Information recommendation method and device

Abstract

The invention discloses an information recommendation method and device, and belongs to the technical field of communication. The method comprises the following steps: acquiring historical behavior data of a user; generating at least one type of record fragment based on the historical behavior data; determining user behavior habit information based on the at least one type of record fragment; performing behavior prediction based on the user behavior habit information to obtain a prediction behavior of the user; and generating and outputting first recommendation information of the user according to the prediction behavior of the user.

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and specifically relates to an information recommendation method and device. Background Art

[0002] With the development of science and technology, the types of artificial intelligence software (applications) are increasing, and their functions are becoming more and more powerful. For example, information recommendation is a commonly used function of artificial intelligence software.

[0003] However, the information recommendation method currently used by artificial intelligence software is popular recommendation, but the information recommended in this way cannot meet the personalized needs of users, that is, this recommendation method easily leads to low recommendation accuracy. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an information recommendation method and device that can improve the accuracy of information recommendation.

[0005] In a first aspect, an embodiment of the present application provides an information recommendation method, the method comprising:

[0006] Obtain user historical behavior data;

[0007] generating at least one type of recorded segment based on the historical behavior data;

[0008] Determining user behavior habit information based on the at least one type of recorded segments;

[0009] Performing behavior prediction based on the user behavior habit information to obtain the user's predicted behavior;

[0010] According to the predicted behavior of the user, first recommendation information of the user is generated and output.

[0011] In a second aspect, an embodiment of the present application provides an information recommendation device, comprising:

[0012] The first acquisition module is used to obtain the user's historical behavior data;

[0013] A generating module, configured to generate at least one type of recording segment based on the historical behavior data;

[0014] A first determining module, configured to determine user behavior habit information based on the at least one type of recorded segments;

[0015] A prediction module, configured to perform behavior prediction based on the user behavior habit information to obtain the user's predicted behavior;

[0016] The first output module is used to generate and output first recommendation information of the user according to the predicted behavior of the user.

[0017] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0019] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, the communication interface is used to transmit image data, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0020] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0021] In an embodiment of the present application, at least one type of record fragment of the user can be generated based on the user's historical behavior data. The user's behavior habits can be analyzed by using the generated at least one type of record fragment. The user's possible behavior is predicted based on the user's behavior habits to obtain the user's predicted behavior. The user's predicted behavior is used to generate and output the first recommendation information of the user. In this way, the generated first recommendation information can be more consistent with the user's behavior habits and the user's possible behavior, providing personalized recommendations that meet the user's needs and improving the accuracy of recommendations for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is one of the flow charts of the information recommendation method provided in the embodiment of the present application;

[0023] Figure 2 This is an interface diagram of a memory fragment scene provided by an embodiment of the present application;

[0024] Figure 3 This is an interface diagram of a generated memory fragment provided by an embodiment of the present application;

[0025] Figure 4 This is the second flowchart of an information recommendation method provided in an embodiment of the present application;

[0026] Figure 5 This is a schematic diagram of the principle of predicting future user behavior provided by an embodiment of the present application;

[0027] Figure 6 This is an interface diagram showing recommended information via a desktop component provided by an embodiment of the present application;

[0028] Figure 7 This is an intelligent question-answering flow chart provided in an embodiment of the present application;

[0029] Figure 8 This is one of the intelligent question-and-answer interface diagrams provided in the embodiments of the present application;

[0030] Figure 9 This is the second diagram of an intelligent question-and-answer interface provided in an embodiment of the present application;

[0031] Figure 10 This is a flowchart of information usage provided by the embodiments of the present application;

[0032] Figure 11 This is an interface diagram for triggering a sidebar in a chat interface provided by an embodiment of the present application;

[0033] Figure 12 This is a memory content window diagram provided by an embodiment of the present application;

[0034] Figure 13 This is an interface diagram provided by an embodiment of the present application for sharing articles saved in a memory content window to a chat interface;

[0035] Figure 14 This is a module diagram of the information recommendation device provided in an embodiment of the present application;

[0036] Figure 15 is a structural diagram of an electronic device provided in an embodiment of the present application;

[0037] Figure 16 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0039] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0040] The following describes in detail the information recommendation provided by the embodiments of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0041] like Figure 1 As shown, the present application provides an information recommendation method according to an embodiment. The method can be executed by an electronic device, and specifically can be implemented by an artificial intelligence application in the electronic device. The method includes:

[0042] Step 101: Obtain the user's historical behavior data.

[0043] Historical behavior data can be behavior data within a preset historical time period. Historical behavior data can be understood as record data of various operations and behaviors of users on applications, platforms or services. For example, it may include but is not limited to travel information (for example, travel location information), captured media information, sports information, and application usage information (that is, records of the use (operation) of the application, such as browsing, clicking, playing music, playing videos, shooting, sharing, liking, forwarding, etc.), etc., and may also include the corresponding time of this information, etc.

[0044] Step 102: Generate at least one type of recording segment based on the historical behavior data.

[0045] After obtaining the user's historical data, the user's historical data can be integrated in chronological order to generate record fragments (which can also be memory fragments) related to time and events. Each record fragment corresponds to an event, and each record fragment includes time, event (an event identified based on historical user data) and data corresponding to the event in the historical user data. As an example, a record fragment related to time, place, and event can be generated, that is, the record fragment can also include a place. In addition, it should be noted that a type of record fragment may include at least one record fragment, and this at least one record fragment belongs to the same type. For example, historical behavior data of last weekend is collected. The user went to place A for fun last Saturday and went to place B for fun last Sunday. A record fragment of the travel type can be generated. The record fragment of the travel type can include a record fragment of going to place A for fun and a record fragment of going to place B for fun, or the record fragment of the travel type includes one record fragment, and the one record fragment includes a record of going to place A for fun and a record of going to place B for fun.

[0046] Step 103: Determine user behavior habit information based on at least one type of recorded segments.

[0047] After generating at least one type of record fragment, the at least one type of record fragment can be used to determine the user behavior habit information. It can be understood that the user behavior habit information may include behavior habit information corresponding to at least one type of record fragment. As an example, feature extraction can be performed on at least one type of record fragment, and based on the extracted features, the user behavior habit information is determined by artificial intelligence (AI) algorithm analysis. As an example, the user behavior habit information may include at least one of the following: travel behavior habit information (for example, user travel cycle, user travel place, type of travel place, etc., for example, travel every weekend, where to go, what type of place), exercise behavior habit information (for example, user exercise type, exercise pattern, etc.), eating habit information (for example, user dining pattern, user dining type, etc., for example, the pattern and type of user dining out), application usage habit information (for example, music playback behavior habits, video playback behavior habits, etc., such as listening to songs within a fixed time range every day, favorite songs, chasing dramas every day, etc.).

[0048] Step 104: Perform behavior prediction based on the user's behavior habit information to obtain the user's predicted behavior.

[0049] Based on the understanding of user behavior habits, inference can be performed to predict user behavior and obtain the user's predicted behavior. As an example, based on user behavior habits, user behavior prediction can be performed through AI algorithms to obtain the user's predicted behavior.

[0050] Step 105: Generate and output first recommendation information of the user based on the predicted behavior of the user.

[0051] After determining the predicted behavior of the user, first recommendation information of the user is generated based on the predicted behavior of the user, and the first recommendation information is output to provide information recommendation to the user so that the user can make a decision.

[0052] In an embodiment of the present application, at least one type of record fragment can be generated for the user based on the user's historical behavior data. The user's behavior habits can be analyzed by using the generated at least one type of record fragment. The user's possible behavior can be predicted based on the user's behavior habit information to obtain the user's predicted behavior. The user's predicted behavior can be used to generate and output the user's first recommendation information. In this way, the generated first recommendation information can be more consistent with the user's behavior habits and the user's possible behavior, providing personalized recommendations that meet the user's needs and improving the accuracy of recommendations for users.

[0053] In one embodiment, generating at least one type of record segment based on the user historical behavior data includes:

[0054] Classifying the user's historical behavior data to obtain at least one category of behavior data;

[0055] Based on the at least one type of behavior data, the at least one type of recording segment is generated.

[0056] In this embodiment, the user's historical behavior data can be classified to obtain at least one type of behavior data. The at least one type of behavior data can be used to generate the at least one type of record fragment. For a certain type of record fragment, one or more types of behavior data from the at least one type of behavior data can be used to generate the record fragment. The record fragment of this type may include one or more types of behavior data. At least one type of record fragment is generated by the classified at least one type of behavior data to improve the accuracy of the record fragment generation. As an example, based on the at least one type of behavior data, the at least one type of record fragment can be generated by an AI algorithm to improve the intelligence of the record fragment generation.

[0057] In one embodiment, the at least one type of behavior data includes at least one of the following: location information; motion information; media information; application usage information;

[0058] The generating of the at least one type of record segment based on the at least one type of behavior data includes at least one of the following:

[0059] Based on the location information, or the location information and the media information, generate a first recording segment whose content includes a travel type;

[0060] generating a second recording segment including content of the motion type based on the motion information, or the position information and the media information;

[0061] generating a third recording segment including content of food type based on the location information and the food media information in the media information;

[0062] Based on the application usage information, a fourth record segment of the application usage type is generated.

[0063] It is understood that in this embodiment, at least one type of behavioral data may include, but is not limited to, at least one of the following four types of information: location information, exercise information, media information, and application usage information. This at least one type may include at least one of travel type, exercise type, food type (also referred to as gourmet type), and application usage type (also referred to as long-term usage type). Media information may include, but is not limited to, images and videos. In this embodiment, different types of user recorded segments can be generated to improve the comprehensiveness of the user's recorded segments, thereby facilitating subsequent analysis of user behavioral habits and improving the comprehensiveness of user behavioral habits, thereby enhancing the effectiveness of information recommendations.

[0064] It should be noted that, in the process of generating the third documentary of the food type based on the location information and the food media information in the media information, the food media information may be food media collected (e.g., photographed) at the location of the location information, such as food pictures, food videos, etc.

[0065] In one embodiment, the location information includes a plurality of stop locations; and generating a first record segment including a travel type based on the location information includes:

[0066] Filtering the position of the first stay point in the position information to obtain first updated position information, wherein the position of the first stay point is a stay point position having a stay time less than a first preset time;

[0067] Merging the locations of the stay points in the first updated location information according to the distances between the locations of the stay points in the first updated location information to obtain second updated location information;

[0068] Filtering the preset stay point locations in the second updated location information to obtain third updated location information;

[0069] The first recording segment is generated according to the second stay point position in the third updated position information, or the second stay point position and the media information, where the second stay point position is a stay point position whose stay duration exceeds a second preset duration.

[0070] When generating the first recorded segment of a travel type, the historical data required includes stop location data. First, the locations of first stop locations with shorter durations can be filtered. During the merging process, adjacent stop locations (which can be temporally adjacent, meaning two stop locations are merged into a single stop location if the distance between them is less than a preset distance threshold) with a short distance (e.g., less than a preset distance threshold) can be merged to form a single stop location, with the distance between the stop locations in the second updated location information less than the preset distance threshold. The preset stop locations in the second updated location information can then be filtered to generate third updated location information. The locations of second stop locations in the third updated location information with a duration exceeding a second preset duration can then be determined. The first recorded segment of the movement type can be generated using these second stop locations, or using the second stop location and information corresponding to the second stop location in media information (e.g., media information collected at the second stop location). For example, the preset stop location can include at least one of a home location and a work location. The first preset duration, second preset duration, and preset distance threshold can all be pre-set based on actual needs and historical experience, and are not specifically limited.

[0071] In this embodiment, when generating the first recorded segment for a trip type, only the location information and its corresponding dwell duration may be used, or the location information and its corresponding dwell duration may be used in addition to the media information at the location of the location information (i.e., the media information corresponding to the location information). Furthermore, the first recorded segment is generated using the second dwell point location in the third updated location information, whose dwell duration exceeds the second preset duration, or the second dwell point location and its corresponding media information, thereby reducing the impact of dwell points with shorter dwell durations on the recorded segment, thereby improving the accuracy of the first recorded segment for the trip type.

[0072] In one embodiment, the motion information includes at least one motion type and the motion duration, motion occurrence time period, and geographic location within the motion occurrence time period of each motion type;

[0073] The step of generating a second recording segment including a motion type based on the motion information includes:

[0074] Determining a first exercise type from the at least one exercise type according to the exercise duration, wherein the exercise duration of the first exercise type exceeds a third preset duration;

[0075] A second recording segment of the first motion type is generated based on the geographical location within the motion occurrence time period of the first motion type, or the geographical location and the media information.

[0076] In the process of generating the second recording segment of the motion type in this embodiment, the motion type with a shorter motion duration can be excluded first, and the first motion type with a longer motion duration can be screened out. The second recording segment of the first motion type is generated by utilizing the geographic location within the time period of the motion of the first motion type, or the geographic location and the media collected at the geographic location in the media information, thereby reducing the impact of the motion with a shorter motion duration on the recording segment, thereby improving the accuracy of the second recording segment of the motion type.

[0077] In one embodiment, the application usage information includes an identifier of at least one application and a start time and usage duration of the at least one application;

[0078] The generating, based on the application usage information, a fourth record segment of the application usage type includes:

[0079] Determining a first application according to the application usage information, wherein the first application is an application whose usage duration in the application usage information exceeds a fourth preset duration;

[0080] A fourth record segment of the first application is generated according to the application usage information of the first application.

[0081] Based on the application usage information, the applications that the user frequently uses or uses for a long time can be determined. In the process of generating the fourth record segment of the application usage type in this embodiment, the applications with shorter usage time can be excluded first, and the first application (one or more) with longer usage time can be screened out. The usage information of the first application in the application usage information is used to generate the fourth record segment of the first application, reducing the impact of the application with shorter usage time on the record segment, so as to improve the accuracy of the fourth record segment of the application usage type.

[0082] In one embodiment, generating and outputting the first recommendation information of the user based on the predicted behavior of the user includes:

[0083] Display prompt information, which is used to prompt the user's behavioral habit information and whether to accept the information recommendation;

[0084] When the user confirms and accepts the recommendation input in response to the prompt information, the first recommendation information is generated and output according to the predicted behavior of the user.

[0085] The determined user behavior habits may be different from the user's actual habits, and the user may not be satisfied with the determined user behavior habits, or the determined user behavior habits may match the user's actual habits, and the determined user behavior habits are more accurate, and the user is satisfied with the determined user behavior habits. Therefore, the user can be prompted with user behavior habit information by displaying prompt information, and the user can be asked to confirm whether to accept the information recommendation. If the user is satisfied, the user can confirm to accept the recommendation, and the user can make an input to accept the recommendation (for example, click the control to confirm acceptance). In this way, the first recommendation information can be generated and output based on the user's predicted behavior.

[0086] In one embodiment, after displaying the prompt information, the method further includes:

[0087] In the case of obtaining the user's modification input to the prompt information, modifying the user behavior habit information according to the modification input;

[0088] Modifying the predicted behavior of the user based on the modified user behavior habit information;

[0089] The generating and outputting the first recommendation information of the user according to the predicted behavior of the user includes: generating and outputting the first recommendation information according to the corrected predicted behavior of the user.

[0090] If the user is not satisfied with the determined user behavior habits or believes that there is a certain difference between the user behavior habits and the user's actual habits (that is, the determined user behavior habits are inaccurate), the user can modify the user habits, that is, when obtaining the user's modification input for the prompt information, the user behavior habit information is modified according to the modification input, so that the modified user behavior habits are more in line with the user's actual behavior habits, and the modified user behavior habit information is used to modify the user's predicted behavior and improve the accuracy of the user's predicted behavior. Subsequently, based on the modified user's predicted behavior, the first recommendation information is generated and output to improve the accuracy of information recommendation.

[0091] In one embodiment, in the process of generating and outputting the first recommendation information based on the predicted behavior of the user, it may include, upon obtaining the user's modification input for the prompt information, modifying the user's behavior habits based on the modification input; modifying the user's predicted behavior based on the modified user behavior habits; and generating and outputting the first recommendation information based on the modified user's predicted behavior.

[0092] In one embodiment, generating and outputting the first recommendation information of the user based on the predicted behavior of the user includes:

[0093] Obtain travel status data of at least one dimension;

[0094] Based on the travel status data of the at least one dimension and the predicted behavior of the user, the first recommendation information is generated and output.

[0095] In this embodiment, based on the user's predicted behavior, at least one dimension of travel status data is also considered to generate first recommendation information for the user, output the first recommendation information to the user, and implement information recommendation to the user, thereby improving the effectiveness of information recommendation. As an example, the at least one dimension of travel status data may include, but is not limited to, at least one of the following: weather information, environmental information, network information, traffic information, and surrounding service information (e.g., nearby restaurants, nearby attractions, etc.).

[0096] In one embodiment, after generating and outputting the first recommendation information, the method may further include: receiving a fourth input from the user to the first recommendation information (for example, click input), jumping to a first page, wherein the first page includes detailed information corresponding to the first recommendation information, for example, behavioral suggestions, strategy information, etc., to assist the user in making decisions, etc.

[0097] In one embodiment, the method further comprises:

[0098] Obtaining question information input by the user;

[0099] In the case where the question information is associated with a memory library, searching the memory library for information matching the question information; the memory library includes user favorite information and the at least one type of record fragment;

[0100] Based on the information matching the question information, answer information is generated and output.

[0101] That is, in this embodiment, interaction with users can be achieved, and knowledge questions and answers can be realized. When the question information is associated with the memory library, the memory library can be analyzed and used first, and information matching the question information can be retrieved from the memory library. In this way, in the process of intelligent question and answer, more personalized and more matching answer information for the user's question can be given.

[0102] In one embodiment, after obtaining the question information input by the user, the method further includes at least one of the following:

[0103] identifying a user intention based on the question information; and determining that the question information is associated with the memory library if the user intention includes a preset intention related to the memory library;

[0104] identifying a user intention based on the question information; and determining that the question information is associated with the memory library if a keyword in the user intention includes a content tag of the memory library;

[0105] When it is determined through an artificial intelligence AI model that a correlation parameter value between the question information and the user collection information is greater than a preset value, it is determined that the question information is associated with the memory library.

[0106] The correlation parameter value may be a correlation degree, which may indicate the degree of association between the two. A larger value indicates a greater association, and vice versa. In this embodiment, any of the three strategies described above may be used to determine whether the question information is associated with the memory bank, thereby increasing the flexibility of determining whether the question information is associated with the memory bank.

[0107] In one embodiment, the method further comprises:

[0108] Obtaining a first input of the user in the first interface;

[0109] In response to the first input, displaying an icon of the smart application on the first interface;

[0110] Obtaining a second input of the user on the icon;

[0111] In response to the second input, displaying the user-associated information in the smart application;

[0112] obtaining a third input by the user regarding the first information in the user-associated information;

[0113] In response to the third input, an operation associated with the scene corresponding to the first interface is performed on the first information.

[0114] It should be noted that the smart application is an artificial intelligence application, and the first interface is any interface displayed on an electronic device. The first input can be an operation such as swiping left, swiping right, and long pressing, without specific limitation. The second input can be an operation such as clicking, long pressing, etc., without specific limitation. The third input can be an operation such as moving / dragging, without specific limitation. The user-associated information in the smart application may include but is not limited to the generated record fragments of the user, the user's favorite information (pictures, files, web pages, etc.), etc. In addition, performing an operation associated with the scene corresponding to the first interface on the first information may include moving the first information to the first interface, etc. As an example, the first interface may include but is not limited to a text input interface (for example, a text / document editing application editing interface, etc., corresponding to a text input scene), a chat interface (corresponding to a chat scene), etc. In response to the third input, during the operation associated with the scene corresponding to the first interface on the first information, for the text input scene, the first information can be inserted into the cursor position in the text input interface, and for the chat scene, the first information can be shared with the person chatting with the user in the chat interface in the chat interface.

[0115] The process of the above method is described in detail below with reference to some embodiments.

[0116] First, the relevant technical introduction:

[0117] Artificial intelligence software has a variety of functions, among which the memory function is an intelligent personal memory manager. This function can record user behavior data and analyze user behavior habits while the user is using the mobile phone. It can automatically integrate and organize various fragmented information through AI capabilities, and construct and record the user's emotional situational memory in a multimodal combination to generate personalized memory fragments (record fragments) to help users capture and retain important moments in life. Memory fragments may include records of sports records, game achievements, birthdays and other important days, as well as daily travel, travel information, daily use of applications (Application, APP) for learning and entertainment and other life details. In addition to intelligently generating memory fragments, users can also manually edit and generate memory fragments. Such as Figure 2 As shown in the figure, you can select the scene to generate memory fragments in multiple memory fragment scenes, such as calls, sports records and achievements, game achievements, important days, entertainment interactions, photo albums, geographic locations, long-term use of applications, etc. Figure 3 The figure shows the memory fragments generated on April 3 and April 4. In addition, the memory function also includes a collection library, which allows users to easily add valuable information (files, pictures, web pages, etc.) from the Internet and local computers to their personal collection library in various ways, enabling efficient management and retrieval within the memory function.

[0118] Memory fragments can record what the user sees, hears, thinks, and feels, and remember the user's daily experiences, movies watched, books read, short videos watched, etc., while the collection library is the user's personal knowledge base, which records the user's collection information. Users realize the mobile phone's understanding of users through memory, but it is currently only used to aggregate data and retain memories for users, and is not effectively used to bring greater value and surprises to users. In this application scheme, user behavior can be predicted based on user historical behavior data, active reasoning and decision-making can be assisted to provide users with subsequent personalized services; the use boundaries of memory fragments / knowledge bases can also be expanded, allowing users to use memory fragment data more conveniently and efficiently, bringing more emotional value.

[0119] In the embodiments of this application, the memory function acts as a user's intelligent memory manager within the AI ​​software. By collecting and integrating scattered information and fragmented memories, it can find hidden memory links, enhance predictions of the user's next action and identification of user intent, and then provide personalized planning, decision support, and execution capabilities. Furthermore, the memory library contains rich data and can be used across more touchpoints and channels, allowing mobile devices to better understand users and more efficiently use memory data.

[0120] Through the solutions in the embodiments of this application, it is possible to achieve:

[0121] By remembering and understanding user behavior and enriching user portraits, it can provide more accurate recommendation guidance, predict user behavior based on user history, and actively recommend appropriate behaviors and content based on current time and space dimensional information, and provide the required service paths, thereby influencing the user's next move.

[0122] When answering questions, artificial intelligence software (AI assistant) prioritizes analyzing and using memory data, making the AI ​​assistant more personalized and understanding you better, taking it one step closer to becoming a personal assistant.

[0123] When in the chat interface of an instant messaging application or the editing interface of a text / document editing application, the sidebar memory window (which may include an icon of the artificial intelligence software) can be triggered, and the content in the memory can be directly dragged out for sharing and / or insertion, thereby achieving efficient use of the memory content.

[0124] like Figure 4 As shown, the process of the information recommendation method provided in the embodiment of the present application is as follows:

[0125] Step 401: The memory function uses AI capabilities to analyze and integrate user behavior data to generate memory fragments.

[0126] For example, the types of memory fragments generated include at least one of the following:

[0127] 1. Memory fragments of daily travel behavior (memory fragments of travel types):

[0128] (1) Data acquisition: The data needed include stay point data, home and company location data;

[0129] (2) Data analysis and fragment generation: First, filter out the short stays; then execute the stay point merging algorithm until the distance between the two previous and next stay points exceeds the preset distance threshold; then execute the stay point filtering algorithm to filter the stay points at and near the home and company locations; finally, record the stay point location and stay duration. If the stay duration exceeds X minutes, generate a daily travel memory lock piece;

[0130] In this way, daily travel habits can be analyzed later: for example, the user goes to certain types of places every weekend, such as shopping malls, leisure places, scenic spots, amusement parks, etc.;

[0131] 2. Sports memory fragments (sports type memory fragments):

[0132] (1) Data acquisition: users generate exercise-related data (exercise data and data donated to the intent framework by the watch), including exercise types such as outdoor running, indoor running, brisk walking, and outdoor cycling, as well as exercise duration, time period of exercise behavior, and geographic location during the exercise behavior time period;

[0133] (2) Data analysis and fragment generation: If a user generates exercise data and the exercise duration exceeds X minutes, and the geographic location is obtained during the time period of the exercise behavior, then an exercise memory is generated;

[0134] In this way, exercise habits can be analyzed later: for example, the user will do a certain exercise at a certain time of day or week and at a certain location;

[0135] 3. Food memory fragments (food type memory fragments):

[0136] (1) Data acquisition: data required for daily travel behavior memory fragments, as well as album photos and video data;

[0137] (2) Data analysis and fragment generation: If a user has a food point of interest (POI) near their stop and takes food photos or videos during their stay, a food memory is generated;

[0138] In this way, food habits can be analyzed later: for example, users prefer certain types of food, such as hot pot, buffet, and barbecue; users prefer to eat in certain places;

[0139] 4. Memory fragments caused by long-term use of applications (memory fragments of application usage types):

[0140] (1) Data acquisition: daily application usage data of users over the past period of time, which may include application package name, start time, usage duration, etc.

[0141] (2) Data analysis and fragment generation: Based on the user's daily application usage habits, determine whether an application is used for an excessively long time on that day (the usage time exceeds the fourth preset time), and generate an excessively used application card for the user;

[0142] In this way, application usage habits can be analyzed later: for example, users will start using a certain application around a certain time period.

[0143] Step 402: Based on the user's memory fragments, analyze and obtain the user's behavior habits (for example, extract features of the memory fragments, and obtain the user's behavior habits through AI analysis based on the extracted features).

[0144] User behavior habits may include but are not limited to:

[0145] (1) Travel behavior habits (e.g., travel habits), such as whether the user travels every weekend, where they go, and what types of places;

[0146] (2) Exercise behavior habits, such as the user's exercise type and exercise patterns;

[0147] (3) Food habits, such as the patterns and types of dining out that users go out to eat;

[0148] (4) Application usage habits, such as music and video playback behaviors, such as listening to music within a fixed time range every day, favorite songs, and TV series that are watched every day.

[0149] Step 403: Predict the user's future behavior.

[0150] That is, behavior prediction is performed to obtain the user's predicted behavior: based on the understanding of the user's behavioral habits, the user's future behavior / actions are actively inferred and predicted, and when the user subsequently enters the memory fragment interface, the user is guided to confirm.

[0151] First, predict future actions / behaviors. The form can be: [time and space] + [verb] + [noun], such as Figure 5 As shown in the figure, such as "Friday night + eat + barbecue", "Every Monday, Wednesday and Friday + run", "Weekend + travel + countryside", "Around 23:00 every night + listen to + pop music", "Every Sunday night at 8:00 + watch + WeChat reading", etc.

[0152] Secondly, when the user subsequently enters the Memory Fragment interface, the system will notify the user of the user's comforting habits inferred by the user through pop-ups or banners, and the user can confirm or modify them;

[0153] If a dialog box pops up with a prompt, the prompt may include the following content: "The system AI assistant has inferred your [behavioral habits (such as cycling in the suburbs every weekend)]. The system will subsequently provide personalized recommendations and suggestions for your weekend cycling. Do you accept?"

[0154] (1) If the user chooses to accept, then proceed to step 404; if not, then terminate the subsequent personalized service process;

[0155] (2) If the user chooses to accept but believes that the user behavior habit results of AI inference are inaccurate, the user can click to modify the inference results. The system will automatically modify the inference results according to the user's modification content, that is, modify the user behavior habits. In this way, the predicted user behavior can be corrected based on the modified user behavior habits.

[0156] Step 404: Trigger the recommendation process before the user is about to perform a possible action.

[0157] That is, generating recommendation information, actively outputting recommendation information to users (for example, recommending user behavior, content, etc.), providing the required service path, and thus influencing the user's next action.

[0158] As an example, Figure 6 As shown, desktop components, such as the recommendation component 601 of the artificial intelligence application, can be used to recommend behaviors and content to users before the timing described in the above steps, such as traveling, food, fitness, listening to music, and watching TV series. Figure 6 As shown, the recommended information includes travel inspiration, "Why not travel to place F for New Year's Day? Winter is sunny and the weather is pleasant. Enjoy a 5-day vacation," and pictures of the scenery of place F. As an example, in addition to desktop components, user behavior and content recommendations can also be made in other forms, including but not limited to at least one of the following:

[0159] (1) Send notification;

[0160] (2) A new personalized recommendation bar is added to the desktop, and recommended information is updated in real time;

[0161] (3) Pop-up recommendation window;

[0162] (4) Recommended content identification for AI application desktop icons;

[0163] (5) Recommended banner on the homepage of artificial intelligence application.

[0164] Step 405: Click on the recommended content to enter the landing page, and / or click on the recommended action to enter the corresponding action interface: When the user clicks on the action / content recommendation information, they will jump to the AI ​​application action / content recommendation landing page. The landing page contains action suggestions / strategies generated by the AI ​​based on various dimensions such as network information, weather / environmental data, etc. to assist the user in making decisions. If the action recommendation is a mobile application, such as listening to music or watching a TV series, clicking it will jump directly to the corresponding resource interface of the corresponding application for playback.

[0165] like Figure 7 As shown, the intelligent question-answering process provided by the embodiment of the present application is as follows:

[0166] Step 701: When a user asks a question in an artificial intelligence application, the artificial intelligence application uses its AI capabilities to understand the semantics and analyze the type of the user's question (question information);

[0167] Step 702: When the artificial intelligence application understands that the user's question is related to the content of the user's memory bank (including memory fragments, collected files, articles, pictures, etc.), it will prioritize retrieving the relevant content of the memory bank for analysis and retrieving information that matches the user's question.

[0168] The process of displaying the contents of the reference memory bank is as follows Figure 8 For example, if the user inputs the question "What are the buy and sell times in swing trading?", the correlation between the user's intention and the memory content can be determined by any of the following strategies:

[0169] (1) The user's intention includes obvious directional intentions such as "collection" and "memory" to search for memory database data;

[0170] (2) The search keywords in the user's intention are related to the tags of the memory library content. For example, the collected articles on swing trading will be automatically labeled by AI as "finance" and "swing trading", and the keywords in the user's search intention also include "swing trading", so there is a correlation;

[0171] (3) The AI ​​model determines the relevance of the retrieved local collection content to the user's query.

[0172] Step 703: The artificial intelligence application sorts out the answers to the user's questions based on the retrieved matching information, displays them to the user, and may display referenced content in the answers, such as Figure 9 shown.

[0173] It should be noted that Figure 9What is shown are quoted collection articles. The user's questions may also be related to memory fragment information. The quoted content displayed at this time is the memory fragment content. For example, the user can ask "Where did I go last month?" "When was the last time I went to XX Park?" "Where is the barbecue restaurant I went to last time / what is it called?" "What songs do I listen to recently?" etc.

[0174] like Figure 10 As shown, the information usage process provided by the embodiment of the present application is as follows:

[0175] Step 1001: triggering the sidebar in the relevant interface, and displaying the icon of the artificial intelligence application in the sidebar, for example, in the chat interface of the instant messaging application, the editing interface of the text / document editing application, triggering the sidebar display, such as Figure 11 As shown, a sidebar 1100 is triggered in the chat interface, and an icon 1101 of an artificial intelligence application is displayed;

[0176] Step 1002: Click on the icon of the artificial intelligence application, such as Figure 12 As shown, a memory content window 1200 pops up, which includes various types of information such as remembered pictures, files, memory fragments, and favorite information.

[0177] Step 1003: Find the content you want to drag out in the memory content window, then long-press and drag out the content, release it and share (chat interface) or insert (edit interface) the content in a suitable format, such as the content source file, such as generating a memory fragment card map, etc. Figure 13 :

[0178] The embodiment of this application provides a method for information recommendation based on personal memory extraction. This method uses historical memory data (user historical behavior data) to predict user behavior, actively infer, and assist in decision-making, thereby providing users with subsequent personalized services. At the same time, it expands the use boundaries of the memory library, allowing users to use memory data more conveniently and efficiently across multiple channels. This greatly enriches the creative ability of personal memory data and better serves users.

[0179] The information recommendation method provided in the embodiment of the present application can be executed by an information recommendation device. In the embodiment of the present application, the information recommendation device provided in the embodiment of the present application is described by taking the information recommendation device executing the information recommendation method as an example.

[0180] like Figure 14 As shown, an information recommendation device 1400 according to an embodiment is provided, which can be used in an electronic device. The device 1400 includes:

[0181] The first acquisition module 1401 is used to acquire the user's historical behavior data;

[0182] A generating module 1402, configured to generate at least one type of record segment based on the historical behavior data;

[0183] A first determining module 1403 is configured to determine user behavior habit information based on the at least one type of recorded segments;

[0184] Prediction module 1404, configured to perform behavior prediction based on the user behavior habit information to obtain the user's predicted behavior;

[0185] The first output module 1405 is configured to generate and output first recommendation information for the user based on the predicted behavior of the user.

[0186] In some embodiments, the generating module 1402 includes:

[0187] a classification unit, configured to classify the user's historical behavior data to obtain at least one category of behavior data;

[0188] A generating unit is configured to generate the at least one type of recording segment based on the at least one type of behavior data.

[0189] In some embodiments, the at least one type of behavioral data includes at least one of the following: location information; motion information; media information; application usage information;

[0190] The generating unit includes at least one of the following:

[0191] A first generating subunit is configured to generate a first recording segment including a travel type based on the location information, or the location information and the media information;

[0192] A second generating subunit is configured to generate a second recording segment including a motion type based on the motion information, or the position information and the media information;

[0193] a third generating subunit, configured to generate a third recording segment including food type based on the location information and the food media information in the media information;

[0194] The fourth generating subunit is configured to generate a fourth record segment of the application usage type based on the application usage information.

[0195] In some embodiments, the first generating subunit includes:

[0196] a first filtering subunit, configured to filter the position of a first stay point in the position information to obtain first updated position information, wherein the position of the first stay point is a stay point position having a stay time shorter than a first preset time;

[0197] a merging subunit, configured to merge the stay point positions in the first updated location information according to the distances between the stay point positions in the first updated location information to obtain second updated location information;

[0198] a second filtering subunit, configured to filter the preset stay point locations in the second updated location information to obtain third updated location information;

[0199] The first segment generating subunit is used to generate the first recording segment according to the second stay point position in the third updated position information, or the second stay point position and the media information, where the second stay point position is a stay point position whose stay duration exceeds a second preset duration.

[0200] In some embodiments, the motion information includes at least one motion type and the motion duration, motion occurrence time period, and geographic location within the motion occurrence time period of each motion type;

[0201] The second generating subunit includes:

[0202] a first determining subunit, configured to determine a first exercise type from the at least one exercise type according to the exercise duration, wherein the exercise duration of the first exercise type exceeds a third preset duration;

[0203] The second generating subunit is configured to generate a second recording segment of the first motion type according to a geographical location within a motion occurrence time period of the first motion type, or the geographical location and the media information.

[0204] In some embodiments, the application usage information includes an identifier of at least one application and a start time and usage duration of the at least one application;

[0205] The fourth generating subunit comprises:

[0206] A second determining subunit is configured to determine a first application according to the application usage information, wherein the first application is an application whose application usage duration in the application usage information exceeds a fourth preset duration;

[0207] The third generating subunit is configured to generate a fourth record segment of the first application according to the application usage information of the first application.

[0208] In some embodiments, the first output module includes:

[0209] A display unit, configured to display prompt information, wherein the prompt information is used to prompt the user's behavioral habit information and whether to accept the information recommendation;

[0210] The output unit is configured to generate and output the first recommendation information based on the predicted behavior of the user when a confirmation input of the user accepting the recommendation in response to the prompt information is obtained.

[0211] In some embodiments, the apparatus further comprises:

[0212] A first correction module is configured to, upon obtaining a modification input of the user to the prompt information, modify the user behavior habit information according to the modification input;

[0213] A second correction module is used to correct the predicted behavior of the user based on the corrected user behavior habit information;

[0214] The generating and outputting the first recommendation information of the user according to the predicted behavior of the user includes: generating and outputting the first recommendation information according to the corrected predicted behavior of the user.

[0215] In some embodiments, generating and outputting first recommendation information for the user based on the predicted behavior of the user includes:

[0216] Obtain travel status data of at least one dimension;

[0217] Based on the travel status data of the at least one dimension and the predicted behavior of the user, the first recommendation information is generated and output.

[0218] In some embodiments, the apparatus further comprises:

[0219] A second acquisition module is used to acquire the question information input by the user;

[0220] a retrieval module, configured to retrieve information matching the question information from the memory bank when the question information is associated with the memory bank; the memory bank includes user favorite information and the at least one type of record fragment;

[0221] The second output module is configured to generate and output answer information based on information matching the question information.

[0222] In some embodiments, the apparatus further comprises at least one of the following:

[0223] an identification module for identifying a user intention based on the question information; a second determination module for determining that the question information is associated with the memory library when the user intention includes a preset intention associated with the memory library;

[0224] an identification module for identifying user intent based on the question information; a third determination module for determining that the question information is associated with the memory library when a keyword in the user intent includes a content tag of the memory library;

[0225] The fourth determination module is used to determine that the question information is associated with the memory library when it is determined through an artificial intelligence AI model that the correlation parameter value between the question information and the user collection information is greater than a preset value.

[0226] In some embodiments, the apparatus further comprises:

[0227] A third acquisition module is used to obtain the first input of the user in the first interface;

[0228] a first display module, configured to display an icon of the smart application on the first interface in response to the first input;

[0229] a fourth obtaining module, configured to obtain a second input of the user on the icon;

[0230] a second display module, configured to display the user-associated information in the smart application in response to the second input;

[0231] A fifth acquisition module, configured to acquire a third input of the user on the first information in the user-associated information;

[0232] An execution module is used to perform an operation associated with the scene corresponding to the first interface on the first information in response to the third input.

[0233] The information recommendation device in the embodiments of the present application can be an electronic device or a component of an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other device other than a terminal. The electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM or self-service machine, etc., and the embodiments of the present application are not specifically limited.

[0234] The information recommendation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0235] The information recommendation device provided in the embodiment of the present application can implement each process implemented in the above-mentioned information recommendation method embodiment, for example, it can implement Figures 1 to 13 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0236] Alternatively, as Figure 15 As shown, an embodiment of the present application also provides an electronic device 1500, including a processor 1501 and a memory 1502, wherein the memory 1502 stores programs or instructions that can be run on the processor 1501. When the program or instructions are executed by the processor 1501, the various steps of the above-mentioned information recommendation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0237] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0238] Figure 16 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present application.

[0239] The electronic device 1600 includes but is not limited to components such as a radio frequency unit 1601 , a network module 1602 , an audio output unit 1603 , an input unit 1604 , a sensor 1605 , a display unit 1606 , a user input unit 1607 , an interface unit 1608 , a memory 1609 , and a processor 1610 .

[0240] Those skilled in the art will understand that the electronic device 1600 may also include a power source (such as a battery) to power each component, and the power source may be logically connected to the processor 1610 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. Figure 16 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be repeated here.

[0241] The processor 1610 is configured to:

[0242] Obtain user historical behavior data;

[0243] generating at least one type of recorded segment based on the historical behavior data;

[0244] Determining user behavior habit information based on the at least one type of recorded segments;

[0245] Performing behavior prediction based on the user behavior habit information to obtain the user's predicted behavior;

[0246] According to the predicted behavior of the user, first recommendation information of the user is generated and output.

[0247] In some embodiments, the processor 1610 is specifically configured to:

[0248] Classifying the user's historical behavior data to obtain at least one category of behavior data;

[0249] Based on the at least one type of behavior data, the at least one type of recording segment is generated.

[0250] In some embodiments, the at least one type of behavioral data includes at least one of the following: location information; motion information; media information; application usage information;

[0251] The processor 1610 is specifically configured to perform at least one of the following:

[0252] Based on the location information, or the location information and the media information, generate a first recording segment whose content includes a travel type;

[0253] generating a second recording segment including content of the motion type based on the motion information, or the position information and the media information;

[0254] generating a third recording segment including content of food type based on the location information and the food media information in the media information;

[0255] Based on the application usage information, a fourth record segment of the application usage type is generated.

[0256] In some embodiments, the processor 1610 is specifically configured to:

[0257] Filtering the position of the first stay point in the position information to obtain first updated position information, wherein the position of the first stay point is a stay point position having a stay time less than a first preset time;

[0258] Merging the locations of the stay points in the first updated location information according to the distances between the locations of the stay points in the first updated location information to obtain second updated location information;

[0259] Filtering the preset stay point locations in the second updated location information to obtain third updated location information;

[0260] The first recording segment is generated according to the second stay point position in the third updated position information, or the second stay point position and the media information, where the second stay point position is a stay point position whose stay duration exceeds a second preset duration.

[0261] In some embodiments, the motion information includes at least one motion type and the motion duration, motion occurrence time period, and geographic location within the motion occurrence time period of each motion type;

[0262] The processor 1610 is specifically configured to:

[0263] Determining a first exercise type from the at least one exercise type according to the exercise duration, wherein the exercise duration of the first exercise type exceeds a third preset duration;

[0264] A second recording segment of the first motion type is generated based on the geographical location within the motion occurrence time period of the first motion type, or the geographical location and the media information.

[0265] In some embodiments, the application usage information includes an identifier of at least one application and a start time and usage duration of the at least one application;

[0266] The processor 1610 is specifically configured to:

[0267] Determining a first application according to the application usage information, wherein the first application is an application whose usage duration in the application usage information exceeds a fourth preset duration;

[0268] A fourth record segment of the first application is generated according to the application usage information of the first application.

[0269] In some embodiments, the processor 1610 is specifically configured to:

[0270] Display prompt information, which is used to prompt the user's behavioral habit information and whether to accept the information recommendation;

[0271] When the user confirms and accepts the recommendation input in response to the prompt information, the first recommendation information is generated and output according to the predicted behavior of the user.

[0272] In some embodiments, the processor 1610 is further configured to:

[0273] In the case of obtaining the user's modification input to the prompt information, modifying the user behavior habit information according to the modification input;

[0274] Modifying the predicted behavior of the user based on the modified user behavior habit information;

[0275] The generating and outputting the first recommendation information of the user according to the predicted behavior of the user includes: generating and outputting the first recommendation information according to the corrected predicted behavior of the user.

[0276] In some embodiments, generating and outputting first recommendation information for the user based on the predicted behavior of the user includes:

[0277] Obtain travel status data of at least one dimension;

[0278] Based on the travel status data of the at least one dimension and the predicted behavior of the user, the first recommendation information is generated and output.

[0279] In some embodiments, the processor 1610 is further configured to:

[0280] Obtaining question information input by the user;

[0281] In the case where the question information is associated with a memory library, searching the memory library for information matching the question information; the memory library includes user favorite information and the at least one type of record fragment;

[0282] Based on the information matching the question information, answer information is generated and output.

[0283] In some embodiments, the processor 1610 is further configured to:

[0284] identifying a user intention based on the question information; and determining that the question information is associated with the memory library if the user intention includes a preset intention related to the memory library;

[0285] identifying a user intention based on the question information; and determining that the question information is associated with the memory library if a keyword in the user intention includes a content tag of the memory library;

[0286] When it is determined through an artificial intelligence AI model that a correlation parameter value between the question information and the user collection information is greater than a preset value, it is determined that the question information is associated with the memory library.

[0287] In some embodiments, the processor 1610 is further configured to:

[0288] Obtaining a first input of the user in the first interface;

[0289] In response to the first input, displaying an icon of the smart application on the first interface;

[0290] Obtaining a second input of the user on the icon;

[0291] In response to the second input, displaying the user-associated information in the smart application;

[0292] obtaining a third input by the user regarding the first information in the user-associated information;

[0293] An execution module is used to perform an operation associated with the scene corresponding to the first interface on the first information in response to the third input.

[0294] It should be understood that in an embodiment of the present application, the input unit 1604 may include a graphics processing unit (GPU) 16041 and a microphone 16042, and the graphics processor 16041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1606 may include a display panel 16061, and the display panel 16061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1607 includes a touch panel 16071 and at least one of other input devices 16072. The touch panel 16071 is also called a touch screen. The touch panel 16071 may include two parts: a touch detection device and a touch controller. Other input devices 16072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0295] Memory 1609 can be used to store software programs and various data. Memory 109 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). Furthermore, memory 109 may include volatile memory or non-volatile memory, or memory 1609 may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0296] Processor 110 may include one or more processing units; optionally, these may include, but are not limited to, applications and an operating system. Processor 1610 may integrate an application processor and a modem processor. The application processor primarily processes the operating system, user interface, and applications, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 1610.

[0297] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information recommendation method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0298] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0299] An embodiment of the present application further provides a chip including a processor and a communication interface, wherein the communication interface and the processor are coupled, the communication interface is used to transmit image data, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information recommendation method embodiment and achieve the same technical effect. To avoid repetition, they will not be described here.

[0300] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0301] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned information recommendation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0302] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0303] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0304] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. An information recommendation method, characterized in that: The method comprises: Obtain user historical behavior data; generating at least one type of recorded segment based on the historical behavior data; Determining user behavior habit information based on the at least one type of recorded segments; Performing behavior prediction based on the user behavior habit information to obtain the user's predicted behavior; According to the predicted behavior of the user, first recommendation information of the user is generated and output.

2. The method according to claim 1, characterized in that The generating of at least one type of record segment based on the historical behavior data includes: Classifying the historical behavior data to obtain at least one category of behavior data; Based on the at least one type of behavior data, the at least one type of recording segment is generated.

3. The method according to claim 2, characterized in that The at least one type of behavioral data includes at least one of the following: location information; movement information; media information; application usage information; The generating of the at least one type of record segment based on the at least one type of behavior data includes at least one of the following: Based on the location information, or the location information and the media information, generate a first recording segment whose content includes a travel type; generating a second recording segment including content of the motion type based on the motion information, or the position information and the media information; generating a third recording segment including content of food type based on the location information and the food media information in the media information; Based on the application usage information, a fourth record segment of the application usage type is generated.

4. The method according to claim 3, characterized in that The location information includes a plurality of stop locations; and generating a first record segment including a travel type based on the location information includes: Filtering the position of the first stay point in the position information to obtain first updated position information, wherein the position of the first stay point is a stay point position having a stay time less than a first preset time; Merging the locations of the stay points in the first updated location information according to the distances between the locations of the stay points in the first updated location information to obtain second updated location information; Filtering the preset stay point locations in the second updated location information to obtain third updated location information; The first recording segment is generated according to the second stay point position in the third updated position information, or the second stay point position and the media information, where the second stay point position is a stay point position whose stay duration exceeds a second preset duration.

5. The method according to claim 3, characterized in that The exercise information includes at least one exercise type and the exercise duration, exercise time period and geographic location within the exercise time period of each exercise type; The step of generating a second recording segment including a motion type based on the motion information includes: Determining a first exercise type from the at least one exercise type according to the exercise duration, wherein the exercise duration of the first exercise type exceeds a third preset duration; A second recording segment of the first motion type is generated based on the geographical location within the motion occurrence time period of the first motion type, or the geographical location and the media information.

6. The method according to claim 3, characterized in that The application usage information includes an identifier of at least one application and a start time and usage duration of the at least one application; The generating, based on the application usage information, a fourth record segment of the application usage type includes: Determining a first application according to the application usage information, wherein the first application is an application whose usage duration in the application usage information exceeds a fourth preset duration; A fourth record segment of the first application is generated according to the application usage information of the first application.

7. The method according to any one of claims 1 to 6, characterized in that Generating and outputting first recommendation information of the user according to the predicted behavior of the user includes: Display prompt information, which is used to prompt the user's behavioral habit information and whether to accept the information recommendation; When the user confirms and accepts the recommendation input in response to the prompt information, the first recommendation information is generated and output according to the predicted behavior of the user.

8. The method according to claim 1 or 7, characterized in that Generating and outputting first recommendation information of the user according to the predicted behavior of the user includes: Obtain travel status data of at least one dimension; Based on the travel status data of the at least one dimension and the predicted behavior of the user, the first recommendation information is generated and output.

9. The method according to claim 2, characterized in that The method further comprises: Obtaining question information input by the user; In the case where the question information is associated with a memory library, searching the memory library for information matching the question information; the memory library includes user favorite information and the at least one type of record fragment; Based on the information matching the question information, answer information is generated and output.

10. An information recommendation device, characterized in that: The device comprises: The first acquisition module is used to obtain the user's historical behavior data; A generating module, configured to generate at least one type of recording segment based on the historical behavior data; A first determining module, configured to determine user behavior habit information based on the at least one type of recorded segments; A prediction module, configured to perform behavior prediction based on the user behavior habit information to obtain the user's predicted behavior; The first output module is used to generate and output first recommendation information of the user according to the predicted behavior of the user.

11. The device according to claim 10, characterized in that The generation module includes: a classification unit, configured to classify the historical behavior data to obtain at least one category of behavior data; A generating unit is configured to generate the at least one type of recording segment based on the at least one type of behavior data.

12. The device according to claim 11, characterized in that The at least one type of behavioral data includes at least one of the following: location information; movement information; media information; application usage information; The generating unit includes at least one of the following: A first generating subunit is configured to generate a first recording segment including a travel type based on the location information, or the location information and the media information; A second generating subunit is configured to generate a second recording segment including a motion type based on the motion information, or the position information and the media information; a third generating subunit, configured to generate a third recording segment including food type based on the location information and the food media information in the media information; The fourth generating subunit is configured to generate a fourth record segment of the application usage type based on the application usage information.

13. The device according to claim 12, characterized in that The first generating subunit includes: a first filtering subunit, configured to filter the position of a first stay point in the position information to obtain first updated position information, wherein the position of the first stay point is a stay point position having a stay time shorter than a first preset time; a merging subunit, configured to merge the stay point positions in the first updated location information according to the distances between the stay point positions in the first updated location information to obtain second updated location information; a second filtering subunit, configured to filter the preset stay point locations in the second updated location information to obtain third updated location information; The first segment generating subunit is used to generate the first recording segment according to the second stay point position in the third updated position information, or the second stay point position and the media information, where the second stay point position is a stay point position whose stay duration exceeds a second preset duration.

14. The device according to claim 12, characterized in that The exercise information includes at least one exercise type and the exercise duration, exercise time period and geographic location within the exercise time period of each exercise type; The second generating subunit includes: a first determining subunit, configured to determine a first exercise type from the at least one exercise type according to the exercise duration, wherein the exercise duration of the first exercise type exceeds a third preset duration; The second generating subunit is configured to generate a second recording segment of the first motion type according to a geographical location within a motion occurrence time period of the first motion type, or the geographical location and the media information.

15. The device according to claim 12, characterized in that The application usage information includes an identifier of at least one application and a start time and usage duration of the at least one application; The fourth generating subunit comprises: A second determining subunit is configured to determine a first application according to the application usage information, wherein the first application is an application whose application usage duration in the application usage information exceeds a fourth preset duration; The third generating subunit is configured to generate a fourth record segment of the first application according to the application usage information of the first application.

16. The device according to any one of claims 10 to 15, characterized in that The first output module includes: A display unit, configured to display prompt information, wherein the prompt information is used to prompt the user's behavior habits and whether to accept the information recommendation; The output unit is configured to generate and output the first recommendation information based on the predicted behavior of the user when a confirmation input of the user accepting the recommendation in response to the prompt information is obtained.

17. The device according to claim 10 or 16, characterized in that Generating and outputting first recommendation information of the user according to the predicted behavior of the user includes: Obtain travel status data of at least one dimension; Based on the travel status data of the at least one dimension and the predicted behavior of the user, the first recommendation information is generated and output.

18. The device according to claim 11, characterized in that The device further comprises: A second acquisition module is used to acquire the question information input by the user; a retrieval module, configured to retrieve information matching the question information from the memory bank when the question information is associated with the memory bank; the memory bank includes user favorite information and the at least one type of record fragment; The second output module is configured to generate and output answer information based on information matching the question information.

Images