Automatic information generation method and related device

Abstract

The invention provides an automatic information generation method and a related device, and relates to the technical field of software, and the method comprises the steps: receiving an information request of a client, the information request comprising version attributes; determining a version generation rule corresponding to the version attribute, and screening original information content meeting the version generation rule from the data source; and obtaining user behavior information of the client, screening target information content matched with the user behavior information from the original information content, and outputting the target information content to the client. In the application, on one hand, business personnel only need to configure version attributes and version generation rules of different businesses at the management end to quickly generate the information content, massive development is not needed, and the workload is reduced; and on the other hand, information contents can be displayed according to user behaviors on the basis of meeting business requirements, so that user interest points can be effectively fit, and user experience is improved.

Description

Technical Field

[0001] This application relates to the field of software technology, and in particular to a method and apparatus for automatically generating information. Background Technology

[0002] Currently, users often need to browse various information (such as financial information, real estate information, etc.) in applications to understand market conditions.

[0003] However, before information is generated, business personnel often need to manually configure different content generation rules frequently based on market trends and business needs. Moreover, the generated results are usually displayed according to time or fixed sorting rules, which cannot meet the user's interests. Summary of the Invention

[0004] In view of the above problems, this application provides a method and related apparatus for automatically generating information, so as to quickly display information content that meets user needs by configuring page position attributes and their generation rules. The specific solution is as follows:

[0005] The first aspect of this application provides a method for automatically generating information, the method comprising:

[0006] Receive information requests from clients, wherein the information requests include page position attributes;

[0007] Determine the page position generation rules corresponding to the page position attributes, and filter the original information content that meets the page position generation rules from the data source;

[0008] The system obtains user behavior information from the client, filters target information content that matches the user behavior information from the original information content, and outputs it to the client.

[0009] In one possible implementation, the page position attribute includes a combined page position attribute, and the page position generation rule corresponding to the page position attribute includes:

[0010] Determine multiple page slot types corresponding to the combined page slot attributes;

[0011] Obtain the page generation rules for each of the multiple page types.

[0012] In one possible implementation, filtering the original information content from the data source that satisfies the page layout generation rules includes:

[0013] Obtain configuration information for different data objects in the data source. The configuration information includes metadata and category tags. The category tags are obtained by pre-classifying the data objects.

[0014] Target data objects whose metadata and category tags meet the page layout generation rules are filtered from the data source, and the data content of the target data objects is loaded as the original information content.

[0015] In one possible implementation, the step of filtering target information content that matches the user behavior information from the original information content and outputting it to the client includes:

[0016] Filter the first target information content that matches the user behavior information from the original information content;

[0017] Retrieve the second target information content that is highlighted and pinned at the top;

[0018] The first target information content and the second target information content are merged and deduplicated before being output to the client.

[0019] In one possible implementation, the step of filtering the first target information content from the original information content that matches the user behavior information includes:

[0020] Using the user behavior information as the state and the recommended information content as the action, the first target information content is obtained by filtering from the original information content through a reinforcement learning model.

[0021] In one possible implementation, the step of merging and deduplicating the first target information content and the second target information content before outputting them to the client includes:

[0022] The first target information content and the second target information content are merged and deduplicated to obtain the third target information content;

[0023] Obtain key risk fields;

[0024] The information content containing the risk key field in the third target information content is removed to obtain the fourth target information content, and the fourth target information content is output to the client.

[0025] A second aspect of this application provides an automatic information generation device, the automatic information generation device comprising:

[0026] The request receiving module is used to receive information requests from clients, wherein the information requests contain page position attributes;

[0027] The information generation module is used to determine the page position generation rules corresponding to the page position attributes, and to filter the original information content that meets the page position generation rules from the data source; to obtain the user behavior information of the client, to filter the target information content that matches the user behavior information from the original information content, and to output it to the client.

[0028] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the information automatic generation method of the first aspect or any implementation thereof.

[0029] A fourth aspect of this application provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0030] The memory is used to store computer programs;

[0031] The processor is used to execute the computer program so that the electronic device can implement the information automatic generation method of the first aspect or any implementation thereof.

[0032] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the information automatic generation method described in the first aspect or any implementation thereof.

[0033] By employing the above technical solution, this application provides an automatic information generation method and related apparatus, comprising: receiving an information request from a client, the information request including a page position attribute; determining the page position generation rule corresponding to the page position attribute, and filtering original information content that meets the page position generation rule from a data source; obtaining user behavior information from the client, filtering target information content that matches the user behavior information from the original information content, and outputting it to the client. This application can determine the page position generation rule based on the page position attribute when the client requests it, and obtain information content from the data source through two filtering processes using the page position generation rule and user behavior information before outputting it to the client. In this application, on the one hand, business personnel only need to configure the page position attributes and page position generation rules for different businesses on the management end to quickly generate information content, without requiring extensive development and reducing workload; on the other hand, while meeting business requirements, information content can be displayed based on user behavior, which can effectively align with user interests and improve user experience. Attached Figure Description

[0034] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0035] Figure 1 A flowchart illustrating an automatic information generation method provided in this application embodiment;

[0036] Figure 2 This is a partial flowchart illustrating an automatic information generation method provided in an embodiment of this application;

[0037] Figure 3 This is another schematic flowchart of an automatic information generation method provided in an embodiment of this application;

[0038] Figure 4 This is another schematic flowchart of an automatic information generation method provided in an embodiment of this application;

[0039] Figure 5 This is another schematic flowchart of an automatic information generation method provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the structure of an automatic information generation device provided in an embodiment of this application;

[0041] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0042] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0043] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0044] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0045] To facilitate understanding of this application, the relevant concepts involved in this application will be explained below:

[0046] News: This refers to information with a specific scope and purpose, through which users can learn about market trends, such as financial news or real estate news. Display methods include: images, articles, videos, etc.

[0047] Page layout: A combination of specific information, such as: article layout (a layout composed of several articles), image layout (a layout composed of several images), and video layout (a layout composed of several videos).

[0048] Page layout combination: Composed of different page layouts, such as a text and image article layout which is formed by combining article layouts and image layouts.

[0049] Page placement rules: Rules established based on page placement, such as article page placement rules (algorithm rules established based on articles as the data source).

[0050] Polymorphic models: Through contrastive learning, images and text are mapped to the same feature space, enabling cross-modal understanding and classification. The core idea is to pre-train on large-scale image-text pairs, allowing the model to understand the semantic relationships between images and text. It can process images, videos, and text simultaneously, making it ideal for scenarios requiring the classification of multiple data types.

[0051] Reinforcement learning is a machine learning method that uses an agent to interact with its environment and learn the optimal strategy through trial and error. In content recommendation systems, reinforcement learning can be used to dynamically adjust recommendation strategies to maximize user satisfaction or platform goals (such as click-through rates, purchase rates, etc.).

[0052] Currently, before generating news and information, business personnel often need to manually configure different content generation rules frequently based on market trends and business needs. Furthermore, the generated results are generally displayed according to time or fixed sorting rules, failing to capture users' interests promptly. In addition, content generation rules for different news items require continuous development, testing, and deployment, resulting in high personnel costs and long deployment cycles. This leads to low market sensitivity and significant lag.

[0053] To address the aforementioned problems, embodiments of this application provide a method for automatically generating information. The method for automatically generating information according to embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0054] See Figure 1 , Figure 1 This is a flowchart illustrating an automatic information generation method provided in an embodiment of this application. Figure 1 As shown in the embodiment of this application, an automatic information generation method is provided, which can be applied to the server. The information generation method includes steps S101 to S103, which are described in detail below.

[0055] S101 receives information requests from clients, which include page position attributes.

[0056] In this embodiment, a user accesses a news application through a client, generating a news request during the access process and sending it to the server. The server receives the news request from the client, parses it to obtain the section attributes, which may include section name, section identifier, and section category, uniquely identifying the section to which it belongs. Therefore, the section attributes in the news request can determine at least one section contained in the news to be generated.

[0057] S102, determine the page position generation rules corresponding to the page position attributes, and filter the original information content that meets the page position generation rules from the data source.

[0058] In this embodiment of the application, business personnel can pre-establish a forum position table and a forum position generation rule table for the same forum position in the database through the management terminal. The forum position table records information such as the forum position name, forum position identifier, and forum position category of the forum position. The forum position generation rule table records information such as the rule name, rule identifier, rule content, and rule category of the forum position generation rule corresponding to the forum position.

[0059] The server can determine at least one section in the information to be generated based on the section attribute in the information request. For each section, it can determine the rule content of the corresponding section generation rule table, and then filter information content that meets the rule content from the data source according to the rule content of the section generation rule to obtain the original information content. It should be noted that the data source can include articles, images, videos, etc.

[0060] In one possible implementation, multiple page positions in the news to be generated can belong to the same page position type, such as all being article page positions or all being image page positions. Of course, multiple page positions in the news to be generated can also belong to different page position types, such as a combination of article and image page positions. In this case, the page position attributes include combined page position attributes, which can contain information such as page position names, page position identifiers, and page position types for multiple sets of page positions. This uniquely identifies page positions of multiple page position types in the news to be generated, thereby determining the page position generation rules corresponding to multiple page position types. See also Figure 2 , Figure 2 This is a partial flowchart illustrating an automatic information generation method provided in an embodiment of this application. Figure 2 As shown in the embodiment of this application, an automatic information generation method is provided, wherein step S102, "determining the page position generation rule corresponding to the page position attribute", may include steps S201 to S202, which are described in detail below.

[0061] S201, determine multiple page type corresponding to the combined page attribute.

[0062] In this embodiment of the application, the server can determine multiple page positions of different page position types contained in the information to be generated based on the combined page position attributes in the information request.

[0063] S202, obtain the page generation rules for each of the multiple page types.

[0064] In this embodiment of the application, for each type of forum section, the server can determine the rule content of the forum section generation rule corresponding to that section based on the section section generation rule of that section. Thus, the server can obtain the rule content of multiple section section generation rules corresponding to different section section types.

[0065] It should be noted that business personnel first add a specific section type in the management interface based on actual business needs, and then add its corresponding section generation rules. Specifically, when configuring combined section attributes for information, such as configuring article section types and image section types, the steps are as follows: 1) Create an article section type pending review section p11, generate an official section p1 after the review is successful, and create the corresponding pending review section generation rule u11, generate an official section generation rule u1 after the review is successful; 2) Create an image section type pending review section p22, generate an official section p2 after the review is successful, and create the corresponding pending review section generation rule u22, generate an official section generation rule u2 after the review is successful; 3) Combine the official section p1 and the official section p2 into a pending review combined section p33, generate the official combined section p3 after the review is successful; 4) Click preview, query the results returned by the server interface, and if they meet expectations, provide them to the front end for display after approval. Therefore, when the client's information request includes the combined page position p3 attribute, the formal page position generation rule u1 and formal page position generation rule u2 can be determined by determining the formal page positions p1 and p2 that make up it.

[0066] In one possible implementation, business users can pre-create a data source configuration table in the database through the management interface. This table records the configuration information of different data objects in the data source. The server constructs the original news content by filtering the configuration information in the table that meets the page layout generation rules. See also Figure 3 , Figure 3 This is another schematic flowchart illustrating an automatic information generation method provided in an embodiment of this application. For example... Figure 3As shown in the embodiment of this application, an automatic information generation method is provided, wherein step S102, "filtering original information content that meets the page layout generation rules from the data source", may include steps S301 to S302, which are described in detail below.

[0067] S301, obtain the configuration information of different data objects in the data source. The configuration information includes metadata and category labels. The category labels are obtained by pre-classifying the data objects.

[0068] In this embodiment, the server can query the configuration table of the data source from the database to obtain the configuration information of different data objects in the data source. This configuration information includes the metadata of the data object and its category tag. The category tag is obtained by the management end through pre-classification of the data object using a polymorphic model. To better understand the category tags in this embodiment, the following are examples of classifying data objects of image, video, and article types respectively:

[0069] Image Types: Classified according to image content. They can be categorized as follows: 1) Natural Landscapes: Mountains, Seas, Forests, Deserts, Grasslands, etc.; 2) Animals: Cats, Dogs, Birds, Fish, Tigers, Elephants, etc.; 3) Transportation: Cars, Bicycles, Airplanes, Trains, Ships, etc.; 4) Architecture: Houses, Bridges, Churches, Skyscrapers, Pyramids, etc.; 5) Everyday Items: Cell Phones, Computers, Books, Cups, Keys, etc.; 6) Food: Apples, Pizza, Sushi, Cakes, Hamburgers, etc.; 7) Human Actions: Running, Jumping, Swimming, Dancing, Sleeping, etc.; 8) Weather Phenomena: Sunny Days, Rainy Days, Snowy Days, Foggy Days, Thunderstorms, etc.; 9) Art Styles: Oil Paintings, Watercolors, Sketches, Photography, Sculptures, etc.; 10) Sports: Basketball, Football, Swimming, Running, Yoga, etc.

[0070] Video Types: Classification is achieved by extracting keyframes from videos or generating video descriptions. Specifically, videos can be converted into image sequences, and then feature extraction and classification are performed using polymorphic models. Categories include: 1) Sports: basketball, football, badminton, swimming, running, etc.; 2) Animals: cats, dogs, birds, fish, elephants, etc.; 3) Nature: mountains, seas, forests, deserts, rivers, etc.; 4) Technology: robots, drones, computers, mobile phones, artificial intelligence, etc.; 5) Transportation: cars, trains, airplanes, bicycles, ships, etc.; 6) Entertainment: movies, music, dance, games, drama, etc.; 7) Education: classrooms, lectures, experiments, learning, teaching, etc.; 8) Food: cooking, baking, food preparation, restaurants, ingredients, etc.; 9) Architecture: high-rise buildings, bridges, parks, museums, residences, etc.; 10) Daily Life: cooking, cleaning, shopping, walking, working, etc.

[0071] Article type: Classified according to article content. A polymorphic model text encoder can be used to extract text features, which can then be used for classification. The categories can be divided as follows: 1) News: Political news, economic news, science and technology news, sports news, entertainment news, social news; 2) Science and technology: Artificial intelligence, blockchain, the Internet, robotics, 5G technology, green energy; 3) Entertainment: Film reviews, music reviews, TV series and variety shows, celebrity gossip, game reviews, fashion trends; 4) Health: Health and wellness, medical information, mental health, sports and fitness, nutrition, disease prevention and control; 5) Finance: Stock market, fund investment, insurance and financial management, economic analysis, financial market, foreign exchange trading; 6) Education: Educational policies, academic research, exam preparation, campus life, educational technology, vocational education; 7) Lifestyle: Family life, travel guides, food and cooking, interior design, parenting education, health and wellness; 8) Law: Criminal cases, civil disputes, laws and regulations, intellectual property, labor law, commercial law; 9) Military: Military news, weapons and equipment, military history, national defense policies, military exercises, military technology; 10) Culture: Literary works, art exhibitions, history and culture, folk customs, film art, music art.

[0072] S302: Filter target data objects from the data source whose metadata and category tags meet the page layout generation rules, and load the data content of the target data objects as the original information content.

[0073] In this embodiment, for the metadata and category tags of different data objects in the data source, the server can determine whether the metadata and category tags of each data object meet the page layout generation rules, and filter out at least one data object that meets the page layout generation rules as the target data object. Furthermore, the server can load the data content of the target data object from the data source and use the loaded data content as the original information content.

[0074] S103: Obtain user behavior information from the client, filter target information content that matches the user behavior information from the original information content, and output it to the client.

[0075] In this embodiment, the server obtains user behavior information, such as interest tags, browsing duration, and published content, from the client's historical operation records to acquire user profile information. The server then filters content matching the user profile from the original information content as target information and outputs this target information to the client. The client then renders and displays the target information returned by the server. It should be noted that existing technologies can be used to create user profiles based on user behavior information, and this embodiment will not elaborate on these techniques.

[0076] In one possible implementation, business users pre-create a configuration table in the database using the management interface to specify the pinned news content. This table records the news content marked for pinning. The server then needs to combine this pinned news content with the information output to the client. See also... Figure 4 , Figure 4 This is another schematic flowchart illustrating an automatic information generation method provided in an embodiment of this application. For example... Figure 4 As shown in the embodiment of this application, an automatic information generation method is provided, wherein step S103, "filtering target information content that matches user behavior information from the original information content and outputting it to the client", may include steps S401 to S403, which are described in detail below.

[0077] S401: Filter the primary target information content from the original information content that matches the user behavior information.

[0078] In this embodiment of the application, the server can obtain user profile information based on user behavior information, and then use the user profile information to search for the first target information content in the original information content.

[0079] In one possible implementation, a reinforcement learning model can be used to display first target information content in descending order of user interest. To this end, an embodiment of this application provides an automatic information generation method, wherein step S401, "filtering first target information content that matches user behavior information from the original information content," can take the following steps:

[0080] Using user behavior information as the state and recommended information content as the action, a reinforcement learning model is used to filter out the first target information content from the original information content.

[0081] In this embodiment, the state and action space of the reinforcement learning model can be defined to determine the factors to be considered and the recommendation strategies to be adopted during recommendation. For this purpose, user behavior information can be used as the state (e.g., interest tags, current time, article category, etc.), and recommended information content (e.g., recommending different articles) can be used as the action. The reinforcement learning model then filters and obtains the first target information content from the original information content. Of course, in practical applications, a reward mechanism can also be set for the reinforcement learning model to determine how to measure the recommendation effect, such as whether the user clicks to read, the reading time, etc., and a deep reinforcement learning algorithm can be selected for continuous learning. Through interaction with the environment, the agent of the reinforcement learning model continuously adjusts its strategy to maximize the cumulative reward.

[0082] S402, retrieve the second target information content that is marked and pinned to the top.

[0083] In this embodiment of the application, the server retrieves the information content marked and pinned by the business personnel from the database as the second target information content.

[0084] S403: Merge the first target information content and the second target information content, remove duplicates, and output the result to the client.

[0085] In this embodiment of the application, the first target information content and the second target information content are merged and deduplicated before being output to the client, thereby ensuring the integrity and validity of the target information content.

[0086] In one possible implementation, business personnel create a configuration table for key risk fields in the database through the management interface. This table records the key risk fields for the current business. The server then needs to filter the information content based on these key risk fields before outputting it to the client. See also... Figure 5 , Figure 5 This is another schematic flowchart illustrating an automatic information generation method provided in an embodiment of this application. For example... Figure 5 As shown in the embodiment of this application, an automatic information generation method is provided, wherein step S403, "merging and deduplicating the first target information content and the second target information content and then outputting it to the client", may include steps S501 to S503, which are described in detail below.

[0087] S501, merge and deduplicate the first target information content and the second target information content to obtain the third target information content.

[0088] In this embodiment of the application, the server merges the first target information content and the second target information content, and then removes duplicates to obtain the third target information content.

[0089] S502, retrieve key risk fields.

[0090] In this embodiment of the application, the server obtains the risk key fields from the database.

[0091] S503, remove the information content containing risk key fields from the third target information content to obtain the fourth target information content, and output the fourth target information content to the client.

[0092] In this embodiment of the application, the server detects whether all information content in the third target information content contains risk key fields, removes the information content containing risk keywords to obtain the fourth information content, and outputs the fourth information content to the client.

[0093] It should be noted that in this application, business personnel can perform operations such as adding, deleting, modifying, and querying all data tables in the database through the management terminal. The database supports the management terminal to manage page position attributes, page position generation rules, top news content, risk keywords, etc. through the interface.

[0094] Based on the above description, the automatic information generation method provided in this application supports business personnel in customizing the display of complex information. It establishes different page generation rules for different page positions, generates information content based on these rules, and then recommends and sorts information based on user behavior. Simultaneously, it filters risky key fields, making the information display more accurate, the business more secure, and the user interest higher. Business personnel can generate different information content in real time by modifying the page generation rules, solving the problem of long deployment cycles and providing greater responsiveness and automation. This application has the following advantages:

[0095] 1) Assist business personnel in the entire process of generating, managing, filtering, previewing, and publishing information content, reducing their workload; 2) Introduce polymorphic model training for data classification, making the data source more granular and the data classification more accurate and thorough; 3) Combine information content with user behavior recommendations, and based on meeting specific business rules, prioritize information that users are most interested in, effectively matching user interests and improving user experience; 4) For different business rules, business personnel only need to configure different page attributes and page generation rules on the management terminal and quickly display content, without needing to do a lot of development, reducing workload and lowering labor costs.

[0096] The above describes an automatic information generation method provided by the embodiments of this application. The following will describe the apparatus for performing the above-described automatic information generation method.

[0097] See Figure 6 , Figure 6 This is a schematic diagram of the structure of an automatic information generation device provided in an embodiment of this application. Figure 6 As shown in the embodiment of this application, an automatic information generation device includes:

[0098] The request receiving module 601 is used to receive information requests from clients, and the information requests contain page position attributes;

[0099] The information generation module 602 is used to determine the page position generation rules corresponding to the page position attributes, and to filter the original information content that meets the page position generation rules from the data source; to obtain user behavior information from the client, to filter the target information content that matches the user behavior information from the original information content, and to output it to the client.

[0100] In one possible implementation, the page placement attribute includes a combined page placement attribute, and an information generation module 602 is used to determine the page placement generation rule corresponding to the page placement attribute, specifically for:

[0101] Identify multiple page layout types corresponding to the combined page layout attributes; obtain the page layout generation rules for each of the multiple page layout types.

[0102] In one possible implementation, the information generation module 602, used to filter original information content that meets the page layout generation rules from the data source, is specifically used for:

[0103] Obtain configuration information for different data objects in the data source. The configuration information includes metadata and category tags. The category tags are obtained by pre-classifying the data objects.

[0104] Filter target data objects from the data source that meet the page layout generation rules based on metadata and category tags, and load the data content of the target data objects as the original information content.

[0105] In one possible implementation, the information generation module 602, used to filter target information content that matches user behavior information from the original information content and output it to the client, is specifically used for:

[0106] The process involves: filtering the first target information content from the original information content that matches the user's behavior information; obtaining the second target information content that is marked and pinned; merging the first and second target information content, removing duplicates, and then outputting the result to the client.

[0107] In one possible implementation, the information generation module 602, used to filter first target information content that matches user behavior information from the original information content, is specifically used for:

[0108] Using user behavior information as the state and recommended information content as the action, a reinforcement learning model is used to filter out the first target information content from the original information content.

[0109] In one possible implementation, the information generation module 602, which merges and deduplicates the first target information content and the second target information content before outputting it to the client, is specifically used for:

[0110] The first and second target information contents are merged and deduplicated to obtain the third target information content; the risk key fields are obtained; the information content containing the risk key fields in the third target information content is removed to obtain the fourth target information content, and the fourth target information content is output to the client.

[0111] It should be noted that the detailed functions of each module in the embodiments of this application can be found in the corresponding disclosure of the above-mentioned automatic information generation method embodiments, and will not be repeated here.

[0112] This application also provides an electronic device in its embodiments. See also... Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device in this embodiment may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0113] like Figure 7 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. When the electronic device is powered on, the RAM 703 also stores various programs and data required for the operation of the electronic device. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0114] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, memory cards, hard drives, etc.; and communication devices 709. Communication device 709 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0115] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the information automatic generation methods provided in this application.

[0116] This application also provides a computer-readable storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the information automatic generation methods provided in this application.

[0117] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0118] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0119] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0120] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A method for automatically generating information, characterized in that, The automatic information generation method includes: Receive information requests from clients, wherein the information requests include page position attributes; Determine the page position generation rules corresponding to the page position attributes, and filter the original information content that meets the page position generation rules from the data source; The system obtains user behavior information from the client, filters target information content that matches the user behavior information from the original information content, and outputs it to the client.

2. The information automatic generation method according to claim 1, characterized in that, The page placement attributes include combined page placement attributes, and the page placement generation rules corresponding to the page placement attributes include: Determine multiple page slot types corresponding to the combined page slot attributes; Obtain the page generation rules for each of the multiple page types.

3. The information automatic generation method according to claim 1, characterized in that, The step of filtering original information content from the data source that meets the page layout generation rules includes: Obtain configuration information for different data objects in the data source. The configuration information includes metadata and category tags. The category tags are obtained by pre-classifying the data objects. Target data objects whose metadata and category tags meet the page layout generation rules are filtered from the data source, and the data content of the target data objects is loaded as the original information content.

4. The information automatic generation method according to claim 1, characterized in that, The step of filtering target information content that matches the user behavior information from the original information content and outputting it to the client includes: Filter the first target information content that matches the user behavior information from the original information content; Retrieve the second target information content that is highlighted and pinned at the top; The first target information content and the second target information content are merged and deduplicated before being output to the client.

5. The information automatic generation method according to claim 4, characterized in that, The step of filtering the first target information content from the original information content that matches the user behavior information includes: Using the user behavior information as the state and the recommended information content as the action, the first target information content is obtained by filtering from the original information content through a reinforcement learning model.

6. The information automatic generation method according to claim 4, characterized in that, The step of merging and deduplicating the first target information content and the second target information content before outputting them to the client includes: The first target information content and the second target information content are merged and deduplicated to obtain the third target information content; Obtain key risk fields; The information content containing the risk key field in the third target information content is removed to obtain the fourth target information content, and the fourth target information content is output to the client.

7. An automatic information generation device, characterized in that, The automatic information generation device includes: The request receiving module is used to receive information requests from clients, wherein the information requests contain page position attributes; The information generation module is used to determine the page position generation rules corresponding to the page position attributes, and to filter the original information content that meets the page position generation rules from the data source; to obtain the user behavior information of the client, to filter the target information content that matches the user behavior information from the original information content, and to output it to the client.

8. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the information automatic generation method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the information automatic generation method as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the information automatic generation method as described in any one of claims 1 to 6.

Images