Remote supervision and control system integrating deep learning and virtual reality

Abstract

The invention provides a remote supervision and control system integrating deep learning and virtual reality, and the system comprises an obtaining module which obtains the remote control information and actual monitoring data of a target factory, and obtains a virtual factory model; the first analysis module is used for analyzing to obtain a first display coefficient, a second display coefficient, a digital display coefficient and a digital marking coefficient of the factory digital information; obtaining a digital supervision coefficient of the factory digital information according to the digital display coefficient and the digital marking coefficient; the second analysis module is used for analyzing to obtain an information matching degree between the remote monitoring information and the factory digital information, and analyzing to obtain a digital control coefficient of the target digital information; the supervision control module obtains a supervision control coefficient of the factory digital information according to the digital supervision coefficient and the digital control coefficient; and obtaining the supervision control degree of the actual monitoring data of the target factory according to the supervision control coefficient. According to the invention, the comprehensiveness and accuracy of supervision and control of the target factory are improved.

Description

Technical Field

[0001] The present application relates to the field of remote supervision, and specifically to a remote supervision and control system integrating deep learning with virtual reality. Background Art

[0002] With the rapid development of Internet technology, remote monitoring and control systems also play a vital role in remote monitoring and control of factories in many fields such as industry, medical care, and security. However, traditional remote monitoring and control systems have many limitations. Traditional systems usually rely on two-dimensional image display and can only observe the monitored objects from a limited angle. For tasks that require fine operation and accurate judgment, two-dimensional images often cannot meet the needs. With the continuous development of sensor technology, the amount of data that remote monitoring and control systems need to process has exploded, including images, videos, sensor data, etc., and traditional data processing methods make it difficult to quickly and accurately analyze these data and extract useful information.

[0003] The remote supervision and control systems in related technologies often do not conduct comprehensive analysis of the actual data of the target factory, resulting in a lack of comprehensiveness and accuracy in the supervision and control of the target factory, which is prone to errors in the supervision and control of the target factory. There is room for improvement. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a remote supervision and control system that integrates deep learning with virtual reality, so as to improve the problem that the remote supervision and control system in the related technology often does not conduct comprehensive analysis of the actual data of the target factory, resulting in a lack of comprehensiveness and accuracy in the supervision and control of the target factory, and easily causing supervision and control errors of the target factory.

[0005] This application provides a remote monitoring and control system that integrates deep learning and virtual reality, including:

[0006] Acquisition module: obtains the remote control information of the target factory and the actual monitoring data of the target factory within the preset time;

[0007] Obtaining factory digital information of the target factory based on the actual monitoring data, and constructing a virtual factory model corresponding to the target factory based on the factory digital information;

[0008] Obtaining the digital information category corresponding to the factory digital information of the virtual factory model, and the information change parameter of the factory digital information within a preset time;

[0009] The first analysis module: analyzes the digital information category corresponding to the factory digital information to obtain a first display coefficient of the factory digital information; analyzes the information change parameter of the factory digital information within a preset time to obtain a second display coefficient of the factory digital information;

[0010] Obtaining a digital display coefficient of factory digital information according to the first display coefficient and the second display coefficient;

[0011] According to the preset time and the digital information category corresponding to the factory digital information, setting the information change parameter threshold corresponding to the factory digital information of different digital information categories within the preset time;

[0012] Compare and analyze the information change parameter of the factory digital information within a preset time with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information;

[0013] The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and the digital marking coefficient of the factory digital information;

[0014] The second analysis module: performs information matching analysis on the remote monitoring information of the target factory and the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information;

[0015] Comparing and analyzing the information matching degree with the information matching degree threshold, obtaining the factory digital information matching the remote control information, and marking the factory digital information as the target digital information;

[0016] Obtaining a digital control coefficient of the target digital information according to the information matching degree and the information matching degree threshold;

[0017] Supervision and control module: obtains the supervision and control coefficient corresponding to the factory digital information of the virtual factory model according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information;

[0018] The degree of supervision and control of the actual monitoring data of the target factory is obtained according to the supervision and control coefficient.

[0019] Preferably, the remote control information of the target factory and the actual monitoring data of the target factory within a preset time are obtained; the factory digital information of the target factory is obtained according to the actual monitoring data, and a virtual factory model corresponding to the target factory is constructed according to the factory digital information, specifically:

[0020] Obtaining a remote control instruction of a target factory, and obtaining remote control information of the target factory according to the remote control instruction;

[0021] A preset virtual model is set, and the factory digital information of the target factory is imported into the preset virtual model to obtain a virtual factory model corresponding to the target factory.

[0022] Preferably, the digital information category corresponding to the factory digital information is analyzed to obtain the first display coefficient of the factory digital information; and the information change parameter of the factory digital information within a preset time is analyzed to obtain the second display coefficient of the factory digital information, specifically:

[0023] Setting the information weight value corresponding to the factory digital information according to the digital information category corresponding to the factory digital information;

[0024] The information weight value corresponding to the factory digital information is taken and marked to obtain the information weight value QZ;

[0025] The first display coefficient OXX of the factory digital information is calculated by a first calculation function OXX=α×QZ, wherein α is a preset proportional factor;

[0026] The information change parameters include the information change frequency and information change amplitude of the factory digital information within a preset time;

[0027] The frequency of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change frequency BP; the amplitude of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change amplitude BF;

[0028] By the second calculation function TXX=a 1 ×BP+a 2 ×BF calculates the second display coefficient TXX of the factory digital information, where a 1 、a 2 is the preset scale factor.

[0029] Preferably, the digital display coefficient of the factory digital information is obtained according to the first display coefficient and the second display coefficient, specifically:

[0030] By the third calculation function SXX=b 1 ×OXX+b 2 ×TXX calculates the digital display coefficient SXX of the factory digital information, where b 1 , b 2 is the preset scaling factor;

[0031] Setting display coefficient intervals, each of which corresponds to an interval display weight value;

[0032] Matching and analyzing the digital display coefficient SXX of the factory digital information with the display coefficient interval to obtain the display coefficient interval where the digital display coefficient SXX of the factory digital information is located;

[0033] Marking the display coefficient interval as a target display coefficient interval, taking and marking the interval display weight value corresponding to the target display coefficient interval to obtain an interval display weight value XQ;

[0034] The digital display coefficient SXX' of the factory digital information is calculated by the fourth calculation function SXX'=ε×SXX×XQ, wherein ε is a preset proportional factor.

[0035] Preferably, the information change parameter thresholds corresponding to the factory digital information of different digital information categories within the preset time are set according to the preset time and the digital information category corresponding to the factory digital information, specifically:

[0036] The information change parameter thresholds include an information change frequency threshold and an information change amplitude threshold;

[0037] Taking and marking the preset time to obtain the preset time YS;

[0038] Through the fifth calculation function The information change frequency threshold PY corresponding to the factory digital information of different digital information categories within the preset time is calculated, where c 1 is the preset scaling factor;

[0039] Through the sixth calculation function Calculate the information change amplitude threshold FY corresponding to the factory digital information of different digital information categories within the preset time, where c 2 is the preset scale factor.

[0040] Preferably, the information change parameter of the factory digital information within a preset time is compared and analyzed with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information, specifically:

[0041] The digital marking coefficients of the factory digital information include a first digital marking coefficient and a second digital marking coefficient;

[0042] If the information change frequency BP of the factory digital information within the preset time is less than the information change frequency threshold PY, then the factory digital information does not have the first digital marking coefficient;

[0043] If the information change frequency BP of the factory digital information within the preset time is greater than or equal to the information change frequency threshold PY, then the factory digital information has a first digital marking coefficient;

[0044] And through the seventh calculation function SBX = d 1 ×(BP-PY) calculates the first digital marking coefficient OBX of the factory digital information, where d 1 is the preset scaling factor;

[0045] If the information change amplitude BF of the factory digital information within the preset time is less than the information change amplitude threshold FY, then the factory digital information does not have a second digital marking coefficient;

[0046] If the information change amplitude BF of the factory digital information within the preset time is greater than or equal to the information change amplitude threshold FY, then the factory digital information has a second digital marking coefficient;

[0047] And through the eighth calculation function SBX = d 2 ×(BF-FY) to calculate the second digital marking coefficient TBX of the factory digital information, where d 2 is the preset scaling factor;

[0048] By the ninth calculation function SBX=e 1 ×OBX+e 2 ×TBX calculates the digital marking coefficient SBX of the factory digital information, where e 1 、e 2 is the preset scaling factor;

[0049] The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and digital marking coefficient of the factory digital information, which is specifically:

[0050] By the tenth calculation function JGX = f 1 ×SXX'+f 2 ×SBX calculates the digital supervision coefficient JGX of the factory digital information, where f 1 、f 2 is the preset scale factor.

[0051] Preferably, the remote monitoring information of the target factory is matched with the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information, specifically:

[0052] Extracting control information keywords corresponding to the remote control information according to the remote control information of the target factory;

[0053] Performing a word meaning matching analysis based on the control information keywords and the factory digital information of the virtual factory model to obtain the information word meaning matching degree between the control information keywords and the factory digital information;

[0054] The information word meaning matching degree is evaluated and marked to obtain the information word meaning matching degree XC;

[0055] The first matching coefficient OPX between the control information keyword and the factory digital information is calculated by an eleventh calculation function OPX=β×XC, wherein β is a preset proportional factor;

[0056] Performing a word meaning repetition rate matching analysis based on the control information keywords and the factory digital information of the virtual factory model to obtain the information word meaning repetition rate between the control information keywords and the factory digital information;

[0057] Taking and marking the information word sense repetition rate to obtain the information word sense repetition rate XF;

[0058] The second matching coefficient TPX between the control information keyword and the factory digital information is calculated by a twelfth calculation function TPX=χ×XF, wherein χ is a preset proportional factor;

[0059] By the thirteenth calculation function XPD = g 1 ×OPX+g 2 ×TPX calculates the information matching degree XPD between remote monitoring information and factory digital information, where g 1 , g 2 is the preset scale factor.

[0060] Preferably, a comparison analysis is performed based on the information matching degree and the information matching degree threshold to obtain the factory digital information matching the remote control information, and the factory digital information is marked as the target digital information; and a digital control coefficient of the target digital information is obtained based on the information matching degree and the information matching degree threshold, specifically:

[0061] If the information matching degree XPD between the remote monitoring information and the factory digital information is less than the information matching degree threshold, the factory digital information does not match the remote monitoring information;

[0062] If the information matching degree XPD between the remote monitoring information and the factory digital information is greater than or equal to the information matching degree threshold, the factory digital information matches the remote monitoring information, and the factory digital information is marked as the target digital information;

[0063] The information matching degree threshold is taken and marked to obtain the information matching degree threshold DY;

[0064] The digital control coefficient KZX of the target digital information is calculated by a fourteenth calculation function KZX=δ×(XPD-DY), wherein δ is a preset proportional factor.

[0065] Preferably, the supervision control coefficient corresponding to the factory digital information of the virtual factory model is obtained according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information; and the supervision control degree of the actual monitoring data of the target factory is obtained according to the supervision control coefficient, specifically:

[0066] By the fifteenth calculation function JKX=h 1 ×JGX+h 2×KZX calculates the supervisory control coefficient JKX corresponding to the factory digital information of the virtual factory model, where h 1 、h 2 is the preset scaling factor;

[0067] The degree of supervision and control of the actual monitoring data of the target factory is positively correlated with the supervision and control coefficient JKX corresponding to the factory digital information of the virtual factory model.

[0068] In summary, the beneficial effects of this application are:

[0069] 1. The present application obtains a first display coefficient of the factory digital information by analyzing the digital information category corresponding to the factory digital information; obtains a second display coefficient of the factory digital information by analyzing the information change parameters of the factory digital information within a preset time, and obtains a digital display coefficient of the factory digital information based on the first display coefficient and the second display coefficient; in addition, a digital marking coefficient of the factory digital information is obtained by setting an information change parameter threshold corresponding to the factory digital information within a preset time, and comparing and analyzing the information change parameters of the factory digital information within the preset time with the information change parameter threshold; obtains a digital supervision coefficient of the factory digital information based on the digital display coefficient and the digital marking coefficient of the factory digital information, and implements effective supervision of the target factory based on the digital supervision coefficient.

[0070] 2. The present application obtains the information matching degree between the remote monitoring information of the target factory and the factory digital information of the virtual factory model by performing information matching analysis, and obtains the target digital information that matches the remote control information by comparing and analyzing the information matching degree and the information matching degree threshold; obtains the digital control coefficient of the target digital information based on the information matching degree and the information matching degree threshold, and realizes effective control of the target factory based on the digital supervision coefficient; finally, obtains the supervision control coefficient corresponding to the factory digital information of the virtual factory model based on the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information, and comprehensively and accurately reflects the supervision control degree of the actual monitoring data of the target factory through the supervision control coefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present application, some of the drawings in the embodiments of the present application will be briefly described below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be considered as limiting the scope of the present application.

[0072] Figure 1 A schematic diagram of the structure of a remote monitoring and control system integrating deep learning and virtual reality provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] Below is a combination of the embodiments and Figure 1 The present application is further described in detail, but the implementation methods of the present application are not limited thereto.

[0074] Reference Figure 1 As shown, it is a structural schematic diagram of a remote supervision and control system of deep learning fusion virtual reality provided by an embodiment of the present application. In the embodiment of the present application, the application scenario is to obtain the factory digital information of the target factory based on the actual monitoring data of the target factory, and to build a virtual factory model corresponding to the target factory based on the factory digital information, and to obtain the digital display coefficient and the digital marking coefficient of the factory digital information by analyzing the factory digital information of the virtual factory model, and to obtain the digital supervision coefficient of the factory digital information based on the digital display coefficient and the digital marking coefficient; in addition, by matching and analyzing the remote monitoring information of the target factory with the factory digital information of the virtual factory model, the digital control coefficient of the target digital information is obtained; finally, the supervision control coefficient corresponding to the factory digital information of the virtual factory model is obtained based on the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information, and the supervision control degree of the actual monitoring data of the target factory is obtained based on the supervision control coefficient, which is different from the remote supervision and control system in the prior art, which often does not fully analyze the actual data of the target factory, resulting in a lack of comprehensiveness and accuracy in the supervision and control of the target factory, and is prone to supervision and control errors of the target factory.

[0075] A remote monitoring and control system integrating deep learning and virtual reality, comprising:

[0076] Acquisition module: obtains the remote control information of the target factory and the actual monitoring data of the target factory within the preset time;

[0077] Obtain the factory digital information of the target factory based on the actual monitoring data, and build a virtual factory model corresponding to the target factory based on the factory digital information;

[0078] Obtaining the digital information category corresponding to the factory digital information of the virtual factory model, and the information change parameter of the factory digital information within a preset time;

[0079] The first analysis module: analyzes the digital information category corresponding to the factory digital information to obtain a first display coefficient of the factory digital information; analyzes the information change parameter of the factory digital information within a preset time to obtain a second display coefficient of the factory digital information;

[0080] Obtaining a digital display coefficient of the factory digital information according to the first display coefficient and the second display coefficient;

[0081] According to the preset time and the digital information category corresponding to the factory digital information, the information change parameter threshold corresponding to the factory digital information of different digital information categories within the preset time is set;

[0082] Compare and analyze the information change parameter of the factory digital information within a preset time with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information;

[0083] The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and the digital marking coefficient of the factory digital information;

[0084] The second analysis module: performs information matching analysis on the remote monitoring information of the target factory and the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information;

[0085] Compare and analyze the information matching degree with the information matching degree threshold to obtain the factory digital information matching the remote control information, and mark the factory digital information as the target digital information;

[0086] Obtaining a digital control coefficient of target digital information according to the information matching degree and the information matching degree threshold;

[0087] Supervision and control module: obtains the supervision and control coefficient corresponding to the factory digital information of the virtual factory model according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information;

[0088] The degree of supervision and control of the actual monitoring data of the target factory is obtained based on the supervision and control coefficient.

[0089] Obtain the remote control information of the target factory and the actual monitoring data of the target factory within the preset time; obtain the factory digital information of the target factory based on the actual monitoring data, and build a virtual factory model corresponding to the target factory based on the factory digital information, specifically:

[0090] Obtain remote control instructions of the target factory, and obtain remote control information of the target factory according to the remote control instructions;

[0091] A preset virtual model is set, and the factory digital information of the target factory is imported into the preset virtual model to obtain a virtual factory model corresponding to the target factory.

[0092] It should be noted that the preset virtual model can be preset based on the factory model software. After the factory digital information of the target factory is imported into the preset model, the preset virtual model will generate a virtual factory model corresponding to the target factory based on the factory digital information.

[0093] The digital information category corresponding to the factory digital information is analyzed to obtain the first display coefficient of the factory digital information; the information change parameter of the factory digital information within a preset time is analyzed to obtain the second display coefficient of the factory digital information, which is specifically:

[0094] The information weight value corresponding to the factory digital information is set according to the digital information category corresponding to the factory digital information;

[0095] The information weight value corresponding to the factory digital information is taken and marked to obtain the information weight value QZ;

[0096] The first display coefficient OXX of the factory digital information is calculated by a first calculation function OXX=α×QZ, wherein α is a preset proportional factor;

[0097] The information change parameters include the information change frequency and information change amplitude of the factory digital information within a preset time;

[0098] The frequency of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change frequency BP; the amplitude of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change amplitude BF;

[0099] By the second calculation function TXX=a 1 ×BP+a 2 ×BF calculates the second display coefficient TXX of the factory digital information, where a 1 、a 2 is the preset scale factor.

[0100] It should be noted that the information weight value corresponding to the factory digital information can be obtained based on the digital information category-information weight value comparison table, where the digital information category-information weight value comparison table is obtained based on the historical data of the target factory;

[0101] In some embodiments, if the information weight value corresponding to the factory digital information is 10, the information weight value QZ is 10, and if the preset proportional factor α is 1, the first display coefficient OXX of the factory digital information calculated by the first calculation function OXX=α×QZ is 10;

[0102] If the factory digital information changes 10 times within the preset time, the information change frequency BP is 10; if the factory digital information changes 20 times within the preset time, the information change amplitude BF is 20; if the preset proportional factor a 1 、a 2 is 1, 0.5, then through the second calculation function TXX=a 1 ×BP+a 2×BF calculates the second display coefficient TXX of the factory digital information to be 20.

[0103] The digital display coefficient of the factory digital information is obtained according to the first display coefficient and the second display coefficient, specifically:

[0104] By the third calculation function SXX=b 1 ×OXX+b 2 ×TXX calculates the digital display coefficient SXX of the factory digital information, where b 1 , b 2 is the preset scaling factor;

[0105] Set the display coefficient interval, and the display coefficient interval corresponds to the interval display weight value;

[0106] Matching and analyzing the digital display coefficient SXX of the factory digital information with the display coefficient interval, to obtain the display coefficient interval where the digital display coefficient SXX of the factory digital information is located;

[0107] Mark the display coefficient interval as the target display coefficient interval, and obtain and mark the interval display weight value corresponding to the target display coefficient interval to obtain the interval display weight value XQ;

[0108] The digital display coefficient SXX' of the factory digital information is calculated by the fourth calculation function SXX'=ε×SXX×XQ, wherein ε is a preset proportional factor.

[0109] In some embodiments, if the first display coefficient OXX of the factory digital information is 10; the second display coefficient TXX of the factory digital information is 20; the preset scale factor b 1 , b 2 is 1, 1, then through the third calculation function SXX=b 1 ×OXX+b 2 ×TXX calculates the digital display coefficient SXX of the factory digital information to be 30;

[0110] At this time, if the interval display weight value corresponding to the target display coefficient interval is 0.8, and the preset proportional factor ε is 1, the digital display coefficient SXX' of the factory digital information is calculated by the fourth calculation function SXX'=ε×SXX×XQ to be 24;

[0111] It should be noted that there is at least one display coefficient interval, and each display coefficient interval corresponds to an interval display weight value.

[0112] According to the preset time and the digital information category corresponding to the factory digital information, the information change parameter threshold corresponding to the factory digital information of different digital information categories within the preset time is set, specifically:

[0113] The information change parameter threshold includes an information change frequency threshold and an information change amplitude threshold;

[0114] Taking and marking the preset time to obtain the preset time YS;

[0115] Through the fifth calculation function The information change frequency threshold PY corresponding to the factory digital information of different digital information categories within the preset time is calculated, where c 1 is the preset scaling factor;

[0116] Through the sixth calculation function Calculate the information change amplitude threshold FY corresponding to the factory digital information of different digital information categories within the preset time, where c 2 is the preset scale factor.

[0117] In some embodiments, if the preset time is 10 hours, the preset time YS is 10; if the information weight value QZ corresponding to the factory digital information is 5; at this time, if the preset proportionality factor c 1 is 5, then through the fifth calculation function The information change frequency threshold PY corresponding to the factory digital information of different digital information categories within the preset time is calculated to be 10; at this time, if the preset proportional factor c 2 is 3, then through the sixth calculation function The information change amplitude threshold FY corresponding to the factory digital information of different digital information categories within the preset time is calculated to be 6.

[0118] The information change parameters of the factory digital information within the preset time are compared and analyzed with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information, which is specifically:

[0119] The digital marking coefficients of the factory digital information include a first digital marking coefficient and a second digital marking coefficient;

[0120] If the information change frequency BP of the factory digital information within the preset time is less than the information change frequency threshold PY, then the factory digital information does not have the first digital marking coefficient;

[0121] If the information change frequency BP of the factory digital information within the preset time is greater than or equal to the information change frequency threshold PY, then the factory digital information has a first digital marking coefficient;

[0122] And through the seventh calculation function SBX = d 1 ×(BP-PY) calculates the first digital marking coefficient OBX of the factory digital information, where d 1 is the preset scaling factor;

[0123] If the information change amplitude BF of the factory digital information within the preset time is less than the information change amplitude threshold FY, then the factory digital information does not have the second digital marking coefficient;

[0124] If the information change amplitude BF of the factory digital information within the preset time is greater than or equal to the information change amplitude threshold FY, then the factory digital information has a second digital marking coefficient;

[0125] And through the eighth calculation function SBX = d 2 ×(BF-FY) to calculate the second digital marking coefficient TBX of the factory digital information, where d 2 is the preset scaling factor;

[0126] By the ninth calculation function SBX=e 1 ×OBX+e 2 ×TBX calculates the digital marking coefficient SBX of the factory digital information, where e 1 、e 2 is the preset scaling factor;

[0127] The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and digital marking coefficient of the factory digital information, which is specifically:

[0128] By the tenth calculation function JGX = f 1 ×SXX'+f 2 ×SBX calculates the digital supervision coefficient JGX of the factory digital information, where f 1 、f 2 is the preset scale factor.

[0129] In some embodiments, if the factory digital information has an information change frequency BP of 20 within a preset time, an information change frequency threshold PY of 10, and a preset proportionality factor d 1 is 1, then through the seventh calculation function SBX=d 1 ×(BP-PY) calculates the first digital marking coefficient OBX of the factory digital information to be 10;

[0130] If the factory digital information changes within the preset time, the information change amplitude BF is 15, the information change amplitude threshold FY, and the preset proportional factor d 2 is 1, then through the eighth calculation function SBX=d 2 ×(BF-FY) is calculated to obtain the second digital marking coefficient TBX of the factory digital information as 5;

[0131] At this time, if the preset proportional factor e 1 、e 2 is 1, 1, then through the ninth calculation function SBX = e 1 ×OBX+e2 ×TBX calculates the digital marking factor SBX of the factory digital information to be 15;

[0132] If the digital display coefficient SXX' of the factory digital information is 10, the digital marking coefficient SBX of the factory digital information is 15, the preset scaling factor f 1 、f 2 is 1, 0.8, then through the tenth calculation function JGX = f 1 ×SXX'+f 2 ×SBX calculates the digital supervision coefficient JGX of the factory digital information to be 22.

[0133] The remote monitoring information of the target factory is matched with the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information, which is as follows:

[0134] Extracting control information keywords corresponding to the remote control information according to the remote control information of the target factory;

[0135] According to the control information keywords and the factory digital information of the virtual factory model, the word meaning matching analysis is performed to obtain the information word meaning matching degree between the control information keywords and the factory digital information;

[0136] The information word meaning matching degree is evaluated and marked to obtain the information word meaning matching degree XC;

[0137] The first matching coefficient OPX between the control information keyword and the factory digital information is calculated by an eleventh calculation function OPX=β×XC, wherein β is a preset proportional factor;

[0138] According to the control information keywords and the factory digital information of the virtual factory model, the word meaning repetition rate matching analysis is performed to obtain the information word meaning repetition rate of the control information keywords and the factory digital information;

[0139] The information word sense repetition rate is taken and marked to obtain the information word sense repetition rate XF;

[0140] The second matching coefficient TPX between the control information keyword and the factory digital information is calculated by a twelfth calculation function TPX=χ×XF, wherein χ is a preset proportional factor;

[0141] By the thirteenth calculation function XPD = g 1 ×OPX+g 2 ×TPX calculates the information matching degree XPD between remote monitoring information and factory digital information, where g 1 , g 2 is the preset scale factor.

[0142] In some embodiments, if the information meaning matching degree between the control information keyword and the factory digital information is 80%, the information meaning matching degree XC is 80, and if the preset proportional factor β is 0.1, the first matching coefficient OPX between the control information keyword and the factory digital information is calculated by the eleventh calculation function OPX=β×XC to be 8;

[0143] If the information word meaning repetition rate between the control information keyword and the factory digital information is 70%, the information word meaning repetition rate XF is 70, and if the preset proportional factor χ is 0.1, the second matching coefficient TPX between the control information keyword and the factory digital information is calculated by the twelfth calculation function TPX=χ×XF to be 7;

[0144] At this time, if the preset proportional factor g 1 , g 2 is 1, 1, then through the thirteenth calculation function XPD = g 1 ×OPX+g 2 ×TPX calculated that the information matching degree XPD between remote monitoring information and factory digital information is 15.

[0145] According to the information matching degree and the information matching degree threshold, a comparison analysis is performed to obtain the factory digital information that matches the remote control information, and the factory digital information is marked as the target digital information; according to the information matching degree and the information matching degree threshold, the digital control coefficient of the target digital information is obtained, which is specifically:

[0146] If the information matching degree XPD between the remote monitoring information and the factory digital information is less than the information matching degree threshold, the factory digital information does not match the remote monitoring information;

[0147] If the information matching degree XPD between the remote monitoring information and the factory digital information is greater than or equal to the information matching degree threshold, the factory digital information matches the remote monitoring information, and the factory digital information is marked as the target digital information;

[0148] The information matching degree threshold is taken and marked to obtain the information matching degree threshold DY;

[0149] The digital control coefficient KZX of the target digital information is calculated by a fourteenth calculation function KZX=δ×(XPD-DY), wherein δ is a preset proportional factor.

[0150] In some embodiments, if the information matching threshold is 10, the information matching threshold DY is 10. If the preset proportional factor δ is 2, the digital control coefficient KZX of the target digital information calculated by the fourteenth calculation function KZX=δ×(XPD-DY) is 10.

[0151] The supervision control coefficient corresponding to the factory digital information of the virtual factory model is obtained according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information; the supervision control degree of the actual monitoring data of the target factory is obtained according to the supervision control coefficient, specifically:

[0152] By the fifteenth calculation function JKX=h 1 ×JGX+h 2 ×KZX calculates the supervisory control coefficient JKX corresponding to the factory digital information of the virtual factory model, where h 1 、h 2 is the preset scaling factor;

[0153] The degree of supervision and control of the actual monitoring data of the target factory is positively correlated with the supervision and control coefficient JKX corresponding to the factory digital information of the virtual factory model.

[0154] In some embodiments, if the digital supervision coefficient JGX of the target digital information is 20, the digital control coefficient KZX of the target digital information is 10, and the preset proportionality factor h 1 、h 2 is 1, 0.5, then through the fifteenth calculation function JKX = h 1 ×JGX+h 2 ×KZX calculates the supervisory control coefficient JKX corresponding to the factory digital information of the virtual factory model to be 20;

[0155] It should be noted that the larger the supervisory control coefficient JKX corresponding to the factory digital information of the virtual factory model, the greater the supervisory control degree of the actual monitoring data of the target factory.

[0156] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A remote monitoring and control system integrating deep learning and virtual reality, characterized in that: include: Acquisition module: obtains the remote control information of the target factory and the actual monitoring data of the target factory within the preset time; Obtaining factory digital information of the target factory based on the actual monitoring data, and constructing a virtual factory model corresponding to the target factory based on the factory digital information; Obtaining the digital information category corresponding to the factory digital information of the virtual factory model, and the information change parameter of the factory digital information within a preset time; The first analysis module: analyzes the digital information category corresponding to the factory digital information to obtain a first display coefficient of the factory digital information; analyzes the information change parameter of the factory digital information within a preset time to obtain a second display coefficient of the factory digital information; Obtaining a digital display coefficient of factory digital information according to the first display coefficient and the second display coefficient; According to the preset time and the digital information category corresponding to the factory digital information, setting the information change parameter threshold corresponding to the factory digital information of different digital information categories within the preset time; Compare and analyze the information change parameter of the factory digital information within a preset time with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information; The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and the digital marking coefficient of the factory digital information; The second analysis module: performs information matching analysis on the remote monitoring information of the target factory and the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information; Comparing and analyzing the information matching degree with the information matching degree threshold, obtaining the factory digital information matching the remote control information, and marking the factory digital information as the target digital information; Obtaining a digital control coefficient of the target digital information according to the information matching degree and the information matching degree threshold; Supervision and control module: obtains the supervision and control coefficient corresponding to the factory digital information of the virtual factory model according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information; The degree of supervision and control of the actual monitoring data of the target factory is obtained according to the supervision and control coefficient.

2. A remote monitoring and control system for deep learning fusion virtual reality according to claim 1, characterized in that: Acquire the remote control information of the target factory and the actual monitoring data of the target factory within a preset time; obtain the factory digital information of the target factory based on the actual monitoring data, and construct a virtual factory model corresponding to the target factory based on the factory digital information, specifically: Obtaining a remote control instruction of a target factory, and obtaining remote control information of the target factory according to the remote control instruction; A preset virtual model is set, and the factory digital information of the target factory is imported into the preset virtual model to obtain a virtual factory model corresponding to the target factory.

3. A remote monitoring and control system for deep learning fusion virtual reality according to claim 2, characterized in that: The digital information category corresponding to the factory digital information is analyzed to obtain the first display coefficient of the factory digital information; the information change parameter of the factory digital information within a preset time is analyzed to obtain the second display coefficient of the factory digital information, which is specifically: Setting the information weight value corresponding to the factory digital information according to the digital information category corresponding to the factory digital information; The information weight value corresponding to the factory digital information is taken and marked to obtain the information weight value QZ; The first display coefficient OXX of the factory digital information is calculated by a first calculation function OXX=α×QZ, wherein α is a preset proportional factor; The information change parameters include the information change frequency and information change amplitude of the factory digital information within a preset time; The frequency of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change frequency BP; the amplitude of information change of the factory digital information within a preset time is obtained by taking values ​​and marking the information change amplitude BF; The second display coefficient TXX of the factory digital information is calculated by the second calculation function TXX=a1×BP+a2×BF, wherein a1 and a2 are preset proportional factors.

4. The remote monitoring and control system of deep learning fusion virtual reality according to claim 3 is characterized in that: The digital display coefficient of the factory digital information is obtained according to the first display coefficient and the second display coefficient, specifically: The digital display coefficient SXX of the factory digital information is calculated by the third calculation function SXX=b1×OXX+b2×TXX, wherein b1 and b2 are preset proportional factors; Setting display coefficient intervals, each of which corresponds to an interval display weight value; Matching and analyzing the digital display coefficient SXX of the factory digital information with the display coefficient interval to obtain the display coefficient interval where the digital display coefficient SXX of the factory digital information is located; Marking the display coefficient interval as a target display coefficient interval, taking and marking the interval display weight value corresponding to the target display coefficient interval to obtain an interval display weight value XQ; The digital display coefficient SXX' of the factory digital information is calculated by the fourth calculation function SXX'=ε×SXX×XQ, wherein ε is a preset proportional factor.

5. The remote monitoring and control system of deep learning fusion virtual reality according to claim 4 is characterized in that: According to the preset time and the digital information category corresponding to the factory digital information, the information change parameter threshold corresponding to the factory digital information of different digital information categories within the preset time is set, specifically: The information change parameter thresholds include an information change frequency threshold and an information change amplitude threshold; Taking and marking the preset time to obtain the preset time YS; Through the fifth calculation function Calculate and obtain the information change frequency threshold PY corresponding to the factory digital information of different digital information categories within a preset time, where c1 is a preset proportional factor; Through the sixth calculation function The information change amplitude threshold FY corresponding to the factory digital information of different digital information categories within the preset time is calculated, wherein c2 is a preset proportional factor.

6. The remote monitoring and control system of deep learning fusion virtual reality according to claim 5 is characterized in that: The information change parameter of the factory digital information within a preset time is compared and analyzed with the information change parameter threshold to obtain the digital marking coefficient of the factory digital information, specifically: The digital marking coefficients of the factory digital information include a first digital marking coefficient and a second digital marking coefficient; If the information change frequency BP of the factory digital information within the preset time is less than the information change frequency threshold PY, then the factory digital information does not have the first digital marking coefficient; If the information change frequency BP of the factory digital information within the preset time is greater than or equal to the information change frequency threshold PY, then the factory digital information has a first digital marking coefficient; The first digital marking coefficient OBX of the factory digital information is calculated by the seventh calculation function SBX=d1×(BP-PY), wherein d1 is a preset proportional factor; If the information change amplitude BF of the factory digital information within the preset time is less than the information change amplitude threshold FY, then the factory digital information does not have a second digital marking coefficient; If the information change amplitude BF of the factory digital information within the preset time is greater than or equal to the information change amplitude threshold FY, then the factory digital information has a second digital marking coefficient; The second digital marking coefficient TBX of the factory digital information is calculated by an eighth calculation function SBX=d2×(BF-FY), wherein d2 is a preset proportional factor; The digital marking coefficient SBX of the factory digital information is calculated by the ninth calculation function SBX=e1×OBX+e2×TBX, wherein e1 and e2 are preset proportional factors; The digital supervision coefficient of the factory digital information is obtained according to the digital display coefficient and digital marking coefficient of the factory digital information, which is specifically: The digital supervision coefficient JGX of the factory digital information is calculated by the tenth calculation function JGX=f1×SXX′+f2×SBX, wherein f1 and f2 are preset proportional factors.

7. The remote monitoring and control system of deep learning fusion virtual reality according to claim 6 is characterized in that: The remote monitoring information of the target factory is matched with the factory digital information of the virtual factory model to obtain the information matching degree between the remote monitoring information and the factory digital information, which is as follows: Extracting control information keywords corresponding to the remote control information according to the remote control information of the target factory; Performing a word meaning matching analysis based on the control information keywords and the factory digital information of the virtual factory model to obtain the information word meaning matching degree between the control information keywords and the factory digital information; The information word meaning matching degree is evaluated and marked to obtain the information word meaning matching degree XC; The first matching coefficient OPX between the control information keyword and the factory digital information is calculated by an eleventh calculation function OPX=β×XC, wherein β is a preset proportional factor; Performing a word meaning repetition rate matching analysis based on the control information keywords and the factory digital information of the virtual factory model to obtain the information word meaning repetition rate between the control information keywords and the factory digital information; Taking and marking the information word sense repetition rate to obtain the information word sense repetition rate XF; The second matching coefficient TPX between the control information keyword and the factory digital information is calculated by a twelfth calculation function TPX=χ×XF, wherein χ is a preset proportional factor; The information matching degree XPD between the remote monitoring information and the factory digital information is calculated by the thirteenth calculation function XPD=g1×OPX+g2×TPX, wherein g1 and g2 are preset proportional factors.

8. The remote monitoring and control system of deep learning fusion virtual reality according to claim 7 is characterized in that: According to the information matching degree and the information matching degree threshold, a comparison analysis is performed to obtain the factory digital information matching the remote control information, and the factory digital information is marked as the target digital information; according to the information matching degree and the information matching degree threshold, the digital control coefficient of the target digital information is obtained, which is specifically: If the information matching degree XPD between the remote monitoring information and the factory digital information is less than the information matching degree threshold, the factory digital information does not match the remote monitoring information; If the information matching degree XPD between the remote monitoring information and the factory digital information is greater than or equal to the information matching degree threshold, the factory digital information matches the remote monitoring information, and the factory digital information is marked as the target digital information; The information matching degree threshold is taken and marked to obtain the information matching degree threshold DY; The digital control coefficient KZX of the target digital information is calculated by a fourteenth calculation function KZX=δ×(XPD-DY), wherein δ is a preset proportional factor.

9. The remote monitoring and control system of deep learning fusion virtual reality according to claim 8 is characterized in that: The supervision control coefficient corresponding to the factory digital information of the virtual factory model is obtained according to the digital supervision coefficient of the factory digital information and the digital control coefficient of the target digital information; the supervision control degree of the actual monitoring data of the target factory is obtained according to the supervision control coefficient, specifically: The supervisory control coefficient JKX corresponding to the factory digital information of the virtual factory model is calculated by the fifteenth calculation function JKX=h1×JGX+h2×KZX, where h1 and h2 are preset proportional factors; The degree of supervision and control of the actual monitoring data of the target factory is positively correlated with the supervision and control coefficient JKX corresponding to the factory digital information of the virtual factory model.

Images