User data real-time management method and system for intelligent wearable device

Abstract

The invention relates to the technical field of data analysis, and provides a user data real-time management method and system for an intelligent wearable device, and the method achieves the refined processing of amusement park equipment data through obtaining amusement park equipment sensing and monitoring data streams and screening out key sensing and monitoring data streams from the amusement park equipment sensing and monitoring data streams. The amusement park equipment trend vector flow and the key trend vector flow are respectively obtained through two branches of the amusement park equipment data disaster recovery algorithm, the change trend of the amusement park equipment data is comprehensively analyzed, and the dynamic state of the key data is focused, so that the amusement park equipment data disaster recovery algorithm can be obtained through the data disaster recovery voting branches according to the trend vector flows. According to the method, the stability and reliability of amusement park equipment sensing monitoring data flow are intelligently judged, and a real-time disaster recovery strategy is determined accordingly, so that the accuracy of amusement park equipment monitoring data and the robustness of the system are greatly improved, and the continuity and integrity of the data can be ensured even in the face of data transmission problems or equipment faults.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, in particular to a real-time management method and system for user data of intelligent wearable devices. BACKGROUND

[0002] In the current remote amusement park wearable interaction system, amusement park device sensing monitoring data is one of the important data. However, due to various potential problems in the data transmission process, such as network delay, data loss, device failure, etc., it has become a great challenge to ensure the integrity and accuracy of the amusement park device sensing monitoring data. These problems may cause instability or abnormality of the data. In order to solve this technical problem, there is an urgent need for a technical solution that can analyze the amusement park device data trend in real time and take disaster recovery measures when necessary to ensure the continuity and reliability of the data. SUMMARY

[0003] In order to improve the above problems, the present application provides a real-time management method and system for user data of intelligent wearable devices.

[0004] The first aspect of the embodiment of the present application provides a real-time management method for user data of intelligent wearable devices, applied to a data management system, the method comprising:

[0005] Obtaining an amusement park device sensing monitoring data stream, wherein the amusement park device sensing monitoring data stream comprises X sets of amusement park device sensing monitoring data with time sequence relationship, X being an integer not less than 1;

[0006] Obtaining a key sensing monitoring data stream based on the amusement park device sensing monitoring data stream, wherein the key sensing monitoring data stream comprises X sets of key sensing monitoring data with time sequence relationship;

[0007] According to the amusement park device sensing monitoring data stream, obtaining an amusement park device trend vector stream through a first amusement park device trend identification branch included in an amusement park device data disaster recovery algorithm, wherein the amusement park device trend vector stream comprises X amusement park device trend vectors;

[0008] According to the key sensing monitoring data stream, obtaining a key trend vector stream through a second amusement park device trend identification branch included in the amusement park device data disaster recovery algorithm, wherein the key trend vector stream comprises X key trend vectors;

[0009] According to the amusement park device trend vector stream and the key trend vector stream, obtaining a disaster recovery voting result corresponding to the amusement park device sensing monitoring data stream through a data disaster recovery voting branch included in the amusement park device data disaster recovery algorithm;

[0010] determine a real-time disaster recovery strategy of the amusement park equipment sensing monitoring data stream based on the disaster recovery voting result.

[0011] Preferably, the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream and the key trend vector stream, including:

[0012] X first linear embedding encodings are obtained by a first privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector;

[0013] X second linear embedding encodings are obtained by a second privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, wherein each second linear embedding encoding corresponds to a key trend vector;

[0014] X target linear embedding encodings are obtained by combining the X first linear embedding encodings and the X second linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding;

[0015] The disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings.

[0016] Preferably, the X first linear embedding encodings are obtained by the first privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, including:

[0017] For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first local decoding trend vector is obtained by a local decoding layer included in the first privacy element reinforcement model, wherein the first privacy element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm;

[0018] For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first global decoding trend vector is obtained by a global decoding layer included in the first privacy element reinforcement model;

[0019] For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first integrated trend vector is obtained by a feature mapping layer included in the first privacy element reinforcement model according to the first local decoding trend vector and the first global decoding trend vector;

[0020] For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first linear embedding encoding is obtained by a first global decoding layer included in the first privacy element reinforcement model according to the first integrated trend vector and the amusement park equipment trend vector;

[0021] The X second linear embedding encodings obtained by the second privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, comprise:

[0022] For each group of key trend vectors in the key trend vector stream, a second local decoding trend vector is obtained by a local decoding layer included in the second privacy element reinforcement model, wherein the second privacy element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm;

[0023] For each group of key trend vectors in the key trend vector stream, a second global decoding trend vector is obtained by a global decoding layer included in the second privacy element reinforcement model;

[0024] For each group of key trend vectors in the key trend vector stream, a second integrated trend vector is obtained by a feature mapping layer included in the second privacy element reinforcement model according to the second local decoding trend vector and the second global decoding trend vector;

[0025] For each group of key trend vectors in the key trend vector stream, a second linear embedding encoding is obtained by a second global decoding layer included in the second privacy element reinforcement model according to the second integrated trend vector and the key trend vector.

[0026] Preferably, X is an integer greater than 1; the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, comprising:

[0027] A linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor;

[0028] The disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the linear embedding integrated encoding;

[0029] The X target linear embedding encodings are used to obtain a linear embedding integrated encoding by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm, and the linear embedding integrated encoding comprises:

[0030] The X target linear embedding encodings are used to obtain X first partial linear embedding encodings by a first model component included in the state element reinforcement model, wherein the state element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm;

[0031] The X first partial linear embedding encodings are used to obtain X second partial linear embedding encodings by a second model component included in the state element reinforcement model;

[0032] X user amusement park equipment state factors are determined according to the X second partial linear embedding encodings, wherein each user amusement park equipment state factor corresponds to one target linear embedding encoding;

[0033] The linear embedding integrated encoding is determined according to the X target linear embedding encodings and the X user amusement park equipment state factors.

[0034] Preferably, X is an integer greater than 1; and the amusement park equipment data disaster recovery algorithm comprises a data disaster recovery voting branch, and the data disaster recovery voting branch is used to obtain a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream according to the amusement park equipment trend vector stream and the key trend vector stream, and the disaster recovery voting result comprises:

[0035] X first linear embedding encodings are obtained by a first global decoding layer included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, wherein each first linear embedding encoding corresponds to one amusement park equipment trend vector;

[0036] X second linear embedding encodings are obtained by a second global decoding layer included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, wherein each second linear embedding encoding corresponds to one key trend vector;

[0037] The X first linear embedding encodings and the X second linear embedding encodings are combined to obtain X target linear embedding encodings, wherein each target linear embedding encoding comprises one first linear embedding encoding and one second linear embedding encoding;

[0038] The X target linear embedding encodings are used to obtain a linear embedding integrated encoding by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to one user amusement park equipment state factor;

[0039] According to the linear embedding integrated coding, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm.

[0040] In a third aspect, the embodiments of the present application provide a data management system, which is used for:

[0041] Obtaining an amusement park equipment sensing monitoring data stream, wherein the amusement park equipment sensing monitoring data stream includes X sets of amusement park equipment sensing monitoring data in chronological order, X being an integer not less than 1;

[0042] Obtaining a key sensing monitoring data stream based on the amusement park equipment sensing monitoring data stream, wherein the key sensing monitoring data stream includes X sets of key sensing monitoring data in chronological order;

[0043] According to the amusement park equipment sensing monitoring data stream, an amusement park equipment trend vector stream is obtained through a first amusement park equipment trend identification branch included in the amusement park equipment data disaster recovery algorithm, wherein the amusement park equipment trend vector stream includes X amusement park equipment trend vectors;

[0044] According to the key sensing monitoring data stream, a key trend vector stream is obtained through a second amusement park equipment trend identification branch included in the amusement park equipment data disaster recovery algorithm, wherein the key trend vector stream includes X key trend vectors;

[0045] According to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm;

[0046] A real-time disaster recovery strategy of the amusement park equipment sensing monitoring data stream is determined based on the disaster recovery voting result.

[0047] Preferably, according to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm, including:

[0048] According to the amusement park equipment trend vector stream, X first linear embedding codes are obtained through a first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm, wherein each first linear embedding code corresponds to an amusement park equipment trend vector;

[0049] X second linear embedding encodings are obtained from a second privacy element enhancement model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, and each second linear embedding encoding corresponds to a key trend vector;

[0050] X target linear embedding encodings are obtained by combining the X first linear embedding encodings and the X second linear embedding encodings;

[0051] A disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained from a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings;

[0052] The X first linear embedding encodings are obtained from a first privacy element enhancement model included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, and the first privacy element enhancement model belongs to the amusement park equipment data disaster recovery algorithm;

[0053] A first local decoding trend vector is obtained from a local decoding layer included in the first privacy element enhancement model for each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream;

[0054] A first global decoding trend vector is obtained from a global decoding layer included in the first privacy element enhancement model for each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream;

[0055] A first integrated trend vector is obtained from a feature mapping layer included in the first privacy element enhancement model according to the first local decoding trend vector and the first global decoding trend vector for each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream;

[0056] A first linear embedding encoding is obtained from a first global decoding layer included in the first privacy element enhancement model according to the first integrated trend vector and the amusement park equipment trend vector for each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream;

[0057] The X second linear embedding encodings are obtained from a second privacy element enhancement model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, and each second linear embedding encoding corresponds to a key trend vector;

[0058] For each group of key trend vectors in the key trend vector stream, a second local decoding trend vector is obtained by a local decoding layer included in the second privacy element reinforcement model, wherein the second privacy element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm;

[0059] For each group of key trend vectors in the key trend vector stream, a second global decoding trend vector is obtained by a global decoding layer included in the second privacy element reinforcement model;

[0060] For each group of key trend vectors in the key trend vector stream, a second integrated trend vector is obtained by a feature mapping layer included in the second privacy element reinforcement model according to the second local decoding trend vector and the second global decoding trend vector;

[0061] For each group of key trend vectors in the key trend vector stream, a second linear embedding encoding is obtained by a second global decoding layer included in the second privacy element reinforcement model according to the second integrated trend vector and the key trend vector;

[0062] X is an integer greater than 1; and the linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor;

[0063] The linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor;

[0064] The linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor;

[0065] The linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor;

[0066] X target linear embedding encodings are obtained by a first model component included in the state element reinforcement model based on the X target linear embedding encodings, wherein the state element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm;

[0067] X second local linear embedding encodings are obtained by a second model component included in the state element reinforcement model based on the X first local linear embedding encodings;

[0068] X user park equipment state factors are determined according to the X second local linear embedding encodings, wherein each user park equipment state factor corresponds to a target linear embedding encoding;

[0069] The linear embedding integrated encoding is determined according to the X target linear embedding encodings and the X user park equipment state factors.

[0070] Preferably, X is an integer greater than 1; the disaster recovery voting result corresponding to the park equipment sensing monitoring data stream is obtained by a data disaster recovery voting branch included in the park equipment data disaster recovery algorithm according to the park equipment trend vector stream and the key trend vector stream, and the data disaster recovery voting branch includes:

[0071] X first linear embedding encodings are obtained by a first global decoding layer included in the park equipment data disaster recovery algorithm according to the park equipment trend vector stream, wherein each first linear embedding encoding corresponds to a park equipment trend vector;

[0072] X second linear embedding encodings are obtained by a second global decoding layer included in the park equipment data disaster recovery algorithm according to the key trend vector stream, wherein each second linear embedding encoding corresponds to a key trend vector;

[0073] X target linear embedding encodings are obtained by combination processing of the X first linear embedding encodings and the X second linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding;

[0074] The linear embedding integrated encoding is obtained by a state element reinforcement model included in the park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and the X user park equipment state factors, and each target linear embedding encoding corresponds to a user park equipment state factor;

[0075] The disaster recovery voting result corresponding to the park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the park equipment data disaster recovery algorithm according to the linear embedding integrated encoding.

[0076] In a third aspect, the present application provides a data management system, comprising: a processor, and a memory and a bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is used to call a computer program in the memory to execute the real-time management method for user data of a smart wearable device.

[0077] In a fourth aspect, the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to implement the real-time management method for user data of a smart wearable device.

[0078] The real-time management method for user data of a smart wearable device provided by the present application realizes fine processing of amusement park equipment data by obtaining amusement park equipment sensing monitoring data streams and screening key sensing monitoring data streams from the data streams. Further, the two branches of the amusement park equipment data disaster recovery algorithm respectively obtain amusement park equipment trend vector streams and key trend vector streams, which not only comprehensively analyzes the change trend of the amusement park equipment data, but also focuses on the dynamics of the key data. The design enables the system to intelligently judge the stability and reliability of the amusement park equipment sensing monitoring data stream according to the trend vector streams through the data disaster recovery voting branch, and determine the real-time disaster recovery strategy accordingly. This greatly improves the accuracy of the amusement park equipment monitoring data and the robustness of the system, and even when facing data transmission problems or equipment failures, it can ensure the continuity and integrity of the data, and provides strong support for amusement park wearable interaction and other application scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0080] Figure 1 A flowchart of a real-time management method for user data of a smart wearable device provided by the present application.

[0081] Figure 2 A product module schematic diagram of a data management system provided by the present application. DETAILED DESCRIPTION

[0082] The exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood, and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0083] In order to better understand the above technical solutions, the technical solutions of the present application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0084] Please refer to Figure 1 The flowchart of the real-time management method for smart wearable device users provided by the embodiments of the present application is applied to a data management system, and the specific content description includes steps 110-160.

[0085] In one exemplary application scenario, a remote amusement park wearable interaction system is involved, which uses various amusement park device sensors (such as heart rate monitors, blood pressure meters, thermometers, etc.) to collect real-time physiological data of patients, and sends these data to the data management system for analysis and storage. However, due to various potential problems in the data transmission process (such as network delay, data loss, device failure, etc.), it is a challenge to ensure the integrity and accuracy of the data.

[0086] Step 110, acquiring amusement park device sensor monitoring data stream, wherein the amusement park device sensor monitoring data stream includes X sets of amusement park device sensor monitoring data with time sequence relationship, and X is an integer not less than 1.

[0087] The data management system first receives real-time monitoring data streams from different amusement park device sensors. These data streams include X sets of amusement park device sensor monitoring data with time sequence relationship, where X is an integer not less than 1. Each set of data contains a specific timestamp and corresponding amusement park device measurement values such as heart rate, blood pressure, body temperature, etc.

[0088] Step 120, acquiring key sensor monitoring data stream based on the amusement park device sensor monitoring data stream, wherein the key sensor monitoring data stream includes X sets of key sensor monitoring data with time sequence relationship.

[0089] Upon receiving the raw amusement park device sensor monitoring data stream, the data management system performs an initial data filtering to identify key sensor monitoring data within the stream. These key data are typically the most important measurements for assessing patient health, such as heart rate and blood pressure, which are particularly critical for monitoring patients with heart conditions. The filtered key sensor monitoring data stream also contains X sets of data, but only those identified as key amusement park device measurements.

[0090] Step 130, obtaining an amusement park device trend vector stream from a first amusement park device trend identification branch of the amusement park device data disaster recovery algorithm based on the amusement park device sensor monitoring data stream, wherein the amusement park device trend vector stream comprises X amusement park device trend vectors.

[0091] Next, the data management system processes the raw amusement park device sensor monitoring data stream using the first amusement park device trend identification branch of the amusement park device data disaster recovery algorithm. The purpose of this branch is to analyze trends in the data stream to identify any potential anomalies or instabilities. By analyzing the difference between each set of data and its preceding set, the system generates an amusement park device trend vector stream containing X amusement park device trend vectors. Each trend vector represents the trend of the corresponding amusement park device measurement over time.

[0092] Step 140, obtaining a key trend vector stream from a second amusement park device trend identification branch of the amusement park device data disaster recovery algorithm based on the key sensor monitoring data stream, wherein the key trend vector stream comprises X key trend vectors.

[0093] Similarly, the data management system also processes the key sensor monitoring data stream using the second amusement park device trend identification branch of the amusement park device data disaster recovery algorithm. This branch focuses on analyzing the key amusement park device data to identify trends that could have a significant impact on patient health. Using the same analysis method, the system generates a key trend vector stream containing X key trend vectors. These vectors provide important information about how key amusement park device measurements change over time.

[0094] Step 150, obtaining a disaster recovery voting result corresponding to the amusement park device sensor monitoring data stream from a data disaster recovery voting branch of the amusement park device data disaster recovery algorithm based on the amusement park device trend vector stream and the key trend vector stream.

[0095] After obtaining the amusement park equipment trend vector stream and the key trend vector stream, the data management system utilizes the data disaster recovery voting branch of the amusement park equipment data disaster recovery algorithm to make decisions. This branch synthesizes information from the two trend identification branches and determines whether disaster recovery measures need to be taken for the current amusement park equipment sensor monitoring data stream through a voting mechanism. The voting result is based on the consistency between trend vectors, the change amplitude, and whether it exceeds the preset threshold. If the majority of trend vectors indicate that the data is abnormal or unstable, the voting result will support taking disaster recovery strategies.

[0096] Step 160, determining the real-time disaster recovery strategy of the amusement park equipment sensor monitoring data stream based on the disaster recovery voting result.

[0097] Finally, based on the disaster recovery voting result, the data management system will determine and implement appropriate real-time disaster recovery strategies. These strategies may include starting backup sensors, increasing data transmission frequency, using data interpolation methods to fill in missing data points, or temporarily ignoring data that is considered unreliable. By implementing these strategies, the system can ensure accurate and reliable amusement park equipment sensor monitoring data even when facing data transmission problems or equipment failures.

[0098] The present application realizes the fine processing of amusement park equipment data by obtaining the amusement park equipment sensor monitoring data stream and screening out the key sensor monitoring data stream. Further, by obtaining the amusement park equipment trend vector stream and the key trend vector stream through the two branches of the amusement park equipment data disaster recovery algorithm, not only the change trend of the amusement park equipment data is comprehensively analyzed, but also the dynamics of the key data are focused on. This design enables the system to intelligently judge the stability and reliability of the amusement park equipment sensor monitoring data stream based on these trend vector streams through the data disaster recovery voting branch, and accordingly determine the real-time disaster recovery strategy. This greatly improves the accuracy of the amusement park equipment monitoring data and the robustness of the system, ensuring data continuity and integrity even when facing data transmission problems or equipment failures, providing strong support for amusement park wearable interaction and other application scenarios.

[0099] In some optional embodiments, the obtaining, according to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream by a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm comprises: obtaining, according to the amusement park equipment trend vector stream, X first linear embedding encodings by a first privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector; obtaining, according to the key trend vector stream, X second linear embedding encodings by a second privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm, wherein each second linear embedding encoding corresponds to a key trend vector; and combining the X first linear embedding encodings and the X second linear embedding encodings to obtain X target linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding; and obtaining, based on the X target linear embedding encodings, the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm.

[0100] It can be understood that the process of obtaining, according to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream by a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm is a complex process that integrates data analysis, privacy protection and decision making. This process not only ensures the accuracy and reliability of the data, but also fully considers the protection of data privacy. The following is a detailed introduction to this embodiment technical solution.

[0101] Firstly, the system will process each amusement park equipment trend vector according to the amusement park equipment trend vector stream by using the first privacy element reinforcement model in the amusement park equipment data disaster recovery algorithm, thereby obtaining X first linear embedding encodings. The key to this step lies in the design and application of the first privacy element reinforcement model, which can protect the privacy of the original amusement park equipment trend vector while extracting the key feature information in the vector and converting it into the form of linear embedding encoding. Each first linear embedding encoding uniquely corresponds to an amusement park equipment trend vector, so that the system can further analyze and process the amusement park equipment trend vector on the premise of protecting privacy.

[0102] Secondly, the system will also process each key trend vector based on the key trend vector flow using the second privacy element reinforcement model in the amusement park equipment data disaster recovery algorithm, thereby obtaining X second linear embedding encodings. Similar to the first privacy element reinforcement model, the second privacy element reinforcement model can also extract key feature information from the key trend vector while protecting data privacy and convert it into the form of linear embedding encoding. Each second linear embedding encoding uniquely corresponds to a key trend vector, so that the system can further analyze and process the key trend vector under the premise of protecting privacy.

[0103] Then, the system will combine the X first linear embedding encodings and the X second linear embedding encodings to obtain X target linear embedding encodings. Each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding, so that the system can integrate the feature information of the amusement park equipment trend vector and the key trend vector together to provide comprehensive data support for subsequent disaster recovery voting.

[0104] After obtaining the X target linear embedding encodings, the system will obtain the disaster recovery voting results corresponding to the amusement park equipment sensor monitoring data stream based on these encodings through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm. This step is a key link in decision-making. The system will judge the stability and reliability of the amusement park equipment sensor monitoring data stream according to the feature information in the target linear embedding encoding, and determine whether disaster recovery measures need to be taken accordingly. If the system determines that the data stream is abnormal or unstable, the disaster recovery mechanism will be triggered and appropriate measures will be taken to ensure the continuity and integrity of the data.

[0105] Specifically, the data disaster recovery voting branch will vote on each amusement park equipment sensor monitoring data based on the feature information in the target linear embedding encoding to determine whether it is reliable data. The voting results will be determined according to the majority principle, that is, if the majority vote that a certain data is reliable, the system will consider it as valid data; otherwise, if the majority vote that a certain data is unreliable, the system will consider it as abnormal data and take appropriate disaster recovery measures to handle it.

[0106] In this process, the design and application of the first privacy element reinforcement model and the second privacy element reinforcement model play a crucial role. They not only protect the privacy of the original amusement park equipment trend vector and key trend vector, but also extract key feature information from the vector and convert it into the form of linear embedding encoding. In this way, the system can comprehensively analyze and process the amusement park equipment sensor monitoring data stream under the premise of protecting privacy, thereby ensuring the accuracy and reliability of the data.

[0107] Meanwhile, the design of the data disaster recovery voting branch also reflects the intelligence and adaptability of the system. It can intelligently judge the stability and reliability of the amusement park equipment sensing monitoring data stream according to the feature information in the target linear embedding code, and determine whether disaster recovery measures need to be taken accordingly. This intelligent decision-making approach not only improves the efficiency and accuracy of the system, but also enhances the robustness and reliability of the system.

[0108] It can be seen that the technical scheme of this embodiment realizes comprehensive analysis and processing of amusement park equipment sensing monitoring data stream by comprehensively applying various technical means such as amusement park equipment trend vector stream, key trend vector stream, privacy element strengthening model and data disaster recovery voting branch. It not only ensures the accuracy and reliability of the data, but also fully considers the protection of data privacy, providing strong support for remote amusement park wearable interaction and other application scenarios. The proposal and application of this technical scheme will undoubtedly further improve the quality and efficiency of remote amusement park wearable interaction services.

[0109] In some optional embodiments, the first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm is a local decoding layer, a global decoding layer, and a feature mapping layer. The local decoding layer is used to extract the local feature information of each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, and the global decoding layer is used to extract the global feature information of each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream. The feature mapping layer is used to integrate the local feature information and the global feature information of each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, and obtain the first integrated trend vector of each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream.

[0110] In some optional embodiments, the process of obtaining X first linear embedding codes from the amusement park equipment trend vector stream through the first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm is a complex process that integrates local decoding, global decoding and feature mapping. This process aims to extract key feature information from the amusement park equipment trend vector and convert it into linear embedding code form for subsequent data analysis and processing. The following is a detailed introduction to the technical scheme of this embodiment. ​​​

[0111] First, for each set of amusement park device trend vectors in the amusement park device trend vector stream, the system will utilize the local decoding layer in the first privacy element reinforced model to obtain a first local decoding trend vector. The design of the local decoding layer aims to focus on the local features in the amusement park device trend vector, and through the decoding of these local features, the system can obtain more detailed and accurate information. In this way, the first local decoding trend vector contains the local feature information in the amusement park device trend vector, providing a basis for subsequent global decoding and feature mapping.

[0112] Secondly, the system will also utilize the global decoding layer in the first privacy element reinforced model to obtain a first global decoding trend vector. Unlike the local decoding layer, the design of the global decoding layer aims to focus on the global features in the amusement park device trend vector, and through the decoding of these global features, the system can obtain more comprehensive and macroscopic information. In this way, the first global decoding trend vector contains the global feature information in the amusement park device trend vector, providing an important supplement for subsequent feature mapping and linear embedding coding.

[0113] Then, the system will obtain a first integrated trend vector through the feature mapping layer in the first privacy element reinforced model according to the first local decoding trend vector and the first global decoding trend vector. The design of the feature mapping layer aims to integrate and map the local feature information and the global feature information, so as to obtain a more comprehensive and accurate feature representation. In this way, the first integrated trend vector contains the local and global feature information in the amusement park device trend vector, providing a solid foundation for subsequent linear embedding coding.

[0114] Finally, the system will obtain a first linear embedding coding through the first global decoding layer in the first privacy element reinforced model according to the first integrated trend vector and the original amusement park device trend vector. This step is the final generation link of linear embedding coding, and the system will obtain a linear, easy-to-process and analyze coding form through complex calculation and transformation according to the information in the first integrated trend vector and the original amusement park device trend vector. In this way, the first linear embedding coding contains the key feature information in the amusement park device trend vector, providing important data support for subsequent data disaster recovery voting and decision making.

[0115] It can be seen that the technical scheme of this embodiment realizes the conversion from the amusement park device trend vector to the first linear embedding code by comprehensively applying various technical means such as the local decoding layer, the global decoding layer, the feature mapping layer, and the first global decoding layer. This process not only fully considers the local and global feature information in the amusement park device trend vector, but also obtains a linear, easy-to-process and analyze code form through complex calculation and transformation. The proposal and application of this technical scheme will undoubtedly further improve the processing efficiency and accuracy of amusement park device sensing monitoring data streams, and provide more reliable data support for remote amusement park wearable interaction and other application scenarios.

[0116] In practical applications, the design and implementation of the first privacy element enhancement model is key. The model needs to be able to effectively extract key feature information from the amusement park device trend vector and convert it into a linear embedding code form. At the same time, the model also needs to fully consider the protection of data privacy to ensure that sensitive information of users is not leaked during the processing and analysis of the amusement park device trend vector. In order to achieve this goal, the model can use advanced technical means such as deep learning to continuously optimize and adjust the structure and parameters of the model through training and learning, so as to achieve better processing and protection effects.

[0117] In addition, the acquisition and application of the first linear embedding code is also an important part of this technical scheme. The code needs to accurately reflect the key feature information in the amusement park device trend vector in order to facilitate subsequent data disaster recovery voting and decision making. At the same time, the code also needs to have certain robustness and stability to maintain good performance in different application scenarios and environments. In order to achieve this goal, various technical means can be used to enhance the robustness and stability of the code, such as data enhancement, model regularization, etc.

[0118] In summary, the technical scheme of this embodiment realizes the conversion and application from the amusement park device trend vector to the first linear embedding code by comprehensively applying various technical means and methods. This process not only fully considers the key feature information in the amusement park device trend vector and the protection of data privacy, but also continuously improves the processing and protection effects by optimizing and adjusting the structure and parameters of the model. The proposal and application of this technical scheme will provide more reliable and efficient data support and services for remote amusement park wearable interaction and other application scenarios.

[0119] In a preferred embodiment, the obtaining X second linear embedding codes from the second privacy element reinforced model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream comprises: for each group of key trend vectors in the key trend vector stream, obtaining a second local decoding trend vector from a local decoding layer included in the second privacy element reinforced model, wherein the second privacy element reinforced model belongs to the amusement park equipment data disaster recovery algorithm; for each group of key trend vectors in the key trend vector stream, obtaining a second global decoding trend vector from a global decoding layer included in the second privacy element reinforced model; for each group of key trend vectors in the key trend vector stream, obtaining a second integrated trend vector from a feature mapping layer included in the second privacy element reinforced model according to the second local decoding trend vector and the second global decoding trend vector; and for each group of key trend vectors in the key trend vector stream, obtaining a second linear embedding code from a second global decoding layer included in the second privacy element reinforced model according to the second integrated trend vector and the key trend vector.

[0120] In a preferred embodiment, the process of obtaining X second linear embedding codes from the second privacy element reinforced model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream is a delicate and complex process that combines local decoding, global decoding, feature mapping, and reapplication of the global decoding layer, aiming to extract the most core feature information from the key trend vector and convert it into the form of linear embedding code.

[0121] Firstly, for each group of key trend vectors in the key trend vector stream, the system will obtain the corresponding second local decoding trend vector with the help of the local decoding layer in the second privacy element reinforced model. This step is crucial because the local decoding layer is specifically designed to capture local features in the key trend vector. By deeply decoding these local features, the system can reveal more detailed and accurate information, providing strong support for subsequent global decoding and feature mapping. The second local decoding trend vector, as the output of this step, contains rich local feature information in the key trend vector.

[0122] Subsequently, the system will also use the global decoding layer in the second privacy element reinforced model to process each group of key trend vectors, thereby obtaining the second global decoding trend vector. Unlike the local decoding layer, the global decoding layer is designed to focus on global features in the key trend vector. By comprehensively decoding these global features, the system can obtain a more macroscopic and overall information perspective. The second global decoding trend vector, as the product of this step, contains global feature information in the key trend vector, providing valuable supplements for subsequent feature mapping and linear embedding coding.

[0123] Subsequently, the system will obtain a second integrated trend vector by the feature mapping layer in the second privacy element reinforcement model, according to the second local decoding trend vector and the second global decoding trend vector that have been obtained. The essence of the design of the feature mapping layer is to integrate and map local feature information and global feature information, so as to create a more comprehensive and accurate feature representation. The second integrated trend vector, as the output of this step, integrates local and global feature information in the key trend vector, laying a solid foundation for subsequent linear embedding coding.

[0124] Finally, the system will obtain a second linear embedding code by the second global decoding layer in the second privacy element reinforcement model, according to the second integrated trend vector and the original key trend vector. This step marks the final generation of linear embedding coding. The system will obtain a linear, easy-to-process and analyze coding form through a series of complex calculations and transformations, according to the rich information in the second integrated trend vector and the original key trend vector. The second linear embedding code, as the crystallization of this process, contains the core feature information in the key trend vector, providing crucial data support for subsequent data disaster recovery voting and decision-making.

[0125] In summary, the preferred embodiment realizes the magnificent transformation from the key trend vector to the second linear embedding code by skillfully integrating various technical means such as the local decoding layer, the global decoding layer, the feature mapping layer, and the second global decoding layer. This process not only comprehensively considers the local and global feature information in the key trend vector, but also obtains a linear, easy-to-process and analyze coding form through exquisite calculation and transformation methods. The advent of this technical solution will undoubtedly further improve the processing efficiency and accuracy of amusement park equipment sensing monitoring data streams, and inject more powerful data support power into remote amusement park wearable interaction and other application scenarios.

[0126] In practical applications, the design and implementation of the second privacy element reinforcement model play a crucial role. This model needs to have the ability to extract core feature information from the key trend vector and convert it into linear embedding code. At the same time, data privacy protection is also a factor that must be considered in model design to ensure that sensitive information of users can be strictly protected in the process of processing and analyzing the key trend vector. In order to achieve this goal, the model can skillfully integrate cutting-edge technologies such as deep learning, and through continuous training and learning, optimize and adjust the structure and parameters of the model, so as to achieve better processing effect and protection effect.

[0127] In addition, the acquisition and application of the second linear embedding code is also an indispensable part of this technical solution. These codes need to accurately reflect the core feature information in the key trend vector to provide strong support for subsequent data disaster recovery voting and decision-making. At the same time, the codes also need to have excellent robustness and stability to ensure excellent performance in different application scenarios and environments. In order to achieve this goal, the data management system can use various technical means to enhance the robustness and stability of the code, such as data enhancement and model regularization.

[0128] It is worth mentioning that the preferred embodiment also fully considers the problems of computational efficiency and resource consumption in the implementation process. Through ingenious algorithm design and optimization means, the embodiment can realize efficient calculation and lower resource consumption while guaranteeing the processing effect and protection effect. This feature makes this technical solution more attractive and competitive in actual application.

[0129] In summary, the preferred embodiment realizes the magnificent transformation and application from the key trend vector to the second linear embedding code by comprehensively using various technical means and methods. This process not only fully considers the core feature information in the key trend vector and the protection of data privacy, but also continuously optimizes and adjusts to improve the processing effect and protection effect. The emergence of this technical solution will bring more reliable and efficient data support and service experience for remote amusement park wear interaction and other application scenarios.

[0130] In some examples, X is an integer greater than 1; the data disaster recovery voting result corresponding to the amusement park device sensor monitoring data stream is obtained based on the X target linear embedding codes through the data disaster recovery voting branch included in the amusement park device data disaster recovery algorithm, including: based on the X target linear embedding codes, the state factor strengthening model included in the amusement park device data disaster recovery algorithm is used to obtain a linear embedding integrated code, wherein the linear embedding integrated code is determined according to the X target linear embedding codes and X user amusement park device state factors, and each target linear embedding code corresponds to a user amusement park device state factor; the data disaster recovery voting result corresponding to the amusement park device sensor monitoring data stream is obtained based on the linear embedding integrated code through the data disaster recovery voting branch included in the amusement park device data disaster recovery algorithm.

[0131] In some examples, X is set to an integer greater than 1, which represents that the data management system will handle multiple target linear embedding encodings. Based on such a setting, the data management system obtains the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm. This process not only involves the comprehensive processing of multiple target linear embedding encodings, but also fully considers the influence of user amusement park equipment state factors to ensure the accuracy and reliability of the voting result. The following is a detailed and coherent introduction to this technical solution.

[0132] First, the data management system needs to obtain a linear embedding integrated encoding based on X target linear embedding encodings through the state element strengthening model in the amusement park equipment data disaster recovery algorithm. This step is the core of the whole process, which requires the data management system to not only consider the X target linear embedding encodings, but also combine them with user amusement park equipment state factors. Each target linear embedding encoding corresponds to a specific user amusement park equipment state factor, and this one-to-one correspondence ensures that the data management system can fully consider individual differences and changes in amusement park equipment state when integrating the encoding. The design of the state element strengthening model is to achieve this goal, which can obtain a comprehensive linear embedding integrated encoding based on X target linear embedding encodings and corresponding X user amusement park equipment state factors through complex calculations and transformations. This integrated encoding not only contains the information of the original target linear embedding encoding, but also integrates the influence of the user amusement park equipment state factor, providing a more comprehensive and accurate data basis for subsequent data disaster recovery voting.

[0133] Second, after the data management system obtains the linear embedding integrated encoding, it can obtain the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm according to this encoding. The data disaster recovery voting branch is an important part of the amusement park equipment data disaster recovery algorithm, which is responsible for making voting decisions based on the input linear embedding integrated encoding. In this process, the data disaster recovery voting branch will fully utilize the information in the linear embedding integrated encoding, and through a series of complex calculations and judgments, it will obtain the final voting result. This result represents the disaster recovery measures or decisions that the amusement park equipment sensing monitoring data stream should take in the current state, and is an important basis for subsequent data processing and analysis.

[0134] It is worth mentioning that the data disaster recovery voting branch fully considers the reliability and accuracy of data in design. It adopts multiple technical means and methods to ensure the accuracy and reliability of the voting results. For example, it may perform multiple verifications and checks on the input linear embedding integrated encoding to ensure its integrity and consistency; at the same time, it also uses advanced algorithms and models to deeply analyze and mine the data to extract more useful and accurate information. These measures together ensure that the data disaster recovery voting branch can make correct and reliable voting decisions.

[0135] In addition, the implementation of the entire technical solution also fully considers the problems of computing efficiency and resource consumption. When processing a large number of target linear embedding encodings and user amusement park device state factors, the data management system needs to ensure the efficiency and stability of the algorithm. In order to achieve this goal, the data management system uses multiple optimization means and techniques to improve the processing speed of the algorithm and reduce resource consumption. For example, the data management system can use parallel computing and distributed storage technologies to speed up data processing and storage; at the same time, the data management system can also simplify and optimize the algorithm to reduce its complexity and computational load. These measures together ensure that the entire technical solution can guarantee the processing effect and protection effect while realizing efficient computing and low resource consumption.

[0136] In summary, based on X target linear embedding encodings, the data disaster recovery voting branch in the amusement park device data disaster recovery algorithm obtains the disaster recovery voting results corresponding to the amusement park device sensor monitoring data stream is a complex and delicate process. It requires the data management system not only to fully consider the influence of multiple target linear embedding encodings and user amusement park device state factors, but also to ensure the accuracy and reliability of the voting results. In order to achieve this goal, the data management system uses advanced technical means and methods such as state element strengthening model and data disaster recovery voting branch, and through multiple optimization means to improve the processing speed of the algorithm and reduce resource consumption. The proposal and application of this technical solution will undoubtedly provide more comprehensive, accurate and reliable support for the processing and analysis of amusement park device sensor monitoring data stream.

[0137] In further embodiments, the obtaining of the linear embedding integrated code based on the X target linear embedding codes through the state element reinforcement model included in the amusement park device data disaster recovery algorithm comprises: obtaining X first partial linear embedding codes based on the X target linear embedding codes through a first model component included in the state element reinforcement model, wherein the state element reinforcement model belongs to the amusement park device data disaster recovery algorithm; obtaining X second partial linear embedding codes based on the X first partial linear embedding codes through a second model component included in the state element reinforcement model; determining X user amusement park device state factors according to the X second partial linear embedding codes, wherein each user amusement park device state factor corresponds to a target linear embedding code; and determining the linear embedding integrated code according to the X target linear embedding codes and the X user amusement park device state factors.

[0138] In further embodiments, the data management system delves into the specific implementation of obtaining the linear embedding integrated code based on the X target linear embedding codes through the state element reinforcement model in the amusement park device data disaster recovery algorithm. This process not only involves fine processing of the target linear embedding codes, but also gradually refines and strengthens the core information in the codes through two key model components of the state element reinforcement model, ultimately achieving a comprehensive and accurate description of the user's amusement park device state.

[0139] First, the data management system obtains X first partial linear embedding codes based on the X target linear embedding codes through a first model component included in the state element reinforcement model. This step is the starting point of the entire process, which requires the data management system to take each target linear embedding code as input and perform preliminary processing and transformation through the first model component. The design of the first model component fully considers the characteristics and structure of the target linear embedding codes, and through a series of complex calculations and mappings, it transforms the original target linear embedding codes into first partial linear embedding codes that are more expressive and descriptive. This transformation process not only preserves the core information in the original codes, but also further strengthens their local features and details, providing a more rich and accurate data foundation for subsequent processing and analysis.

[0140] Subsequently, the data management system obtains X second local linear embedding encodings through the second model component included in the state element enhancement model based on the X first local linear embedding encodings obtained in the previous step. This step is a further refinement and enhancement of the first local linear embedding encodings. The second model component fully considers the characteristics and requirements of the first local linear embedding encodings in design, and through more complex and delicate calculations and mappings, it converts the first local linear embedding encodings into second local linear embedding encodings that are more representative and descriptive. This conversion process not only further enhances the local features and details in the encodings, but also optimizes and adjusts the robustness and stability of the encodings, providing more reliable and accurate data support for the subsequent determination of user amusement park equipment state factors.

[0141] Then, the data management system determines X user amusement park equipment state factors based on the X second local linear embedding encodings obtained in the previous step. This step is a key link in the entire process, which requires the data management system to correspond the second local linear embedding encodings with the user amusement park equipment state factors. Each user amusement park equipment state factor corresponds to a specific second local linear embedding encoding, and this one-to-one correspondence ensures that the data management system can fully consider the local features and details in the encodings when determining the user amusement park equipment state factors. Through complex calculations and judgments, the data management system can extract the core information of the user amusement park equipment state factors from the second local linear embedding encodings and use it as an important basis for subsequent processing and analysis.

[0142] Finally, the data management system determines the linear embedding integrated encoding based on the X target linear embedding encodings and the X user amusement park equipment state factors determined in the previous step. This step is the end of the entire process and the core goal of the entire technical solution. The design and requirements of the linear embedding integrated encoding fully consider the characteristics and requirements of the target linear embedding encodings and the user amusement park equipment state factors. Through ingenious algorithm design and optimization means, the data management system can integrate the core information of the target linear embedding encodings and the user amusement park equipment state factors together to form a comprehensive, more expressive and descriptive linear embedding integrated encoding. This integrated encoding not only contains the information of the original target linear embedding encodings, but also incorporates the influence of the user amusement park equipment state factors, providing a more comprehensive and accurate data basis and support for subsequent data processing and analysis.

[0143] In summary, based on X target linear embedding encodings, the linear embedding integrated encoding is obtained through the state element strengthening model in the amusement park equipment data disaster recovery algorithm, which is a complex and delicate process. It requires the data management system not only to fully consider the characteristics and structure of the target linear embedding encoding, but also to gradually refine and strengthen through the two key model components of the state element strengthening model. At the same time, the data management system also needs to correspond the second local linear embedding encoding with the user amusement park equipment state factor, and finally determine a comprehensive linear embedding integrated encoding. The proposal and application of this technical solution will undoubtedly provide more comprehensive, accurate and reliable support and help for the processing and analysis of amusement park equipment sensor monitoring data stream. In practical application, the data management system can adjust and optimize the technical solution according to specific needs and scenarios to achieve better processing effect and application value.

[0144] In some examples, X is an integer greater than 1; and the obtaining, according to the amusement park equipment trend vector stream and the key trend vector stream, the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm, comprises: obtaining X first linear embedding encodings according to the amusement park equipment trend vector stream through a first global decoding layer included in the amusement park equipment data disaster recovery algorithm, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector; obtaining X second linear embedding encodings according to the key trend vector stream through a second global decoding layer included in the amusement park equipment data disaster recovery algorithm, wherein each second linear embedding encoding corresponds to a key trend vector; combining processing the X first linear embedding encodings and the X second linear embedding encodings to obtain X target linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding; obtaining a linear embedding integrated encoding based on the X target linear embedding encodings through a state element strengthening model included in the amusement park equipment data disaster recovery algorithm, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor; obtaining the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the linear embedding integrated encoding.

[0145] In yet another example, X is set to an integer greater than 1, which represents that the data management system will consider multiple amusement park equipment trend vectors and key trend vectors simultaneously when processing the amusement park equipment sensor monitoring data stream. The goal of the data management system is to obtain corresponding disaster recovery voting results based on these vector streams through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm. This process involves multiple steps, including processing by the global decoding layer, combination of linear embedding codes, application of state element reinforcement models, and finally obtaining the voting results. The following is a detailed and coherent introduction to this technical solution.

[0146] First, the data management system needs to obtain X first linear embedding codes from the amusement park equipment trend vector stream through the first global decoding layer in the amusement park equipment data disaster recovery algorithm. The purpose of this step is to convert the amusement park equipment trend vector stream into a more expressive and processable linear embedding code form. Each first linear embedding code corresponds to an amusement park equipment trend vector, and this one-to-one correspondence ensures that the data management system can fully consider the influence of each amusement park equipment trend vector in subsequent processing. The design of the first global decoding layer fully considers the characteristics and structure of the amusement park equipment trend vector, and through complex calculations and transformations, it is converted into a first linear embedding code that is more descriptive and analyzable.

[0147] Second, the data management system needs to obtain X second linear embedding codes from the key trend vector stream through the second global decoding layer in the amusement park equipment data disaster recovery algorithm. This step is similar to the previous step, but the object of processing is the key trend vector stream. Each second linear embedding code corresponds to a key trend vector, and this correspondence also ensures that the data management system can fully consider the influence of each key trend vector in subsequent processing. The second global decoding layer is designed to fully consider the characteristics and requirements of the key trend vector, and through targeted calculations and mappings, it is converted into a second linear embedding code that is more representative and descriptive.

[0148] Next, the data management system needs to combine X first linear embedding codes and X second linear embedding codes to obtain X target linear embedding codes. This step is a key link in the entire process, which requires the data management system to effectively combine and integrate two different types of linear embedding codes. Each target linear embedding code includes a first linear embedding code and a second linear embedding code, and this combination ensures that the data management system can consider the influence of both amusement park equipment trend vectors and key trend vectors in subsequent processing. Through clever algorithm design and optimization means, the data management system can effectively integrate the two linear embedding codes to form a target linear embedding code that is more comprehensive and descriptive.

[0149] Then, the data management system needs to obtain the linear embedding integrated encoding based on the X target linear embedding encodings through the state element reinforcement model in the amusement park equipment data disaster recovery algorithm. This step is the core link of the entire technical solution, which requires the data management system to not only consider the information of the target linear embedding encodings, but also fully consider the influence of the user amusement park equipment state factors. The design of the linear embedding integrated encoding fully considers the characteristics and needs of the target linear embedding encodings and the user amusement park equipment state factors. Through the processing and optimization of the state element reinforcement model, the data management system can fuse the core information of the target linear embedding encodings and the user amusement park equipment state factors together to form a comprehensive, more expressive and descriptive linear embedding integrated encoding. This integrated encoding not only contains the information of the original target linear embedding encodings, but also integrates the influence of the user amusement park equipment state factors, providing a more comprehensive and accurate data basis and support for subsequent data processing and analysis.

[0150] Finally, the data management system needs to obtain the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream according to the linear embedding integrated encoding through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm. This step is the final goal of the entire technical solution and is also the key link for the data management system to transform the results of all previous steps into practical applications. The design of the data disaster recovery voting branch fully considers the characteristics and needs of the linear embedding integrated encoding, and through complex calculations and judgments, the data management system can extract key information from the linear embedding integrated encoding and make disaster recovery voting decisions accordingly. This decision represents the judgment and selection of the data management system on the disaster recovery measures or strategies that should be taken for the amusement park equipment sensor monitoring data stream under the current state.

[0151] In summary, obtaining the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream through the data disaster recovery voting branch in the amusement park equipment data disaster recovery algorithm based on the amusement park equipment trend vector stream and the key trend vector stream is a complex and delicate process. It requires the data management system to not only fully consider the characteristics and structure of the amusement park equipment trend vector and the key trend vector, but also to perform effective transformation and processing through the global decoding layer. At the same time, the data management system needs to effectively combine and integrate two different types of linear embedding encodings and obtain a more comprehensive linear embedding integrated encoding through the state element reinforcement model. Finally, the data management system needs to make disaster recovery voting decisions based on this integrated encoding. The proposal and application of this technical solution will undoubtedly provide more comprehensive, accurate and reliable support and help for the processing and analysis of amusement park equipment sensor monitoring data streams. In actual applications, the data management system can adjust and optimize this technical solution according to specific needs and scenarios to achieve better processing results and application value.

[0152] Reference should also be made to Figure 2 The embodiment of the present application further provides a data management system 100, comprising a processor 111, a memory 112 and a bus 113 connected with the processor 111. The processor 111 and the memory 112 complete mutual communication through the bus 113. The processor 111 is used for calling program instructions in the memory 112, so as to execute the real-time management method for user data of the smart wearable device.

[0153] It should be further understood that the terms "comprise", "comprising", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or system including a series of elements does not only include those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or system. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another same element in the process, method, article or system including the element.

[0154] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0155] The above merely illustrates the embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various modifications and changes to the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A smart wearable device user data real-time management method, characterized in that, The method is applied to a data management system and comprises: obtaining an amusement park equipment sensing monitoring data stream, wherein the amusement park equipment sensing monitoring data stream comprises X sets of amusement park equipment sensing monitoring data in chronological order, X being an integer not less than 1; obtaining a key sensing monitoring data stream based on the amusement park equipment sensing monitoring data stream, wherein the key sensing monitoring data stream comprises X sets of key sensing monitoring data in chronological order; obtaining an amusement park equipment trend vector stream by a first amusement park equipment trend identification branch included in an amusement park equipment data disaster recovery algorithm according to the amusement park equipment sensing monitoring data stream, wherein the amusement park equipment trend vector stream comprises X amusement park equipment trend vectors; obtaining a key trend vector stream by a second amusement park equipment trend identification branch included in the amusement park equipment data disaster recovery algorithm according to the key sensing monitoring data stream, wherein the key trend vector stream comprises X key trend vectors; obtaining a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream by a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream and the key trend vector stream; determining a real-time disaster recovery strategy of the amusement park equipment sensing monitoring data stream based on the disaster recovery voting result.

2. The method of claim 1, wherein, The method further comprises: obtaining X first linear embedding codes by a first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, wherein each first linear embedding code corresponds to an amusement park equipment trend vector; obtaining X second linear embedding codes by a second privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, wherein each second linear embedding code corresponds to a key trend vector; performing combination processing on the X first linear embedding codes and the X second linear embedding codes to obtain X target linear embedding codes, wherein each target linear embedding code comprises a first linear embedding code and a second linear embedding code; obtaining the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding codes.

3. The method of claim 2, wherein, The method further comprises: obtaining first local decoding trend vectors by a local decoding layer included in the first privacy element strengthening model for each set of amusement park equipment trend vectors in the amusement park equipment trend vector stream, wherein the first privacy element strengthening model belongs to the amusement park equipment data disaster recovery algorithm. For each set of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first global decoding trend vector is obtained by a global decoding layer included in the first privacy element reinforcement model; For each set of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first integrated trend vector is obtained by a feature mapping layer included in the first privacy element reinforcement model according to the first local decoding trend vector and the first global decoding trend vector; For each set of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first linear embedding encoding is obtained by a first global decoding layer included in the first privacy element reinforcement model according to the first integrated trend vector and the amusement park equipment trend vector; The X second linear embedding encodings obtained by the second privacy element reinforcement model included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, comprise: For each set of key trend vectors in the key trend vector stream, a second local decoding trend vector is obtained by a local decoding layer included in the second privacy element reinforcement model, wherein the second privacy element reinforcement model belongs to the amusement park equipment data disaster recovery algorithm; For each set of key trend vectors in the key trend vector stream, a second global decoding trend vector is obtained by a global decoding layer included in the second privacy element reinforcement model; For each set of key trend vectors in the key trend vector stream, a second integrated trend vector is obtained by a feature mapping layer included in the second privacy element reinforcement model according to the second local decoding trend vector and the second global decoding trend vector; For each set of key trend vectors in the key trend vector stream, a second linear embedding encoding is obtained by a second global decoding layer included in the second privacy element reinforcement model according to the second integrated trend vector and the key trend vector.

4. The method of claim 2, wherein, X is an integer greater than 1; the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, comprising: Based on the X target linear embedding encodings, a linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor; According to the linear embedding integrated encoding, the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm; The linear embedding integrated encoding obtained by the state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, comprises: X target linear embedding encodings are obtained based on the state element strengthening model included in the state element strengthening model, wherein the state element strengthening model belongs to the amusement park equipment data disaster recovery algorithm; X second local linear embedding encodings are obtained based on the X first local linear embedding encodings through the second model component included in the state element strengthening model; X user amusement park equipment state factors are determined according to the X second local linear embedding encodings, wherein each user amusement park equipment state factor corresponds to a target linear embedding encoding; The linear embedding integrated encoding is determined according to the X target linear embedding encodings and the X user amusement park equipment state factors.

5. The method of claim 1, wherein, X is an integer greater than 1; and the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained based on the amusement park equipment trend vector stream and the key trend vector stream through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm, which comprises: X first linear embedding encodings are obtained based on the amusement park equipment trend vector stream through the first global decoding layer included in the amusement park equipment data disaster recovery algorithm, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector; X second linear embedding encodings are obtained based on the key trend vector stream through the second global decoding layer included in the amusement park equipment data disaster recovery algorithm, wherein each second linear embedding encoding corresponds to a key trend vector; X target linear embedding encodings are obtained by combining the X first linear embedding encodings and the X second linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding; The linear embedding integrated encoding is obtained based on the X target linear embedding encodings through the state element strengthening model included in the amusement park equipment data disaster recovery algorithm, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and the X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor; The disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained based on the linear embedding integrated encoding through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm.

6. A data management system characterized by, The data management system is used for: Obtaining an amusement park equipment sensing monitoring data stream, wherein the amusement park equipment sensing monitoring data stream includes X sets of amusement park equipment sensing monitoring data in time sequence, and X is an integer not less than 1; A key sensing monitoring data stream is obtained based on the amusement park equipment sensing monitoring data stream, wherein the key sensing monitoring data stream includes X sets of key sensing monitoring data in time sequence; An amusement park equipment trend vector stream is obtained based on the amusement park equipment sensing monitoring data stream through the first amusement park equipment trend identification branch included in the amusement park equipment data disaster recovery algorithm, wherein the amusement park equipment trend vector stream includes X amusement park equipment trend vectors; According to the key sensing monitoring data stream, a key trend vector stream is obtained through a second amusement park equipment trend identification branch included in the amusement park equipment data disaster recovery algorithm, wherein the key trend vector stream includes X key trend vectors; According to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm; Based on the disaster recovery voting result, a real-time disaster recovery strategy of the amusement park equipment sensing monitoring data stream is determined.

7. The data management system of claim 6, wherein, According to the amusement park equipment trend vector stream and the key trend vector stream, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm, including: According to the amusement park equipment trend vector stream, X first linear embedding encodings are obtained through a first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector; According to the key trend vector stream, X second linear embedding encodings are obtained through a second privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm, wherein each second linear embedding encoding corresponds to a key trend vector; X target linear embedding encodings are obtained by combining X first linear embedding encodings and X second linear embedding encodings, wherein each target linear embedding encoding includes a first linear embedding encoding and a second linear embedding encoding; Based on the X target linear embedding encodings, a disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm; According to the amusement park equipment trend vector stream, X first linear embedding encodings are obtained through a first privacy element strengthening model included in the amusement park equipment data disaster recovery algorithm, including: For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first local decoding trend vector is obtained through a local decoding layer included in the first privacy element strengthening model, wherein the first privacy element strengthening model belongs to the amusement park equipment data disaster recovery algorithm; For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first global decoding trend vector is obtained through a global decoding layer included in the first privacy element strengthening model; For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first integrated trend vector is obtained through a feature mapping layer included in the first privacy element strengthening model according to the first local decoding trend vector and the first global decoding trend vector; For each group of amusement park equipment trend vectors in the amusement park equipment trend vector stream, a first linear embedding encoding is obtained through a first global decoding layer included in the first privacy element strengthening model according to the first integrated trend vector and the amusement park equipment trend vector; Based on the key trend vector flow, X second linear embedding codes are obtained through the second privacy element enhancement model included in the amusement park equipment data disaster recovery algorithm, including: For each set of key trend vectors in the key trend vector stream, a second local decoded trend vector is obtained through the local decoding layer included in the second privacy element enhancement model, wherein the second privacy element enhancement model belongs to the amusement park equipment data disaster recovery algorithm. For each set of key trend vectors in the key trend vector stream, a second global decoded trend vector is obtained through the global decoding layer included in the second privacy element enhancement model; For each set of key trend vectors in the key trend vector stream, a second integrated trend vector is obtained through the feature mapping layer included in the second privacy element enhancement model, based on the second local decoded trend vector and the second global decoded trend vector. For each set of key trend vectors in the key trend vector stream, based on the second integrated trend vector and the key trend vector, the second linear embedding code is obtained through the second global decoding layer included in the second privacy element enhancement model; X is an integer greater than 1; the step of obtaining the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm based on X target linear embedding codes includes: Based on X target linear embedding codes, linear embedding integrated codes are obtained through the state element enhancement model included in the amusement park equipment data disaster recovery algorithm. The linear embedding integrated codes are determined according to X target linear embedding codes and X user amusement park equipment state factors, and each target linear embedding code corresponds to a user amusement park equipment state factor. Based on the linear embedded integrated coding, the disaster recovery voting result corresponding to the amusement park equipment sensor monitoring data stream is obtained through the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm; The linear embedding encoding based on X targets, obtained through the state element enhancement model included in the amusement park equipment data disaster recovery algorithm, includes: Based on X target linear embedding codes, X first local linear embedding codes are obtained through the first model component included in the state element enhancement model, wherein the state element enhancement model belongs to the amusement park equipment data disaster recovery algorithm. Based on X first local linear embedding codes, X second local linear embedding codes are obtained through the second model components included in the state element enhancement model; X user amusement park equipment state factors are determined based on X second local linear embedding codes, wherein each user amusement park equipment state factor corresponds to a target linear embedding code; The linear embedding integrated coding is determined based on X target linear embedding codes and X user amusement park equipment state factors.

8. The data management system of claim 6, wherein, X is an integer greater than 1; the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by a data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream and the key trend vector stream, and the data disaster recovery voting branch comprises: X first linear embedding encodings are obtained by a first global decoding layer included in the amusement park equipment data disaster recovery algorithm according to the amusement park equipment trend vector stream, wherein each first linear embedding encoding corresponds to an amusement park equipment trend vector; X second linear embedding encodings are obtained by a second global decoding layer included in the amusement park equipment data disaster recovery algorithm according to the key trend vector stream, wherein each second linear embedding encoding corresponds to a key trend vector; X target linear embedding encodings are obtained by combining the X first linear embedding encodings and the X second linear embedding encodings, wherein each target linear embedding encoding comprises a first linear embedding encoding and a second linear embedding encoding; a linear embedding integrated encoding is obtained by a state element reinforcement model included in the amusement park equipment data disaster recovery algorithm based on the X target linear embedding encodings, wherein the linear embedding integrated encoding is determined according to the X target linear embedding encodings and X user amusement park equipment state factors, and each target linear embedding encoding corresponds to a user amusement park equipment state factor; the disaster recovery voting result corresponding to the amusement park equipment sensing monitoring data stream is obtained by the data disaster recovery voting branch included in the amusement park equipment data disaster recovery algorithm according to the linear embedding integrated encoding.

9. A data management system, characterized by a processor, a memory and a bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to call a computer program in the memory to execute the real-time management method for smart wearable device user data according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, a program is stored thereon, and the program is executed by a processor to implement the real-time management method for smart wearable device user data according to any one of claims 1-5.

Images