Block chain-based house renting system capable of realizing intelligent recommendation and adaptive performance adjustment

Abstract

The invention discloses a blockchain-based house renting system capable of realizing intelligent recommendation and adaptive performance adjustment. The method comprises the steps that a user registers and uploads identity information; user identity information is verified through the trusted mechanism interface; the landlord uploads a house resource video and releases the house resource video to the IPFS network; the tenant browses house resource information and receives intelligent recommendation; the system automatically adjusts performance parameters according to resource use conditions. The performance of the server can be fully utilized to maintain the optimal operation state of the block chain, the performance of the block chain is automatically adjusted by monitoring the real-time system resource use condition of the server where the block chain node is located, and efficient operation of the block chain is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of house rental systems, and in particular to a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment. Background Art

[0002] Blockchain technology, through distributed ledgers, encryption technology, smart contracts and other means, has built a decentralized, tamper-proof, transparent and traceable data management platform. This technology has not only revolutionized the financial sector, but also demonstrated great potential in product traceability, data circulation, supply chain management and other fields. Blockchain will be deeply integrated with the Internet, big data, artificial intelligence and other technologies, and will be widely used in various fields.

[0003] Although blockchain technology has many potential advantages, such as improving transparency, reducing transaction costs and enhancing security, there are still many problems that need to be solved and innovated in its application, such as: (1) The functions currently implemented in the field of blockchain technology application are often relatively simple, such as auctions, product traceability, data sharing, copyright notarization, etc. (2) The combination of machine learning, deep learning and blockchain application technology (3) Dynamic optimization and adjustment of the performance of blockchain system applications. Therefore, it is necessary to develop a functionally rich, up-to-date and popular intelligent recommendation technology that can make full use of blockchain performance, user-friendly intelligent recommendation and performance adaptive adjustment rental system. Summary of the invention

[0004] The embodiment of the present application provides a blockchain-based house rental system that can intelligently recommend and adaptively adjust performance, so as to at least partially solve the above technical problems.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In one aspect, a construction module is used to construct a blockchain, wherein the blockchain includes a plurality of data transmission nodes, identify the data processing capability of each of the data transmission nodes and arrange the plurality of data transmission nodes in descending order according to the data processing capability, and use the first plurality of data transmission nodes as central transmission nodes;

[0007] User identity upload module, used to encrypt the user's identity information and store it on the blockchain, as well as the landlord uploading the house video, encrypting the video content, and uploading the encrypted video to the IPFS network;

[0008] The IPFS encryption module is used to upload the encrypted video to the IPFS network, calculate the unique hash value of the file and return the file identification ID. The file identification ID is stored in the encryption module on the blockchain by calling the contract, which is used to encrypt the uploaded video;

[0009] The intelligent recommendation service module is used to dynamically adjust the weights through the CFCR algorithm based on the user's property browsing history and UGC tags, and generate personalized property recommendation information through the intelligent recommendation algorithm.

[0010] Furthermore, the dynamic weight adjustment method is used to extract features from UGC tags using the TF-IDF algorithm, and dynamically adjust the weights of content recommendation and collaborative filtering recommendation according to user behavior.

[0011] Furthermore, the system also includes a performance adaptive adjustment module, which is used to automatically adjust the chain performance parameters according to the system resource usage and the dynamic threshold. The adaptive adjustment method includes:

[0012] By real-time monitoring of the system's CPU usage, memory usage and network bandwidth;

[0013] Automatically adjust decision thresholds using time series forecasting models;

[0014] Adjust chain performance parameters based on decision values ​​and update chain configuration via smart contracts;

[0015] The input data required by the time series forecasting model (ARIMA) is required to be stable, so the input data needs to be differentiated to eliminate the trend, and then trained through the time series forecasting model (ARIMA). The basic formula of the ARIMA model is:

[0016]

[0017] Among them, Y t is the resource utilization rate at time t, Y t-i is the resource utilization rate at the previous time ti, ε t is the error term at the current time t, ε t-j is the error term at the previous time tj, φ i is the linear relationship between time series data and the previous i time points, θ j Because the time series depends on the linear relationship of the first j error terms, the data needs to be segmented during the model training process. The data is divided into a training set and a test set, and then the ARIMA model is used to fit the training set. The trained model can predict the resource utilization rate in the future. After obtaining the predicted value of the ARIMA model for the future resource utilization rate, the threshold can be dynamically adjusted according to these predicted values. In the dynamic threshold result, the trained ARIMA model is used to predict the resource utilization rate in the future. Calculate the mean μ of the predicted values pred and standard deviation σ pred ;

[0018] The average value formula of the predicted value is:

[0019]

[0020] The formula for the standard deviation of the predicted values ​​is:

[0021]

[0022] Set dynamic high and low thresholds based on the mean and standard deviation of the predicted values:

[0023] High threshold: HighThreshold = μ pred +k high ×σ pred

[0024] Low threshold: LowThreshold = μ pred -k low ×σ pred

[0025] where k high and k low It is a constant for adjusting the width of the threshold. During the operation of the system, the latest resource utilization data is continuously input, and the future resource utilization is predicted in real time through the trained model, and the threshold is adjusted dynamically. The weighted fusion method is used to combine the weights of multiple indicators to calculate the comprehensive score;

[0026] The value of each indicator is standardized and mapped to an interval (0 to 1). The high and low thresholds are used to determine whether the decision value needs to be reduced or increased. The following formula can be used to standardize each indicator:

[0027]

[0028] If x≥HighThreshold, the standardized value is 1, and if x≤LowThreshold, the standardized value is 0. The comprehensive score can be calculated by weighted summation of the standardized values ​​of each indicator;

[0029] The summation formula is:

[0030] score=w cpu ×cpu_score+w men ×mem_score+w net ×net_score

[0031] Where w is the weight of each indicator. If the comprehensive score is close to 1, it means that the resource utilization rate is very high and the decision value should be reduced. If the comprehensive score is close to 0, it means that the resource utilization rate is very low and the decision value should be increased.

[0032] Furthermore, the data transmission node of the building module communicates with the national housing rental management department through a trusted institution interface to verify the user identity information.

[0033] Furthermore, the system is deployed in a distributed network environment to ensure the security and non-tamperability of data.

[0034] Furthermore, the intelligent recommendation algorithm includes:

[0035] A collects multi-source user data, including user behavior data and property attribute data, and processes the multi-source user data to obtain a keyword set;

[0036] B. extracting key features that can reflect user preferences from the keyword set,

[0037] Feature extraction requires the use of TF-IDF to vectorize the description text. The formula is:

[0038]

[0039] The TF-IDF formula calculates term frequency minus inverse document frequency, where the denominator d is the sum of all keyword occurrences, N is the number of all documents in the document set, and DF(t) is the number of documents containing keyword t. It is used to measure the importance of a word in a single document, while reducing the weight of common words that appear frequently in multiple documents.

[0040] User preference matching is performed based on a hybrid recommendation system to recommend similar properties, wherein the hybrid recommendation system includes a content-based recommendation algorithm and a collaborative filtering recommendation algorithm.

[0041] Furthermore, the content-based recommendation algorithm constructs a feature vector v for each house i , converting the user's historical behavior into the user's feature vector u j

[0042] Use the cosine similarity formula to calculate recommendations. The cosine similarity formula is:

[0043]

[0044] The same filtering recommendation algorithm focuses on making recommendations by analyzing the similarities between listings and uses the Pearson correlation coefficient to calculate the similarity. The formula is:

[0045]

[0046] Among them, r is the value of Pearson correlation coefficient, and its value range is [-1,1], which indicates the correlation between two variables. -1 indicates that the two variables are completely negatively correlated, 0 indicates that the two variables have no linear correlation, and 1 indicates a completely positive correlation. i and i are the values ​​of two variables, representing the data point of the ith observation, x and y are the mean values ​​of the variables, representing the center position of the x and y data;

[0047] The CFCR hybrid recommendation algorithm adopts adaptive weighted model fusion. In weighted fusion, the weights α(u) and β(u) are dynamically adjusted based on the behavioral characteristics of user u. The adaptive weight formula is:

[0048]

[0049] in and They are the output of the content-based recommendation model and the output of the collaborative filtering recommendation model respectively.

[0050] On the other hand, a blockchain-based housing rental method with intelligent recommendation and adaptive performance adjustment includes the following steps:

[0051] Users register and upload their identity information;

[0052] Verify user identity information through a trusted authority interface;

[0053] The landlord uploads the property video and publishes it to the IPFS network;

[0054] Tenants browse listings and receive smart recommendations;

[0055] The system automatically adjusts performance parameters based on resource usage.

[0056] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0057] (1) The present invention uses smart contracts and consensus algorithms to achieve decentralization of rental housing, truly solving the problem of market stability being undermined by the participation of third-party intermediaries in the transaction process.

[0058] (2) The present invention combines the technologies of the InterPlanetary File System and blockchain to solve the problem of limited storage space in traditional blockchain structures.

[0059] (3) The present invention applies the recommendation algorithm to house rental, which provides convenience for users to view houses and improves the user experience.

[0060] (4) The present invention uses the blockchain performance to adaptively adjust according to the server resource usage, optimizes the speed of node processing transactions, and enhances the stability of the node. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0062] Figure 1 A schematic diagram of a process of a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment provided in an embodiment of this specification;

[0063] Figure 2 A system architecture diagram of a blockchain-based rental system with intelligent recommendation and adaptive performance adjustment provided in an embodiment of this specification;

[0064] Figure 3 A flowchart of an intelligent recommendation algorithm for a rental system capable of intelligent recommendation and adaptive performance adjustment based on blockchain provided in an embodiment of this specification;

[0065] Figure 4 A performance adaptive adjustment flow chart of a rental system capable of intelligent recommendation and performance adaptive adjustment based on blockchain provided in an embodiment of this specification; DETAILED DESCRIPTION

[0066] The present invention will be further described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0067] refer to Figure 1 , a house rental system capable of intelligent recommendation and adaptive performance adjustment based on blockchain includes a construction module for constructing a blockchain, the blockchain includes a plurality of data transmission nodes, identifies the data processing capability of each of the data transmission nodes and arranges the plurality of data transmission nodes in descending order according to the data processing capability, and uses the first plurality of data transmission nodes as central transmission nodes;

[0068] User identity upload module, used to encrypt the user's identity information and store it on the blockchain, as well as the landlord uploading the house video, encrypting the video content, and uploading the encrypted video to the IPFS network;

[0069] The IPFS module is used to upload the encrypted video to the IPFS network, calculate the unique hash value of the file and return the file ID. The file ID is stored in the blockchain by calling the contract. The encryption module is used to encrypt the uploaded video.

[0070] The intelligent recommendation service module is used to dynamically adjust the weights through the CFCR algorithm based on the user's property browsing history and UGC tags, and generate personalized property recommendation information through the intelligent recommendation algorithm.

[0071] The backend of the system runs on each node of Changan Chain and combines with the Interstellar File System to form the chain's large file storage function. The front-end page provides users with a good interactive environment, through which users can easily complete the release and rental of housing. The rental system includes the following modules:

[0072] Trusted institutions - national housing rental management departments, management departments play an important role in ensuring the security and legitimacy of blockchain technology. By implementing effective regulatory measures, they can protect user privacy while being able to view the identity information of all users on the blockchain and supervise user identity information to ensure the legitimacy of user identities.

[0073] Interplanetary File System (IPFS), landlords can publish video resource information of the house, upload the video to IPFS, IPFS then calculates the unique hash value of the file and returns the file identification ID, and finally stores the file identification ID on the blockchain by calling the contract. Tenants can download the corresponding video file from IPFS through the file identification ID on the chain.

[0074] Intelligent recommendation: When users view property information, the recommendation algorithm can recommend similar properties to tenants at the bottom of the detail page so that tenants can conduct more extensive searches, saving users time in searching for properties.

[0075] System performance is adaptively adjusted. Once the rental system is deployed, it will immediately start real-time monitoring of server resource usage. Through this monitoring, the system can dynamically adjust its performance through algorithms based on current resource usage, ensuring that the entire platform always runs in the best state. This automated resource management strategy helps maintain the efficiency and stability of the system and provide users with a smooth rental experience.

[0076] refer to Figure 2, described is the architecture diagram of the intelligent recommendation and performance adaptive adjustment rental system, which describes a typical multi-layer architecture design with front-end and back-end separation. The front-end UI layer builds the user interface through HTML, CSS and JavaScript technology, and uses the React framework and Node.js back-end service for interaction. The back-end service layer is further subdivided into the service layer and the interface layer. The Gin framework is used to provide a RESTful API to ensure efficient communication between the front and back ends. Modules such as intelligent recommendation, performance adaptive adjustment and large file storage constitute the core functions of the back-end service layer, while the underlying system support is provided by the Ubuntu operating system and Docker containerization technology, ensuring the stability and scalability of the entire system. The overall architecture embodies the modularity, security and high performance characteristics of modern Web application development.

[0077] refer to Figure 3 , which describes the intelligent recommendation algorithm process and the construction and operation process of the hybrid recommendation system. In the data collection and preprocessing stage, the system needs to collect user behavior data, property attribute data, etc. from multiple sources, and process these data to obtain a set of keywords. Then it enters the feature extraction and combination stage, extracting key features that can reflect user preferences from the original data, and effectively combining these features to enhance the model's understanding of user preferences. Feature extraction requires the use of TF-IDF to vectorize the description text, and its formula is:

[0078]

[0079] Next is the stage of selecting and building the algorithm model. The hybrid recommendation system combines the content-based recommendation algorithm and the collaborative filtering recommendation algorithm. The content-based recommendation algorithm focuses on analyzing the characteristics of the listings and matching these characteristics with the user's historical preferences to recommend similar listings. The implementation method is to construct a feature vector v for each listing. i , converting the user's historical behavior into the user's feature vector u j Then use the cosine similarity formula to calculate the recommendation. The cosine similarity formula is:

[0080]

[0081] The collaborative filtering recommendation algorithm focuses on making recommendations by analyzing the similarities between properties and uses the Pearson correlation coefficient to calculate the similarity. The formula is:

[0082]

[0083] The CFCR hybrid recommendation algorithm adopts adaptive weighted model fusion. In weighted fusion, the weights α(u) and β(u) are dynamically adjusted based on the behavioral characteristics of user u (interaction frequency, historical data richness). The adaptive weight formula is:

[0084]

[0085] in and They are the output of the content-based recommendation model and the output of the collaborative filtering recommendation model. Then, the model training phase begins. The trained model generates recommendation results and recommends properties that may be of interest to users based on the results, thus completing the entire recommendation process.

[0086] refer to Figure 4 , what is described is the performance adaptive adjustment process. The system first collects the system resource usage on the server of the deployed system in real time, including memory usage, CPU usage, network bandwidth and other data, and then makes a decision on whether to update the parameters on the chain through the configuration parameter adjustment strategy algorithm. If the decision result indicates that the chain configuration parameters need to be updated, the system will construct a chain configuration update transaction and send a transaction to update the configuration of the blockchain. In the configuration parameter adjustment strategy algorithm, CPU usage, memory usage and network usage are used as input data. Because the input data required by the time series prediction model (ARIMA) is required to be stable, the input data also needs to be differentiated to eliminate the trend, and then trained through the time series prediction model (ARIMA). The basic formula of the ARIMA model is:

[0087]

[0088] The result Y t is the resource utilization rate at time t. In the process of model training, the data needs to be segmented into training set and test set, and then the ARIMA model is used to fit the training set. The trained model can predict the resource utilization rate for a period of time in the future. After obtaining the predicted value of the ARIMA model for the future resource utilization rate, the threshold can be dynamically adjusted based on these predicted values. In the dynamic threshold result, the trained ARIMA model is used to predict the resource utilization rate for a period of time in the future. Then calculate the mean μ of the predicted values pred and standard deviation σ pred .

[0089] The average value formula of the predicted value is:

[0090]

[0091] The formula for the standard deviation of the predicted values ​​is:

[0092]

[0093] Set dynamic high and low thresholds based on the mean and standard deviation of the predicted values:

[0094] High threshold: HighThreshold = μ pred +k high ×σ pred

[0095] Low threshold: LowThreshold = μ pred -k low ×σ pred

[0096] where k high and k low is a constant for adjusting the width of the threshold. During the operation of the system, the latest resource utilization data is continuously input, and the future resource utilization is predicted in real time through the trained model, and the threshold is adjusted dynamically. In order to calculate the decision value more reasonably, a weighted fusion method is also used to combine the weights of multiple indicators to calculate a comprehensive score. Then, based on this comprehensive score, determine whether adjustments are needed. Consider the impact of each resource indicator (CPU, memory, network) on the overall performance of the system and set different weights for them. In addition, the value of each indicator is standardized and mapped to an interval (0 to 1), and the decision value needs to be reduced or increased based on the high and low thresholds. The following formula can be used to standardize each indicator:

[0097]

[0098] If x≥HighThreshold, the normalized value is 1, and if x≤LowThreshold, the normalized value is 0. The comprehensive score can be calculated by weighted summing of the normalized values ​​of each indicator. The summation formula is:

[0099] score=w cpu ×cpu_score+w men ×mem_score+w net ×net_score

[0100] Where w is the weight of each indicator. If the comprehensive score is close to 1, it means that the resource utilization rate is very high and the decision value should be reduced. If the comprehensive score is close to 0, it means that the resource utilization rate is very low and the decision value should be increased.

[0101] At the hardware level, a rental system with intelligent recommendation and adaptive performance adjustment based on blockchain can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in software form. The above processor can be a general-purpose processor, which can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or a combination of hardware and software modules in the decoding processor to execute. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0102] The electronic device may also perform Figure 1 A blockchain-based rental system with intelligent recommendation and adaptive performance adjustment Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0103] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned blockchain-based intelligent recommendation and performance adaptive adjustment rental systems is executed.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0106] 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.

[0107] 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 for the functions specified in one or more boxes.

[0108] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0109] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0110] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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.) that contain computer-usable program code.

[0112] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A blockchain-based house rental system with intelligent recommendation and adaptive performance adjustment, characterized in that: include: A construction module is used to construct a blockchain, wherein the blockchain includes a plurality of data transmission nodes, identify the data processing capability of each of the data transmission nodes and arrange the plurality of data transmission nodes in descending order according to the data processing capability, and use the first plurality of data transmission nodes as central transmission nodes; The user identity upload module is used to encrypt the user's identity information and store it on the blockchain, as well as the landlord's upload of the property video, encrypt the video content, and upload the encrypted video to the IPFS network; The IPFS encryption module is used to upload the encrypted video to the IPFS network, calculate the unique hash value of the file and return the file identification ID. The file identification ID is stored in the encryption module on the blockchain by calling the contract, which is used to encrypt the uploaded video; The intelligent recommendation service module is used to dynamically adjust the weights through the CFCR algorithm based on the user's property browsing history and UGC tags, and generate personalized property recommendation information through the intelligent recommendation algorithm.

2. According to claim 1, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The dynamic weight adjustment method is used to extract features from UGC tags using the TF-IDF algorithm, and dynamically adjust the weights of content recommendation and collaborative filtering recommendation according to user behavior.

3. According to claim 1, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The system also includes a performance adaptive adjustment module, which is used to automatically adjust the chain performance parameters according to the system resource usage and the dynamic threshold. The adaptive adjustment method includes: By real-time monitoring of the system's CPU usage, memory usage and network bandwidth; Automatically adjust decision thresholds using time series forecasting models; Adjust chain performance parameters based on decision values ​​and update chain configuration via smart contracts; The input data required by the time series forecasting model (ARIMA) is required to be stable, so the input data needs to be differentiated to eliminate the trend, and then trained through the time series forecasting model (ARIMA). The basic formula of the ARIMA model is: Among them, Y t is the resource utilization rate at time t, Y t-i is the resource utilization rate at the previous time ti, ε t is the error term at the current time t, ε t-j is the error term at the previous time tj, φ i is the linear relationship between time series data and the previous i time points, θ j Because the time series depends on the linear relationship of the first j error terms, the data needs to be segmented during the model training process. The data is divided into a training set and a test set, and then the ARIMA model is used to fit the training set. The trained model can predict the resource utilization rate in the future. After obtaining the predicted value of the ARIMA model for the future resource utilization rate, the threshold can be dynamically adjusted according to these predicted values. In the dynamic threshold result, the trained ARIMA model is used to predict the resource utilization rate in the future. Calculate the mean μ of the predicted values pred and standard deviation σ pred ; The average value formula of the predicted value is: The formula for the standard deviation of the predicted values ​​is: Set dynamic high and low thresholds based on the mean and standard deviation of the predicted values: High threshold: HighThreshold = μ pred +k high ×σ pred Low threshold: LowThreshold = μ pred -k low ×σ pred where k high and k low It is a constant for adjusting the width of the threshold. During the operation of the system, the latest resource utilization data is continuously input, and the future resource utilization is predicted in real time through the trained model, and the threshold is adjusted dynamically. The weighted fusion method is used to combine the weights of multiple indicators to calculate the comprehensive score; The value of each indicator is standardized and mapped to an interval (0 to 1). The high and low thresholds are used to determine whether the decision value needs to be reduced or increased. The following formula can be used to standardize each indicator: If x≥HighThreshold, the standardized value is 1, and if x≤LowThreshold, the standardized value is 0. The comprehensive score can be calculated by weighted summation of the standardized values ​​of each indicator; The summation formula is: score=w cpu ×cpu_score+w men ×mem_score+w net ×net_score Where w is the weight of each indicator. If the comprehensive score is close to 1, it means that the resource utilization rate is very high and the decision value should be reduced. If the comprehensive score is close to 0, it means that the resource utilization rate is very low and the decision value should be increased.

4. According to claim 1, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The data transmission node of the building module communicates with the national housing rental management department through a trusted institution interface to verify user identity information.

5. According to claim 1, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The system is deployed in a distributed network environment to ensure the security and non-tamperability of data.

6. According to claim 1, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The intelligent recommendation algorithm includes: A collects multi-source user data, including user behavior data and property attribute data, and processes the multi-source user data to obtain a keyword set; B. extracting key features that can reflect user preferences from the keyword set, Feature extraction requires the use of TF-IDF to vectorize the description text. The formula is: The TF-IDF formula calculates term frequency minus inverse document frequency, where the denominator d is the sum of all keyword occurrences, N is the number of all documents in the document set, and DF(t) is the number of documents containing keyword t. It is used to measure the importance of a word in a single document, while reducing the weight of common words that appear frequently in multiple documents. User preference matching is performed based on a hybrid recommendation system to recommend similar properties, wherein the hybrid recommendation system includes a content-based recommendation algorithm and a collaborative filtering recommendation algorithm.

7. According to claim 6, a blockchain-based house rental system capable of intelligent recommendation and adaptive performance adjustment is characterized in that: The content-based recommendation algorithm constructs a feature vector v for each listing i , converting the user's historical behavior into the user's feature vector u j Use the cosine similarity formula to calculate recommendations. The cosine similarity formula is: The same filtering recommendation algorithm focuses on making recommendations by analyzing the similarities between listings and uses the Pearson correlation coefficient to calculate the similarity. The formula is: Among them, r is the value of Pearson correlation coefficient, and its value range is [-1,1], which indicates the correlation between two variables. -1 indicates that the two variables are completely negatively correlated, 0 indicates that the two variables have no linear correlation, and 1 indicates a completely positive correlation. i and i are the values ​​of two variables, representing the data point of the i-th observation, and is the mean value of the variable, representing the center position of the x and y data; The CFCR hybrid recommendation algorithm adopts adaptive weighted model fusion. In weighted fusion, the weights α(u) and β(u) are dynamically adjusted based on the behavioral characteristics of user u. The adaptive weight formula is: in and They are the output of the content-based recommendation model and the output of the collaborative filtering recommendation model respectively.

8. A blockchain-based intelligent recommendation and performance adaptive rental method for executing any of the systems described in claims 1-7, characterized in that: The following steps are involved: User registration and upload of identity information; Verify user identity information through a trusted authority interface; The landlord uploads the property video and publishes it to the IPFS network; Tenants browse listings and receive smart recommendations; The system automatically adjusts performance parameters based on resource usage.

Images