An enterprise management system and method based on cloud platform

Abstract

The present invention discloses a cloud-based enterprise management system and method, which specifically relates to the field of enterprise data processing technology. Based on the connection topology and logic of enterprise equipment, a digital twin model is constructed on the cloud platform; users access the digital twin model through an interface, remotely control the equipment and issue operation instructions; based on the digital twin model, instructions are verified, the instruction security risk index is evaluated, and executable instructions are screened to avoid economic losses and abnormal operations; if the operation instructions do not comply, early warning information is generated, thereby improving enterprise management efficiency and security, and solving the problem of abnormal remote control of enterprises and economic losses in the existing technology; the response time of the equipment in executing the operation instructions, the number of times the equipment successfully executes the instructions, and the error code are analyzed to obtain the equipment operation quality index, and abnormal equipment is screened out based on the relationship between the equipment operation quality index and the corresponding threshold, thereby realizing intelligent management of enterprise equipment.

Description

Technical Field

[0001] The present invention relates to the field of enterprise data processing technology, and more specifically, to a cloud platform-based enterprise management system and method. Background Art

[0002] Data is the lifeblood of any enterprise. As data continues to grow, more and more companies are choosing to store their core data in cloud platforms and implement intelligent enterprise management through remote device control. Existing enterprise management systems have indeed improved operational efficiency and management capabilities to a certain extent. Remote device control further promotes intelligent enterprise management, enabling real-time monitoring of equipment status, prompt identification and resolution of potential issues, and ensuring smooth production processes.

[0003] However, in actual use, it still has many shortcomings. For example, the enterprise remote control in the existing technology is not smart enough and cannot effectively judge the operation instructions, resulting in economic losses. The implementation of abnormal operation instructions will increase the risk of the enterprise; there is insufficient big data analysis in the enterprise management process, which cannot provide decision-making support for enterprise management. For example, when equipment fails or requires maintenance, if the remote control system cannot respond in a timely and accurate manner, it may cause the production line to stagnate or the equipment to be damaged. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an enterprise management system and method based on a cloud platform to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solutions: a cloud-based enterprise management system, comprising:

[0006] The data acquisition module obtains the connection topology and logical connection relationship of enterprise equipment, collects the time series data of enterprise equipment, and transmits the collected data to the cloud platform;

[0007] The digital twin model building module builds digital twin models corresponding to enterprise devices based on the device connection topology and logical connection relationships of enterprise devices, and deploys the built digital twin models on the cloud platform;

[0008] In the enterprise device management module, users access the digital twin model through an interface and remotely control enterprise devices based on the digital twin model in the cloud platform. The user issues operation instructions, which are verified based on the digital twin model, and executable operation instructions are screened out, and the enterprise device executes the operation instructions.

[0009] The process of screening executable operation instructions includes:

[0010] Convert the operation instruction into a single operation instruction set, and obtain the logical connection relationship of the single operation instruction set;

[0011] Establish a mapping between a single operation instruction and a device state feature vector, and predict a device state feature vector group after executing a single operation instruction set;

[0012] Based on the logical connection relationship of a single operation instruction set, the device state feature vector group is processed, and vector superposition of the device state feature vector group is completed to obtain the device superposition state feature vector group corresponding to the operation instruction;

[0013] Analyze the device superposition state feature vector group and device safety constraints, match the offset rate weight coefficient for each feature vector, and calculate the instruction safety risk index Sof;

[0014] Based on the instruction security risk index, executable operation instructions are screened from the operation instructions and transmitted to the device end. If the operation instructions do not meet the requirements, an early warning message is generated.

[0015] Preferably, the instruction security risk index is obtained in the following manner:

[0016] Analyze the device superposition state feature vector group and the device safety constraints, match the offset rate weight coefficient for each device state feature vector, and the offset rate weight coefficient of the i-th feature vector is recorded as qs i ,

[0017] The number of device superposition state feature vector groups is recorded as n, i is used to represent the sequence number of the feature vectors, and the predicted value of the i-th feature vector is St i ; Set the constraint value of the i-th eigenvector to Yt i ;

[0018] By formula The instruction security risk index Sof is calculated.

[0019] Preferably, the enterprise equipment management module includes an equipment quality management unit, which is used to screen out abnormal equipment. After the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns information about the execution status; if the equipment executes unsuccessfully, it returns an error code; analyze the response time of the equipment to execute the operation instruction, the number of times the equipment successfully executes the instruction, and the error code to obtain the equipment operation quality index, and screen out abnormal equipment based on the relationship between the equipment operation quality index and the corresponding threshold; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment is operating abnormally, and the faulty equipment is screened out to form a faulty equipment set, and a maintenance instruction is generated for the faulty equipment set.

[0020] Preferably, the device operation quality index is obtained in the following manner:

[0021] Analyze the execution data of device operation instructions to obtain response time, number of times the device successfully executes instructions, and error codes;

[0022] The number of operation instructions that the device can execute is recorded as m, and the sequence number of the operation instructions is represented by j. Based on the importance of each operation instruction to the operation quality of the device, a weight coefficient is set for each operation instruction;

[0023] Get the response time of the jth operation instruction, analyze and get the successful execution ratio of the jth operation instruction, recorded as the success rate s j ; Get the error code encountered when executing the j-th operation instruction, and set the weight E corresponding to each error code j ;

[0024] Through Z-score normalization, we obtain the normalized value σ_T of the device's response time when executing the jth operation instruction and the normalized value σ_E of the weight of the error code of the jth operation instruction. The normalized weight value is used to convert the weights of different error codes to the same scale for comparison or further analysis.

[0025] By formula The equipment operation quality index Sq is calculated; where w j The weight coefficient of the j-th operation instruction is represented by F1 and F2, which are adjustment coefficients used to balance the impact of response time and error code on the device operation quality index. 0<F1<1, 0<F2<1, and F1+F2=1.0.

[0026] Preferably, the enterprise management system includes:

[0027] The cloud platform management module is used to manage cloud platform data and ensure the security of cloud platform data. It includes an identity authentication login unit and an interface management unit. The identity authentication login unit is used to verify the user's identity. After the verification is passed, the user logs into the cloud platform; the interface management unit is used to filter abnormal interfaces based on the access security reliability index to obtain a set of secure interfaces.

[0028] Preferably, the operation process of the cloud platform management module includes the following steps:

[0029] Receiving access application: The cloud platform receives the user's access application, which includes a digital twin model access application and a time series data access application;

[0030] Verify the user's role information through smart contracts to confirm whether the user has the role permissions required for the requested access;

[0031] If the role permission verification is passed, the user's access security reliability index is calculated based on the user's role and historical user behavior data and stored in the database;

[0032] comparing the calculated access security reliability index with a preset critical access security reliability index;

[0033] If the access security reliability index reaches or exceeds the critical value, the cloud platform allows the user to access and continuously evaluates the user's trustworthy behavior during the access process;

[0034] If the access security reliability index is lower than the critical value, the cloud platform will automatically reject the user's access request.

[0035] Preferably, the access security reliability index is obtained in the following manner:

[0036] Divide access data by time zone and obtain user access behavior data for each time zone;

[0037] Analyze the user's access behavior in the previous time zone to obtain the illegal connection frequency p1, the attempt to exceed the authority frequency p2 and the user infection frequency p3. Through the formula cp = e p1*w1+p2*w2+p3*w3 The behavior penalty parameter cp is calculated, where w1, w2, and w3 represent the proportional coefficients of each item, based on user settings;

[0038] Obtain the user's basic access security reliability index from the database, denoted as Fa;

[0039] By formula Calculate the user's current access security reliability index Fnx, where Ft represents the attenuation function, satisfying the formula Where α is the decay rate adjustment factor; t n -t n-1 It represents the time interval between the user access request time point and the previous time zone, and hf represents the number of access operations in the previous time zone.

[0040] Preferably, the enterprise management system further includes:

[0041] The cloud platform risk management module divides enterprise data by time zones, obtains the average value of the access security reliability index, the average value of the instruction security risk index, and the average value of the equipment operation quality index in each time zone, and conducts joint analysis to obtain the cloud platform management coefficient. When the cloud platform management coefficient is lower than the corresponding threshold, it indicates that the cloud platform management quality is abnormal, and an early warning is issued to the user, prompting the enterprise to maintain equipment quality and increase data security maintenance.

[0042] To achieve the above objectives, the present invention provides the following technical solution: a cloud platform-based enterprise management method, comprising the following steps:

[0043] Step 1: Based on the device connection topology and logical connection relationships of enterprise devices, build a digital twin model corresponding to the enterprise devices and deploy the built digital twin model on the cloud platform;

[0044] Step 2: Collect time series data from enterprise equipment and transmit the collected data to the cloud platform;

[0045] Step 3: The user accesses the digital twin model through the interface and remotely controls the enterprise equipment based on the digital twin model in the cloud platform. The user issues an operation instruction, which is verified based on the digital twin model. Executable operation instructions are screened out, and the enterprise equipment executes the operation instructions. The process of screening executable operation instructions includes:

[0046] Step S301: convert the operation instruction into a single operation instruction set, and obtain the logical connection relationship of the single operation instruction set;

[0047] Step S302: Establish a mapping between a single operation instruction and a device state feature vector, and predict a device state feature vector group after executing a single operation instruction set;

[0048] Step S303: Based on the logical connection relationship of the single operation instruction set, the device state feature vector group is processed to complete vector superposition of the device state feature vector group to obtain the device superposition state feature vector group corresponding to the operation instruction;

[0049] Step S304: Analyze the device superposition state feature vector group and the device safety constraint conditions, match the offset rate weight coefficient for each feature vector, and calculate the instruction safety risk index Sof;

[0050] Step S305: Filter executable operation instructions from the operation instructions based on the instruction security risk index and transmit them to the device end. If the operation instructions do not meet the requirements, generate warning information.

[0051] Preferably, after the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns information on the execution status; if the equipment executes unsuccessfully, it returns an error code; analyze the response time of the equipment to execute the operation instruction, the number of times the equipment successfully executes the instruction, and the error code to obtain the equipment operation quality index, and screen out abnormal equipment based on the relationship between the equipment operation quality index and the corresponding threshold; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment is operating abnormally, and the faulty equipment is screened out to form a faulty equipment set, and a maintenance instruction is generated for the faulty equipment set.

[0052] Technical effects and advantages of the present invention:

[0053] (1) The cloud-based enterprise management system provided by the present invention builds a digital twin model corresponding to the enterprise equipment based on the device connection topology and logical connection relationship of the enterprise equipment, and deploys the built digital twin model in the cloud platform; users access the digital twin model through the interface, remotely control the equipment and issue operation instructions; verify the instructions based on the digital twin model, evaluate the instruction security risk index, and screen executable instructions to avoid economic losses and abnormal operations; if the operation instruction does not comply, generate early warning information, thereby improving the efficiency and security of enterprise management and solving the problem of abnormal remote control of enterprises in the existing technology, which causes economic losses.

[0054] (2) The cloud-based enterprise management system provided by the present invention can screen out abnormal equipment through the equipment quality management unit. After the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns the information execution status; if the equipment executes unsuccessfully, it returns an error code; the response time of the equipment executing the operation instruction, the number of times the equipment successfully executes the instruction, and the error code are analyzed to obtain the equipment operation quality index, and the abnormal equipment is screened out based on the relationship between the equipment operation quality index and the corresponding threshold; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment is operating abnormally, and the faulty equipment is screened out to form a faulty equipment set, and a maintenance instruction for the faulty equipment set is generated, thereby realizing intelligent management of the enterprise equipment and effectively avoiding the problem of insufficient data analysis and failure to provide decision support for enterprise management. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a flow chart of the cloud platform-based enterprise management system of the present invention.

[0056] Figure 2 This is a structural block diagram of the enterprise management system based on cloud platform risk management of the present invention. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0058] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0059] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0060] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0061] Example 1, see Figure 1 The present invention provides a flow chart of an enterprise management system based on a cloud platform. Figure 1 The cloud-based enterprise management system shown includes:

[0062] The data acquisition module obtains the connection topology and logical connection relationship of enterprise equipment, collects the time series data of enterprise equipment, and transmits the collected data to the cloud platform;

[0063] The digital twin model building module builds digital twin models corresponding to enterprise devices based on the device connection topology and logical connection relationships of enterprise devices, and deploys the built digital twin models on the cloud platform;

[0064] In the enterprise device management module, users access the digital twin model through an interface and remotely control enterprise devices based on the digital twin model in the cloud platform. The user issues operation instructions, which are verified based on the digital twin model, and executable operation instructions are screened out, and the enterprise device executes the operation instructions.

[0065] It should be further explained in the embodiment of the present invention that the process of screening out executable operation instructions includes:

[0066] Convert the operation instruction into a single operation instruction set, and obtain the logical connection relationship of the single operation instruction set;

[0067] Establish a mapping between a single operation instruction and a device state feature vector, and predict a device state feature vector group after executing a single operation instruction set;

[0068] Based on the logical connection relationship of a single set of operation instructions, the device state feature vector group is processed to complete vector superposition of the device state feature vector group to obtain a device superposition state feature vector group corresponding to the operation instruction; the device state feature vector group includes at least: device temperature, wear, load, efficiency rate, and output;

[0069] Analyze the device superposition state feature vector group and the device safety constraints, match the offset rate weight coefficient for each device state feature vector, and the offset rate weight coefficient of the i-th feature vector is recorded as qs i ,The offset rate weight coefficient refers to the degree of the deviation of the device state ,feature vector from the device safety constraint condition on the device quality and is ,based on user settings;

[0070] The number of device superposition state feature vector groups is recorded as n, i is used to represent the sequence number of the feature vectors, and the predicted value of the i-th feature vector is St i ; Set the constraint value of the i-th eigenvector to Yt i ;

[0071] By formula Calculate the instruction security risk index Sof;

[0072] Based on the instruction security risk index, executable operation instructions are screened from the operation instructions and transmitted to the device end. If the operation instructions do not meet the requirements, an early warning message is generated.

[0073] What needs to be further explained in the embodiments of the present invention is that the enterprise equipment management module includes an equipment quality management unit, which is used to screen out abnormal equipment. After the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns information execution status; if the equipment executes unsuccessfully, it returns an error code; analyze the response time of the equipment to execute the operation instruction, the number of times the equipment successfully executes the instruction, and the error code to obtain the equipment operation quality index, and screen out abnormal equipment based on the relationship between the equipment operation quality index and the corresponding threshold; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment operation is abnormal, and the faulty equipment is screened out to form a faulty equipment set, and a maintenance instruction is generated for the faulty equipment set; the error code is a code generated by the equipment when encountering an abnormal situation during the execution of the instruction. The error code is used to identify a specific error type, thereby facilitating subsequent fault diagnosis and repair; when the instruction is executed, the equipment will monitor the execution status and generate a corresponding error code when encountering an abnormal situation, and the error code will be recorded in the log.

[0074] It needs to be further explained in the embodiment of the present invention that the device operation quality index is obtained in the following manner:

[0075] Analyze the execution data of device operation instructions to obtain response time, number of times the device successfully executes instructions, and error codes;

[0076] The number of operation instructions that the device can execute is recorded as m, and the sequence number of the operation instructions is represented by j. Based on the importance of each operation instruction to the operation quality of the device, a weight coefficient is set for each operation instruction;

[0077] Get the response time of the jth operation instruction, analyze and get the successful execution ratio of the jth operation instruction, recorded as the success rate s j ; Get the error code encountered when executing the j-th operation instruction, and set the weight E corresponding to each error code j ;

[0078] Through Z-score normalization, we obtain the normalized value σ_T of the device's response time when executing the jth operation instruction and the normalized value σ_E of the weight of the error code of the jth operation instruction. The normalized weight value is used to convert the weights of different error codes to the same scale for comparison or further analysis.

[0079] By formula The equipment operation quality index Sq is calculated; where w j The weight coefficient of the j-th operation instruction is represented by F1 and F2, which are adjustment coefficients used to balance the impact of response time and error code on the device operation quality index. 0<F1<1, 0<F2<1, and F1+F2=1.0.

[0080] Explanation: The process of building a digital twin model corresponding to an enterprise device includes the following steps:

[0081] Step S01, data collection and preprocessing: Obtain the connection topology and logical connection relationships of enterprise equipment; Collect real-time data of enterprise equipment: Through sensors, programmable logic controllers, and API interfaces, collect the operating status, performance parameters, and error code data of the equipment in real time; Clean and convert the collected data to ensure data accuracy and consistency to facilitate subsequent analysis and modeling;

[0082] Explanation: The enterprise equipment connection topology diagram intuitively displays the physical or logical connection relationship between devices, such as the connection between routers, switches, servers, and workstations. It is a graphical expression method used to intuitively display the layout and structure of the enterprise's internal network, and depicts the connection relationship between network devices through nodes and connecting lines, helping network engineers and managers to better understand and plan network architecture; nodes represent various network devices, such as routers, switches, servers, workstations, etc.; connecting lines represent the physical or logical connection relationship between devices; the logical connection relationship is used to show how data flows and interacts between devices. The logical connection describes the communication and collaboration relationship between devices through protocols, interfaces, network layers, etc. For example, two servers may transmit data through the TCP / IP protocol. This relationship is a logical connection relationship.

[0083] Step S02: Basic model construction: Based on the device connection topology and logical connection relationships, a physical model and a logical model of the device are constructed; the physical model reflects the physical structure and properties of the device, and the logical model is used to describe the data interaction and business processes between devices;

[0084] Step S03, functional model construction: Establish functional models for equipment status monitoring, fault diagnosis, and performance prediction. Use sensors to establish the equipment status monitoring functional model. Leverage network data in the data warehouse and perform data analysis, simulation, and prediction using deep learning algorithms to implement the fault diagnosis and performance prediction functional models. The performance prediction functional model involves establishing a mapping between a single operating instruction and an equipment status feature vector, and predicting the set of equipment status feature vectors after executing a single set of operating instructions.

[0085] Step S04: Integration and Verification: Integrate the basic model and the functional model to form a complete digital twin model. Ensure the accuracy and reliability of the digital twin model by comparing it with the actual system, and output the constructed digital twin model.

[0086] Step S05, Deployment and Operation and Maintenance: Deploy the constructed digital twin model on the cloud platform, and use the computing and storage resources of the cloud platform to achieve remote access and real-time updates of the model; continuously operate and optimize the digital twin model, including data updates, model adjustments, and performance optimization, to ensure that the digital twin model can accurately reflect the actual status and behavior of the device.

[0087] Example 2, see Figure 2 The structure block diagram of the enterprise management system based on cloud platform risk management is shown in FIG. The difference between this embodiment of the present invention and Example 1 is that the enterprise management system includes:

[0088] The cloud platform management module is used to manage cloud platform data and ensure the security of cloud platform data. It includes an identity authentication login unit and an interface management unit. The identity authentication login unit is used to verify the user's identity. After the verification is passed, the user logs into the cloud platform; the interface management unit is used to filter abnormal interfaces based on the access security reliability index to obtain a set of secure interfaces.

[0089] It should be further explained in the embodiment of the present invention that the operation process of the cloud platform management module includes the following steps:

[0090] Receiving access application: The cloud platform receives the user's access application, which includes a digital twin model access application and a time series data access application;

[0091] Verify the user's role information through smart contracts to confirm whether the user has the role permissions required for the requested access;

[0092] If the role permission verification is passed, the user's access security reliability index is calculated based on the user's role and historical user behavior data and stored in the database;

[0093] comparing the calculated access security reliability index with a preset critical access security reliability index;

[0094] If the access security reliability index reaches or exceeds the critical value, the cloud platform allows the user to access and continuously evaluates the user's trustworthy behavior during the access process;

[0095] If the access security reliability index is lower than the critical value, the cloud platform will automatically reject the user's access request.

[0096] It needs to be further explained in the embodiment of the present invention that the access security reliability index is obtained in the following manner:

[0097] Divide the access data by time zone and obtain the user access behavior data of each time zone; analyze the user's access behavior in the previous time zone to obtain the illegal connection frequency p1, the attempt to exceed the authority frequency p2 and the user infection frequency p3. p1*w1+p2*w2+p3*w3 The behavior penalty parameter cp is calculated, where w1, w2, and w3 represent the proportional coefficients of each item, based on user settings;

[0098] Obtain the user's basic access security reliability index from the database, denoted as Fa. The basic access security reliability index refers to the access security reliability index before the user's access behavior in the previous time zone, that is, the access security reliability index when the user's access behavior in the previous time zone is not considered;

[0099] By formula Calculate the user's current access security reliability index Fnx, where Ft represents the attenuation function, satisfying the formula Where α is the decay rate adjustment factor; t n -t n-1 It represents the time interval between the user access request time point and the previous time zone, and hf represents the number of access operations in the previous time zone.

[0100] In a further design, the enterprise management system further includes:

[0101] The cloud platform risk management module divides enterprise data by time zones, obtains the average value of the access security reliability index, the average value of the instruction security risk index, and the average value of the equipment operation quality index in each time zone, and conducts joint analysis to obtain the cloud platform management coefficient. When the cloud platform management coefficient is lower than the corresponding threshold, it indicates that the cloud platform management quality is abnormal, and an early warning is issued to the user, prompting the enterprise to maintain equipment quality and increase data security maintenance.

[0102] In a further design, the operation process of the cloud platform risk management module includes the following steps:

[0103] Step S11: Divide the collected data into time zones and number them; suppose the data is divided into m time zones, and j represents the number of the time zones;

[0104] Step S12: Calculate the weight coefficient of each time zone, and record the weight coefficient of the jth time zone as q wj ;

[0105] Assume that there are k operations in the time region, and s represents the order of operations. Calculate the weight coefficient of the jth time zone, where ct_s represents the duration of the sth operation and cy_s represents the impact range of the sth operation on the device;

[0106] Step S13: Obtain the average value of the access security reliability index, the average value of the instruction security risk index, and the average value of the equipment operation quality index in the jth time zone, and record them as Fag_j, Zag_j, and Sag_j respectively;

[0107] Explanation: By obtaining the access security reliability index of all users in the time zone, taking the average value of the access security reliability index, obtaining the instruction security risk index of all operation instructions in the time zone, taking the average value of the instruction security risk index, and obtaining the average value of the operation quality index of all devices after executing the operation instruction in the time zone, the average value of the device operation quality index is obtained.

[0108] Step S14: By formula The cloud platform management risk coefficient YG is calculated; where qa, qb, and qc represent the weight coefficients of each item; form(·) represents the linear normalization function;

[0109] Step S15: Determine whether the cloud platform management risk coefficient is lower than the corresponding threshold. When the cloud platform management risk coefficient is not lower than the corresponding threshold, it indicates that the cloud platform management quality is abnormal, and an early warning is issued to the user, prompting the enterprise to maintain equipment quality and increase data security maintenance; if the cloud platform management risk coefficient is lower than the corresponding threshold, it indicates that the cloud platform management risk is within the controllable range and no measures are taken.

[0110] In embodiment 3, the present invention provides a cloud platform-based enterprise management method, comprising the following steps:

[0111] Step 1: Based on the device connection topology and logical connection relationships of enterprise devices, build a digital twin model corresponding to the enterprise devices and deploy the built digital twin model on the cloud platform;

[0112] Step 2: Collect time series data from enterprise equipment and transmit the collected data to the cloud platform;

[0113] Step 3: The user accesses the digital twin model through the interface and remotely controls the enterprise equipment based on the digital twin model in the cloud platform. The user issues an operation instruction, which is verified based on the digital twin model. Executable operation instructions are screened out, and the enterprise equipment executes the operation instructions. The process of screening executable operation instructions includes:

[0114] Step S301: convert the operation instruction into a single operation instruction set, and obtain the logical connection relationship of the single operation instruction set;

[0115] Step S302: Establish a mapping between a single operation instruction and a device state feature vector, and predict a device state feature vector group after executing a single operation instruction set;

[0116] Step S303: Based on the logical connection relationship of the single operation instruction set, the device state feature vector group is processed to complete vector superposition of the device state feature vector group to obtain the device superposition state feature vector group corresponding to the operation instruction;

[0117] Step S304: Analyze the device superposition state feature vector group and the device safety constraint conditions, match the offset rate weight coefficient for each feature vector, and calculate the instruction safety risk index Sof;

[0118] Step S305: Filter executable operation instructions from the operation instructions based on the instruction security risk index and transmit them to the device end. If the operation instructions do not meet the requirements, generate warning information.

[0119] Explanation: Assume there are two single operation instructions, denoted as A and B. After each instruction is executed, the device will have a corresponding device state feature vector. The feature vector group contains multiple state parameters of the device, such as temperature, wear, etc.

[0120] The feature vector of instruction A:

[0121] After instruction A is executed, the equipment temperature rises by 5 degrees, the wear degree increases by 0.1, the load increases by 10%, the efficiency rate decreases by 2%, and the output remains unchanged;

[0122] Therefore, the feature vector of instruction A can be expressed as: [5, 0.1, 10%, -2%, 0];

[0123] The feature vector of instruction B is:

[0124] After instruction B is executed, the temperature of the equipment rises by 3 degrees, the wear degree increases by 0.05, the load remains unchanged, the efficiency rate increases by 1%, and the output increases by 5%;

[0125] Therefore, the feature vector of instruction B can be expressed as: [3, 0.05, 0%, 1%, 5%];

[0126] Consider the logical connection relationship for vector superposition:

[0127] Assume that instructions A and B are executed sequentially (i.e., A is executed before B);

[0128] Then, the overall effect of the entire instruction set on the device state is the superposition of the feature vectors of instructions A and B;

[0129] The superimposed eigenvector is: [5+3, 0.1+0.05, 10%+0%, -2%+1%, 0+5%], that is, [8, 0.15, 10%, -1%, 5%]; this superimposed eigenvector represents the overall state change of the device after instruction sets A and B are executed sequentially.

[0130] What needs to be further explained in the embodiments of the present invention is that after the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns information on the execution status; if the equipment executes unsuccessfully, it returns an error code; the response time of the equipment to execute the operation instruction, the number of times the equipment successfully executes the instruction, and the error code are analyzed to obtain the equipment operation quality index, and abnormal equipment is screened out based on the relationship between the equipment operation quality index and the corresponding threshold; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment is operating abnormally, and the faulty equipment is screened out to form a faulty equipment set, and maintenance instructions are generated for the faulty equipment set.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An enterprise management system based on a cloud platform, characterized in that: include: The data acquisition module obtains the connection topology and logical connection relationship of enterprise equipment, collects the time series data of enterprise equipment, and transmits the collected data to the cloud platform; The digital twin model building module builds digital twin models corresponding to enterprise devices based on the device connection topology and logical connection relationships of enterprise devices, and deploys the built digital twin models on the cloud platform; In the enterprise device management module, users access the digital twin model through an interface and remotely control enterprise devices based on the digital twin model in the cloud platform. The user issues operation instructions, which are verified based on the digital twin model, and executable operation instructions are screened out, and the enterprise device executes the operation instructions. The process of screening executable operation instructions includes: converting the operation instructions into a single operation instruction set, obtaining the logical connection relationship of the single operation instruction set; establishing a mapping between the single operation instruction and the device state feature vector, and predicting the device state feature vector group after the single operation instruction set is executed; based on the logical connection relationship of the single operation instruction set, processing the device state feature vector group, completing the vector superposition of the device state feature vector group, and obtaining the device superposition state feature vector group corresponding to the operation instruction; analyzing the device superposition state feature vector group and the device safety constraint conditions, matching the offset rate weight coefficient for each device state feature vector, and the i-th feature vector offset rate weight coefficient is recorded as qs i , the number of device superposition state feature vector groups is recorded as n, i is used to represent the sequence number of the feature vector, and the predicted value of the i-th feature vector is St i ; Set the constraint value of the i-th eigenvector to Yt i ; Through the formula Calculate the instruction security risk index Sof; based on the instruction security risk index, screen the executable operation instructions from the operation instructions and transmit them to the device end. If the operation instructions do not meet the requirements, generate a warning message; The cloud platform management process includes the following steps: Receive user access requests; verify user role permissions through smart contracts. Once verified, calculate and store the access security reliability index based on the user's historical behavior data; compare the access security reliability index with the preset critical value; if it does not meet the threshold, deny access; calculate the access security reliability index by dividing access data by time zone, analyzing historical access behavior frequency, and calculating behavior penalty parameters based on the frequency of illegal connections, unauthorized attempts, and virus infections; calculate the access security reliability index based on the user's basic security reliability index and adjust it using an attenuation function; Enterprise data is divided into time zones, and the average value of the access security reliability index, the average value of the instruction security risk index, and the average value of the equipment operation quality index in each time zone are obtained. The cloud platform management coefficient is obtained through joint analysis. When the cloud platform management coefficient is lower than the corresponding threshold, it indicates that the cloud platform management quality is abnormal, and an early warning is issued to the user.

2. The cloud-based enterprise management system according to claim 1, characterized in that: The enterprise equipment management module includes an equipment quality management unit for screening out abnormal equipment. After the enterprise equipment executes the operation instruction, if the equipment executes successfully, it returns the execution status information; if the equipment executes unsuccessfully, it returns an error code; Analyze the response time of the equipment in executing operation instructions, the number of times the equipment successfully executes instructions, and the error code to obtain the equipment operation quality index. Based on the relationship between the equipment operation quality index and the corresponding threshold, abnormal equipment is screened out; if the equipment operation quality index of the equipment is lower than the corresponding threshold, it indicates that the equipment is operating abnormally. The faulty equipment is screened out to form a faulty equipment set, and maintenance instructions are generated for the faulty equipment set.

3. The cloud-based enterprise management system according to claim 2, characterized in that: The equipment operation quality index is obtained as follows: Analyze the execution data of device operation instructions to obtain response time, number of times the device successfully executes instructions, and error codes; The number of operation instructions that the device can execute is recorded as m, and the sequence number of the operation instructions is represented by j. Based on the importance of each operation instruction to the operation quality of the device, a weight coefficient is set for each operation instruction; Get the response time of the jth operation instruction, analyze and get the successful execution ratio of the jth operation instruction, recorded as the success rate s j ; Get the error code encountered when executing the j-th operation instruction, and set the weight E corresponding to each error code j ; Through Z-score normalization, we obtain the normalized value σ_T of the device's response time when executing the jth operation instruction and the normalized value σ_E of the weight of the error code of the jth operation instruction. The normalized weight value is used to convert the weights of different error codes to the same scale. By formula The equipment operation quality index Sq is calculated; where w j The weight coefficient of the jth operation instruction is represented by F1 and F2, which are adjustment coefficients used to balance the impact of response time and error code on the device operation quality index. 0<F1<1, 0<F2<1, and F1+F2=1.

0.

4. The cloud-based enterprise management system according to claim 3, characterized in that: The enterprise management system includes: The cloud platform management module is used to manage cloud platform data and ensure the security of cloud platform data. It includes an identity authentication login unit and an interface management unit. The identity authentication login unit is used to verify the user's identity. After the verification is passed, the user logs into the cloud platform; the interface management unit is used to filter abnormal interfaces based on the access security reliability index to obtain a set of secure interfaces.

5. The cloud-based enterprise management system according to claim 4, characterized in that: The operation process of the cloud platform management module includes the following steps: Receiving access application: The cloud platform receives the user's access application, which includes a digital twin model access application and a time series data access application; Verify the user's role information through smart contracts to confirm whether the user has the role permissions required for the requested access; If the role permission verification is passed, the user's access security reliability index is calculated based on the user's role and historical user behavior data and stored in the database; comparing the calculated access security reliability index with a preset critical access security reliability index; If the access security reliability index reaches or exceeds the critical value, the cloud platform allows the user to access and continuously evaluates the user's trustworthy behavior during the access process; If the access security reliability index is lower than the critical value, the cloud platform will automatically reject the user's access request.

6. The cloud-based enterprise management system according to claim 5, characterized in that: The access security reliability index is obtained as follows: Divide access data by time zone and obtain user access behavior data for each time zone; Analyze the user's access behavior in the previous time zone to obtain the illegal connection frequency p1, the frequency of attempted overreach p2 and the frequency of user virus infection p3. The behavior penalty parameter cp is calculated, where w1, w2, and w3 represent the proportional coefficients of each item, based on user settings; Obtain the user's basic access security reliability index from the database, denoted as Fa; By formula Calculate the user's current access security reliability index Fnx, where Ft represents the attenuation function, satisfying the formula , where α is the decay rate adjustment factor; It represents the time interval between the user access request time point and the previous time zone, and hf represents the number of access operations in the previous time zone.

7. A cloud platform-based enterprise management method, implemented based on the enterprise management system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: Based on the device connection topology and logical connection relationships of enterprise devices, build a digital twin model corresponding to the enterprise devices and deploy the built digital twin model on the cloud platform; Step 2: Collect time series data from enterprise equipment and transmit the collected data to the cloud platform; Step 3: The user accesses the digital twin model through the interface and remotely controls the enterprise equipment based on the digital twin model in the cloud platform. The user issues an operation instruction, which is verified based on the digital twin model. The executable operation instructions are screened out, and the enterprise equipment executes the operation instruction. The process of screening executable operation instructions includes: Step S301: convert the operation instruction into a single operation instruction set, and obtain the logical connection relationship of the single operation instruction set; Step S302: Establish a mapping between a single operation instruction and a device state feature vector, and predict a device state feature vector group after executing a single operation instruction set; Step S303: Based on the logical connection relationship of the single operation instruction set, the device state feature vector group is processed to complete vector superposition of the device state feature vector group to obtain the device superposition state feature vector group corresponding to the operation instruction; Step S304: Analyze the device superposition state feature vector group and the device safety constraint conditions, match the offset rate weight coefficient for each feature vector, and calculate the instruction safety risk index Sof; Step S305: Filter executable operation instructions from the operation instructions based on the instruction security risk index and transmit them to the device end. If the operation instructions do not meet the requirements, generate warning information.

Images