only used to facilitate the description of the present application and distinguish each step, and thus cannot be understood as a limitation to the present application.

[0021] First, the following provides explanations of the terms involved in the present application: Large model: It is a machine learning model with a very large parameter scale and a complex structure. It usually contains billions or even tens of billions of parameters and can process and analyze a large amount of data to complete various complex tasks.

[0022] User profile: It is a multi-dimensional and three-dimensional description of a user formed by collecting and analyzing the user's data, forming a virtual "user model". This model can help us better understand the user and thus provide more accurate decision-making support for aspects such as products, services, and marketing.

[0023] Behavior tracing: It is a data collection technology that records various user behaviors in an application, such as clicks, browsing, swiping, searching, purchasing, etc., by inserting specific code snippets into the application. After these behavior data are collected, they can be used to analyze user behavior, thereby providing data support for product optimization and operation decision-making.

[0024] Secondly, to facilitate the understanding of the technical solutions provided by the embodiments of the present application by those skilled in the art, the related technologies will be described below: As the functions and content of applications become more and more, the pages of applications are becoming more and more complex. For a user to enter a certain page from the current page, it may require a very complex path to enter, resulting in a poor user experience. In addition, due to the increasingly rapid update of new words on the Internet, many times when a user finds a new word with an unclear meaning while browsing content, the user usually hopes to understand the meaning of the new word, but needs to exit the current application and use other applications to query the meaning of the new word. After querying the meaning of the new word, the user then returns to the original application again. This process is relatively complex and will affect the user's browsing experience.

[0025] Therefore, the embodiments of the present application provide an intelligent interaction technical solution. In this technical solution, operation prompts can be generated by predicting user behaviors, enabling users to directly enter the desired page by skipping complex paths; and content queries can be performed within the application, so that users do not need to exit the application to perform content queries, improving the user experience. See the following for details.

[0026] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0027] As Figure 1 shown, the environmental schematic diagram includes a service platform 2, a network 4, and a client 6, where: The service platform 2 can be composed of a single or multiple computing devices. The multiple computing devices can include virtualized computing instances. The virtualized computing instances can include virtual machines, such as emulations of computer systems, operating systems, servers, etc. The computing devices can load virtual machines based on virtual images and / or other data that define specific software (e.g., operating systems, dedicated applications, servers) for emulation. As the demand for different types of processing services changes, different virtual machines can be loaded and / or terminated on one or more computing devices. A hypervisor can be implemented to manage the use of different virtual machines on the same computing device.

[0028] The service platform 2 can be configured to communicate with the client 6 etc. via the network 4. The network 4 includes various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices and / or the like. The network 4 can include physical links such as coaxial cable links, twisted pair cable links, fiber optic links and combinations thereof, etc., or wireless links such as cellular links, satellite links, Wi-Fi links, etc.

[0029] The service platform 2 can provide services such as storage, reading, writing, querying, deleting, etc., such as providing a service for the client to read videos.

[0030] The client 6 can be an electronic device running an operating system such as Windows, Android™ or iOS, such as a smart phone, a tablet device, a laptop computer, a virtual reality device, a gaming device, a set-top box, a vehicle terminal, a smart TV. Based on the above operating systems, various application programs can be run, such as running an application program for watching videos.

[0031] The client 6 can provide / configure a user access page for manipulating the service platform 2 or uploading objects, etc.

[0032] It should be noted that the above devices are exemplary, and in different scenarios or according to different requirements, the number and types of devices can be adjusted.

[0033] The following takes the client as the execution subject and introduces the technical solutions of the present application through multiple embodiments. It should be noted that these embodiments can be implemented in many different forms and should not be construed as being limited only to the embodiments described herein.

[0034] Embodiment 1 Figure 2 A flowchart of the intelligent interaction method according to Embodiment 1 of the present application is schematically shown.

[0035] As Figure 2 shown, the intelligent interaction method can include steps S200 to S206, where: Step S200, obtain the user portrait of the user under the condition of user authorization.

[0036] Step S202, obtain the current operation of the user on the current page of the application program.

[0037] Step S204, predict the next operation of the user based on the user portrait and the current operation, and generate an operation prompt based on the next operation.

[0038] Step S206, display the operation prompt on the current page.

[0039] The intelligent interaction method provided in this embodiment obtains the user profile of the user under the condition of user authorization, obtains the current operation of the user on the current page of the application program, predicts the next operation of the user based on the user profile and the current operation, generates an operation prompt based on the next operation, and displays the operation prompt on the current page. It can generate operation prompts according to the user profile and the current operation of the user, enabling the user to quickly perform the desired operation according to the operation prompt on the current page, thereby avoiding having to go through a complex path to enter the desired page and improving the user experience.

[0040] The following combines Figure 2 to elaborate in detail on each step in steps S200 to S206 and other optional steps.

[0041] Step S200 Under the condition of user authorization, obtain the user profile of the user.

[0042] Specifically, the server can collect and analyze the user's data to create a user profile for the user under the condition of user authorization; the client can obtain the user profile of the user from the server under the condition of user authorization. Alternatively, the client can collect and analyze the user's data to create a user profile for the user under the condition of user authorization, thereby obtaining the user profile.

[0043] Step S202 Obtain the current operation of the user on the current page of the application program.

[0044] Optionally, the client can obtain the current operation of the user on the current page through behavior tracing of the application program. Specifically, it can listen for events such as clicks, inputs, swipes, and scrolls within the user's application program through behavior tracing, and obtain the current operation of the user based on the event listening.

[0045] Step S204 Predict the next operation of the user based on the user profile and the current operation, and generate an operation prompt based on the next operation.

[0046] The client can send the two data of the user profile and the current operation to the server. The server uses a pre-trained model to predict the next operation of the user based on these two data, generates an operation prompt based on the next operation, and then receives the operation prompt returned by the server.

[0047] In an alternative embodiment, step S204 may include: using an artificial intelligence assistant to predict the target page corresponding to the next operation of the user based on the user profile and the current operation of the user, and generating an operation prompt for the target page. The artificial intelligence assistant is located within the application program.

[0048] The AI assistant can appear in the form of cartoons, animations, etc. within the application. Specifically, a floating ball view component can be created inside the application to display the AI assistant, and the AI assistant can receive user interactions, such as clicks, text inputs, voice inputs, etc.

[0049] Specifically, the AI assistant itself can include a pre-trained model. This model can predict the target page corresponding to the user's next operation based on the user profile and the user's current operation using the AI assistant, and generate operation prompts for the target page. Optionally, the AI assistant can also send the user profile and the user's current operation to the server. The server predicts the target page corresponding to the user's next operation based on the user profile and the user's current operation, and generates operation prompts for the target page. Then the AI assistant obtains the operation prompts for the target page returned by the server. Among them, the operation prompts for the target page can include the link address of the target page. For example, if the user clicks an operation that requires membership on the current page and the user is not a member currently, then based on the user profile and the current operation for prediction, if the prediction result is that the user wants to open a membership, a jump link to the membership opening page can be generated, and an operation prompt can be generated based on this jump link, enabling the user to quickly jump to the membership opening page according to the jump link in the operation prompt. Another example, as Figure 3 shown, if the user watched TV A the previous day and then enters the application, based on the user profile and the current operation for prediction, if the prediction result is that the user wants to continue watching TV A, a jump link to TV A can be generated, and an operation prompt can be generated based on this jump link, enabling the user to quickly jump to the viewing page of TV A according to the jump link in the operation prompt to continue watching.

[0050] In this embodiment, by predicting the target page corresponding to the user's next operation based on the user profile and the current operation using the AI assistant located within the application, and generating operation prompts for the target page, the prediction of user behavior and operation prompts can be achieved using the AI assistant within the application. This enables the user to quickly switch to the target page according to the operation prompts, achieving the effect of active prompting and improving the user experience.

[0051] In an alternative embodiment, the AI assistant includes a lightweight model deployed on the client. Correspondingly, as Figure 4 shown, step S204 may include: Step S300, converting the input tokens of the lightweight model based on the user profile and the current operation.

[0052] Step S302: Input the input token into the lightweight model, and use the lightweight model to predict the target page corresponding to the user's next operation based on the input token, and generate an operation prompt for the target page.

[0053] The lightweight model can be a neural network model based on a deep learning framework, which reduces the volume and inference speed of the model through optimization (such as compression, model quantization, model pruning, or knowledge distillation, etc.), and can run on a client with relatively limited resources.

[0054] Specifically, the two data items of the user portrait and the current operation can be preprocessed, the features of the user portrait and the current operation are extracted, and these two features are converted into input tokens (tokens) that the lightweight model can accept; then, the obtained input tokens are input into the lightweight model, and the lightweight model is used to predict the target page corresponding to the user's next operation based on the input tokens, and an operation prompt for the target page is generated.

[0055] In this embodiment, by converting the input token of the lightweight model based on the user portrait and the current operation, inputting the input token into the lightweight model, and using the lightweight model to predict the target page corresponding to the user's next operation based on the input token and generating an operation prompt for the target page, the prediction of the user's behavior and the operation prompt can be realized on the client, quickly responding to the user's needs; at the same time, since there is no need to communicate with the server, the availability of the function can still be guaranteed in the offline case.

[0056] Step S206 , display the operation prompt on the current page.

[0057] Specifically, a window with a preset shape (such as a rectangle) can be created on the current page, and the operation prompt is displayed on the current page, so that it is convenient for the user to perform corresponding operations on the current page according to the operation prompt.

[0058] In an alternative embodiment, as Figure 5 shown, the intelligent interaction method of the embodiment of the present application may further include: Step S400: Use the artificial intelligence assistant to obtain the user's query keyword.

[0059] Step S402: Use the artificial intelligence assistant to obtain the query result based on the query keyword.

[0060] Step S404: Display the query result on the current page.

[0061] Specifically, it can be that the user clicks on the artificial intelligence assistant on the current page. The artificial intelligence assistant provides an input box for the user to input. After the user inputs a query keyword, the artificial intelligence assistant sends the query keyword to the server. The server obtains the query result according to the query keyword and returns it to the artificial intelligence assistant. The artificial intelligence assistant then displays the query result on the current page. When the user inputs the query keyword and displays the query result, it can be done by embedding a dedicated query page in the current page. Of course, in practical applications, it can also be done by jumping to another page to input the query keyword and display the query result.

[0062] In this embodiment, by using the artificial intelligence assistant to obtain the user's query keyword, and based on the query keyword, using the artificial intelligence assistant to obtain the query result and display the query result on the current page, the user can obtain the desired query result without exiting the application, thereby improving the browsing experience of the user in the application.

[0063] In an alternative embodiment, the artificial intelligence assistant further includes a large model deployed in the cloud. Correspondingly, as Figure 6 shown, the above steps S400 to S404 can further include: Step S500, when the artificial intelligence assistant receives a target instruction, obtain the user's query keyword and display the chat page of the large model on the current page.

[0064] Step S502, send the query keyword to the large model to obtain the query result by using the large model.

[0065] Step S504, display the query result in the chat page.

[0066] The target instruction can be a specific input. For example, the user makes a selection or a box selection of certain content in the comment area of the current page, or uses voice input for this specific input. The specific instruction can be set according to actual needs. When the target instruction is received, the corresponding content can be obtained according to the target instruction as the user's query keyword. For example, when the user makes a box selection of "Word A" in the comment area, the artificial intelligence assistant receives the target instruction, then identifies the content selected by the user and obtains "Word A" as the user's query keyword. Another example is that voice input can be provided in the artificial intelligence assistant. If the user inputs voice through the artificial intelligence assistant, it is considered that the target instruction is received, then the voice input by the user is recognized, and the recognized result is used as the user's query keyword.

[0067] Specifically, the AI assistant can monitor the user's operations. When receiving a target instruction, it obtains the user's query keyword according to the target instruction and displays the chat page of the large model on the current page. Then, it sends the query keyword to the large model, and the large model in the cloud obtains the query result according to the query keyword and returns it. Finally, the query result is displayed on the chat page.

[0068] In this embodiment, when the AI assistant receives a target instruction, it obtains the user's query keyword, displays the chat page of the large model on the current page, and sends the query keyword to the large model to obtain the query result using the large model. Displaying the query result on the chat page can implement the query desired by the user within the application, improve the convenience of the user's query, and ensure the browsing experience of the user within the application.

[0069] In an alternative embodiment, as Figure 7 shown, in step S400, using the AI assistant to obtain the user's query keyword may include: Step S600, in response to a copy operation on the current page, use the AI assistant to identify the keyword corresponding to the copy operation.

[0070] Step S602, use the identified keyword as the query keyword.

[0071] Specifically, the AI assistant can be used to monitor whether there is a copy operation on the current page. When there is a copy operation, the AI assistant is used to obtain the keyword corresponding to the copy operation, and the identified keyword is used as the query keyword. For example, if the user copies the unfamiliar "Word B" on the current page, when the AI assistant monitors the user's copy operation, it obtains the "Word B" copied by the user as the query keyword. Of course, if the content of the copy operation includes other non-text content (such as emojis, symbols), the other non-text content can be removed, and the remaining copied content can be used as the query keyword.

[0072] In this embodiment, by responding to a copy operation on the current page, using the AI assistant to identify the keyword corresponding to the copy operation, and using the identified keyword as the query keyword, the query can be implemented based on the user's query habit, and at the same time, the query content can be actively obtained instead of waiting passively for the user's input, further improving the user experience.

[0073] Embodiment Two Figure 8A block diagram of an intelligent interaction device according to Embodiment 2 of the present application is schematically shown. The device can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiments of the present application. The program modules referred to in the embodiments of the present application refer to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. As Figure 8 shown, the device 700 may include a first acquisition module 710, a second acquisition module 720, a prediction module 730, and a display module 740, where: The first acquisition module 710 is configured to acquire the user profile of the user with the user's authorization. The second acquisition module 720 is configured to acquire the current operation of the user on the current page of the application program. The prediction module 730 is configured to predict the next operation of the user based on the user profile and the current operation, and generate an operation prompt based on the next operation. The display module 740 is configured to display the operation prompt on the current page.

[0074] In an alternative embodiment, the prediction module 730 is further configured to: Predict the target page corresponding to the next operation of the user based on the user profile and the current operation by using an artificial intelligence assistant, and generate an operation prompt for the target page. The artificial intelligence assistant is located within the application program.

[0075] In an alternative embodiment, the artificial intelligence assistant includes a lightweight model deployed on the client side; correspondingly, the prediction module 730 is further configured to: Convert the user profile and the current operation into input tokens for the lightweight model. Input the input tokens into the lightweight model, and use the lightweight model to predict the target page corresponding to the next operation of the user based on the input tokens, and generate an operation prompt for the target page.

[0076] In an alternative embodiment, the device 700 is further configured to: Obtain the query keywords of the user by using the artificial intelligence assistant. Obtain query results by using the artificial intelligence assistant based on the query keywords. Display the query results on the current page.

[0077] In an alternative embodiment, the artificial intelligence assistant further includes a large model deployed on the cloud; correspondingly, the device 700 is further configured to: When the artificial intelligence assistant receives a target instruction, obtain the user's query keyword and display the chat page of the large model on the current page; Send the query keyword to the large model to obtain a query result using the large model; Display the query result in the chat page.

[0078] In an alternative embodiment, the apparatus 700 is further configured to: In response to a copy operation in the current page, use the artificial intelligence assistant to identify the keyword corresponding to the copy operation; Use the identified keyword as the query keyword.

[0079] Embodiment III Figure 9 Schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing the intelligent interaction method according to Embodiment III of the present application. In some embodiments, the computer device 10000 may be a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, and other terminal devices. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers), etc. As Figure 9 shown, the computer device 10000 includes, but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them: The memory 10010 includes at least one type of computer-readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 10000. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed on the computer device 10000, such as the program code of the intelligent interaction method. In addition, the memory 10010 may also be used to temporarily store various types of data that have been output or will be output.

[0080] In some embodiments, the processor 10020 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other chip. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0081] The network interface 10030 may include a wireless network interface or a wired network interface, which is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal via a network, and establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an enterprise intranet (Intranet), the Internet, Global System of Mobile communication (GSM for short), Wideband Code Division Multiple Access (WCDMA for short), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0082] It should be noted that Figure 9 only the computer device with components 10010 - 10030 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0083] In this embodiment, the intelligent interaction method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as the processor 10020) to complete the embodiments of the present application.

[0084] Embodiment 4 The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent interaction method in the embodiment are implemented.

[0085] In this embodiment, the computer-readable storage medium includes flash memory, hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), random access memories (RAM), static random access memories (SRAM), read-only memories (ROM), electrically erasable programmable read-only memories (EEPROM), programmable read-only memories (PROM), magnetic memories, magnetic disks, optical discs, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device. Of course, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is generally used to store the operating system installed on the computer device and various application software, such as the program code of the intelligent interaction method in the embodiment. In addition, the computer-readable storage medium may also be used to temporarily store various data that have been output or will be output.

[0086] Embodiment 5 The embodiment of the present application further provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0087] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the embodiments of the present application can be implemented by a general computer device. They can be concentrated on a single computer device or distributed on a network composed of multiple computer devices. Optionally, they can be implemented by program codes executable by the computer device, so that they can be stored in a storage device and executed by the computer device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0088] It should be noted that the above are only the preferred embodiments of the present application, and do not limit the patent protection scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. An intelligent interaction method, characterized in that: The method comprises: With the user's authorization, obtain the user's user profile; Get the current operation of the user on the current page of the application; Predicting the user's next operation based on the user portrait and the current operation, and generating an operation prompt based on the next operation; The operation prompt is displayed on the current page.

2. The method according to claim 1, characterized in that The predicting the next operation of the user based on the user portrait and the current operation, and generating an operation prompt based on the next operation, includes: Based on the user portrait and the current operation, an artificial intelligence assistant is used to predict the target page corresponding to the user's next operation, and an operation prompt for the target page is generated. The artificial intelligence assistant is located in the application.

3. The method according to claim 2, characterized in that The artificial intelligence assistant includes a lightweight model deployed on the client; Correspondingly, predicting the target page corresponding to the user's next operation by using an artificial intelligence assistant based on the user portrait and the current operation, and generating an operation prompt for the target page, includes: Obtaining an input token of the lightweight model based on the user portrait and the current operation conversion; The input token is input into the lightweight model, and the lightweight model is used to predict the target page corresponding to the user's next operation based on the input token, and an operation prompt for the target page is generated.

4. The method according to claim 2, characterized in that: The method further comprises: Utilizing the artificial intelligence assistant to obtain the user's query keywords; Obtaining query results using the artificial intelligence assistant based on the query keywords; The query result is displayed on the current page.

5. The method according to claim 4, characterized in that The AI ​​assistant also includes a large model deployed in the cloud; Correspondingly, the using the artificial intelligence assistant to obtain the user's query keywords, using the artificial intelligence assistant to obtain query results based on the query keywords, and displaying the query results on the current page includes: When the artificial intelligence assistant receives the target instruction, it obtains the query keyword of the user and displays the chat page of the large model on the current page; Sending the query keyword to the big model to obtain query results using the big model; The query result is displayed in the chat page.

6. The method according to claim 4, characterized in that The using the artificial intelligence assistant to obtain the user's query keywords includes: In response to a copy operation in the current page, using the artificial intelligence assistant to identify a keyword corresponding to the copy operation; The identified keyword is used as the query keyword.

7. An intelligent interactive device, characterized in that: The device comprises: A first acquisition module, used to acquire a user portrait of the user with the user's authorization; A second acquisition module is used to acquire the current operation of the user on the current page of the application; A prediction module, used to predict the next operation of the user based on the user portrait and the current operation, and generate an operation prompt based on the next operation; A display module is used to display the operation prompt on the current page.

8. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images