Intelligent equipment control system and method based on 5G communication

Abstract

The invention discloses an intelligent equipment control system and method based on 5G communication, and belongs to the technical field of intelligent control. According to the method, a prediction model of the cross operation area of an early warning equipment group is established; establishing a prediction model of the time length spent by the first intelligent device to execute the change instruction once and a prediction model of the time length spent by the second intelligent device to execute the change instruction once in the early warning device group; establishing a prediction model of the working duration of the early warning equipment group before the early warning, and establishing a prediction model of the number of times of executing the change instruction of the early warning equipment group; and monitoring the early warning equipment group in real time, calculating to obtain the prediction frequency of executing the change instruction by the early warning equipment group, and when the real-time frequency of executing the change instruction by the early warning equipment group is equal to the prediction frequency, recovering the early warning equipment group to the initial position. The influence between intelligent devices is reduced, and the working efficiency of the intelligent devices is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an intelligent equipment control system and method based on 5G communication. Background Technology

[0002] With the advancement of technology, the application of intelligent equipment has gradually penetrated into various industries, from manufacturing and logistics to construction and agriculture. The use of intelligent equipment has greatly improved production efficiency and safety. These intelligent devices typically use technologies such as sensors and 5G to collect environmental data in real time and make self-adjustments and feedback.

[0003] In many industrial and logistics scenarios, intelligent equipment needs to perform complex collaborations and operations within confined spaces. These devices are often equipped with sensors and intelligent control systems, enabling them to independently assess their surroundings and make corresponding adjustments. Although these devices can sense external collision threats, the risk of collisions still exists when they are working collaboratively due to unstable equipment trajectories or insufficient predictive capabilities. Collisions not only damage equipment but can also affect the efficiency of the entire work chain. To better address this issue, it is essential to leverage the advantages of 5G communication to establish a more refined inter-device collaboration mechanism. This will effectively reduce accidents caused by interference between devices and improve production efficiency and safety. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent device control system and method based on 5G communication to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, the present invention provides the following technical solution: an intelligent device control method based on 5G communication, the method comprising:

[0006] Step S100: Obtain collision warning information of intelligent devices; set two adjacent intelligent devices as a device group, analyze the collision warning information to obtain the warning device group, and determine the intelligent devices that have an influencing relationship;

[0007] Step S200: Analyze the control commands of intelligent devices that have an influence relationship to obtain the characteristic early warning records of the early warning device group; obtain the spacing of the early warning device group and analyze it to obtain the spacing threshold of the early warning device group;

[0008] Step S300: Obtain the area of ​​the cross-operation zone of the early warning equipment group in the characteristic early warning records of the early warning equipment group, and establish a prediction model for the area of ​​the cross-operation zone of the early warning equipment group;

[0009] Step S400: Obtain the time taken for the first intelligent device and the second intelligent device in the early warning device group to execute a change command in the feature early warning record of the early warning device group, and establish a prediction model for the time taken for the first intelligent device to execute a change command and a prediction model for the time taken for the second intelligent device to execute a change command in the early warning device group.

[0010] Step S500: Obtain the working duration data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, establish a prediction model of the working duration of the early warning equipment group before issuing an early warning, obtain the data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establish a prediction model of the number of times the early warning equipment group executes change commands.

[0011] Step S600: Monitor the early warning equipment group in real time, calculate the predicted number of times the early warning equipment group will execute change commands, and when the real-time number of times the early warning equipment group executes change commands equals the predicted number, restore the early warning equipment group to its initial position and re-execute the change commands.

[0012] Furthermore, step S100 includes:

[0013] Step S101: Through the intelligent control system of the intelligent device, remote control of several intelligent devices is performed and the sensors of several intelligent devices are monitored. When the sensors of two or more intelligent devices simultaneously issue collision warning signals, the intelligent control system issues a collision warning. Historical warning records of collision warnings are collected to obtain the intelligent devices that issued collision warnings from all warning records.

[0014] Step S102: Set two adjacent intelligent devices as a device group. When two intelligent devices in the device group issue collision warnings in the same warning record, the device group is a warning device group. Collect the warning device group in a certain warning record, summarize the collected warning device group, and obtain the warning record set of a certain warning device group.

[0015] Step S103: Collect the number of early warning records in the early warning record set of a certain early warning device group, according to the formula:

[0016]

[0017] Among them, U i Let K represent the frequency of the i-th warning device group. i Let U represent the number of warning records in the warning record set of the i-th warning device group, and K represent the total number of warning records. i If the frequency exceeds the threshold, it is determined that the two intelligent devices in the i-th early warning device group have an operational impact relationship.

[0018] The above steps are equivalent to determining whether there is an influence relationship between two intelligent devices. In the intelligent control system of intelligent devices, when an intelligent device encounters an obstacle, it will issue a collision warning. However, there are many types of obstacles, so if adjacent intelligent devices issue collision warnings, it does not necessarily mean that there is an operational influence between the two intelligent devices. Therefore, it is necessary to determine whether there is an influence relationship based on the frequency of the warning device group. This method can more accurately identify the intelligent devices that have an influence relationship.

[0019] Furthermore, step S200 includes:

[0020] Step S201: In a certain early warning record of a certain early warning device group, when both intelligent devices in a certain early warning device group issue an early warning, the control commands issued by the intelligent control systems of the two intelligent devices are collected. When the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature early warning record. In all the early warning records of a certain early warning device group, the feature early warning records of a certain early warning device group are collected to obtain the feature early warning record set of a certain early warning device group.

[0021] Step S202: In a certain feature warning record of a certain warning device group, the distance between the center points of two intelligent devices in a certain warning device group is collected to obtain the distance of a certain warning device group in a certain feature warning record. The distances of a certain warning device group in all feature warning records of a certain warning device group are summarized, and the maximum value in the summative set of distances of a certain warning device group is used as the distance threshold of a certain warning device group.

[0022] Although intelligent devices that have operational impact relationships have been identified, it is not certain that two intelligent devices will affect each other in a certain warning record. Therefore, the warning records need to be filtered to avoid obtaining warning records that have not had an impact, which would lead to a decrease in the accuracy of subsequent calculations.

[0023] The different control commands of the two intelligent devices mean that the control command of the first intelligent device is to control the second intelligent device, and the control command of the second intelligent device is to control the first intelligent device. Only under these circumstances will the two intelligent devices affect each other.

[0024] Furthermore, step S300 includes:

[0025] Step S301: In a certain feature warning record of a certain warning equipment group, the normal operating range of two intelligent devices in a certain warning equipment group is collected, a three-dimensional model of the normal operating range of the two intelligent devices in a certain warning equipment group is established, the three-dimensional models of the two intelligent devices are compared and overlapped, the three-dimensional model of the overlapping part is extracted, and the cross-operation area of ​​a certain warning equipment group in a certain feature warning record of a certain warning equipment group is obtained.

[0026] Step S302: Set the spacing and cross-operation area of ​​a certain early warning equipment group in the same feature early warning record as the cross-operation area data group of that early warning equipment group. Summarize all feature early warning records of a certain early warning equipment group. Perform function fitting on several cross-operation area data groups of a certain early warning equipment group to obtain the regression equation for the cross-operation area of ​​the i-th early warning equipment group:

[0027] Y i =a i ×X i +b i ;

[0028] Among them, X i Y represents the spacing between the i-th early warning device groups. i Let a be the area of ​​the cross-operation zone of the i-th early warning equipment group. i Let b be the first weight of the area of ​​the cross-operation zone of the i-th early warning equipment group. i Let represent the second weight of the cross-operation area of ​​the i-th early warning equipment group, and set the regression equation of the cross-operation area of ​​the i-th early warning equipment group as the prediction model of the cross-operation area of ​​the i-th early warning equipment group.

[0029] Furthermore, step S400 includes:

[0030] Step S401: Designate two intelligent devices in a certain early warning device group as the first intelligent device and the second intelligent device, respectively. Designate the control commands and adjustment commands issued by the intelligent control system executed by the first intelligent device as the change commands executed by the first intelligent device, and designate the control commands and adjustment commands issued by the intelligent control system executed by the second intelligent device as the change commands executed by the second intelligent device.

[0031] Step S402: In a certain feature warning record of a certain warning device group, the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once is collected respectively, so as to obtain the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once in a certain feature warning record;

[0032] Step S403: Summarize all feature warning records of a certain warning device group, and perform function fitting on the time taken by the first intelligent device and the second intelligent device in a certain warning device group to execute a change command once in several feature warning records, to obtain the regression equations for the time taken by the first intelligent device and the second intelligent device in the i-th warning device group to execute a change command once:

[0033] T i1 =c i1 ×P i1 +d i1

[0034] T i2 =c i2 ×P i2 +d i2 ;

[0035] Where P i1 and P i2 T represents the change instructions executed by the first and second intelligent devices in the i-th early warning device group, respectively. i1 and T i2 c represents the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command. i1 and c i2 Let d represent the first weights of the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command, respectively. i1 and d i2 Let represent the second weights of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command, respectively. Let the regression equations of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command be set as the prediction models of the time taken for the first intelligent device to execute a change command and the prediction models of the time taken for the second intelligent device to execute a change command, respectively.

[0036] Because intelligent devices use control commands and adjustment commands most frequently during operation, and both types of commands can change the running time of the intelligent device, it is necessary to analyze these two types of commands to provide data analysis for subsequent determination of whether initialization is required.

[0037] Furthermore, step S500 includes:

[0038] Step S501: In a certain feature warning record of a certain warning equipment group, obtain the working time of the certain warning equipment group before issuing the warning. Set the working time of a certain warning equipment group and the area of ​​the cross-operation area in the same feature warning record as the working time data group of a certain warning equipment group. Collect all feature warning records of a certain warning equipment group to obtain several working time data groups of warning equipment groups. Perform function fitting to obtain the regression equation of the working time of the i-th warning equipment group before issuing the warning:

[0039] T i =n i ×Y i +m i ;

[0040] Among them, T i Let n represent the working time of the i-th early warning equipment group before issuing an early warning. i Let m represent the first weight of the working time of the i-th early warning device group before issuing an early warning. i Let represent the second weight of the working time of the i-th early warning equipment group before issuing an early warning. Let the regression equation of the working time of the i-th early warning equipment group before issuing an early warning be set as the prediction model of the working time of the i-th early warning equipment group before issuing an early warning.

[0041] Step S502: For a given feature-based early warning record, define the working time of a certain early warning device group before issuing an early warning, the cross-operation area model, and the time taken for the first and second intelligent devices to execute a change command once as the data group for that early warning device group. Collect all feature-based early warning records for that early warning device group to obtain several data groups for different early warning device groups. Perform function fitting to obtain the regression equation for the number of times the i-th early warning device group executes a change command:

[0042]

[0043] Among them, Q i w represents the number of times the i-th early warning device group executes the change command. i Let z be the first weight representing the number of times the i-th early warning device group executes the change command. i The second weight is represented as the number of times the i-th early warning equipment group executes change commands. The regression equation for the number of times the i-th early warning equipment group executes change commands is set as the prediction model for the number of times the i-th early warning equipment group executes change commands.

[0044] The above steps are necessary because the early warning equipment group may have already been working for some time when it issues an early warning. Since the size of the cross-operation area is different, the working time may also be different. Therefore, it is necessary to predict the working time to provide data support for subsequent analysis on whether to initialize.

[0045] Furthermore, step S600 includes:

[0046] Step S601: Real-time monitoring of the i-th early warning device group. When the control commands of the i-th early warning device group are different, the real-time spacing of the i-th early warning device group is collected. When the real-time spacing of the i-th early warning device group does not exceed the spacing threshold of the i-th early warning device group, the real-time spacing is input into the prediction model of the cross-operation area of ​​the i-th early warning device group to obtain the predicted area of ​​the cross-operation area of ​​the i-th early warning device group.

[0047] Step S602: Input the predicted area of ​​the cross-operation area into the prediction model of the working time of the i-th early warning equipment group before issuing the early warning, and obtain the predicted working time of the i-th early warning equipment group before issuing the early warning;

[0048] Step S603: Obtain the change instructions executed by the first intelligent device and the second intelligent device in the i-th early warning device group, and input them into the prediction model of the time taken for the first intelligent device to execute a change instruction and the prediction model of the time taken for the second intelligent device to execute a change instruction in the i-th early warning device group, so as to obtain the predicted time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change instruction.

[0049] Step S604: Input the predicted area of ​​the cross-operation area of ​​the i-th early warning equipment group, the predicted working time before issuing the early warning, and the predicted time spent by the first intelligent device and the second intelligent device to execute a change command once into the prediction model of the number of times the i-th early warning equipment group executes the change command, and obtain the predicted number of times the i-th early warning equipment group executes the change command. When the real-time number of times the i-th early warning equipment group executes the change command is equal to the predicted number, restore the i-th early warning equipment group to the initial position and re-execute the change command.

[0050] The control commands of the early warning equipment group are analyzed because if the commands do not conform to the control commands, no collision warning will occur between the early warning equipment groups. The number of times the early warning equipment group executes the change command prediction is calculated. Since the two intelligent devices in the early warning equipment group execute the change command differently, the time spent is also different. Before the number of times the early warning equipment group executes the change command equals the prediction number, they work simultaneously. When the number of times the early warning equipment group executes the change command equals the prediction number, it is necessary to restore the initialization and recalculate and judge to avoid the two intelligent devices issuing collision warnings during operation, which would lead to a decrease in the operation efficiency of the intelligent equipment.

[0051] To better implement the above method, an intelligent equipment control system based on 5G communication is also proposed. The system includes a module for determining the influence relationship, a spacing threshold module, a module for predicting the area of ​​the cross-operation zone, a module for calculating the duration of change instructions, a module for calculating the number of change instructions, and a real-time monitoring module.

[0052] The module for determining the relationship of influence is as follows: it acquires collision warning information of intelligent devices; it sets two adjacent intelligent devices as a device group, analyzes the collision warning information to obtain the warning device group, and determines the intelligent devices that have an influence relationship.

[0053] Spacing threshold module: Analyzes control commands of intelligent devices with interrelationships to obtain characteristic early warning records of the early warning device group; obtains the spacing of the early warning device group and analyzes it to obtain the spacing threshold of the early warning device group;

[0054] Cross-operation area prediction module: Obtain the cross-operation area of ​​the early warning equipment group from the characteristic early warning records of the early warning equipment group, and establish a prediction model for the cross-operation area of ​​the early warning equipment group;

[0055] Change command time module: Obtain the time taken for the first and second intelligent devices in the early warning device group to execute a change command once in the feature early warning record of the early warning device group, and establish a prediction model for the time taken for the first intelligent device to execute a change command once in the early warning device group and a prediction model for the time taken for the second intelligent device to execute a change command once in the early warning device group;

[0056] The module for the number of times a change command is executed is as follows: It obtains the working time data of the early warning equipment in the characteristic early warning record of the early warning equipment group, establishes a prediction model of the working time of the early warning equipment group before issuing an early warning, obtains the data of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establishes a prediction model of the number of times the early warning equipment group executes change commands.

[0057] Real-time monitoring module: Monitors the early warning equipment group in real time, calculates the predicted number of times the early warning equipment group will execute change commands, and restores the early warning equipment group to its initial position and re-executes the change commands when the real-time number of times the early warning equipment group executes change commands equals the predicted number.

[0058] Furthermore, the spacing threshold module includes an analysis feature warning record unit and a spacing threshold judgment unit;

[0059] Feature-based early warning record unit: When two intelligent devices in a certain early warning device group issue early warnings, the control commands issued by the intelligent control systems of the two intelligent devices are collected. When the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature-based early warning record.

[0060] The distance threshold unit is determined by collecting the distance between the center points of two intelligent devices in a certain early warning device group, summarizing the distances of a certain early warning device group in all feature early warning records of the group, and taking the maximum value in the summarized distance set of the group as the distance threshold of the group.

[0061] Furthermore, the real-time monitoring module includes a unit for calculating the number of predictions and a judgment unit;

[0062] Calculation of Execution Prediction Count Unit: In the real-time data of the intelligent control system of intelligent equipment, the early warning equipment group is monitored in real time, and the predicted number of execution changes of the early warning equipment group is obtained through the prediction model of the number of execution changes of the early warning equipment group;

[0063] Judgment Unit: When the number of times the early warning equipment group executes the change command in real time equals the number of times it is predicted, the early warning equipment group is restored to its initial position and the change command is executed again.

[0064] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: Collision warning information of intelligent devices is obtained from the historical data of the intelligent control system of intelligent devices; the collision warning information is analyzed to determine intelligent devices with influencing relationships, which can more accurately identify such devices; the control commands of the intelligent devices with influencing relationships are analyzed to obtain a set of characteristic warning records for the warning device group, which filters the warning records and ensures the accuracy of subsequent data analysis; the spacing between the warning device groups is obtained, and the spacing threshold of the warning device groups is analyzed; the area of ​​the cross-operation zone of the warning device groups in the characteristic warning records of the warning device groups is obtained, and a prediction model for the area of ​​the cross-operation zone of the warning device groups is established. The system establishes predictive models for the time taken for the first intelligent device in the early warning equipment group to execute a change command, and for the time taken for the second intelligent device to execute a change command. It also establishes predictive models for the working time of the early warning equipment group before issuing an early warning, and for the number of times the early warning equipment group executes change commands. These predictive models provide data support for analyzing whether to restore initialization. The system performs real-time monitoring of the early warning equipment group, calculates the predicted number of times the early warning equipment group executes change commands, and restores the early warning equipment group to its initial position and re-executes the change commands when the real-time number of times the early warning equipment group executes change commands equals the predicted number. This prevents collision warnings between the two intelligent devices during operation, which could lead to a decrease in the operating efficiency of the intelligent equipment. Attached Figure Description

[0065] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0066] Figure 1 This is a flowchart illustrating an intelligent device control method based on 5G communication according to the present invention. Detailed Implementation

[0067] Please see Figure 1 The present invention provides a technical solution: an intelligent device control method based on 5G communication, the method comprising:

[0068] Step S100: Obtain collision warning information of intelligent devices; set two adjacent intelligent devices as a device group, analyze the collision warning information to obtain the warning device group, and determine the intelligent devices that have an influencing relationship;

[0069] Step S100 includes:

[0070] Step S101: Through the intelligent control system of the intelligent device, remote control of several intelligent devices is performed and the sensors of several intelligent devices are monitored. When the sensors of two or more intelligent devices simultaneously issue collision warning signals, the intelligent control system issues a collision warning. Historical warning records of collision warnings are collected to obtain the intelligent devices that issued collision warnings from all warning records.

[0071] Step S102: Set two adjacent intelligent devices as a device group. When two intelligent devices in the device group issue collision warnings in the same warning record, the device group is a warning device group. Collect the warning device group in a certain warning record, summarize the collected warning device group, and obtain the warning record set of a certain warning device group.

[0072] Step S103: Collect the number of early warning records in the early warning record set of a certain early warning device group, according to the formula:

[0073]

[0074] Among them, U i Let K represent the frequency of the i-th warning device group. i Let U represent the number of warning records in the warning record set of the i-th warning device group, and K represent the total number of warning records. i If the frequency exceeds the threshold, it is determined that the two intelligent devices in the i-th early warning device group have an operational impact relationship.

[0075] Step S200: Analyze the control commands of intelligent devices that have an influence relationship to obtain the characteristic early warning records of the early warning device group; obtain the spacing of the early warning device group and analyze it to obtain the spacing threshold of the early warning device group;

[0076] Step S200 includes:

[0077] Step S201: In a certain early warning record of a certain early warning device group, when both intelligent devices in a certain early warning device group issue an early warning, the control commands issued by the intelligent control systems of the two intelligent devices are collected. When the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature early warning record. In all the early warning records of a certain early warning device group, the feature early warning records of a certain early warning device group are collected to obtain the feature early warning record set of a certain early warning device group.

[0078] For example, a and b, c and d are two intelligent devices that have an influence relationship. a and b are the first warning device group, and c and d are the second warning device group. In the first warning record, the control command of intelligent device a is directed to b, the control command of intelligent device b is directed to a, the control command of intelligent device c is directed to d in the opposite direction, and the control command of intelligent device d is directed to c. Then the characteristic warning record set of the first warning device group is {the first warning record}.

[0079] Step S202: In a certain feature warning record of a certain warning device group, the distance between the center points of two intelligent devices in the certain warning device group is collected to obtain the distance of a certain warning device group in a certain feature warning record. The distances of a certain warning device group in all feature warning records of a certain warning device group are summarized, and the maximum value in the summative set of distances of a certain warning device group is taken as the distance threshold of a certain warning device group.

[0080] Step S300: Obtain the area of ​​the cross-operation zone of the early warning equipment group in the characteristic early warning records of the early warning equipment group, and establish a prediction model for the area of ​​the cross-operation zone of the early warning equipment group;

[0081] Step S300 includes:

[0082] Step S301: In a certain feature warning record of a certain warning equipment group, the normal operating range of two intelligent devices in a certain warning equipment group is collected, a three-dimensional model of the normal operating range of the two intelligent devices in a certain warning equipment group is established, the three-dimensional models of the two intelligent devices are compared and overlapped, the three-dimensional model of the overlapping part is extracted, and the cross-operation area of ​​a certain warning equipment group in a certain feature warning record of a certain warning equipment group is obtained.

[0083] Step S302: Set the spacing and cross-operation area of ​​a certain early warning equipment group in the same feature early warning record as the cross-operation area data group of that early warning equipment group. Summarize all feature early warning records of a certain early warning equipment group. Perform function fitting on several cross-operation area data groups of a certain early warning equipment group to obtain the regression equation for the cross-operation area of ​​the i-th early warning equipment group:

[0084] Y i =a i ×X i +b i ;

[0085] Among them, X i Y represents the spacing between the i-th early warning device groups. i Let a be the area of ​​the cross-operation zone of the i-th early warning equipment group. i Let b be the first weight of the area of ​​the cross-operation zone of the i-th early warning equipment group. i Let represent the second weight of the cross-operation area of ​​the i-th early warning equipment group, and set the regression equation of the cross-operation area of ​​the i-th early warning equipment group as the prediction model of the cross-operation area of ​​the i-th early warning equipment group.

[0086] Step S400: Obtain the time taken for the first intelligent device and the second intelligent device in the early warning device group to execute a change command in the feature early warning record of the early warning device group, and establish a prediction model for the time taken for the first intelligent device to execute a change command and a prediction model for the time taken for the second intelligent device to execute a change command in the early warning device group.

[0087] Step S400 includes:

[0088] Step S401: Designate two intelligent devices in a certain early warning device group as the first intelligent device and the second intelligent device, respectively. Designate the control commands and adjustment commands issued by the intelligent control system executed by the first intelligent device as the change commands executed by the first intelligent device, and designate the control commands and adjustment commands issued by the intelligent control system executed by the second intelligent device as the change commands executed by the second intelligent device.

[0089] Step S402: In a certain feature warning record of a certain warning device group, the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once is collected respectively, so as to obtain the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once in a certain feature warning record;

[0090] Step S403: Summarize all feature warning records of a certain warning device group, and perform function fitting on the time taken by the first intelligent device and the second intelligent device in a certain warning device group to execute a change command once in several feature warning records, to obtain the regression equations for the time taken by the first intelligent device and the second intelligent device in the i-th warning device group to execute a change command once:

[0091] T i1 =c i1 ×P i1 +d i1

[0092] T i2 =c i2 ×P i2 +d i2 ;

[0093] Where P i1 and P i2 T represents the change instructions executed by the first and second intelligent devices in the i-th early warning device group, respectively. i1 and T i2 c represents the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command. i1 and c i2 Let d represent the first weights of the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command, respectively. i1 and d i2 Let represent the second weights of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command, respectively. Let the regression equations of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command be set as the prediction models of the time taken for the first intelligent device to execute a change command and the prediction models of the time taken for the second intelligent device to execute a change command, respectively.

[0094] Step S500: Obtain the working duration data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, establish a prediction model of the working duration of the early warning equipment group before issuing an early warning, obtain the data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establish a prediction model of the number of times the early warning equipment group executes change commands.

[0095] Step S500 includes:

[0096] Step S501: In a certain feature warning record of a certain warning equipment group, obtain the working time of the certain warning equipment group before issuing the warning. Set the working time of a certain warning equipment group and the area of ​​the cross-operation area in the same feature warning record as the working time data group of a certain warning equipment group. Collect all feature warning records of a certain warning equipment group to obtain several working time data groups of warning equipment groups. Perform function fitting to obtain the regression equation of the working time of the i-th warning equipment group before issuing the warning:

[0097] T i =n i ×Y i +m i ;

[0098] Among them, T i Let n represent the working time of the i-th early warning equipment group before issuing an early warning. i Let m represent the first weight of the working time of the i-th early warning device group before issuing an early warning. i Let represent the second weight of the working time of the i-th early warning equipment group before issuing an early warning. Let the regression equation of the working time of the i-th early warning equipment group before issuing an early warning be set as the prediction model of the working time of the i-th early warning equipment group before issuing an early warning.

[0099] Step S502: For a given feature-based early warning record, define the working time of a certain early warning device group before issuing an early warning, the cross-operation area model, and the time taken for the first and second intelligent devices to execute a change command once as the data group for that early warning device group. Collect all feature-based early warning records for that early warning device group to obtain several data groups for different early warning device groups. Perform function fitting to obtain the regression equation for the number of times the i-th early warning device group executes a change command:

[0100]

[0101] Among them, Q i w represents the number of times the i-th early warning device group executes the change command. i Let z be the first weight representing the number of times the i-th early warning device group executes the change command. i The second weight is represented as the number of times the i-th early warning equipment group executes change commands. The regression equation for the number of times the i-th early warning equipment group executes change commands is set as the prediction model for the number of times the i-th early warning equipment group executes change commands.

[0102] Step S600: Monitor the early warning equipment group in real time, calculate the predicted number of times the early warning equipment group will execute change commands, and when the real-time number of times the early warning equipment group executes change commands equals the predicted number, restore the early warning equipment group to its initial position and re-execute the change commands.

[0103] Step S600 includes:

[0104] Step S601: Real-time monitoring of the i-th early warning device group. When the control commands of the i-th early warning device group are different, the real-time spacing of the i-th early warning device group is collected. When the real-time spacing of the i-th early warning device group does not exceed the spacing threshold of the i-th early warning device group, the real-time spacing is input into the prediction model of the cross-operation area of ​​the i-th early warning device group to obtain the predicted area of ​​the cross-operation area of ​​the i-th early warning device group.

[0105] Step S602: Input the predicted area of ​​the cross-operation area into the prediction model of the working time of the i-th early warning equipment group before issuing the early warning, and obtain the predicted working time of the i-th early warning equipment group before issuing the early warning;

[0106] Step S603: Obtain the change instructions executed by the first intelligent device and the second intelligent device in the i-th early warning device group, and input them into the prediction model of the time taken for the first intelligent device to execute a change instruction and the prediction model of the time taken for the second intelligent device to execute a change instruction in the i-th early warning device group, so as to obtain the predicted time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change instruction.

[0107] Step S604: Input the predicted area of ​​the cross-operation zone of the i-th early warning equipment group, the predicted working time before issuing the early warning, and the predicted time spent by the first intelligent device and the second intelligent device to execute a change command once into the prediction model of the number of times the i-th early warning equipment group executes the change command, and obtain the predicted number of times the i-th early warning equipment group executes the change command. When the real-time number of times the i-th early warning equipment group executes the change command is equal to the predicted number, restore the i-th early warning equipment group to the initial position and re-execute the change command.

[0108] To better implement the above method, an intelligent equipment control system based on 5G communication is also proposed. The system includes a module for determining the influence relationship, a spacing threshold module, a module for predicting the area of ​​the cross-operation zone, a module for calculating the duration of change instructions, a module for calculating the number of change instructions, and a real-time monitoring module.

[0109] The module for determining the relationship of influence is as follows: it acquires collision warning information of intelligent devices; it sets two adjacent intelligent devices as a device group, analyzes the collision warning information to obtain the warning device group, and determines the intelligent devices that have an influence relationship.

[0110] Spacing threshold module: Analyzes control commands of intelligent devices with interrelationships to obtain characteristic early warning records of the early warning device group; obtains the spacing of the early warning device group and analyzes it to obtain the spacing threshold of the early warning device group;

[0111] The spacing threshold module includes an analysis feature warning record unit and a spacing threshold judgment unit;

[0112] Feature-based early warning record unit: When two intelligent devices in a certain early warning device group issue early warnings, the control commands issued by the intelligent control systems of the two intelligent devices are collected. When the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature-based early warning record.

[0113] The distance threshold unit is determined by collecting the distance between the center points of two intelligent devices in a certain early warning device group, summarizing the distances of a certain early warning device group in all feature early warning records of a certain early warning device group, and taking the maximum value in the summarized distance set of a certain early warning device group as the distance threshold of a certain early warning device group.

[0114] Cross-operation area prediction module: Obtain the cross-operation area of ​​the early warning equipment group from the characteristic early warning records of the early warning equipment group, and establish a prediction model for the cross-operation area of ​​the early warning equipment group;

[0115] Change command time module: Obtain the time taken for the first and second intelligent devices in the early warning device group to execute a change command once in the feature early warning record of the early warning device group, and establish a prediction model for the time taken for the first intelligent device to execute a change command once in the early warning device group and a prediction model for the time taken for the second intelligent device to execute a change command once in the early warning device group;

[0116] The module for the number of times a change command is executed is as follows: It obtains the working time data of the early warning equipment in the characteristic early warning record of the early warning equipment group, establishes a prediction model of the working time of the early warning equipment group before issuing an early warning, obtains the data of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establishes a prediction model of the number of times the early warning equipment group executes change commands.

[0117] Real-time monitoring module: Monitors the early warning equipment group in real time, calculates the predicted number of times the early warning equipment group will execute change commands, and restores the early warning equipment group to its initial position and re-executes the change commands when the real-time number of times the early warning equipment group executes change commands equals the predicted number.

[0118] The real-time monitoring module includes a unit for calculating the number of predictions and a judgment unit.

[0119] Calculation of Execution Prediction Count Unit: In the real-time data of the intelligent control system of intelligent equipment, the early warning equipment group is monitored in real time, and the predicted number of execution changes of the early warning equipment group is obtained through the prediction model of the number of execution changes of the early warning equipment group;

[0120] Judgment Unit: When the number of times the early warning equipment group executes the change command in real time equals the number of times it is predicted, the early warning equipment group is restored to its initial position and the change command is executed again.

[0121] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0122] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for controlling intelligent devices based on 5G communication, characterized in that, The methods include: Step S100: Obtain collision warning information of intelligent devices; set two adjacent intelligent devices as a device group, analyze the collision warning information to obtain the warning device group, and determine the intelligent devices that have an influencing relationship; Step S200: Analyze the control commands of intelligent devices that have an influence relationship to obtain the characteristic early warning records of the early warning device group; obtain the spacing of the early warning device group and analyze it to obtain the spacing threshold of the early warning device group; Step S300: Obtain the area of ​​the cross-operation zone of the early warning equipment group in the characteristic early warning records of the early warning equipment group, and establish a prediction model for the area of ​​the cross-operation zone of the early warning equipment group; Step S400: Obtain the time taken for the first intelligent device and the second intelligent device in the early warning device group to execute a change command in the feature early warning record of the early warning device group, and establish a prediction model for the time taken for the first intelligent device to execute a change command and a prediction model for the time taken for the second intelligent device to execute a change command in the early warning device group. Step S500: Obtain the working duration data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, establish a prediction model of the working duration of the early warning equipment group before issuing an early warning, obtain the data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establish a prediction model of the number of times the early warning equipment group executes change commands. Step S600: Monitor the early warning equipment group in real time, calculate the predicted number of times the early warning equipment group will execute change commands, and when the real-time number of times the early warning equipment group executes change commands equals the predicted number, restore the early warning equipment group to its initial position and re-execute the change commands.

2. The intelligent device control method based on 5G communication according to claim 1, characterized in that, Step S100 includes the following steps: Step S101: Through the intelligent control system of the intelligent device, remote control of several intelligent devices is performed and the sensors of several intelligent devices are monitored. When the sensors of two or more intelligent devices simultaneously issue collision warning signals, the intelligent control system issues a collision warning. Historical warning records of collision warnings are collected to obtain the intelligent devices that issued collision warnings from all warning records. Step S102: Set two adjacent intelligent devices as a device group. When two intelligent devices in the device group issue collision warnings in the same warning record, the device group is a warning device group. Collect the warning device group in a certain warning record, summarize the collected warning device group, and obtain the warning record set of a certain warning device group. Step S103: Collect the number of early warning records in the early warning record set of a certain early warning device group, according to the formula: Among them, U i Let K represent the frequency of the i-th warning device group. i Let U represent the number of warning records in the warning record set of the i-th warning device group, and K represent the total number of warning records. i If the frequency exceeds the threshold, it is determined that the two intelligent devices in the i-th early warning device group have an operational impact relationship.

3. The intelligent device control method based on 5G communication according to claim 2, characterized in that, Step S200 includes the following steps: Step S201: In a certain early warning record of a certain early warning device group, when both intelligent devices in a certain early warning device group issue an early warning, the control commands issued by the intelligent control systems of the two intelligent devices are collected. When the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature early warning record. In all the early warning records of a certain early warning device group, the feature early warning records of a certain early warning device group are collected to obtain the feature early warning record set of a certain early warning device group. Step S202: In a certain feature warning record of a certain warning device group, the distance between the center points of two intelligent devices in the certain warning device group is collected to obtain the distance of a certain warning device group in a certain feature warning record. The distances of a certain warning device group in all feature warning records of a certain warning device group are summarized, and the maximum value in the summative set of distances of a certain warning device group is taken as the distance threshold of a certain warning device group.

4. The intelligent device control method based on 5G communication according to claim 3, characterized in that, Step S300 includes the following steps: Step S301: In a certain feature warning record of a certain warning equipment group, the normal operating range of two intelligent devices in a certain warning equipment group is collected, a three-dimensional model of the normal operating range of the two intelligent devices in a certain warning equipment group is established, the three-dimensional models of the two intelligent devices are compared and overlapped, the three-dimensional model of the overlapping part is extracted, and the cross-operation area of ​​a certain warning equipment group in a certain feature warning record of a certain warning equipment group is obtained. Step S302: Set the spacing and cross-operation area of ​​a certain early warning equipment group in the same feature early warning record as the cross-operation area data group of that early warning equipment group. Summarize all feature early warning records of a certain early warning equipment group. Perform function fitting on several cross-operation area data groups of a certain early warning equipment group to obtain the regression equation for the cross-operation area of ​​the i-th early warning equipment group: AND i =a i ×X i +b i ; Among them, X i Y represents the spacing between the i-th early warning device groups. i Let a be the area of ​​the cross-operation zone of the i-th early warning equipment group. i Let b be the first weight of the cross-operation area of ​​the i-th early warning equipment group. i Let represent the second weight of the cross-operation area of ​​the i-th early warning equipment group, and set the regression equation of the cross-operation area of ​​the i-th early warning equipment group as the prediction model of the cross-operation area of ​​the i-th early warning equipment group.

5. The intelligent device control method based on 5G communication according to claim 4, characterized in that, Step S400 includes the following steps: Step S401: Designate two intelligent devices in a certain early warning device group as the first intelligent device and the second intelligent device, respectively. Designate the control commands and adjustment commands issued by the intelligent control system executed by the first intelligent device as the change commands executed by the first intelligent device, and designate the control commands and adjustment commands issued by the intelligent control system executed by the second intelligent device as the change commands executed by the second intelligent device. Step S402: In a certain feature warning record of a certain warning device group, the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once is collected respectively, so as to obtain the time taken for the first intelligent device and the second intelligent device in the certain warning device group to execute a change command once in a certain feature warning record; Step S403: Summarize all feature warning records of a certain warning device group, and perform function fitting on the time taken by the first intelligent device and the second intelligent device in a certain warning device group to execute a change command once in several feature warning records, to obtain the regression equations for the time taken by the first intelligent device and the second intelligent device in the i-th warning device group to execute a change command once: T i1 =c i1 ×P i1 +d i1 T i2 =c i2 ×P i2 +d i2 ; Where P i1 and P i2 T represents the change instructions executed by the first and second intelligent devices in the i-th early warning device group, respectively. i1 and T i2 c represents the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command. i1 and c i2 Let d represent the first weights of the time taken for the first and second intelligent devices in the i-th early warning device group to execute a change command, respectively. i1 and d i2 Let represent the second weights of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command, respectively. Let the regression equations of the time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change command be set as the prediction models of the time taken for the first intelligent device to execute a change command and the prediction models of the time taken for the second intelligent device to execute a change command, respectively.

6. The intelligent device control method based on 5G communication according to claim 5, characterized in that, Step S500 includes the following steps: Step S501: In a certain feature warning record of a certain warning equipment group, obtain the working time of the certain warning equipment group before issuing the warning. Set the working time of a certain warning equipment group and the area of ​​the cross-operation area in the same feature warning record as the working time data group of a certain warning equipment group. Collect all feature warning records of a certain warning equipment group to obtain several working time data groups of warning equipment groups. Perform function fitting to obtain the regression equation of the working time of the i-th warning equipment group before issuing the warning: T i =n i ×Y i +m i ; Among them, T i Let n represent the working time of the i-th early warning equipment group before issuing an early warning. i Let m represent the first weight of the working time of the i-th early warning device group before issuing an early warning. i Let represent the second weight of the working time of the i-th early warning equipment group before issuing an early warning. Let the regression equation of the working time of the i-th early warning equipment group before issuing an early warning be set as the prediction model of the working time of the i-th early warning equipment group before issuing an early warning. Step S502: For a given feature-based early warning record, define the working time of a certain early warning device group before issuing an early warning, the cross-operation area model, and the time taken for the first and second intelligent devices to execute a change command once as the data group for that early warning device group. Collect all feature-based early warning records for that early warning device group to obtain several data groups for different early warning device groups. Perform function fitting to obtain the regression equation for the number of times the i-th early warning device group executes a change command: Among them, Q i w represents the number of times the i-th early warning device group executes the change command. i Let z be the first weight representing the number of times the i-th early warning device group executes the change command. i The second weight is represented as the number of times the i-th early warning equipment group executes change commands. The regression equation for the number of times the i-th early warning equipment group executes change commands is set as the prediction model for the number of times the i-th early warning equipment group executes change commands.

7. The intelligent device control method based on 5G communication according to claim 6, characterized in that, Step S600 includes the following steps: Step S601: Real-time monitoring of the i-th early warning device group. When the control commands of the i-th early warning device group are different, the real-time spacing of the i-th early warning device group is collected. When the real-time spacing of the i-th early warning device group does not exceed the spacing threshold of the i-th early warning device group, the real-time spacing is input into the prediction model of the cross-operation area of ​​the i-th early warning device group to obtain the predicted area of ​​the cross-operation area of ​​the i-th early warning device group. Step S602: Input the predicted area of ​​the cross-operation area into the prediction model of the working time of the i-th early warning equipment group before issuing the early warning, and obtain the predicted working time of the i-th early warning equipment group before issuing the early warning; Step S603: Obtain the change instructions executed by the first intelligent device and the second intelligent device in the i-th early warning device group, and input them into the prediction model of the time taken for the first intelligent device to execute a change instruction and the prediction model of the time taken for the second intelligent device to execute a change instruction in the i-th early warning device group, so as to obtain the predicted time taken for the first intelligent device and the second intelligent device in the i-th early warning device group to execute a change instruction. Step S604: Input the predicted area of ​​the cross-operation zone of the i-th early warning equipment group, the predicted working time before issuing the early warning, and the predicted time spent by the first intelligent device and the second intelligent device to execute a change command once into the prediction model of the number of times the i-th early warning equipment group executes the change command, and obtain the predicted number of times the i-th early warning equipment group executes the change command. When the real-time number of times the i-th early warning equipment group executes the change command is equal to the predicted number, restore the i-th early warning equipment group to the initial position and re-execute the change command.

8. A 5G-based intelligent device control system, used to implement the 5G-based intelligent device control method according to any one of claims 1-7, characterized in that, The system includes: a module for determining the influence relationship, a spacing threshold module, a module for predicting the area of ​​the cross-operation zone, a module for calculating the duration of change instructions, a module for calculating the number of change instructions, and a real-time monitoring module. The module for determining the influence relationship: acquires collision warning information of intelligent devices; sets two adjacent intelligent devices as a device group, analyzes the collision warning information to obtain the warning device group, and determines the intelligent devices that have an influence relationship; The spacing threshold module: analyzes the control commands of intelligent devices that have an influence relationship to obtain the characteristic early warning records of the early warning device group; obtains the spacing of the early warning device group and analyzes it to obtain the spacing threshold of the early warning device group; The cross-operation area prediction module: obtains the cross-operation area of ​​the early warning equipment group from the characteristic early warning records of the early warning equipment group, and establishes a prediction model for the cross-operation area of ​​the early warning equipment group; The change instruction time-consuming module: respectively obtains the time spent by the first intelligent device and the second intelligent device in the early warning device group to execute a change instruction once in the feature early warning record of the early warning device group, and establishes a prediction model for the time spent by the first intelligent device in the early warning device group to execute a change instruction once and a prediction model for the time spent by the second intelligent device in the early warning device group to execute a change instruction once. The module for the number of times a change command is executed: acquires the working time data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, establishes a prediction model of the working time of the early warning equipment group before issuing an early warning, acquires the data group of the early warning equipment in the characteristic early warning record of the early warning equipment group, and establishes a prediction model of the number of times the early warning equipment group executes change commands. The real-time monitoring module monitors the early warning equipment group in real time, calculates the predicted number of times the early warning equipment group will execute change commands, and restores the early warning equipment group to its initial position and re-executes the change commands when the real-time number of times the early warning equipment group executes change commands equals the predicted number.

9. A smart device control system based on 5G communication according to claim 8, characterized in that, The spacing threshold module includes an analysis feature early warning recording unit and a spacing threshold judgment unit; The feature-based early warning recording unit: when two intelligent devices in a certain early warning device group issue early warnings, it collects the control commands issued by the intelligent control systems of the two intelligent devices; when the control commands issued by the intelligent control systems of the two intelligent devices are different, the early warning record is a feature-based early warning record. The distance threshold unit for judging distances: collects the distance between the center points of two intelligent devices in a certain early warning device group, summarizes the distances of a certain early warning device group in all feature early warning records of a certain early warning device group, and takes the maximum value in the summative distance set of a certain early warning device group as the distance threshold of a certain early warning device group.

10. A smart device control system based on 5G communication according to claim 8, characterized in that, The real-time monitoring module includes a unit for calculating the number of prediction executions and a judgment unit; The calculation and execution prediction number unit: In the real-time data of the intelligent control system of the intelligent device, the early warning device group is monitored in real time, and the predicted number of execution changes of the early warning device group is obtained through the prediction model of the number of execution changes of the early warning device group; The judgment unit: when the number of times the early warning equipment group executes the change command in real time is equal to the number of times it is predicted, it restores the early warning equipment group to its initial position and re-executes the change command.

Images