Adjustment method and device based on user behavior, equipment and storage medium

Abstract

The invention relates to an adjustment method and device based on user behaviors, equipment and a storage medium. The user behavior-based adjustment method comprises the steps of obtaining user behavior data sent by a target terminal; user behavior characteristics are extracted from the user behavior data through a pre-trained neural network model, configuration information conforming to user behavior habits is generated according to the user behavior characteristics, and the configuration information is related configuration information about operation interface layout and / or content recommendation logic of the target terminal; and generating a configuration packet executable by the target terminal according to the configuration information, and issuing the configuration packet to the target terminal, so that the target terminal performs adjustment conforming to the behavior habits of the user. According to the method provided by the invention, the response speed is effectively improved, so that a real-time recommendation result is provided for the user, and the fluency and satisfaction of user experience are further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular, to a user behavior-based adjustment method and device, equipment and storage medium. BACKGROUND

[0002] In the field of personalized recommendation, recommendation systems have been widely used in e-commerce, social media, online video and news information scenarios, etc. By analyzing user historical behavior data, the recommendation system can filter goods, content or services for users, and improve information acquisition efficiency and platform conversion rate. However, the related recommendation system still has some deficiencies, which makes it difficult to accurately capture the dynamic interest changes of users, resulting in a significant deviation between recommended content and user real needs, and failing to achieve deep personalized services. At the same time, the response speed of the recommendation system is slow in high concurrency scenarios, which cannot provide real-time recommendation results in time, and seriously weakens the fluency and satisfaction of user experience. SUMMARY

[0003] To solve the above technical problems, the present application provides a user behavior-based adjustment method, device, equipment and storage medium.

[0004] In a first aspect, the present application provides a user behavior-based adjustment method, comprising: obtaining user behavior data sent by a target terminal; extracting user behavior features from the user behavior data through a pre-trained neural network model, and generating configuration information conforming to user behavior habits according to the user behavior features, wherein the configuration information is related configuration information about the operation interface layout and / or content recommendation logic of the target terminal; generating a configuration package executable by the target terminal according to the configuration information, and downlinking the configuration package to the target terminal, so that the target terminal is adjusted to conform to the user behavior habits.

[0005] Optionally, extracting the user behavior features from the user behavior data and generating the configuration information conforming to the user behavior habits comprises: performing time series clustering analysis on the user behavior data to obtain user behavior features, wherein the user behavior features are used to represent related features of high-frequency user behaviors; performing semantic understanding on the user behavior features to analyze user operation intentions; generating configuration information conforming to user behavior habits according to the user operation intentions.

[0006] Optionally, the configuration information includes a behavior mode and / or a recommendation weight of at least one recommended content, and generating a configuration package executable by the target terminal according to the configuration information comprises: mapping the behavior mode to an interface component library to generate interface rendering instructions; synchronize the content recommendation algorithm parameters according to the recommendation weights of the at least one recommended content; generate a configuration package executable by the target terminal according to the interface rendering instruction and / or the synchronized content recommendation algorithm, wherein a file size of the configuration package is less than a set threshold.

[0007] Optionally, the user behavior data includes an operation event and operation data corresponding to the operation event, and after the user behavior data sent by the target terminal is acquired, the method further includes: packaging the user behavior data into a structured event to obtain at least one behavior event data, wherein the structured event includes an event type, an operation object, an operation trajectory, and / or an operation time sequence; converting the at least one behavior event data into a language description text or a prompt word as an input of the neural network model.

[0008] Optionally, converting the at least one behavior event data into a language description text or a prompt word includes: performing denoising processing on the at least one behavior event data; classifying the at least one behavior event data into an interface operation class or a content interaction class; converting the at least one behavior event data into a language description text or a prompt word according to a classification result.

[0009] Optionally, the target terminal is configured to, after receiving the configuration package, update an operation interface layout and / or a content recommendation algorithm to display an updated operation interface and / or recommended content at a target time, wherein the target time is determined according to the user behavior data.

[0010] Optionally, after the user behavior data sent by the target terminal is acquired, the method further includes: storing the user behavior data into a multi-modal behavior database after the user behavior data is parsed according to a set modality, wherein the multi-modal behavior database is configured to provide configuration information output by the neural network model.

[0011] In a second aspect, the embodiments of the present disclosure provide an adjustment device based on user behavior, including: a data acquisition unit configured to acquire user behavior data sent by a target terminal; a configuration generation unit configured to extract user behavior features from the user behavior data by using a pre-trained neural network model, and generate configuration information conforming to user behavior habits according to the user behavior features, wherein the configuration information is related configuration information about an operation interface layout and / or content recommendation logic of the target terminal; The configuration issuing unit is configured to generate a configuration package executable by the target terminal according to the configuration information, and issue the configuration package to the target terminal, so that the target terminal performs adjustment in line with the user behavior habit.

[0012] In a third aspect, the embodiments of the present disclosure provide an electronic device, comprising: a memory; a processor; and a computer program; The computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.

[0013] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method of the first aspect.

[0014] The present disclosure provides a user behavior-based adjustment method, which acquires user behavior data sent by a target terminal, extracts user behavior features from the user behavior data through a pre-trained neural network model, and generates configuration information in line with a user behavior habit according to the user behavior features, wherein the configuration information is related configuration information about an operation interface layout and / or content recommendation logic of the target terminal; a configuration package executable by the target terminal is generated according to the configuration information, and the configuration package is issued to the target terminal, so that the target terminal performs adjustment in line with the user behavior habit. The method provided in the present application can accurately capture user behavior habits by analyzing behavior data, generate personalized configuration strategies in line with user behavior habits, and generate executable configuration packages based on the personalized configuration strategies, effectively improving the response speed to provide real-time recommendation results for users and further improving the smoothness and satisfaction of user experience. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0017] Figure 1 A flowchart of the user behavior-based adjustment method provided by the embodiments of the present disclosure; Figure 2 A timing flowchart of the user behavior-based adjustment method provided by the embodiments of the present disclosure; Figure 3 A structural schematic diagram of a user behavior-based adjustment system provided by an embodiment of the present disclosure is shown in FIG. 1. Figure 4 A structural schematic diagram of a user behavior-based adjustment apparatus provided by an embodiment of the present disclosure is shown in FIG. 2. Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown in FIG. 3. DETAILED DESCRIPTION

[0018] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the schemes of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0019] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some of the embodiments of the present disclosure, not all the embodiments.

[0020] Specifically, in the current mobile application scenario, the recommendation system generally has the problems of low personalization degree and response lag. For example, the e-commerce software only recommends similar goods according to the user's historical purchase records, and cannot identify the cross-domain demand of "frequently searching for job books after browsing baby products"; the information software mostly relies on manual subscription of interest tags, and when the user shifts from technology news to financial content, the recommendation system needs several days to adjust the recommendation strategy, which has the problem of response lag; the function layout of the tool software is fixed, and it cannot automatically adapt to the personalized demand of "left-handed users habit of single-handed operation of the lower right corner function area". In summary, the related recommendation method lacks in-depth analysis of the user's implicit operation habits (such as operation frequency, interface stay time, gesture path), and does not have the ability to dynamically reconstruct the recommendation system in real time.

[0021] In view of the above technical problems, the embodiments of the present disclosure provide a user behavior-based adjustment method. One or more embodiments are described in detail as follows.

[0022] The method based on user behavior provided by the embodiments of the present disclosure can be applied to the scenario of adjusting based on user behavior. The method can be executed by an adjusting device based on user behavior. The device can be implemented by software and / or hardware, and the device can be integrated in an electronic device. The electronic device can include, but is not limited to, a mobile terminal such as a smart phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet personal computer (Tablet PC), a PMP (portable multimedia player), a vehicle terminal (for example, a vehicle navigation terminal), a wearable device, and the like, and a fixed terminal such as a digital television, a desktop computer, a smart home device, and the like.

[0023] Figure 1 The flowchart of the method based on user behavior provided by the embodiments of the present disclosure specifically includes the following steps as shown in Figure 1 S101, obtaining user behavior data sent by a target terminal.

[0024] It can be understood that the user behavior data refers to the behavior data of the target user acting on the target terminal, specifically, the operation behavior of the target terminal collected when the target user uses the target terminal, which is used for subsequent analysis and personalized service. For example, the user behavior includes at least one of page browsing, clicking, searching, playing, liking, collecting, adding to shopping cart, ordering, staying time, sliding track, and the like. In addition, the target terminal can record the operation events in real time in a user-unaware state, for example, the clicking position, the sliding track, the function switching sequence, and the like.

[0025] The user behavior data includes operation events and operation data corresponding to the operation events.

[0026] It can be understood that the operation event refers to the specific behavior type performed by the user, for example, a user touch event. The operation data refers to the sensor data collected before and after the operation event occurs, for example, the object clicked, the product name browsed, the keyword searched, the timestamp of the operation, the staying time, the page path, and the like, which are used to describe the context and details of the event. In an example, the user behavior data is "the user continuously browses red wine products by sliding at 19:00 for 3 consecutive days", wherein "3 consecutive days", "19:00", "sliding", "browsing", and "red wine products" are all user behavior data (i.e., adjusting recommended content) collected.

[0027] Optionally, after obtaining the user behavior data sent by the target terminal, the method further includes: ​User behavior data is encapsulated into structured events to obtain at least one behavior event data, wherein the structured event includes event type, operation object, operation trajectory and / or operation sequence; at least one behavior event data is converted into language description text or prompt words as input to the neural network model.

[0028] Understandably, after collecting user behavior data, this data is encapsulated into structured events, resulting in at least one behavioral event data point, which can be understood as a behavioral event stream. Each structured event includes at least one of the following: event type, operation object, operation trajectory, and operation sequence. The ordering of different data points is not limited. In the example above, the structured event is {Event Type: Gesture swipe, Coordinates: [x1,y1→x2,y2], Duration: 1200ms, Operation Object: Wine products}, where the coordinates represent the operation trajectory, and the duration is one type of data in the operation sequence. Understandably, different behavioral event data points correspond to different event types or specific events. For example, one behavioral event data point might be "The user adjusts the background to dark mode between 20:00 and 22:00 (i.e., adjusts application functions)," while another might be "The user places the back button in the lower right corner (i.e., adjusts the interface layout)." Subsequently, at least one behavioral event data is converted into language description text or prompt words that the neural network model can understand, serving as the context or input of the neural network model. For example, the language description text converted in the above example is "The user swipes on a wine product for 1200ms". The swiping duration is relatively long, indicating that the user may be interested in the wine product.

[0029] Optionally, at least one behavioral event data point can be converted into a descriptive text or prompt word, which can be achieved through the following steps: Denoising is applied to at least one behavioral event data point; the denoised behavioral event data point is then categorized into interface operation type or content interaction type; based on the classification results, the at least one behavioral event data point is converted into language description text or prompt words.

[0030] Understandably, before using behavioral event data as input to the neural network model, at least one behavioral event data point is denoised to filter out accidental touch events. Subsequently, the denoised behavioral event data is classified into either interface operation or content interaction categories, resulting in a standardized behavioral dataset or a standardized dataset. Later, during the conversion of the at least one behavioral event data point into descriptive text or prompts, the classification results are considered to improve the processing efficiency of the neural network model.

[0031] Optionally, after obtaining the user behavior data sent by the target terminal, the method further includes: User behavior data is parsed according to a set modality and then stored in a multimodal behavior database, which is used to provide configuration information for the neural network model to output.

[0032] Understandably, after preprocessing user behavior data (e.g., structuring, denoising, and classifying), the data is parsed according to defined modalities (e.g., operational behaviors, interface interactions). This means classifying different information within the behavioral data by dimension. For example, "clicks" and "browsing duration" are categorized as operational behaviors, while "screen coordinates" and "gesture paths" are categorized as interaction modalities. After parsing, the multimodal data is stored in a multimodal behavior database, forming a comprehensive record of user behavior. This database serves as the contextual input source for neural network models, analyzing user habits and intentions, and generating corresponding configuration information. For example, the neural network model can output instructions such as "adjust interface button size" or "enable one-handed mode" to adapt to user operating habits and achieve a personalized experience.

[0033] S102. Extract user behavior features from user behavior data using a pre-trained neural network model, and generate configuration information that conforms to user behavior habits based on the user behavior features.

[0034] The configuration information includes configuration details related to the target terminal's user interface layout and / or content recommendation logic.

[0035] Understandably, based on the above S101, user behavior data or preprocessed user behavior data is used as input to a pre-trained neural network model (e.g., an LSTM (Long Short-Term Memory Network) model). The neural network model extracts user behavior features from the input data and generates configuration information that conforms to user behavior habits based on these features. This configuration information can also be understood as a habit analysis report or a personalized configuration strategy. The configuration information can be at least one configuration related to the target terminal's user interface layout, application functions, and content recommendation logic. For example, the configuration information could be: {Dark Mode Time Period: 20:00-22:00, Recommendation Weight: Finance > Technology}, where dark mode is used to adjust application functions, and recommendation weight is used to adjust recommended content, i.e., emphasizing financial content and reducing technology content compared to financial content.

[0036] Optionally, user behavior features can be extracted from user behavior data, and configuration information that conforms to user behavior habits can be generated based on these features. This can be achieved through the following steps: Temporal clustering analysis is performed on user behavior data to obtain user behavior features, which are used to characterize the relevant features of high-frequency user behaviors. Semantic understanding is performed on user behavior features to parse user operation intentions. Configuration information that conforms to user behavior habits is generated based on user operation intentions.

[0037] Understandingly, a neural network model can be viewed as a time-series analysis model. It identifies behavioral patterns (e.g., frequent use of dark mode between 8:00 PM and 9:00 PM) and combines this with semantic understanding to interpret the user's intent (e.g., long-pressing an icon indicates a custom shortcut). Specifically, time-series clustering analysis is performed on user behavior data to obtain user behavior features, such as analyzing high-frequency behavior sequences. Then, semantic understanding is applied to these user behavior features, for example, by combining context and a knowledge base to accurately understand the true intent behind ambiguous or omitted expressions, thus parsing the user's operational intent. For instance, NLP (Natural Language Processing) can be used for operational intent recognition; other possible parsing methods are not elaborated upon. Finally, configuration information that conforms to user behavior habits is generated based on the user's operational intent. This configuration information can also be understood as a user habit map or habit analysis results.

[0038] S103. Generate an executable configuration package for the target terminal based on the configuration information, and send the configuration package to the target terminal so that the target terminal can make adjustments that conform to user behavior habits.

[0039] Understandably, based on the above S102, an executable configuration package for the client (target terminal) is generated according to the configuration information; the specific generation method will not be elaborated here. Subsequently, the configuration package is sent to the target terminal, which runs the configuration package to perform real-time dynamic reconstruction (e.g., taking effect within 200ms) to quickly complete personalized adjustments.

[0040] Optionally, the configuration information includes behavioral patterns and / or recommendation weights for at least one recommended content. Based on this configuration information, an executable configuration package for the target terminal is generated, which can be achieved through the following steps: The behavior pattern is mapped to the interface component library to generate interface rendering instructions; the content recommendation algorithm parameters are synchronized according to the recommendation weight of at least one recommended content; and an executable configuration package for the target terminal is generated according to the interface rendering instructions and / or the synchronized content recommendation algorithm, wherein the file size of the configuration package is less than a set threshold.

[0041] Understandably, configuration information includes behavioral patterns (e.g., setting the background color to dark mode or placing the back button in the bottom right corner) and the weight of at least one recommended content (e.g., financial content has a higher weight than technology content). In this case, the behavioral patterns are mapped to the UI component library, and UI rendering instructions are generated. Based on the recommendation weights of each recommended content item, the content recommendation algorithm parameters are synchronized. Subsequently, based on the UI rendering instructions and / or the synchronized content recommendation algorithm, a configuration package is generated. The configuration package file size is less than a set threshold, for example, a threshold of 10KB, making the configuration package lightweight and further improving refactoring speed.

[0042] Optionally, the target terminal is used to update the user interface layout and / or content recommendation algorithm after receiving the configuration package, so as to display the updated user interface and / or recommended content at a target time, wherein the target time is determined based on user behavior data.

[0043] Understandably, after receiving the configuration package, the target terminal adjusts the layout of interface components (e.g., moves frequently used functions to the thumb hotspot) and / or optimizes the recommendation algorithm (e.g., filters certain types of content).

[0044] In one application example, taking an e-commerce app, if a user browses wine products at 7 PM for three consecutive days, a neural network model identifies this "after-get off work wine browsing" behavior pattern. Based on this pattern, the e-commerce app is configured to prioritize wine recommendations and automatically open a dedicated wine section for users at 7 PM. Subsequently, users entering the e-commerce app will directly see wine promotional pop-ups, effectively increasing click-through rates.

[0045] This disclosure provides a user behavior-based adjustment method that constructs a dynamic behavior profile by real-time collection and analysis of user operation events and their associated data. This enables accurate identification of users' implicit needs and operational intentions, effectively improving personalized response speed and overcoming the latency bottleneck of related recommendation methods that rely on more than 24 hours of data accumulation. Secondly, by predicting high-frequency user behavior sequences and analyzing user operational intentions, the interaction process is optimized, effectively reducing user operation steps. Simultaneously, personalized configuration strategies and client-side executable configuration packages are generated, effectively improving recommendation conversion rates. This application solves the problems of low personalization and slow response in existing systems, significantly improving user experience and service efficiency, and is applicable to various mobile applications and smart terminal scenarios.

[0046] Based on the above embodiments, Figure 2 The timing flowchart of the user behavior-based adjustment method provided in this embodiment of the disclosure specifically includes the following steps: 1) The client (target terminal) uploads an encrypted behavior stream to the server. The behavior stream includes data such as coordinates, time sequence, and event type. 2) The server includes an analysis engine and a configuration center. The analysis engine extracts behavioral features using an LSTM model and pushes the generated habit analysis report to the configuration center. 3) The configuration center generates interface rendering instructions based on the habit analysis report and synchronizes the algorithm parameters of the recommendation algorithm, and sends a lightweight configuration package to the client. 4) The client runs the configuration package and dynamically reconstructs the interface and recommendation logic.

[0047] Understandably, the specific descriptions of 1) to 4) above are provided in the above embodiments and will not be repeated here.

[0048] Based on the above embodiments, Figure 3 This is a schematic diagram of the structure of a user behavior-based adjustment system provided in an embodiment of this disclosure. The adjustment system includes a client behavior acquisition module, a real-time data pipeline, a multimodal behavior database, a large model analysis engine, a dynamic capability configuration center, and a client rendering engine. The client-side behavior acquisition module is used to acquire behavior data, encapsulate the behavior data into structured events, and output a behavior event stream.

[0049] Real-time data pipelines are used to denoise and classify behavioral event streams to obtain standardized datasets.

[0050] Multimodal behavioral databases are used to store behavioral data, behavioral event streams, and standardized datasets.

[0051] The large model analysis engine is used to perform time-series clustering analysis on standardized datasets, parse operational intent, and generate user habit maps to obtain personalized configuration strategies. The dynamic capability configuration center is used to map personalized configuration strategies to the UI component library, generate interface rendering instructions and synchronize recommendation algorithm parameters, and generate client-executable configuration packages.

[0052] The client-side rendering engine is used to run configuration packages, hot-reload UI component layouts and recommendation algorithms, and create personalized interfaces for Shanghai.

[0053] Figure 4 This is a schematic diagram of the structure of the user behavior-based adjustment device provided in this embodiment of the disclosure. The user behavior-based adjustment device provided in this embodiment of the disclosure can execute the processing flow provided in the user behavior-based adjustment method embodiment, such as... Figure 4 As shown, the user behavior-based adjustment device 400 includes: Data acquisition unit 410 is used to acquire user behavior data sent by the target terminal; The configuration generation unit 420 is used to extract user behavior features from user behavior data through a pre-trained neural network model, and generate configuration information that conforms to user behavior habits based on the user behavior features. The configuration information is related to the layout of the target terminal's operating interface and / or content recommendation logic. The configuration distribution unit 430 is used to generate an executable configuration package for the target terminal based on the configuration information, and distribute the configuration package to the target terminal so that the target terminal can make adjustments that conform to the user's behavior habits.

[0054] Optionally, the configuration generation unit 420 is used for: Time-series clustering analysis is performed on user behavior data to obtain user behavior features, which are used to characterize the relevant features of high-frequency user behaviors. Perform semantic understanding of user behavior characteristics to parse user operation intentions; Generate configuration information that aligns with user behavior based on user intent.

[0055] Optionally, the configuration information includes behavioral patterns and / or the recommendation weight of at least one recommended content.

[0056] Optionally, the configuration distribution unit 430 is used for: Map behavior patterns to UI component libraries to generate UI rendering instructions; Synchronize the content recommendation algorithm parameters based on the recommendation weight of at least one recommended item; Based on the interface rendering instructions and / or the synchronized content recommendation algorithm, generate a configuration package executable for the target terminal, wherein the file size of the configuration package is less than a set threshold.

[0057] Optionally, the user behavior-based adjustment device 400 is also used for: User behavior data is encapsulated into structured events to obtain at least one behavior event data, wherein the structured event includes event type, operation object, operation trajectory and / or operation sequence; At least one behavioral event data point is converted into a language description text or prompt word, which is then used as input to a neural network model.

[0058] Optionally, the user behavior-based adjustment device 400 is also used for: Denoise the data for at least one behavioral event; The noise-reduced data of at least one behavioral event is divided into either interface operation type or content interaction type. Based on the classification results, at least one behavioral event data point is converted into a descriptive text or prompt word.

[0059] Optionally, the target terminal is used to update the user interface layout and / or content recommendation algorithm after receiving the configuration package, so as to display the updated user interface and / or recommended content at a target time, wherein the target time is determined based on user behavior data.

[0060] Optionally, the user behavior-based adjustment device 400 is also used for: User behavior data is parsed according to a set modality and then stored in a multimodal behavior database, which is used to provide configuration information for the neural network model to output.

[0061] Figure 4 The user behavior-based adjustment device shown in the embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0062] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. See below for details. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device 500 in the embodiments of this disclosure. The electronic device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), wearable electronic devices, etc., as well as fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0063] like Figure 5 As shown, the electronic device 500 may include a processing unit 501 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503 to implement the user behavior-based adjustment method as described in the embodiments of this disclosure. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0064] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0065] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts, thereby implementing the user behavior-based adjustment method as described above. In such embodiments, the computer program can be downloaded and installed from a network via communication device 509, or installed from storage device 508, or installed from ROM 502. When the computer program is executed by processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0066] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0067] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0068] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0069] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.

[0070] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0072] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0073] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0074] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0075] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or gateway that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or gateway. Without further limitations, an element defined by the phrase "comprising a user behavior-based adjustment" does not exclude the presence of other identical elements in the process, method, article, or gateway that includes said element.

[0076] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A user behavior-based adjustment method, characterized in that, include: Acquire user behavior data sent by the target terminal; User behavior features are extracted from the user behavior data using a pre-trained neural network model, and configuration information that conforms to user behavior habits is generated based on the user behavior features. The configuration information is related to the operation interface layout and / or content recommendation logic of the target terminal. An executable configuration package for the target terminal is generated based on the configuration information, and the configuration package is sent to the target terminal so that the target terminal can make adjustments that conform to user behavior habits.

2. The method according to claim 1, characterized in that, The step of extracting user behavior features from the user behavior data and generating configuration information that conforms to user behavior habits based on the user behavior features includes: The user behavior data is subjected to time-series clustering analysis to obtain user behavior features, wherein the user behavior features are used to characterize the relevant features of high-frequency user behaviors; Perform semantic understanding on the user behavior features to parse the user's operational intent; Based on the user's operational intent, configuration information that conforms to the user's behavioral habits is generated.

3. The method according to claim 1, characterized in that, The configuration information includes behavioral patterns and / or recommendation weights for at least one recommended content. Generating a configuration package executable by the target terminal based on the configuration information includes: The behavior pattern is mapped to the interface component library to generate interface rendering instructions; Based on the recommendation weight of the at least one recommended content, synchronize the content recommendation algorithm parameters; Based on the interface rendering instructions and / or the synchronized content recommendation algorithm, a configuration package executable for the target terminal is generated, wherein the file size of the configuration package is less than a set threshold.

4. The method according to claim 1, characterized in that, The user behavior data includes operation events and corresponding operation data. After obtaining the user behavior data sent by the target terminal, the method further includes: The user behavior data is encapsulated into structured events to obtain at least one behavior event data, wherein the structured event includes event type, operation object, operation trajectory and / or operation sequence; The at least one behavioral event data is converted into language description text or prompt words, which are then used as input to the neural network model.

5. The method according to claim 4, characterized in that, The step of converting the at least one behavioral event data into language description text or prompt words includes: The at least one behavioral event data is denoised. The noise-reduced data of at least one behavioral event is divided into either interface operation type or content interaction type. Based on the classification results, the at least one behavioral event data is converted into language description text or prompt words.

6. The method according to claim 1, characterized in that, The target terminal is used to update the user interface layout and / or content recommendation algorithm after receiving the configuration package, so as to display the updated user interface and / or recommended content at a target time, wherein the target time is determined based on the user behavior data.

7. The method according to claim 1, characterized in that, After obtaining the user behavior data sent by the target terminal, the method further includes: The user behavior data is parsed according to a set modality and then stored in a multimodal behavior database, wherein the multimodal behavior database is used to provide configuration information for the neural network model to output.

8. An adjustment device based on user behavior, characterized in that, include: The data acquisition unit is used to acquire user behavior data sent by the target terminal; The configuration generation unit is used to extract user behavior features from the user behavior data through a pre-trained neural network model, and generate configuration information that conforms to user behavior habits based on the user behavior features. The configuration information is related to the operation interface layout and / or content recommendation logic of the target terminal. The configuration distribution unit is used to generate an executable configuration package for the target terminal based on the configuration information, and distribute the configuration package to the target terminal so that the target terminal can make adjustments that conform to user behavior habits.

9. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the user behavior-based adjustment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the user behavior-based adjustment method as described in any one of claims 1 to 7.

Images