Shared service income creating method

Abstract

The invention discloses a shared service income creating method. The method comprises the following steps: S1, setting a unique electronic code on each device in a room, and creating a cloud platform matched with the corresponding room; s2, the cloud platform is divided into a registration end and a management end, the registration end is used for collecting registration information of the user, and the management end is used for checking and setting data of the cloud platform. According to the invention, by setting a unique electronic code on each device and creating the cloud platform, accurate management and efficient monitoring of the devices are realized, and the use state and position transparency of the devices are ensured. And the cloud platform is divided into the registration end and the management end, so that user information can be effectively collected, an administrator can conveniently monitor and adjust, and the data management efficiency is improved. According to the recommendation system based on the user historical data, personalized equipment, commodity and activity recommendation is provided, and the user experience and the satisfaction degree are improved.

Description

Technical Field

[0001] The present invention belongs to the field of revenue generating methods, and in particular, relates to a shared service revenue generating method. Background Art

[0002] This technology aims to provide a new business model for the physical industry, and is suitable for rental housing, beverage and leisure stations, apartment-type housing, commercial housing and other places. By providing shared computers in these places, convenient services can be provided to user groups in need. For example, a lounge for shared computers is set up in a public area, which is convenient for users to use them for free and unified management. This service not only increases social opportunities for neighbors, but also allows users to experience an atmosphere similar to that of Internet cafes in the 1990s, thereby enhancing the in-store experience of physical stores.

[0003] In addition, individual users can register on the platform to obtain the qualification to use shared equipment. After successful registration, they can use it by scanning the code with their mobile phone or logging in with their account. During use, if the equipment fails, individual users can contact the maintenance master in the area through the platform and pay an appropriate fee for repair. For equipment in public areas, a simple fixing frame can be used to fix it, or a special person can be arranged to supervise it. If the equipment fails, it can also be reported through the platform, and the cost of the equipment damage will be borne by the user.

[0004] Since the environment of some rental houses is not as good as that of new rental houses, the platform can attract tenants in need by providing free computer use services. In the future, the platform can also be expanded to rental services of other equipment, such as electric cars and washing machines, which will not only help landlords to manage more easily, but also attract tenants to use them at preferential prices.

[0005] For outsiders, they can pay preferential fees to use the equipment after registration, but tenants have priority in use. Physical leisure stores can also provide users with free use of computers by offering recharge discounts, thereby improving the in-store experience and attracting more customers. At the same time, for users who urgently need to use computers, preferential charging services can also be provided. Apartments, hotels and commercial housing can improve their service levels through these free use areas, attract more guests and residents, and increase rental income.

[0006] However, this technology has the limitation of being unable to achieve real-time monitoring and status tracking of equipment, and it is difficult to accurately identify the usage and fault status of equipment, resulting in waste of resources and complex management. In addition, traditional technology also has limitations in data collection, and it is difficult to comprehensively collect equipment usage records, commodity purchase records, and activity participation records. It lacks in-depth analysis of user behavior, making it difficult to provide personalized recommendation services.

[0007] In view of this, the present invention is proposed. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a shared service revenue generation method, and solve the problems raised in the above-mentioned background technology.

[0009] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0010] A shared service revenue generating method comprises the following steps:

[0011] Step S1: Set a unique electronic code on each device in the room and create a cloud platform matching the corresponding room;

[0012] Step S2: The cloud platform is divided into a registration end and a management end, the registration end is used to collect user registration information, and the management end is used to view and set the data of the cloud platform;

[0013] Step S3: recommending devices, products or activities similar to those liked by the user based on the user's historical usage data, and recommending options that meet the user's preferences based on the characteristics of the device;

[0014] Step S4: Optimize resource allocation using a linear programming model, monitor resource usage in real time, and dynamically adjust the allocation of equipment and services;

[0015] Step S5: Use historical data to perform trend analysis and demand forecasting, analyze factors that affect demand, and predict future equipment usage and service needs;

[0016] Step S6: Unlock the device according to the type selected by the user and generate the corresponding data. The obtained data will be uploaded to the blockchain and encrypted.

[0017] Optionally, the registration end is divided into tenants and non-tenants, and the user is identified as a tenant or a non-tenant based on the obtained user registration information, and the project in the cloud platform is adjusted according to the obtained category, wherein resources give priority to meeting the needs of tenants, and the service requests of tenants will be processed first.

[0018] Optionally, in step S2, the steps for the user to register the cloud platform registration terminal are:

[0019] Step S2.1: Open a browser for tenants and non-tenants, enter the URL address of the platform, and enter the registration page;

[0020] Step S2.2: The user fills in the name, password, confirm password, ID number, ID date, and contact information in the registration form and performs face recognition authentication based on the name, ID number, and ID date;

[0021] Step S2.3: If the verification fails, the server returns the corresponding error message, and the front end prompts the user to make changes;

[0022] Step S2.4: After all verifications are passed, the server hashes the user password and stores the user information in the database;

[0023] Step S2.5: The user returns to the login page and logs in using the registered ID number and password.

[0024] Optionally, based on the user's historical usage data, recommend similar devices, products or activities that the user likes. Based on the characteristics of the device, the steps of recommending options that meet the user's preferences are:

[0025] Step 3.1: Collect the user's device usage records, product purchase records, and activity participation records and use the cosine similarity method to calculate the similarity between users; based on the historical behaviors of similar users, recommend the user's favorite devices, products, or activities;

[0026] Step S3.2: Construct feature vector v for each device, product, and activity i , based on the user's historical usage records, calculate the user's preference vector u, and calculate the similarity sim(u,v i ) is used for recommendation, and the expression for calculating similarity is: In the formula, sim(u,v i ) represents the user preference vector u and the content feature vector v i The similarity of , · represents the dot product of vectors, ||u|| and ||v i || respectively represent the Euclidean norm of the vector, v i is the feature vector of the ith content, v uj is the feature vector of the jth content used by the user historically, u represents the user's preference vector, and m is the number of contents used by the user historically.

[0027] Step S3.3: Hybrid recommendation combines the results of collaborative filtering and content recommendation to generate a final recommendation list. According to the priority of the final recommendation list, the corresponding service is recommended to the user. The expression is: In the formula, is the final rating prediction of hybrid recommendation, μ is the global average of all ratings, and b u and b i are the bias terms of user u and item i, respectively, and q i and p u are the feature vectors of item i and user u respectively, and α is the weight parameter.

[0028] Optionally, step S4.1: the processor collects usage data from each device in real time, including the usage time, idle time, maintenance records and fault logs of the device, and updates the collected data to the optimization model in real time to ensure that the model reflects the latest status and usage of the device;

[0029] Step S4.2: Calculate the optimal allocation plan of equipment using linear programming, with the goal of maximizing equipment utilization and minimizing idle time;

[0030] Step S4.3: Based on the optimization results, the equipment is preferentially allocated to the tenants with the most urgent current needs. When there is no tenant demand, the equipment is reasonably allocated to non-tenants. By dynamically adjusting the equipment allocation, the use of the equipment is monitored in real time, and the allocation plan is adjusted in time.

[0031] Optionally, step S5 uses historical data to perform trend analysis and demand forecasting, analyzes factors that affect demand, and forecasts future equipment usage and service demand as follows:

[0032] Step S5.1: Collect the usage time, usage duration and user information of each device, collect the time, product type, purchase quantity and purchaser information of each product purchase, and collect the participation time, activity type, number of participants and participant information of each activity;

[0033] Step S5.2: Use interpolation, filling, deletion and other methods to handle missing values ​​in the data and identify and handle outliers in the data, and calculate the device usage frequency FD, product purchase frequency FS, and activity participation frequency FA;

[0034] Step S5.3: Decomposing time series data Decompose the time series data Yt into trend component Tt, seasonal component St and random component Rt, identify and analyze the long-term trend Tt in the data; extract the long-term trend Tt in the data, calculate the seasonal component St, subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle;

[0035] Step S5.4: Perform time series forecasting, analyze the factors that affect demand, and finally identify and analyze random fluctuations and noise in the data. Through the decomposed time series data, identify and analyze the long-term trends in the data to predict future changes in demand.

[0036] Optionally, the original time series data Y in step S.3 t Decomposed into trend component T t , seasonal component S t and the random component R t , which uses the moving average method to extract the long-term trend T t The expression is: Among them, k is the size of the moving window, and then the seasonal component S is calculated t , subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle. The expression is: Where P is the period length, n is the number of periods, and the expression for calculating time series data is: t =T t +S t +R t .

[0037] Optionally, in step S2.5.3, the user returns to the login page and logs in using the registered ID number and password:

[0038] Step S2.5.1: The user logs in to the system and enters his ID number and password. The user submits a login request, and the system verifies the user information. If the verification is successful, the user category is verified. After the verification is passed, the user successfully logs in to the system and enters the main page;

[0039] Step S2.5.2: The system main page displays different types of device options according to user categories, and classifies user categories using a priority algorithm, and queries the currently available device list based on the classification results;

[0040] Step S2.5.3: The retrieved list of available devices is displayed to the user, and the user selects a device from the list of available devices to rent or use.

[0041] Optionally, step S6 unlocks the device according to the type selected by the user and generates corresponding data. The obtained data will be uploaded to the blockchain. The steps for encrypting the data are as follows:

[0042] According to the device type selected by the user, send a command to unlock the corresponding device. After the device is unlocked, the device status is recorded as "used";

[0043] After the device starts to be used, the system collects and records usage data in real time and uploads the generated device usage data to the blockchain;

[0044] The system verifies whether the data upload is successful, ensuring that the data has been accepted and recorded by the blockchain network. If the upload fails, retry the upload.

[0045] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all the advantages described below at the same time:

[0046] 1. By setting a unique electronic code on each device and creating a cloud platform, accurate management and efficient monitoring of the device are achieved, ensuring the transparency of the device's usage status and location. Dividing the cloud platform into a registration end and a management end can effectively collect user information and facilitate administrators to monitor and adjust, thereby improving data management efficiency. The recommendation system based on user historical data provides personalized recommendations for devices, products, and activities to improve user experience and satisfaction. The linear programming model is used to optimize resource allocation, monitor device usage in real time, and dynamically adjust to ensure efficient use of resources and reduce waste.

[0047] 2. Through historical data analysis and demand forecasting, peak periods and demand changes can be identified in advance, and resource preparation and configuration can be optimized. Equipment usage data is uploaded to the blockchain and encrypted, which enhances data security and transparency and prevents data tampering and leakage. Overall, this method not only optimizes resource management and user experience, but also improves operational efficiency and service quality, and enhances the competitiveness and profitability of the platform.

[0048] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described below are only some embodiments. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0050] In the figure:

[0051] Figure 1 Flowchart of methods for generating revenue for shared services.

[0052] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but are intended to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] The present invention will now be described in further detail with reference to the accompanying drawings.

[0054] See also Figure 1 As shown, in this embodiment, a shared service revenue generating method is provided, comprising the following steps:

[0055] Step S1: Set a unique electronic code on each device in the room and create a cloud platform that matches the corresponding room; through the unique electronic code, each device can be quickly identified and located to ensure that the device's usage status and location are clearly visible. Secondly, the creation of a cloud platform makes device management more efficient and intelligent. Administrators can remotely monitor and control devices, discover and solve problems in a timely manner, and improve management efficiency. In addition, users can easily register and use devices through the cloud platform to improve user experience and satisfaction. At the same time, centralized management and analysis of data can provide support for optimal resource allocation, ensure maximum equipment utilization, reduce resource waste, and ultimately achieve improved service quality and reduced operating costs.

[0056] Step S2: The cloud platform is divided into a registration end and a management end, the registration end is used to collect user registration information, and the management end is used to view and set the data of the cloud platform;

[0057] The registration end is specifically used to collect user registration information, simplifying the user registration process, ensuring centralized management and efficient entry of user data, and improving user experience. By separating the registration end and the management end, data security and privacy protection can be strengthened to prevent unauthorized access. The management end is used to view and set the data of the cloud platform, enabling administrators to monitor and manage the platform in real time, update and maintain data in a timely manner, and improve management efficiency. Such division of labor not only optimizes system performance and resource utilization, but also ensures the stability and reliability of the platform, supports efficient user management and data processing, and ultimately improves the overall operational efficiency and user satisfaction of the platform.

[0058] Step S3: Based on the user's historical usage data, recommend similar devices, products or activities that the user likes, and based on the characteristics of the device, recommend options that meet the user's preferences; first, this personalized recommendation can significantly improve the user experience, making users feel more convenient and satisfied when using the platform, and increasing user stickiness and loyalty. Secondly, by analyzing historical data and user behavior, the platform can understand user needs more accurately, thereby providing more targeted services and products, and improving sales and usage efficiency. Personalized recommendations can also optimize resource allocation, reduce the idle rate of equipment and products, and improve overall operational efficiency. At the same time, an accurate recommendation system can tap into potential user needs, promote cross-selling and up-selling, and increase the platform's revenue and profitability.

[0059] Step S4: Use the linear programming model to optimize resource allocation, monitor resource usage in real time, and dynamically adjust the allocation of equipment and services; the linear programming model can determine the optimal resource allocation plan through scientific calculations, ensure maximum resource utilization, reduce waste and idleness, and improve operational efficiency. Secondly, real-time monitoring of resource usage can promptly discover and solve problems and ensure the efficient operation of equipment and services. Dynamically adjust the allocation of equipment and services so that the system can flexibly respond to changes in demand and provide more flexible and efficient services. This method not only improves the utilization efficiency of resources, but also reduces operating costs and increases revenue. In addition, through optimization and dynamic adjustment, the user experience can be significantly improved, the diverse and personalized needs of users can be met, and user satisfaction and loyalty can be enhanced.

[0060] Step S5: Use historical data to perform trend analysis and demand forecasting, analyze factors that affect demand, and predict future equipment usage and service needs;

[0061] Through trend analysis, it is possible to identify long-term trends in equipment use and service demand, helping companies develop more scientific and sustainable development strategies. Secondly, demand forecasting can identify peak and trough periods in advance, thereby optimizing resource allocation, avoiding resource waste and service shortages, and improving operational efficiency. Analyzing factors that affect demand, such as seasons, holidays, and promotional activities, can help companies more accurately grasp market dynamics and changes in user demand and develop more effective marketing and service strategies. In addition, accurate demand forecasting can improve user satisfaction, and by preparing and allocating resources in advance, it can ensure stable and high-quality services during peak periods of user demand.

[0062] Step S6: Unlock the device according to the type selected by the user, and generate the corresponding data. The obtained data will be uploaded to the blockchain and encrypted. Unlock the device according to the type selected by the user, and generate the corresponding data. The data will be uploaded to the blockchain and encrypted. The automation of data generation and upload process improves the operation efficiency. Blockchain technology ensures the transparency and immutability of data, and encryption further enhances the security and privacy protection of data.

[0063] In this embodiment, the registration end is divided into tenants and non-tenants. The user is identified as a tenant or non-tenant based on the obtained user registration information, and the projects in the cloud platform are adjusted according to the obtained categories, where resources give priority to meeting the needs of tenants, and the service requests of tenants will be given priority. In this way, user types can be accurately identified and distinguished to ensure the pertinence and effectiveness of services. Secondly, giving priority to meeting the needs and service requests of tenants can improve tenant satisfaction and loyalty and enhance user experience. In addition, through reasonable resource allocation and priority processing of tenant requests, resource utilization can be optimized, service efficiency and system operation efficiency can be improved, and ultimately service quality can be improved and operating costs can be reduced, which is conducive to the sustainable development and profitability of the platform.

[0064] In this embodiment, in step S2, the steps for the user to register the cloud platform registration terminal are:

[0065] Step S2.1: Open a browser for tenants and non-tenants, enter the URL address of the platform, and enter the registration page;

[0066] Step S2.2: The user fills in the name, password, confirm password, ID number, ID date, and contact information in the registration form and performs face recognition authentication based on the name, ID number, and ID date;

[0067] Step S2.3: If the verification fails, the server returns the corresponding error message, and the front end prompts the user to make changes;

[0068] Step S2.4: After all verifications are passed, the server hashes the user password and stores the user information in the database;

[0069] Step S2.5: The user returns to the login page and logs in using the registered ID number and password.

[0070] In this embodiment, in step S3, based on the user's historical usage data, the step of recommending devices, products or activities similar to those liked by the user, and based on the characteristics of the device, the step of recommending options that meet the user's preferences is as follows:

[0071] Step 3.1: Collect the user's device usage records, product purchase records, and activity participation records and use the cosine similarity method to calculate the similarity between users; based on the historical behaviors of similar users, recommend the user's favorite devices, products, or activities;

[0072] Step S3.2: Construct feature vector v for each device, product, and activity i , based on the user's historical usage records, calculate the user's preference vector u, and calculate the similarity sim(u,v i ) is used for recommendation, and the expression for calculating similarity is: In the formula, sim(u,v i ) represents the user preference vector u and the content feature vector v i The similarity of , · represents the dot product of vectors, ||u|| and ||v i || respectively represent the Euclidean norm of the vector, v i is the feature vector of the ith content, v uj is the feature vector of the jth content used by the user historically, u represents the user's preference vector, and m is the number of contents used by the user historically.

[0073] Step S3.3: Hybrid recommendation combines the results of collaborative filtering and content recommendation to generate a final recommendation list. According to the priority of the final recommendation list, the corresponding service is recommended to the user. The expression is: In the formula, is the final rating prediction of hybrid recommendation, μ is the global average of all ratings, and b u and b i are the bias terms of user u and item i, respectively, and q i and p u are the feature vectors of item i and user u respectively, and α is the weight parameter.

[0074] In this embodiment, step S4 uses a linear programming model to optimize resource allocation, monitor resource usage in real time, and dynamically adjust the allocation of equipment and services.

[0075] Step S4.1: The processor collects usage data from each device in real time, including the device's usage time, idle time, maintenance records, and fault logs, and updates the collected data to the optimization model in a timely manner to ensure that the model reflects the latest status and usage of the device;

[0076] Step S4.2: Calculate the optimal allocation plan of equipment using linear programming, with the goal of maximizing equipment utilization and minimizing idle time;

[0077] Step S4.3: Based on the optimization results, the equipment is preferentially allocated to the tenants with the most urgent current needs. When there is no tenant demand, the equipment is reasonably allocated to non-tenants. By dynamically adjusting the equipment allocation, the equipment usage is monitored in real time, and the allocation plan is adjusted in time. When resources are idle, they are reasonably allocated to non-tenants to maximize the equipment utilization rate and reduce waste. Real-time monitoring and dynamic adjustment of allocation plans enable the system to flexibly respond to changes in demand and optimize equipment utilization efficiency and service quality.

[0078] In this embodiment, step S5 uses historical data to perform trend analysis and demand forecasting, analyzes factors that affect demand, and predicts future equipment usage and service demand.

[0079] Step S5.1: Collect the usage time, usage duration and user information of each device, collect the time, product type, purchase quantity and purchaser information of each product purchase, and collect the participation time, activity type, number of participants and participant information of each activity;

[0080] Step S5.2: Use interpolation, filling, deletion and other methods to handle missing values ​​in the data and identify and handle outliers in the data, and calculate the device usage frequency FD, product purchase frequency FS, and activity participation frequency FA;

[0081] Step S5.3: Decomposing time series data Decompose the time series data Yt into trend component Tt, seasonal component St and random component Rt, identify and analyze the long-term trend Tt in the data; extract the long-term trend Tt in the data, calculate the seasonal component St, subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle;

[0082] Step S5.4: Perform time series forecasting, analyze the factors that affect demand, and finally identify and analyze random fluctuations and noise in the data. Through the decomposed time series data, identify and analyze the long-term trends in the data to predict future changes in demand. By analyzing the factors that affect demand, we can gain a deep understanding of market dynamics and user behavior, providing strong support for marketing and operational decisions. Identify random fluctuations and noise, improve the accuracy and reliability of forecasts, and reduce forecast errors.

[0083] In this embodiment, the original time series data Y in step S.3 t Decomposed into trend component T t , seasonal component S t and the random component R t , which uses the moving average method to extract the long-term trend T t The expression is: Among them, k is the size of the moving window, and then the seasonal component S is calculated t , subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle. The expression is: Where P is the period length, n is the number of periods, and the expression for calculating time series data is: t =T t +S t +R t .

[0084] In this embodiment, in step S2.5.3, the user returns to the login page and logs in using the registered ID number and password as follows:

[0085] Step S2.5.1: The user logs in to the system and enters his / her ID number and password. The user submits a login request, and the system verifies the user information. If the verification is successful, the user category is verified. After the verification is passed, the user successfully logs in to the system and enters the main page;

[0086] Step S2.5.2: The system main page displays different types of device options according to user categories, and classifies user categories using a priority algorithm, and queries the currently available device list based on the classification results;

[0087] Displaying different types of device options on the system homepage according to user categories, and using a priority algorithm to classify user categories, and querying the currently available device list based on the classification results has significant benefits. First, this method can accurately match user needs, making the user experience more personalized and more satisfactory. Secondly, the priority algorithm ensures that the needs of important users are met first, optimizes resource utilization, and improves service response speed and quality. In addition, this classification and query mechanism can effectively reduce device idle time, improve resource utilization efficiency, and enhance the overall operational benefits of the platform. Overall, this method not only improves user satisfaction, but also optimizes resource allocation and promotes the sustainable development of the platform.

[0088] Step S2.5.3: Display the queried available device list to the user, and the user selects a device from the available device list for rental or use. By providing a real-time list of available devices, the platform can better manage resources, optimize operational processes, and meet the personalized needs of users, thereby improving overall service quality and operational efficiency.

[0089] In this embodiment, step S6 unlocks the device according to the type selected by the user and generates corresponding data. The obtained data will be uploaded to the blockchain. The steps for encrypting the data are as follows:

[0090] According to the device type selected by the user, send a command to unlock the corresponding device. After the device is unlocked, the device status is recorded as "used";

[0091] After the device starts to be used, the system collects and records usage data in real time and uploads the generated device usage data to the blockchain;

[0092] The system verifies whether the data upload is successful, ensuring that the data has been accepted and recorded by the blockchain network. If the upload fails, retry the upload.

[0093] The present invention is not limited to the above-mentioned embodiments. Anyone should be aware that any structural changes made under the enlightenment of the present invention, and any technical solutions that are the same or similar to the present invention, fall within the protection scope of the present invention. The technology, shape, and structural parts not described in detail in the present invention are all well-known technologies.

Claims

1. A shared service revenue generation method, characterized in that: The following steps are involved: Step S1: Set a unique electronic code on each device in the room and create a cloud platform matching the corresponding room; Step S2: The cloud platform is divided into a registration end and a management end, the registration end is used to collect user registration information, and the management end is used to view and set the data of the cloud platform; Step S3: recommending devices, products or activities similar to those liked by the user based on the user's historical usage data, and recommending options that meet the user's preferences based on the characteristics of the device; Step S4: Optimize resource allocation using a linear programming model, monitor resource usage in real time, and dynamically adjust the allocation of equipment and services; Step S5: Use historical data to perform trend analysis and demand forecasting, analyze factors that affect demand, and predict future equipment usage and service needs; Step S6: Unlock the device according to the type selected by the user and generate the corresponding data. The obtained data will be uploaded to the blockchain and encrypted.

2. A shared service revenue generating method according to claim 1, characterized in that: The registration end is divided into tenants and non-tenants. The user is identified as a tenant or non-tenant based on the obtained user registration information, and the project in the cloud platform is adjusted according to the obtained category. Among them, resources give priority to meeting the needs of tenants, and the service requests of tenants will be processed first.

3. A shared service revenue generating method according to claim 1, characterized in that: In step S2, the steps for the user to register the cloud platform registration terminal are: Step S2.1: Open a browser for tenants and non-tenants, enter the URL address of the platform, and enter the registration page; Step S2.2: The user fills in the name, password, confirm password, ID number, ID date, and contact information in the registration form and performs face recognition authentication based on the name, ID number, and ID date; Step S2.3: If the verification fails, the server returns the corresponding error message, and the front end prompts the user to make changes; Step S2.4: After all verifications are passed, the server hashes the user password and stores the user information in the database; Step S2.5: The user returns to the login page and logs in using the registered ID number and password.

4. A shared service revenue generating method according to claim 1, characterized in that: In step S3, based on the user's historical usage data, the steps of recommending devices, products or activities similar to those liked by the user and recommending options that meet the user's preferences based on the characteristics of the device are as follows: Step 3.1: Collect the user's device usage records, product purchase records, and activity participation records and use the cosine similarity method to calculate the similarity between users; based on the historical behaviors of similar users, recommend the user's favorite devices, products, or activities; Step S3.2: Construct feature vector v for each device, product, and activity i , based on the user's historical usage records, calculate the user's preference vector u, and calculate the similarity sim(u,v i ) is used for recommendation, and the expression for calculating similarity is: In the formula, sim(u,v i ) represents the user preference vector u and the content feature vector v i The similarity of , · represents the dot product of vectors, ||u|| and ||v i || respectively represent the Euclidean norm of the vector, v i is the feature vector of the ith content, v uj is the feature vector of the jth content used by the user historically, u represents the user's preference vector, and m is the number of contents used by the user historically. Step S3.3: Hybrid recommendation combines the results of collaborative filtering and content recommendation to generate a final recommendation list. According to the priority of the final recommendation list, the corresponding service is recommended to the user. The expression is: In the formula, is the final rating prediction of hybrid recommendation, μ is the global average of all ratings, and b u and b i are the bias terms of user u and item i, respectively, and q i and p u are the feature vectors of item i and user u respectively, and α is the weight parameter.

5. A shared service revenue generating method according to claim 1, characterized in that: Step S4 uses a linear programming model to optimize resource allocation, monitor resource usage in real time, and dynamically adjust the allocation of equipment and services. Step S4.1: The processor collects usage data from each device in real time, including the device's usage time, idle time, maintenance records, and fault logs, and updates the collected data to the optimization model in a timely manner to ensure that the model reflects the latest status and usage of the device; Step S4.2: Calculate the optimal allocation plan of equipment using linear programming, with the goal of maximizing equipment utilization and minimizing idle time; Step S4.3: Based on the optimization results, the equipment is preferentially allocated to the tenants with the most urgent current needs. When there is no tenant demand, the equipment is reasonably allocated to non-tenants. By dynamically adjusting the equipment allocation, the use of the equipment is monitored in real time, and the allocation plan is adjusted in time.

6. A shared service revenue generating method according to claim 1, characterized in that: Step S5 uses historical data to perform trend analysis and demand forecasting, analyzes factors that affect demand, and predicts future equipment usage and service demand. The steps are: Step S5.1: Collect the usage time, usage duration and user information of each device, collect the time, product type, purchase quantity and purchaser information of each product purchase, and collect the participation time, activity type, number of participants and participant information of each activity; Step S5.2: Use interpolation, filling, deletion and other methods to handle missing values ​​in the data and identify and handle outliers in the data, and calculate the device usage frequency FD, product purchase frequency FS, and activity participation frequency FA; Step S5.3: Decomposing time series data Decompose the time series data Yt into trend component Tt, seasonal component St and random component Rt, identify and analyze the long-term trend Tt in the data; extract the long-term trend Tt in the data, calculate the seasonal component St, subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle; Step S5.4: Perform time series forecasting, analyze the factors that affect demand, and finally identify and analyze random fluctuations and noise in the data. Through the decomposed time series data, identify and analyze the long-term trends in the data to predict future changes in demand.

7. A shared service revenue generating method according to claim 1, characterized in that: The original time series data Y in step S.3 t Decomposed into trend component T t , seasonal component S t and the random component R t , which uses the moving average method to extract the long-term trend T t The expression is: Among them, k is the size of the moving window, and then the seasonal component S is calculated t , subtract the long-term trend component from the data at each time point, and then calculate the average value within each seasonal cycle. The expression is: Where P is the period length, n is the number of periods, and the expression for calculating time series data is: t =T t +S t +R t .

8. A shared service revenue generating method according to claim 1, characterized in that: In step S2.5.3, the user returns to the login page and logs in using the registered ID number and password: Step S2.5.1: The user logs in to the system and enters his / her ID number and password. The user submits a login request, and the system verifies the user information. If the verification is successful, the user category is verified. After the verification is passed, the user successfully logs in to the system and enters the main page; Step S2.5.2: The system main page displays different types of device options according to user categories, and classifies user categories using a priority algorithm, and queries the currently available device list based on the classification results; Step S2.5.3: The retrieved list of available devices is displayed to the user, and the user selects a device from the list of available devices to rent or use.

9. A shared service revenue generating method according to claim 1, characterized in that: Step S6 unlocks the device according to the type selected by the user and generates the corresponding data. The obtained data will be uploaded to the blockchain. The steps for encrypting the data are as follows: According to the device type selected by the user, send a command to unlock the corresponding device. After the device is unlocked, the device status is recorded as "used"; After the device starts to be used, the system collects and records usage data in real time and uploads the generated device usage data to the blockchain; The system verifies whether the data upload is successful, ensuring that the data has been accepted and recorded by the blockchain network. If the upload fails, retry the upload.

Images