Data generation method and data pushing method

Abstract

The invention provides a data generation method and a data pushing method.The data generation method comprises the steps that in response to a data access request sent by a user, a user identifier and user information of the user are obtained; the user information is processed within a preset time period to generate n levels of original data, the nth level of original data comprises the (n-1) th level of original data, and n is a positive integer; and generating target data based on the user identifier and the n-level original data.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data generation method and a data push method. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this application as set forth in the claims. The description herein is not to be construed as prior art simply because it is included in this section.

[0003] In the online education sector, as users increasingly demand personalized learning experiences, accurately matching users with learning tools and content has become a pain point for the industry. Currently, most education platforms have begun to utilize user behavior data to optimize recommendations.

[0004] However, existing technologies still have significant limitations. For example, data collection often focuses on superficial information such as click counts and usage duration, lacking in-depth capture of behaviors such as question types and essay editing traces, resulting in vague user profiles and difficulty in supporting accurate analysis. Recommendation logic often relies on fixed rules or lagging offline calculations, failing to respond in real time to changes in users' short-term learning needs, leading to insufficient timeliness of recommendation results. In terms of storage and querying, either reliance on relational databases results in slow response times during high-frequency queries, impacting user experience, or the pursuit of speed leads to simplified storage structures, causing a break in the connection between recommendation results and specific resources, making it difficult to quickly complete content. Furthermore, the granularity of personalization is coarse, mostly limited to broad category recommendations, failing to refine to the specific learning stage and knowledge point needs of users, resulting in prominent homogenization issues.

[0005] Therefore, this application urgently needs to propose a data generation method and a data push method that can solve the above-mentioned technical problems. Summary of the Invention

[0006] This application provides a data generation method and a data push method to improve the rationality of data processing and further enhance the accuracy and reliability of services.

[0007] One aspect of this application provides a data generation method, the method comprising: In response to a data access request sent by a user, the user's user identifier and user information are obtained; The user information is processed within a preset time period to generate n-level raw data, where the n-level raw data includes the (n-1)-level raw data, and n is a positive integer. Target data is generated based on the user identifier and the n-level raw data.

[0008] Furthermore, the step of obtaining the user's user identifier and user information in response to a data access request sent by the user includes: obtaining the user's user identifier in response to a data request sent by the user; and obtaining the user information based on a preset user information acquisition rule, wherein the preset user information acquisition rule includes at least one of the following: front-end page tracking points, back-end service logs, and database.

[0009] Furthermore, the step of processing the user information to generate n-level raw data within a preset time period includes: obtaining the number of data access requests sent by the user within a preset first time period based on the user identifier; when the number of requests is a positive integer, processing the user information to generate n-level raw data within a preset second time period and resetting the number of requests; wherein the second time period is later than the first time period.

[0010] Further, the step of generating target data based on the user identifier and the n-level raw data includes: obtaining the correlation degree of each level of raw data sequentially, starting with the first level of raw data, based on the n-level raw data; generating n-level raw data when the correlation degree of the raw data at the same level is lower than a preset value, wherein the number of n-level raw data is at least one; generating first data based on the n-level raw data and the (n-1)-level raw data, generating second data based on the user identifier and the n-level raw data; and generating target data based on the first data and the second data.

[0011] Furthermore, the method further includes: obtaining the number of requests for the data access request, and generating a second time period when the number of requests exceeds a first preset value; and / or obtaining the historical access frequency of the data access request, and determining the time period of the second preset value of the historical access frequency as the second time period.

[0012] Furthermore, the user information includes information content and information dimensions; wherein, the information content includes at least one of photo search, specialized learning, and auxiliary work, and the information dimensions include at least one of basic operation records, process data, result data, and time-series data.

[0013] In another aspect, this application provides a data push method, the method comprising: In response to a target data push request, obtain the weight of the target data; Based on the weight of the target data, the target data is pushed to the target area of ​​the target page; The target data is generated based on the data generation method described above.

[0014] Furthermore, the method also includes: acquiring the user's operation behavior on the target page, acquiring the (n-1)th level raw data based on the operation behavior and pushing it to the target page, until the user stops the operation behavior.

[0015] Another aspect of this application provides a data generation device, the device comprising: A response unit is used to obtain the user's user identifier and user information in response to a data access request sent by the user; The first generation unit is used to process the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes the (n-1)-level raw data, and n is a positive integer. The second generation unit is used to generate target data based on the user identifier and the n-level raw data.

[0016] In another aspect, this application provides a data push device, the device comprising: A response unit is used to obtain the weight of the target data in response to a target data push request; A push unit is used to push the target data to a target area of ​​a target page based on the weight of the target data; The target data is generated based on the data generation device described above.

[0017] This application proposes a data generation method and a data push method. The data generation method includes: in response to a data access request sent by a user, obtaining the user's user identifier and user information; processing the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes n-1-level raw data, and n is a positive integer; and generating target data based on the user identifier and the n-level raw data.

[0018] Based on the data generation method proposed above, the rationality of data processing is improved, while the accuracy and reliability of the service are also enhanced. On the one hand, from a data processing perspective, processing user information into n-level raw data with progressive relationships according to a preset time period can make the data present a clear hierarchical structure. This not only preserves the details of user information, but also achieves orderly integration of data through hierarchical inclusion relationships, which facilitates efficient subsequent data retrieval and in-depth analysis, and avoids the problem of low processing efficiency caused by messy data.

[0019] On the other hand, generating target data based on user identifiers and n-level raw data can ensure the unique correspondence between target data and users, reduce the risk of data confusion, and ensure that each piece of target data can be accurately associated with a specific user. This provides an accurate and structured foundation for subsequent services based on target data (such as personalized recommendations and information queries), thereby improving the overall service quality and user experience. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A schematic flowchart illustrating a data generation method provided in an embodiment of this application; Figure 2 A schematic flowchart illustrating a data push method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the architecture of a data generation device proposed in an embodiment of this application; Figure 4 This is a schematic diagram of the architecture of a data push device proposed in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing the solutions in the embodiments of this application; The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] In a typical configuration of this application, the terminal and the service network devices each include one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0024] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0025] Computer-readable media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer program instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only optical disc (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0026] This application provides a data generation method, which includes the following steps: Step S101: In response to the data access request sent by the user, obtain the user's user identifier and user information; Step S102: Process the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes the (n-1)-level raw data, and n is a positive integer; Step S103: Generate target data based on the user identifier and the n-level raw data.

[0027] In practical scenarios, the execution entity of this method can be a user device, or a device formed by integrating a user device and a network device through a network, or it can be an application running on the aforementioned devices. The user device includes, but is not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and wristbands. The network device includes, but is not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets, and can be used to implement some processing functions when setting an alarm clock. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets. Example 1

[0028] Figure 1 The present application illustrates a data generation method processing flow according to an embodiment of the present application, the method comprising at least the following processing steps: Step S101: In response to the data access request sent by the user, obtain the user's user identifier and user information; Step S102: Process the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes the (n-1)-level raw data, and n is a positive integer; Step S103: Generate target data based on the user identifier and the n-level raw data.

[0029] In one embodiment, the step of obtaining the user's user identifier and user information in response to a data access request sent by the user includes: obtaining the user's user identifier in response to a data request sent by the user; and obtaining the user information based on a preset user information acquisition rule, wherein the preset user information acquisition rule includes at least one of front-end page tracking points, back-end service logs, and database.

[0030] Specifically, user information can include in-depth data on more than 20 learning tools and content, such as single-question photography, full-page photo search, Chinese composition, English vocabulary, calculator, listening and learning, and Chinese poetry, from the user's recent n days.

[0031] The user information obtained based on the preset user information rules includes: based on the user device cuid dimension, obtaining the user's behavior on various learning tools and learning content pages, and reporting three types of data, including at least one from the front-end page tracking, back-end service logs, and the database.

[0032] In one embodiment, the step of processing the user information to generate n-level raw data within a preset time period includes: obtaining the number of data access requests sent by the user within a preset first time period based on the user identifier; when the number of requests is a positive integer, processing the user information to generate n-level raw data within a preset second time period and resetting the number of requests; wherein the second time period is later than the first time period.

[0033] In one embodiment, to improve the efficiency of generating raw data across levels, the value of n is preferably in the range of 2-5 and is an integer; it should be understood that this application does not limit the value of n and those skilled in the art can make a reasonable choice according to the actual situation.

[0034] It's important to understand that generating n-level raw data from user information within a preset time period can be achieved either by periodically generating n-level raw data based on the number of data access requests sent by the user, or by monitoring the data cycle of user data access requests (such as peak and off-peak periods) to process user information and generate n-level raw data. In practical applications, user information obtained through the above-mentioned user information acquisition rules is cached in the cache layer, undergoes t+1 offline calculation and aggregation, and the calculation results generated based on the user information are pushed to the user's corresponding CUID (client unique identifier) ​​device (including learning tools / learning content, etc.).

[0035] In one embodiment, generating target data based on the user identifier and the n-level raw data includes: obtaining the correlation degree of each level of raw data sequentially, starting with the first level of raw data, based on the n-level raw data; generating n-level raw data when the correlation degree of the raw data at the same level is lower than a preset value, wherein the number of n-level raw data is at least one; generating first data based on the n-level raw data and the (n-1)-level raw data, generating second data based on the user identifier and the n-level raw data; and generating target data based on the first data and the second data.

[0036] The correlation of the raw data can be dynamically calculated using a machine learning model, with user information as input. Specifically, the user information includes math learning videos and English learning videos. The math learning videos include the first summary of Chapter 1 (hereinafter referred to as Chapter 1.1), the second summary of Chapter 1 (hereinafter referred to as Chapter 1.2), and the first summary of Chapter 2 (hereinafter referred to as Chapter 2.1). The English learning videos include the first summary of Chapter 3 (hereinafter referred to as Chapter 3.1), the second summary of Chapter 3 (hereinafter referred to as Chapter 3.1), and the first summary of Chapter 4 (hereinafter referred to as Chapter 4.1). The first level 1 raw data is generated based on Chapters 1.1 and 1.2, the second level 1 raw data is generated based on Chapter 2.1, and the second level 1 raw data is generated based on the first and second level 1 raw data. The target data is generated based on the level 1 and level 2 raw data.

[0037] Specifically, by processing the raw data and storing it in a non-relational database, data storage and retrieval are facilitated. By calculating the correlation degree of the n-level raw data hierarchically, data at levels with low correlation can be accurately filtered out, generating at least one n-level raw data. This effectively achieves hierarchical refinement and precise extraction of data, avoiding interference from redundant data in the generation of target data. Based on this, first data is generated from the n-level and (n-1)-level raw data respectively, and second data is generated by combining the user identifier with the n-level raw data. The two are then merged to obtain the target data. This ensures the inherent logical connection between the data and strengthens the unique correspondence between the target data and the user. The generated target data possesses both a hierarchical structure and closely matches user characteristics, thereby improving the accuracy, relevance, and usability of the target data. This provides a high-quality data foundation for subsequent services based on the target data (such as personalized recommendations and information processing).

[0038] In one embodiment, the method further includes: obtaining the number of requests for the data access request, and generating a second time period when the number of requests exceeds a first preset value; and / or obtaining the historical access frequency of the data access request, and determining the time period of the second preset value of the historical access frequency as the second time period.

[0039] In this implementation, by dynamically adjusting the time period (generating a second time period), data processing can be more closely aligned with actual access pressure and user behavior patterns. When the number of requests exceeds a first preset value, generating a second time period can flexibly handle access peaks, avoiding data processing delays or excessive system load caused by concentrated requests, thus ensuring service stability. Furthermore, determining the second time period based on historical access frequency aligns with the periodic patterns of user access (such as peak hours or active periods), allowing for proactive optimization of data processing rhythm and improved resource allocation efficiency. This dynamic adjustment mechanism balances real-time access pressure and historical behavioral characteristics, enabling data processing to not only handle sudden traffic surges but also achieve predictive optimization based on user habits, ultimately improving the system's load-bearing capacity, resource utilization, and overall service response efficiency.

[0040] In one embodiment, the user information includes information content and information dimensions; wherein, the information content includes at least one of photo search, specialized learning, and auxiliary work, and the information dimensions include at least one of basic operation records, process data, result data, and time-series data.

[0041] Based on the data generation method proposed in this embodiment, by clearly dividing user information into information content and information dimensions, a refined and structured analysis of user learning behavior data is achieved, yielding significant beneficial effects. From the perspective of information content, it covers specific scenarios such as photo search, specialized learning, and auxiliary tools, accurately capturing user behavioral characteristics at different learning stages. For example, it tracks whether users rely on photo search to solve problems, strengthen weak areas through specialized learning, or improve efficiency with auxiliary tools, ensuring data collection covers the entire learning scenario. The information dimensions include basic operation records, process data, result data, and time-series data. This records not only what the user "did" (basic operations) but also tracks "how they did it" (process), "how well they did it" (result), and "when they did it" (time series), forming a complete behavioral trajectory chain. This multi-dimensional, full-scenario data division method transforms user information from fragmented pieces into structured data capable of supporting in-depth analysis. This lays a solid foundation for subsequently generating accurate n-level raw and target data, thereby improving the quality of data-driven personalized services, such as more accurately recommending tools or content tailored to user learning habits.

[0042] The data generation method proposed in this embodiment uses the user device CUID as the core identifier. First, it collects user behavior data from various learning tools and content pages across multiple dimensions. Specifically, it uses two real-time reporting methods: front-end event tracking and back-end service log tracking. Combined with the storage of some key behaviors in a MySQL database, a complete user behavior data collection system is formed. This multi-source data is then uniformly aggregated into a big data Hive platform. Data aggregation and analysis are completed through T+1 offline computation, generating the next day's user-facing (by CUID) sorting results for learning tools / content, as well as specific resource IDs under some categories. The computation results are stored in file format. Daily, the above offline data is processed via a cron job in the engineering service. The calculation results are synchronously updated to a non-relational data storage (non-relational database) according to the cuid dimension, achieving efficient storage of recommended data. When a user requests recommended learning data, the system directly reads the data with the corresponding key value from the non-relational database based on the device cuid, and returns the recommended learning tool category and learning content category with a millisecond response speed. For scenarios that require further acquisition of specific synchronous learning content IDs (such as the learning video ID, essay ID, and math knowledge point ID corresponding to the second week of the first-grade spring semester), the specific ID and configuration text are obtained by calling the configuration platform and the Plamides synchronous learning configuration backend. Then, the detailed data is requested from the corresponding resource platform or service through the ID, and finally the complete presentation of recommended content is completed. Example 2

[0043] Figure 2This application illustrates a data push method processing flow according to an embodiment of the present application, the method comprising: Step S201: In response to the target data push request, obtain the weight of the target data; Step S202: Push the target data to the target area of ​​the target page based on the weight of the target data; The target data is generated based on the data generation method described above.

[0044] In one implementation, in response to a target data push request, the weighting of the target data includes: dynamic weighting based on user behavior; specifically, extracting key indicators from the user's historical operation trajectory (corresponding to "basic operation records" and "process data") and converting them into weighting factors. For example: click depth: the more times a user clicks on a certain type of data and further views the details or performs interactions (such as collecting or sharing), the higher the weighting; dwell time: if the dwell time on the data page exceeds a threshold (such as 3 minutes), the weighting increases proportionally; if the user quickly leaves (such as <10 seconds), the weighting decreases; conversion path: if the data guides the user to complete a core behavior (such as jumping from "knowledge point recommendations" to "practice questions"), the data weight is added with conversion reward points.

[0045] In one implementation, in response to a target data push request, the weight of the target data is obtained by: static weighting based on data attributes. Specifically, a basic weight is preset according to the inherent characteristics of the data itself, and then adjusted in conjunction with business rules. Taking learning content as an example: Timeliness: New semester synchronous courses have a higher weight than previous content, and recently updated question banks have an added weight; Matching degree: The higher the matching degree with the user's current learning stage (e.g., first grade spring semester) and ability tags (e.g., weak in math geometry), the higher the weight value; Quality score: The data quality (e.g., video clarity, parsing completeness) evaluated by humans or algorithms is converted into a weight ratio (e.g., a quality score of 10 points corresponds to a weight of 1.0).

[0046] In one implementation, in response to a target data push request, the weighting of the target data includes: real-time weighting based on the scene context; specifically, dynamically adjusting the weights based on the user's current operation scenario (corresponding to "time-series data") to achieve "personalized adaptation." For example: time period association: on weekday evenings from 8-10 pm (peak homework time), the weights of data such as "scan and search for solutions" and "error analysis" are temporarily increased; on weekend mornings, the weights of "extended reading" and "interest courses" are increased; path association: if a user has just used the "English vocabulary" tool, the weights of subsequent related data such as "vocabulary memorization" and "example sentence expansion" are immediately increased; device association: mobile users are given priority in increasing the weights of adapted data such as "short video explanations" and "audio learning."

[0047] In one implementation, in response to a target data push request, obtaining the weight of the target data includes: comprehensive weighting based on an algorithm model; specifically, multi-dimensional features are fused through a machine learning model to output precise weights. For example: a logistic regression model is constructed, using user behavior (clicks, dwell time), data attributes (timeliness, matching degree), and scene features (time period, path) as independent variables, and "whether the user has completed effective learning" as the dependent variable, to train and obtain the weight coefficients of each feature; a collaborative filtering algorithm is used, referring to the preferences of similar users (such as those in the same class or with high overlap in the types of incorrect questions) for the same type of data, to correct the weight calculation of the target user (e.g., if the average weight of similar users for a certain video is 0.8, then the initial weight of the target user is fine-tuned based on this).

[0048] In one implementation, in response to a target data push request, obtaining the weight of the target data includes: rule calibration based on business objectives; specifically, overlaying a weight correction factor guided by the platform's strategy to balance user needs and business value. For example, if the platform is currently focusing on promoting "essay correction" tools, a basic weight bonus can be set for this type of data (such as a default weight × 1.2); for newly launched high-quality content (such as courses taught by renowned teachers), a temporary weight boost can be used to ensure initial exposure, and then the weight calculation will gradually revert to user behavior-driven calculation.

[0049] This embodiment proposes a data push method. By first obtaining the weight of the target data and then pushing the data to the target area of ​​the target page based on the weight, it is possible to achieve precise hierarchical display of recommended content. On the one hand, the weight mechanism can prioritize pushing data with higher value and stronger matching degree with users (such as high-weight core learning resources), ensuring that users first come into contact with the most relevant content and reducing interference from invalid information. On the other hand, targeted push combined with specific areas of the target page (such as placing high-weight data in the core visual area of ​​the page) can guide users' attention to focus on key content and improve the efficiency of reaching key information.

[0050] The "weighted sorting + regional targeting" combination proposed in this embodiment not only optimizes the priority of content display but also enhances the scenario adaptability of push notifications, ultimately improving the efficiency of users obtaining effective information and the overall user experience.

[0051] Furthermore, the method also includes: acquiring the user's operational behavior on the target page, acquiring the (n-1)th level raw data based on the operational behavior and pushing it to the target page, until the user stops the operational behavior. By continuously capturing the user's operational behavior on the target page and dynamically generating and pushing the (n-1)th level raw data, a real-time closed loop of "user behavior - data feedback" is formed. On the one hand, it can dynamically adjust the pushed content according to the user's real-time operations (such as clicks, pauses, interactions, etc.), making the subsequently pushed data more in line with the user's current needs and avoiding the lag of static recommendations; on the other hand, through the progressively layered push of raw data (tracing back from the target data to the (n-1)th level), it can gradually meet the user's deeper needs (such as gradually pushing detailed data such as specific knowledge points and related exercises from the recommended learning content categories), achieving precise "on-demand" service; at the same time, the mechanism of stopping the push only when the user stops the operation ensures the continuity of the service and avoids the interference of excessive push to the user, ultimately improving the timeliness and relevance of data push while enhancing the smoothness and satisfaction of the user's operating experience.

[0052] Based on the data push method proposed in this application (which is implemented based on the data generation method proposed in this application), performance data collection over one day showed that the average time to recommend learning content and tools to users was 14.1 milliseconds, demonstrating excellent performance. Meanwhile, the recommendation system showed positive growth in key metrics such as daily active users, next-day retention rate, and member conversion rate. Example 3

[0053] Figure 3 This application illustrates a data generation device according to an embodiment of the present application, the device comprising: A response unit is used to obtain the user's user identifier and user information in response to a data access request sent by the user; The first generation unit is used to process the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes the (n-1)-level raw data, and n is a positive integer. The second generation unit is used to generate target data based on the user identifier and the n-level raw data. Example 4

[0054] Figure 4 This application illustrates a data push device according to an embodiment of the present application. The device includes: A response unit is used to obtain the weight of the target data in response to a target data push request; A push unit is used to push the target data to a target area of ​​a target page based on the weight of the target data; The target data is generated based on the data generation device described above. Example 5

[0055] Based on the same inventive concept, this application also provides an electronic device. The method corresponding to the electronic device can be the data generation method and data push method in the foregoing embodiments, and its problem-solving principle is similar to that method. The electronic device provided in this application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the methods and / or technical solutions of the foregoing embodiments of this application.

[0056] The electronic device can be a user device, or a device formed by integrating user devices and network devices through a network, or it can be an application running on the aforementioned devices. The user device includes, but is not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and wristbands. The network device includes, but is not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets, and can be used to implement some processing functions when setting an alarm clock. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets.

[0057] Figure 5 The diagram illustrates the structure of an electronic device suitable for implementing the methods and / or technical solutions in the embodiments of this application. The device 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes based on a program stored in a Read-Only Memory (ROM) 502 or a program loaded from a storage portion 508 into a Random Access Memory (RAM) 503. The RAM 503 also stores various programs and data required for system operation. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An Input / Output (I / O) interface 505 is also connected to the bus 504.

[0058] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, touchscreen, microphone, infrared sensor, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), LED display, OLED display, etc., and speakers, etc.; a storage section 508 including one or more computer-readable media such as hard disk, optical disk, magnetic disk, semiconductor memory, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet.

[0059] In particular, the methods and / or embodiments in this application can be implemented as computer software programs. For example, the embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by the central processing unit (CPU) 501, it performs the functions defined in the methods of this application. Example 6

[0060] Another embodiment of this application provides a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of this application described above.

[0061] Specifically, this embodiment may employ any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or apparatus.

[0062] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, device, or apparatus.

[0063] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0064] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0065] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0066] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0067] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or page components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces, or indirect couplings or communication connections between devices or units, and may be electrical, mechanical, or other forms.

[0068] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0069] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0070] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0072] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

Claims

1. A data generation method, characterized in that, The method includes: In response to a data access request sent by a user, the user's user identifier and user information are obtained; The user information is processed within a preset time period to generate n-level raw data, where the n-level raw data includes the (n-1)-level raw data, and n is a positive integer. Target data is generated based on the user identifier and the n-level raw data.

2. The data generation method according to claim 1, characterized in that, The step of obtaining the user's user identifier and user information in response to a data access request sent by the user includes: In response to a data request sent by a user, obtain the user's user identifier; The user information is obtained based on a preset user information acquisition rule, which includes at least one of the following: front-end page tracking points, back-end service logs, and database.

3. The data generation method according to claim 1 or 2, characterized in that, The step of processing the user information to generate n-level raw data within a preset time period includes: The number of data access requests sent by the user within a preset first time period is obtained based on the user identifier; When the number of requests is a positive integer, the user information is processed to generate n-level raw data within a preset second time period, and the number of requests is reset. The second time period is later than the first time period.

4. The data generation method according to claim 3, characterized in that, The generation of target data based on the user identifier and the n-level raw data includes: Based on the n-level raw data, the correlation degree of each level of raw data is obtained sequentially, starting with the first-level raw data. When the correlation of the original data at the same level is lower than a preset value, then the original data at level n is generated, and the number of the original data at level n is at least one. First data is generated based on the nth level original data and the (n-1)th level original data, and second data is generated based on the user identifier and the nth level original data; Target data is generated based on the first data and the second data.

5. The data generation method according to claim 4, characterized in that, The method further includes: The number of data access requests is obtained, and when the number of requests exceeds a first preset value, a second time period is generated. And / or, Obtain the historical access frequency of the data access request, and determine the time period of the second preset value of the historical access frequency as the second time period.

6. The data generation method according to claim 1 or 5, characterized in that, The user information includes information content and information dimensions; wherein, the information content includes at least one of photo search, specialized learning, and auxiliary work, and the information dimensions include at least one of basic operation records, process data, result data, and time series data.

7. A data push method, characterized in that, The method includes: In response to a target data push request, obtain the weight of the target data; Based on the weight of the target data, the target data is pushed to the target area of ​​the target page; The target data is generated based on the data generation method according to any one of claims 1 to 6.

8. The data push method according to claim 7, characterized in that, The method further includes: The system acquires the user's actions on the target page, obtains the (n-1)th level raw data based on the actions, and pushes it to the target page until the user stops the actions.

9. A data generation device, characterized in that, The device includes: A response unit is used to obtain the user's user identifier and user information in response to a data access request sent by the user; The first generation unit is used to process the user information within a preset time period to generate n-level raw data, wherein the n-level raw data includes the (n-1)-level raw data, and n is a positive integer. The second generation unit is used to generate target data based on the user identifier and the n-level raw data.

10. A data push device, characterized in that, The device includes: A response unit is used to obtain the weight of the target data in response to a target data push request; A push unit is used to push the target data to a target area of ​​a target page based on the weight of the target data; The target data is generated based on the data generation device of claim 9.

Images