Notebook adaptation test method and system combined with user habits

Abstract

The application relates to a notebook adaptation test method and system combined with user habits. In the application, user habit data containing software use preferences, input method characteristics and environment setting behaviors in multiple scenarios are collected first, and a typical user habit model library is constructed through a clustering algorithm. Then, a simulated operation habit sequence set is generated based on the model library and injected into a notebook system, and resource occupation characteristic vectors and operation response delay data are synchronously collected as system adaptation response data. Subsequently, multi-dimensional correlation analysis is performed on the response data and the model library, and a user habit adaptation degree index and a key adaptation bottleneck path are obtained. Finally, a user habit adaptation optimization report is generated based on the analysis results, which is used to guide the adaptation optimization of software and hardware parameters of the notebook system and improve the adaptation of the system to user habits.

Description

Technical Field

[0001] This application relates to the field of intelligent testing technology for computer equipment, and in particular to a laptop adaptation testing method and system that incorporates user habits. Background Technology

[0002] With the rapid development of information technology, laptops have become indispensable tools for people's work, study, and daily life. Throughout the development of laptops, compatibility testing has always been a crucial step in ensuring that their performance meets user needs. However, traditional laptop compatibility testing methods have significant limitations.

[0003] Past tests have mostly focused on standardized hardware performance metrics, such as using specific benchmark programs to evaluate the CPU's processing speed, memory's data transfer capabilities, and the GPU's graphics rendering capabilities. On the software side, the focus was primarily on the compatibility of common office software and basic operating system functions, ensuring stable operation on laptops. However, with the continuous expansion of laptop application scenarios and the increasing diversification of user needs, traditional testing methods are no longer sufficient to meet actual requirements. Different users exhibit vastly different habits when using laptops. In work scenarios, some users focus on word processing, frequently using specific functions of document editing software, such as formatting and content revision; while users engaged in data analysis tend to frequently use the complex data calculation and chart generation functions of spreadsheet software. Regarding input methods, some users prefer fast keyboard input and shortcut key operations, some are accustomed to touchpad gestures, and others use external input devices, such as designers using drawing tablets and gamers using game controllers. In terms of environmental settings, users adjust screen brightness according to ambient light, change volume according to usage scenarios and personal preferences, and switch power management modes based on battery level and task requirements.

[0004] Therefore, traditional testing methods often fail to adequately consider the diverse user habits, resulting in a mismatch between laptop performance and user needs in actual use. For example, users who frequently switch between multiple tasks or use specific software functions at high frequency may experience excessive resource consumption and long response times, issues that traditional testing methods cannot effectively detect, thus failing to provide accurate guidance for optimizing the laptop system. Summary of the Invention

[0005] In view of the above, in order to at least partially address the shortcomings of the prior art, in a first aspect, embodiments of this application provide a laptop compatibility testing method that incorporates user habits, the method comprising:

[0006] Collect user habit data from multiple scenarios and construct a typical user habit model library. Classify the user habit data using a clustering algorithm to obtain a variety of typical user habit models. The typical user habit models correspond to the operational behavior characteristics of different user groups.

[0007] Based on the typical user habit model library, a set of simulated operation habit sequences is generated. The set of simulated operation habit sequences is constructed according to the operation preference features, input timing features and environmental adjustment rules in each typical user habit model, and includes user operation instructions that conform to the behavior patterns of different user groups.

[0008] The simulated operation habit sequence set is injected into the laptop system, and system adaptation response data is collected synchronously. The system adaptation response data includes resource consumption feature vectors and operation response delay data.

[0009] A multi-dimensional correlation analysis is performed on the system adaptation response data and the typical user habit model library. By comparing the system adaptation response data corresponding to different typical user habit models, user habit adaptation index and key adaptation bottleneck paths are calculated.

[0010] A user habit adaptation optimization report is generated based on the user habit adaptation index and the key adaptation bottleneck path.

[0011] Secondly, embodiments of this application also provide a laptop adaptation testing system that incorporates user habits, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the machine-readable storage medium to implement the laptop adaptation testing method that incorporates user habits.

[0012] In summary, the laptop adaptation testing method and system based on user habits provided in this application comprehensively collects user habit data across multiple scenarios and uses clustering algorithms to construct a typical user habit model library. This accurately characterizes the differences among different user groups in multiple dimensions, such as software usage preferences, input method characteristics, and environmental setting behaviors. This targeted analysis of user operation behavior characteristics provides a reliable basis for subsequent testing based on real user behavior patterns, significantly improving the relevance and effectiveness of the testing. Furthermore, the generation of simulated operation habit sequence sets based on the typical user habit model library closely matches the actual behavior patterns of different user groups. Injecting these sequences into the laptop system and simultaneously collecting system adaptation response data, including resource consumption feature vectors and operation response latency data, can realistically reflect the performance of the laptop system when facing various actual user habit operations. Compared to traditional standardized testing, this testing method based on real user behavior simulation is better able to reveal potential problems in actual system use.

[0013] Simultaneously, a multi-dimensional correlation analysis was conducted between system adaptation response data and a typical user habit model library to accurately calculate user habit adaptation metrics and key adaptation bottleneck paths. The user habit adaptation metrics clearly quantify the laptop system's adaptability to specific user habits, while the key adaptation bottleneck paths explicitly indicate the correlation between specific user operation sequences leading to abnormal system responses and system components. This provides crucial clues for a deeper understanding of system performance bottlenecks, facilitating targeted optimization. Finally, a user habit adaptation optimization report generated based on the above analysis results, including detailed user habit type identification, system adaptation bottleneck analysis, and targeted adjustment suggestions, provides guidance for optimizing the laptop system's hardware and software parameters. This ensures that optimization work is targeted and effectively improves the system's compatibility with user habits, thereby comprehensively enhancing the laptop system's performance and user experience in real-world usage scenarios and strengthening the product's market competitiveness.

[0014] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the above drawings without creative effort.

[0016] To gain a more complete understanding of this application and its beneficial effects, the following description will be provided in conjunction with the accompanying drawings, wherein the same reference numerals in the following description denote the same parts.

[0017] Figure 1 This is a flowchart illustrating a laptop adaptation testing method that incorporates user habits, as provided in an embodiment of this application.

[0018] Figure 2 This is the intended application scenario for the laptop adaptation testing method based on user habits provided in the embodiments of this application.

[0019] Figure 3 This is a schematic diagram of a laptop adaptation testing system that incorporates user habits, as provided in an embodiment of this application. Detailed Implementation

[0020] 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 a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the protection scope of this application.

[0021] Please see Figure 1 and Figure 2 , Figure 1 This is a flowchart illustrating a laptop compatibility testing method that incorporates user habits, as provided in an embodiment of this application. Figure 2 This is a schematic diagram illustrating an application scenario of the laptop adaptation testing method based on user habits provided in this application embodiment. The application scenario includes a system-side platform for information interaction and multiple laptops. In this embodiment, as an example, the system-side platform can be a server, server cluster, or other device with big data processing and storage capabilities; this embodiment does not specifically limit its application. The system-side platform can receive and store various types of information generated by multiple laptops during the adaptation testing process in an office scenario, covering typical user habit model data, simulated operation habit sequences, system adaptation response data (including resource consumption feature vectors and operation response latency data), and data related to user habit adaptation indicators and key adaptation bottleneck paths. Furthermore, the system-side platform performs in-depth analysis of the above information, such as correlating system adaptation response data with a typical user habit model library, thereby identifying the laptop system's adaptation shortcomings and key adaptation bottlenecks for different user groups' habits. The analysis results help optimize the laptop system's hardware and software parameters or provide targeted adjustment suggestions, and can serve as a backend for providing system updates and maintenance for the laptops. Of course, in other embodiments, the testing method can also be executed locally on the laptop, flexibly meeting the testing needs of different office scenarios (such as local testing for small office teams, custom testing for individual users, etc.). The system platform can be a backend used to provide various functions such as system updates, maintenance, and adaptation testing for the laptop. In other embodiments, the method can also be executed locally on the laptop, and there is no specific limitation.

[0022] like Figure 1 As shown, the method includes steps S110-S150, which will be described in detail below.

[0023] Step S110: Collect user habit data from multiple scenarios and construct a typical user habit model library. The user habit data includes software usage preference data, input method feature data, and environmental setting behavior data. The user habit data is classified using a clustering algorithm to obtain various typical user habit models, each corresponding to the operational behavior characteristics of different user groups.

[0024] In this embodiment, only one optional example is used, with the office scenario serving as the consistent example throughout the text. In an office scenario, when collecting user habit data, software usage preference data needs to record information related to the user launching applications such as word processing software, spreadsheet software, and email clients; input method feature data needs to capture operational features such as keyboard keystrokes and touchpad swipes; and environment setting behavior data needs to track the adjustment of parameters such as screen brightness and volume. By classifying the above data using a clustering algorithm, a typical user habit model is formed that reflects the operational characteristics of different user groups in an office scenario. For example, some users frequently use word processing software and rely on keyboard input, while others frequently use spreadsheet software and operate the touchpad extensively.

[0025] In this embodiment, step S110 may include sub-steps S111-S114, which will be described in detail below.

[0026] Step S111: Collect user habit data under multiple preset scenarios. For example, the software usage preference data includes application launch frequency, usage duration, and function module call records; the input method characteristic data includes keyboard key press frequency, touchpad swipe trajectory, and external device operation mode; and the environment setting behavior data includes screen brightness adjustment cycle, volume change pattern, and power management mode switching records. As an example, the preset scenarios may include, but are not limited to, office scenarios, entertainment scenarios, and mobile scenarios.

[0027] In this embodiment, when collecting user habit data in an office setting, regarding software usage preference data, it is necessary to statistically analyze the launch frequency of applications such as word processing software and spreadsheet software, record the usage duration after each launch, and record the calls to functional modules such as "paragraph settings" and "insert table" in word processing software. Regarding input method characteristic data, it is necessary to statistically analyze the keystroke frequency per unit time of each keyboard key, record the trajectory characteristics of touchpad swiping, including the swiping direction and path, and record the operation modes of external devices such as external mouse clicks. Regarding environmental setting behavior data, it is necessary to track the time interval of screen brightness adjustment, i.e., the adjustment cycle, record the change pattern of volume, and record the switching records of power management modes between "balanced mode" and "high-performance mode."

[0028] Step S112: Preprocess the user habit data and classify the preprocessed user habit data using a clustering algorithm. Calculate the similarity between user behavior feature vectors and cluster the user habit data based on the similarity.

[0029] In the clustering process, the number of clusters is determined based on the data density distribution, so that the clustering results can distinguish user groups with different operation preferences. The preprocessing includes data cleaning, feature standardization, and behavior event alignment. Data cleaning is used to remove abnormal operation records and duplicate data. Feature standardization is used to convert habitual data of different dimensions into a unified feature space. Behavior event alignment is used to integrate related operation behaviors into a complete behavior sequence according to timestamps.

[0030] In this embodiment, when preprocessing user habit data collected in an office setting, the data cleaning stage needs to remove abnormal operation records such as single abnormal continuous keystrokes on the keyboard or random swiping on the touchpad when there is no operation, as well as duplicate data such as repeated storage of the same application startup record. In the feature standardization stage, data with different dimensions, such as application usage time (in minutes) and keyboard keystroke frequency (in times / minute), are transformed into a unified feature space to ensure the rationality of subsequent calculations. In the behavior event alignment stage, related user operations such as launching word processing software, inputting text, and adjusting screen brightness are integrated according to timestamps to form a complete behavior sequence. Then, a clustering algorithm is used for classification, calculating the similarity between user behavior feature vectors. The number of clusters is determined based on the density distribution of data in the office setting, allowing the clustering results to distinguish user groups with different operating preferences, such as users who frequently use spreadsheet software or users who frequently use email clients.

[0031] In this embodiment, step S112 may include sub-steps S1121-S1124, which will be described in detail below.

[0032] Step S1121: Convert the preprocessed user habit data into high-dimensional feature vectors. Each feature vector corresponds to a user habit feature in terms of dimension. The dimensions include software usage frequency dimension, input method proportion dimension, environment setting parameter dimension, and time sequence behavior transfer dimension.

[0033] In this embodiment, when converting preprocessed user habit data in an office setting into a high-dimensional feature vector, the software usage frequency dimension corresponds to features such as the launch frequency of word processing software and spreadsheet software; the input method proportion dimension corresponds to features such as the proportion of keyboard input time and touchpad operation time; the environmental setting parameter dimension corresponds to features such as the screen brightness adjustment range and volume adjustment range; and the temporal behavior transition dimension corresponds to the behavior transition feature from launching word processing software to calling the "paragraph settings" function. Each dimension accurately corresponds to a user habit feature in an office setting, collectively forming a high-dimensional feature vector.

[0034] Step S1122: Use density clustering algorithm to cluster high-dimensional feature vectors. By calculating the density reachability of data points in the feature space, density-connected points are divided into a cluster. Set the cluster radius and minimum sample number parameters. The cluster radius is determined by the distance distribution statistics of the feature space, and the minimum sample number is set according to the size of the user group.

[0035] In this embodiment, when using density clustering to cluster high-dimensional feature vectors in an office setting, the density reachability of each data point in the feature space is calculated. This means determining whether a data point can reach another data point through a series of sufficiently dense data points, and grouping densely connected points into a cluster. The cluster radius is determined by statistically analyzing the distance distribution between data points in the feature space within the office setting, ensuring a reasonable distinction between dense and sparse regions. The minimum sample size is set based on the size of the user group involved in the office setting, ensuring that each cluster represents a certain size of users with similar operating habits.

[0036] Step S1123: Evaluate the effectiveness of the clustering results by calculating the cluster similarity of each data point using the silhouette coefficient. The silhouette coefficient assesses the clustering effect through sample-to-cluster similarity and inter-cluster similarity. Abnormal clusters with silhouette coefficients below a set threshold are removed to obtain valid clusters.

[0037] In this embodiment, when evaluating the effectiveness of clustering results in an office setting, the silhouette coefficient is used to calculate the cluster similarity of each data point. The similarity between each sample and other samples within the same cluster (intra-cluster similarity) is calculated, and the similarity between the sample and samples within other clusters (inter-cluster similarity) is also calculated. The silhouette coefficient is then calculated using these two similarities. A threshold is set to remove abnormal clusters with silhouette coefficients below this threshold. These abnormal clusters may be due to the specific operating habits of individual users in an office setting. After removal, effective clusters that accurately reflect the operating habits of different user groups in an office setting are obtained.

[0038] Step S1124: Name and label the effective clusters. Based on the common characteristics of user habit data within each effective cluster, assign user group labels to each effective cluster. The user group labels are determined based on the common characteristics of user habit data within each effective cluster. The feature labels include descriptions of typical user operation behaviors within each effective cluster.

[0039] In this embodiment, when naming and labeling effective clusters in an office setting, the common characteristics of user habit data within each effective cluster are observed. If users in a certain effective cluster frequently launch word processing software and primarily input data via keyboard, the cluster is labeled as a "word processing-keyboard dependent" user group. The feature labeling section describes in detail the typical operational behaviors of users within this cluster, such as launching word processing software multiple times a day, using it for extended periods each time, and frequently using keyboard shortcuts for text formatting.

[0040] Step S113: Extract features from each clustering result to obtain the target habit features of the typical user habit model. The target habit features include the set of frequently used software, input device preference weights, environmental parameter adjustment ranges, and temporal behavior dependencies. The set of frequently used software is determined by ranking the application call frequency; the input device preference weights are calculated by the usage ratio of different input methods; the environmental parameter adjustment ranges are obtained by statistically analyzing the distribution intervals of settings such as brightness and volume; and the temporal behavior dependencies are learned using a Markov chain model to study the transition probabilities of user operation sequences.

[0041] In this embodiment, when extracting features from each clustering result in an office setting, the set of frequently used software is determined by ranking the frequency of user calls to each application within the cluster. For example, word processing software, email clients, and spreadsheet software have the highest call frequency after ranking, and these three constitute the set of frequently used software corresponding to that clustering result. The input device preference weight is obtained by calculating the usage ratio of different input methods such as keyboard, touchpad, and external mouse. If the keyboard usage ratio is the highest, its corresponding preference weight is the largest. The environmental parameter adjustment range is determined by statistically analyzing the distribution range of screen brightness, volume, and other settings. For example, if the screen brightness setting value mostly falls within a certain range, that range is the screen brightness adjustment range. The temporal behavior dependency is determined by learning the transition probability of user operation sequences through a Markov chain model. For example, learning the transition probability of a user's operation sequence from launching a word processing software to calling the "save" function, and then closing the software, thereby determining the temporal behavior dependency.

[0042] In this embodiment, step S113 may include sub-steps S1131-S1134, which will be described in detail below.

[0043] Step S1131: Record the keystroke frequency on the keyboard. By statistically analyzing the number of times different keys are triggered and the frequency of use of key combinations within a unit of time, the user's input habit characteristics can be obtained. Key combinations include system shortcut keys and application shortcut keys.

[0044] In this embodiment, when recording keyboard keystroke frequency in an office setting, the number of times each letter key, number key, and function key is triggered per unit time is counted. Simultaneously, the usage frequency of system shortcuts such as "Ctrl+C" and "Ctrl+V," as well as application shortcuts such as "Ctrl+B" (bold text) and "Ctrl+I" (italic text) is also counted. Through these statistical data, user input habit characteristics can be obtained; for example, some users frequently use the "Ctrl+S" (save) shortcut, while others frequently use letter keys for text input.

[0045] Step S1132: Collect touchpad sliding trajectory data, which includes sliding direction, sliding speed, and pressure change characteristics. The sliding direction is represented by horizontal and vertical displacement components, the sliding speed is calculated using the ratio of displacement to time, and the pressure change characteristics are recorded using the output value sequence of the touchpad pressure sensor.

[0046] In this embodiment, when collecting touchpad swipe trajectory data in an office setting, the swipe direction is represented by horizontal and vertical displacement components. For example, a positive horizontal displacement component indicates a rightward swipe, and a positive vertical displacement component indicates an upward swipe. The swipe speed is calculated as the ratio of displacement to time during the swipe, reflecting how quickly the user swipes the touchpad. Pressure change characteristics are recorded through a sequence of output values ​​from the touchpad pressure sensor. Different output values ​​correspond to different pressure levels, reflecting the pressure changes when the user operates the touchpad.

[0047] Step S1133: Record the operation mode of the external device, including the click frequency of the external mouse, the number of times the scroll wheel is used, and the key layout preference of the external keyboard. The operation mode of the external device is obtained by correlation analysis of the device connection status log and the input event log.

[0048] In this embodiment, when recording the operation mode of external devices in an office setting, the click frequency of the external mouse (i.e., the number of clicks per unit time) and the number of scroll wheel uses are statistically analyzed. For external keyboards, user preferences for key layouts are investigated, such as whether they are accustomed to using external keyboards with numeric keypads. By performing correlation analysis on the connection status logs (recording when the device connects and disconnects) and input event logs (recording the device's input operations), the operation mode of the external devices is determined. For example, when processing large amounts of data, users often connect an external mouse and an external keyboard with a numeric keypad.

[0049] Step S1134: Perform feature fusion on the input method feature data, and concatenate the feature vectors of the keyboard, touchpad and external devices into a unified input method feature vector for subsequent cluster analysis.

[0050] In this embodiment, when performing feature fusion on input method feature data in an office setting, the previously obtained keyboard keystroke frequency feature vector, touchpad swipe trajectory feature vector, and external device operation mode feature vector are concatenated. During the concatenation process, it is ensured that the dimensions of each feature vector correspond reasonably. After concatenation, a unified input method feature vector is formed. This vector contains comprehensive features of user input via keyboard, touchpad, and external devices in an office setting, and can be used for subsequent clustering analysis.

[0051] Step S114: Add each of the typical user habit models to a preset model library to obtain a typical user habit model library. The typical user habit model library includes a model identifier, user group tags, target habit feature vectors, and applicable scenario descriptions. The model identifier is used to uniquely distinguish different models, the user group tags are used to describe the user type corresponding to the model, the target habit feature vectors are used to quantify the behavioral characteristics of the model, and the applicable scenario descriptions are used to explain the usage scenarios corresponding to the model.

[0052] In this embodiment, when adding typical user habit models obtained in office scenarios to a preset model library, a unique model identifier is assigned to each model, such as "BM001" or "BM002," to distinguish different models. User group tags, such as "frequent text processing user" or "email-dominated user," describe the user type corresponding to the model. The target habit feature vector quantifies the behavioral characteristics of the model, including quantified data on frequently used software, input device preferences, and other features. The applicable scenario description clearly states that the model corresponds to an office scenario, ultimately forming a typical user habit model library containing the above information.

[0053] Step S120: Generate a set of simulated operation habits based on the typical user habit model library. The set of simulated operation habits is constructed according to the operation preference features, input timing features and environmental adjustment rules in each typical user habit model, and includes user operation instructions that conform to the behavior patterns of different user groups.

[0054] The process involves several key steps. First, it analyzes the target habit feature vectors of typical user habit models. Then, it combines this with the operation node attributes of the user behavior graph to extract a set of frequently used software (with usage frequencies exceeding a preset frequency) as operation objects, and constructs an operation object association graph. Based on temporal behavior dependencies and path mining results from the user behavior graph, it builds a user operation sequence generator to generate user operation sequences containing user operation instructions that conform to the model's characteristics. These instructions include application startup instructions, input user operation instructions, environment adjustment instructions, and task switching instructions. The generated user operation sequences undergo multi-dimensional rationality verification. Abnormal sequences are corrected using the operation specification library of the user behavior graph. Finally, the verified user operation sequences are combined into a simulated operation habit sequence set. Each user operation sequence corresponds to a typical user habit model, and the simulated operation habit sequence set contains complete operation processes for different user groups in different scenarios.

[0055] In this embodiment, when performing step S120 in an office setting, models corresponding to user group tags such as "high-frequency word processing" and "high-frequency spreadsheet" can be selected from the typical user habit model library. A model association network is constructed by combining this model with the office scenario user behavior graph (including operation nodes and relationships such as document editing and spreadsheet processing), clarifying the operational association logic between each model. Next, the model target habit feature vector is analyzed, and combined with the software usage attributes of the operation nodes in the graph, a set of frequently used software (such as word processing and spreadsheet software) is extracted, and an operation object association graph is constructed. Then, a generator is constructed based on temporal behavior dependencies and graph path mining results (such as the high-frequency path "start software - input content - save document") to generate various operation instructions. Finally, after multi-dimensional verification and correction, these instructions are combined into a simulated operation habit sequence set.

[0056] In this embodiment, step S120 may include sub-steps S121-S124, which will be described in detail below.

[0057] Step S121: Select typical user habit models corresponding to each user group label from the typical user habit model library, and construct a model association network in combination with the user behavior graph as the basis for generating simulated operation habit sequences.

[0058] In this embodiment, in an office scenario, models corresponding to tags such as "high-frequency word processing," "high-frequency spreadsheet," and "high-frequency email communication" are selected from a typical user habit model library. The user behavior graph includes operation nodes and associated edges (e.g., "starting software" is associated with "entering document") in an office scenario, such as "launching word processing software," "keyboard input," and "saving document." When constructing the model association network, the selected models are used as nodes, and network edges are constructed based on the overlap of the corresponding operation paths of each model in the graph (e.g., both the "word processing" and "email communication" models contain the "save document" operation path). The association strength of the edges is labeled, and the resulting model association network provides a basis for the subsequent generation of simulation sequences.

[0059] Step S122: Analyze the target habit feature vector of the typical user habit model, combine it with the operation node attributes of the user behavior graph, extract the set of high-frequency software used with a frequency higher than the preset frequency as the operation object, and construct the operation object association graph.

[0060] In this embodiment, the target habit feature vector of the "high-frequency word processing" model in an office setting is analyzed to extract software usage frequency data. Combined with the "usage frequency attribute" of operation nodes such as "word processing software" and "spreadsheet software" in the user behavior graph, software with usage frequencies higher than a preset frequency is selected to form a set of high-frequency used software (such as word processing, spreadsheet, and email software). When constructing the operation object association graph, these software programs are used as nodes, and edges are constructed based on the association relationships of software operations in the graph (e.g., "word processing software" and "email software" have a "document sending" association). The association probabilities of the edges are labeled to complete the construction of the operation object association graph.

[0061] Step S123: Based on the path mining results of temporal behavior dependencies and user behavior graphs, construct a user operation sequence generator to generate user operation sequences containing user operation instructions that conform to the model features. The user operation instructions include application startup instructions, input user operation instructions, environment adjustment instructions, and task switching instructions.

[0062] In this embodiment, for the "high-frequency word processing" model in an office scenario, the temporal behavior dependency relationship includes the operation interval and transition probability of "starting software - inputting content - saving document". User behavior graph path mining results show that the model corresponds to the high-frequency path of "starting word processing software - keyboard input of document - adjusting screen brightness - saving document". Based on this, a generator is constructed to generate application startup instructions (starting word processing software), input user operation instructions (keyboard input of document), environment adjustment instructions (adjusting screen brightness), and task switching instructions (switching to email software), forming a user operation sequence that conforms to the model characteristics.

[0063] In this embodiment, step S123 may include sub-steps S1231-S1237, which will be described in detail below.

[0064] Step S1231: Extract temporal behavior dependency parameters from the core feature vector of the typical user habit model. The temporal behavior dependency parameters include operation interval distribution characteristics, operation transition probability matrix, and operation duration pattern. The operation interval distribution characteristics are obtained by statistically analyzing the frequency distribution of time intervals between adjacent operations in user habit data. The operation transition probability matrix is ​​obtained by calculating the transition probability between different operation types using a Markov chain model. The operation duration pattern is obtained by analyzing the duration distribution characteristics of similar operations.

[0065] In this embodiment, temporal behavior dependency parameters are extracted from the core feature vector of the "high-frequency word processing" model in an office setting. The operation interval distribution features are obtained by statistically analyzing the frequency distribution of time intervals between adjacent operations such as "launching software" and "inputting content," and "inputting content" and "saving document" in the user habit data of this model. The operation transition probability matrix is ​​obtained by calculating the transition probabilities between different operation types such as "launching software" to "inputting content" and "inputting content" to "adjusting brightness" using a Markov chain model. The operation duration pattern is obtained by analyzing the duration distribution features of similar operations such as "keyboard input" and "document saving," forming complete temporal behavior dependency parameters.

[0066] Step S1232: Construct a temporal behavior state transition model based on the temporal behavior dependency parameters. The temporal behavior state transition model takes the current operation type as the state, predicts the next hop operation type through the operation transition probability matrix, determines the operation execution time point by combining the operation interval distribution characteristics, and sets the operation execution duration according to the operation duration pattern. The model outputs a temporal operation framework that includes operation type, execution time point, and duration.

[0067] In this embodiment, a temporal behavior state transition model is constructed based on the temporal behavior dependency parameters of the "high-frequency word processing" model in an office scenario. The model takes "starting word processing software" as the current state and predicts the next hop operation type as "keyboard input document" using the operation transition probability matrix. Combining the operation interval distribution characteristics, it determines that "keyboard input" will be executed at interval t1 after "starting the software." Based on the operation duration pattern, the duration of "keyboard input" is set to t2. The model ultimately outputs a temporal operation framework containing information such as "operation type: keyboard input document, execution time point: t1 after startup, duration: t2."

[0068] Step S1233: Create a multi-level architecture for the user operation sequence generator. The multi-level architecture includes a feature input layer, a time-series decision layer, and an instruction generation layer. The feature input layer receives the core feature vectors of a typical user habit model, including a set of frequently used software, input device preference weights, and environmental parameter adjustment ranges.

[0069] The temporal decision layer loads the temporal behavior state transition model and outputs the type, timestamp, and associated entity of the next operation based on the current operation state and the parameters of the feature input layer. The instruction generation layer generates specific user operation instructions based on the output of the temporal decision layer, including instruction identifier, operation object, parameter value, and execution sequence.

[0070] In this embodiment, a multi-level architecture for a user operation sequence generator is designed for an office scenario. The feature input layer receives the core feature vector of the "high-frequency text processing" model, such as the set of frequently used software (text processing, email software), input device preference weights (keyboard x%, touchpad y%), and environmental parameter adjustment ranges (brightness AB, volume CD). The timing decision layer loads the timing behavior state transition model, and based on the current "keyboard input" state and input parameters, outputs the next operation type "save document", timestamp "t3 after input", and associated entity "text processing software". The instruction generation layer generates an instruction based on this (identifier: CMD001, operation object: text processing software, parameter value: default save path, execution timing: t3 after input).

[0071] Step S1234: Generate an application operation instruction sequence through the user operation sequence generator, determine the application operation object based on the set of frequently used software, and generate application start instruction, function module call instruction and application close instruction according to the operation transition probability matrix. The timing of the application start instruction conforms to the high-frequency start period pattern in the operation interval distribution characteristics, and the parameter value of the function module call instruction is determined according to the function module call frequency in the model.

[0072] In this embodiment, the generator in the office scenario determines the operation object based on the set of frequently used software (word processing and email software) in the "high-frequency word processing" model. According to the operation transition probability matrix, it generates application startup instructions (start word processing software, start email software), function module call instructions (word processing software "paragraph settings", "insert table", email software "attach attachment"), and shutdown instructions. The timing of the startup instructions conforms to the high-frequency startup periods of "t4-t5 in the morning, t6-t7 in the afternoon" in the operation interval distribution characteristics; the parameter values ​​of the function module call instructions (such as "line spacing: default value" in "paragraph settings") are determined according to the call frequency of that module in the model.

[0073] Step S1235: Generate an input operation instruction sequence. Select keyboard operation or touchpad operation as the primary input method based on the input device preference weight. Keyboard operation instructions include key combination sequence and duration parameters. The key combination sequence is generated based on the usage frequency of system shortcut keys and application shortcut keys in the model, and the duration parameter is set according to the operation duration pattern. Touchpad operation instructions include sliding trajectory parameters, click count parameters, and pressure parameters. The sliding trajectory parameters are generated through touchpad sliding trajectory feature data in the model, and the pressure parameter reflects the touch pressure characteristics in the input device preference weight.

[0074] In this embodiment, the input device preference weights for the "high-frequency word processing" model in an office scenario are keyboard x%, touchpad y%, and the generator selects the keyboard as the primary input method. Keyboard operation commands include key combination sequences such as "Ctrl+S" and "Ctrl+B" (generated based on the frequency of shortcut key usage in the model), and the duration parameter (e.g., "Ctrl+S" press duration t8) is set according to the operation duration pattern. If touchpad operation is involved, the command includes sliding trajectory parameters (e.g., "horizontal sliding length t9," generated based on model trajectory features), click count parameters (e.g., "double-click"), and pressure parameters (e.g., "medium pressure," reflecting the touch pressure characteristics in the preference weights).

[0075] Step S1236: Generate an environmental adjustment command sequence. Based on the environmental parameter adjustment range, determine the target values ​​for brightness adjustment, volume adjustment, and power mode type. Combined with the operation interval distribution characteristics in the timing behavior dependency parameters, determine the trigger time point for the environmental adjustment command. The trigger time point is consistent with the timing of application operation commands and input operation commands. For example, a brightness adjustment command is generated at a preset time interval after the application starts, and a volume adjustment command is generated during periods when the input operation frequency decreases.

[0076] In this embodiment, the environmental parameter adjustment range for the "high-frequency word processing" model in an office scenario is brightness AB, volume CD, and power mode "balanced mode". Based on this, the generator determines the target values ​​for brightness adjustment (e.g., A1), volume (e.g., C1), and power mode "balanced mode". Combining the operation interval distribution characteristics, a brightness adjustment command is triggered at an interval t10 after "starting the word processing software", and a volume adjustment command is triggered during periods when "keyboard input frequency is below the threshold" (e.g., input interval exceeds t11), ensuring that the triggering time is consistent with the timing of the application and input operation commands.

[0077] Step S1237: The application operation instruction sequence, input operation instruction sequence, and environmental adjustment instruction sequence are integrated in a temporal manner using a temporal behavior state transition model. The operation instructions contained in the application operation instruction sequence, input operation instruction sequence, and environmental adjustment instruction sequence are sorted according to the operation timestamp to form a complete user operation sequence that conforms to the behavioral characteristics of a typical user habit model. The user operation sequence includes application operation instructions, input operation instructions, and environmental adjustment instructions arranged in order of timestamp.

[0078] In this embodiment, the temporal behavior state transition model in the office scenario integrates the three types of instruction sequences of the "high-frequency word processing" model in a temporal sequence. The timestamps of each instruction are extracted, such as "start word processing software (t12)", "keyboard input document (t12+t1)", "brightness adjustment (t12+t10)", and "save document (t12+t1+t3)", and sorted by timestamp from smallest to largest to form a complete user operation sequence: t12 starts software → t12+t1 keyboard input → t12+t10 adjusts brightness → t12+t1+t3 saves document. This sequence conforms to the model's behavioral characteristics.

[0079] Step S124: Perform multi-dimensional rationality verification on the generated user operation sequence, correct abnormal sequences by combining the operation specification library of user behavior graph, and combine the verified user operation sequences into a simulated operation habit sequence set. Each user operation sequence corresponds to a typical user habit model. The simulated operation habit sequence set contains the complete operation process of different user groups in different scenarios.

[0080] In this embodiment, the operation sequences generated by models such as "high-frequency word processing" and "high-frequency spreadsheet" in an office setting are validated from multiple dimensions. Logical validation references the user behavior graph operation specification library (e.g., "saving document" must follow "input content") to correct the abnormal sequence "save after closing software"; temporal validation checks whether the interval between "starting software" and "input content" conforms to the high-frequency interval range of the graph, correcting any abnormal interval sequences. The sequences corresponding to each validated model are combined to form a set of simulated operation habit sequences containing the complete operation flow of different user groups in an office setting.

[0081] Step S130: Inject the simulated operation habit sequence set into the laptop system and simultaneously collect system adaptation response data. The system adaptation response data includes resource usage feature vectors and operation response latency data. The resource usage feature vectors represent the real-time load status of the central processing unit, memory, and graphics processing unit, and the operation response latency data represents the time interval from the injection of the user operation command to the completion of the system function.

[0082] In this embodiment, when injecting the simulated operation habit sequence set into the laptop system in an office scenario, it is necessary to first ensure that the initial state of the laptop system is consistent with the system state commonly used by users in an office scenario, such as pre-installing frequently used word processing software, spreadsheet software, etc., and that system parameters (such as default input method and screen resolution) conform to the conventional settings of an office scenario. The injection process must be carried out sequentially according to the timing relationship of each instruction in the simulated operation habit sequence set to avoid distortion of the collected response data due to disordered instruction execution order.

[0083] When synchronously acquiring system adaptation response data, the resource usage feature vector needs to capture the load status of the CPU, memory, and graphics processor in real time. For example, when injecting the "Start word processing software" command, record the load percentage of each CPU core, the percentage of memory usage, and the percentage of graphics processor rendering load; when injecting the "Enter document content and insert table" command, continuously record the load changes of the above hardware resources, forming a feature vector composed of multiple sets of resource usage data. Operation response latency data needs to accurately record the time interval from command injection to system function completion, such as the time from issuing the "Start word processing software" command to the software's main interface fully loading and displaying, and the time from issuing the "Save document" command to the system indicating that saving is complete. This data needs to be correlated with the corresponding operation commands to ensure the accuracy of subsequent analysis.

[0084] In this embodiment, step S130 may include sub-steps S131-S136, which will be described in detail below.

[0085] Step S131: Configure the laptop test environment, which includes the operating system version, driver version, pre-installed application version and hardware configuration parameters, so that the test environment is consistent with the actual use environment of mainstream users.

[0086] In this embodiment, when configuring the laptop test environment in an office setting, the operating system version should be a mainstream version used in office settings to ensure it matches the system version actually used by most users; the driver version should be a stable version corresponding to the hardware (such as graphics card, sound card, touchpad) to avoid hardware malfunctions due to outdated or outdated driver versions; the pre-installed application version should be consistent with the mainstream version of frequently used software in the typical user habit model library, such as word processing software and spreadsheet software, which should be a recently updated stable version to ensure that simulated operation commands can be executed normally.

[0087] Hardware configuration parameters need to be adjusted to the mainstream configuration level in office scenarios. For example, the memory capacity should be set to the capacity specification commonly used by most office users, the hard drive should be selected as the mainstream solid-state drive type and the appropriate partition size should be configured, and the graphics card parameters should be set to the performance mode commonly used in office scenarios. This will prevent the test results from deviating from the actual user scenario due to excessively high or low hardware configuration.

[0088] Step S132: Invoke the user operation sequence injection tool, which includes a software interface calling module, an input device simulation module, and an environmental parameter adjustment module. The software interface calling module starts and controls the application through the system API, the input device simulation module simulates keyboard and touchpad input signals through a hardware interface, and the environmental parameter adjustment module adjusts parameters such as brightness and volume through the system settings interface.

[0089] In this embodiment, when the user operation sequence injection tool is invoked in an office setting, the software interface calling module needs to use the laptop system's API to launch and control the application. For example, the "launch word processing software" command is implemented by calling the word processing software's launch API, and the "save document" command is implemented by calling the software's "save document" API, ensuring that the application's launch and operation are consistent with the effect of the user's manual operation.

[0090] The input device simulation module needs to simulate keyboard and touchpad input signals through a hardware interface. When simulating keyboard input, it needs to generate electrical signals consistent with the triggering of real keyboard keys. For example, when simulating the "Ctrl+S" shortcut key input, it needs to generate the corresponding key trigger signal. When simulating touchpad input, it needs to generate signals consistent with touchpad sliding and clicking. For example, when simulating touchpad sliding to select text, it needs to generate the corresponding sliding trajectory signal to ensure that the input operation can be accurately recognized by the system.

[0091] The environmental parameter adjustment module needs to adjust parameters such as brightness and volume through the system settings interface. For example, it can implement screen brightness adjustment commands by calling the system's screen brightness adjustment interface and volume adjustment commands by calling the system's volume control interface. The adjustment process must be consistent with the response characteristics of the system's native adjustment functions to avoid adjustment delays or parameter anomalies.

[0092] Step S133: Load the simulated operation habit sequence set into the user operation sequence injection tool, parse the instruction type, operation object, parameter value and timing information of each user operation sequence, and generate an instruction execution plan. The instruction execution plan includes the execution order and time interval of each user operation instruction.

[0093] In this embodiment, after loading the simulated operation habit sequence set into the injection tool in an office scenario, the tool needs to first parse the specific information of each user operation sequence. Instruction type parsing needs to distinguish between application startup instructions, input instructions, environment adjustment instructions, etc., such as "start word processing software" being an application startup instruction, and "keyboard input 'meeting minutes'" being an input instruction; operation object parsing needs to clarify the target corresponding to the instruction, such as the operation object of the "save document" instruction being the currently edited word processing document; parameter value parsing needs to extract the specific setting parameters in the instruction, such as the target range midpoint in "adjust screen brightness to the midpoint of the target range"; timing information parsing needs to obtain the time interval between each instruction, such as the time interval between "start word processing software" and "start inputting document content".

[0094] The instruction execution plan generated based on the analysis results needs to clearly define the execution order of each user operation instruction to ensure consistency with the user's habitual operation process; at the same time, it is necessary to accurately set the time interval between each instruction. For example, based on the pattern in the user habit data of "start input after x time after starting the software", the time interval of the corresponding instruction should be set to avoid excessive deviation between the simulated operation and the real user operation due to unreasonable time intervals.

[0095] Step S134: Activate the user operation sequence injection tool and inject user operation commands into the laptop system sequentially according to the instruction execution plan. During the injection process, maintain time intervals consistent with the temporal behavior dependencies in a typical user habit model to ensure the authenticity of the operation flow.

[0096] In this embodiment, after the injection tool is launched in an office setting, the tool must strictly follow the order of the instruction execution plan to inject user operation instructions. For example, it must inject instructions in the order of "launch word processing software - type 'meeting minutes' on the keyboard - adjust screen brightness - save document - close software", without skipping any instructions or changing the order of instructions.

[0097] During the injection process, the time intervals between each instruction must be consistent with the temporal behavioral dependencies in a typical user habit model. For example, if the model shows that after a user starts the word processing software, they begin inputting on average after a time interval of t1, then after injecting the "start word processing software" instruction, a time interval of t1 is needed before injecting the "keyboard input 'meeting minutes'" instruction. Similarly, if the user adjusts the screen brightness on average after completing input, then after injecting the input instruction, a time interval of t2 is needed before injecting the brightness adjustment instruction. By maintaining consistent time intervals, the simulated operation process is ensured to closely match the actual user operation process.

[0098] Step S135: Simultaneously with the injection of user operation instructions, the response data collector is started. The response data collector collects resource usage feature vectors through kernel-mode monitoring, including the utilization rate of each core of the central processing unit, memory usage, graphics processor rendering frame rate, and storage device read / write throughput. It also collects operation response latency data through user-mode monitoring, including application startup time, window switching latency, and input response time.

[0099] In this embodiment, when the response data collector is started in an office scenario, the kernel-mode monitoring driver needs to directly interact with the laptop's hardware kernel to collect resource usage feature vectors in real time. When collecting the utilization rate of each CPU core, it is necessary to obtain the load percentage of each core per unit time to form multi-core utilization data; when collecting memory usage, it is necessary to record the used memory capacity, free memory capacity, and memory read / write speed to form memory usage feature data; when collecting the graphics processor rendering frame rate, it is necessary to count the number of rendering frames of the graphics processor per unit time, especially when executing instructions that require graphics processing such as "insert table" and "display high-definition image", it is necessary to focus on recording frame rate changes; when collecting the storage device read / write throughput, it is necessary to record the read / write speed of the storage device when executing instructions such as "save document" and "open file" to form storage device load data. The above data together constitute the resource usage feature vector.

[0100] The user-mode monitoring program needs to collect operation response latency data through the system's user-mode interface. When collecting application startup time, it records the time from when the application startup command is issued to when the application's main interface is fully loaded and operable; when collecting window switching latency, it records the time from when the window switching command is issued to when the target window becomes the active window and the interface refresh is completed; when collecting input response time, it records the time from when the command to input via keyboard, touchpad, etc., is issued to when the system provides feedback on the operation result on the interface, such as the time from when the command to input text is issued to when the text is displayed in the document.

[0101] Step S136: Align the collected resource occupancy feature vector and operation response delay data with the instruction timestamps of the user operation sequence to generate a time-stamped system adaptation response dataset. Each user operation instruction corresponds to a set of associated response data. The system adaptation response dataset includes multiple system adaptation response datasets.

[0102] In this embodiment, when performing data alignment in an office setting, it is necessary to first extract the timestamp of each instruction issued in the user operation sequence, and then match the collection timestamp corresponding to the collected resource usage feature vector, the recording timestamp corresponding to the operation response delay data, and the instruction timestamp. For example, if the timestamp of the instruction "start word processing software" is T1, the CPU, memory, and GPU resource data collected at time T1 and within a short period before and after T1 are used as the resource usage feature vector corresponding to this instruction, and the application startup time recorded from T1 onwards is used as the operation response delay data corresponding to this instruction.

[0103] By aligning with timestamps, each user operation command is ensured to have a unique set of associated response data. For example, the command "keyboard input 'meeting minutes'" corresponds to a set of resource usage data and input response time data during the input process, and the command "save document" corresponds to a set of resource usage data and save response time data during the saving process. The response data corresponding to all commands are integrated to generate a time-stamped system adaptation response dataset. This dataset fully records the system response status corresponding to each simulated operation command in an office scenario. Step S140: A multi-dimensional correlation analysis is performed between the system adaptation response data and the typical user habit model library. By comparing the system adaptation response data corresponding to different typical user habit models, user habit adaptation indexes and key adaptation bottleneck paths are calculated. The user habit adaptation indexes characterize the laptop system's adaptability to specific user habits, and the key adaptation bottleneck paths characterize the correlation between user operation sequences that cause abnormal system responses and system components.

[0104] In this embodiment, when performing multi-dimensional correlation analysis in an office setting, the system adaptation response data needs to be grouped according to the corresponding typical user habit models. For example, the response data generated by simulated operation commands corresponding to the "word processing - keyboard-dependent" model is grouped into one group, and the response data corresponding to the "spreadsheet - touchpad operation" model is grouped into another group. When comparing different groups of data, the focus is on analyzing the differences in resource consumption feature vectors and operation response latency data. For example, comparing indicators such as CPU utilization during application startup, peak memory usage, and application startup time in the two groups of data can help determine the differences in how the laptop system adapts to different user habits.

[0105] When calculating user habit adaptation metrics, it's necessary to consider performance dimensions that users care about in office scenarios, such as application response speed and hardware resource stability. Resource usage characteristics and operation response latency data should be weighted according to user sensitivity and then comprehensively evaluated to obtain metrics that reflect the system's adaptability to specific user habits. When analyzing key adaptation bottleneck paths, it's necessary to correlate abnormal response data with corresponding user operation sequences and system components. For example, if the memory usage rate and response latency for the command "insert a large amount of data into a spreadsheet" abnormally increase in a certain set of data, it's necessary to locate the correlation between this operation sequence and memory components, identifying insufficient memory resources as the adaptation bottleneck and forming key adaptation bottleneck paths.

[0106] In this embodiment, step S140 may include sub-steps S141-S145, which will be described in detail below.

[0107] Step S141: Group the multiple system adaptation response data according to their corresponding typical user habit models to obtain a dedicated response data group for each typical user habit model. The dedicated response data group includes a resource consumption feature vector sequence and an operation response delay data sequence corresponding to that typical user habit model.

[0108] In this embodiment, when grouping data in an office setting, it is necessary to first identify the typical user habit model identifier corresponding to the system adaptation response data, such as "BM001" (corresponding to the "word processing - keyboard dependent" model) and "BM002" (corresponding to the "spreadsheet - touchpad operation" model) marked in the data. The data is then classified according to the model identifier, and a dedicated response data group is constructed for each model.

[0109] The resource consumption feature vector sequence in each dedicated response data group needs to be arranged in the order of operation command execution. For example, in the dedicated group of the "BM001" model, it contains the resource consumption feature vectors corresponding to commands such as "start word processing software", "input document content", and "save document". The operation response delay data sequence is also arranged in the order of commands, including the application startup time, input response time and other data corresponding to each command, to ensure that each data group can completely reflect the system response process under the simulation operation of the corresponding model.

[0110] Step S142: Perform statistical analysis on each dedicated response data group to calculate the average resource usage, resource usage fluctuation coefficient, average response latency, and response latency jitter rate. The average resource usage reflects the average load level of the system under this user habit model; the resource usage fluctuation coefficient reflects the stability of the load; the average response latency reflects the overall response speed; and the response latency jitter rate reflects the smoothness of the response.

[0111] In this embodiment, when performing statistical analysis on the dedicated response data group in an office scenario, the calculation of the average resource usage requires extracting all data from the resource usage feature vector sequence in the dedicated response data group. This includes dimensions such as the utilization rate of each core of the central processing unit, memory usage, the rendering frame rate of the graphics processor, and the read / write throughput of the storage device. The average of all data under each dimension is calculated to obtain the average resource usage for each dimension. The combined average of each dimension can reflect the average load level of the system under the corresponding typical user habit model. For example, the average resource usage of the dedicated group of the "word processing - keyboard dependent" model can reflect the average load of the system in handling high-frequency text input, document saving, and other operations of this type of user.

[0112] When calculating the resource usage fluctuation coefficient, it is necessary to first determine the dispersion of data for each resource dimension, and then combine it with the mean resource usage for the corresponding dimension. The fluctuation coefficient is obtained by reflecting the relationship between the data dispersion and the mean. The smaller the fluctuation coefficient, the smoother the load change of the corresponding system resources under the user habit model, and the higher the stability. For example, if the memory usage fluctuation coefficient is small in the "spreadsheet-touchpad operation type" model group, it indicates that the memory load is stable when the system processes spreadsheet data editing and touchpad operation for this type of user.

[0113] The calculation of the average response latency requires extracting all data from the operation response latency data sequence in the dedicated response data group, including application startup time, window switching latency, and input response time. The average of each type of latency data is then calculated to obtain the average response latency for each type. The average response latency, which is composed of the averages of all types, can reflect the overall response speed of the system under the corresponding user habit model. For example, the average response latency of the dedicated group of the "email communication - external device assisted type" model can reflect the overall response speed of the system in handling commands such as sending emails and operating external mice for this type of user.

[0114] Calculating response latency jitter rate requires analyzing the variation range of response latency data for each type. The jitter rate is obtained by measuring the degree to which the latency data deviates from the average response latency. The lower the jitter rate, the more stable the system's response time for this type of user operation. For example, if the input response latency jitter rate is low in the "Word Processing - Keyboard Dependent" model group, it indicates that when the user performs continuous keyboard input, the time difference in the system's feedback of the input result is small, and the response is stable.

[0115] Step S143: Invoke the pre-built user habit adaptation index calculation model, and weight and fuse the resource consumption feature and response latency feature to obtain the user habit adaptation index. The weights of the resource consumption feature and response latency feature are determined according to the user's sensitivity to different performance indicators. For example, office users are more sensitive to response latency than resource consumption, and entertainment users are more sensitive to graphics processor frame rate than other indicators.

[0116] In this embodiment, when calling the user habit adaptation index calculation model in an office scenario, it is first necessary to clarify the specific dimensions of the resource consumption characteristics and response latency characteristics of the model input. The resource consumption characteristics include statistical values ​​of dimensions such as CPU load, memory usage, and GPU load, while the response latency characteristics include statistical values ​​of dimensions such as application startup latency, input response latency, and window switching latency.

[0117] When determining the weights, the results of a survey on user performance needs in office scenarios are used. Office users are more concerned about the system's response speed after issuing commands when handling daily operations such as documents and emails. Therefore, higher weights are assigned to response latency features and relatively lower weights are assigned to resource consumption features. For example, if a user's sensitivity to response latency is x times that of resource consumption, then the weight of the response latency feature is x times that of the resource consumption feature.

[0118] The model obtains a single user habit adaptation index by multiplying the resource consumption features of each dimension with their corresponding weights, and the response latency features of each dimension with their corresponding weights, and then fusing the two weighted results. The higher the adaptation index value, the stronger the laptop system's ability to adapt to the operating habits of the user group corresponding to the typical user habit model. For example, a high adaptation index for the "word processing-keyboard dependent" model indicates that the system can better adapt to the high-frequency text input and document operation habits of this type of user.

[0119] Step S144: By comparing the user habit adaptation index of different typical user habit models, identify typical user habit models whose adaptation index is lower than the set threshold, and determine the user group with adaptation shortcomings of the laptop system.

[0120] In this embodiment, when comparing the adaptability indicators of different typical user habit models in an office setting, it is necessary to first set an adaptability indicator threshold. This threshold is determined based on the system performance level acceptable to most users in an office setting. If the adaptability indicator of a typical user habit model is lower than this threshold, it indicates that the system's ability to adapt to the operating habits of the user group corresponding to the model is insufficient. This user group is the user group with the shortcoming of the laptop system's adaptability.

[0121] For example, comparing the compatibility metrics of the three models "word processing - keyboard dependent", "spreadsheet - touchpad operation", and "email communication - external device assisted", if the metrics of the "spreadsheet - touchpad operation" model are below the threshold, it indicates that the system's performance is not up to the acceptable level for most users when handling high-frequency operations such as editing spreadsheet data and selecting cells by sliding on the touchpad. This type of office user who uses spreadsheets and relies on touchpad operation is the user group with the system's compatibility shortcomings.

[0122] Step S145: Perform bottleneck path analysis on the dedicated response data group corresponding to the user group with adaptation shortcomings. By associating high-frequency user operation commands and abnormal resource usage data in the user operation sequence, locate the target operation link and target system component that causes the adaptation index to fall below the set threshold. For example, frequent application switching leads to excessive memory usage, or high brightness adjustment leads to a decrease in battery life.

[0123] In this embodiment, when analyzing the dedicated response data group corresponding to the user group with the adaptation shortcomings in the office scenario, the high-frequency operation commands of the user operation sequence in the dedicated group are first extracted. For example, the high-frequency commands of the "spreadsheet-touchpad operation type" user group may be "insert multiple rows of data", "touchpad slide to filter table content", "save large table file", etc.

[0124] Next, the high-frequency operation commands are associated with the corresponding resource usage data to check whether there are any abnormal resource usages during the execution of each high-frequency command. For example, if the memory usage data is far beyond the normal range and continues to rise when executing the "insert multiple rows of data" command, it indicates that there are abnormal resource usages during the execution of this command. If the storage device read / write throughput is abnormally low and the response latency is longer when executing the "save large table file" command, it indicates that there are abnormal storage performances during the execution of this command.

[0125] Based on the type of abnormal resource usage, the target system component is located. Memory usage abnormality corresponds to the memory component, and storage read / write abnormality corresponds to the storage device component. The operation instruction links with abnormal associations mentioned above are the target operation links. The target operation links and target system components together constitute the key adaptation bottleneck path. For example, the "insert multiple rows of data" instruction (target operation link) - memory component (target system component) is the key bottleneck path that leads to the low adaptability of the "spreadsheet-touchpad operation type" model.

[0126] Step S150: Generate a user habit adaptation optimization report based on the user habit adaptation index and the key adaptation bottleneck path. The user habit adaptation optimization report includes user habit type identifiers, system adaptation shortcoming analysis and targeted adjustment suggestions, which are used to guide the adaptation and optimization of the hardware and software parameters of the laptop system.

[0127] In this embodiment, when generating a user habit adaptation and optimization report in an office setting, the user habit type identifier must clearly correspond to each typical user habit model, such as "BM001 (word processing - keyboard dependent type)" and "BM002 (spreadsheet - touchpad operation type)" to ensure that the report can clearly distinguish different user groups.

[0128] The system adaptation bottleneck analysis section needs to combine the adaptation index of each model and the key adaptation bottleneck path to explain in detail the performance of the adaptation bottleneck. For example, the adaptation degree of "BM002 (spreadsheet-touchpad operation type)" is lower than the threshold. The bottleneck is that when executing commands such as "insert multiple rows of data" and "save large spreadsheet files", the memory usage is too high and the storage read and write is slow, resulting in longer operation response delays.

[0129] Targeted adjustment recommendations should propose hardware and software optimization solutions for key adaptation bottlenecks. On the hardware side, suggestions could include adjusting memory configuration parameters and optimizing storage device read / write modes. On the software side, suggestions could include optimizing spreadsheet software data processing algorithms and improving touchpad operation response logic. The report should be clearly structured to enable technical personnel to accurately optimize the laptop system's hardware and software parameters, improving the system's adaptability to the habits of various office user groups.

[0130] In this embodiment, step S150 may include sub-steps S151-S155, which will be described in detail below.

[0131] Step S151: Based on the user habit adaptability index of each typical user habit model, generate an adaptability distribution heatmap. The horizontal axis of the adaptability distribution heatmap represents user habit type, the vertical axis represents performance index dimension, and the color intensity indicates the adaptability level, intuitively displaying the adaptability of different user groups.

[0132] In this embodiment, when generating a heatmap of adaptability distribution in an office setting, the horizontal axis should list the user habit types corresponding to all typical user habit models, such as "word processing - keyboard dependent type", "spreadsheet - touchpad operation type", "email communication - external device assisted type", etc., with each type occupying an independent interval on the horizontal axis.

[0133] The vertical axis needs to define performance metrics dimensions, covering resource consumption-related dimensions (such as average CPU load and average memory usage) and response latency-related dimensions (such as average application startup latency and average input response latency), with each dimension occupying a separate row on the vertical axis.

[0134] The color settings for heatmaps must follow a consistent rule: darker colors indicate higher adaptability, and lighter colors indicate lower adaptability. For example, using a gradient from light blue to dark blue, light blue corresponds to low adaptability, and dark blue corresponds to high adaptability. The adaptability indicators of each user habit type across various performance metrics are mapped to corresponding colors in the heatmap cells according to the color rules. The resulting heatmap allows technical personnel to intuitively see which performance metrics show high and which show low adaptability for a particular user habit type. For example, "word processing - keyboard dependent" shows a darker color (high adaptability) for input response latency and a lighter color (low adaptability) for memory usage.

[0135] Step S152: For the trigger operation nodes in the critical adaptation bottleneck path, generate operation flow optimization strategies. The operation flow optimization strategies include adjusting the software default settings, optimizing the shortcut key layout, and simplifying the multi-task switching steps. For users who frequently switch applications, add support for quick application switching gestures.

[0136] In this embodiment, when generating strategies for trigger operation nodes for critical adaptation bottleneck paths in an office scenario, if the trigger operation node is the "insert multiple rows of data" command for the "spreadsheet-touchpad operation type" group, adjusting the software's default settings can optimize the default caching mechanism of the "insert data" function in the spreadsheet software, reducing redundancy in temporary data storage during data insertion; optimizing the shortcut key layout can set more user-friendly shortcut key combinations for the "insert multiple rows of data" function in the spreadsheet software, such as setting shortcut keys based on the key positions commonly used by office users.

[0137] If the triggering node is the "frequent switching between email clients and word processing software" group of "email communication - external device assistance type", simplifying the multi-task switching steps can optimize the system's task switching logic and reduce the process loading steps during switching; add support for quick application switching gestures, and you can set up the system to switch between these two frequently used applications directly through specific touchpad swipe gestures (such as three-finger left and right swipes), without having to click to switch through the taskbar, thus improving switching efficiency.

[0138] Step S153: For resource consumption nodes in the critical adaptation bottleneck path, generate hardware resource configuration optimization strategies, including memory allocation adjustment strategies, graphics processor parameter optimization strategies, and storage device cache optimization strategies.

[0139] In this embodiment, when generating strategies for resource-consuming nodes in an office scenario, if the resource-consuming node is a memory component (such as the "insert multiple rows of data" instruction causing abnormal memory usage), the memory allocation adjustment strategy can set the initial memory allocation amount when the spreadsheet software starts. Based on the memory requirements of the software's high-frequency operations, the initial allocation amount can be appropriately increased, while the system's memory reclamation mechanism can be optimized to release memory space that the software no longer uses in a timely manner.

[0140] If the resource-consuming node is a graphics processor component (such as the "display high-definition tables and charts" instruction causing excessive graphics processor load), the graphics processor parameter optimization strategy can adjust the graphics processor's rendering mode, adopt a more efficient rendering algorithm for table and chart display scenarios, and reduce resource consumption during the rendering process; at the same time, the performance priority of the graphics processor for office software can be set to ensure that the graphics processor can allocate resources first when office software is used.

[0141] If the resource-consuming node is a storage device component (such as the "save large spreadsheet file" instruction causing slow storage read / write), the storage device caching optimization strategy can increase the storage device's cache capacity and improve the read / write speed of temporary data; at the same time, optimize the storage device's read / write scheduling algorithm to prioritize the processing of file save and open instructions from office software, reducing instruction queuing time.

[0142] Step S154: Generate software performance optimization strategies for response latency nodes in the critical adaptation bottleneck path. For example, software performance optimization strategies may include targeted strategies for optimizing the application startup loading process, reducing background process resource consumption, and improving interface rendering efficiency, in order to optimize the application cold start path or add a preloading mechanism for users with slow application startup.

[0143] In this embodiment, when generating strategies for response delay nodes in an office scenario, if the response delay node is an application startup delay (such as a slow response to the "start large spreadsheet software" command), optimizing the application startup loading process can streamline unnecessary plugins and services loaded when the software starts, loading only the core functional modules; adding a preloading mechanism can predict which spreadsheet software the user may start based on user habits when the system is idle, and preload some of the data required for startup, shortening the waiting time when the user actually starts the software.

[0144] If the response delay node is the input response delay (such as slow feedback for the "keyboard input table data" command), reducing background process resource consumption can be achieved by setting the office software to automatically limit the resource usage of other non-essential background processes in the system during runtime, ensuring that the office software can prioritize accessing resources such as the central processing unit and memory; improving interface rendering efficiency can be achieved by optimizing the interface drawing logic of the office software, reducing the number of times the interface is refreshed after input operations, and improving the input feedback speed.

[0145] Step S155: Integrate the adaptation distribution heatmap, adaptation bottleneck analysis, operation process optimization strategy, hardware resource configuration optimization strategy and software performance optimization strategy to generate a user habit adaptation optimization report.

[0146] The user habit adaptation optimization report includes an execution priority ranking, with priorities determined based on the improvement in adaptation and implementation costs, ensuring that each strategy can efficiently address core adaptation issues.

[0147] In this embodiment, when generating a user habit adaptation optimization report in an office setting, the content is first organized according to the structure of "User Habit Type Identifier - Adaptation Status (including description of corresponding areas in the heatmap) - Adaptation Shortcoming Analysis - Corresponding Optimization Strategies," with each user habit type forming a separate section to ensure a clear and organized report. When prioritizing, the improvement in adaptation after implementing each optimization strategy is first evaluated. For example, if a strategy is expected to improve the adaptation of the "spreadsheet-touchpad operation type" model by x units, and another strategy is expected to improve it by y units (x is greater than y), then the former will have a greater improvement. Next, the implementation cost is evaluated, including hardware costs (such as the cost of increasing memory) and software development costs (such as the development resources required to optimize the application startup process). Strategies with lower costs are easier to implement.

[0148] Prioritization is determined by combining both factors. Strategies with high improvement and low implementation cost are listed as the highest priority and implemented first; strategies with high improvement but high implementation cost are listed as medium priority and implemented based on resource availability; strategies with low improvement and high implementation cost are listed as low priority and considered later. For example, the strategy of "optimizing the spreadsheet software startup loading process" (high improvement, low cost) is listed as the highest priority, while the strategy of "increasing storage device cache capacity" (high improvement, high cost) is listed as medium priority. This ensures that each strategy can efficiently solve core adaptation issues according to priority, improving the system's adaptability to various user groups in office scenarios.

[0149] Based on the above, such as Figure 3 The diagram shown is a schematic of a laptop adaptation testing system based on user habits provided in an embodiment of this application. The system includes components such as a processor, a machine-readable storage medium, and input / output devices. The machine-readable storage medium is connected to the processor. The machine-readable storage medium stores programs, instructions, or code, and the processor executes the programs, instructions, or code in the machine-readable storage medium to implement the aforementioned laptop adaptation testing method based on user habits. The laptop adaptation testing system based on user habits can be understood as the system described in this application. Figure 1 The application scenario shown can be a part of the system platform or laptop, or it can be the system platform or laptop itself.

[0150] The machine-readable storage medium may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc. The machine-readable storage medium is used to store a program, which the processor executes upon receiving an execution instruction.

[0151] The processor may be an integrated circuit chip with signal processing capabilities. The processor mentioned above can be, but is not limited to, a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), etc.

[0152] In summary, the laptop adaptation testing method and system based on user habits provided in this application comprehensively collects user habit data across multiple scenarios and uses clustering algorithms to construct a typical user habit model library. This accurately characterizes the differences among different user groups in multiple dimensions, such as software usage preferences, input method characteristics, and environmental setting behaviors. This targeted analysis of user operation behavior characteristics provides a reliable basis for subsequent testing based on real user behavior patterns, significantly improving the relevance and effectiveness of the testing. Furthermore, the generation of simulated operation habit sequence sets based on the typical user habit model library closely matches the actual behavior patterns of different user groups. Injecting these sequences into the laptop system and simultaneously collecting system adaptation response data, including resource consumption feature vectors and operation response latency data, can realistically reflect the performance of the laptop system when facing various actual user habit operations. Compared to traditional standardized testing, this testing method based on real user behavior simulation is better able to reveal potential problems in actual system use.

[0153] Simultaneously, a multi-dimensional correlation analysis was conducted between system adaptation response data and a typical user habit model library to accurately calculate user habit adaptation metrics and key adaptation bottleneck paths. The user habit adaptation metrics clearly quantify the laptop system's adaptability to specific user habits, while the key adaptation bottleneck paths explicitly indicate the correlation between specific user operation sequences leading to abnormal system responses and system components. This provides crucial clues for a deeper understanding of system performance bottlenecks, facilitating targeted optimization. Finally, a user habit adaptation optimization report generated based on the above analysis results, including detailed user habit type identification, system adaptation bottleneck analysis, and targeted adjustment suggestions, provides guidance for optimizing the laptop system's hardware and software parameters. This ensures that optimization work is targeted and effectively improves the system's compatibility with user habits, thereby comprehensively enhancing the laptop system's performance and user experience in real-world usage scenarios and strengthening the product's market competitiveness.

[0154] It should be noted that this embodiment will take necessary measures to adhere to the principle of legal data collection during data acquisition. For example, before data collection, the user is clearly informed that the purpose of the data collection is for laptop compatibility testing to improve product performance and user experience, and the user's explicit consent is obtained. The collection process is strictly limited to a predetermined range of scenarios, such as office, entertainment, and mobile scenarios. Only information related to software usage preference data (including application launch frequency, usage duration, and function module call records), input method characteristic data (keyboard key press frequency, touchpad swipe trajectory, and external device operation mode), and environmental setting behavior data (screen brightness adjustment cycle, volume change pattern, and power management mode switching records) is collected, without exceeding this scope to collect other irrelevant or sensitive information. At the same time, safe and reliable data collection technologies are used to ensure the security of data transmission and storage processes, prevent data leakage and illegal acquisition, and protect user data privacy and the legality of data collection.

[0155] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. The embodiments, implementation methods, and related technical features of this application can be combined and substituted with each other without conflict. The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A laptop compatibility testing method that incorporates user habits, characterized in that, The method includes: Collect user habit data from multiple scenarios and construct a typical user habit model library. Classify the user habit data using a clustering algorithm to obtain various typical user habit models. The typical user habit models correspond to the operational behavior characteristics of different user groups. The user habit data includes software usage preference data, input method feature data, and environmental setting behavior data. Based on the typical user habit model library, a set of simulated operation habit sequences is generated. The set of simulated operation habit sequences is constructed according to the operation preference features, input timing features and environmental adjustment rules in each typical user habit model, and includes user operation instructions that conform to the behavior patterns of different user groups. The simulated operation habit sequence set is injected into the laptop system, and system adaptation response data is collected synchronously. The system adaptation response data includes resource consumption feature vectors and operation response delay data. A multi-dimensional correlation analysis is performed on the system adaptation response data and the typical user habit model library. By comparing the system adaptation response data corresponding to different typical user habit models, user habit adaptation index and key adaptation bottleneck paths are calculated. A user habit adaptation optimization report is generated based on the user habit adaptation index and the key adaptation bottleneck path.

2. The laptop adaptation testing method based on user habits according to claim 1, characterized in that, The process of collecting user habit data from multiple scenarios and constructing a typical user habit model library includes: User habit data is collected in multiple preset scenarios. The software usage preference data includes application launch frequency, usage duration and function module call records. The input method feature data includes keyboard key press frequency, touchpad sliding trajectory and external device operation mode. The environment setting behavior data includes screen brightness adjustment cycle, volume change pattern and power management mode switching records. The user habit data is preprocessed, and a clustering algorithm is used to classify the preprocessed user habit data. The similarity between user behavior feature vectors is calculated and the user habit data is clustered based on the similarity. During the clustering process, the number of clusters is determined according to the data density distribution, so that the clustering results can distinguish user groups with different operating preferences. Feature extraction is performed on each clustering result to obtain the target habit features of the typical user habit model. The target habit features include the set of frequently used software, input device preference weights, environmental parameter adjustment ranges, and time-series behavioral dependencies. Each of the typical user habit models is added to a preset model library to obtain a typical user habit model library, which includes model identifiers, user group tags, target habit feature vectors, and descriptions of applicable scenarios.

3. The laptop adaptation testing method based on user habits according to claim 2, characterized in that, The step of classifying the preprocessed user habit data using a clustering algorithm, and clustering the user habit data based on the similarity between user behavior feature vectors, includes: The preprocessed user habit data is converted into high-dimensional feature vectors. Each feature vector corresponds to a user habit feature in terms of its dimension. The dimensions of the feature vectors include software usage frequency dimension, input method proportion dimension, environmental setting parameter dimension, and time sequence behavior transfer dimension. Density clustering algorithm is used to cluster high-dimensional feature vectors. By calculating the density reachability of data points in the feature space, points that are density connected are divided into a cluster. Cluster radius and minimum sample number parameters are set. The cluster radius is determined by the distance distribution statistics in the feature space, and the minimum sample number is set according to the size of the user group. The effectiveness of the clustering results is evaluated by calculating the cluster similarity of each data point using the silhouette coefficient. The silhouette coefficient evaluates the clustering effect by considering the similarity between samples and within and between clusters. Abnormal clusters with silhouette coefficients below a set threshold are removed to obtain effective clusters. The effective clusters are named and labeled with features. Based on the common features of user habit data within each effective cluster, user group labels are assigned to each effective cluster. The user group labels are determined based on the common features of user habit data within each effective cluster. The feature labels include descriptions of typical user operation behaviors within each effective cluster.

4. The laptop compatibility testing method based on user habits according to claim 1, characterized in that, The generation of a set of simulated operation habit sequences based on the typical user habit model library includes: Typical user habit models corresponding to each user group label are selected from the typical user habit model library, and a model association network is constructed in combination with the user behavior graph as the basis for generating simulated operation habit sequences. The target habit feature vector of a typical user habit model is analyzed, and the operation node attributes of the user behavior graph are combined to extract the set of high-frequency software used with a frequency higher than the preset frequency as operation objects, and an operation object association graph is constructed. Based on the path mining results of temporal behavior dependencies and user behavior graphs, a user operation sequence generator is constructed to generate user operation sequences containing user operation instructions that conform to the model features. The user operation instructions include application startup instructions, input user operation instructions, environment adjustment instructions, and task switching instructions. The generated user operation sequences are subjected to multi-dimensional rationality verification. Abnormal sequences are corrected by combining the operation specification library of user behavior graph. The verified user operation sequences are combined into a set of simulated operation habit sequences. Each user operation sequence corresponds to a typical user habit model. The set of simulated operation habit sequences contains the complete operation process of different user groups in different scenarios.

5. The laptop adaptation testing method based on user habits according to claim 4, characterized in that, Based on the path mining results of temporal behavior dependencies and user behavior graphs, a user operation sequence generator is constructed to generate user operation sequences containing user operation instructions that conform to the model features, including: Temporal behavior dependency parameters are extracted from the core feature vectors of typical user habit models. These parameters include operation interval distribution characteristics, operation transition probability matrix, and operation duration patterns. The operation interval distribution characteristics are obtained by statistically analyzing the frequency distribution of time intervals between adjacent operations in user habit data. The operation transition probability matrix is ​​obtained by calculating the transition probabilities between different operation types using a Markov chain model. The operation duration patterns are obtained by analyzing the duration distribution characteristics of similar operations. A temporal behavior state transition model is constructed based on the temporal behavior dependency parameters. The temporal behavior state transition model takes the current operation type as the state, predicts the next hop operation type through the operation transition probability matrix, determines the operation execution time point by combining the operation interval distribution characteristics, and sets the operation execution duration according to the operation duration pattern. A multi-level architecture for creating a user operation sequence generator is established, comprising a feature input layer, a temporal decision layer, and an instruction generation layer. The feature input layer receives core feature vectors from a typical user habit model, including a set of frequently used software, input device preference weights, and environmental parameter adjustment ranges. The temporal decision layer loads the temporal behavior state transition model and, based on the current operation state and the parameters of the feature input layer, outputs the type, timestamp, and associated entity of the next operation. The instruction generation layer generates specific user operation instructions based on the output of the temporal decision layer, including instruction identifier, operation object, parameter values, and execution timing. The user operation sequence generator generates an application operation instruction sequence, determines the application operation object based on a set of frequently used software, and generates application start instructions, function module call instructions, and application close instructions according to the operation transition probability matrix. The system generates a sequence of input operation instructions. Based on the input device preference weights, it selects either keyboard operation or touchpad operation as the primary input method. Keyboard operation instructions include key combination sequences and duration parameters. The key combination sequences are generated based on the usage frequency of system shortcut keys and application shortcut keys in the model, and the duration parameter is set according to the operation duration pattern. Touchpad operation instructions include sliding trajectory parameters, click count parameters, and pressure parameters. Generate an environmental adjustment command sequence, determine the target values ​​for brightness adjustment, volume adjustment, and power mode type based on the environmental parameter adjustment range, and determine the trigger time point of the environmental adjustment command by combining the operation interval distribution characteristics in the timing behavior dependency parameters; The application operation instruction sequence, input operation instruction sequence, and environmental adjustment instruction sequence are integrated in a temporal manner using a temporal behavior state transition model. The operation instructions included in the application operation instruction sequence, input operation instruction sequence, and environmental adjustment instruction sequence are sorted according to the operation timestamp to form a complete user operation sequence that conforms to the behavioral characteristics of a typical user habit model. The user operation sequence includes application operation instructions, input operation instructions, and environmental adjustment instructions arranged in order of timestamp.

6. The laptop adaptation testing method based on user habits according to claim 1, characterized in that, The step of injecting the simulated operation habit sequence set into the laptop system and synchronously collecting system adaptation response data includes: Configure the laptop test environment, which includes the operating system version, driver version, pre-installed application version, and hardware configuration parameters; The user-operated sequence injection tool is invoked, which includes a software interface calling module, an input device simulation module, and an environmental parameter adjustment module. The simulated operation habit sequence set is loaded into the user operation sequence injection tool, and the instruction type, operation object, parameter value and timing information of each user operation sequence are parsed to generate an instruction execution plan. The instruction execution plan includes the execution order and time interval of each user operation instruction. Start the user operation sequence injection tool and inject user operation commands into the laptop system sequentially according to the instruction execution plan; Simultaneously with the injection of user operation commands, a response data collector is started. The response data collector collects resource usage feature vectors through kernel-mode monitoring, including the utilization rate of each core of the central processing unit, memory usage, graphics processor rendering frame rate, and storage device read / write throughput. It also collects operation response latency data through a user-mode monitoring program, including application startup time, window switching latency, and input response time. The collected resource consumption feature vectors and operation response delay data are aligned with the instruction timestamps of the user operation sequence to generate a time-stamped system adaptation response dataset. Each user operation instruction corresponds to a set of associated response data, and the system adaptation response dataset includes multiple system adaptation response datasets.

7. The laptop adaptation testing method based on user habits according to claim 6, characterized in that, The user-mode monitoring program collects operation response latency data, including application startup time, window switching latency, and input response time, including: Record the timestamp of the application startup command being issued and the timestamp of the first completion of rendering of the application's main window to obtain the application startup time; Record the timestamp of the window switching command being issued and the timestamp of the target window becoming the active window and completing the interface refresh to obtain the window switching delay; Record the timestamp of the user input command and the timestamp of the laptop system's first response to the user input command to obtain the input response time; Outlier processing is performed on the collected operation response delay data. A sliding window filtering algorithm is used to remove abnormal fluctuations caused by transient interference, and retain valid data that reflects the true response characteristics of the system.

8. The laptop adaptation testing method based on user habits according to claim 1, characterized in that, The process involves performing a multi-dimensional correlation analysis between the system adaptation response data and the typical user habit model library. By comparing the system adaptation response data corresponding to different typical user habit models, user habit adaptation indicators and key adaptation bottleneck paths are calculated, including: The system adaptation response data, including multiple data sets, are grouped according to the corresponding typical user habit models to obtain a dedicated response data set for each typical user habit model. The dedicated response data set contains the resource consumption feature vector sequence and the operation response delay data sequence corresponding to the typical user habit model. Perform statistical analysis on each dedicated response data group to calculate the average resource usage, resource usage fluctuation coefficient, average response latency, and response latency jitter rate; The pre-built user habit adaptation index calculation model is invoked to weight and fuse resource consumption characteristics and response latency characteristics to obtain the user habit adaptation index. By comparing the user habit adaptation index of different typical user habit models, we can identify typical user habit models whose adaptation index is lower than a set threshold and determine the user group with adaptation shortcomings of the laptop system. Bottleneck path analysis is performed on the dedicated response data group corresponding to the user group with adaptation shortcomings. By associating high-frequency user operation commands and abnormal resource consumption data in the user operation sequence, the target operation link and target system component that cause the adaptation index to be lower than the set threshold are located. The relationship between the target operation and the target system components is represented as a critical adaptation bottleneck path. Each critical adaptation bottleneck path includes a trigger operation node, a resource consumption node, and a response delay node, which is used to clarify the transmission path of adaptation problems.

9. The laptop adaptation testing method based on user habits according to claim 8, characterized in that, The process of generating a user habit adaptation optimization report based on the user habit adaptation index and the key adaptation bottleneck path includes: Based on the user habit fit index of each typical user habit model, a fit distribution heatmap is generated. The horizontal axis of the fit distribution heatmap represents the user habit type, the vertical axis represents the performance index dimension, and the color intensity indicates the fit level. For the trigger operation nodes in the critical adaptation bottleneck path, generate operation process optimization strategies; For resource-consuming nodes in the critical adaptation bottleneck path, hardware resource configuration optimization strategies are generated, including memory allocation adjustment strategies, graphics processor parameter optimization strategies, and storage device cache optimization strategies. For response latency nodes in critical adaptation bottleneck paths, generate software performance optimization strategies; Based on the integration of adaptation distribution heatmap, adaptation shortcoming analysis, operation process optimization strategy, hardware resource configuration optimization strategy and software performance optimization strategy, a user habit adaptation optimization report is generated.

10. A laptop compatibility testing system that incorporates user habits, characterized in that, The method includes a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the method of any one of claims 1-9.

Images