Method and system for realizing enterprise collaborative office based on intelligent AI
Through intelligent AI, analyzing the functional system and data correlation of the enterprise office system, optimizing resource scheduling, solving the problem of inefficient collaborative office work in large-scale data processing, and achieving a more efficient collaborative office process.
Patent Information
- Application Number
- CN202410286048.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-13
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-03-13
AI Technical Summary
The existing corporate collaborative office methods will experience task load when processing large-scale data, resulting in inefficient collaborative office work.
Using an intelligent AI-based method, by acquiring and analyzing the functional systems and responsibilities in the enterprise office system, using a cooperative analysis model for visual processing and timing correlation analysis, combining data correlation to evaluate data synergy, and scheduling resource priorities to perform collaborative processing.
The efficiency of corporate collaborative office work has been improved, and by clarifying the correlation of functional system and data collaborativeness and optimizing resource utilization, the accuracy and efficiency of office tasks have been improved.
Smart Images

Figure CN118071104B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of collaborative office technology, and in particular to a method and system for realizing enterprise collaborative office based on intelligent AI. Background Art
[0002] Enterprise collaborative office refers to the way of achieving efficient collaboration and collaborative work between different departments within the enterprise by integrating and sharing information, resources and work processes. It can achieve information and resource sharing between enterprise structures based on corresponding processing tasks, thereby improving the office efficiency of the enterprise.
[0003] The existing method of enterprise collaborative office is mainly to build a shared cloud platform. By building a storage device, the enterprise data is stored in the storage device, the corresponding data is scheduled according to the specific office task requirements, and then the data processing resources are scheduled to achieve the purpose of collaborative office. However, this method is suitable for office systems with a small amount of data. If the enterprise data is huge, the method will have a task load phenomenon during use, which will lead to low efficiency of enterprise collaborative office. Summary of the invention
[0004] The present invention provides a method and system for realizing enterprise collaborative office based on intelligent AI, the main purpose of which is to improve the efficiency of enterprise collaborative office.
[0005] To achieve the above objectives, the present invention provides a method for realizing enterprise collaborative office based on intelligent AI, comprising:
[0006] Acquire the enterprise office system to be processed, identify the functional system in the enterprise office system, analyze the system responsibilities corresponding to the functional system, and analyze the system correlation between the functional systems according to the system responsibilities;
[0007] Collecting system data corresponding to the functional system, inputting the system data into a pre-trained cooperative analysis model, using a visualization network in the cooperative analysis model to visualize the system data to obtain visualization data, and analyzing the temporal correlation between the system data using a temporal neural network in the cooperative analysis model based on the visualization data;
[0008] Analyzing the data correlation between the system data by using the correlation analysis network in the cooperative analysis model, and evaluating the data synergy between the system data by combining the time series correlation and the data correlation;
[0009] receiving an office task corresponding to the enterprise office system, determining a task function system corresponding to the office task from the function system, scheduling system resources corresponding to the task function system, and calculating a resource priority corresponding to the system resources according to the office task;
[0010] According to the system relevance, the data coordination and the task function system, the task data corresponding to the office task is screened out from the system data, and the collaborative processing of the office task is performed in combination with the resource priority and the task data to obtain a processing result.
[0011] Optionally, analyzing the system relevance between the functional systems according to the system responsibilities includes:
[0012] Identify the responsibility description information in the system responsibility, and extract key responsibility information in the responsibility description information;
[0013] Performing semantic analysis on the key responsibility information to obtain responsibility information language;
[0014] Constructing semantic vectors corresponding to the semantics of the responsibility information, and calculating similarity indexes between the semantic vectors;
[0015] According to the similarity index, the system correlation between the functional systems is analyzed.
[0016] Optionally, the calculating the similarity index between the semantic vectors includes:
[0017] The similarity index between the semantic vectors is calculated by the following formula:
[0018]
[0019] Among them, A represents the similarity index between semantic vectors, B a represents the vector value corresponding to the ath vector in the semantic vector, a represents the sequence number of the semantic vector, B , represents the vector mean of the semantic vector, B a+1 Represents the vector value corresponding to the a+1th semantic vector.
[0020] Optionally, the visualizing the system data using the visualization network in the collaborative analysis model to obtain the visualization data includes:
[0021] Using the automatic encoder in the visualization network to perform data purification on the system data to obtain target system data;
[0022] Using the convolutional layer in the visualization network to extract features of the target system data, to obtain system data features;
[0023] Calculating the feature contribution corresponding to the system data feature using the feature selection function in the visualization network;
[0024] According to the feature contribution, feature selection is performed on the system data feature to obtain the target data feature;
[0025] Analyzing the feature type corresponding to the target data feature;
[0026] The system data is visualized according to the feature type and the target data feature to obtain visualized data.
[0027] Optionally, the calculating the feature contribution corresponding to the system data feature by using the feature selection function in the visualization network includes:
[0028] The feature selection function includes:
[0029]
[0030] Among them, E represents the feature contribution corresponding to the system data feature, F represents the number of features corresponding to the system data feature, b represents the sequence number of the system data feature, t represents the total number of system data features, and H b represents the eigenvalue of the bth feature in the system data feature, H ′ represents the characteristic mean of the system data characteristics, and ω represents the average regression coefficient corresponding to the system data characteristics.
[0031] Optionally, analyzing the data association between the system data using the association analysis network in the cooperative analysis model includes:
[0032] Using the normalization function in the association analysis network to normalize the system data to obtain standard system data;
[0033] Analyzing key data variables corresponding to the standard system data using the principal component analysis neural unit in the association analysis network;
[0034] Calculating the variable correlation between the key data variables using the correlation function in the correlation analysis network;
[0035] Calculating the data linear value corresponding to the system data using the linear function in the association analysis network;
[0036] Calculating the data covariance between the system data according to the data linearity value;
[0037] The data correlation between the system data is analyzed according to the variable correlation and the data covariance.
[0038] Optionally, the calculating the variable correlation between the key data variables using the correlation function in the correlation analysis network includes:
[0039] The correlation function includes:
[0040]
[0041] Among them, G represents the variable correlation between key data variables, K e Indicates the occurrence frequency of the e-th variable in the key data variable, K e+1 Indicates the occurrence frequency of the e+1th variable in the key data variable, K e,e+1 It represents the probability of the e-th variable and the e+1-th variable occurring simultaneously in the key data variables.
[0042] Optionally, calculating the resource priority corresponding to the system resource according to the office task includes:
[0043] querying resource status corresponding to the system resources, and identifying idle system resources among the system resources according to the resource status;
[0044] Scheduling resource logs corresponding to the idle system resources, and extracting log information from the resource logs;
[0045] Calculating the resource utilization rate corresponding to the idle system resources according to the log information;
[0046] Splitting the office task into subtasks;
[0047] Analyze the attributes corresponding to the office subtask and the idle system resource to obtain task attributes and resource attributes;
[0048] Calculating the attribute matching degree between the task attribute and the resource attribute;
[0049] According to the attribute matching degree, the resource priority corresponding to the system resource is determined.
[0050] Optionally, the calculating the attribute matching degree between the task attribute and the resource attribute includes:
[0051] The attribute matching degree between the task attribute and the resource attribute is calculated by the following formula:
[0052]
[0053] Where M represents the attribute matching degree between task attributes and resource attributes, R represents the total number of task attributes and resource attributes, f and f+1 represent the sequence numbers of module data and data to be interacted with, respectively, and Jf,f+1 represents the joint probability value corresponding to the fth attribute in the task attribute and the f+1th attribute in the resource attribute, P f Indicates the mapping value corresponding to the fth attribute in the task attribute, Q f+1 Indicates the mapping value corresponding to the f+1th attribute in the resource attributes.
[0054] A system for realizing enterprise collaborative office based on intelligent AI, characterized in that the system comprises:
[0055] A system correlation analysis module is used to obtain the enterprise office system to be processed, identify the functional system in the enterprise office system, analyze the system responsibilities corresponding to the functional system, and analyze the system correlation between the functional systems according to the system responsibilities;
[0056] A time series correlation analysis module is used to collect system data corresponding to the functional system, input the system data into a pre-trained cooperative analysis model, use the visualization network in the cooperative analysis model to visualize the system data to obtain visualization data, and analyze the time series correlation between the system data based on the visualization data using the time series neural network in the cooperative analysis model;
[0057] A synergy analysis module, used to analyze the data correlation between the system data by using the correlation analysis network in the cooperative analysis model, and to evaluate the data synergy between the system data by combining the time series correlation and the data correlation;
[0058] A resource priority calculation module is used to receive office tasks corresponding to the enterprise office system, determine the task function system corresponding to the office tasks from the function system, schedule system resources corresponding to the task function system, and calculate the resource priority corresponding to the system resources according to the office tasks;
[0059] The collaborative processing module is used to filter out the task data corresponding to the office task from the system data according to the system relevance, the data collaboration and the task function system, and perform collaborative processing of the office task in combination with the resource priority and the task data to obtain a processing result.
[0060] The present invention analyzes the system correlation between the functional systems according to the system responsibilities, and then can understand the correlation between the functional systems, so as to facilitate the scheduling of information and resources for subsequent collaborative office processing. The present invention visualizes the system data by using the visualization network in the cooperative analysis model, and can display the system data in the form of charts or graphs, so as to discover the data trends between the system data, and then facilitate the subsequent analysis of the time series correlation between the system data. The present invention analyzes the data correlation between the system data by using the correlation analysis network in the cooperative analysis model to understand the correlation between the system data. Thereby, the potential rules between the system data can be discovered, thereby improving the accuracy of subsequent data synergy evaluation. The present invention can obtain the computing resources required for the office task by scheduling the system resources corresponding to the task function system. According to the office task, the resource priority corresponding to the system resources is calculated, and the usage priority corresponding to each resource in the system resources can be understood, thereby improving the processing efficiency of the office task. The present invention filters out the task data corresponding to the office task from the system data according to the system relevance, the data synergy and the task function system, thereby improving the accuracy of collaborative data acquisition during office task processing, thereby improving the processing efficiency of the office task. Therefore, the method and system for realizing enterprise collaborative office based on intelligent AI provided in an embodiment of the present invention can improve the efficiency of enterprise collaborative office. BRIEF DESCRIPTION OF THE DRAWINGS
[0061] Figure 1 A flowchart of a method for realizing enterprise collaborative office based on intelligent AI provided by one embodiment of the present invention;
[0062] Figure 2 A functional module diagram of a system for implementing enterprise collaborative office based on intelligent AI provided in one embodiment of the present invention.
[0063] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0065] The embodiment of the present application provides a method for realizing enterprise collaborative office based on intelligent AI. In the embodiment of the present application, the execution subject of the method for realizing enterprise collaborative office based on intelligent AI includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for realizing enterprise collaborative office based on intelligent AI can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.
[0066] Reference Figure 1 FIG. 1 is a flow chart of a method for realizing enterprise collaborative office based on intelligent AI provided by an embodiment of the present invention. In this embodiment, the method for realizing enterprise collaborative office based on intelligent AI includes steps S1-S5.
[0067] S1. Acquire an enterprise office system to be processed, identify a functional system in the enterprise office system, analyze system responsibilities corresponding to the functional system, and analyze system relevance between the functional systems based on the system responsibilities.
[0068] The present invention analyzes the system correlation between the functional systems based on the system responsibilities, and further can understand the correlation between the functional systems, so as to facilitate the scheduling and processing of information and resources for subsequent collaborative office processing, wherein the enterprise office system is the organizational structure of the entire enterprise, the functional system is a subsystem in the enterprise office system, that is, the corresponding workflow in the organizational structure, the system responsibilities are the specific work responsibilities or corresponding services corresponding to the functional system, and the system correlation describes the correlation between the functional systems. Optionally, the functional system in the enterprise office system can be realized by viewing the organizational chart, and the analysis of the system responsibilities corresponding to the functional system can be achieved by analyzing the functional responsibility descriptions provided by the enterprise to understand the scope of responsibilities and work content of each position.
[0069] As an embodiment of the present invention, the system correlation between the functional systems is analyzed based on the system responsibilities, including: identifying responsibility description information in the system responsibilities, extracting key responsibility information in the responsibility description information, performing semantic analysis on the key responsibility information to obtain responsibility information semantics, constructing semantic vectors corresponding to the responsibility information semantics, calculating the similarity index between the semantic vectors, and analyzing the system correlation between the functional systems based on the similarity index.
[0070] Among them, the responsibility description information is a detailed and accurate description of the system responsibilities, the key responsibility information is the representative information in the responsibility description information, the responsibility information semantics is the meaning analysis corresponding to the key responsibility information, the semantic vector is the expression vector corresponding to the responsibility information semantics, and the similarity index represents the degree of similarity between the semantic vectors.
[0071] Optionally, identifying the responsibility description information in the system responsibilities can be achieved through OCR text recognition technology, extracting key responsibility information in the responsibility description information can be achieved through TextRank algorithm, semantic analysis of the key responsibility information can be achieved through semantic analysis method, constructing the semantic vector corresponding to the semantics of the responsibility information can be achieved through word2vec algorithm, and based on the similarity index, the similarity between the functional systems is analyzed to determine the system correlation between the functional systems.
[0072] Further, as an optional embodiment of the present invention, the calculating the similarity index between the semantic vectors includes:
[0073] The similarity index between the semantic vectors is calculated by the following formula:
[0074]
[0075] Among them, A represents the similarity index between semantic vectors, B a represents the vector value corresponding to the ath vector in the semantic vector, a represents the sequence number of the semantic vector, B , represents the vector mean of the semantic vector, B a+1 Represents the vector value corresponding to the a+1th semantic vector.
[0076] S2. Collect system data corresponding to the functional system, input the system data into a pre-trained collaborative analysis model, use the visualization network in the collaborative analysis model to visualize the system data to obtain visualization data, and analyze the temporal correlation between the system data based on the visualization data using the temporal neural network in the collaborative analysis model.
[0077] The present invention visualizes the system data by utilizing the visualization network in the collaborative analysis model, and can display the system data in the form of charts or graphs, thereby discovering the data trends between the system data, thereby facilitating the subsequent analysis of the temporal correlation between the system data, wherein the system data is the corresponding office-related data in the functional system, the collaborative analysis model is a model for analyzing the cooperative relationship between the system data, and the visualization data is the data obtained after the system data is visualized. Optionally, the collection of the system data corresponding to the functional system can be achieved through a data collection tool, and the data collection tool is compiled by a scripting language.
[0078] As an embodiment of the present invention, the method of using the visualization network in the collaborative analysis model to visualize the system data to obtain the visualized data includes: using the autoencoder in the visualization network to perform data purification on the system data to obtain target system data, using the convolutional layer in the visualization network to perform feature extraction on the target system data to obtain system data features, using the feature selection function in the visualization network to calculate the feature contribution corresponding to the system data features, performing feature selection on the system data features based on the feature contribution to obtain target data features, analyzing the feature type corresponding to the target data features, and visualizing the system data based on the feature type and the target data features to obtain visualized data.
[0079] Among them, the automatic encoder maps the system data from the original high-dimensional space to the low-dimensional space, and then reconstructs it from the low-dimensional space back to the original space, so as to achieve the purpose of data dimensionality reduction, cleaning and denoising. The convolution layer is a neural network for feature extraction of the target system data, which is composed of multiple convolution kernels. The system data feature is the data representation in the target system data. The feature selection function is a function for selecting representative features from the system data features. The feature contribution degree indicates the degree of influence of each feature in the system data features on the whole. The feature type is the type corresponding to the system data feature, such as numerical features or text features.
[0080] Optionally, the system data can be purified by the encoder and decoder in the automatic encoder, and the target system data can be feature extracted by the convolution kernel in the convolution layer. Feature selection of the system data features can be achieved by a screening function, and the screening function is compiled in JAVA language. The feature type can be determined by the expression form corresponding to the target data feature, and the visualization method corresponding to the target data feature is determined according to the feature type. The target data feature is visualized using the visualization method to obtain a visualization result, which is used as the visualization data of the system data.
[0081] Optionally, as an optional embodiment of the present invention, the calculating the feature contribution corresponding to the system data feature by using the feature selection function in the visualization network includes:
[0082] The feature selection function includes:
[0083]
[0084] Among them, E represents the feature contribution corresponding to the system data feature, F represents the number of features corresponding to the system data feature, b represents the sequence number of the system data feature, t represents the total number of system data features, and H b represents the eigenvalue of the bth feature in the system data feature, H ′ represents the characteristic mean of the system data characteristics, and ω represents the average regression coefficient corresponding to the system data characteristics.
[0085] The present invention analyzes the temporal correlation between the system data based on the visualization data and the time series neural network in the cooperative analysis model, so as to understand the correlation between the system data at different time points, thereby providing a basis for the subsequent evaluation of data synergy, wherein the time series correlation is the corresponding correlation between the system data at different time points. Optionally, the time series in the visualization data, that is, the corresponding time point, is identified, and the data value corresponding to each data in the visualization data in the time series is recorded. According to the data value, the change rate of each data in the visualization data in the adjacent time series is calculated, and the change correlation between each data in the visualization data is analyzed according to the change rate, such as positive correlation, negative correlation or no correlation, so as to determine the temporal correlation between each data.
[0086] S3. Analyze the data correlation between the system data using the correlation analysis network in the cooperative analysis model, and evaluate the data synergy between the system data by combining the time series correlation and the data correlation.
[0087] The present invention analyzes the data correlation between the system data by utilizing the association analysis network in the collaborative analysis model to understand the correlation between the system data, thereby discovering the potential rules between the system data and improving the accuracy of subsequent data collaboration evaluation, wherein the association analysis network is a neural network used to analyze the correlation relationship between the system data, and the data correlation is the correlation relationship between the system data.
[0088] As an embodiment of the present invention, the use of the association analysis network in the cooperative analysis model to analyze the data correlation between the system data includes: using the normalization function in the association analysis network to normalize the system data to obtain standard system data, using the principal component analysis neural unit in the association analysis network to analyze the key data variables corresponding to the standard system data, using the association function in the association analysis network to calculate the variable correlation between the key data variables, using the linear function in the association analysis network to calculate the data linear value corresponding to the system data, calculating the data covariance between the system data based on the data linear value, and analyzing the data correlation between the system data based on the variable correlation and the data covariance.
[0089] Among them, the normalization function is used to eliminate the dimensional differences between different data in the system data, so as to make the system data comparable, such as the Softmax normalization function, the principal component analysis neural unit is a neural unit used to analyze the data components of the standard system data, the principal component analysis neural unit is composed of the linalg.eig function, the key data variables are important components in the standard system data, the correlation function is a function used to calculate the correlation between the key data variables, the variable correlation represents the degree of correlation between the key data variables, the data linear value is the numerical expression corresponding to the system data, the data covariance represents the degree of correlation between the system data, and the linear function includes a first-order linear function.
[0090] Optionally, as an optional embodiment of the present invention, the calculating the variable correlation between the key data variables using the association function in the association analysis network includes:
[0091] The correlation function includes:
[0092]
[0093] Among them, G represents the variable correlation between key data variables, K e Indicates the occurrence frequency of the e-th variable in the key data variable, K e+1Indicates the occurrence frequency of the e+1th variable in the key data variable, K e,e+1 It represents the probability of the e-th variable and the e+1-th variable occurring simultaneously in the key data variables.
[0094] Furthermore, we can count the variable frequency corresponding to the e-th variable and divide the variable frequency by the total number of variables to get the frequency of occurrence corresponding to the e-th variable. Similarly, we can count the frequency of simultaneous occurrence of the e-th variable and the e+1-th variable and divide the frequency by the total number of variables to get the probability of simultaneous occurrence of the e-th variable and the e+1-th variable.
[0095] The present invention evaluates the data synergy between the system data by combining the time series correlation and the data correlation, and then can understand the data dependence degree between the system data, and then determine the synergy between the system data, so as to facilitate the subsequent collaborative office data scheduling and processing, wherein the data synergy represents the data causal relationship and dependency between the system data, and optionally, determines the corresponding degree of the time series correlation and the data correlation, and evaluates the data synergy between the system data according to the degree, for example, if the time series correlation is positively correlated and the data correlation is high, it means that the data synergy is high.
[0096] S4. Receive office tasks corresponding to the enterprise office system, determine the task function system corresponding to the office tasks from the function system, schedule system resources corresponding to the task function system, and calculate resource priorities corresponding to the system resources according to the office tasks.
[0097] The present invention can obtain the computing resources required for the office task by scheduling the system resources corresponding to the task function system, and calculate the resource priority corresponding to the system resources according to the office task, so as to understand the usage priority corresponding to each resource in the system resources, thereby improving the processing efficiency of the office task, wherein the office task is the work that needs to be processed by the enterprise office system, the task function system is the relevant system in the function system that needs to process the office task, and the system resources are the computing resources corresponding to the task function system. Optionally, the function system involved in the office task is queried to determine the task function system corresponding to the office task from the function system.
[0098] As an embodiment of the present invention, the resource priority corresponding to the system resource is calculated according to the office task, including: querying the resource status corresponding to the system resource, identifying the idle system resources in the system resources according to the resource status, scheduling the resource log corresponding to the idle system resource, extracting the log information in the resource log, calculating the resource utilization corresponding to the idle system resource according to the log information, splitting the office task to obtain office sub-tasks, and analyzing the attributes corresponding to the office sub-tasks and the idle system resources to obtain task attributes and resource attributes, calculating the attribute matching degree between the task attributes and the resource attributes, and determining the resource priority corresponding to the system resource according to the attribute matching degree.
[0099] Among them, the resource status is the current usage status corresponding to the system resources, the idle system resources are the resources in the system resources that are not used or can execute tasks, the resource log is a log file of information such as the usage, operation records and performance indicators of the idle system resources, the log information is the detailed record information in the resource log, the resource utilization rate indicates the usage degree of the idle system resources, the office subtask is a subordinate task in the office task, the task attributes and the resource attributes are the properties corresponding to the office subtask and the idle system resources respectively, and the attribute matching degree indicates the matching degree between the task attributes and the resource attributes.
[0100] Optionally, the resource status corresponding to the system resources can be queried through professional monitoring tools or dashboards, such as Nagios, Zabbix, Prometheus, etc., and the resource logs corresponding to the idle system resources can be scheduled through a scheduling tool compiled by a scripting language. The log information in the resource log can be extracted through an extraction function compiled by a programming language. The resource usage information and resource allocation information of the idle system resources are determined according to the log information, and the remaining computing power of the idle system resources is calculated according to the resource usage information and the resource allocation information. The computing power ratio of the remaining computing power to the total computing power is calculated, and the resource utilization rate of the idle system resources is obtained according to the computing power ratio. The attributes corresponding to the office subtasks and the idle system resources can be analyzed by a hierarchical clustering method, and the sum of the attribute matching degrees of the office subtasks is calculated to obtain the total matching degree of the office tasks and the idle system resources. The resource priority corresponding to the system resources is set according to the numerical value of the total matching degree.
[0101] Optionally, as an optional embodiment of the present invention, the calculating the attribute matching degree between the task attribute and the resource attribute includes:
[0102] The attribute matching degree between the task attribute and the resource attribute is calculated by the following formula:
[0103]
[0104] Where M represents the attribute matching degree between task attributes and resource attributes, R represents the total number of task attributes and resource attributes, f and f+1 represent the sequence numbers of module data and data to be interacted with, respectively, and J f,f+1 represents the joint probability value corresponding to the fth attribute in the task attribute and the f+1th attribute in the resource attribute, P f Indicates the mapping value corresponding to the fth attribute in the task attribute, Q f+1 Indicates the mapping value corresponding to the f+1th attribute in the resource attributes.
[0105] S5. According to the system relevance, the data coordination and the task function system, the task data corresponding to the office task is filtered out from the system data, and the collaborative processing of the office task is performed in combination with the resource priority and the task data to obtain a processing result.
[0106] The present invention filters out the task data corresponding to the office task from the system data according to the system relevance, the data synergy and the task function system, which can improve the accuracy of collaborative data acquisition during office task processing, thereby improving the processing efficiency of the office task. Optionally, according to the system relevance, the data synergy and the task function system, filtering conditions for the system data are set, and according to the filtering conditions, the task data corresponding to the office task is filtered out using the above-mentioned filtering function, the office task is calculated and processed through the resource priority, and the task data is interactively and shared to achieve collaborative processing of the office task.
[0107] The present invention analyzes the system correlation between the functional systems according to the system responsibilities, and then can understand the correlation between the functional systems, so as to facilitate the scheduling of information and resources for subsequent collaborative office processing. The present invention visualizes the system data by using the visualization network in the cooperative analysis model, and can display the system data in the form of charts or graphs, so as to discover the data trends between the system data, and then facilitate the subsequent analysis of the time series correlation between the system data. The present invention analyzes the data correlation between the system data by using the correlation analysis network in the cooperative analysis model to understand the correlation between the system data. Thereby, the potential rules between the system data can be discovered, thereby improving the accuracy of subsequent data synergy evaluation. The present invention can obtain the computing resources required for the office task by scheduling the system resources corresponding to the task function system. According to the office task, the resource priority corresponding to the system resources is calculated, and the usage priority corresponding to each resource in the system resources can be understood, thereby improving the processing efficiency of the office task. The present invention filters out the task data corresponding to the office task from the system data according to the system relevance, the data synergy and the task function system, thereby improving the accuracy of collaborative data acquisition during office task processing, thereby improving the processing efficiency of the office task. Therefore, a method for realizing enterprise collaborative office based on intelligent AI provided in an embodiment of the present invention can improve the efficiency of enterprise collaborative office.
[0108] like Figure 2 The figure shows a functional module diagram of a system for realizing enterprise collaborative office based on intelligent AI provided by one embodiment of the present invention.
[0109] The system 100 for realizing enterprise collaborative office based on intelligent AI described in the present invention can be installed in an electronic device. According to the functions implemented, the system 100 for realizing enterprise collaborative office based on intelligent AI can include a system correlation analysis module 101, a timing correlation analysis module 102, a synergy analysis module 103, a resource priority calculation module 104 and a collaborative processing module 105. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0110] In this embodiment, the functions of each module / unit are as follows:
[0111] The system correlation analysis module 101 is used to obtain the enterprise office system to be processed, identify the functional system in the enterprise office system, analyze the system responsibilities corresponding to the functional system, and analyze the system correlation between the functional systems according to the system responsibilities;
[0112] The temporal correlation analysis module 102 is used to collect system data corresponding to the functional system, input the system data into a pre-trained cooperative analysis model, use the visualization network in the cooperative analysis model to visualize the system data to obtain visualization data, and analyze the temporal correlation between the system data based on the visualization data using the temporal neural network in the cooperative analysis model;
[0113] The synergy analysis module 103 is used to analyze the data correlation between the system data by using the correlation analysis network in the cooperative analysis model, and evaluate the data synergy between the system data by combining the time series correlation and the data correlation;
[0114] The resource priority calculation module 104 is used to receive the office task corresponding to the enterprise office system, determine the task function system corresponding to the office task from the function system, schedule the system resources corresponding to the task function system, and calculate the resource priority corresponding to the system resources according to the office task;
[0115] The collaborative processing module 105 is used to filter out the task data corresponding to the office task from the system data according to the system relevance, the data collaboration and the task function system, and perform collaborative processing of the office task in combination with the resource priority and the task data to obtain a processing result.
[0116] In detail, each module described in the system 100 for realizing enterprise collaborative office based on intelligent AI described in the embodiment of the present application is used in the same manner as described above. Figure 1 The technical means described in the method of realizing enterprise collaborative office based on intelligent AI are the same as those described in the method and can produce the same technical effects, so I will not go into details here.
[0117] In the several embodiments provided by the present invention, it should be understood that the provided methods and systems can be implemented in other ways. For example, the method embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for realizing enterprise collaborative office based on intelligent AI, characterized in that: The method comprises: Acquire the enterprise office system to be processed, identify the functional system in the enterprise office system, analyze the system responsibilities corresponding to the functional system, and analyze the system correlation between the functional systems according to the system responsibilities; Collecting system data corresponding to the functional system, inputting the system data into a pre-trained cooperative analysis model, using a visualization network in the cooperative analysis model to visualize the system data to obtain visualization data, and analyzing the temporal correlation between the system data using a temporal neural network in the cooperative analysis model based on the visualization data; Analyzing the data correlation between the system data by using the correlation analysis network in the cooperative analysis model, and evaluating the data synergy between the system data by combining the time series correlation and the data correlation; receiving an office task corresponding to the enterprise office system, determining a task function system corresponding to the office task from the function system, scheduling system resources corresponding to the task function system, and calculating a resource priority corresponding to the system resources according to the office task; According to the system relevance, the data coordination and the task function system, the task data corresponding to the office task is screened out from the system data, and the collaborative processing of the office task is performed in combination with the resource priority and the task data to obtain a processing result.
2. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 1, characterized in that: According to the system responsibilities, the system relevance between the functional systems is analyzed, including: Identify the responsibility description information in the system responsibility, and extract key responsibility information in the responsibility description information; Performing semantic analysis on the key responsibility information to obtain responsibility information language; Constructing semantic vectors corresponding to the responsibility information language, and calculating similarity indexes between the semantic vectors; According to the similarity index, the system correlation between the functional systems is analyzed.
3. A method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 2, characterized in that: The calculating the similarity index between the semantic vectors includes: The similarity index between the semantic vectors is calculated by the following formula: Among them, A represents the similarity index between semantic vectors, B a represents the vector value corresponding to the ath vector in the semantic vector, a represents the sequence number of the semantic vector, B , represents the vector mean of the semantic vector, B a+1 Represents the vector value corresponding to the a+1th semantic vector.
4. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 1, characterized in that: The step of visualizing the system data using the visualization network in the cooperative analysis model to obtain the visualization data includes: Using the automatic encoder in the visualization network to perform data purification on the system data to obtain target system data; Using the convolutional layer in the visualization network to extract features of the target system data, to obtain system data features; Calculating the feature contribution corresponding to the system data feature using the feature selection function in the visualization network; According to the feature contribution, feature selection is performed on the system data feature to obtain the target data feature; Analyzing the feature type corresponding to the target data feature; The system data is visualized according to the feature type and the target data feature to obtain visualized data.
5. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 4, characterized in that: The step of calculating the feature contribution corresponding to the system data feature by using the feature selection function in the visualization network includes: The feature selection function includes: Among them, E represents the feature contribution corresponding to the system data feature, F represents the number of features corresponding to the system data feature, b represents the sequence number of the system data feature, t represents the total number of system data features, and H b represents the eigenvalue of the bth feature in the system data features, H' represents the characteristic mean of the system data features, and ω represents the average regression coefficient corresponding to the system data features.
6. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 1, characterized in that: The analyzing the data association between the system data by using the association analysis network in the cooperative analysis model includes: Using the normalization function in the association analysis network to normalize the system data to obtain standard system data; Analyzing key data variables corresponding to the standard system data using the principal component analysis neural unit in the association analysis network; Calculating the variable correlation between the key data variables using the correlation function in the correlation analysis network; Calculating the data linear value corresponding to the system data using the linear function in the association analysis network; Calculating the data covariance between the system data according to the data linearity value; The data correlation between the system data is analyzed according to the variable correlation and the data covariance.
7. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 6, characterized in that: The step of calculating the variable correlation between the key data variables using the correlation function in the correlation analysis network includes: The correlation function includes: Among them, G represents the variable correlation between key data variables, K e Indicates the occurrence frequency of the e-th variable in the key data variable, K e+1 Indicates the occurrence frequency of the e+1th variable in the key data variable, K e,e+1 It represents the probability of the e-th variable and the e+1-th variable occurring simultaneously in the key data variables.
8. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 1, characterized in that: The calculating, according to the office task, the resource priority corresponding to the system resource comprises: querying resource status corresponding to the system resources, and identifying idle system resources among the system resources according to the resource status; Scheduling resource logs corresponding to the idle system resources, and extracting log information from the resource logs; Calculating the resource utilization rate corresponding to the idle system resources according to the log information; Splitting the office task into subtasks; Analyze the attributes corresponding to the office subtask and the idle system resource to obtain task attributes and resource attributes; Calculating the attribute matching degree between the task attribute and the resource attribute; According to the attribute matching degree, the resource priority corresponding to the system resource is determined.
9. The method for realizing enterprise collaborative office based on intelligent AI as claimed in claim 8, characterized in that: The calculating the attribute matching degree between the task attribute and the resource attribute includes: The attribute matching degree between the task attribute and the resource attribute is calculated by the following formula: Where M represents the attribute matching degree between task attributes and resource attributes, R represents the total number of task attributes and resource attributes, f and f+1 represent the sequence numbers of module data and data to be interacted with, respectively, and J f,f+1 represents the joint probability value corresponding to the fth attribute in the task attribute and the f+1th attribute in the resource attribute, P f Indicates the mapping value corresponding to the fth attribute in the task attribute, Q f+1 Indicates the mapping value corresponding to the f+1th attribute in the resource attributes.
10. A system for realizing enterprise collaborative office based on intelligent AI, characterized in that: The system comprises: A system correlation analysis module is used to obtain the enterprise office system to be processed, identify the functional system in the enterprise office system, analyze the system responsibilities corresponding to the functional system, and analyze the system correlation between the functional systems according to the system responsibilities; A time series correlation analysis module is used to collect system data corresponding to the functional system, input the system data into a pre-trained cooperative analysis model, use the visualization network in the cooperative analysis model to visualize the system data to obtain visualization data, and analyze the time series correlation between the system data based on the visualization data using the time series neural network in the cooperative analysis model; A synergy analysis module, used to analyze the data correlation between the system data by using the correlation analysis network in the cooperative analysis model, and to evaluate the data synergy between the system data by combining the time series correlation and the data correlation; A resource priority calculation module is used to receive office tasks corresponding to the enterprise office system, determine the task function system corresponding to the office tasks from the function system, schedule system resources corresponding to the task function system, and calculate the resource priority corresponding to the system resources according to the office tasks; The collaborative processing module is used to filter out the task data corresponding to the office task from the system data according to the system relevance, the data collaboration and the task function system, and perform collaborative processing of the office task in combination with the resource priority and the task data to obtain a processing result.
Citation Information
Patent Citations
Blockchain based coordinated officing method and system and computer readable storage medium
CN108388988A
Block chain cloud collaborative enterprise data system
CN113158256A
Modeled enterprise management method and system based on block chain
CN113191743A
Visual management method and system for automatically generating protocol template, and electronic equipment
CN116151774A
Office data management method and system based on edge computing
CN117611096A
