Data collection recommendation method and device, electronic equipment and readable storage medium

Abstract

The invention relates to a data set recommendation method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a target label; aggregating target data matched with the target tag into a corresponding recommendation set; the target data is recorded from at least two application programs; the target data is obtained based on a preset recording operation; and displaying the recommendation set. By adopting the method, the data set can be automatically and accurately recommended.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and in particular, to a data collection recommendation method and device, an electronic device, a computer readable storage medium, and a computer program product. BACKGROUND

[0002] With the rapid development of computer and network technology, electronic devices are increasingly widely used and have more and more functions, and have become an indispensable part of people's daily life. Users can record the details of work and life through electronic devices and store them in the form of data, but in the case of a large amount of stored data, the user's real needs cannot be presented through simple search, and therefore, a strategy is needed to automatically present a data collection that matches the user's real needs. SUMMARY

[0003] The embodiments of the present application provide a data collection recommendation method, device, electronic device, computer readable storage medium, which can automatically recommend a data collection that matches the user's real needs to the user.

[0004] In a first aspect, the present application provides a data collection recommendation method, comprising:

[0005] obtaining a target label;

[0006] aggregating target data matching the target label into a corresponding recommended collection; the target data is recorded from at least two application programs; the target data is obtained based on a preset recording operation;

[0007] displaying the recommended collection.

[0008] In a second aspect, the present application further provides a data collection recommendation device, comprising:

[0009] a label obtaining module configured to obtain a target label;

[0010] a data aggregation module configured to aggregate target data matching the target label into a corresponding recommended collection; the target data is recorded from at least two application programs; the target data is obtained based on a preset recording operation;

[0011] a collection display module configured to display the recommended collection.

[0012] In a third aspect, the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the data collection recommendation method provided in the first aspect when executing the computer program.

[0013] In a fourth aspect, the present application also provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the data collection recommendation method provided in the first aspect.

[0014] In a fifth aspect, the present application also provides a computer program product, comprising a computer program which, when executed by a processor, implements the steps of the data collection recommendation method provided in the first aspect.

[0015] The data collection recommendation method, device, electronic device, computer readable storage medium and computer program product described above can realize the selection and aggregation of data matched with the real needs of a user into a collection and then recommend the collection to the user, improve the accuracy of the recommendation, and automatically provide the user with data information matched with the real needs of the user, thereby improving the use experience of the device. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 Computer system block diagram for performing visual or multi-modal search services in some embodiments;

[0018] Figure 2 Framework diagram of a data processing system of an electronic device in some embodiments;

[0019] Figure 3 Internal structure diagram of a data processing system of an electronic device in some embodiments;

[0020] Figure 4 Flow diagram of a data collection recommendation method in some embodiments;

[0021] Figure 5 Display diagram of a recommended collection in some embodiments;

[0022] Figure 6 Display diagram of recorded data in a target recommended collection in some embodiments;

[0023] Figure 7 Display diagram after the "reserved collection" control is triggered in some embodiments;

[0024] Figure 8 A display schematic diagram for the "not interested" control triggering in some embodiments;

[0025] Figure 9 A display schematic diagram for the candidate function control in some embodiments;

[0026] Figure 10 A flowchart of the data collection recommendation method in some other embodiments;

[0027] Figure 11 A structural block diagram of the data collection recommendation device in some embodiments. DETAILED DESCRIPTION

[0028] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is 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 not to limit the present application.

[0029] The data collection recommendation method provided by the embodiments of the present application can be applied to an electronic device. The electronic device can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, aircraft, unmanned aerial vehicles, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. It should be noted that the electronic device can be a terminal or a server.

[0030] Figure 1 A block diagram of an example computing system 100 that performs a visual or multi-modal search service in accordance with example embodiments of the present application is depicted. The computing system 100 includes a user computing system 110, a server computing system 130, and / or a third-party computing system 150 that are communicatively coupled by a network 160.

[0031] The user computing system 110 can include any type of computing device, such as, for example, a personal computing device (e.g., a laptop or desktop computer), a mobile computing device (e.g., a smartphone or tablet computer), a gaming console or controller, a wearable computing device (e.g., a smart watch or smart glasses, etc.), an embedded computing device, or any other type of computing device.

[0032] The user computing system 110 includes one or more processors 112 and a memory 114. The one or more processors 112 can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, a FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memory 114 can include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc. and combinations thereof. The memory 114 can store data 116 and instructions 118 that are executed by the processor 112 to cause the user computing system 110 to perform operations.

[0033] In some implementations, the user computing system 110 can store or include one or more machine learning models 120. For example, the machine learning models 120 can be or can otherwise include various machine learning models such as neural networks (e.g., deep neural networks) or other types of machine learning models, including non-linear models and / or linear models. The neural networks can include feed-forward neural networks, recurrent neural networks (e.g., long short-term memory recurrent neural networks), convolutional neural networks, or other forms of neural networks.

[0034] In some implementations, the one or more machine learning models 120 can be received from the server computing system 130 over the network 160, stored in the memory 114 of the user computing system 110, and then used or otherwise implemented by the one or more processors 112. In some implementations, the user computing system 110 can implement multiple parallel instances of a single machine learning model 120 (e.g., to perform parallel machine learning model processing across multiple instances of input data and / or detected features).

[0035] Additionally or alternatively, one or more machine-learned models 140 can be included in or otherwise stored and implemented by a server computing system 130 that communicates with the user computing system 110 according to a client / server relationship. For example, the machine-learned models 140 can be implemented by the server computing system 130 as part of a web service (e.g., a lens service, a visual search service, an image processing service, an environmental computing service, and / or an overlay application service). Thus, one or more machine-learned models 120 can be stored and implemented at the user computing system 110 and / or one or more machine-learned models 140 can be stored and implemented at the server computing system 130.

[0036] The machine-learned models 120 or 140 can include one or more generative models, one or more object detection models, one or more segmentation models, one or more classification models, one or more embedding models, one or more semantic analysis models, and / or one or more search engines, among others.

[0037] One or more generative models can be used to process display data and / or one or more processing outputs to generate natural language outputs (e.g., natural language outputs including additional information about the display data and / or entities associated with data depicted in the displayed content), generate images, and / or other model-generated media content items. For example, one or more web resources can be accessed and processed to generate a summary of a particular topic. One or more object detection models can be used to perform object detection in the display data. One or more segmentation models can be used to segment objects and / or text snippets from the displayed content. One or more classification models can be used to perform object classification, image classification, entity classification, format classification, sentiment classification, and / or other classification tasks. One or more embedding models can be used to embed portions and / or all of the display data. The embeddings can then be utilized to search for similar objects and / or text, classify, group, and / or compress. Semantic analysis models can be used to process the display data to generate semantic outputs regarding topic understanding, scene understanding, focus, pattern recognition, application understanding, describing an understanding of the display data, and / or one or more other semantic outputs.

[0038] One or more search engines can process the display data, portions of the display data, and / or the output of the one or more machine learning models to determine one or more search results. The one or more search results can include web pages, images, text, videos, and / or other data. The search results can be determined based on feature mapping, feature matching, embedding search, metadata search, tag search, clustering, and / or other search techniques. The search results can be determined based on query intent classification, search result classification, and / or entity classification. The output of the models and / or the search results can be sent back to the user computing device to be provided to the user through one or more user interface elements generated and provided by the visual search interface.

[0039] The user computing system 110 can also include one or more user input components 122 that receive user input. For example, the user input components 122 can be a touch-sensitive component (e.g., a touch-sensitive display screen or trackpad) that is sensitive to the touch of a user input object (e.g., a finger or a stylus). The touch-sensitive component can be used to implement a virtual keyboard. Other example user input components include a microphone, a conventional keyboard, or other devices by which a user can provide user input.

[0040] In some implementations, the user computing system 110 can store and / or provide one or more user interfaces 124 that can be associated with one or more applications. The one or more user interfaces 124 can be configured to receive input and / or provide data for display (e.g., image data, text data, audio data, one or more user interface elements, an augmented reality experience, a virtual reality experience, and / or other data for display). The user interfaces 124 can be associated with one or more other computing systems (e.g., the server computing system 130 and / or the third-party computing system 150). The user interfaces 124 can include a viewfinder interface, a search interface, a generate model interface, a social media interface, a media content gallery interface, and / or the like.

[0041] User computing system 110 can include and / or receive data from one or more sensors 126. One or more sensors 126 can be housed in a housing assembly that houses one or more processors 112, memory 114, and / or one or more hardware components that can store and / or cause execution of one or more software packages. One or more sensors 126 can include one or more image sensors (e.g., cameras), one or more radar sensors, one or more audio sensors (e.g., microphones), one or more inertial sensors (e.g., inertial measurement units), one or more biological sensors (e.g., heart rate sensors, pulse sensors, retinal sensors, and / or fingerprint sensors), one or more infrared sensors, one or more location sensors (e.g., global positioning system, GPS), one or more touch sensors (e.g., conductive touch sensors and / or mechanical touch sensors), and / or one or more other sensors. One or more sensors can be utilized to obtain data associated with a user’s environment (e.g., images of a user’s environment, recordings of an environment, and / or a user’s location).

[0042] User computing system 110 can include and / or be part of a user computing device 111. User computing device 111 can include a mobile computing device (e.g., a smartphone or a tablet computer), a desktop computer, a laptop computer, a smart wearable device, and / or a smart appliance or an aircraft or a vehicle mounted device, among others. Additionally and / or alternatively, user computing system 110 can obtain data from and / or generate data using one or more user computing devices 111. For example, image data depicting an environment can be captured using a camera of a smartphone, and / or data provided to a user can be tracked and / or processed using an overlay application of user computing device 111. Similarly, data about a user and / or about a user’s environment can be obtained using one or more sensors associated with a smart wearable device (e.g., image data can be obtained using a camera housed in a user’s smart glasses). Additionally and / or alternatively, data can be obtained and uploaded from other user devices that can be dedicated for data obtaining or generating.

[0043] Server computing system 130 includes one or more processors 132 and memory 134. The one or more processors 132 can be any suitable processing device (e.g., processor core, microprocessor, ASIC, FPGA, controller, microcontroller, etc.) and can be a single processor or multiple processors operatively connected. Memory 134 may include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, disks, etc., and combinations thereof. Memory 134 may store data 136 and instructions 138 that are executed by processor 132 to cause server computing system 130 to perform operations.

[0044] In some implementations, the server computing system 130 includes one or more server computing devices or is otherwise implemented by one or more server computing devices. Where the server computing system 130 includes multiple server computing devices, such server computing devices may operate according to a sequential computing architecture, a parallel computing architecture, or some combination thereof.

[0045] As described above, the server computing system 130 may store or otherwise include one or more machine learning models 140. For example, the machine learning model 140 may be, or may otherwise include, various machine learning models. Example machine learning models include neural networks or other multi-layer nonlinear models. Example neural networks include feedforward neural networks, deep neural networks, recurrent neural networks, and convolutional neural networks.

[0046] Additionally and / or alternatively, server computing system 130 may include search engine 142 and / or be communicatively connected to search engine 142, which may be used to crawl one or more databases (and / or resources). Search engine 142 may process data from user computing system 110, server computing system 130, and / or third-party computing system 150 to determine one or more search results associated with input data. Search engine 142 may perform term-based searches, tag-based searches, Boolean-based searches, image searches, embedding-based searches (e.g., nearest neighbor searches), multimodal searches, and / or one or more other search techniques.

[0047] Server computing system 130 may store and / or provide one or more user interfaces 144 for obtaining input data and / or providing output data to one or more users. The one or more user interfaces 144 may include one or more user interface elements, such as input fields, navigation tools, content tiles, optional tiles, widgets, data display carousels, dynamic animations, information pop-ups, image enhancement, text-to-speech, speech-to-text, augmented reality, virtual reality, feedback loops, and / or other interface elements.

[0048] User computing system 110 and / or server computing system 130 can train machine learning models 120 and / or 140 via interaction with a third-party computing system 150 that is communicatively coupled by network 160. Third-party computing system 150 can be separate from server computing system 130 or can be part of server computing system 130. Alternatively and / or additionally, third-party computing system 150 can be associated with one or more network resources, one or more network platforms, one or more other users, and / or one or more contexts.

[0049] Third-party computing system 150 can include one or more processors 152 and memory 154. The one or more processors 152 can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, a FPGA, a controller, a microcontroller, a

[0050] controller, etc.) and can be one processor or a plurality of processors that are operatively connected. Memory 154 can include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. Memory 154 can store data 156 and instructions 158 used by processor 152 to implement the functionality of third-party computing system 150. In some implementations, third-party computing system 150 includes or is otherwise implemented by one or more server computing devices.

[0051] Network 160 can be any type of communications network, such as a local area network (e.g., an intranet), a wide area network (e.g., the Internet), or some combination thereof, and can include any number of wired or wireless links. Commumcations over network 180 can be carried using a variety of commumcations protocols, encodings, or formats (e.g., TCP / IP, HTTP, SMTP, FTP), and / or protection schemes (e.g., VPN, secure HTTP, SSL), and via any type of wired and / or wireless connection.

[0052] The machine learning models described in this application can be used for a variety of tasks, applications, and / or use cases.

[0053] In some implementations, an input to a machine learning model of the present disclosure can be image data. The machine learning model can process the image data to generate an output. As one example, the machine learning model can process the image data to generate an image recognition output (e.g., a recognition of the image data, a latent embedding of the image data, an encoded representation of the image data, a hash of the image data, etc.). As another example, the machine learning model can process the image data to generate an image segmentation output. As another example, the machine learning model can process the image data to generate an image classification output. As another example, the machine learning model can process the image data to generate an image data modification output (e.g., a change to the image data, etc.). As another example, the machine learning model can process the image data to generate an encoded image data output (e.g., an encoded and / or compressed representation of the image data, etc.). As another example, the machine learning model can process the image data to generate an upgraded image data output. As another example, the machine learning model can process the image data to generate a prediction output.

[0054] In some implementations, an input to a machine learning model of the present disclosure can be text or natural language data. The machine learning model can process the text or natural language data to generate an output. As one example, the machine learning model can process the natural language data to generate a language encoding output. As another example, the machine learning model can process the text or natural language data to generate a latent text embedding output. As another example, the machine learning model can process the text or natural language data to generate a translation output. As another example, the machine learning model can process the text or natural language data to generate a classification output. As another example, the machine learning model can process the text or natural language data to generate a text segmentation output. As another example, the machine learning model can process the text or natural language data to generate a semantic intent output. As another example, the machine learning model can process the text or natural language data to generate an upgraded text or natural language output (e.g., text or natural language data of higher quality than the input text or natural language, etc.). As another example, the machine learning model can process the text or natural language data to generate a prediction output.

[0055] In some implementations, an input to a machine learning model of the present disclosure can be speech data. The machine learning model can process the speech data to generate an output. As one example, the machine learning model can process the speech data to generate a speech recognition output. As another example, the machine learning model can process the speech data to generate a speech translation output. As another example, the machine learning model can process the speech data to generate a latent embedding output. As another example, the machine learning model can process the speech data to generate an encoded speech output (e.g., an encoded and / or compressed representation of the speech data, etc.). As another example, the machine learning model can process the speech data to generate an upscaled speech output (e.g., speech data of higher quality than the input speech data, etc.). As another example, the machine learning model can process the speech data to generate a textual representation output (e.g., a textual representation of the input speech data, etc.). As another example, the machine learning model can process the speech data to generate a prediction output.

[0056] In some implementations, an input to a machine learning model of the present disclosure can be sensor data. The machine learning model can process the sensor data to generate an output. As one example, the machine learning model can process the sensor data to generate a recognition output. As another example, the machine learning model can process the sensor data to generate a prediction output. As another example, the machine learning model can process the sensor data to generate a classification output. As another example, the machine learning model can process the sensor data to generate a segmentation output. As another example, the machine learning model can process the sensor data to generate a segmentation output. As another example, the machine learning model can process the sensor data to generate a visualization output. As another example, the machine learning model can process the sensor data to generate a diagnosis output. As another example, the machine learning model can process the sensor data to generate a detection output.

[0057] In some cases, the input includes visual data, and the task is a computer vision task. In some cases, the input includes pixel data of one or more images, and the task is an image processing task. For example, the image processing task can be image classification, in which the output is a set of scores, each score corresponding to a different object class and representing a likelihood that the one or more images depict an object belonging to the object class.

[0058] User computing system 110 can include a number of applications (e.g., applications 1 through N). Each application can include its own respective machine learning library and machine learning models. For example, each application can include a machine learning model. Example applications include a text messaging application, an email application, a dictation application, a virtual keyboard application, a browser application, and the like. In some implementations, each application can use an API (e.g., a common API across all applications) to communicate with the central intelligence layer (and models stored therein).

[0059] The central intelligence layer can include a number of machine learning models. For example, a respective machine learning model (e.g., model) can be provided for each application, and the machine learning models are managed by the central intelligence layer. In other implementations, two or more applications can share a single machine learning model. For example, in some implementations, the central intelligence layer can provide a single model (e.g., a single model) for all applications. In some implementations, the central intelligence layer is included within or otherwise implemented by the operating system of computing system 1100.

[0060] The central intelligence layer can communicate with a central device data layer. The central device data layer can be a centralized data store for computing system 100. The central device data layer can communicate with many other components of the computing device, such as, for example, one or more sensors, a context manager, a device state component, and / or additional components. In some implementations, the central device data layer can communicate with each device component using an API (e.g., a private API).

[0061] User computing device 111 can be an electronic device. Figure 2 A schematic diagram of a framework of a data processing system of an electronic device 200 in some embodiments. The electronic device 200 includes a data collection module 210, a large model 220, and a database 230. The electronic device 200 can implement a series of functions such as data collection, preprocessing, storage, mining, retrieval, recommendation, and question and answer for various applications.

[0062] In the process of displaying application page content or webpage content, the electronic device 200 can detect that the user starts the data recording function through a preset triggering mode. The preset triggering mode can be triggering of a target function key, gesture triggering (such as three-finger upward sliding), or triggering of a data recording application program, and the like.

[0063] The data collection module 210 is configured to record the screen display content of the electronic device 200 or the page content of the application running in the background according to the opened data recording function. The screen display content or the page content of the application running in the background can include text, pictures, videos, audios and the like. If it is text, the text data can be directly obtained. If it is a picture, the picture can be downloaded according to the address of the picture. If it is a video, the URL address of the video can be obtained, and the whole or fragment content of the video can be downloaded according to the URL address. If it is an audio, the download address of the audio can be obtained, and the whole or part of the data of the audio can be downloaded. The data collection module 210 can also record the screen display content in the form of a screenshot or preprocess the voice data input by the user through a microphone.

[0064] The data collection module 210 is further configured to call the large model 220 or some algorithms to preprocess the recorded screen display content to obtain data in a target format. For example, if the screen display content is text, entity extraction and summarization can be performed; if the screen display content is a picture, the picture can be recognized to obtain the picture content and classify the picture; if the screen display content is a video, key frame extraction and key frame content recognition can be performed on the video, and summary information of the video can be generated. The processed data can be stored in the database 230. The large model 220 can be a machine learning model in the Figure 1

[0065] The database 230 is a carrier or system for storing, managing and retrieving information, and its form can be different according to the storage object, use scenario and technical architecture. The database 230 can store data and has at least one management capability such as classification, retrieval, synchronization, permission control and the like. The database 230 can be an application program, an applet, an API interface, a personal dedicated storage hardware, an embedded hardware recording module, a cloud service form database, a browser plug-in, a bookmark management tool, an enterprise knowledge base system, a cache type database, a personal information base and the like. The personal dedicated storage hardware can be a mobile hard disk with a dedicated management system, an encrypted U disk, a personal cloud storage hard disk and the like. The embedded hardware recording module can be a dedicated storage module in a smart device for recording various data. The cloud service form database can be a cloud database providing interface calling service function or a database of personal cloud data management service.

[0066] ​The database 230 includes a data management module 240 and a data interaction module 250. The data management module 240 can call the large model 220 to mine the stored data, and the mined data can be stored in the database 230, and data retrieval functions, etc. can be provided. The mining method can include data desensitization processing, label classification, entity extraction, schedule extraction, to-do item extraction, abstract generation, generating a collection, recommending a collection, data correlation, etc. The data management module 240 can also summarize and organize various types of data recorded by the user, and can obtain user portrait information. The user portrait information can include user personal information, personal preference information, etc. The user personal information can include the user's identity information, occupation, education, family information, etc. The personal preference information can include favorite people, things, places, scenery, games, etc., without limitation.

[0067] The data interaction module 250 can provide interaction functions with application programs, and can obtain data required for interaction through the data management module 240. The interaction functions can include recommending a collection, data search, data detail viewing, data sharing, AI Q&A, data association, etc., without limitation. For example, the AI Q&A function, the data interaction module 250 obtains a question provided by the user in the AI Q&A application, and sends the question to the data management module 240, the data management module 240 searches for the corresponding answer, and provides it to the data interaction module 250 Feedback to the AI Q&A related application.

[0068] Further, the data collected by the data collection module 210 in the electronic device 200 and the mined user portrait information, etc. can be synchronized to the cloud as needed, the collected data can also be processed by means of the large model of the cloud, and the data synchronized to the cloud can also be synchronized to other electronic devices through the cloud, realizing the sharing of data between different devices.

[0069] Figure 3 An internal structure diagram of the data processing system of the electronic device in some embodiments. The data collection module 210 can include a collection entry submodule 211, an extraction submodule 212, a screenshot acquisition submodule 213, a preprocessing submodule 214, and a writing submodule 215, etc.

[0070] The collection entry sub-module 211 is configured to provide an entry for data collection, for example, a voice assistant entry through which a data record instruction in the form of a user voice input is received, a gesture trigger entry such as a long entry of a hardware key or a three-finger upward swipe entry, or a trigger entry of a specific control of a user such as a like control, a collection control, a sharing control, and the like. The collection entry sub-module 211 can automatically collect data according to a set rule, for example, a collection trigger condition is a preset page content, and when it is detected that the page information displayed by the electronic device contains the preset page content, the page information is automatically collected. The collection entry sub-module 211 can also receive donated data of some application programs (such as a weather application, a clock application, a pedometer application, and the like), such as weather data, time data, walking data, running mileage, and the like, without being limited thereto.

[0071] The extraction sub-module 212 can perform image-text extraction on the page content of the application that needs to be recorded.

[0072] The screenshot acquisition sub-module 213 can acquire a screenshot of the screen content, and then acquire text content by calling an OCR recognition algorithm to recognize the content of the screenshot.

[0073] The preprocessing sub-module 214 can perform word segmentation, denoising, or processing into a preset format on the collected data.

[0074] The writing sub-module 215 is configured to write the collected data or the preprocessed data into the database 230.

[0075] The data management module 240 can include a data mining sub-module 241, a question and answer sub-module 242, a retrieval sub-module 243, a source data processing sub-module 244, and the like.

[0076] The data mining sub-module 241 is configured to mine data. The mining manner can include data desensitization processing, label classification, entity extraction, schedule extraction, to-do item extraction, abstract generation, generation of a collection, recommendation of a collection, data correlation, and the like.

[0077] The question and answer sub-module 242 is configured to search for corresponding data according to a user question, and generate a corresponding answer according to the searched data.

[0078] The retrieval sub-module 243 is configured to retrieve corresponding data from the database 230 according to a search request, and arrange the retrieved data or directly feed back the retrieved data to a user.

[0079] The source data processing sub-module 244 is configured to provide addition, modification, deletion, and update operations on source data. The source data can be data recorded in the database 230 after collection or data obtained by preprocessing the collected data.

[0080] The data interaction module 250 includes a data addition / edit / view submodule 251, a data recommendation submodule 252, a data search submodule 254, a related data submodule 254, and the like.

[0081] The data addition / edit / view submodule 251 is configured to provide functions of adding, editing, viewing, and the like of data.

[0082] The data recommendation submodule 252 is configured to recommend collection data to a user or recommend stored data according to a user portrait.

[0083] The data search submodule 253 is configured to obtain a search demand of a user and transmit the search demand to a retrieval submodule 243 in the data management module 240. The retrieval submodule 243 retrieves corresponding data from the database 230 according to the search demand and feeds back the retrieved data to the data search submodule 253.

[0084] The related data submodule 254 is configured to associate or recommend recorded data to other application programs.

[0085] In some exemplary embodiments, as shown in FIG. 5, a data collection recommendation method is provided, including the following steps 402 to 406. Among them: Figure 4

[0086] Step 402: Obtain a target label.

[0087] Among them, the recorded data can be structured information obtained through a data recording function of an electronic device and obtained after processing. The data recording function is configured to analyze and store data information. The structured information is a data organization form in which data is organized into a predefined format. The structured information can include explicit fields or columns, corresponding data types, and the like. Such a data organization method can make data storage, retrieval, and analysis more efficient and accurate. In actual application scenarios, the recorded data can be obtained by processing voice information input by a user through a data recording function, or obtained by processing text information input by a user through a data function, or obtained by processing interface information of an interface through a data function. After obtaining a plurality of pieces of recorded data, the recorded data can be stored for the user to review when needed.

[0088] ​It is easy to understand that each piece of record data has a corresponding label. The label corresponding to the record data can be generated when the record data is generated. The label can be understood as a semantic keyword of the corresponding record data. Each piece of record data can include one or more labels. The label of each piece of record data can be generated by manual annotation or by semantic recognition algorithm for semantic recognition of record data. Assuming that there is no duplicate record data, the labels of different record data are usually different. The target label can be used to represent the content of interest of the user. After determining the target label, the record data of interest of the user can be obtained based on the target label.

[0089] Exemplarily, the target label can be determined according to the number of record data corresponding to the label of all record data. For example, the label with the number of record data exceeding a number threshold is determined as the target label, or the label with the number of record data from high to low target number is determined as the target label, etc. Alternatively, the candidate data list can also be filtered according to a preset condition, and the candidate data is stored in the candidate data list. The target label can be determined according to the number of record data matched in the local data list according to the candidate label of the candidate data. Alternatively, the target label can also be determined according to the user operation content.

[0090] Step 404, aggregating target data matched with the target label to a corresponding recommendation set; wherein the target data is recorded from at least two application programs; and the target data is obtained based on a preset recording operation.

[0091] The aggregation is used to represent the process of classification according to a preset classification rule. Each set is used to represent a kind of record data. For example, the record data can be classified according to transaction attributes, and the corresponding set of classified data is created, such as the corresponding set of travel strategy, fitness, food or interpersonal relationship, etc. It is easy to understand that the number and type of the set can be set according to the actual application scene, which is not limited here.

[0092] Exemplarily, the record data including the target label in the local data list can be taken as the target data matched with the target label. In an actual application scenario, if the target label includes multiple target labels, the target data matched with each target label can be selected as the aggregation data, and the number of the aggregation data corresponding to each target label does not exceed a second threshold. The first threshold is less than the second threshold. The second threshold can be an integer multiple of the first threshold. For example, the first threshold is 100, and the second threshold is 1000. The first threshold or the second threshold can be set according to an actual application scenario, which is not limited herein. It is easy to understand that if the number of the target data matched with the target label is greater than the first threshold, the target data matched with the target label can be selected as the aggregation data according to the data generation time from near to far. Then the aggregation data is aggregated into the corresponding recommendation collection, so as to limit the number of the aggregation data aggregated into the corresponding recommendation collection each time, and reduce the storage pressure of the recommendation collection.

[0093] Exemplarily, the target data can be matched with the collection keyword of the recommendation collection, and the recommendation collection corresponding to the collection keyword matched with the target data is taken as the corresponding recommendation collection of the target data. The collection keyword is used to represent the corresponding collection, and each collection can include one or more collection keywords. It is easy to understand that the target data is matched with the recommendation collection, and the semantic similarity between the label of the target data and the collection keyword of the recommendation collection is higher than a similarity threshold.

[0094] The record data stored in the electronic device can be recorded from one or more application programs installed on the electronic device. That is, the data in each application program on the electronic device can be recorded. The target data is recorded from at least two application programs. For example, the target data includes data recorded from an A application program and data recorded from a B application program, or the target data includes data recorded from an A application program, data recorded from a B application program and data recorded from a C application program, and the like. In some application scenarios, the at least two application programs can include a target application program having a data recording function.

[0095] The preset recording operation can include, for example, a screenshot operation, a like operation, a share operation, a collection operation, or a search operation, and the like. The preset recording operation can also include an operation of triggering a voice dialogue, or satisfying other preset recording conditions, and the like. In an actual application scenario, in response to the triggering of the preset recording operation, the content corresponding to the preset recording operation is recorded to obtain the corresponding record data. Generally, the target data can be part or all of the record data saved in the electronic device.

[0096] Step 406, display the recommendation collection.

[0097] The aggregation of the target data into the corresponding recommendation set is equivalent to an updating process of the original recommendation set. After obtaining the updated recommendation set, the recommendation set can be displayed. The recommendation set can include multiple, for example, multiple recommendation sets can be displayed in a preset order in turn, or the recommendation set can be displayed randomly. The display mode of the recommendation set can be displayed in the form of a card, a pop-up window, a banner, a scroll comment, etc., which is not limited herein.

[0098] For example, the recommendation set can be displayed in the recommendation list of the corresponding application interface, for example, each recommendation set can be dynamically displayed, or each recommendation set can be displayed in a tiled manner, or each recommendation set can be displayed in a stacked manner, etc.

[0099] The above data set recommendation method can achieve the following effects: by obtaining the target label, and then aggregating the target data matched with the target label into the corresponding recommendation set, and displaying the recommendation set, the data matched with the real needs of the user can be selected and aggregated into a set and recommended to the user, the accuracy of the recommendation is improved, and the use experience of the device is improved.

[0100] In some embodiments, the target label is obtained in step 402, comprising:

[0101] The target label is obtained according to the number of record data in the local data list matched with the candidate label of the candidate data in the candidate data list.

[0102] The candidate data list is a list for storing candidate data. The candidate data is the record data in the local data list filtered according to a preset condition. The candidate label refers to the label of the candidate data. The record data in the local data list is used to represent all record data stored in the electronic device, i.e., the full amount of data stored in the local data list. The preset condition can be, for example, a preset time period, a preset theme, or a preset location, etc. It is easy to understand that different application scenarios correspond to different preset conditions. For example, in one application scenario, the preset condition can be a preset time period, and in another scenario, the preset condition can be a preset theme, etc. For example, the preset time period includes a preset time period, such as the last day (24 hours), the last 2 days, or the last month, etc., which can be set according to the actual application scenario.

[0103] In an example embodiment, the electronic device is pre-established with a candidate data list and a local data list, the candidate data list storing candidate data, and the local data list storing full-amount data recorded by the user. The electronic device can acquire candidate labels of the candidate data, match each candidate label with recorded data in the local data list, acquire the number of recorded data matched by each candidate label, and designate candidate labels with a number of matched recorded data from the most to the least as target labels. It is easy to understand that the more the number of matched recorded data, the more the frequency of the corresponding candidate label, and the more the candidate label can represent the real intention of the user. Alternatively, candidate labels with a number of matched recorded data greater than a number threshold can also be designated as target labels.

[0104] In the present embodiment, the target labels are acquired according to the number of recorded data in the local data list matched by the candidate labels of the candidate data in the candidate data list, so that the target labels can be quickly determined from the candidate labels while ensuring the accuracy of the target labels.

[0105] In some embodiments, the target labels are acquired according to the number of recorded data in the local data list matched by the candidate labels of the candidate data in the candidate data list, including:

[0106] The candidate labels of the candidate data in the candidate data list are acquired, the recorded data in the local data list is matched with the candidate labels, and the number of recorded data matched by each candidate label is acquired. The target labels with a number of matched recorded data greater than a number threshold are determined from the candidate labels.

[0107] In which, the labels of each recorded data in the local data list can be compared with the candidate labels one by one. If the label of a recorded data includes one of the candidate labels, it means that the recorded data is matched with the corresponding candidate label. In this way, the recorded data matched with each candidate label and the number of matched recorded data can be acquired.

[0108] In an actual application scenario, the electronic device can obtain the label of each candidate data in the candidate data list, perform deduplication processing on the labels of all candidate data in the candidate data list, and obtain the candidate label of the candidate data. By matching the record data in the local data list with each candidate label, record data matching each candidate label can be obtained, and the number of record data matching each candidate label is obtained. The number of record data matching each candidate label is compared with the number threshold, and the candidate label with the number of matching record data greater than the number threshold is taken as the target label. As can be easily understood, the candidate label with the number of matching record data greater than the number threshold indicates that the frequency of the candidate label is high, which can represent the user's intention to a certain extent, and the target data more in line with the user's demand can be screened based on the target label. The number threshold can be set according to the actual application scenario. For example, the number threshold can be 3, 5, or 10, etc.

[0109] In this embodiment, by matching the record data in the local data list with the candidate label of the candidate data in the candidate data list, the target label with the number of matching record data greater than the number threshold is determined from the candidate label, which can quickly determine the target label matching the real demand of the user, and improve the accuracy and determination efficiency of the target label.

[0110] In some embodiments, before obtaining the candidate label of the candidate data in the candidate data list, the above method further comprises:

[0111] identifying the number of candidate data in the candidate data list; and in a case where the number of candidate data reaches a target number, performing the step of obtaining the candidate label of the candidate data in the candidate data list.

[0112] The candidate data is record data selected from the local data list. If the number of candidate data is small, the number of target labels determined based on the candidate label of the candidate data is also small, and the number of target data matching the target label is also small, thereby increasing the number of execution of the data collection recommendation process and increasing power consumption. At the same time, the degree of updating the recommended collection each time is also small, which is easy to cause the recommended collection to have high repetition, thereby reducing the use experience of the data collection recommendation.

[0113] For example, the electronic device can store the data meeting the preset condition from the local data list to the candidate data list as candidate data in real time, identify the number of candidate data in the candidate data list, and if the number of candidate data in the candidate data list reaches a target number, perform the step of obtaining the candidate label of the candidate data in the candidate data list, that is, perform the data collection recommendation process. The target number can be set according to the actual application scenario. For example, the target number can be 5, 10, or 20, etc.

[0114] Exemplarily, the electronic device monitors the number of candidate data in the candidate data list, can set the number variable value of the candidate data in the candidate data list to 0 in the initial state, add 1 to the number variable value each time a candidate data is added to the candidate data list, and obtain the candidate labels of the candidate data in the candidate data list when the number variable value is the target number. Then, the data in the local data list is matched with the candidate labels, the number of data matched with each candidate label is obtained, the target label whose matched data number is greater than the number threshold is determined from the candidate labels, or the candidate label with the specified number of matched data from the most to the least is taken as the target label. The target data in the local data list matched with the target label is aggregated to the corresponding recommended collection, and the recommended collection is displayed.

[0115] In the embodiment, by identifying the number of candidate data in the candidate data list, the step of obtaining the candidate labels of the candidate data in the candidate data list is performed when the number of candidate data reaches the target number, which can reduce the execution frequency of the data collection recommendation process within a fixed time and reduce the device power consumption. At the same time, by setting the target number, the device power consumption and the recommendation repetition can be well balanced, thereby improving the device use experience.

[0116] In some embodiments, after obtaining the candidate labels of the candidate data in the candidate data list, the above method further includes:

[0117] removing the candidate data whose candidate labels have been obtained from the candidate data list.

[0118] In the embodiment, if the candidate labels of the candidate data have been obtained, it means that the corresponding candidate data has been subjected to the data collection recommendation process, i.e., the candidate labels of the candidate data have participated in the selection of the target data and the display of the corresponding recommended collection. Therefore, the candidate data whose candidate labels have been obtained can be removed from the data list to avoid repeated acquisition of the candidate labels of the candidate data, thereby affecting the accuracy of the recommended collection.

[0119] In some practical application scenarios, when the number of candidate data in the candidate data list identified by the electronic device reaches the target number, the electronic device obtains the candidate labels of the candidate data in the candidate data list, matches the data in the local data list with the candidate labels, and obtains the number of data matched with each candidate label. The electronic device determines a target label from the candidate labels, where the number of matched data is greater than the number threshold, aggregates the target data in the local data list matched with the target label to the corresponding recommendation set, and displays the corresponding recommendation set according to the predetermined strategy. After obtaining the candidate labels of the candidate data in the candidate data list, the candidate data for which the candidate labels have been obtained is removed from the candidate data list, that is, is not saved in the candidate data list. The candidate data list is used to save the subsequently newly screened candidate data. When the number of newly screened candidate data reaches the target number, the candidate labels of the candidate data in the candidate data list under the current condition are obtained, and the above data set recommendation process can be repeatedly executed.

[0120] In this embodiment, after obtaining the candidate labels of the candidate data in the candidate data list, the candidate data for which the candidate labels have been obtained is removed from the candidate data list, which can avoid repeated acquisition and use of the candidate labels, realize sufficient updating of the candidate data in the candidate data list, improve the accuracy of the target label determined from the candidate labels, and thus improve the recommendation accuracy of each data set recommendation.

[0121] In some embodiments, the aggregation of the target data matched with the target label to the corresponding recommendation set in step 404 includes:

[0122] determining the target data matched with the target label from the local data list; performing deduplication processing on the target data matched with the target label to obtain deduplicated target data; and aggregating the deduplicated target data to the corresponding recommendation set.

[0123] The target label can include one or more. If the label of a target data includes the target label, it means that the target data matches the target label. For example, assuming that the target label includes label 2, label 4 and label 5, and the label of target data A includes label 1, label 2 and label 3, since the label of target data A includes label 2 in the target label, it means that target data A matches label 2 in the target label. Assuming that the label of target data B includes label 2 and label 4, since the label of target data B includes label 2 and label 4 in the target label, it means that target data A matches label 2 and label 4 in the target label. Alternatively, if the similarity between the label of a target data and the target label reaches a similarity threshold, it means that the target data matches the target label. The target data matching each target label can be determined from the local data list, the target data matching each target label is de-duplicated, the de-duplicated target data is obtained, and then the de-duplicated target data is aggregated into the corresponding recommendation set. De-duplication refers to processing in which only one of the repeated objects is retained. Since a record data can include multiple labels, different target labels can match the same target data, and thus repeated target data can occur, and the target data needs to be de-duplicated.

[0124] For example, the electronic device can determine the target data matching each target label from the local data list, thereby obtaining the target data matching each target label, de-duplicate the target data matching each target label, obtain the de-duplicated target data, and aggregate the de-duplicated target data into the corresponding recommendation set. For example, repeated data can be filtered from the target data matching each target label, and if repeated data exists, only one record data of the repeated data needs to be retained until there is no repeated record data in all target data, thereby obtaining the de-duplicated target data. Then the de-duplicated target data is aggregated into the corresponding recommendation set. It should be noted that the implementation of de-duplication is not limited here, as long as there is no repeated record data in the de-duplicated target data.

[0125] In this embodiment, by determining the target data matching the target label from the local data list, de-duplicating the target data matching the target label, obtaining the de-duplicated target data, and then aggregating the de-duplicated target data into the corresponding recommendation set, the situation that the final matched target data is repeated due to different target labels matching the same target data can be avoided, and the experience of set recommendation of the device is improved.

[0126] In some embodiments, the step 104 of aggregating the target data matching the target label into the corresponding recommendation set includes:

[0127] match each target data in the local data list matching the target label with the historical recommendation set; if there is a historical recommendation set matching the target data successfully, the target data is aggregated into the matching historical recommendation set; if the target data does not match all historical recommendation sets successfully, a new recommendation set is created according to the target data; the new recommendation set includes the target data.

[0128] The historical recommendation set refers to a recommendation set that has been established. The historical recommendation set can be created according to the target data determined by initialization. The historical recommendation set can include one or more. It is easy to understand that if it is the first time to implement the data set recommendation process, there may be no historical recommendation set, and a corresponding recommendation set needs to be created according to the target data. Aggregating the target data into the matching historical recommendation set can be understood as classifying the target data into the corresponding data category.

[0129] Exemplarily, the electronic device matches each target data in the local data list matching the target label with each historical recommendation set in turn, and if there is a historical recommendation set matching the target data successfully, the target data is aggregated into the matching historical recommendation set. If there is a semantic similarity between the set keywords of the historical recommendation set and the target data greater than a similarity threshold, it means that the target data matches the historical recommendation set. Alternatively, the set keywords of the historical recommendation set can also be matched with the labels of the target data, and if there is a semantic similarity between one set keyword and one label of the target data greater than a similarity threshold, it means that the corresponding historical recommendation set matches the target data. Conversely, if there is no semantic similarity between the set keywords of the historical recommendation set and the target data greater than a similarity threshold, or there is no semantic similarity between the set keywords and the labels of the target data greater than a similarity threshold, it means that the historical recommendation set does not match the target data.

[0130] Exemplarily, if the target data fails to match all the historical recommendation sets, it indicates that the target data does not belong to any data category corresponding to the historical recommendation sets, and a new recommendation set needs to be created according to the target data. In other words, the target data for initialization determination refers to the target data used to create a new recommendation set. For example, if the target data fails to match all the historical recommendation sets, the set keyword can be determined according to the target data, and a new recommendation set corresponding to the target data is created according to the set keyword. Exemplarily, the determined set keyword can be used as the set name to create a new recommendation set, and the target data is added to the new recommendation set. As an example, if the determined set keyword is "food in different places", a new recommendation set with the set name "food in different places" can be created, and the target data is added to the new recommendation set with the set name "food in different places".

[0131] In some examples, if the target data fails to match all the historical recommendation sets, the set keyword is determined according to the target data, and in the subsequent target data that fails to match all the historical recommendation sets, the first data matching the determined set keyword is screened, and if the number of the first data reaches a preset number, a new recommendation set corresponding to the set keyword is created based on the first data. If the number of the first data does not reach the preset number, a new recommendation set corresponding to the set keyword can not be created. Each recommendation set usually includes a plurality of target data.

[0132] Exemplarily, after the new recommendation set is created, the user can manually update the new recommendation set. For example, the user can manually modify the set name of the new recommendation set, manually add other data information to the new recommendation set, and manually delete part of the data information from the new recommendation set.

[0133] In this embodiment, by matching each target data in the local data list that matches the target tag with the historical recommendation set, if there is a historical recommendation set that matches the target data, the target data is aggregated into the matched historical recommendation set, and if the target data fails to match all the historical recommendation sets, a new recommendation set is created according to the target data, which can ensure that all target data matching the target tag can be accurately aggregated into the corresponding recommendation set, and improve the accuracy of the recommendation set.

[0134] In some examples, if there is a historical recommendation set that matches the target data, the target data is aggregated into the matched historical recommendation set, including:

[0135] If the historical recommendation set matches the target data, the similarity between each record data in the matched historical recommendation set and the target data is calculated; if the similarity between each record data in the matched historical recommendation set and the target data is less than or equal to the similarity threshold, the target data is aggregated into the matched historical recommendation set; if there is record data in the matched historical recommendation set that has a similarity greater than the similarity threshold with the target data, the target data is not aggregated into the matched historical recommendation set.

[0136] The similarity between each record data in the historical recommendation set and the target data is used to represent the semantic similarity between each record data in the historical recommendation set and the target data. If the similarity is greater than the threshold, it means that the corresponding record data in the historical recommendation set is more similar to the target data, and the similar target data can not be aggregated into the corresponding historical recommendation set; if the similarity is less than or equal to the similarity threshold, it means that the corresponding record data in the historical recommendation set is less similar to the target data, and the dissimilar target data can be aggregated into the corresponding historical recommendation set. The similarity threshold can be set according to the actual application scenario, for example, the similarity threshold is 80%, 85% or 90%, etc.

[0137] For example, after determining the historical recommendation set that the target data matches, the similarity between each record data in the matched historical recommendation set and the target data is calculated, and the similarity between each record data in the matched historical recommendation set and the target data is compared with the similarity threshold. If the similarity between each record data in the matched historical recommendation set and the target data is less than or equal to the similarity threshold, the target data is aggregated into the matched historical recommendation set; if there is record data in the matched historical recommendation set that has a similarity greater than the similarity threshold with the target data, it means that there is record data in the matched historical recommendation set that is semantically similar to the target data, and the target data can not be aggregated into the matched historical recommendation set, i.e., the target data is regarded as duplicate data, avoiding aggregating two duplicate data into the same recommendation set.

[0138] In this embodiment, by calculating the similarity between the target data and the record data in the matched historical recommendation set, in the case where the similarity is less than or equal to the similarity threshold, i.e., the target data and the record data in the matched historical recommendation set are not too similar, the target data is aggregated into the matched historical recommendation set; if there is record data in the matched historical recommendation set that has a similarity greater than the similarity threshold with the target data, i.e., there is similar data in the matched historical recommendation set, the target data is not aggregated into the matched recommendation set, which can avoid aggregating multiple semantically similar data into the same recommendation set, occupying the recommendation resources, and improving the recommendation efficiency.

[0139] In some embodiments, the target label is acquired in step 402, including:

[0140] The user operation content is acquired, and the target label is acquired according to the user operation content.

[0141] The user operation content may, for example, be content searched, browsed, liked, collected or shared by the user on a system application or a third-party application, and the user operation content is used to represent content of interest to the user.

[0142] For example, the electronic device can detect the user operation content in real time, and determine the target label according to the user operation content detected within a target time period. The target time period may, for example, be set according to an actual application scenario. For example, the target time period is 1 hour, 2 hours or 5 hours, etc. Alternatively, the target label may, for example, be determined according to the user operation content when the user operation content detected reaches a target amount.

[0143] For example, the electronic device can determine the target label according to the semantics of the user operation content.

[0144] In this embodiment, by acquiring the target label according to the user operation content, the target data matched with the target label in the local data list is aggregated into a corresponding recommended collection, and the recommended collection is recommended to the user, which can improve the matching degree between the recommended collection and the real needs of the user, and improve the accuracy of the data collection recommendation.

[0145] In some embodiments, the target label is acquired according to the user operation content, including:

[0146] The user operation content is subjected to semantic recognition to obtain a semantic recognition result, and a content keyword is determined according to the semantic recognition result, and the content keyword is determined as the target label.

[0147] The electronic device may, for example, detect the user operation content and extract semantic information of the user operation content to obtain the semantic recognition result, represent the semantic recognition result by a content keyword, and determine the content keyword as the target label. The content keyword may, for example, be used to represent the user operation content.

[0148] In an actual application scenario, the electronic device can detect the content of the target operation of the user in a system application or a third-party application in real time to obtain the user operation content, extract semantic information of the user operation content through a semantic extraction tool to obtain a semantic recognition result, summarize the semantic recognition result as a content keyword, and thus obtain the target label. The target operation can be a search, browsing, liking, collecting, or reposting operation of the user. For example, if the user searches for "what are the local delicacies in XX place" on a search engine, the electronic device can detect that the content of the search operation is "what are the local delicacies in XX place", perform semantic recognition according to the content of the corresponding search operation to obtain a semantic recognition result, determine that the content keyword is "XX place" and "delicacies" according to the semantic recognition result, and determine the content keywords "XX place" and "delicacies" as the target label. As an example, if the target operation is a browsing operation, the user operation content can be determined according to the browsing duration. For example, content with a browsing duration greater than or equal to a duration threshold value can be taken as the user operation content, and if the browsing duration is less than the duration threshold value, the content is not taken as the user operation content. In other words, if the electronic device detects a browsing operation of the user, it needs to further detect the browsing duration corresponding to the browsing operation. If the browsing duration is greater than or equal to the duration threshold value, the content of the browsing operation is determined as the user operation content. Otherwise, if the browsing duration is less than the duration threshold value, even if the browsing operation is detected, the content corresponding to the browsing operation is not determined as the user operation content.

[0149] In an example embodiment, the electronic device can integrate the user operation content detected within the target duration or the user operation content reaching the target amount to obtain integrated operation content, perform semantic recognition on the integrated operation content to obtain a semantic recognition result, and then determine a content keyword according to the semantic recognition result and determine the content keyword as the target label. The target amount can be represented by the size of the occupied storage space or the structural complexity. The size of the target amount can be set according to an actual application scenario. As an example, the integration can be implemented through an artificial intelligence model. For example, the artificial intelligence model is used to generate user operation content for integration to obtain integrated operation content, generate an abstract corresponding to the integrated operation content, extract a content keyword based on the abstract, and determine the extracted content keyword as the target label. The integration method is not limited to being implemented through an artificial intelligence model, but can also be implemented through other methods, which are not limited herein. Alternatively, the user operation content detected within the target duration or the user operation content reaching the target amount can be directly subjected to semantic recognition to obtain a semantic recognition result, and then a content keyword is determined according to the semantic recognition result.

[0150] In this embodiment, the semantic recognition result is obtained by performing semantic recognition on the user operation content, the content keyword is determined according to the semantic recognition result, the content keyword is determined as the target label, the target label can be matched with the semantic of the user operation content, the target label can be accurately determined through the user operation content, the matching between the target label and the user intention is improved, and therefore the recommendation accuracy is improved.

[0151] In some embodiments, the step 406 of displaying the recommendation collection comprises:

[0152] The recommendation collections are displayed in the preset order in turn.

[0153] Generally, the recommendation collection includes a plurality of recommendation collections, and each recommendation collection includes a plurality of record data. The record data in each recommendation collection can be arranged in a time sequence from new to old or from old to new, or can be arranged in other sequences. The preset arrangement order of the plurality of record data in each collection can be set according to actual application scenarios. Each displayed recommendation collection can correspond to the display of the collection name of the recommendation collection, the number of included record data, and the like. The preset order can be set according to actual application scenarios. The preset order includes a random order, i.e., the recommendation collections are displayed randomly. Alternatively, the preset order can be an update time order of the recommendation collections. For example, the preset order is an order from late to early of the update time of the recommendation collections, the recommendation collection updated later is arranged in front, and the recommendation collection updated earlier is arranged in back.

[0154] Exemplarily, the recommendation collections can be displayed in the preset order in turn, a preset number of recommendation collections are displayed each time, and the display lasts for a preset time length. The preset number or the preset time length can be set according to actual application scenarios. For example, the preset number is 3, 4, or 5, and the preset time length is 1 second, 2 seconds, or 3 seconds, without limitation. As an example, 3 recommendation collections are displayed each time in the preset order, the 3 recommendation collections displayed each time are displayed for 1 second, and then another 3 recommendation collections are displayed, so as to realize dynamic display of the recommendation collections.

[0155] In an exemplary embodiment, in the process of displaying the recommendation collections in the preset order in turn, in response to a selection operation of a target recommendation collection by a user, the electronic device can display a certain number of data each time according to the arrangement mode of the data in the target recommendation collection, and display the summary information of the target recommendation collection. The number of record data displayed each time can be set according to actual application scenarios. The target recommendation collection can be any one of the recommendation collections. Each data in the target recommendation collection can display at least one of the following data information: a corresponding record data name, a record data source, a number of associated data, a record data summary, a record data recording time, and a representative picture. The arrangement mode of the data information is not limited here.

[0156] As an example, a display schematic of a recommended collection is shown in Figure 5 The recommended collections can be displayed in the application interface of the target application in a preset order, each recommended collection displays a collection name and a number of record data included in the recommended collection. In response to a selection operation on the target recommended collection "XX travel strategy", the record data information included in the target recommended collection can be displayed in a list, a stack, or a tile in a preset arrangement order, as shown in Figure 6 The record data information included in the target recommended collection can be displayed in a list, a stack, or a tile in a preset arrangement order, as shown in

[0157] In this embodiment, by displaying the recommended collections in a preset order, the information of each recommended collection can be better displayed to the user, and the data collection recommendation experience of the device is improved.

[0158] In some embodiments, the step 406 of displaying the recommended collection includes:

[0159] The recommended collections are displayed in a stack.

[0160] The stack display refers to a display mode in which multiple recommended collections are interleaved and stacked. In actual application scenarios, each recommended collection can be displayed in a stack in a sequence from new to old or from old to new. Alternatively, each recommended collection can be displayed in a stack in a sequence from high to low according to the highlight level of the collection. The highlight level of each recommended collection can be determined according to the collection keywords of the recommended collection. For example, if the collection keywords represent themes such as sports, parties, and travel, the highlight level is high, and if the collection keywords represent themes such as to-do lists and work reminders, the highlight level is low. It is easy to understand that the highlight level can be determined according to actual application scenarios.

[0161] In this embodiment, by displaying the recommended collections in a stack, the overall information of the recommended collections can be displayed intuitively, and the data collection recommendation experience is improved.

[0162] In some embodiments, the above method further includes:

[0163] Displaying multiple recommended collections and a collection editing control; in response to a triggering operation on the collection editing control, adding or deleting a recommended collection.

[0164] The collection editing control refers to a control for editing a recommended collection. Each recommended collection corresponds to a corresponding collection editing control, and in response to a triggering operation on the collection editing control, the corresponding recommended collection can be added or deleted. The collection editing control includes at least an adding control and a deleting control.

[0165] Exemplarily, in response to the triggering of the adding control of the target recommendation collection, the target recommendation collection is added into the "my collection". In response to the triggering of the deleting control of the target recommendation collection, the target recommendation collection is deleted from the recommendation collection list.

[0166] In some examples, the collection editing control further includes a changing control. For example, in the display interface of the recommendation collection, the name of the displayed target recommendation collection can be changed; or the record data not interested in the target recommendation collection is deleted, or the record data is added to the target recommendation collection; or the displayed target recommendation collection can be moved to other collection categories, for example, moved to the "my collection" representing the user's focus; or the target recommendation collection is labeled with a preset label, such as "interested", "not interested", "no longer recommended", etc.; or the target recommendation collection can be deleted. The target recommendation collection can be any displayed recommendation collection.

[0167] Exemplarily, the display interface of the recommendation collection is provided with an editing control corresponding to the editing operation of the recommendation collection, and in response to the triggering of the editing control, the processing corresponding to the editing operation of the displayed recommendation collection is performed. As an example, in response to the selection operation of the target recommendation collection, the record data information included in the target recommendation collection is displayed in a preset arrangement order, and the "keep collection", "not interested" and "chat" editing controls can also be displayed. The "keep collection" control is used to move the target recommendation collection to the "my collection" category; the "not interested" control is used to represent that the corresponding target recommendation collection is not interested at the current time, and "no longer recommend this collection"; the "chat" control is used to represent the response or processing according to the input content or question. It is easy to understand that the editing control can be set according to the actual application scenario. In the actual application scenario, if in response to the triggering of the "keep collection" control in the middle, as shown in Figure 6 Figure 7 "has been added to my collection" is displayed, indicating that the target recommendation collection is added to the "my collection". The electronic device can also obtain the question related to the target recommendation collection input by the user from the dialog box, and in response to the triggering of the "chat" control by the user, the answer corresponding to the question in the dialog box is displayed. If in response to the triggering of the "not interested" control, as shown in Figure 8 "no longer recommend this collection" is displayed.

[0168] In this embodiment, by displaying a plurality of recommendation collections and collection editing controls, and in response to the triggering operation of the collection editing control, the recommendation collection is added or deleted, the recommendation collection can be flexibly and conveniently deleted or added, the editing efficiency of the displayed recommendation collection is improved, and the collection recommendation experience of the device is improved.

[0169] ​In some embodiments, the above method further includes:

[0170] In response to viewing the target recommendation collection, display the collection page of the target recommendation collection; in response to triggering an operation on the target control of the target page of the target recommendation collection, display candidate function controls; in response to triggering an operation on the target function control, execute the function corresponding to the target function control.

[0171] The target recommendation set is any set of recommendations. The target control is used to trigger the display of candidate function controls. The target function control is one of the candidate function controls. Each candidate function control corresponds to a set processing function. For example, functions such as adding record data, batch management of record data in the target recommendation set, modifying the set name, adjusting set rules, or deleting the set.

[0172] In one example, such as Figure 9 As shown, the viewing operation includes a click operation. In response to a click operation on the target recommendation collection, the collection page 902 of the target recommendation collection is displayed. In response to a click operation on the target control 904 of the target page of the target recommendation collection, the candidate function control 906 is displayed. In response to a click operation on the target function control 908, the function corresponding to the target function control is executed.

[0173] In this embodiment, in response to the viewing operation of the target recommendation collection, the collection page of the target recommendation collection is displayed; in response to the triggering operation of the target control on the target page of the target recommendation collection, candidate function controls are displayed; and in response to the triggering operation of the target function control, the function corresponding to the target function control is executed. This facilitates the processing of the data recorded in the target recommendation collection and improves the data collection recommendation experience.

[0174] In some embodiments, the above method further includes:

[0175] The target application's interface is displayed, which includes a Q&A assistant entry point. The target application is used to record data based on preset records. In response to a trigger operation on the Q&A assistant entry point, the Q&A assistant interface is displayed. In response to Q&A information entered in the Q&A assistant interface, the Q&A results corresponding to the Q&A information are displayed.

[0176] The target application refers to the application that records data and displays the aforementioned recommended collection. The target application can record data based on preset recording operations. These preset recording operations include, for example, taking a screenshot, liking, sharing, saving, or searching. Preset recording operations may also include triggering a voice conversation or fulfilling other preset recording conditions.

[0177] Exemplarily, the electronic device displays the question and answer assistant interface in response to a trigger operation such as a long press operation, a click operation, or a preset voice input on the question and answer assistant portal, and displays the question and answer result corresponding to the question and answer information input in the question and answer assistant interface. Alternatively, the electronic device can search the Internet for the question and answer result corresponding to the question and answer information input in the question and answer assistant interface, and display the question and answer result. The question and answer assistant interface can invoke an artificial intelligence question and answer assistant, and the artificial intelligence question and answer assistant can determine the question and answer result corresponding to the question and answer information. It can be easily understood that the artificial intelligence question and answer assistant can be implemented by an artificial intelligence question and answer model or a question and answer algorithm.

[0178] In this embodiment, the question and answer assistant interface is displayed in response to a trigger operation on the question and answer assistant portal displayed on the display interface of the target application, and the question and answer result corresponding to the question and answer information input in the question and answer assistant interface is displayed, so that the question and answer can be conveniently implemented, the question and answer result corresponding to the question and answer information can be obtained, and the device use experience is improved.

[0179] In one example, a flowchart of a data collection recommendation method is shown in Figure 10 The following steps 1002 to 1012 are included.

[0180] Step 1002, triggering the data collection recommendation process, and obtaining all A2 tags of the record data in the queue.

[0181] The data collection recommendation process can be implemented when the target application is running. The target application is an application that loads the data collection recommendation method in the above embodiments. The queue is equivalent to a candidate data list, and the data in the queue is equivalent to candidate data. All A2 tags of the data in the queue are equivalent to all candidate tags of the candidate data. That is, all candidate tags of the candidate data in the candidate data list are obtained. The candidate data list is, for example, data generated in a period of a preset time length. The candidate data can be obtained by screening from the local data list. In actual application scenarios, the recommendation can be triggered when the number of candidate data in the candidate data list reaches 5 (target number), and the recommendation is not triggered when the number is less than 5. It can be easily understood that the corresponding tags can also be generated when the record data is generated.

[0182] Step 1004, searching local data, and counting the number of data matched with each A2 tag.

[0183] The local data is equivalent to the record data in the local data list. That is, the data in the local data list is matched with the candidate tags to obtain the number of record data matched with each candidate tag.

[0184] Step 1006, screening out A2 labels with a number of matched record data greater than 3.

[0185] In this example, the number threshold is 3, that is, the target label with a number of matched record data greater than 3 is screened out from the candidate label.

[0186] Step 1008, filtering the record data in the local data list according to the screened A2 label.

[0187] Among them, the screened A2 label is the target label. That is, the target data matched with the target label is screened out from the local data list. In the screening process, the number of target data matched with each target label does not exceed the first threshold, and the number of target data matched with all target labels does not exceed the second threshold. In this example, the first threshold is 100 and the second threshold is 1000. If the number of target data matched with a certain target label exceeds the first threshold, the first threshold of target data can be selected from the matched target data according to the data generation time from near to far as the final screened target data.

[0188] Step 1010, requesting the server to summarize the collection.

[0189] The electronic device can send a data aggregation request to the cloud or server to realize the aggregation (summary) of the screened target data to the corresponding recommended collection.

[0190] Step 1012, storing the return result and putting it into the recommended collection queue.

[0191] Among them, the return result can be the aggregation information of the target data returned by the server or the cloud, that is, the association information between each target data and the corresponding recommended collection. Or, the return result can be the recommended collection returned by the server or the cloud after aggregating the target data. If there is no historical recommended collection matched with the target data, a new recommended collection is created according to the target data, and a new recommended collection name is generated according to the collection creation algorithm. That is, the recommended collection includes historical recommended collection and new recommended collection.

[0192] After receiving the return result, the electronic device can put the return result into the recommended collection queue, and then display each recommended collection in turn according to the preset order. For example, the recommended collection is cycled, played N times a day, and at most a preset number of recommended collections are displayed each day, for example, at most 10 recommended collections are displayed each day. Among them, N is a positive integer, which can be set according to the actual application scene. The user can perform editing operations such as deleting and updating on the displayed recommended collection.

[0193] In the above embodiments, by matching the record data in the local data list with the candidate tags of the candidate data in the queue, the candidate tags with the number of record data matched with the candidate tags greater than the number threshold are taken as the target tags, the target tags matching the real demand corresponding to the user historical record data are quickly determined, the corresponding data is filtered based on the target tags, the recommended collection after aggregation is recommended, the automatic recommendation of the data collection for the user is implemented, and the accuracy of the recommendation is improved, thereby greatly improving the data collection recommendation experience of the device.

[0194] It should be understood that, although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0195] Based on the same inventive concept, the embodiments of the present application also provide a data collection recommendation device for implementing the above-mentioned data collection recommendation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more data collection recommendation device embodiments provided below can refer to the limitations of the data collection recommendation method in the above text, which will not be repeated here.

[0196] In some exemplary embodiments, as shown in Figure 11 A data collection recommendation device 1100 is provided, including a tag acquisition module 1102, a data aggregation module 1104, and a collection display module 1106, wherein:

[0197] The tag acquisition module 1102 is configured to acquire a target tag.

[0198] The data aggregation module 1104 is configured to aggregate target data matched with the target tag into a corresponding recommended collection; the target data is recorded from at least two application programs; and the target data is obtained based on a preset recording operation.

[0199] The collection display module 1106 is configured to display the recommended collection.

[0200] In some embodiments, the label obtaining module 1102 is further configured to obtain the target label according to the number of record data in the local data list matched by the candidate label of the candidate data in the candidate data list.

[0201] In some embodiments, the label obtaining module 1102 is further configured to obtain the candidate label of the candidate data in the candidate data list; match the record data in the local data list with the candidate label, and obtain the number of record data matched with each candidate label; and determine the target label from the candidate label, where the number of record data matched is greater than the number threshold.

[0202] In some embodiments, the apparatus further comprises a data quantity monitoring module configured to, before obtaining the candidate label of the candidate data in the candidate data list, identify the number of candidate data in the candidate data list; and in the case that the number of candidate data reaches the target number, perform the obtaining of the candidate label of the candidate data in the candidate data list.

[0203] In some embodiments, the apparatus further comprises a data removing module configured to, after obtaining the candidate label of the candidate data in the candidate data list, remove the candidate data whose candidate label has been obtained from the candidate data list.

[0204] In some embodiments, the data aggregation module 1104 is further configured to determine the target data matched with the target label from the local data list; perform deduplication processing on the target data matched with the target label to obtain deduplicated target data; and aggregate the deduplicated target data to the corresponding recommendation set.

[0205] In some embodiments, the data aggregation module 1104 is further configured to match each target data matched with the target label in the local data list with the historical recommendation set; if there is a historical recommendation set that matches the target data successfully, aggregate the target data to the matched historical recommendation set; if the target data does not match all historical recommendation sets successfully, create a new recommendation set according to the target data; and the new recommendation set includes the target data.

[0206] In some embodiments, the data aggregation module 1104 is further configured to, if there is a historical recommendation set that matches the target data successfully, calculate the similarity between the target data and each record data in the matched historical recommendation set; if the similarity between each record data in the matched historical recommendation set and the target data is less than or equal to the similarity threshold, aggregate the target data to the matched historical recommendation set.

[0207] If there is record data in the matched historical recommendation set that has a similarity greater than the similarity threshold with the target data, the target data is not aggregated to the matched historical recommendation set.

[0208] In some embodiments, the tag obtaining module 1102 is further configured to obtain user operation content, and obtain the target tag according to the user operation content.

[0209] In some embodiments, the tag obtaining module 1102 is further configured to perform semantic recognition on the user operation content to obtain a semantic recognition result, determine a content keyword according to the semantic recognition result, and determine the content keyword as the target tag.

[0210] In some embodiments, the collection display module 1106 is further configured to display the recommended collections in a preset order in turn.

[0211] In some embodiments, the apparatus further includes a collection editing module configured to display a plurality of recommended collections and a collection editing control, and in response to a triggering operation on the collection editing control, add or delete a recommended collection.

[0212] In some embodiments, the apparatus further includes a collection processing module configured to, in response to a viewing operation on a target recommended collection, display a collection page of the target recommended collection, in response to a triggering operation on a target control of a target page of the target recommended collection, display a candidate function control, and in response to a triggering operation on the target function control, execute a function corresponding to the target function control.

[0213] In some embodiments, the apparatus further includes a question and answer display module configured to display a display interface of a target application program, display a question and answer assistant portal in the display interface, and in response to a triggering operation on the question and answer assistant portal, display a question and answer assistant interface, in response to question and answer information input in the question and answer assistant interface, display a question and answer result corresponding to the question and answer information.

[0214] The various modules in the data collection recommendation apparatus can be implemented in whole or in part by software, hardware, and combinations thereof. The various modules can be embedded in or independent of a processor in an electronic device in hardware form, or stored in a memory in the electronic device in software form, so as to be called and executed by a processor to perform operations corresponding to the various modules.

[0215] In some example embodiments, an electronic device is provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the data collection recommendation method in the above embodiments when executing the computer program.

[0216] In some embodiments, a computer readable storage medium is provided, storing a computer program, and the computer program implements the steps of the data collection recommendation method in the above embodiments when executed by a processor.

[0217] In some embodiments, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the data aggregation recommendation method of the above embodiments.

[0218] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0219] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0220] The technical features of the above embodiments can be combined in any manner. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict each other, they should be considered to be within the scope of the present application.

[0221] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A data aggregation recommendation method, characterized by, The method comprises: acquiring a target label; aggregating target data matching the target label into a corresponding recommendation set; the target data is recorded from at least two application programs; the target data is obtained based on a preset recording operation; displaying the recommendation set.

2. The method of claim 1, wherein, The acquiring of the target label comprises: acquiring the target label according to the number of recorded data in the local data list matching the candidate label of the candidate data in the candidate data list.

3. The method of claim 2, wherein, The acquiring of the target label according to the number of recorded data in the local data list matching the candidate label of the candidate data in the candidate data list comprises: acquiring the candidate label of the candidate data in the candidate data list; matching the recorded data in the local data list with the candidate label and acquiring the number of recorded data matching each candidate label; determining the target label from the candidate label whose number of matching recorded data is greater than a number threshold.

4. The method of claim 3, wherein, Before the acquiring of the candidate label of the candidate data in the candidate data list, the method further comprises: identifying the number of candidate data in the candidate data list; in the case that the number of candidate data reaches a target number, performing the step of acquiring the candidate label of the candidate data in the candidate data list.

5. The method of claim 3, wherein, After the acquiring of the candidate label of the candidate data in the candidate data list, the method further comprises: removing the candidate data whose candidate label has been acquired from the candidate data list.

6. The method of claim 1, wherein, The aggregating of the target data matching the target label into a corresponding recommendation set comprises: determining the target data matching the target label from the local data list; performing deduplication processing on the target data matching the target label to obtain deduplicated target data; aggregating the deduplicated target data into a corresponding recommendation set.

7. The method of claim 1, wherein, The aggregating of the target data matching the target label into a corresponding recommendation set comprises: matching each target data in the local data list matching the target label with a historical recommendation set; if there is a historical recommendation set matching the target data successfully, aggregating the target data into the matching historical recommendation set; if the target data does not match all historical recommendation sets successfully, creating a new recommendation set according to the target data; the new recommendation set comprises the target data.

8. The method of claim 7, wherein, The aggregating of the target data into the matching historical recommendation set if there is a historical recommendation set matching the target data successfully comprises: if there is a historical recommendation set matching the target data successfully, calculating the similarity between the target data and each recorded data in the matching historical recommendation set; if the similarity between each recorded data in the matching historical recommendation set and the target data is less than or equal to a similarity threshold, aggregating the target data into the matching historical recommendation set; if there is recorded data in the matching historical recommendation set whose similarity with the target data is greater than the similarity threshold, not aggregating the target data into the matching historical recommendation set.

9. The method of claim 1, wherein, The acquiring of the target label comprises: Obtaining user operation content, and obtaining a target label according to the user operation content.

10. The method of claim 9, wherein, The obtaining of the target label according to the user operation content comprises: performing semantic recognition on the user operation content to obtain a semantic recognition result; determining a content keyword according to the semantic recognition result, and determining the content keyword as the target label.

11. The method according to any one of claims 1 to 10, characterized in that, The displaying of the recommended collection comprises: displaying the recommended collection in turn according to a preset order.

12. The method according to any one of claims 1 to 10, characterized in that, The displaying of the recommended collection comprises: stacked display of the recommended collection.

13. The method of claim 1, wherein, The method further comprises: displaying a plurality of recommended collections and a collection editing control; in response to a triggering operation on the collection editing control, adding or deleting the recommended collection.

14. The method of claim 1, wherein, The method further comprises: in response to a viewing operation on a target recommended collection, displaying a collection page of the target recommended collection; in response to a triggering operation on a target control of a target page of the target recommended collection, displaying a candidate function control; in response to a triggering operation on a target function control, executing a function corresponding to the target function control.

15. The method of claim 1, wherein, The method further comprises: displaying a display interface of a target application program, and displaying a question and answer assistant portal in the display interface; the target application program is used to record data based on a preset recording operation; in response to a triggering operation on the question and answer assistant portal, displaying a question and answer assistant interface; in response to question and answer information input in the question and answer assistant interface, displaying a question and answer result corresponding to the question and answer information.

16. A data aggregation recommendation apparatus, comprising: The device comprises: a label obtaining module configured to obtain a target label; a data aggregation module configured to aggregate target data matching the target label to a corresponding recommended collection; the target data is recorded from at least two application programs; the target data is obtained based on a preset recording operation; a collection display module configured to display the recommended collection.

17. An electronic device, comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 15.

18. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 15.

19. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 15. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 15.

Images