Intelligent office remote cooperation method and system based on 5G communication

Abstract

The invention discloses an intelligent office remote cooperation method and system based on 5G communication, and relates to the technical field of remote cooperation, and the method comprises the steps: setting a 5G communication module according to a real-time network environment; acquiring information of the real-time remote cooperation request; inputting the information into a request identification module for analysis, and obtaining a cooperative load index; if the cooperative load index is greater than a preset cooperative load index, performing cooperative communication through a first 5G communication module; and if the cooperative load index is less than or equal to the preset cooperative load index, performing cooperative communication by using the second 5G communication module. The technical problems of low remote cooperative communication efficiency, poor stability and insufficient adaptability caused by the fact that the 5G communication module cannot be dynamically selected according to the real-time network environment and the cooperative load in the prior art are solved, and intelligent selection of the 5G communication module based on the real-time network environment and the cooperative load index is realized; and the efficiency, the stability and the adaptability of remote cooperative communication are improved.

Description

Technical Field

[0001] The present invention relates to the field of remote collaboration technology, and specifically to a smart office remote collaboration method and system based on 5G communication. Background Art

[0002] In today's era of rapid digital development, remote collaboration has become a key means for enterprises and teams to transcend geographical restrictions and achieve efficient collaborative office work. With the increasing complexity of business and the increasing diversification of collaboration needs, remote collaboration technology has been posed with severe challenges. Traditional remote collaboration solutions mostly rely on a single network channel for data transmission, without fully considering the dynamic changes in the real-time network environment. During network peak hours, bandwidth congestion and latency increase dramatically, resulting in HD video conference freezes, slow or even interrupted large file transfers during the collaboration process, seriously affecting communication efficiency and project progress. Moreover, there is a lack of accurate resource adaptation mechanisms for collaborative tasks of different scales and natures. There is no effective distinction between the network resources and processing capabilities required for small collaborative simple tasks and large and complex projects, resulting in waste or insufficient resources.

[0003] The existing technology is unable to dynamically select 5G communication modules based on the real-time network environment and collaborative load, resulting in technical problems such as low efficiency, poor stability and insufficient adaptability of remote collaborative communications. Summary of the invention

[0004] The present application provides a smart office remote collaboration method and system based on 5G communication, which is used to solve the technical problem in the prior art that the 5G communication module cannot be dynamically selected according to the real-time network environment and collaboration load, resulting in low efficiency, poor stability and insufficient adaptability of remote collaborative communication.

[0005] In view of the above problems, the present application provides a smart office remote collaboration method and system based on 5G communication.

[0006] In a first aspect of the present application, a smart office remote collaboration method based on 5G communication is provided, the method comprising:

[0007] A first 5G communication module and a second 5G communication module are set according to the real-time network environment, wherein the first 5G communication module is used to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is used to transmit a remote collaboration request carrying second identification information; information of the real-time remote collaboration request is obtained, including a remote collaboration user, a remote collaboration method, a collaboration resource file, and a required calling component; the information in the real-time remote collaboration request is input into a request identification module for analysis to obtain a collaboration load indicator; if the collaboration load indicator is greater than a preset collaboration load indicator, the real-time remote collaboration request is identified according to the first identification information, and collaborative communication is performed with the first 5G communication module; if the collaboration load indicator is less than or equal to the preset collaboration load indicator, the real-time remote collaboration request is identified according to the second identification information, and collaborative communication is performed with the second 5G communication module.

[0008] The second aspect of the present application provides a smart office remote collaboration system based on 5G communication, the system comprising:

[0009] A 5G communication module setting unit, used to set the first 5G communication module and the second 5G communication module according to the real-time network environment, wherein the first 5G communication module is used to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is used to transmit a remote collaboration request carrying second identification information; a real-time remote collaboration request information acquisition unit, used to obtain information of the real-time remote collaboration request, including remote collaboration users, remote collaboration methods, collaboration resource files, and required calling components; a collaboration load indicator acquisition unit, used to input the information in the real-time remote collaboration request into the request identification module for analysis to obtain a collaboration load indicator; a first 5G communication module collaboration communication unit, used to identify the real-time remote collaboration request according to the first identification information if the collaboration load indicator is greater than a preset collaboration load indicator, and to perform collaborative communication with the first 5G communication module; a second 5G communication module collaboration communication unit, used to identify the real-time remote collaboration request according to the second identification information if the collaboration load indicator is less than or equal to the preset collaboration load indicator, and to perform collaborative communication with the second 5G communication module.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The first 5G communication module and the second 5G communication module are set according to the real-time network environment; the information of the real-time remote collaboration request is obtained; the information in the real-time remote collaboration request is input into the request identification module for analysis to obtain the collaboration load index; if the collaboration load index is greater than the preset collaboration load index, the real-time remote collaboration request is identified according to the first identification information, and the first 5G communication module is used for collaborative communication; if the collaboration load index is less than or equal to the preset collaboration load index, the real-time remote collaboration request is identified according to the second identification information, and the second 5G communication module is used for collaborative communication. The technical effect of realizing intelligent selection of 5G communication modules based on the real-time network environment and collaboration load index, and improving the efficiency, stability and adaptability of remote collaborative communication is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a process flow of a smart office remote collaboration method based on 5G communication provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a smart office remote collaboration system based on 5G communication provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: 5G communication module setting unit 10, real-time remote collaboration request information acquisition unit 20, collaboration load indicator acquisition unit 30, first 5G communication module collaboration communication unit 40, second 5G communication module collaboration communication unit 50. DETAILED DESCRIPTION

[0016] This application provides a smart office remote collaboration method and system based on 5G communication, which is used to solve the technical problem that the prior art cannot dynamically select 5G communication modules according to the real-time network environment and collaboration load, resulting in low efficiency, poor stability and insufficient adaptability of remote collaborative communication.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a smart office remote collaboration method based on 5G communication, the method comprising:

[0019] Step S100: Set a first 5G communication module and a second 5G communication module according to the real-time network environment, wherein the first 5G communication module is used to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is used to transmit a remote collaboration request carrying second identification information.

[0020] Specifically, in the initial stage of remote collaboration in smart office, the communication module needs to be flexibly configured according to the current real-time network environment. First, the first 5G communication module and the second 5G communication module are set up to meet the needs of collaboration with different characteristics. The first 5G communication module has a high-frequency receiver and transmitter, a 2x2 antenna array, a quad-core processor and a storage element. Its advantage is that it can quickly process relatively small-scale collaboration requests, which is suitable for transmitting remote collaboration requests carrying the first identification information. These requests often have high real-time requirements and relatively small data volumes; the second 5G communication module is equipped with a 5G medium- and low-frequency receiver and transmitter, a 16x16 antenna array, an eight-core processor and a storage element, which can cope with large-scale collaboration tasks with relatively time-consuming processing, and is responsible for transmitting remote collaboration requests carrying the second identification information. Through this module setting based on the real-time network environment and the characteristics of the collaboration request, the foundation is laid for the subsequent accurate selection of communication lines and the realization of efficient and stable remote collaboration.

[0021] Step S200: obtaining information of a real-time remote collaboration request, including remote collaboration users, remote collaboration methods, collaboration resource files, and required calling components.

[0022] Specifically, in the remote collaboration process of smart office based on 5G communication, when the remote collaboration request is initiated, a comprehensive data acquisition mechanism is immediately started. For remote collaboration users, their identity information, including name, department, authority level, etc., is accurately identified, so that personalized collaboration resource allocation and authority management can be performed according to user roles in the future. The acquisition of remote collaboration methods involves determining whether to use video conferencing, real-time document collaborative editing, screen sharing demonstration or a combination of other methods. Different collaboration methods have different requirements for network resources and system functions. At the same time, deep scanning and acquisition of collaboration resource files, which may cover various types of documents, spreadsheets, presentations, design drawings, multimedia materials, etc., and detailed records of key attributes such as file format, size, storage path, etc., provide necessary information for subsequent data transmission and processing. In addition, for the required call components, their names, version numbers, functional interfaces and other information are accurately identified to ensure that the corresponding software tools, system function modules or external device drivers can be accurately called during the collaboration process, so as to ensure that the entire remote collaboration process can be carried out smoothly and efficiently, and provide comprehensive and accurate data support for subsequent collaboration load evaluation and communication module selection.

[0023] Step S300: Input the information in the real-time remote collaboration request into the request identification module for analysis to obtain a collaboration load indicator.

[0024] Specifically, the rich information in the real-time remote collaboration request is accurately input into a dedicated request identification module to obtain valuable collaborative load indicators. In this process, the request identification module first uses a feature extraction algorithm to mine key feature vectors from the request information, and then obtains multiple important indicators, including the amount of interactive data, that is, the total amount of data expected to be transmitted during the collaboration process, including file transfer size, message interaction data flow, etc.; collaboration duration, which is an estimate of the duration of this remote collaboration from the beginning to the end; component bandwidth requirements, which clearly define the network bandwidth required when calling various components; and real-time indicators, which are used to measure the strictness of collaborative tasks for real-time feedback and immediate processing. Subsequently, by calculating the information entropy size of these indicators based on the load, the information entropy reflects the uncertainty and amount of information of the data, and based on this, the weight sharing network is carefully configured to assign reasonable weights to each indicator. Finally, based on this weight sharing network, the request identification module performs complex comprehensive calculations on the interactive data volume, collaboration duration, component bandwidth requirements, and real-time indicators, thereby obtaining a collaborative load indicator that can accurately quantify the degree of demand for network resources and system performance for this remote collaboration task, providing a scientific and accurate decision-making basis for the subsequent reasonable selection of communication modules.

[0025] Step S400: If the collaborative load indicator is greater than a preset collaborative load indicator, the real-time remote collaborative request is identified according to the first identification information, and collaborative communication is performed using the first 5G communication module.

[0026] Specifically, the previously obtained collaborative load indicator is strictly compared with the preset collaborative load indicator. Once it is determined that the collaborative load indicator is greater than the preset collaborative load indicator, this indicates that the current remote collaborative task has high real-time requirements, and its data volume and processing complexity are relatively low, and it is more suitable for transmission through efficient and fast communication links. At this time, according to the pre-set first identification information, the real-time remote collaboration request is accurately identified to clarify the characteristics and processing path of the request. Subsequently, the first 5G communication module is quickly started for collaborative communication. The first 5G communication module, with its 5G high-frequency receiver and transmitter, 2x2 antenna array, quad-core processor and storage element configuration advantages, quickly and stably transmits remote collaboration requests carrying the first identification information, ensuring timely data interaction and efficient advancement of collaborative tasks, providing strong communication support for remote collaboration scenarios with high real-time requirements, and ensuring the smoothness and efficiency of the collaboration process.

[0027] Step S500: If the collaborative load indicator is less than or equal to the preset collaborative load indicator, the real-time remote collaborative request is identified according to the second identification information, and collaborative communication is performed using the second 5G communication module.

[0028] Specifically, when it is detected that the collaborative load index is less than or equal to the preset collaborative load index, it means that the data volume of this remote collaborative task is large, the processing time may be long, and the real-time requirements are relatively less stringent. Based on this situation, the real-time remote collaboration request is accurately identified according to the preset second identification information, which helps to identify the attributes of the request and the corresponding processing method. The second 5G communication module will then be enabled to carry out collaborative communication. The second 5G communication module has powerful data processing capabilities and stable transmission performance due to its 5G medium and low frequency receivers and transmitters, 16x16 antenna arrays, eight-core processors and storage elements, and can effectively carry and process such collaborative tasks with large loads. It can ensure the reliable transmission of large-scale collaborative resource files, meet the bandwidth and computing resources required for complex component calls, thereby ensuring that the entire remote collaboration process runs stably and efficiently for a relatively long time, providing solid communication guarantees for large-load remote collaboration scenarios, and achieving smooth interaction of collaborative data and smooth completion of collaborative tasks.

[0029] In a possible implementation, step S300 further includes:

[0030] Step S310: extract feature vectors from the information of the real-time remote collaboration request, and output the interactive data volume, collaboration duration, component bandwidth requirements, and real-time indicators.

[0031] Step S320: Obtain the information entropy size of the interaction data volume, collaboration duration, component bandwidth requirements, and real-time indicators based on the load.

[0032] Step S330: configuring a weight sharing network according to the information entropy size.

[0033] Step S340: the request identification module calculates the interactive data volume, collaboration duration, component bandwidth requirement and real-time index according to the weight sharing network to obtain a collaboration load index.

[0034] Specifically, in order to extract feature vectors from the information of real-time remote collaboration requests and output relevant indicators, a series of specific implementation methods are adopted. First, for the amount of interactive data, the file transfer data and message interaction data involved in the request are captured in real time through the network traffic monitoring tool, and the sum is calculated using the data statistical algorithm to accurately obtain the data transmission scale. For the collaboration duration, the task analysis algorithm is used to analyze the process and operation logic of the collaboration task, and the estimated duration is obtained by combining the user quantity estimation model and the historical collaboration duration data. In terms of component bandwidth requirements, based on the pre-built component library, which contains the bandwidth occupancy parameters of various components, the bandwidth calculation model is used to obtain accurate requirements by querying and matching the required call components. The acquisition of real-time indicators is based on the intelligent recognition system of the collaboration task type to determine whether it belongs to a task type with high real-time requirements, such as video conferencing, and combined with the real-time expectation parameters set by the user, the specific indicator value is obtained through the real-time evaluation algorithm, and finally the interactive data volume, collaboration duration, component bandwidth requirements and real-time indicators are successfully output, providing solid data support for subsequent steps.

[0035] In order to obtain the information entropy of the interaction data volume, collaboration duration, component bandwidth requirements and real-time indicators based on load, firstly, for the interaction data volume, the data fluctuations in different time periods and the correlation between the data volume and load changes are counted, and these data are input into a special information entropy calculation model. Based on the principle of information theory, this model calculates the probability density function of data distribution to obtain the information entropy of the interaction data volume based on load. For the collaboration duration, the occupation of system resources under different collaboration durations and the impact of duration changes on the stability of the overall collaboration load are analyzed. These factors are combined to calculate the information entropy of the collaboration duration using multivariate statistical analysis methods. In terms of component bandwidth requirements, the bandwidth occupation changes of components under different load conditions are monitored in real time, the probability distribution of bandwidth requirements is recorded, and then the information entropy size is obtained using the information entropy calculation formula. The information entropy of real-time indicators is obtained by calculating the dynamic programming algorithm based on the different degrees of influence of the real-time requirements on the collaboration load and the distribution of response time. Finally, the information entropy size of each indicator based on load is accurately obtained, which provides a key basis for the subsequent reasonable configuration of weight sharing networks.

[0036] When configuring the weight sharing network according to the information entropy, the following method is used: First, the information entropy is normalized so that the information entropy of each indicator is in the same order of magnitude for subsequent comparison and calculation. Then, the normalized information entropy value is used as the initial weight of each indicator. Next, a weight sharing network model based on a neural network architecture is constructed, in which the input layer receives the normalized information entropy value, the hidden layer performs a nonlinear transformation on the input through a specific activation function (such as the ReLU function), and the output layer generates the final weight allocation scheme. When training this network model, the back propagation algorithm is used to minimize the error between the predicted weight and the actual demand weight, and the parameters of the hidden layer are continuously adjusted. Through multiple iterative training, the weight sharing network can accurately allocate reasonable weights for the amount of interactive data, collaboration time, component bandwidth requirements, and real-time indicators according to the information entropy, thereby ensuring the accuracy and effectiveness of the subsequent calculation of the collaboration load indicator, so that the entire remote collaboration system can be intelligently optimized according to the characteristics of different collaboration requests.

[0037] The request identification module will make full use of the configured weight sharing network to perform key calculations to obtain the collaborative load index. First, the interactive data volume, collaboration duration, component bandwidth requirements and real-time indicators are connected to the weight sharing network as input data. Each node in the weight sharing network performs weighted processing on these input data according to the pre-assigned weights. For the interactive data volume, its weight will enlarge or reduce the data volume according to the importance determined in the previous step; the collaboration duration will also play an appropriate influence in the calculation according to its weight; the component bandwidth requirements are also adjusted according to the weight; and the real-time indicators are no exception. Then, through the weighted summation and nonlinear transformation operations within the network, the weight-adjusted indicator data is deeply integrated and calculated. Finally, after multiple rounds of calculation and integration, a collaborative load indicator that can comprehensively and accurately reflect the degree of demand for system resources and network load for this real-time remote collaboration request is obtained. This indicator will serve as the key basis for the subsequent decision on which communication module to use for collaborative communication, ensuring that the entire remote collaboration process can be carried out efficiently and stably under the communication resource configuration that matches the actual needs.

[0038] In a possible implementation, step S100 further includes:

[0039] Step S110: The first 5G communication module includes a 5G high-frequency receiver and transmitter, a 2x2 antenna array, a quad-core processor, and a storage element.

[0040] Specifically, the first 5G communication module is a carefully designed, highly integrated communication component, whose internal structure and configuration work together to achieve efficient and fast remote collaborative communication. As core components, 5G high-frequency receivers and transmitters can utilize high-frequency spectrum resources to achieve high-speed data transmission, ensuring that information is quickly sent and received in a short time, which is particularly suitable for small remote collaborative requests with high real-time requirements. The 2x2 antenna array enhances the stability and reliability of communication by optimizing the direction and strength of signal reception and transmission, ensuring that good signal quality can be maintained in complex wireless environments. The quad-core processor provides the module with powerful computing power, which can quickly process the received collaborative request data, perform operations such as data parsing and protocol conversion, and efficiently control the various work processes of the communication module to ensure the timeliness of data processing. The storage element is used to temporarily store key data in the collaborative process, such as communication cache, configuration information, etc., to avoid the impact of frequent data reading operations on communication efficiency, further improving the performance of the entire communication module, enabling it to quickly and stably transmit remote collaborative requests carrying the first identification information in the smart office remote collaboration scenario, laying a solid foundation for efficient collaborative communication.

[0041] In a possible implementation, step S100 further includes:

[0042] Step S120: The second 5G communication module includes a 5G medium and low frequency receiver and transmitter, a 16x16 antenna array, an eight-core processor, and a storage element.

[0043] Specifically, the second 5G communication module is a powerful communication unit specially designed to handle large-scale, high-load remote collaboration tasks. 5G medium and low frequency receivers and transmitters are key components of its communication. The medium and low frequency band signals have better penetration and coverage, and can stably transmit data in a wider area. Even in some environments with strong signal interference, they can ensure the reliable transmission and reception of collaboration requests, which is suitable for transmitting large remote collaboration requests carrying second identification information. The 16x16 antenna array is large in scale. Compared with the antenna array of the first 5G communication module, it can provide stronger signal gain and wider signal coverage, effectively improve the stability and anti-interference ability of data transmission, and ensure the integrity and accuracy of large-scale collaborative data during transmission. The eight-core processor gives the module excellent computing power, which can easily cope with complex collaborative task processing requirements, such as decompression, encryption, transmission control of large-scale collaborative resource files, and efficient management of multiple required call components, to ensure the smoothness of the collaboration process. The storage component has a large capacity, which can not only store massive collaborative resource files, but also provide sufficient cache space for long-running collaborative tasks, reduce data reading and writing delays, and further improve the performance of the entire module when processing high-load remote collaborative communications, providing solid communication support for large-scale remote collaboration in smart office environments.

[0044] In a possible implementation, step S300 further includes:

[0045] Step S350: Determine whether the real-time remote collaboration request is a decomposable collaboration request.

[0046] Step S360: If the real-time remote collaboration request is a decomposable collaboration request, multiple decomposable collaboration requests are obtained.

[0047] Step S370: Input the multiple decomposition collaboration requests into the request identification module for analysis, and obtain multiple identification information corresponding to the multiple decomposition collaboration requests.

[0048] Step S380: Based on the multiple identification information, the multiple decomposed collaboration requests are used for collaborative communication with the first 5G communication module or the second 5G communication module.

[0049] Specifically, a comprehensive analysis algorithm is used to determine whether a real-time remote collaboration request is a decomposable collaboration request. First, for remote collaboration users, the user behavior analysis algorithm is used to analyze their operation modes and interaction rules in past collaborations to determine the degree of coupling between different user workflows; at the same time, the role association algorithm is used to evaluate the closeness between user roles to determine whether there are user groups that can operate independently. For remote collaboration methods, the process pattern recognition algorithm is used to analyze its task execution process to identify whether it contains a decomposable sub-process structure. In terms of collaborative resource files, the file structure analysis algorithm is used to analyze the logical architecture and data distribution of the file to determine whether it can be divided according to content modules or data blocks. For the required calling components, the functional dependency graph algorithm is used to draw the functional dependency relationship diagram between components to find the component subset that can run independently. Based on the above analysis results, the weighted fusion algorithm is used to assign corresponding weights to the analysis results of different factors and then make an integrated judgment to finally determine whether the real-time remote collaboration request is a decomposable collaboration request, providing a key basis for subsequent optimization processing.

[0050] After determining that the real-time remote collaboration request is a decomposable collaboration request, the operation of obtaining multiple decomposed collaboration requests is started. First, the preliminary decomposition is performed according to the independent collaboration relationship of the remote collaboration users. The user task association analysis algorithm is used to deeply explore the task division and data interaction mode of the users in the collaboration process, and a relatively independent user task set is identified, thereby obtaining the first-level decomposition result. Then, according to the remote collaboration mode, the collaboration resource file and the required calling components, the resource and process matching algorithm is used to comprehensively analyze the relationship between the process steps defined by the collaboration mode and the data flow of the collaboration resource file and the component calling logic, and check whether there is a parallel request relationship between each part in the first-level decomposition result. If a parallel request relationship is found, the parallel task merging optimization algorithm is used to merge and integrate the task parts with parallel relationships, eliminate redundant operations, optimize the task structure, and then obtain the second-level decomposition result with clearer logic and higher processing efficiency. Finally, based on this, multiple decomposed collaboration requests with reasonable structure, interrelated and independently processable are successfully obtained. These decomposed collaboration requests will lay a solid foundation for the subsequent precise allocation of communication resources and efficient processing of collaboration tasks.

[0051] The obtained multiple decomposed collaboration requests are sequentially input into the request identification module, and a comprehensive and in-depth analysis process is started to obtain multiple corresponding identification information. For each decomposed collaboration request, the request identification module first uses a feature extraction algorithm to extract features such as the number of collaborative users and the level of authority from the remote collaborative user information contained therein, extracts features such as the operation frequency and synchronization requirements from the remote collaboration mode, extracts features such as the file type, data volume, and update frequency from the collaborative resource file, and extracts features such as the component function type, resource occupancy rate, and interface complexity from the required call components, thereby constructing a feature vector for each decomposed collaboration request. Subsequently, the load evaluation algorithm is used to calculate the amount of interactive data, collaboration duration, component bandwidth requirements, and real-time indicators corresponding to each feature vector, and the information entropy calculation model is further used to obtain the information entropy size of these indicators based on the load. Then, the weight sharing network is configured based on the information entropy, so that each indicator is assigned an appropriate weight according to its importance and uncertainty. Finally, the request identification module uses a comprehensive calculation model to perform weighted calculation and integrated analysis on the interaction data volume, collaboration duration, component bandwidth requirements, and real-time indicators of each decomposed collaboration request based on the weight sharing network, thereby generating multiple identification information that can accurately characterize the characteristics, resource requirements, and processing priorities of each decomposed collaboration request, providing an accurate basis for the subsequent selection of appropriate communication modules for collaborative communication based on the identification information.

[0052] According to the multiple identification information obtained in the previous steps, multiple decomposition and collaboration requests are accurately and intelligently assigned to the corresponding communication modules to achieve efficient collaborative communication. For those decomposition and collaboration requests whose identification information shows that the amount of interactive data is small, the real-time requirements are extremely high, and the component bandwidth requirements are relatively low, they are preferentially matched with the first 5G communication module. With its own 5G high-frequency receiver and transmitter, 2x2 antenna array, quad-core processor and storage elements, the first 5G communication module can give full play to the advantages of high-frequency spectrum resources, quickly process and quickly transmit these lightweight but time-demanding requests, and avoid delays that affect the smoothness of collaboration. For decomposition and collaboration requests whose identification information shows that the amount of interactive data is large, the processing process takes a long time, the urgency of real-time feedback is slightly lower, and the component bandwidth requirements are higher, the second 5G communication module is decisively selected. The module's 5G medium and low frequency receivers and transmitters have stronger penetration and coverage capabilities. Combined with a 16x16 antenna array, an eight-core processor, and large-capacity storage components, it can steadily bear the heavy task of transmitting large amounts of data, ensuring that complex and data-intensive decomposition and collaboration requests can proceed in an orderly manner. Even in the face of massive information interactions, it can also ensure the stability and efficiency of collaboration, ultimately achieving optimized execution of the entire remote collaboration task.

[0053] In a possible implementation, step S350 further includes:

[0054] Step S351: Decompose and extract features of the remote collaboration users, remote collaboration methods, collaboration resource files, and required calling components, and output the number of collaboration users, real-time collaboration methods, resource data volume, and component coupling degree.

[0055] Step S352: The number of collaborative users, the real-time nature of the collaborative mode, the amount of resource data, and the degree of component coupling are used as multi-level nodes to generate a request decomposition decision tree, wherein each node includes a preset sorting threshold.

[0056] Step S353: judging whether the real-time remote collaboration request is a decomposable collaboration request according to the request decomposition decision tree, and outputting a decision result, wherein the decision result includes decomposable and indecomposable.

[0057] Specifically, deep feature extraction operations are carried out on key elements in real-time remote collaboration requests. For remote collaboration users, by establishing an efficient connection with the user management database, the data mining algorithm is used to deeply traverse the user login log table, accurately extract the login timestamp information of each user, and combine the detailed operation sequence in the operation behavior record table. The cluster analysis algorithm is used to identify the user group belonging to the same collaborative task, and then the number of collaborative users is accurately output through the counting function to achieve accurate quantification of the scale of collaborative manpower. For remote collaboration, the collaborative process definition file is imported, and the process parsing engine is used to analyze the task nodes, time constraints and information synchronization mechanisms therein. Through the pattern recognition algorithm, high-frequency interactive scenarios such as instant messaging and real-time data sharing are marked as high real-time modes, and processes that are executed periodically and have obvious time delays are judged as low real-time modes, so as to accurately output the real-time characteristics of the collaborative mode and provide key basis for subsequent judgment. When processing collaborative resource files, the multimodal file parsing module is started, and the corresponding parsing submodules are enabled for different types of files. For text files, character counting and encoding conversion algorithms are used to count the number of bytes; for image files, image analysis algorithms are called to obtain parameters such as resolution and color depth, and the storage format conversion formula is used to calculate the occupied space; for video files, video bitrate analysis tools are used in combination with duration information, and the video data volume calculation formula is used to obtain accurate resource data volume to ensure a comprehensive quantitative evaluation of file resources. For the required calling components, a knowledge graph based on component calling relationships is constructed, and the depth-first search algorithm in graph theory is used to traverse the calling links between components, the frequency of data interaction between nodes is counted, and the functional dependency strength between components is evaluated through the correlation calculation model. Finally, the coupling degree of components is scientifically quantified to clearly present the closeness of component collaboration. Through the above series of complex and sophisticated technical processes, four key indicators are output: the number of collaborative users, the real-time nature of the collaboration method, the amount of resource data, and the coupling degree of components, laying a solid foundation for subsequent decision-making processes.

[0058] The number of collaborative users, the real-time nature of the collaborative mode, the amount of resource data, and the degree of component coupling that are accurately extracted are used as core elements, and they are established as multi-level nodes of the decision tree. For the node of the number of collaborative users, based on the big data analysis of a large number of past collaborative projects and combined with the common team size classification standards in the industry, different intervals such as small teams (less than 10 people), medium teams (10-50 people), and large teams (more than 50 people) are divided. Each interval is a branch of the node, and accurate preset sorting thresholds are set for each branch as a key yardstick for judging the scale of collaborative users. For the node of the real-time nature of the collaborative mode, time series analysis technology is used to refer to the response time requirements under different real-time demand scenarios, and it is subdivided into high real-time (response time within 1 second), medium real-time (1-5 seconds), and low real-time (more than 5 seconds). Corresponding thresholds are also set for each category to identify the immediacy requirements of the collaborative process. For resource data volume nodes, with the help of storage capacity and network bandwidth adaptation models, according to the actual performance of data transmission and storage, small (below 100MB), medium (100MB-1GB), large (above 1GB) and other data volume levels are set. These levels and their corresponding thresholds can effectively measure the scale of collaborative resources. For component coupling nodes, through deep machine learning modeling of component interaction relationships, according to the strength of the degree of dependency between components, they are divided into loose coupling (low interaction frequency, few functional dependencies), moderate coupling (with a certain interaction frequency and functional dependency), tight coupling (frequent interaction, high functional dependency) and other states. Each state is equipped with a clear threshold to determine the tightness of component collaboration. In this way, a request decomposition decision tree with a rigorous structure, clear hierarchy, and each node with a precise preset sorting threshold is successfully constructed, providing a powerful decision-making tool for subsequent accurate judgment of whether real-time remote collaboration requests can be decomposed.

[0059] Start using the constructed request decomposition decision tree to make accurate judgments on real-time remote collaboration requests. First, compare the key indicator values ​​corresponding to the current real-time remote collaboration request, including the number of collaborative users, real-time collaboration mode, resource data volume, and component coupling, with the preset sorting thresholds of the root node of the decision tree and its subordinate branch nodes at all levels. Starting from the root node, if the number of collaborative users falls into the small team interval, continue to go deeper along the branch to check whether the real-time collaboration mode meets the threshold requirements of the corresponding sub-branch, such as whether it is high real-time or medium real-time. If the match is successful here, further verify whether the resource data volume is at the corresponding small or medium data volume level, and whether the component coupling degree matches the corresponding loose coupling or medium coupling state. In this top-down, step-by-step judgment process, as long as all indicators on a complete branch path of the decision tree meet the preset threshold conditions, the "decomposable" decision result will be decisively output; on the contrary, if the indicator does not match the threshold at any node, resulting in the inability to follow a complete branch, the real-time remote collaboration request will be judged as "indecomposable", thereby providing a clear and critical basis for the planning of subsequent collaboration processes, ensuring that the entire remote collaboration system can make the best arrangement based on the request characteristics.

[0060] In a possible implementation, step S360 further includes:

[0061] Step S361: Perform a preliminary decomposition according to the independent user collaboration relationship of the remote collaborative users to obtain a first-level decomposition result.

[0062] Step S362: determine whether there is a parallel request relationship for the first-level decomposition result according to the remote collaboration mode, collaboration resource file and required calling components; if there is a parallel request relationship, merge the parallel requests for the first-level decomposition result to obtain the second-level decomposition result.

[0063] Step S363: According to the second-level decomposition result, multiple decomposition collaboration requests are obtained.

[0064] Specifically, a highly refined analysis process was launched to achieve a preliminary decomposition and obtain the first-level decomposition results based on the independent user collaboration relationship of remote collaboration users. First, an efficient connection was established with the database that stores historical user collaboration data, and the detailed operation logs of users in each past remote collaboration were accurately extracted using data retrieval tools. These operation logs fully record every action of each user in the collaboration process in the form of structured data, including the timestamp of the operation, the type of operation (such as document editing, data uploading, command issuance, etc.), and the object of the operation. At the same time, the permission management module was called to deeply analyze the permission allocation table to obtain the various permission levels and specific permission scopes granted to each user, such as the read and write permissions for specific files, the call permissions for certain functional modules, etc., so as to clearly define the responsibilities of each user in the collaboration framework. Furthermore, the flow of interactive data between users was deeply analyzed through the traffic monitoring and analysis system. The source node (i.e., the sender user), the destination node (the receiver user), and the key indicators such as the amount of data transmitted and the transmission frequency of the data were tracked in real time to accurately depict the dynamic path and density of information transmission between users. After completing the above data collection, the cluster analysis algorithm is introduced. This algorithm uses the user's operation independence, authority boundaries, and interactive data flow characteristics as the basis for multi-dimensional clustering. Users with similar characteristics, that is, relatively independent operation paths, non-intersection in authority scope, and relatively independent interactive data flows are identified and grouped together to form independent user groups. Finally, for each independent user group generated by clustering, combined with the goals and architecture of the overall collaborative task, the corresponding preliminary task modules are automatically matched and assigned. These preliminary task modules are customized according to the capabilities and authority scope of the user group to ensure the executability and rationality of the task, smoothly realize the preliminary decomposition, and accurately obtain the first-level decomposition results. This key output has laid a solid foundation for further refining the collaborative process and improving collaborative efficiency.

[0065] Based on the obtained first-level decomposition results, we fully combine the remote collaboration mode, collaboration resource files, and the required calling components to conduct in-depth analysis to determine whether there is a potential parallel request relationship. For the remote collaboration mode, we retrieve its detailed process definition document, parse the execution order, synchronization requirements, and time constraints of each link, and clarify the order and parallel possibility of different subtasks in the process advancement. For example, some links require multiple sets of data entry to be carried out at the same time, which implies potential parallel opportunities. In the face of collaborative resource files, we enable professional file parsing tools to deeply explore the file structure, identify the data correlation between different chapters and modules in the file, and determine whether there are independent parts that can be operated synchronously by different users. For the required calling components, we use the component dependency map to analyze the resource occupancy, mutual call relationship, and data transmission flow of each component at runtime, and determine which components can run collaboratively without interfering with each other in the same period to provide support for parallel tasks. For some data processing components and visualization components, if the resource occupancy does not conflict, there are conditions for parallel operation. Once the above comprehensive analysis finds that there is a parallel request relationship in the first-level decomposition results, the task merging optimization module is immediately activated. This module follows the principle of balanced resource allocation and task synergy to finely integrate these parallel requests. It re-plans the task scheduling sequence, rationally allocates resources, and logically combines the originally scattered parallel tasks, eliminating redundant operations such as repeated data verification and multiple resource initializations, and finally successfully obtains the second-level decomposition results with more rigorous logic and more efficient resource utilization, further laying a solid foundation for the subsequent precise promotion of the collaborative process.

[0066] Based on the carefully crafted second-level decomposition results, the process of refining tasks is started to obtain multiple accurate and independent decomposition and collaboration requests. First, each task module in the second-level decomposition results is deeply analyzed, and the task feature extraction algorithm is used to sort out the key attributes of each module, such as the task objectives, start and end time nodes, required resource types and estimated usage, as well as the user groups and operation permissions involved. For example, for the second-level decomposition results of a software development project, it is clear that a certain module is responsible for the front-end interface design, the start and end time is a specific time period, graphic design software, certain memory resources are required, and a user group with art skills is involved and given specific editing permissions. Then, based on these detailed attributes, through task segmentation and reorganization technology, according to the principles of logical independence between tasks, exclusivity of resource utilization, and convenience of user operation, the large modules in the second-level decomposition results are disassembled into subtasks with clear boundaries and single functions, namely, decomposition and collaboration requests. These decomposed collaboration requests each have an independent task identifier to facilitate subsequent tracking and management. They can independently schedule the required resources to ensure that there will be no resource conflicts with other requests during execution. At the same time, they can also allow the corresponding user groups to focus on the subtasks they are responsible for without interfering with each other, thereby providing a solid task foundation for the subsequent smooth and efficient remote collaboration and ensuring that the entire collaboration process proceeds in an orderly manner.

[0067] In a possible implementation, step S100 further includes:

[0068] Step S130: Setting a first 5G communication module and a second 5G communication module according to a real-time network environment; wherein the first 5G communication module includes a first communication key, and the second 5G communication module includes a second communication key.

[0069] Step S140: When the first 5G communication module is used for collaborative communication, decryption of the collaborative communication is performed according to the first communication key.

[0070] Step S150: When the second 5G communication module is used for collaborative communication, decryption of the collaborative communication is performed according to the second communication key.

[0071] Specifically, the intelligent configuration process of the 5G communication module is started, and the first 5G communication module and the second 5G communication module are finely set according to the real-time network environment. First, through the built-in network monitoring component, the network's bandwidth, delay, packet loss rate, signal strength and other key indicator information are collected in all directions, and the intelligent analysis algorithm is used to deeply analyze these data to accurately judge the real-time status of the current network. For example, if it is monitored that the network bandwidth is relatively abundant, the delay is extremely low and the signal is stable, the first 5G communication module is preferred for collaborative tasks with extremely high real-time requirements and relatively small data transmission volume; on the contrary, when the network presents the characteristics of large bandwidth fluctuations, slightly higher delays but wide coverage, the second 5G communication module will be more suitable for those collaborative tasks with high requirements for data transmission stability and large data volume. At the same time, in order to ensure the security and confidentiality of communication, during the module initialization process, a unique first communication key is generated for the first 5G communication module, and a corresponding second communication key is generated for the second 5G communication module. These keys are generated based on complex encryption algorithms and have extremely high randomness and anti-cracking capabilities.

[0072] When it is determined that the first 5G communication module is used for collaborative communication, the matching decryption process will be immediately started. At the receiving end, the built-in decryption module will quickly obtain the encryption identifier attached to the transmitted data and recognize that the data is encrypted and transmitted via the first 5G communication module. Subsequently, based on the pre-stored first communication key, the decryption mechanism of the symmetric encryption algorithm is used to accurately restore the encrypted data. The entire decryption process is completed efficiently in a very short time, ensuring that real-time collaborative communication is not hindered, allowing data to be presented to the recipient at the fastest speed and with the most accurate content, ensuring smooth collaboration.

[0073] Similarly, if you choose to use the second 5G communication module for collaborative communication, you can also follow the established decryption process in an orderly manner. The receiving end relies on the specific identifier in the data packet header to identify that the data source is the second 5G communication module, and then calls the corresponding second communication key, and uses the adapted decryption algorithm to peel off the encrypted information layer by layer to accurately restore the encrypted data. Even in the face of massive data transmission, the original data can be accurately parsed under the premise of ensuring data security, so that the two parties can communicate and collaborate efficiently based on accurate data to meet diverse collaboration needs.

[0074] In a possible implementation, step S100 further includes:

[0075] Step S160: When any communication module among the first 5G communication module and the second 5G communication module detects an abnormality, collaborative communication is performed according to the backup communication module.

[0076] Specifically, the first 5G communication module and the second 5G communication module continue to play a key role to ensure the smooth progress of collaborative communication. However, once any of the communication modules detects an abnormal situation, such as a sudden drop in bandwidth, frequent packet loss, or signal interruption in the first 5G communication module, or an abnormality such as a surge in latency or connection timeout in the second 5G communication module, the built-in fault monitoring and early warning mechanism will be triggered immediately. With the real-time data monitoring algorithm, this mechanism can accurately locate the communication module with problems in a very short time. At the same time, it quickly switches to the backup communication mode and enables the pre-configured backup communication module. Before starting, the backup communication module has generated the corresponding backup communication key based on encryption standards similar to the original module to ensure the security of communication. During the switching process, the key information of the current collaborative task, including the data status being transmitted, user permission settings, and collaborative process nodes, is quickly synchronized to the backup communication module, so that it can seamlessly undertake subsequent collaborative communication tasks. The receiving end will also make corresponding adjustments. Based on the specific identifier in the data packet header sent by the backup communication module, it will identify the change in the communication path, call the backup communication key, and restore the data according to the adapted decryption algorithm, thereby ensuring that collaboration is not hindered by communication module failures and is always carried out stably and efficiently to meet the stringent needs of various types of real-time remote collaboration.

[0077] Embodiment 2 is based on the same inventive concept as the smart office remote collaboration method based on 5G communication in the aforementioned embodiment. Figure 2 As shown, the present application provides a smart office remote collaboration system based on 5G communication, and the system and method embodiments in the present application embodiments are based on the same inventive concept. The system includes:

[0078] The 5G communication module setting unit 10 is used to set the first 5G communication module and the second 5G communication module according to the real-time network environment, wherein the first 5G communication module is used to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is used to transmit a remote collaboration request carrying second identification information.

[0079] The real-time remote collaboration request information acquisition unit 20 is used to acquire the information of the real-time remote collaboration request, including the remote collaboration user, the remote collaboration mode, the collaboration resource file and the required calling component.

[0080] The collaboration load indicator acquisition unit 30 is used to input the information in the real-time remote collaboration request into the request identification module for analysis to acquire the collaboration load indicator.

[0081] The first 5G communication module collaborative communication unit 40 is used to identify the real-time remote collaboration request according to the first identification information if the collaborative load indicator is greater than a preset collaborative load indicator, and to perform collaborative communication with the first 5G communication module.

[0082] The second 5G communication module collaborative communication unit 50 is used to identify the real-time remote collaboration request according to the first identification information if the collaborative load indicator is less than or equal to the preset collaborative load indicator, and to perform collaborative communication with the second 5G communication module.

[0083] Furthermore, the collaborative load indicator acquisition unit 30 further includes:

[0084] The feature vector extraction unit is used to extract feature vectors from the information of the real-time remote collaboration request, and output the interactive data volume, collaboration duration, component bandwidth requirements and real-time indicators.

[0085] The information entropy size acquisition unit is used to obtain the information entropy size of the interaction data volume, collaboration duration, component bandwidth requirements and real-time indicators based on the load.

[0086] The weight sharing network configuration unit is used to configure the weight sharing network according to the size of the information entropy.

[0087] The collaborative load indicator acquisition unit is used for the request identification module to calculate the interactive data volume, collaboration duration, component bandwidth requirements and real-time indicators according to the weight sharing network to obtain the collaborative load indicator.

[0088] Furthermore, the 5G communication module setting unit 10 also includes:

[0089] The first 5G communication module includes a 5G high-frequency receiver and transmitter, a 2x2 antenna array, a quad-core processor, and a storage element.

[0090] Furthermore, the 5G communication module setting unit 10 also includes:

[0091] The second 5G communication module includes 5G medium and low frequency receivers and transmitters, a 16x16 antenna array, an eight-core processor, and storage elements.

[0092] Furthermore, the collaborative load indicator acquisition unit 30 further includes:

[0093] The decomposable collaboration request judging unit is used to judge whether the real-time remote collaboration request is a decomposable collaboration request.

[0094] The decomposition collaboration request acquisition unit is used to acquire multiple decomposition collaboration requests if the real-time remote collaboration request is a decomposable collaboration request.

[0095] The identification information acquisition unit is used to input the multiple decomposition and collaboration requests into the request identification module for analysis, and obtain multiple identification information corresponding to the multiple decomposition and collaboration requests.

[0096] The communication module collaborative communication unit is used to perform collaborative communication with the first 5G communication module or the second 5G communication module according to the multiple identification information.

[0097] Furthermore, the decomposable collaboration request determination unit further includes:

[0098] The decomposition feature extraction unit is used to extract decomposition features of the remote collaboration users, remote collaboration methods, collaboration resource files and required calling components respectively, and output the number of collaboration users, real-time collaboration methods, resource data volume and component coupling degree.

[0099] The request decomposition decision tree generation unit is used to use the number of collaborative users, the real-time performance of the collaboration mode, the amount of resource data, and the degree of component coupling as multi-level nodes to generate a request decomposition decision tree, wherein each node includes a preset sorting threshold.

[0100] The decision result output unit is used to determine whether the real-time remote collaboration request is a decomposable collaboration request according to the request decomposition decision tree, and output a decision result, wherein the decision result includes a decomposable request and an indecomposable request.

[0101] Furthermore, the decomposition collaboration request acquisition unit further includes:

[0102] The first-level decomposition result obtaining unit is used to perform preliminary decomposition according to the user collaboration independent relationship of the remote collaborative users to obtain the first-level decomposition result.

[0103] The second-level decomposition result acquisition unit is used to determine whether there is a parallel request relationship between the first-level decomposition results according to the remote collaboration method, collaboration resource files and required calling components. If there is a parallel request relationship, the parallel requests of the first-level decomposition results are merged to obtain the second-level decomposition results.

[0104] A multiple decomposition collaboration request acquisition unit is used to acquire multiple decomposition collaboration requests according to the second-level decomposition result.

[0105] Furthermore, the 5G communication module setting unit 10 also includes:

[0106] The first 5G communication module and the second 5G communication module are set according to the real-time network environment; wherein the first 5G communication module includes a first communication key, and the second 5G communication module includes a second communication key.

[0107] The first communication key decryption unit is used to decrypt collaborative communication according to the first communication key when the first 5G communication module performs collaborative communication.

[0108] The second communication key decryption unit is used to decrypt collaborative communication according to the second communication key when the second 5G communication module is used for collaborative communication.

[0109] Furthermore, the 5G communication module setting unit 10 also includes:

[0110] The backup communication module collaborative communication unit is used to perform collaborative communication according to the backup communication module when any communication module among the first 5G communication module and the second 5G communication module detects an abnormality.

[0111] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0112] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0113] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A smart office remote collaboration method based on 5G communication, characterized in that: The method comprises: Setting a first 5G communication module and a second 5G communication module according to a real-time network environment, wherein the first 5G communication module is used to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is used to transmit a remote collaboration request carrying second identification information; Obtain information about real-time remote collaboration requests, including remote collaboration users, remote collaboration methods, collaboration resource files, and required calling components; Inputting information in the real-time remote collaboration request into a request identification module for analysis to obtain a collaboration load indicator; If the collaboration load indicator is greater than a preset collaboration load indicator, identifying the real-time remote collaboration request according to the first identification information, and performing collaborative communication with the first 5G communication module; If the collaborative load indicator is less than or equal to the preset collaborative load indicator, the real-time remote collaborative request is identified according to the second identification information, and collaborative communication is performed using the second 5G communication module.

2. The method according to claim 1, characterized in that Inputting information in the real-time remote collaboration request into a request identification module for analysis to obtain a collaboration load indicator, the method comprising: Extract feature vectors from the information of the real-time remote collaboration request, and output the amount of interactive data, collaboration duration, component bandwidth requirements, and real-time indicators; Obtaining the information entropy size of the interaction data volume, collaboration duration, component bandwidth requirements, and real-time indicators based on the load; According to the information entropy, a weight sharing network is configured; The request identification module calculates the interactive data volume, collaboration duration, component bandwidth requirements, and real-time indicators according to the weight sharing network to obtain a collaboration load indicator.

3. The method according to claim 1, characterized in that The first 5G communication module includes a 5G high-frequency receiver and transmitter, a 2x2 antenna array, a quad-core processor, and a storage element.

4. The method according to claim 1, characterized in that The second 5G communication module includes 5G medium and low frequency receivers and transmitters, a 16x16 antenna array, an eight-core processor, and storage elements.

5. The method according to claim 1, characterized in that Before inputting the information in the real-time remote collaboration request into the request identification module for analysis, the method includes: Determining whether the real-time remote collaboration request is a decomposable collaboration request; If the real-time remote collaboration request is a decomposable collaboration request, obtaining multiple decomposable collaboration requests; Input the multiple decomposition and collaboration requests into the request identification module for analysis, and obtain multiple identification information corresponding to the multiple decomposition and collaboration requests; According to the multiple identification information, the multiple decomposed collaboration requests are used for collaborative communication with the first 5G communication module or the second 5G communication module.

6. The method according to claim 5, characterized in that The method for determining whether the real-time remote collaboration request is a decomposable collaboration request includes: Decompose and extract features of the remote collaboration users, remote collaboration methods, collaboration resource files, and required call components, and output the number of collaboration users, real-time collaboration methods, resource data volume, and component coupling degree; The number of collaborative users, the real-time nature of the collaborative mode, the amount of resource data, and the degree of component coupling are used as multi-level nodes to generate a request decomposition decision tree, wherein each node includes a preset sorting threshold; According to the request decomposition decision tree, it is determined whether the real-time remote collaboration request is a decomposable collaboration request, and a decision result is output, wherein the decision result includes decomposable and indecomposable.

7. The method according to claim 5, characterized in that If the real-time remote collaboration request is a decomposable collaboration request, obtaining multiple decomposable collaboration requests, the method includes: Performing a preliminary decomposition according to the user collaboration independent relationship of the remote collaboration users to obtain a first-level decomposition result; According to the remote collaboration mode, the collaboration resource file and the required calling component, it is determined whether there is a parallel request relationship between the first-level decomposition results; if there is a parallel request relationship, the parallel requests of the first-level decomposition results are merged to obtain the second-level decomposition results; According to the second-level decomposition result, multiple decomposition collaboration requests are obtained.

8. The method according to claim 1, characterized in that Setting a first 5G communication module and a second 5G communication module according to a real-time network environment; Wherein, the first 5G communication module includes a first communication key, and the second 5G communication module includes a second communication key; When the first 5G communication module is used for collaborative communication, decrypting the collaborative communication according to the first communication key; When the second 5G communication module is used for collaborative communication, the collaborative communication is decrypted according to the second communication key.

9. The method according to claim 1, characterized in that When any one of the first 5G communication module and the second 5G communication module detects an abnormality, collaborative communication is performed according to the backup communication module.

10. The smart office remote collaboration system based on 5G communication is characterized by: The system is used to implement the smart office remote collaboration method based on 5G communication according to any one of claims 1 to 9, and the system includes: a 5G communication module setting unit, configured to set a first 5G communication module and a second 5G communication module according to a real-time network environment, wherein the first 5G communication module is configured to transmit a remote collaboration request carrying first identification information, and the second 5G communication module is configured to transmit a remote collaboration request carrying second identification information; A real-time remote collaboration request information acquisition unit, used to acquire information of real-time remote collaboration requests, including remote collaboration users, remote collaboration methods, collaboration resource files, and required calling components; A collaboration load indicator acquisition unit, configured to input information in the real-time remote collaboration request into a request identification module for analysis to acquire a collaboration load indicator; A first 5G communication module collaborative communication unit, configured to identify the real-time remote collaboration request according to the first identification information and perform collaborative communication with the first 5G communication module if the collaborative load indicator is greater than a preset collaborative load indicator; The second 5G communication module collaborative communication unit is used to identify the real-time remote collaboration request according to the second identification information if the collaborative load indicator is less than or equal to the preset collaborative load indicator, and to perform collaborative communication with the second 5G communication module.

Images