Personalized office environment configuration method and system based on text analysis and machine learning

Abstract

The invention relates to a personalized office environment configuration method and system based on text analysis and machine learning, and the method specifically comprises the steps: collecting user demands through natural language processing and preliminary clustering analysis, and constructing a user portrait; office environment parameters are defined and classified, a personalized recommendation engine is designed, and an office environment configuration scheme suitable for a user is proposed in combination with collaborative filtering and a deep learning model; according to the method, a recommendation engine is optimized through Monte Carlo simulation and reinforcement learning, and a final configuration scheme is generated, so that more accurate personalized recommendation can be provided, manual operation of a user is reduced in the automatic configuration and implementation process, the configuration efficiency is improved, the configuration scheme can be continuously adjusted and optimized through real-time user feedback and simulation optimization, and the user experience is improved. The method adapts to the change of user requirements, can apply the learning ability of a large model, and provides more comprehensive personalized configuration by integrating and analyzing data from multiple sources, including user historical behaviors, workflow description and the like.

Description

Technical Field

[0001] The present invention relates to the fields of natural language processing, text analysis, and machine learning, and specifically proposes a personalized office environment configuration method and system based on text analysis and machine learning to achieve intelligent and personalized configuration of the office environment. Background Art

[0002] With the rapid development of information technology, intelligent office environment has become one of the key factors for enterprises to enhance their competitiveness. In the configuration of traditional office environment, conventional means usually include questionnaire surveys, manual configuration, simple rule-based recommendations, etc. These methods rely on the user's active input or simple rule matching to achieve a certain degree of personalization, requiring users to spend time and energy to fill out questionnaires or manually adjust configurations. In addition, rule-based recommendations can often only cover limited situations and are difficult to handle complex and changeable personalized needs. Once the configuration is completed, it is difficult to automatically adjust according to changes in user behavior;

[0003] In intelligent office environments, big models have shown broad application potential, such as data analysis and decision support, natural language processing, and the development of intelligent office assistants, but there are no effective applications for the intelligent configuration of office environments.

[0004] In response to the above problems, the present invention proposes a personalized office environment configuration method based on text analysis and machine learning. Through deep learning of user behavior and preferences, accurate personalized recommendations are provided. The automated configuration and implementation process reduces the user's manual operations and improves configuration efficiency. Through real-time user feedback and simulation optimization, the configuration plan can be continuously adjusted and optimized to adapt to changes in user needs. Data from multiple sources, including user historical behavior, workflow descriptions, etc., can be integrated and analyzed to provide comprehensive personalized configuration. Summary of the invention

[0005] In order to address the deficiencies of the prior art, the present invention proposes a personalized office environment configuration method and system based on text analysis and machine learning.

[0006] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0007] A personalized office environment configuration method based on text analysis and machine learning, characterized by comprising the following steps:

[0008] S1. Receive user data and use text analysis to collect requirements;

[0009] S2. Based on the demand collection results, use feature engineering and decision tree classification to build user portraits;

[0010] S3. Define office environment parameters and use hierarchical clustering algorithm to cluster and generate office environment configuration plan;

[0011] S4. Based on the user portrait and the office environment parameters, a personalized recommendation engine is designed using collaborative filtering combined with a deep learning model, and a personalized first configuration solution is generated;

[0012] S5. Simulate and optimize the first configuration scheme by Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme;

[0013] S6. Receive feedback on the second configuration solution, perform fine-tuning and optimization through online learning and real-time user interaction, and generate a final configuration solution.

[0014] Further, the step S1 specifically includes:

[0015] S11. Receive user data, the user data including natural language data, historical office environment data, workflow data, commonly used software data, and device usage habit data;

[0016] S12. Processing the natural language data using natural language processing technology and extracting key information;

[0017] S13. Using K-means clustering algorithm to classify user behavior patterns based on the historical office environment data;

[0018] S14. Based on the workflow data, the commonly used software data and the device usage habit data, the correlation between software and device usage is calculated using the Apriori association rule mining method.

[0019] Furthermore, the step S2 specifically includes:

[0020] S21. Perform feature coding and standardization based on the demand collection results to obtain processing results;

[0021] S22. Using the CART decision tree algorithm to build a user portrait classification model based on the processing results;

[0022] S23. Apply the user data to the user portrait classification model to obtain a corresponding user portrait.

[0023] Furthermore, the step S3 specifically includes:

[0024] S31. Define office environment parameters, including display resolution, keyboard type, IDE brand, construct parameter list and make preliminary classification;

[0025] S32. Applying the AGNES hierarchical clustering algorithm to cluster the office environment parameters to form different configuration categories;

[0026] S33. Generate different office environment configuration options according to the configuration category, and use the configuration template to generate corresponding configuration solutions.

[0027] Furthermore, the step S4 specifically includes:

[0028] S41. Based on the user portrait, a collaborative filtering algorithm is used to find similar users, and the configuration of similar users is used as a reference for recommendation;

[0029] S42. Perform deep feature learning on the user portrait and the office environment parameters using a deep neural network;

[0030] S43. Combining the outputs of collaborative filtering and deep learning, a multi-objective optimization algorithm is used to select the optimal configuration plan and generate a personalized first configuration plan.

[0031] Furthermore, the step S5 specifically includes:

[0032] S51. Using the Monte Carlo simulation method to simulate the first configuration scheme in an actual office to generate simulation results;

[0033] S52. Applying a reinforcement learning algorithm to adjust the recommendation engine according to the simulation results;

[0034] S53. Generate a second configuration solution based on the adjusted recommendation engine.

[0035] Furthermore, the step S6 specifically includes:

[0036] S61. Using an online survey or real-time feedback tool to receive feedback on the second configuration scheme;

[0037] S62. According to the feedback information, use an online learning algorithm to update the second configuration scheme to obtain a final configuration scheme.

[0038] In addition, the present invention also relates to a personalized office environment configuration system based on text analysis and machine learning, which is characterized by comprising:

[0039] The receiving module is used to receive user data and collect requirements using text analysis;

[0040] User portrait building module, which is used to build user portraits based on demand collection results using feature engineering and decision tree classification;

[0041] An office environment parameter definition module is used to define office environment parameters and use a hierarchical clustering algorithm to perform clustering to generate an office environment configuration plan;

[0042] A personalized recommendation engine module, for designing personalized recommendations based on the user portrait and the office environment parameters by using collaborative filtering combined with a deep learning model, and generating a personalized first configuration plan;

[0043] A simulation and optimization module, used to simulate and optimize the first configuration scheme by Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme;

[0044] The feedback processing module is used to receive feedback on the second configuration solution, and to perform fine-tuning and optimization through online learning and real-time user interaction to generate a final configuration solution.

[0045] In addition, the present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0046] The memory is used to store operation instructions;

[0047] The processor is used to execute the above method by calling the operation instruction.

[0048] In addition, the present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0049] The present invention provides a personalized office environment configuration method based on text analysis and machine learning, aiming to solve the problems of insufficient personalization, low configuration efficiency and difficulty in adapting to changes in user needs in traditional office environment configuration methods. The method comprises the following steps: collecting user needs through natural language processing and preliminary cluster analysis to build user portraits; defining and classifying office environment parameters, designing a personalized recommendation engine, and proposing an office environment configuration plan suitable for users in combination with collaborative filtering and deep learning models; optimizing the recommendation engine using Monte Carlo simulation and reinforcement learning to generate a final configuration plan. This solution can provide more accurate personalized recommendations, and the automated configuration and implementation process reduces the user's manual operations and improves the configuration efficiency. Through real-time user feedback and simulation optimization, the configuration plan can be continuously adjusted and optimized to adapt to changes in user needs. The learning ability of large models can be applied to provide more comprehensive personalized configuration by integrating and analyzing data from multiple sources, including user historical behavior, workflow descriptions, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a personalized office environment configuration method based on text analysis and machine learning provided in an embodiment of the present application;

[0051] Figure 2A structural diagram of a personalized office environment configuration system based on text analysis and machine learning provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0054] Those skilled in the art can understand that, unless otherwise stated, the singular forms "one", "an", "said" and "the" used herein may also include plural forms, and the "first", "second", etc., are only used to distinguish and define objects for the purpose of introducing the scheme clearly, and do not limit the objects themselves. Of course, the objects defined by "first" and "second" may be the same terminal, device, user, etc., or the same type of terminal, device and user. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0055] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0056] like Figure 1 As shown, a personalized office environment configuration method based on text analysis and machine learning is characterized by comprising:

[0057] S1. Receive user data and use text analysis to collect requirements;

[0058] Specifically, the step S1 includes:

[0059] S11. Receive user data, which includes natural language data, historical office environment data, workflow data, commonly used software data, and device usage habit data.

[0060] S12. Use natural language processing (NLP) technology to process the natural language data and extract key information using the following formula:

[0061] Embedding = BERT (UserInput)

[0062] Embedding represents the semantic vector of user input, and UserInput represents the natural language data input by the user;

[0063] S13. K-means clustering algorithm is used to classify user behavior patterns based on the historical office environment data, wherein the historical office environment data includes software usage records and device connection logs. The specific classification adopts the following formula:

[0064] Clusters=K-means(HistoryData)

[0065] Clusters represents the clustering results of user behavior patterns, and HistoryData represents historical office environment data;

[0066] S14. Based on the workflow data, the commonly used software data and the device usage habit data, the Apriori association rule mining method is used to calculate the correlation between software and device usage, specifically using the following formula:

[0067] Rules = Apriori(WorkflowData)

[0068] Rules represent the mined association rules, and WorkflowData represents the user's workflow data.

[0069] S2. Based on the demand collection results, use feature engineering and decision tree classification to build user portraits;

[0070] Specifically, step S2 includes:

[0071] S21. Perform feature coding and standardization based on the demand collection results to obtain processing results;

[0072] S22. Use the CART decision tree algorithm to build a user portrait classification model based on the processing results, specifically using the following formula:

[0073] UserProfile=DecisionTree(Features)

[0074] UserProfile represents the user's profile classification result, and Features represents the features extracted from step S1;

[0075] S23. Apply the user data to the user portrait classification model to obtain a corresponding user portrait.

[0076] S3. Define office environment parameters and use hierarchical clustering algorithm to cluster and generate office environment configuration plan;

[0077] Specifically, step S3 includes:

[0078] S31. Define office environment parameters, including display resolution, keyboard type, IDE brand, construct parameter list and make preliminary classification;

[0079] S32. Apply the AGNES hierarchical clustering algorithm to cluster the office environment parameters to form different configuration categories, specifically using the following formula:

[0080] Clusters=AGNES(Parameters)

[0081] Clusters represents the clustering results of parameters, and Parameters represents the defined office environment parameters;

[0082] S33. Generate different office environment configuration options according to the configuration category, and use the configuration template to generate corresponding configuration solutions.

[0083] S4. Based on the user portrait and the office environment parameters, a personalized recommendation engine is designed using collaborative filtering combined with a deep learning model, and a personalized first configuration solution is generated;

[0084] Specifically, step S4 includes:

[0085] S41. Based on the user portrait, a User-based CF collaborative filtering algorithm is used to find similar users, and the configurations of similar users are used as a recommendation reference, specifically using the following formula:

[0086] Recommendation=UserCF(UserProfile,SimilarUsers)

[0087] Recommendation indicates the recommended configuration of similar users, UserProfile indicates the user profile, and SimilarUsers indicates similar users;

[0088] S42. Perform deep feature learning on the user portrait and the office environment parameters using a deep neural network;

[0089] S43. Combining the output of collaborative filtering and deep learning, the NSGA-II multi-objective optimization algorithm is used to select the optimal configuration plan and generate a personalized first configuration plan.

[0090] S5. Simulate and optimize the first configuration scheme by Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme;

[0091] Specifically, step S5 includes:

[0092] S51. Use the Monte Carlo simulation method to simulate the first configuration scheme in actual office work and generate simulation results, specifically using the following formula:

[0093] Performance=MonteCarlo(Configuration,Scenarios)

[0094] Performance refers to the performance evaluation of the configuration scheme, Configuration refers to the configuration scheme, and Scenarios refers to different simulated office scenarios;

[0095] S52. Apply the Q-learning reinforcement learning algorithm to adjust the recommendation engine according to the simulation results, specifically using the following formula:

[0096] Reward=Q-learning(State,Action)

[0097] Reward represents the result of taking an action, State represents the current environment state, and Action represents the adjustment action of the recommendation engine;

[0098] S53. Generate a second configuration solution based on the adjusted recommendation engine.

[0099] S6. Receive feedback on the second configuration solution, perform fine-tuning and optimization through online learning and real-time user interaction, and generate a final configuration solution.

[0100] Specifically, step S6 includes:

[0101] S61. Use an online survey or real-time feedback tool to receive feedback on the second configuration solution, including satisfaction and improvement suggestions;

[0102] S62. According to the feedback information, use the Online Gradient Descent online learning algorithm to update the second configuration solution to obtain a final configuration solution.

[0103] S7. Automatically deploy the office environment according to the final configuration plan;

[0104] Specifically, step S7 includes:

[0105] S71. Generate an automated configuration script according to the final configuration solution, including software installation commands and hardware debugging steps, wherein the script is generated using Ansible or Puppet templates;

[0106] S72. Use SSH remote execution tool to execute the automated configuration script in the office environment to automatically complete software installation and hardware debugging;

[0107] S73. Use automated testing tools to verify that the configuration is deployed correctly, including software version and hardware status.

[0108] S8. Continuously monitor long-term usage data and optimize the office environment based on the long-term usage data;

[0109] Specifically, step S8 includes:

[0110] S81. Analyze the behavioral data of long-term use of office environment, including software usage frequency and device interaction patterns, and use ARIMA model to predict user behavior changes;

[0111] S82. Use A / B testing to compare the impact of different configurations on user work efficiency, and use t-test statistical analysis to analyze the test results;

[0112] S83. Based on the results of long-term behavioral data analysis and A / B test experiments, use the Genetic Algorithm optimization algorithm to continuously optimize the user's office environment configuration.

[0113] The solution provided by this application is used to collect user needs through natural language processing and preliminary cluster analysis to build user portraits; define and classify office environment parameters, design a personalized recommendation engine, and propose an office environment configuration solution suitable for users by combining collaborative filtering and deep learning models; use Monte Carlo simulation and reinforcement learning to optimize the recommendation engine and generate the final configuration solution. This solution can provide more accurate personalized recommendations. The automated configuration and implementation process reduces the user's manual operations and improves configuration efficiency. Through real-time user feedback and simulation optimization, it can continuously adjust and optimize the configuration solution to adapt to changes in user needs. It can apply the learning ability of large models and integrate and analyze data from multiple sources, including user historical behavior, workflow descriptions, etc., to provide more comprehensive personalized configuration.

[0114] In order to more clearly introduce the technical solution of the present application, the following will help understand the personalized office environment configuration method based on text analysis and machine learning disclosed in the present application by way of embodiments:

[0115] 1. Business requirements collection and analysis:

[0116] R&D team members input their own natural language descriptions through the company's internal platform, including "I am a software development engineer. I mainly use Java and Python for back-end development. I hope my office environment can support efficient code writing and debugging." The BERT model is used to process these inputs and extract key information, including job type (software development engineer) and preferred software (Java, Python, back-end development-related software). The historical office environment data of R&D team members is collected, including records of software used in the past and logs of connected devices. The K-means clustering algorithm is used to cluster these data and preliminarily classify the behavior patterns of different users, including "heavy code writers" and "data-intensive workers". The workflow descriptions of R&D team members are analyzed to extract common software and device usage habits. The Apriori association rule mining method is used to discover the correlation between software and device usage, including "engineers who use Java for development usually also use IntelliJ IDEA as an IDE."

[0117] 2. User portrait construction:

[0118] Extract features from the output of user demand collection and preliminary analysis, including work type, commonly used software, and device preferences. Encode and standardize these features for subsequent modeling. Use the CART decision tree algorithm to build a user portrait classification model, and classify R&D team members into different portrait categories, including "Java backend development engineer" and "Python data analyst". Further refine the user portrait based on the classification results, including specific work scenarios (including "frequent code review is required"), preference details (including "preferring to use dark mode IDE"), and use the rule engine to further enrich the details of the user portrait, including adding the rule "this user usually programs for a long time in the afternoon" based on historical data;

[0119] 3. Definition and classification of office environment parameters:

[0120] Define office environment parameters, including display resolution, keyboard type (including mechanical keyboard, silent keyboard), IDE brand, construct parameter list and make preliminary classification, including classifying IDE brands into "IntelliJ IDEA" and "VisualStudio Code" categories, apply AGNES hierarchical clustering algorithm to cluster office environment parameters, form different configuration categories, including "efficient coding environment" and "data analysis workstation", generate different office environment configuration options according to clustering results, including "efficient coding environment" configuration may include high-resolution display, mechanical keyboard, IntelliJ IDEA, use configuration template to quickly generate configuration plan for subsequent implementation;

[0121] 4. Design a personalized recommendation engine:

[0122] Based on user portraits, the user-based CF collaborative filtering algorithm is used to find other users similar to the current user, and their configuration preferences are used as a reference for recommendation. In actual application scenarios, if the current user is a Java backend development engineer, the system will recommend configuration solutions preferred by other Java backend development engineers;

[0123] Use deep neural networks to learn deep features of user portraits and office environment parameters to improve recommendation accuracy. In actual application scenarios, the model may learn the feature combination of "engineers who use Java for development prefer to use high-resolution monitors and mechanical keyboards";

[0124] Combine the output of collaborative filtering and deep learning models to generate multiple recommended office environment configuration plans, and use the NSGA-II multi-objective optimization algorithm to select the optimal configuration plan as the personalized first configuration plan;

[0125] 5. Environmental simulation and feedback loop

[0126] The Monte Carlo simulation method is used to evaluate the performance of the first configuration solution in actual office work. In actual application scenarios, the user's programming efficiency and error rate indicators are simulated to evaluate its actual effect;

[0127] Apply Q-learning reinforcement learning algorithm to adjust the recommendation engine based on simulation results;

[0128] Based on the simulation and optimization results, an office environment configuration plan is generated according to the adjustment recommendation engine as a second configuration plan;

[0129] 6. Real-time user interaction and fine-tuning

[0130] Collect user feedback on the second configuration solution through online surveys or real-time feedback tools. In actual application scenarios, users can evaluate whether the recommended configuration solution meets their needs and put forward improvement suggestions;

[0131] According to the feedback information, using an online learning algorithm to update the second configuration scheme to obtain a final configuration scheme;

[0132] 7.Automated configuration and implementation:

[0133] Generate an automated configuration script based on the final solution. The script may include commands for installing a specific version of the IDE and steps for configuring the display resolution.

[0134] Execute configuration scripts in the user's office environment to automatically complete software installation and hardware debugging. Use SSH remote execution tools to run scripts in the target environment to ensure the accuracy and consistency of configuration. Use automated testing tools to check whether the software version and hardware status meet expected requirements.

[0135] 8. Personalized continuous optimization:

[0136] Analyze the long-term behavioral data of users using the office environment, use the ARIMA model to predict changes in user behavior, including that users may be more inclined to use a new tool or technology in the future, design A / B testing experiments, compare the impact of different configuration schemes on user work efficiency, and test the impact of high-resolution displays and ordinary displays on user programming efficiency in actual application scenarios;

[0137] Based on long-term behavioral analysis and A / B testing results, we continuously optimize users' office environment configurations and use the Genetic Algorithm optimization algorithm to find the optimal configuration.

[0138] In addition, another aspect also relates to a personalized office environment configuration system based on text analysis and machine learning, the structure of which is as follows: Figure 2 As shown, including:

[0139] The receiving module 201 is used to receive user data and collect requirements by using text analysis;

[0140] A user portrait construction module 202 is used to construct a user portrait based on the demand collection results using feature engineering and decision tree classification;

[0141] An office environment parameter definition module 203 is used to define office environment parameters and use a hierarchical clustering algorithm to perform clustering to generate an office environment configuration plan;

[0142] A personalized recommendation engine module 204 is used to design personalized recommendations based on the user portrait and the office environment parameters by using collaborative filtering combined with a deep learning model, and to generate a personalized first configuration solution;

[0143] A simulation and optimization module 205, configured to simulate and optimize the first configuration scheme by using a Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme;

[0144] The feedback processing module 206 is used to receive feedback on the second configuration solution, and to perform fine-tuning and optimization through online learning and real-time user interaction to generate a final configuration solution.

[0145] Further, the receiving module 201 is specifically used for:

[0146] Receive user data, wherein the user data includes natural language data, historical office environment data, workflow data, commonly used software data, and device usage habit data;

[0147] Processing the natural language data using natural language processing technology and extracting key information;

[0148] Using a K-means clustering algorithm to classify user behavior patterns based on the historical office environment data;

[0149] Based on the workflow data, the commonly used software data and the device usage habit data, the Apriori association rule mining method is used to calculate the correlation between software and device usage.

[0150] Furthermore, the user portrait construction module 202 is specifically used for:

[0151] Perform feature coding and standardization processing based on the demand collection results to obtain processing results;

[0152] Using the CART decision tree algorithm to build a user portrait classification model based on the processing results;

[0153] The user data is applied to the user portrait classification model to obtain a corresponding user portrait.

[0154] Furthermore, the office environment parameter definition module 203 is specifically used for:

[0155] Define office environment parameters, including monitor resolution, keyboard type, IDE brand, construct parameter lists and make preliminary classifications;

[0156] Applying the AGNES hierarchical clustering algorithm to cluster the office environment parameters to form different configuration categories;

[0157] Generate different office environment configuration options according to configuration categories, and use configuration templates to generate corresponding configuration plans.

[0158] Furthermore, the personalized recommendation engine module 204 is specifically used for:

[0159] Based on the user portrait, a collaborative filtering algorithm is used to find similar users, and the configurations of similar users are used as a reference for recommendation;

[0160] Using a deep neural network to perform deep feature learning on the user portrait and the office environment parameters;

[0161] Combining the outputs of collaborative filtering and deep learning, a multi-objective optimization algorithm is used to select the optimal configuration plan and generate a personalized first configuration plan.

[0162] Further, the simulation and optimization module 205 is specifically used for:

[0163] Using a Monte Carlo simulation method to simulate the first configuration scheme in actual office work, and generating simulation results;

[0164] Applying a reinforcement learning algorithm to adjust the recommendation engine based on the simulation results;

[0165] A second configuration solution is generated based on the adjusted recommendation engine.

[0166] Further, the feedback processing module 206 is specifically used for:

[0167] receiving feedback information on the second configuration scheme using an online survey or a real-time feedback tool;

[0168] According to the feedback information, an online learning algorithm is used to update the second configuration scheme to obtain a final configuration scheme.

[0169] Furthermore, the system also includes an automatic deployment module 207 and a continuous monitoring module 208;

[0170] The automatic deployment module 207 is specifically used for:

[0171] Generate an automated configuration script according to the final configuration solution, including software installation commands and hardware debugging steps, wherein the script is generated using Ansible or Puppet templates;

[0172] Use SSH remote execution tool to execute the automated configuration script in the office environment to automatically complete software installation and hardware debugging;

[0173] Use automated testing tools to verify that the configuration is deployed correctly, including software version and hardware status.

[0174] The continuous monitoring module 208 is specifically used for:

[0175] Analyze the behavioral data of long-term office environment use, including software usage frequency and device interaction patterns, and use the ARIMA model to predict changes in user behavior;

[0176] A / B testing experiments were used to compare the impact of different configuration schemes on user work efficiency, and t-test statistical tests were used to analyze the test results;

[0177] Based on the results of long-term behavioral data analysis and A / B testing experiments, the Genetic Algorithm optimization algorithm is used to continuously optimize the user's office environment configuration.

[0178] By using this system, the above method can be executed and the corresponding technical effects can be achieved.

[0179] An embodiment of the present invention further provides an electronic device for executing the above method, as an implementation device of the method, comprising a processor and a memory;

[0180] A memory, used for storing operation instructions;

[0181] The processor is used to execute a personalized office environment configuration method based on text analysis and machine learning provided in any embodiment of the present application by calling an operation instruction.

[0182] As an example, Figure 3 A schematic diagram of the structure of an electronic device applicable to an embodiment of the present application is shown, and the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0183] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0184] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0185] The processor 301 may also include one or more processing units, for example: the processor 301 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and / or a neural network processor (Neural-network Processing Unit, NPU), etc. Different processing units can be independent devices or integrated into one or more processors. Among them, the controller can be the nerve center and command center of the electronic device 300. The controller can generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory can also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a cache memory. The memory can save instructions or data that the processor 301 has just used or circulated.

[0186] Processor 301 can run the personalized office environment configuration method based on text analysis and machine learning provided in the embodiment of the present application. Processor 301 may include different devices. For example, when integrating a CPU and a GPU, the CPU and the GPU can cooperate to execute the personalized office environment configuration method based on text analysis and machine learning provided in the embodiment of the present application. Part of the algorithm is executed by the CPU, and the other part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0187] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0188] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0189] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the personalized office environment configuration method based on text analysis and machine learning provided in any embodiment of the present application.

[0190] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0191] The memory 303 may also store one or more computer programs corresponding to the personalized office environment configuration method based on text analysis and machine learning provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0192] Of course, the code of the personalized office environment configuration method based on text analysis and machine learning provided in the embodiment of the present application can also be stored in an external memory.

[0193] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0194] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0195] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0196] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0197] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0198] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0199] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0200] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A personalized office environment configuration method based on text analysis and machine learning, characterized in that: include: S1. Receive user data and use text analysis to collect requirements; S2. Based on the demand collection results, use feature engineering and decision tree classification to build user portraits; S3. Define office environment parameters and use hierarchical clustering algorithm to cluster and generate office environment configuration plan; S4. Based on the user portrait and the office environment parameters, a personalized recommendation engine is designed using collaborative filtering combined with a deep learning model, and a personalized first configuration solution is generated; S5. Simulate and optimize the first configuration scheme by Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme; S6. Receive feedback on the second configuration solution, perform fine-tuning and optimization through online learning and real-time user interaction, and generate a final configuration solution.

2. The method according to claim 1, characterized in that The step S1 specifically includes: S11. Receive user data, the user data including natural language data, historical office environment data, workflow data, commonly used software data, and device usage habit data; S12. Processing the natural language data using natural language processing technology and extracting key information; S13. Using K-means clustering algorithm to classify user behavior patterns based on the historical office environment data; S14. Based on the workflow data, the commonly used software data and the device usage habit data, the correlation between software and device usage is calculated using the Apriori association rule mining method.

3. The method according to claim 2, characterized in that The step S2 specifically includes: S21. Perform feature coding and standardization based on the demand collection results to obtain processing results; S22. Using the CART decision tree algorithm to build a user portrait classification model based on the processing results; S23. Apply the user data to the user portrait classification model to obtain a corresponding user portrait.

4. The method according to claim 3, characterized in that: The step S3 specifically includes: S31. Define office environment parameters, including display resolution, keyboard type, IDE brand, construct parameter list and make preliminary classification; S32. Applying the AGNES hierarchical clustering algorithm to cluster the office environment parameters to form different configuration categories; S33. Generate different office environment configuration options according to the configuration category, and use the configuration template to generate corresponding configuration solutions.

5. The method according to claim 4, characterized in that The step S4 specifically includes: S41. Based on the user portrait, a collaborative filtering algorithm is used to find similar users, and the configuration of similar users is used as a reference for recommendation; S42. Perform deep feature learning on the user portrait and the office environment parameters using a deep neural network; S43. Combining the outputs of collaborative filtering and deep learning, a multi-objective optimization algorithm is used to select the optimal configuration plan and generate a personalized first configuration plan.

6. The method according to claim 5, characterized in that The step S5 specifically includes: S51. Using the Monte Carlo simulation method to simulate the first configuration scheme in an actual office to generate simulation results; S52. Applying a reinforcement learning algorithm to adjust the recommendation engine according to the simulation results; S53. Generate a second configuration solution based on the adjusted recommendation engine.

7. The method according to claim 6, characterized in that The step S6 specifically includes: S61. Using an online survey or real-time feedback tool to receive feedback on the second configuration scheme; S62. According to the feedback information, use an online learning algorithm to update the second configuration scheme to obtain a final configuration scheme.

8. A personalized office environment configuration system based on text analysis and machine learning, characterized in that: include: The receiving module is used to receive user data and collect requirements using text analysis; User portrait building module, which is used to build user portraits based on demand collection results using feature engineering and decision tree classification; An office environment parameter definition module is used to define office environment parameters and use a hierarchical clustering algorithm to perform clustering to generate an office environment configuration plan; A personalized recommendation engine module, configured to design personalized recommendations based on the user portrait and the office environment parameters by using collaborative filtering combined with a deep learning model, and to generate a personalized first configuration solution; A simulation and optimization module, used to simulate and optimize the first configuration scheme by Monte Carlo simulation method and reinforcement learning to generate a second configuration scheme; The feedback processing module is used to receive feedback on the second configuration solution, and to perform fine-tuning and optimization through online learning and real-time user interaction to generate a final configuration solution.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store operation instructions; The processor is used to execute the method according to any one of claims 1 to 7 by calling the operation instruction.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images