Data processing method and device, computer equipment and readable storage medium
By analyzing the usage records and operational data of application functions, the probability of future use can be predicted, and resource allocation can be dynamically adjusted to solve the problem of mobile phone storage space occupation, improve operating efficiency, and reduce user operations.
Patent Information
- Application Number
- CN202411265303.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2025-01-07
AI Technical Summary
Existing memory cleaning software requires frequent manual operation by users, which fails to effectively solve the problem of mobile phone storage space occupation, resulting in slower running speed and frequent system prompts.
By analyzing the usage records and operational data of each function in the application, the probability of use in future periods can be predicted, resource allocation can be dynamically adjusted, and functional operation data can be automatically cleaned up or retained to achieve hierarchical and layered data management.
It improves mobile phone operating efficiency, reduces data storage burden, reduces the frequency of manual memory clearing by users, and achieves intelligent memory management.
Smart Images
Figure CN119271515A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, apparatus, computer device and readable storage medium. Background Art
[0002] In today's era, mobile phones are the main tool for daily communication, and their service life has become one of the important performance indicators that consumers consider when purchasing. However, with the increasing richness and functionality of mobile phone applications, while users enjoy convenient services, they also face the challenge of mobile phone storage space being occupied by a large amount of data.
[0003] Specifically, feature-rich applications will accumulate a large amount of data, such as pictures, audio, and video, during use. Although these data provide users with a rich user experience, the long-term idle and discarded data will occupy a large amount of mobile phone memory. As the mobile phone memory usage increases, the running speed of the mobile phone will gradually slow down, and even freeze. In addition, the mobile phone system will frequently prompt users to clean up the memory to maintain the normal operation of the phone.
[0004] The existing solution is that the user downloads memory cleaning software, starts and runs the corresponding memory cleaning program to free up memory space.
[0005] However, the above solutions fail to effectively solve the problem fundamentally, and users need to repeatedly click to clean up data in subsequent use, which causes a burden. Summary of the invention
[0006] Based on this, it is necessary to provide a data processing method, device, computer equipment and readable storage medium that can realize intelligent data cleaning in response to the above technical problems.
[0007] In a first aspect, the present application provides a data processing method, the method comprising:
[0008] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0009] Analyze the function usage records of each function item in the application during the target period to obtain the usage probability of each function item in the future period;
[0010] The function operation data of each function item is processed according to each usage probability.
[0011] In one embodiment, the function operation data of each function item is processed according to each usage probability, including:
[0012] For each function item, if the usage probability of the function item is greater than or equal to the first probability threshold, retaining the function operation data of the function item;
[0013] If the usage probability of the function item is less than the first probability threshold and greater than the second probability threshold, the function operation data of the function item is subjected to pending confirmation processing;
[0014] If the usage probability of the function item is less than the second probability threshold, cleaning the function operation data of the function item;
[0015] The second probability threshold is smaller than the first probability threshold.
[0016] In one embodiment, the function operation data of the function item is subjected to pending confirmation processing, including:
[0017] Sending the function operation data of the function item and the pending confirmation indication generated for the function item to the confirming party;
[0018] The response message returned by the confirmation indication is processed according to the confirmation policy, and the function operation data of the function item is cleaned up or retained.
[0019] In one embodiment, the function usage records of each function item in the application program within the target period are analyzed to obtain the usage probability of each function item in the future period, including:
[0020] Convert the function usage records of each function item into word vectors;
[0021] The word vector is input into the prediction model to obtain the usage probability of each function item output by the prediction model in the future period.
[0022] In one embodiment, the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0023] In one embodiment, converting the function usage record of each function item into a word vector includes:
[0024] For each target user, determine the analysis window corresponding to the target user based on the target user's behavioral characteristics during the target period;
[0025] The analysis window corresponding to the target user is used to convert the function usage records of each function item corresponding to the target user into a word vector.
[0026] In a second aspect, the present application further provides a data processing device, comprising:
[0027] An acquisition module is used to acquire the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0028] The probability prediction module is used to analyze the function usage records of each function item in the application within the target period to obtain the usage probability of each function item in the future period;
[0029] The data processing module is used to process the function operation data of each function item according to each usage probability.
[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0031] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0032] Analyze the function usage records of each function item in the application during the target period to obtain the usage probability of each function item in the future period;
[0033] The function operation data of each function item is processed according to each usage probability.
[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:
[0035] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0036] Analyze the function usage records of each function item in the application during the target period to obtain the usage probability of each function item in the future period;
[0037] The function operation data of each function item is processed according to each usage probability.
[0038] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0039] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0040] Analyze the function usage records of each function item in the application during the target period to obtain the usage probability of each function item in the future period;
[0041] The function operation data of each function item is processed according to each usage probability.
[0042] The above-mentioned data processing method, device, computer equipment and readable storage medium, the present application collects the usage frequency, usage time information and interaction relationship between each function item in the target time period, realizes in-depth analysis of the acquired data, and predicts the usage probability of each function item in the future time period; according to the usage probability of the function item, the functional operation data of each function item is processed, with the purpose of dynamically adjusting computing resources, storage resources and network resources, etc., to ensure that high-frequency functional items obtain sufficient resource support, improve overall operating efficiency, clean up unimportant or redundant functional operation data, reduce the data storage burden, and realize hierarchical management of data. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0044] FIG1 is a schematic flow chart of a data processing method in one embodiment;
[0045] FIG2 is a schematic diagram of a flow chart of steps for processing function operation data of each function item in one embodiment;
[0046] FIG3 is a flow chart of the steps of obtaining the usage probability of each function item in a future period in one embodiment;
[0047] FIG4 is a flow chart showing the steps of converting the function usage records of each function item corresponding to a target user into a word vector in one embodiment;
[0048] FIG5 is a block diagram of a data processing device in one embodiment;
[0049] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] In an exemplary embodiment, as shown in FIG1 , a data processing method is provided, which is described by taking the method applied to a computer device as an example, and includes the following S101 to S103. Among them:
[0052] S101, obtaining function usage records and function operation data of each function item in the application within a target period.
[0053] It is understandable that there are multiple applications installed in the target device, and each application corresponds to at least one function item; a function item refers to a module or component in an application that has a specific function or service, and they are the basic units for implementing various business logics and operations of the application. For example, a function item can be necessary for the operation of the application, such as login, registration, settings, etc.; a function item can also be directly related to the main business logic of the application, such as product browsing, purchase, payment, etc. in an e-commerce application; further, a function item can also be used to support the normal operation of the application, such as data synchronization, cache management, logging, etc.
[0054] The function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target time period, and the interaction relationship between the function item and other function items.
[0055] It is understood that the function usage record includes:
[0056] 1. The frequency of use of the function item during the target period can include: 1) Number of calls: the total number of times the function item is called by the user or system during the target period. 2) User distribution: if possible, record the number of different users who call the function item and their usage habits (e.g. frequent use, occasional use, etc.).
[0057] 2. Information on the usage time of a function item during the target time period, which may include: 1) Start time and end time: the specific start time and end time of each function item being called. This helps analyze the usage period and user activity of the function item. 2) Duration: the duration of the function item being used, that is, the difference between the end time and the start time. This helps understand the time users spend on the function item. 3) Time distribution: Statistics are collected on a daily, hourly or finer time scale to reveal the time pattern and trend of function item usage.
[0058] 3. The interactive relationship between function items and other function items can include: 1) Call chain: record the call sequence and relationship between function items to form a call chain. This helps to understand the business process of the application and the dependency between function items. 2) Contextual relationship: analyze the user's behavior before and after calling the function item to reveal the user's behavior path and habits. 3) Association analysis: through data mining and association analysis technology, discover the potential association and rules between function items, such as certain function items are often used together.
[0059] Furthermore, function operation data refers to various performance and resource usage related data generated by the function items in the application during operation. This data provides key information about how the function items are executed, how efficient they are, and whether there are any potential problems. Function operation data usually includes but is not limited to the following aspects:
[0060] 1) Performance indicators, including: 1) Response time: the time required for a function item to complete processing and return results after receiving a request. 2) Processing speed: the speed at which a function item processes tasks or data, usually measured in terms of the number of transactions or data processed per second. 3) Resource utilization: the system resources consumed by a function item during operation, such as CPU usage, memory usage, disk I / O, etc.
[0061] 2) Errors and exceptions: 1) Error rate: the frequency or proportion of errors that occur during the operation of a function item. Exception records: 2) Detailed records of any exceptions or errors encountered during the operation of a function item, including error code, occurrence time, impact range, etc.
[0062] 3) System status: the current operating status of the function item, such as running, paused, stopped, etc.; the workload borne by the function item, such as the number of concurrent users, number of requests, amount of data, etc.
[0063] 4) Log information: 1) Operation log: records key operations during the execution of function items, such as user login, data query, file upload, etc. 2) System log: records system-level events during the operation of function items, such as system startup, stop, restart, etc.
[0064] 5) Dependencies: External dependencies: other systems or services that the function item depends on during operation, as well as the status and response time of these dependencies. Internal dependencies: the dependencies between components within the function item, as well as the performance and resource usage of these components.
[0065] Optionally, by building a digital twin model of the target device, function usage records and function operation data of each function item in the application during the target period can be obtained from the digital twin model.
[0066] The process of building the above digital twin model is as follows:
[0067] First, collect real-time operating data from the target device, including sensor data, operation records, fault logs, etc. Collect application log data, including usage records of functional items, user behavior data, etc. Design the structure and framework of the digital twin model based on the collected data. Determine which components and subsystems the model needs to include, and the interactions between them. Use simulation software or platform to build the digital twin model. Incorporate the physical characteristics, operating logic, and constraints of the actual device into the model. Verify the accuracy and reliability of the digital twin model by comparing it with the operating data of the actual device. Make necessary adjustments and optimizations to the model to improve its predictive ability and accuracy.
[0068] Then, map the real-time operation data of the actual device to the digital twin model to maintain the consistency between the model and the actual device. Ensure the accuracy and completeness of the data for subsequent analysis and prediction. Extract the usage records of each function item in the application from the digital twin model. Analyze the usage frequency, usage time, user behavior and other characteristics of the function items. Conduct in-depth analysis of the function operation data in the digital twin model to understand the performance, resource consumption and potential problems of the function items. Use data analysis tools and methods (such as data mining, machine learning, etc.) to discover patterns and trends in the data.
[0069] S102, analyzing the function usage records of each function item in the application program within the target period to obtain the usage probability of each function item in the future period.
[0070] It is understandable that the purpose of analyzing the functional usage records of each functional item in the application during the target period is to infer the possibility of each functional item being used in the future by mining the patterns and trends in the historical usage data.
[0071] Optionally, perform descriptive statistical analysis on the function usage records to understand the basic information such as the frequency and duration of use of each function item. Based on the results of data analysis, extract features that are useful for predicting future usage probabilities. Select a suitable prediction model, such as a machine learning algorithm (logistic regression, random forest, neural network, etc.) or a time series prediction model. Use historical data to train the model so that it can learn the patterns and trends of function item usage.
[0072] Then, the trained model is used to predict the usage probability of each function item in the future period. The prediction results may include the usage probability distribution and confidence interval of each function item in the future period.
[0073] S103, processing the function operation data of each function item according to each usage probability.
[0074] Optionally, first, identify unimportant function operation data and important function operation data based on each usage probability: first set a usage probability threshold, which can be determined based on business requirements, data storage capabilities, and analysis objectives. For example, the threshold can be set to a certain percentage (such as 5% or 10%), and function items below this percentage are considered unimportant. Next, traverse the function operation data and identify those data belonging to unimportant function items. These data may be generated by function items with low usage frequency, poor user feedback, or low business value.
[0075] For the function operation data marked as unimportant, you can choose to delete it directly. This helps to reduce the space occupied by data storage and improve the efficiency of subsequent data processing. In addition, for important function operation data, the data processing strategy is to retain it.
[0076] In the above data processing method, the present application collects the usage frequency, usage time information and interaction relationship between each function item in the target time period, realizes in-depth analysis of the acquired data, and predicts the usage probability of each function item in the future time period; according to the usage probability of the function item, the functional operation data of each function item is processed, with the purpose of dynamically adjusting computing resources, storage resources and network resources, etc., to ensure that high-frequency functional items obtain sufficient resource support, improve overall operating efficiency, clean up unimportant or redundant functional operation data, reduce the data storage burden, and realize hierarchical management of data.
[0077] In an exemplary embodiment, as shown in FIG2 , the function operation data of each function item is processed according to each usage probability, including:
[0078] S201 , for each function item, if the usage probability of the function item is greater than or equal to a first probability threshold, retaining the function operation data of the function item.
[0079] It is understandable that in an application, each function item has its specific usage probability, which is calculated based on user behavior, historical data, and possible prediction models to reflect the possibility of the function item being used by the user in the future. The first probability threshold is a preset limit value used to distinguish which function item data is worth retaining and which can be considered to be discarded or archived.
[0080] When the usage probability of a function item is greater than or equal to the first probability threshold, it means that the function item is likely to be used by users in the future, so the function operation data generated by it (such as user operation records, performance indicators, error logs, etc.) is considered valuable. In order to ensure the availability and traceability of this data, the system will retain this data.
[0081] S202: If the usage probability of the function item is less than the first probability threshold and greater than the second probability threshold, the function operation data of the function item is subjected to pending confirmation processing.
[0082] It is understandable that in the evaluation of the probability of use of the function items of an application, in addition to setting a higher first probability threshold to determine which function items' data need to be explicitly retained, a lower second probability threshold may also be set. This second probability threshold is used to define those function items that have a low probability of use but still have a certain value or potential value. When the probability of use of a function item falls between the first probability threshold and the second probability threshold (i.e., less than the first probability threshold and greater than the second probability threshold), the function operation data of the function item will not be immediately retained or discarded, but will be marked as "pending confirmation" status.
[0083] Specifically, the functional operation data of the functional item is processed for pending confirmation, including: sending the functional operation data of the functional item and the pending confirmation indication generated for the functional item to the confirming party; and cleaning or retaining the functional operation data of the functional item in response to the response message returned by the pending confirmation indication according to the confirmation policy.
[0084] S203: If the usage probability of the function item is less than the second probability threshold, clean up the function operation data of the function item.
[0085] The second probability threshold is smaller than the first probability threshold.
[0086] It is understandable that when the usage probability of a certain function item is less than the first probability threshold and greater than the second probability threshold, a decision to retain or clear the function operation data of the function item will not be made immediately, but the data and the related pending confirmation indication will be sent to the confirming party for further evaluation. Function items whose usage probability falls between the two thresholds will be identified.
[0087] Then, the functional operation data of these functional items will be packaged, and a confirmation indication will be generated, which contains information such as the identification of the functional item, the probability of use, and the data overview.
[0088] The packaged function operation data and confirmation instructions will be sent to the confirming party. The confirming party can be the business team, data analysis team or other relevant decision-making departments. The sending method can be email, notification, call, etc., depending on the design and the needs of the confirming party.
[0089] After receiving the data and the indication to be confirmed, the confirming party will evaluate the data to determine whether they are valuable enough to be retained. The evaluation process may include data analysis, user feedback collection, business needs analysis, etc. After the confirming party completes the evaluation, it will return a response message. The message usually contains processing suggestions for the function item function operation data, that is, cleanup processing or retention processing. The response message can be sent back through the interface or other communication methods.
[0090] According to the response message returned by the confirmer, the functional operation data of the functional item is processed accordingly. If the response message suggests cleaning, the data will be deleted from the primary storage or archived to the backup storage. If the response message suggests retaining, the data will be transferred to the formal data storage and its accessibility and traceability will be ensured.
[0091] In this embodiment, different processing strategies are adopted to process the function operation data according to the usage probability of the function items, thereby realizing hierarchical management of the data.
[0092] In an exemplary embodiment, as shown in FIG3 , the function usage records of each function item in the application program within the target period are analyzed to obtain the usage probability of each function item in the future period, including:
[0093] S301, converting the function usage record of each function item into a word vector.
[0094] It is understandable that the purpose of converting the function usage records of each function item into a word vector is mainly to use the word embedding method in the natural language processing (NLP) technology to capture the semantic relationship and context information between the function items, thereby converting this information into a numerical form that can be understood and processed by computers.
[0095] Specifically, word embedding is a representation method that maps each word in the vocabulary into a high-dimensional vector space. In this vector space, similar words are close in spatial position, so that the similarity and correlation between words can be captured. For the functional items in the application, although they are not traditional text words, the usage record of each functional item can be regarded as a "word" and converted into a word vector through word embedding methods.
[0096] Word vectors can be used to capture the association between functional items: there may be some kind of association or dependency between functional items, for example, some functional items are often used together or there is a sequence of use. After converting the usage records of these functional items into word vectors, the similarity between vectors can be used to capture this association. Furthermore, word vectors can also simplify model input: prediction models usually require input in numerical form. After converting the usage records of functional items into word vectors, these vectors can be used as model input, thereby simplifying the model processing process. Furthermore, word vectors can also improve prediction accuracy: by capturing the semantic relationship and contextual information between functional items, word vectors can provide more useful information for the prediction model, thereby improving the accuracy of the prediction.
[0097] Specifically, the usage record of each function item is regarded as a "word", and a vocabulary is constructed, which contains the unique identifiers of all function items in the application. The word embedding method in natural language processing technology, such as Word2Vec, GloVe or FastText, is used to convert the usage record of each function item into the corresponding word vector. These word vectors can capture the semantic relationship and context information between function items.
[0098] S302, inputting the word vector into the prediction model to obtain the usage probability of each function item output by the prediction model in the future time period.
[0099] Among them, the prediction model can be a time series analysis model (such as ARIMA, LSTM, etc.), a machine learning model (such as random forest, gradient boosting tree, etc.) or a deep learning model (such as neural network, convolutional neural network, etc.).
[0100] Specifically, the prediction model is trained using historical data (i.e., the function usage records of previous time periods and their corresponding future usage probabilities). During the training process, the parameters and hyperparameters of the model are adjusted to optimize the prediction performance of the model. The word vector converted in S301 is input into the trained prediction model. The model will output the usage probability of each function item in the future time period based on the input word vector.
[0101] In an exemplary embodiment, the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0102] It is understood that the function usage record corresponding to each function item refers to the record of the actual usage of the specific function item by each target user (i.e., the user group of the application) during the use of the application. These records may include but are not limited to the following information:
[0103] 1) User behavior: specific actions of users interacting with functional items, such as clicking, sliding, and inputting.
[0104] 2) Frequency of use: the number of times or frequency at which a user uses a function item within a certain period of time.
[0105] 3) Usage duration: the duration for each time a user uses a function item.
[0106] 4) Usage scenario: the context in which the user uses a function item, such as time, location, network status, etc.
[0107] 5) User feedback: user evaluation, rating or feedback on functional items.
[0108] Furthermore, the function operation data corresponding to each function item refers to the data related to the operation of the function item generated by the application program or system when each target user uses the function item. Such data may include:
[0109] 1) Performance indicators: such as function response time, loading speed, resource usage, etc.
[0110] 2) Error log: a record of errors, exceptions or crashes that occur during the operation of a function item.
[0111] 3) User input: data or information entered by the user in a function item, such as text, images, sounds, etc.
[0112] 4) System status: system status information when the function item is running, such as memory usage, CPU occupancy, etc.
[0113] 5) Interaction data: data on the interaction between a function item and other function items or external systems, such as API call records, data transmission logs, etc.
[0114] Accordingly, as shown in FIG4 , the function usage records of each function item are converted into word vectors, including:
[0115] S401, for each target user, determining an analysis window corresponding to the target user according to the behavior characteristics of the target user in a target time period.
[0116] Optionally, for each target user, collect their behavioral feature data during the target time period. These behavioral features may include the user's active time, usage frequency, usage duration, function preferences, etc. Analyze the collected behavioral feature data to identify the user's behavior pattern. For example, some users may be more active in a specific time period, or have a higher frequency of use for certain function items. Based on the user's behavior pattern, determine a personalized analysis window for each target user. This analysis window may be a time period, or a specific combination of behavioral features for subsequent word vector conversion.
[0117] S402, using the analysis window corresponding to the target user, converting the function usage records of each function item corresponding to the target user into a word vector.
[0118] Optionally, select a suitable word embedding method, such as Word2Vec, GloVe, FastText, etc., according to the specific application scenario and requirements.
[0119] For each target user, apply the analysis window determined in S401 to filter and process the function usage records. This helps to ensure that the converted word vectors can accurately reflect the user's behavioral characteristics within the analysis window. The filtered function usage records are input into the selected word embedding method to convert them into corresponding word vectors. These word vectors should be able to capture the semantic relationship and contextual information between function items while retaining the user's personalized usage characteristics. For each target user, the word vector representation of each corresponding function item is output. These word vectors will serve as input for subsequent prediction models or analysis tasks.
[0120] Correspondingly, the input of the prediction model can be the word vector of each target user, and the output is the usage probability of each function item in the future period.
[0121] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0122] Based on the same inventive concept, the embodiment of the present application also provides a data processing device for implementing the data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more data processing device embodiments provided below can refer to the limitations on the data processing method above, and will not be repeated here.
[0123] In an exemplary embodiment, as shown in FIG5 , a data processing device is provided, comprising: an acquisition module 11, a probability prediction module 12 and a data processing module 13, wherein:
[0124] The acquisition module 11 is used to acquire the function usage record and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0125] The probability prediction module 12 is used to analyze the function usage records of each function item in the application program within the target period to obtain the usage probability of each function item in the future period;
[0126] The data processing module 13 is used to process the function operation data of each function item according to each usage probability.
[0127] In one embodiment, the data processing module 12 is used to:
[0128] For each function item, if the usage probability of the function item is greater than or equal to the first probability threshold, retaining the function operation data of the function item;
[0129] If the usage probability of the function item is less than the first probability threshold and greater than the second probability threshold, the function operation data of the function item is subjected to pending confirmation processing;
[0130] If the usage probability of the function item is less than the second probability threshold, cleaning the function operation data of the function item;
[0131] The second probability threshold is smaller than the first probability threshold.
[0132] In one embodiment, the cleaning module 13 is used to: send the function operation data of the function item and the to-be-confirmed indication generated for the function item to the confirming party;
[0133] The response message returned by the confirmation indication is processed according to the confirmation policy, and the function operation data of the function item is cleaned up or retained.
[0134] In one embodiment, the probability prediction module 12 is used to: convert the function usage record of each function item into a word vector;
[0135] The word vector is input into the prediction model to obtain the usage probability of each function item output by the prediction model in the future period.
[0136] In one embodiment, the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0137] In one embodiment, the probability prediction module 12 is used to: for each target user, determine an analysis window corresponding to the target user according to the behavior characteristics of the target user in a target time period;
[0138] The analysis window corresponding to the target user is used to convert the function usage records of each function item corresponding to the target user into a word vector.
[0139] Each module in the above data processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0140] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a data processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0141] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0142] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0143] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0144] The function usage records of each function item in the application during the target period are analyzed to obtain the usage probability of each function item in the future period; according to each usage probability, the function operation data of each function item is processed.
[0145] In one embodiment, when the processor executes the computer program, the following steps are also implemented: for each function item, if the probability of use of the function item is greater than or equal to a first probability threshold, the function operation data of the function item is retained; if the probability of use of the function item is less than the first probability threshold and greater than the second probability threshold, the function operation data of the function item is pending confirmation; if the probability of use of the function item is less than the second probability threshold, the function operation data of the function item is cleaned; wherein the second probability threshold is less than the first probability threshold.
[0146] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the functional operation data of the functional item and the indication to be confirmed generated for the functional item are sent to the confirming party; and the functional operation data of the functional item is cleaned up or retained according to the confirmation policy in response to the response message returned by the indication to be confirmed.
[0147] In one embodiment, when the processor executes the computer program, the following steps are also implemented: converting the function usage record of each function item into a word vector; inputting the word vector into the prediction model to obtain the usage probability of each function item in the future time period output by the prediction model.
[0148] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented: for each target user, based on the behavioral characteristics of the target user within the target time period, an analysis window corresponding to the target user is determined; using the analysis window corresponding to the target user, the function usage records of each function item corresponding to the target user are converted into word vectors.
[0150] In one embodiment, a computer-readable storage medium is provided, including a computer program, which, when executed by a processor, implements the following steps:
[0151] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0152] The function usage records of each function item in the application during the target period are analyzed to obtain the usage probability of each function item in the future period; according to each usage probability, the function operation data of each function item is processed.
[0153] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each function item, if the probability of use of the function item is greater than or equal to a first probability threshold, the function operation data of the function item is retained; if the probability of use of the function item is less than the first probability threshold and greater than a second probability threshold, the function operation data of the function item is pending confirmation; if the probability of use of the function item is less than the second probability threshold, the function operation data of the function item is cleaned; wherein the second probability threshold is less than the first probability threshold.
[0154] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the functional operation data of the functional item and the indication to be confirmed generated for the functional item are sent to the confirming party; and the functional operation data of the functional item is cleaned up or retained according to the confirmation policy in response to the response message returned by the indication to be confirmed.
[0155] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: converting the function usage record of each function item into a word vector; inputting the word vector into the prediction model to obtain the usage probability of each function item in the future time period output by the prediction model.
[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application program; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each target user, the analysis window corresponding to the target user is determined based on the behavioral characteristics of the target user within the target time period; using the analysis window corresponding to the target user, the function usage records of each function item corresponding to the target user are converted into word vectors.
[0158] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0159] Obtaining the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items;
[0160] The function usage records of each function item in the application during the target period are analyzed to obtain the usage probability of each function item in the future period; according to each usage probability, the function operation data of each function item is processed.
[0161] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each function item, if the probability of use of the function item is greater than or equal to a first probability threshold, the function operation data of the function item is retained; if the probability of use of the function item is less than the first probability threshold and greater than a second probability threshold, the function operation data of the function item is pending confirmation; if the probability of use of the function item is less than the second probability threshold, the function operation data of the function item is cleaned; wherein the second probability threshold is less than the first probability threshold.
[0162] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the functional operation data of the functional item and the indication to be confirmed generated for the functional item are sent to the confirming party; and the functional operation data of the functional item is cleaned up or retained according to the confirmation policy in response to the response message returned by the indication to be confirmed.
[0163] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: converting the function usage record of each function item into a word vector; inputting the word vector into the prediction model to obtain the usage probability of each function item in the future time period output by the prediction model.
[0164] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application program; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
[0165] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each target user, the analysis window corresponding to the target user is determined based on the behavioral characteristics of the target user within the target time period; using the analysis window corresponding to the target user, the function usage records of each function item corresponding to the target user are converted into word vectors.
[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0167] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0168] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0169] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A data processing method, characterized in that: The method comprises: Acquire the function usage records and function operation data of each function item in the application within the target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items; Analyze the function usage records of each function item in the application program during the target period to obtain the usage probability of each function item in the future period; The function operation data of each function item is processed according to each of the usage probabilities.
2. The method according to claim 1, characterized in that The processing of the function operation data of each function item according to each of the usage probabilities includes: For each function item, if the usage probability of the function item is greater than or equal to a first probability threshold, retaining the function operation data of the function item; If the usage probability of the function item is less than the first probability threshold and greater than the second probability threshold, the function operation data of the function item is subjected to pending confirmation processing; If the usage probability of the function item is less than the second probability threshold, cleaning up the function operation data of the function item; The second probability threshold is smaller than the first probability threshold.
3. The method according to claim 2, characterized in that The processing of the function operation data of the function item to be confirmed includes: Sending the function operation data of the function item and the indication to be confirmed generated for the function item to the confirming party; According to the response message returned by the confirming party to the indication to be confirmed, the function operation data of the function item is cleaned up or retained.
4. The method according to claim 1, characterized in that: The analyzing the function usage records of each function item in the application program within the target time period to obtain the usage probability of each function item in the future time period includes: Convert the function usage records of each function item into word vectors; The word vector is input into the prediction model to obtain the usage probability of each function item output by the prediction model in the future time period.
5. The method according to claim 4, characterized in that: The function usage record corresponding to each function item includes the function usage record of the function item by each target user in the process of using the application; the function operation data corresponding to each function item includes the function operation data generated in the process of each target user using the function item.
6. The method according to claim 5, characterized in that: The converting the function usage records of each function item into a word vector includes: For each target user, determining an analysis window corresponding to the target user according to the behavior characteristics of the target user within the target time period; The analysis window corresponding to the target user is used to convert the function usage records of each function item corresponding to the target user into a word vector.
7. A data processing device, characterized in that: The device comprises: An acquisition module, used to acquire function usage records and function operation data of each function item in the application within a target period; wherein the function usage record of each function item at least includes the usage frequency and usage time information of the function item within the target period, and the interaction relationship between the function item and other function items; A probability prediction module is used to analyze the function usage records of each function item in the application program within the target time period to obtain the usage probability of each function item in the future time period; The data processing module is used to process the function operation data of each function item according to each of the usage probabilities.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.