A sustainable communication optimization processing method in a limited connection environment

Abstract

The present invention relates to the field of communication optimization technology, and discloses a sustainable communication optimization processing method under a restricted connection environment, the method comprising the following steps: obtaining communication optimization information, the communication optimization information including information in a metal mine cave, equipment information in the mine cave, and employee operation information in the mine cave; constructing plane data and serial data streams based on the communication optimization information; and inputting the plane data and serial data streams constructed by the communication optimization information into a communication optimization model. The present invention selects the best channel according to the real-time environmental conditions through a dynamic channel selection module, avoids high-interference channels, utilizes multipath transmission and transmission path avoidance, effectively utilizes the reflection and refraction paths in the multipath effect, and targets the electromagnetic interference generated by mechanical equipment and cable networks, through equipment status monitoring and environmental noise level monitoring, improves the effectiveness of the signal coverage range of the communication equipment, and reduces the problem of limited communication in the metal mine cave.

Description

Technical Field

[0001] The present invention relates to the field of communication optimization, and more specifically, to a sustainable communication optimization processing method in a restricted connection environment. Background Art

[0002] The inner wall of a metal mine contains a large amount of metal elements, which are highly reflective and absorptive. At the same time, during the mining process, a large number of mechanical equipment and complex cable circuits are used in the metal mine, which will bring obvious electromagnetic interference and affect the signal optimization of existing hybrid communications. This will cause severe attenuation of wireless signals during propagation, reduce signal coverage, and limit communication distance, resulting in limited communications within the metal mine. Summary of the invention

[0003] The present invention provides a sustainable communication optimization processing method in a restricted connection environment to solve the technical problems in related technologies.

[0004] The present invention provides a sustainable communication optimization processing method in a restricted connection environment, comprising the following steps:

[0005] Step 100, obtaining communication optimization information, the communication optimization information including information in the metal mine cave, equipment information in the mine cave, and employee operation information in the mine cave;

[0006] Step 200, constructing a plane data and a serial data stream based on the communication optimization information;

[0007] Step 300, inputting the plane data and serial data stream constructed by the communication optimization information into the communication optimization model, the communication optimization model includes a backbone network and a secondary network, the backbone network output represents the result of the hybrid communication optimization strategy, and the secondary network implements the miner scheduling strategy for communication optimization through the hybrid communication optimization strategy;

[0008] Step 400, deploying network infrastructure and signal expansion and redundancy according to the hybrid communication optimization strategy, deploying a wireless sensor network, and configuring communication equipment for miners in the metal mine to maintain the communication equipment and lines running in the best state;

[0009] Step 500, providing communication support for operations and command and dispatch in the metal mine based on the deployed network infrastructure, adjusting the tasks and work and rest ratio of the miners in the metal mine to maintain the miners' optimal work efficiency.

[0010] Further, in step 100, the information in the metal mine includes the geological structure and layout information in the mine, the transmission path information of the wireless signal, and the information of the current communication device and signal strength;

[0011] The geological structure and layout information in the mine includes the geological characteristics of the mine and the mining path information of the mine;

[0012] Geological characteristics include rock type, texture, faults and fractures, mineralized zones, groundwater, geostress, and chemical weathering;

[0013] The transmission path of wireless signals includes a multipath effect path, which is a combination of direct path, reflection path, refraction path, scattering path, diffraction path, and transmission path.

[0014] The information of current communication devices and signal strength includes the number of communication devices, coverage and signal strength;

[0015] The equipment information in the mine includes electromagnetic interference data information of mechanical equipment, physical layout information of mechanical equipment, structure and electrical characteristics of cable network, real-time strength information of communication signals, environmental noise level information and distribution information of interference sources;

[0016] The geographical layout information of mechanical equipment includes the number of mechanical equipment and the distribution location of mechanical equipment;

[0017] The structure and electrical characteristics of the cable network include the number of cables, cable types, and cable transmission rates and bandwidths;

[0018] Environmental noise level information includes the type of noise source, occurrence time, duration, spatial distribution and background noise level;

[0019] The distribution information of interference sources includes the type of interference source, geographical location of interference sources, distribution range, spectrum characteristics of interference sources, source density of interference sources and intensity of interference sources;

[0020] The information about employees’ work in the mine includes the real-time location information of miners and miners, the working status and rest time of employees, and the environmental parameters in the mine;

[0021] Environmental parameters inside the mine include temperature, humidity, oxygen concentration and harmful gas concentration.

[0022] Furthermore, step 200 also includes step 210, obtaining a first serial data stream based on the sorting of the information in the metal mine cave, the first serial data stream including n first data units sorted in time, the t-th first data unit storing the first plane data generated by the information in the metal mine cave collected at the t-th moment;

[0023] The first plane data includes a first facet for storing data, and a first facet indexes a first data object. The first plane data also includes a first relationship list for storing association relationships between the first data objects indexed by the first facet, and the element value of the i-th row and j-th column of the first relationship list represents a quantitative value of the association relationship between the first data objects indexed by the i-th and j-th first facets;

[0024] The association relationships include high and low, corresponding to two quantitative values;

[0025] The first data object includes: metal mines, wired communication equipment, and wireless communication equipment;

[0026] The first data object with high correlation is defined as follows: metal mine caves are associated with the geological structure in which they are located and the layout structure of the mine cave itself; wired communication equipment is associated with its wired network components, transmission paths and its communication characteristics; wireless communication equipment is associated with its communication strength, communication range, number of required relay devices, location of relay devices, number of required antennas and location of antennas;

[0027] There is a relationship between wired communication devices in the same metal mine cave; there is a relationship between wireless communication devices in the same metal mine cave; there is a relationship between wired communication devices on the same communication path; there is a relationship between wireless communication devices within the same communication range; there is a relationship between wired communication devices and wireless communication devices in the same metal mine cave.

[0028] Furthermore, step 200 further includes step 220, obtaining a second serial data stream based on the sorting of the equipment information in the mine cave, the second serial data stream including m second data units sorted by time, and the t-th second data unit stores the second plane data generated by the equipment information in the mine cave collected at the t-th moment;

[0029] The second plane data includes a second facet for storing data, one second facet indexes a second data object, and the second plane data also includes a second relationship list for storing association relationships between second data objects indexed by the second facet, wherein the element value of the i-th row and j-th column of the second relationship list represents a quantitative value of the association relationship between the second data objects indexed by the i-th and j-th second facets;

[0030] The association relationships include high and low, corresponding to two quantitative values;

[0031] The second data objects include: metal mines, mechanical equipment, and cable networks;

[0032] The second data object with a high correlation is defined as: metal mines are associated with the mechanical equipment used for mining; mechanical equipment is associated with the cable network required; mechanical equipment is associated with its quantity and distribution location; cable network is associated with its cable topology and electrical characteristics; both mechanical equipment and cable network are associated with the environmental noise level and the distribution of interference sources;

[0033] There is a relationship between the mechanical equipment in the same metal mine; there is a relationship between the cable network in the same metal mine; there is a relationship between the mechanical equipment and the cable network they use.

[0034] Furthermore, step 200 also includes step 230, generating third plane data based on the employee operation information in the mine, including a third facet for storing data, a third facet indexing a third serial data stream to a third data object, the third plane data also includes a third relationship list for storing association relationships between third data objects indexed by the third facet, and the element value of the i-th row and j-th column of the third relationship list represents a quantitative value of the association relationship between the third data objects indexed by the i-th and j-th third facets;

[0035] The association relationships include high and low, corresponding to two quantitative values;

[0036] The third data objects include: metal mines, miners, and environmental sensors;

[0037] The third data object with a high correlation is defined as: the number of miners and environmental sensors required for the metal mine; the miners are associated with the location of the mine where they work, their own information, communication equipment and physical condition; the environmental sensors are associated with the environmental parameters of the metal mine where they are located;

[0038] There is a relationship between miners in the same metal mine; there is a relationship between environmental sensors in the same metal mine; there is a relationship between miners and the environmental sensors in the metal mine;

[0039] A third serial data stream of a third data object includes p third data units sorted by time, and the tth third data unit represents the employee operation information in the mine collected at the tth moment of the third data object.

[0040] Further, the backbone network includes a first encoder, a second encoder, a third encoder, a fourth encoder, a first feature fusion layer and a first FC layer, the first plane data and the first serial data stream are input to the first encoder, and the first identification feature is output to the second encoder, the second plane data and the second serial data stream are input to the third encoder, and the third identification feature is output to the fourth encoder, the second encoder and the fourth encoder respectively output the second identification feature and the fourth identification feature to the first feature fusion layer, the first feature fusion layer outputs the first fusion feature to the first FC layer, and the first FC layer outputs the result representing the hybrid communication optimization strategy;

[0041] The results represent hybrid communication optimization strategies including dynamic channel selection, communication transmission path avoidance, optimization on hybrid communication network topology, antenna deployment, antenna control, and hierarchical network protocols.

[0042] Furthermore, dynamic channel selection includes optimal channel and channel switching; communication transmission path avoidance includes communication path selection, multipath transmission, congestion avoidance and network resource redundancy; antenna deployment includes antenna type and antenna distribution physical location; antenna control includes antenna coverage, antenna direction and antenna height; layered network protocol design includes physical layer, data link layer, network layer, transport layer, session layer, presentation layer and application layer.

[0043] Further, the sub-network includes a fifth encoder, a sixth encoder, a seventh encoder, a second feature fusion layer and a second FC layer, the third plane data and the third serial data stream are input to the fifth encoder, the fifth identification feature is output to the second feature fusion layer, the first FC layer outputs the result representing the hybrid communication optimization strategy and inputs it to the sixth encoder, the sixth identification feature is output to the second feature fusion layer, the second feature fusion layer outputs the second fusion feature to the seventh encoder, the seventh encoder outputs the seventh identification feature to the second FC layer, and the second FC layer outputs the result representing the miner scheduling strategy;

[0044] The miner scheduling strategy includes dynamically adjusting the miner task allocation and rest arrangements based on the miner's status and the safety of the mine. The adjustment rules are based on defining the optimal ratio between work and rest.

[0045] A sustainable communication optimization processing system in a restricted connection environment, used to execute the steps in the aforementioned sustainable communication optimization processing method in a restricted connection environment, comprising:

[0046] Information collection and processing module: obtain geological structure, layout information and wireless signal transmission path information in the mine, monitor the number, coverage and signal strength of current communication equipment, and collect distribution information of mechanical equipment, cable network, electromagnetic interference, noise level and interference sources;

[0047] At the same time, obtain the miner's real-time location, operation status and environmental parameters;

[0048] Data processing module: generates first, second, third plane data and serial data streams according to the collected information, calculates the association relationship between different data objects, and constructs a relationship list;

[0049] Communication optimization model module: extracts the features of the communication optimization model, integrates the features, and generates hybrid communication optimization strategy results;

[0050] Communication optimization strategy implementation module: dynamic channel selection, transmission path avoidance, hybrid network topology optimization, antenna deployment and control, and hierarchical protocol optimization based on the results of hybrid communication optimization strategy;

[0051] Miner scheduling model module: extracts miner scheduling related features, generates miner scheduling strategies, and executes miners' scheduling between working state and rest state according to the strategies.

[0052] A storage medium stores non-temporary computer-readable instructions for executing the steps in the aforementioned sustainable communication optimization processing method under a restricted connection environment.

[0053] The beneficial effects of the present invention are:

[0054] The present invention uses a dynamic channel selection module to select the best channel according to real-time environmental conditions, avoid high-interference channels, use multipath transmission and transmission path avoidance, effectively use the reflection and refraction paths in the multipath effect, and target the electromagnetic interference generated by mechanical equipment and cable networks. Through equipment status monitoring and environmental noise level monitoring, the effectiveness of the signal coverage range of communication equipment is improved, and the problem of limited communication in metal mines is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a sustainable communication optimization processing method in a restricted connection environment proposed by the present invention;

[0056] Figure 2 It is a structural block diagram of a sustainable communication optimization processing system in a restricted connection environment proposed by the present invention.

[0057] In the figure: 101, information collection and processing module; 102, data processing module; 103, communication optimization model module; 104, communication optimization strategy implementation module; 105, miner scheduling model module. DETAILED DESCRIPTION

[0058] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0059] like Figure 1 As shown, a sustainable communication optimization processing method in a restricted connection environment includes the following steps:

[0060] Step 100, obtaining communication optimization information, the communication optimization information including information in the metal mine cave, equipment information in the mine cave, and employee operation information in the mine cave;

[0061] The information inside the metal mine includes the geological structure and layout information inside the mine, the transmission path information of the wireless signal, and the information of the current communication equipment and signal strength;

[0062] The geological structure and layout of the mine includes the characteristics of the geology of the mine (rock type, texture, faults and fractures, mineralized zones, groundwater, geostress and chemical weathering) and the mining path information of the mine;

[0063] The transmission path of wireless signals includes multipath effect paths (direct path, reflection path, refraction path, scattering path, diffraction path, and transmission path).

[0064] The information of current communication devices and signal strength includes the number of communication devices, coverage and signal strength;

[0065] The equipment information in the mine includes electromagnetic interference data information of mechanical equipment, physical layout information of mechanical equipment, structure and electrical characteristics of cable network, real-time strength information of communication signals, environmental noise level information and distribution information of interference sources;

[0066] The geographical layout information of mechanical equipment includes the number of mechanical equipment and the distribution location of mechanical equipment;

[0067] The structure and electrical characteristics of the cable network include the number of cables, cable types, and cable transmission rates and bandwidths;

[0068] Environmental noise level information includes the type of noise source, occurrence time, duration, spatial distribution and background noise level;

[0069] The distribution information of interference sources includes the type of interference source, geographical location of interference sources, distribution range, spectrum characteristics of interference sources, source density of interference sources and intensity of interference sources;

[0070] The information about employees’ work in the mine includes the real-time location information of miners and miners, the working status and rest time of employees, and the environmental parameters in the mine;

[0071] Environmental parameters in the mine include temperature, humidity, oxygen concentration, and harmful gas concentration;

[0072] Step 200, constructing a plane data and a serial data stream based on the communication optimization information;

[0073] Step 210, obtaining a first serial data stream based on the sorting of the information in the metal mine cave, the first serial data stream comprising n first data units sorted in time, the t-th first data unit storing the first plane data generated by the information in the metal mine cave collected at the t-th moment;

[0074] The first plane data includes a first facet for storing data, and a first facet indexes a first data object. The first plane data also includes a first relationship list for storing association relationships between the first data objects indexed by the first facet, and the element value of the i-th row and j-th column of the first relationship list represents a quantitative value of the association relationship between the first data objects indexed by the i-th and j-th first facets;

[0075] The association relationships include high and low, corresponding to two quantitative values;

[0076] The first data object includes: metal mines, wired communication equipment, and wireless communication equipment;

[0077] The first data object with high correlation is defined as follows: metal mine caves are associated with the geological structure in which they are located and the layout structure of the mine cave itself; wired communication equipment is associated with its wired network components, transmission paths and its communication characteristics; wireless communication equipment is associated with its communication strength, communication range, number of required relay devices, location of relay devices, number of required antennas and location of antennas;

[0078] There is a relationship between wired communication devices in the same metal mine cave; there is a relationship between wireless communication devices in the same metal mine cave; there is a relationship between wired communication devices on the same communication path; there is a relationship between wireless communication devices within the same communication range; there is a relationship between wired communication devices and wireless communication devices in the same metal mine cave;

[0079] Step 220, obtaining a second serial data stream based on the sorting of the equipment information in the mine cave, the second serial data stream comprising m second data units sorted by time, the t-th second data unit storing the second plane data generated by the equipment information in the mine cave collected at the t-th moment;

[0080] The second plane data includes a second facet for storing data, one second facet indexes a second data object, and the second plane data also includes a second relationship list for storing association relationships between second data objects indexed by the second facet, wherein the element value of the i-th row and j-th column of the second relationship list represents a quantitative value of the association relationship between the second data objects indexed by the i-th and j-th second facets;

[0081] The association relationships include high and low, corresponding to two quantitative values;

[0082] The second data objects include: metal mines, mechanical equipment, and cable networks;

[0083] The second data object with a high correlation is defined as: metal mines are associated with the mechanical equipment used for mining; mechanical equipment is associated with the cable network required; mechanical equipment is associated with its quantity and distribution location; cable network is associated with its cable topology and electrical characteristics; both mechanical equipment and cable network are associated with the environmental noise level and the distribution of interference sources;

[0084] There are relationships between the mechanical equipment in the same metal mine; there are relationships between the cable networks in the same metal mine; there are relationships between the mechanical equipment and the cable networks they use;

[0085] Step 230: Generate third plane data based on the employee operation information in the mine, including a third facet for storing data, a third serial data stream indexed by a third facet to a third data object, and the third plane data further includes a third relationship list for storing association relationships between third data objects indexed by the third facet, wherein the element value of the i-th row and j-th column of the third relationship list represents a quantitative value of the association relationship between the third data objects indexed by the i-th and j-th third facets;

[0086] The association relationships include high and low, corresponding to two quantitative values;

[0087] The third data objects include: metal mines, miners, and environmental sensors;

[0088] The third data object with a high correlation is defined as: the number of miners and environmental sensors required for the metal mine; the miners are associated with the location of the mine where they work, their own information, communication equipment and physical condition; the environmental sensors are associated with the environmental parameters of the metal mine where they are located (temperature, humidity, toxic gas concentration);

[0089] There is a relationship between miners in the same metal mine; there is a relationship between environmental sensors in the same metal mine; there is a relationship between miners and the environmental sensors in the metal mine;

[0090] A third serial data stream of a third data object includes p third data units sorted by time, and the tth third data unit represents the employee operation information in the mine collected at the tth moment of the third data object.

[0091] Step 300, inputting the plane data and serial data stream constructed by the communication optimization information into the communication optimization model, the communication optimization model includes a backbone network and a secondary network, the backbone network includes a first encoder, a second encoder, a third encoder, a fourth encoder, a first feature fusion layer and a first FC (fully connected layer) layer, and the output of the first FC layer represents the result of the hybrid communication optimization strategy;

[0092] The first plane data and the first serial data stream are input to the first encoder, and the first identification feature is output to the second encoder. The second plane data and the second serial data stream are input to the third encoder, and the third identification feature is output to the fourth encoder. The second encoder and the fourth encoder respectively output the second identification feature and the fourth identification feature to the first feature fusion layer. The first feature fusion layer outputs the first fusion feature to the first FC layer. The first FC layer outputs the result representing the hybrid communication optimization strategy.

[0093] Results showing hybrid communication optimization strategies include dynamic channel selection, communication transmission path avoidance, optimization on hybrid communication network topology, antenna deployment, antenna control, and hierarchical network protocols;

[0094] Dynamic channel selection includes best channel and channel switching;

[0095] Communication transmission path avoidance includes communication path selection, multi-path transmission, congestion avoidance and network resource redundancy;

[0096] Antenna deployment includes antenna type and physical location of antenna distribution;

[0097] Antenna control includes antenna coverage, antenna direction and antenna height;

[0098] Layered network protocol design includes physical layer, data link layer, network layer, transport layer, session layer, presentation layer and application layer;

[0099] The secondary network includes a fifth encoder, a sixth encoder, a seventh encoder, a second feature fusion layer, and a second FC layer. The output of the second FC layer represents the result of the miner scheduling strategy.

[0100] The third plane data and the third serial data stream are input to the fifth encoder, and the fifth identification feature is output to the second feature fusion layer. The first FC layer outputs the result representing the hybrid communication optimization strategy and inputs it to the sixth encoder, and the sixth identification feature is output to the second feature fusion layer. The second feature fusion layer outputs the second fusion feature to the seventh encoder, and the seventh encoder outputs the seventh identification feature to the second FC layer. The second FC layer outputs the result representing the miner scheduling strategy.

[0101] Miner scheduling strategies include dynamically adjusting miner task allocation and rest arrangements based on miner status and mine safety. The adjustment rules are defined by the optimal ratio between work and rest.

[0102] Step 400, deploying network infrastructure and signal expansion and redundancy according to the hybrid communication optimization strategy, deploying a wireless sensor network, and configuring communication equipment for miners in the metal mine to maintain the communication equipment and lines running in the best state;

[0103] Step 500, providing communication support for operations and command and dispatch in the metal mine based on the deployed network infrastructure, adjusting the tasks and work and rest ratio of the miners in the metal mine to maintain the miners' optimal work efficiency.

[0104] In one embodiment of the present invention, the calculation formula of the first encoder is as follows:

[0105] ;

[0106] in represents the bin feature of the vth first bin of the lth layer of the tth first data unit of the first serial data stream, represents the set of first facets with high correlation with the first facet v, represents the first plane recognition weight matrix of layer l, is the attention weight of the first surfel u of layer l to the first surfel v, which is calculated by the following formula:

[0107] ;

[0108] in is a learnable attention vector, represents the vector concatenation operation, represents the second plane recognition weight matrix of layer l, represents transpose;

[0109] and represent the bin features of the vth and uth first bins of the tth first data unit of the first serial data stream of the l-1th layer, respectively, , E represents the total number of layers, when l=1 , when l=E is equal to the identification feature of the vth first bin of the tth first data unit of the first serial data stream; wherein and feature representations of the data objects of the vth and uth first bin indexes of the tth first data unit of the first serial data stream, respectively, Represents the LeakyReLU function;

[0110] In one embodiment of the present invention, the calculation formula of the second encoder is as follows:

[0111] ;

[0112] ;

[0113] ;

[0114] in represents the t-th second identification feature, represents the t-1th second identification feature, and denote the first and second intermediate features respectively, , represents the set of first bins of all t-th first data units, and is the serial recognition weight matrix of the second encoder, is the serial identification bias parameter of the second encoder, represents the Sigmoid function, tanh is the hyperbolic tangent function, Represents the dot product.

[0115] In one embodiment of the present invention, the calculation formula of the third encoder is as follows:

[0116] ;

[0117] represents the bin feature of the vth second bin of the lth layer of the tth second data unit of the second serial data stream, represents the bin feature of the u-th second bin of the t-th second data unit of the second serial data stream of the l-1-th layer, and represent the set of second facets with high correlation with the second facet v and the second facet u respectively, represents the cardinality of a set, represents the second plane recognition weight matrix of layer l, , E represents the total number of layers, when l=1 , The characteristic representation of the data object of the u-th second bin index of the t-th second data unit of the second serial data stream, when l=E is equal to the identification feature of the vth second bin of the tth second data unit of the second serial data stream, is the sigmoid function.

[0118] In one embodiment of the present invention, the calculation formula of the fourth encoder is as follows:

[0119] ;

[0120] in represents the tth fourth identification feature, represents the t-1th fourth identification feature, , represents the set of second bins of all t-th second data units, and is the serial recognition weight matrix, is the serial recognition bias parameter, and ReLU is the ReLU activation function.

[0121] In one embodiment of the present invention, the calculation formula of the first recognition fusion layer is as follows:

[0122] ;

[0123] in, represents the first combination feature, represents the feature combination function (concatenation function or summation function), represents the nth second identification feature, n represents the total number of first data units of the first serial data stream, represents the mth fourth identification feature, where m represents the total number of second data units in the second serial data stream;

[0124] In one embodiment of the present invention, the calculation formula of the first FC layer is as follows:

[0125] ;

[0126] in represents the first output vector, the cth component value of which represents the probability value of the cth strategy, and the strategy with the largest probability value is selected as the output. The strategy group contains all executable strategies. A strategy includes an optimization parameter in the hybrid communication optimization strategy. The optimization parameters include dynamic channel selection, communication transmission path avoidance, hybrid communication network topology, antenna deployment, antenna control and hierarchical network protocol;

[0127] For more complex strategies, vector representation can be used: a strategy is represented by a vector, and the jth component of the vector represents the jth optimization direction of the optimization parameter in the hybrid communication optimization strategy. Indicates full connection;

[0128] In one embodiment of the present invention, the calculation formula of the fifth encoder is as follows:

[0129] ;

[0130] ;

[0131] in represents an aggregate representation of the vth third bin of the lth layer of the tth third data unit of the third serial data stream, and represent the bin feature of the vth third bin of the tth third data unit of the third serial data stream of the lth layer and the l-1th layer, respectively, represents a set of third facets with a high correlation with the third facet v; Represents the universal quantifier symbol; The bin feature of the uth bin of the tth third data unit of the third serial data stream of the l-1th layer, when l=1 , when l=E is equal to a fifth identification feature of the vth third bin of the tth third data unit of the third serial data stream; represents the aggregation function of layer l, such as average or maximum pooling function, represents the plane recognition weight matrix of the lth layer of the fifth encoder, σ represents the Sigmoid function, Represents the concatenation function.

[0132] In one embodiment of the present invention, the calculation formula of the sixth encoder is as follows:

[0133] ;

[0134] in represents the sixth identification feature, represents the convolution function;

[0135] In one embodiment of the present invention, the calculation formula of the second recognition fusion layer is as follows:

[0136] ;

[0137] in, represents the second combination feature, represents the feature combination function (concatenation function or summation function), a fifth identification feature of the last layer of the vth third bin of the tth third data unit of the third serial data stream, represents a set of third bins of all t-th third data units;

[0138] In one embodiment of the present invention, the calculation formula of the seventh encoder is as follows:

[0139] ;

[0140] ;

[0141] ;

[0142] in represents the tth seventh identification feature, represents the t-1th seventh identification feature, and denote the first and second intermediate features of the seventh encoder, respectively, , and is the serial recognition weight matrix of the seventh encoder, is the serial identification bias parameter of the seventh encoder, Represents the Sigmoid function.

[0143] In one embodiment of the present invention, the calculation formula of the second FC layer is as follows:

[0144] ;

[0145] in represents the second output vector, whose kth component value represents the probability value of the kth strategy. The strategy with the largest probability value is selected as the output. The strategy group contains all executable strategies. A strategy includes the location, task volume and working time assigned to miners in a metal mine.

[0146] For more complex strategies, vector representation can be used: a strategy is represented by a vector, and the jth component of the vector represents the jth scheduling plan for miners working in a metal mine. The scheduling plan includes working hours, rest time, workload, and work location. represents the p-th seventh identification feature, p represents the total number of third data units of the third serial data stream, Indicates full connection.

[0147] In one embodiment of the present invention, the communication optimization model adopts a multi-classification cross entropy function, and the function expression is as follows:

[0148] ;

[0149] in represents the loss value, M represents the total number of classification categories of the optimization parameters, represents the total number of training samples, It is The symbol value of the training sample, if the The true classification of the training sample is the cth classification category and its value is 1, otherwise it is 0. The communication optimization model predicts The probability that a training sample belongs to the cth classification category, Represents the logarithmic function with the natural constant e as the base.

[0150] like Figure 2 As shown, in one embodiment of the present invention, a sustainable communication optimization processing system in a restricted connection environment includes:

[0151] Information collection and processing module 101: obtains geological structure, layout information and wireless signal transmission path information in the mine, monitors the number, coverage and signal strength of current communication equipment, and collects distribution information of mechanical equipment, cable networks, electromagnetic interference, noise levels and interference sources.

[0152] At the same time, the miners’ real-time location, working status, and environmental parameters (such as temperature, humidity, oxygen concentration, and harmful gas concentration) are obtained.

[0153] Data processing module 102: generates first, second, third plane data and serial data streams according to the collected information, calculates the association relationship between different data objects, and constructs a relationship list.

[0154] Communication optimization model module 103: extracts the features of the communication optimization model, integrates the features, and generates hybrid communication optimization strategy results.

[0155] Communication optimization strategy implementation module 104: performs dynamic channel selection, transmission path avoidance, hybrid network topology optimization, antenna deployment and control, and hierarchical protocol optimization according to the hybrid communication optimization strategy results;

[0156] Miner scheduling model module 105: extracts miner scheduling related features, generates miner scheduling strategies, and recommends miners to allocate between work and rest.

[0157] At least one embodiment of the present disclosure provides a storage medium storing non-transitory computer-readable instructions for executing one or more steps of the aforementioned method for sustainable communication optimization processing in a restricted connection environment.

[0158] The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims should not be construed as limiting the scope.

[0159] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A method for optimizing sustainable communication in a limited connection environment, characterized in that: The following steps are involved: Step 100, obtaining communication optimization information, the communication optimization information including information in the metal mine cave, equipment information in the mine cave, and employee operation information in the mine cave; Step 200, constructing first plane data, second plane data, and third plane data as well as a first serial data stream, a second serial data stream, and a third serial data stream based on the communication optimization information; A first serial data stream is obtained based on the sorting of the information in the metal mine cave, the first serial data stream includes n first data units sorted by time, and the t-th first data unit stores the first plane data generated by the information in the metal mine cave collected at the t-th moment; The first plane data includes a first facet for storing data, and a first facet indexes a first data object. The first plane data also includes a first relationship list for storing association relationships between the first data objects indexed by the first facet, and the element value of the i-th row and j-th column of the first relationship list represents a quantitative value of the association relationship between the first data objects indexed by the i-th and j-th first facets; The first data object includes: metal mines, wired communication equipment, and wireless communication equipment; A second serial data stream is obtained based on the sorting of the equipment information in the mine cave, the second serial data stream includes m second data units sorted by time, and the t-th second data unit stores the second plane data generated by the equipment information in the mine cave collected at the t-th moment; The second plane data includes a second facet for storing data, one second facet indexes a second data object, and the second plane data also includes a second relationship list for storing association relationships between second data objects indexed by the second facet, wherein the element value of the i-th row and j-th column of the second relationship list represents a quantitative value of the association relationship between the second data objects indexed by the i-th and j-th second facets; The second data objects include: metal mines, mechanical equipment, and cable networks; The third plane data generated based on the employee operation information in the mine includes a third facet for storing data, a third facet indexing a third serial data stream to a third data object, the third plane data also includes a third relationship list for storing association relationships between third data objects indexed by the third facet, and the element value of the i-th row and j-th column of the third relationship list represents the quantitative value of the association relationship between the third data objects indexed by the i-th and j-th third facets; The third data objects include: metal mines, miners, and environmental sensors; Step 300, inputting the plane data and serial data stream constructed by the communication optimization information into the communication optimization model, the communication optimization model includes a backbone network and a secondary network, the backbone network output represents the result of the hybrid communication optimization strategy, and the secondary network implements the miner scheduling strategy for communication optimization through the hybrid communication optimization strategy; Results showing hybrid communication optimization strategies include dynamic channel selection, communication transmission path avoidance, optimization on hybrid communication network topology, antenna deployment, antenna control, and hierarchical network protocols; Dynamic channel selection includes optimal channel and channel switching; communication transmission path avoidance includes communication path selection, multi-path transmission, congestion avoidance and network resource redundancy; antenna deployment includes antenna type and antenna distribution physical location; antenna control includes antenna coverage, antenna direction and antenna height; layered network protocol design includes physical layer, data link layer, network layer, transport layer, session layer, presentation layer and application layer; The miner scheduling strategy includes dynamically adjusting the miner task allocation and rest arrangements according to the miner status and safety in the mine. The adjustment rule is to define the optimal ratio between work and rest. Step 400, deploying network infrastructure and signal expansion and redundancy according to the hybrid communication optimization strategy, deploying a wireless sensor network, and configuring communication equipment for miners in the metal mine to maintain the communication equipment and lines running in the best state; Step 500, providing communication support for operations and command and dispatch in the metal mine based on the deployed network infrastructure, adjusting the tasks and work and rest ratio of the miners in the metal mine to maintain the miners' optimal work efficiency.

2. The method for optimizing sustainable communication in a limited connection environment according to claim 1, characterized in that: In step 100, the information in the metal mine includes the geological structure and layout information in the mine, the transmission path information of the wireless signal, and the information of the current communication equipment and signal strength; The geological structure and layout information in the mine includes the geological characteristics of the mine and the mining path information of the mine; Geological characteristics include rock type, texture, faults and fractures, mineralized zones, groundwater, geostress, and chemical weathering; The transmission path of wireless signals includes a multipath effect path, which is a combination of direct path, reflection path, refraction path, scattering path, diffraction path, and transmission path. The information of current communication devices and signal strength includes the number of communication devices, coverage and signal strength; The equipment information in the mine includes electromagnetic interference data information of mechanical equipment, physical layout information of mechanical equipment, structure and electrical characteristics of cable network, real-time strength information of communication signals, environmental noise level information and distribution information of interference sources; The geographical layout information of mechanical equipment includes the number of mechanical equipment and the distribution location of mechanical equipment; The structure and electrical characteristics of the cable network include the number of cables, cable types, and cable transmission rates and bandwidths; Environmental noise level information includes the type of noise source, occurrence time, duration, spatial distribution and background noise level; The distribution information of interference sources includes the type of interference source, geographical location of interference sources, distribution range, spectrum characteristics of interference sources, source density of interference sources and intensity of interference sources; The information about employees’ work in the mine includes the real-time location information of miners and miners, the working status and rest time of employees, and the environmental parameters in the mine; Environmental parameters inside the mine include temperature, humidity, oxygen concentration and harmful gas concentration.

3. The method for optimizing sustainable communication in a restricted connection environment according to claim 2, characterized in that: In step 200, step 210 is also included, the association relationship includes high and low, which correspond to two quantitative values ​​respectively; The first data object with high correlation is defined as follows: metal mine caves are associated with the geological structure in which they are located and the layout structure of the mine cave itself; wired communication equipment is associated with its wired network components, transmission paths and its communication characteristics; wireless communication equipment is associated with its communication strength, communication range, number of required relay devices, location of relay devices, number of required antennas and location of antennas; There is a relationship between wired communication devices in the same metal mine cave; there is a relationship between wireless communication devices in the same metal mine cave; there is a relationship between wired communication devices on the same communication path; there is a relationship between wireless communication devices within the same communication range; there is a relationship between wired communication devices and wireless communication devices in the same metal mine cave.

4. The method for optimizing sustainable communication in a restricted connection environment according to claim 3, characterized in that: In step 200, step 220 is also included, the association relationship includes high and low, which correspond to two quantitative values ​​respectively; The second data object with a high correlation is defined as: metal mines are associated with the mechanical equipment used for mining; mechanical equipment is associated with the cable network required; mechanical equipment is associated with its quantity and distribution location; cable network is associated with its cable topology and electrical characteristics; both mechanical equipment and cable network are associated with the environmental noise level and the distribution of interference sources; There are relationships between mechanical equipment in the same metal mine; there are relationships between cable networks in the same metal mine; There is a relationship between a mechanical device and the network of cables it uses.

5. The method for optimizing sustainable communication in a restricted connection environment according to claim 4, characterized in that: In step 200, step 230 is also included, the association relationship includes high and low, which correspond to two quantitative values ​​respectively; The third data object with a high correlation is defined as: the number of miners and environmental sensors required for the metal mine; the miners are associated with the location of the mine where they work, their own information, communication equipment and physical condition; the environmental sensors are associated with the environmental parameters of the metal mine where they are located; There is a relationship between miners in the same metal mine; there is a relationship between environmental sensors in the same metal mine; there is a relationship between miners and the environmental sensors in the metal mine; A third serial data stream of a third data object includes p third data units sorted by time, and the tth third data unit represents the employee operation information in the mine collected at the tth moment of the third data object.

6. The method for optimizing sustainable communication in a restricted connection environment according to claim 5, characterized in that: The backbone network includes a first encoder, a second encoder, a third encoder, a fourth encoder, a first feature fusion layer and a first FC layer. The first plane data and the first serial data stream are input to the first encoder, and the first identification feature is output to the second encoder. The second plane data and the second serial data stream are input to the third encoder, and the third identification feature is output to the fourth encoder. The second encoder and the fourth encoder respectively output the second identification feature and the fourth identification feature to the first feature fusion layer. The first feature fusion layer outputs the first fusion feature to the first FC layer. The first FC layer outputs the result representing the hybrid communication optimization strategy.

7. The method for optimizing sustainable communication in a limited connection environment according to claim 6, characterized in that: The sub-network includes a fifth encoder, a sixth encoder, a seventh encoder, a second feature fusion layer and a second FC layer. The third plane data and the third serial data stream are input to the fifth encoder, and the fifth identification feature is output to the second feature fusion layer. The first FC layer outputs the result representing the hybrid communication optimization strategy and inputs it to the sixth encoder, which outputs the sixth identification feature to the second feature fusion layer. The second feature fusion layer outputs the second fusion feature to the seventh encoder, and the seventh encoder outputs the seventh identification feature to the second FC layer. The second FC layer outputs the result representing the miner scheduling strategy.

8. A sustainable communication optimization processing system in a restricted connection environment, characterized in that: The method for executing the steps of the method for optimizing sustainable communication in a restricted connection environment as claimed in any one of claims 1 to 7 comprises: Information collection and processing module: obtain geological structure, layout information and wireless signal transmission path information in the mine, monitor the number, coverage and signal strength of current communication equipment, and collect distribution information of mechanical equipment, cable network, electromagnetic interference, noise level and interference sources; At the same time, obtain the miner's real-time location, operation status and environmental parameters; Data processing module: generates first plane data, second plane data and third plane data as well as first serial data stream, second serial data stream and third serial data stream according to the collected information, calculates the association relationship between different data objects, and constructs a relationship list; Communication optimization model module: extracts the features of the communication optimization model, integrates the features, and generates hybrid communication optimization strategy results; Communication optimization strategy implementation module: dynamic channel selection, transmission path avoidance, hybrid network topology optimization, antenna deployment and control, and hierarchical protocol optimization based on the results of hybrid communication optimization strategy; Miner scheduling model module: extracts miner scheduling related features, generates miner scheduling strategies, and executes miners' scheduling between working state and rest state according to the strategies.

9. A storage medium, characterized in that: Non-temporary computer-readable instructions are stored therein for executing the steps in a method for sustainable communication optimization processing in a restricted connection environment as described in any one of claims 1-7.

Images