A smart guidance management platform

The intelligent guidance and management platform optimizes the selection of garbage bins by matching bin information with vehicle waste information, solving the congestion problem caused by garbage trucks blindly entering the bins, and achieving a balance of the heat value of garbage bins and improving transportation efficiency.

CN118504746BActive Publication Date: 2024-11-26BEIJING URBAN CONSTR GROUP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410583359.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-11
Publication Date
2024-11-26
Estimated Expiration
2044-05-11

AI Technical Summary

Technical Problem

In waste-to-energy plants, garbage trucks blindly entering the unloading platform causes congestion, making it difficult to scientifically balance the calorific value of multiple garbage bins, thus affecting transportation efficiency and safety.

Method used

By using a smart guidance and management platform, the system combines information from waste bins with vehicle waste information for matching and analysis, optimizes the screening process, issues guidance instructions to vehicles, and selects the best and second-best waste bins to avoid congestion caused by blind entry.

Benefits of technology

Effectively balance the calorific value of the waste storage area, avoid congestion, improve the reliability and efficiency of the transportation process, and ensure driver safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118504746B_ABST
    Figure CN118504746B_ABST
Patent Text Reader

Abstract

The present invention provides a smart guidance management platform, which belongs to the field of smart guidance technology, and includes: a demand acquisition module, which is used to obtain the actual demand of the waste incineration power plant and determine the bin information of each garbage bin; a garbage bin matching module, which is used to obtain the vehicle garbage information of each target vehicle respectively, and obtain the initial bin set by combining the bin information matching; a guidance module, which is used to obtain the current position of the target vehicle and the current transportation map of the waste incineration power plant, and select the best garbage bin and the second best garbage bin from the initial bin set to send to the corresponding target vehicle for selection; an optimization module, which is used to count the transportation dynamics of each target vehicle according to the selected guidance in real time, and guide and manage the transportation dynamics of all target vehicles to obtain the guidance optimization set, so as to optimize the screening process of the best garbage bin and the second best garbage bin. Congestion caused by blind entry can be effectively avoided, and the efficiency of guidance can be ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent guidance technology, and in particular to an intelligent guidance management platform. Background Art

[0002] Waste incineration has become an important part of the circular economy. In addition, in the process of recycling and utilizing waste resources and waste materials, it not only solves the problem of resource shortage, but also reduces waste emissions, which can be said to be "killing two birds with one stone".

[0003] At present, in the process of transporting garbage to the incineration power plant, since the incineration power plant has multiple garbage bins, the daily garbage storage and incineration volume is large, and there are many types of vehicles and trips. Due to the different heat released by the incineration of garbage transported to the plant from different regions and the different operating conditions of the incineration lines in the plant area, it is necessary to balance the calorific value of multiple garbage bins and dynamically control the storage volume of garbage in the pool. When the garbage truck comes to feed, it needs to drive onto the unloading platform through the ramp. If the driver does not enter the unloading platform, he cannot observe whether there is a feeding position for feeding. If he enters blindly, it is easy to cause congestion. The current response measures are mostly to equip special personnel to clear and guide on-site, but this method is not conducive to the personal health of the dispatcher, and when the traffic volume is large, it is impossible to scientifically balance the calorific value of multiple garbage bins based on human judgment alone, and it is difficult to achieve reasonable and efficient guidance.

[0004] Therefore, the present invention proposes an intelligent guidance management platform. Summary of the invention

[0005] The present invention provides an intelligent guidance management platform for matching and analyzing bin information with vehicle garbage information to effectively balance the calorific value generated by subsequent garbage collection in multiple garbage bins, and by issuing guidance to vehicles matching garbage bins, effectively avoiding congestion caused by blind entry, and then optimizing the screening process by obtaining guidance optimization factors to improve process analysis reliability, further ensuring the efficiency of guidance.

[0006] The present invention provides a smart guidance management platform, comprising:

[0007] The demand acquisition module is used to obtain the actual demand of the waste incineration power plant and determine the bin information of each waste bin;

[0008] The garbage bin matching module is used to obtain the vehicle garbage information of each target vehicle respectively, and match the initial bin set corresponding to the target vehicle from all garbage bins in combination with the bin information;

[0009] A sending guidance module is used to obtain the current position of the target vehicle based on the waste incineration power plant and the current transportation map of the waste incineration power plant, select the best garbage bin and the second best garbage bin from the initial bin set, and send them to the corresponding target vehicle for selection;

[0010] The optimization module is used to count the transportation dynamics of each target vehicle according to the selected guidance in real time, and to guide and manage the transportation dynamics of all target vehicles to obtain the guidance optimization set, so as to optimize the screening process of the best garbage bin and the second best garbage bin.

[0011] Preferably, the demand acquisition module includes:

[0012] a heat value extraction unit, for extracting the required heat value generated by each garbage bin in the waste incineration power plant, a bin type set, and permitted vehicle permissions from the actual demand;

[0013] a range determination unit for monitoring the current calorific value of each garbage bin and determining the residual calorific value of the corresponding garbage bin in combination with the required generated calorific value of each garbage bin;

[0014] a quantity determination unit, for determining a required waste quantity of each bin waste type according to the bin type set and the residual heat value;

[0015] The bin information includes: a bin type set corresponding to the garbage bin, permitted vehicle permissions, and the required amount of garbage for each bin garbage type.

[0016] Preferably, the garbage bin matching module includes:

[0017] A scanning unit, used for scanning the loaded garbage of the target vehicle entering the waste incineration power plant to obtain a surface image, and analyzing the surface image to determine a loading type set corresponding to the target vehicle;

[0018] Weighing and identification unit, used to weigh the target vehicle and identify the license plate;

[0019] Among them, the type recognition result, the weighing result and the license plate recognition result are used as the vehicle junk information of the target vehicle.

[0020] Preferably, the garbage bin matching module further includes:

[0021] The authority matching unit is used to determine the garbage authority of the target vehicle according to the license plate recognition result, and match it with the allowed vehicle authority in the bin information of each garbage bin to obtain a plurality of first bins;

[0022] A type matching unit, used for matching a loading type set corresponding to the target vehicle with a bin type set in the bin information of each first bin, to obtain a plurality of second bins;

[0023] Determine the type space proportion of each loading type according to the surface image, and obtain the loading weight of each loading type in combination with the weighing result of the corresponding target vehicle;

[0024] The quantity matching element is used to match the loading weight of all loading types of the corresponding target vehicle with the required garbage quantity of all bin garbage types in the bin information of each second bin, to obtain a number of third bins;

[0025] The plurality of third bins serve as initial bin sets corresponding to the target vehicle.

[0026] Preferably, the sending guidance module includes:

[0027] An aerial photography unit, used for taking aerial photos of the waste incineration power plant to obtain a first image;

[0028] A positioning unit, configured to obtain a second image based on the vehicle positioning information of the waste incineration power plant captured by the Internet of Things platform;

[0029] An image analysis unit, configured to perform a comprehensive analysis on the first image and the second image to obtain a current transportation map;

[0030] an efficiency calculation unit, configured to determine the degree of vehicle congestion of a transport section between adjacent transport nodes based on the current transport graph, and obtain a driving efficiency of a corresponding target vehicle based on a driving route of each third warehouse in a corresponding initial warehouse set in combination with the node attributes of each transport node and the current position and executed process of the target vehicle;

[0031]

[0032]

[0033] Wherein, max represents the maximum value symbol; n1 represents the total number of transport sections included in the current position of the target vehicle and the driving route of the relevant third warehouse; L1 j1 V1 represents the length of the corresponding j1th transport section; j1 represents the set speed limit of the corresponding j1-th transport section; Y j1 (D j1 , S j1-1 , S j1+1 ) represents the node attributes S of the two transport nodes based on the j1th transport segment j1-1 , S j1+1 and vehicle congestion level D j1 The time estimation function of Express satisfaction All Y j1 (D j1 , S j1-1 , S j1+1 )’s mean square error; ε1 j1 represents the sub-efficiency of the corresponding j1-th transport section; Q j1 (Sj1-1 , S j1+1 ) represents the node attributes S of the two transport nodes based on the j1th transport segment j1-1 , S j1+1 The weight of the road section determined; Ny represents the number of executed processes corresponding to the target vehicle; Nz represents the total number of all executed processes corresponding to the target vehicle; L0 represents the driving length and The sum of; ty represents the actual driving time of the corresponding target vehicle under the executed process; t0 represents the estimated total guidance time of the corresponding target vehicle based on all executed processes; xs i Indicates the driving efficiency of the corresponding target vehicle;

[0034] an efficiency correction unit, configured to correct the driving efficiency to obtain a first efficiency according to a difficulty sequence in an estimated driving time period of a corresponding target vehicle driving along a driving route of a corresponding third warehouse;

[0035] A bin selection unit, used for selecting the best garbage bin corresponding to the maximum efficiency and the second best garbage bin corresponding to the second maximum efficiency from all first efficiencies;

[0036] The guidance unit is used to obtain the guidance instructions input by the driver of the corresponding target vehicle based on the guidance display screen to finally lock the bin from the best garbage bin and the second best garbage bin, and to issue guidance for the driving route corresponding to the final locked bin.

[0037] Preferably, the efficiency calculation unit comprises:

[0038] The sequence construction subunit is used to determine the time when the corresponding target vehicle obtains the corresponding driving route, obtain the number of command inputs at the time from the platform statistical database, and combine the number of command inputs at N0 moments before the time, and construct an input sequence in, Indicates that the time T1 is obtained d The j2th moment before T1 d-j2 The number of instruction inputs;

[0039] A quantity estimation subunit, used for determining, based on the input sequence, an estimated input quantity at a next moment based on the obtaining moment;

[0040]

[0041] in, Indicates the next moment T1 d+1 The estimated number of inputs; Ns d-N0~d Indicates that based on all The fitted value of the constructed quantity curve; Indicates all The variance of

[0042] The splitting subunit is used to split the estimated input quantity according to the driving difficulty of each transport section on the corresponding driving route at the obtained time, and obtain the joining sequence {Rd j1 , j1=1,2,3,..,n1}, where Rd j1 represents the number of j1-th transport sections added to the corresponding travel route, and ΔS j1,N1 represents the average addition of the j1th transport section in the first N0 moments; xs j1 represents the driving difficulty of the j1th transport section at the time of obtaining; xb j1 represents the saturation quantity of the j1th transport section; sb j1 represents the actual number of the j1-th transport segment at the time of obtaining;

[0043] a correction subunit, configured to correct the driving efficiency based on the joining sequence to obtain a first efficiency;

[0044]

[0045]

[0046] Among them, γ j1 represents the adjustment coefficient of the j1th transport section; ys i Indicates the corresponding first efficiency.

[0047] Preferably, the optimization module includes:

[0048] A data acquisition unit, used for acquiring the execution process data of the target vehicle before the execution process is not guided and after the execution process is guided based on each guidance;

[0049] A factor acquisition unit, used to analyze the corresponding execution process data based on the guidance management model of each guidance execution process, and obtain the first management factor of the corresponding target vehicle;

[0050] A frequency statistics unit is used to count the frequencies under different settings and determine the driving interference factors;

[0051] a factor adjustment unit, configured to adjust the first management factor based on the driving interference factor to obtain a second management factor;

[0052] The efficiency optimization unit is used to obtain a guided optimization set based on the second management factors of all target vehicles to optimize the corresponding first efficiency.

[0053] Preferably, the frequency statistics unit includes:

[0054] A situation statistics subunit is used to count the first selection frequency of the driving route corresponding to the best garbage bin by the drivers of all target vehicles, the second selection frequency of the driving route corresponding to the second best garbage bin by the drivers of all target vehicles, the first change frequency of changing from the driving route corresponding to the best garbage bin to the driving route corresponding to the second best garbage bin, the second change frequency of changing from the driving route corresponding to the second best garbage bin to the driving route corresponding to the best garbage bin, and the non-selection frequency of not selecting the guided driving route;

[0055] The interference determination subunit is used to determine the driving interference factor from a multi-frequency combination-factor mapping table according to the first selection frequency, the second selection frequency, the first replacement frequency, the second replacement frequency and the unselected frequency.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The bin information is matched and analyzed with the vehicle garbage information to effectively balance the calorific value generated by the subsequent collection of garbage in multiple garbage bins. By matching the garbage bins to the vehicles for guidance, congestion caused by blind entry can be effectively avoided. Then, the screening process can be optimized by obtaining guidance optimization factors to improve the reliability of process analysis and further ensure the efficiency of guidance.

[0058] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 This is a structural diagram of an intelligent guidance management platform in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0063] The present invention provides a smart guidance management platform, such as Figure 1As shown, including:

[0064] The demand acquisition module is used to obtain the actual demand of the waste incineration power plant and determine the bin information of each waste bin;

[0065] The garbage bin matching module is used to obtain the vehicle garbage information of each target vehicle respectively, and match the initial bin set corresponding to the target vehicle from all garbage bins in combination with the bin information;

[0066] A sending guidance module is used to obtain the current position of the target vehicle based on the waste incineration power plant and the current transportation map of the waste incineration power plant, select the best garbage bin and the second best garbage bin from the initial bin set, and send them to the corresponding target vehicle for selection;

[0067] The optimization module is used to count the transportation dynamics of each target vehicle according to the selected guidance in real time, and to guide and manage the transportation dynamics of all target vehicles to obtain the guidance optimization set, so as to optimize the screening process of the best garbage bin and the second best garbage bin.

[0068] In this embodiment, the actual demand includes the bin information of each garbage bin of the waste incineration power plant, and the bin information includes: the bin type set of the corresponding garbage bin, the allowed vehicle permissions and the required garbage amount of each bin garbage type, and the vehicle garbage information includes: type identification results, weighing results and license plate recognition results as the vehicle garbage information of the target vehicle, wherein the garbage types include: plastic bottle type, metal type, clothing type, kitchen waste type, etc.

[0069] In this embodiment, the initial bin set includes at least one garbage bin.

[0070] In this embodiment, the current transportation map is constructed based on the distribution of vehicles on different road sections in the waste incineration plant.

[0071] In this embodiment, the best garbage bin and the second best garbage bin are determined based on the driving efficiency of the route from the current position of the target vehicle to the corresponding garbage bin.

[0072] For example, the initial bin set corresponding to vehicle A includes: garbage bin 1, garbage bin 2 and garbage bin 3, and the driving efficiency of the route to garbage bin 1 is 90%, the driving efficiency of the route to garbage bin 2 is 89%, and the driving efficiency of the route to garbage bin 3 is 60%. At this time, the best garbage bin is garbage bin 1, and the second best garbage bin is garbage bin 2.

[0073] In this embodiment, two routes are determined for the driver to choose from in order to improve autonomous selection, and the guidance optimization factor is determined by dynamically monitoring the final selected route while guiding it, that is, the accuracy of subsequent garbage bin screening is continuously optimized through the information currently continuously obtained.

[0074] In this embodiment, the guidance optimization set includes a number of guidance optimization factors, and the guidance optimization factors refer to optimizing the calculation parameters in obtaining the driving efficiency, so as to continuously improve the reliability of the subsequent screening process.

[0075] The beneficial effects of the above technical solution are: matching and analyzing the bin information with the vehicle garbage information to effectively balance the calorific value generated by the subsequent collection of garbage in multiple garbage bins, and issuing guidance to the vehicle matching the garbage bin to effectively avoid congestion caused by blind entry, and then optimizing the screening process by obtaining the guidance optimization factor to improve the reliability of the process analysis, and further ensure the efficiency of the guidance.

[0076] The present invention provides a smart guidance management platform, wherein the demand acquisition module comprises:

[0077] a heat value extraction unit, for extracting the required heat value generated by each garbage bin in the waste incineration power plant, a bin type set, and permitted vehicle permissions from the actual demand;

[0078] a range determination unit for monitoring the current calorific value of each garbage bin and determining the residual calorific value of the corresponding garbage bin in combination with the required generated calorific value of each garbage bin;

[0079] a quantity determination unit, for determining a required waste quantity of each bin waste type according to the bin type set and the residual heat value;

[0080] The bin information includes: a bin type set corresponding to the garbage bin, permitted vehicle permissions, and the required amount of garbage for each bin garbage type.

[0081] In this embodiment, the allowed vehicle permissions refer to certain restrictions on vehicles reaching the garbage bin, for example, only vehicles with license plates of Beijing A can reach garbage bin 1.

[0082] In this embodiment, the bin type set includes at least one type of garbage.

[0083] In this embodiment, the remaining heat value = the required heat value - the current heat value.

[0084] In this embodiment, the required amount of garbage for each bin garbage type = the allowable calorific value of the corresponding bin garbage type / the unit calorific value of the corresponding bin garbage type.

[0085] The beneficial effect of the above technical solution is: by extracting the heat value, type and authority from the demand, it is easy to obtain the warehouse information, which provides convenience for the subsequent matching of garbage warehouses.

[0086] The present invention provides a smart guidance management platform, wherein the garbage bin matching module comprises:

[0087] A scanning unit, used for scanning the loaded garbage of the target vehicle entering the waste incineration power plant to obtain a surface image, and analyzing the surface image to determine a loading type set corresponding to the target vehicle;

[0088] Weighing and identification unit, used to weigh the target vehicle and identify the license plate;

[0089] Among them, the type recognition result, the weighing result and the license plate recognition result are used as the vehicle junk information of the target vehicle.

[0090] In this embodiment, the surface of the target vehicle loaded with garbage is scanned by a scanning device to obtain a corresponding image, and the garbage in the image is bounded by a box selection to obtain a number of garbage. The garbage is identified by a garbage classification model to obtain the type of loaded garbage, wherein the loaded garbage set contains at least one type of garbage.

[0091] The beneficial effect of the above technical solution is: by analyzing the image to obtain the loading type set and combining the weighing and license plate recognition results to obtain the vehicle garbage information, providing a basis for subsequent matching of garbage bins.

[0092] The present invention provides a smart guidance management platform, wherein the garbage bin matching module further includes:

[0093] The authority matching unit is used to determine the garbage authority of the target vehicle according to the license plate recognition result, and match it with the allowed vehicle authority in the bin information of each garbage bin to obtain a plurality of first bins;

[0094] A type matching unit, used for matching a loading type set corresponding to the target vehicle with a bin type set in the bin information of each first bin, to obtain a plurality of second bins;

[0095] Determine the type space proportion of each loading type according to the surface image, and obtain the loading weight of each loading type in combination with the weighing result of the corresponding target vehicle;

[0096] The quantity matching element is used to match the loading weight of all loading types of the corresponding target vehicle with the required garbage quantity of all bin garbage types in the bin information of each second bin, to obtain a number of third bins;

[0097] The plurality of third bins serve as initial bin sets corresponding to the target vehicle.

[0098] In this embodiment, the garbage authority is obtained based on a license plate-authority database, which has pre-stored different license plates and the authority of the license plates, mainly to determine which garbage bin the garbage can be transported to.

[0099] In this embodiment, there are 10 garbage bins, and the first bins obtained after authority matching are: garbage bin 1, garbage bin 3, garbage bin 6, and garbage bin 7;

[0100] The second bins obtained after type matching are: garbage bin 1, garbage bin 3, and garbage bin 6;

[0101] After matching the quantities corresponding to the types, the third bins are: garbage bin 3 and garbage bin 6.

[0102] The beneficial effect of the above technical solution is that by performing three rounds of matching, the initial bin set corresponding to the target vehicle can be obtained, which provides a basis for the subsequent route determination and ensures the balance of calorific values ​​of different garbage bins.

[0103] The present invention provides a smart guidance management platform, wherein the guidance module includes:

[0104] An aerial photography unit, used for taking aerial photos of the waste incineration power plant to obtain a first image;

[0105] A positioning unit, configured to obtain a second image based on the vehicle positioning information of the waste incineration power plant captured by the Internet of Things platform;

[0106] An image analysis unit, configured to perform a comprehensive analysis on the first image and the second image to obtain a current transportation map;

[0107] an efficiency calculation unit, configured to determine the degree of vehicle congestion of a transport section between adjacent transport nodes based on the current transport graph, and obtain a driving efficiency of a corresponding target vehicle based on a driving route of each third warehouse in a corresponding initial warehouse set in combination with the node attributes of each transport node and the current position and executed process of the target vehicle;

[0108]

[0109]

[0110] Wherein, max represents the maximum value symbol; n1 represents the total number of transport sections included in the current position of the target vehicle and the driving route of the relevant third warehouse; L1 j1 V1 represents the length of the corresponding j1th transport section; j1 represents the set speed limit of the corresponding j1-th transport section; Y j1 (D j1 , S j1-1 , Sj1+1 ) represents the node attributes S of the two transport nodes based on the j1th transport segment j1-1 , S j1+1 and vehicle congestion level D j1 The time estimation function of Express satisfaction All Y j1 (D j1 , S j1-1 , S j1+1 )’s mean square error; ε1 j1 represents the sub-efficiency of the corresponding j1-th transport section; Q j1 (S j1-1 , S j1+1 ) represents the node attributes S of the two transport nodes based on the j1th transport segment j1-1 , S j1+1 The weight of the road section determined; Ny represents the number of executed processes corresponding to the target vehicle; Nz represents the total number of all executed processes corresponding to the target vehicle; L0 represents the driving length and The sum of; ty represents the actual driving time of the corresponding target vehicle under the executed process; t0 represents the estimated total guidance time of the corresponding target vehicle based on all executed processes; xs i Indicates the driving efficiency of the corresponding target vehicle;

[0111] an efficiency correction unit, configured to correct the driving efficiency to obtain a first efficiency according to a difficulty sequence in an estimated driving time period of a corresponding target vehicle driving along a driving route of a corresponding third warehouse;

[0112] A bin selection unit, used for selecting the best garbage bin corresponding to the maximum efficiency and the second best garbage bin corresponding to the second maximum efficiency from all first efficiencies;

[0113] The guidance unit is used to obtain the guidance instructions input by the driver of the corresponding target vehicle based on the guidance display screen to finally lock the bin from the best garbage bin and the second best garbage bin, and to issue guidance for the driving route corresponding to the final locked bin.

[0114] In this embodiment, the first image is an image obtained based on drone aerial photography, and the second image is obtained based on data obtained by GPS positioning. The comprehensive analysis is to compare the two images to obtain the most complete image information, obtain the current transportation map, and facilitate subsequent calculations.

[0115] In this embodiment, the overall guidance process for the waste incineration power plant includes: vehicle entry guidance → weighing guidance → license plate recognition guidance → waiting guidance at the garbage bin ramp entrance → entering the garbage bin to unload guidance → exiting the garbage bin guidance → weighing guidance → vehicle departure guidance.

[0116] This technical solution is mainly aimed at guiding the vehicle from entering the site to unloading into the garbage bin.

[0117] In this embodiment, after the third warehouse is determined, the intelligent route planning algorithm automatically plans the driving route of the vehicle from the current position to the third warehouse. The intelligent route planning algorithm can be implemented by using an existing route planning algorithm.

[0118] In this embodiment, the vehicle congestion level of the transport section = the current number of vehicles on the section / the maximum number of vehicles that can be accommodated on the section.

[0119] In this embodiment, for example, the driving route includes node 1, node 2, and node 3 that need to be passed in sequence, wherein node 1 and node 2 are adjacent, and node 2 and node 3 are adjacent.

[0120] In this embodiment, the node attributes are related to the execution functions of the corresponding nodes, such as: vehicle entry guidance → weighing guidance → license plate recognition guidance → garbage bin ramp entrance waiting guidance → garbage bin unloading guidance. Each guidance process corresponds to a node, and the process section from one guidance process to the next guidance process is the transportation section, and the execution function is the guidance function of the corresponding guidance process, such as entry guidance attributes, weighing guidance attributes, identification guidance attributes, etc.

[0121] In this embodiment, the executed process refers to the process that has been completed before the current position, for example, from the entry position A to the current position C, which includes the process: vehicle entry guidance → weighing guidance. At this time, the two processes of vehicle entry guidance → weighing guidance are regarded as executed processes, and the complete execution process of each vehicle is the same.

[0122] In this embodiment, Y j1 (D j1 , S j1-1 , S j1+1 ) is based on the results of j1 , S j1-1 , S j1+1 The database formed by the set time is matched and stored in advance and can be directly obtained.

[0123] The beneficial effects of the above technical solution are: using two technologies to obtain images to obtain the current transport map provides a reliable basis for subsequent road analysis, and calculating the driving efficiency through analysis of the current position of the vehicle, executed processes and node attributes, providing a preliminary basis for subsequent screening of reasonable routes, and further correcting and optimizing the driving efficiency through difficulty sequences, etc., to ensure the accuracy of the final efficiency acquisition, and facilitate and effectively issue guidance.

[0124] The present invention provides a smart guidance management platform, wherein the efficiency calculation unit comprises:

[0125] The sequence construction subunit is used to determine the time when the corresponding target vehicle obtains the corresponding driving route, obtain the number of command inputs at the time from the platform statistical database, and combine the number of command inputs at N0 moments before the time, and construct an input sequence in, Indicates that the time T1 is obtained d The j2th moment before T1 d-j2 The number of instruction inputs;

[0126] A quantity estimation subunit, used for determining, based on the input sequence, an estimated input quantity at a next moment based on the obtaining moment;

[0127]

[0128] in, Indicates the next moment T1 d+1 The estimated number of inputs; Ns d-N0~d Indicates that based on all The fitted value of the constructed quantity curve; Indicates all The variance of

[0129] The splitting subunit is used to split the estimated input quantity according to the driving difficulty of each transport section on the corresponding driving route at the obtained time, and obtain the joining sequence {Rd j1 , j1=1,2,3,...,n1}, where Rd j1 represents the number of j1-th transport sections added to the corresponding travel route, and ΔS j1,N1 represents the average addition of the j1th transport section at the first N0 moments; xs j1 represents the driving difficulty of the j1th transport section at the time of obtaining; xb j1 represents the saturation quantity of the j1th transport section; sb j1 represents the actual number of the j1-th transport segment at the time of obtaining;

[0130] a correction subunit, configured to correct the driving efficiency based on the joining sequence to obtain a first efficiency;

[0131]

[0132]

[0133] Among them, γ j1represents the adjustment coefficient of the j1th transport section; ys i Indicates the corresponding first efficiency.

[0134] In this embodiment, the platform statistical database includes the number of command inputs at different times, and the number of command inputs refers to the final guidance route selected by the driver and then the selection is statistically added by one.

[0135] In this embodiment, N0 may be 100.

[0136] In this embodiment, the quantity curve is for all The curve is drawn in chronological order.

[0137] The beneficial effect of the above technical solution is: by obtaining the number of command inputs at the previous moment, an input sequence is constructed to estimate the number of inputs at the next moment, and the joining sequence is obtained by combining the splitting process of driving difficulty to provide an accurate basis for subsequent correction efficiency, thereby ensuring the accuracy of the first efficiency acquisition and the efficiency of guidance.

[0138] The present invention provides a smart guidance management platform, wherein the optimization module comprises:

[0139] A data acquisition unit, used for acquiring the execution process data of the target vehicle before the execution process is not guided and after the execution process is guided based on each guidance;

[0140] A factor acquisition unit, used to analyze the corresponding execution process data based on the guidance management model of each guidance execution process, and obtain the first management factor of the corresponding target vehicle;

[0141] A frequency statistics unit is used to count the frequencies under different settings and determine the driving interference factors;

[0142] a factor adjustment unit, configured to adjust the first management factor based on the driving interference factor to obtain a second management factor;

[0143] The efficiency optimization unit is used to obtain a guided optimization set based on the second management factors of all target vehicles to optimize the corresponding first efficiency.

[0144] Preferably, the frequency statistics unit includes:

[0145] A situation statistics subunit is used to count the first selection frequency of the driving route corresponding to the best garbage bin by the drivers of all target vehicles, the second selection frequency of the driving route corresponding to the second best garbage bin by the drivers of all target vehicles, the first change frequency of changing from the driving route corresponding to the best garbage bin to the driving route corresponding to the second best garbage bin, the second change frequency of changing from the driving route corresponding to the second best garbage bin to the driving route corresponding to the best garbage bin, and the non-selection frequency of not selecting the guided driving route;

[0146] The interference determination subunit is used to determine the driving interference factor from a multi-frequency combination-factor mapping table according to the first selection frequency, the second selection frequency, the first replacement frequency, the second replacement frequency and the unselected frequency.

[0147] In this embodiment, for example, there are processes 1, 2, 3, and 4. The guidance acquisition is performed after process 2 is executed. At this time, the executed processes before the guidance are processes 1 and 2.

[0148] In this embodiment, the execution process data refers to the data generated by the corresponding target vehicle according to the guidance execution process, for example, the vehicle's driving conditions and the vehicle's license plate recognition results obtained during the guidance process after the license plate recognition.

[0149] In this embodiment, each process corresponds to a guidance management model, and both are stored in the process-model comparison table and can be directly obtained when needed.

[0150] In this embodiment, each model is obtained by training the neural network model based on samples of data that may be generated by the corresponding boot process, the management type determined by the expert's analysis of the data, and the management factor. Therefore, the management type and the first management factor can be directly obtained.

[0151] Among them, the management type can be license plate management, and the first management factor is a numerical value representing the smoothness of vehicle driving under the process, with a value ranging from 0 to 1, and the smoother the driving, the smaller the corresponding value.

[0152] In this embodiment, the multi-frequency combination-factor mapping table includes different frequency combinations and interference factors set by experts for the frequency combinations, and the value range is 0 to 1.

[0153] In this embodiment, the second management factor=the first management factor×(1-driving interference factor).

[0154] In this embodiment, the guidance optimization set = {guidance optimization factor of each target vehicle}, where the guidance optimization factor = the second management factor × the matching weight of the corresponding vehicle authority;

[0155] In this embodiment, the optimization of the first efficiency specifically refers to the optimization of Q j1 (S j1-1 ,S j1+1 ), namely: Among them, ave yh is the average value of the optimized guidance factors of all target vehicles involved in the j1th transport section at the time of acquisition; σ0 yh is the variance of the optimized guidance factor involving all target vehicles in the j1th transport section at the time of acquisition; if σ0 yh If a1 is greater than 0.1, the value of a1 is -1, otherwise it is 1.

[0156] The beneficial effect of the above technical solution is: by obtaining the Q at the moment j1 (S j1-1 ,S j1+1 ) updates to provide an accurate basis for subsequent analysis, indirectly improve subsequent efficient guidance, avoid congestion and effectively balance the calorific value of the garbage bin.

[0157] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart guidance management platform, characterized in that: include: The demand acquisition module is used to obtain the actual demand of the waste incineration power plant and determine the bin information of each waste bin; The garbage bin matching module is used to obtain the vehicle garbage information of each target vehicle respectively, and match the initial bin set corresponding to the target vehicle from all garbage bins in combination with the bin information; A sending guidance module is used to obtain the current position of the target vehicle based on the waste incineration power plant and the current transportation map of the waste incineration power plant, select the best garbage bin and the second best garbage bin from the initial bin set, and send them to the corresponding target vehicle for selection; The optimization module is used to count the transportation dynamics of each target vehicle in real time according to the selected guidance, and guide the transportation dynamics of all target vehicles to obtain the guidance optimization set to optimize the selection process of the best garbage bin and the second best garbage bin; Wherein, the demand acquisition module includes: a heat value extraction unit, for extracting the required heat value generated by each garbage bin in the waste incineration power plant, a bin type set, and permitted vehicle permissions from the actual demand; a range determination unit for monitoring the current calorific value of each garbage bin and determining the residual calorific value of the corresponding garbage bin in combination with the required generated calorific value of each garbage bin; a quantity determination unit for determining a required amount of waste for each bin waste type based on the bin type set and the residual heat value; The bin information includes: a bin type set corresponding to the garbage bin, permitted vehicle permissions, and a required amount of garbage for each bin garbage type; Wherein, the garbage bin matching module includes: A scanning unit, used for scanning the loaded garbage of the target vehicle entering the waste incineration power plant to obtain a surface image, and analyzing the surface image to determine a loading type set corresponding to the target vehicle; Weighing and identification unit, used to weigh the target vehicle and identify the license plate; Among them, the type recognition result, the weighing result and the license plate recognition result are used as the vehicle junk information of the target vehicle; Wherein, the garbage bin matching module further includes: The authority matching unit is used to determine the garbage authority of the target vehicle according to the license plate recognition result, and match it with the allowed vehicle authority in the bin information of each garbage bin to obtain a plurality of first bins; A type matching unit, used for matching a loading type set corresponding to the target vehicle with a bin type set in the bin information of each first bin, to obtain a plurality of second bins; Determine the type space proportion of each loading type according to the surface image, and obtain the loading weight of each loading type in combination with the weighing result of the corresponding target vehicle; a quantity matching unit, used for matching the loading weight of all loading types of the corresponding target vehicle with the required garbage quantity of all bin garbage types in the bin information of each second bin, to obtain a plurality of third bins; Wherein, the plurality of third bins are used as initial bin sets corresponding to the target vehicle; Wherein, the sending guidance module includes: An aerial photography unit, used for taking aerial photos of the waste incineration power plant to obtain a first image; A positioning unit, configured to obtain a second image based on the vehicle positioning information of the waste incineration power plant captured by the Internet of Things platform; An image analysis unit, configured to perform a comprehensive analysis on the first image and the second image to obtain a current transportation map; an efficiency calculation unit, configured to determine the degree of vehicle congestion of a transport section between adjacent transport nodes based on the current transport graph, and obtain a driving efficiency of a corresponding target vehicle based on a driving route of each third warehouse in a corresponding initial warehouse set in combination with the node attributes of each transport node and the current position and executed process of the target vehicle; ; ; Among them, max represents the maximum value symbol; Indicates the total number of transport sections included in the driving route between the current position of the target vehicle and the relevant third warehouse; represents the length of the corresponding j1-th transport section; represents the set speed limit of the corresponding j1-th transport section; Represents the node attributes of the two transport nodes based on the j1th transport segment and vehicle congestion The time estimation function of Express satisfaction All The mean square error of represents the sub-efficiency of the corresponding j1-th transport section; Represents the node attributes of the two transport nodes based on the j1th transport segment Determined road segment weights; Indicates the number of executed processes corresponding to the target vehicle; Indicates the total number of all execution processes corresponding to the target vehicle; Indicates the driving length of the target vehicle under the executed process and of and; Indicates the actual driving time of the corresponding target vehicle under the executed process; Indicates the estimated total guidance time of the corresponding target vehicle based on all execution processes; Indicates the driving efficiency of the corresponding target vehicle; an efficiency correction unit, configured to correct the driving efficiency to obtain a first efficiency according to a difficulty sequence in an estimated driving time period of a corresponding target vehicle driving along a driving route of a corresponding third warehouse; A bin selection unit, used for selecting the best garbage bin corresponding to the maximum efficiency and the second best garbage bin corresponding to the second maximum efficiency from all first efficiencies; The sending guidance unit is used to obtain the guidance instruction input by the driver of the corresponding target vehicle based on the guidance display screen, to finally lock the bin from the best garbage bin and the second best garbage bin, and to send guidance for the driving route corresponding to the finally locked bin; Wherein, the efficiency calculation unit includes: The sequence construction subunit is used to determine the time when the corresponding target vehicle obtains the corresponding driving route, obtain the number of command inputs at the time from the platform statistical database, and combine the number of command inputs at N0 moments before the time, and construct an input sequence ,in, Indicates the time The j2th moment before The number of instruction inputs; A quantity estimation subunit, used for determining, based on the input sequence, an estimated input quantity at a next moment based on the obtaining moment; ; in, Indicates the next moment Estimated number of inputs; Indicates that based on all The fitted value of the constructed quantity curve; Indicates all The variance of A splitting subunit is used to split the estimated input quantity according to the driving difficulty of each transport section on the corresponding driving route at the obtained time, and obtain the joining sequence of the corresponding driving route. ,in, represents the number of j1-th transport sections added to the corresponding travel route, and Indicates that the j1th transport section is in front The average amount added at each moment; represents the driving difficulty of the j1-th transport section at the obtained time; represents the saturated quantity of the j1th transport section; represents the actual number of the j1-th transport segment at the time of obtaining; a correction subunit, configured to correct the driving efficiency based on the joining sequence to obtain a first efficiency; ; ; in, represents the adjustment coefficient of the j1th transport section; Indicates the corresponding first efficiency.

2. The intelligent guidance management platform according to claim 1, characterized in that: The optimization module comprises: A data acquisition unit, used for acquiring the execution process data of the target vehicle before the execution process is not guided and after the execution process is guided based on each guidance; A factor acquisition unit, used to analyze the corresponding execution process data based on the guidance management model of each guidance execution process, and obtain the first management factor of the corresponding target vehicle; A frequency statistics unit is used to count the frequencies under different settings and determine the driving interference factors; a factor adjustment unit, configured to adjust the first management factor based on the driving interference factor to obtain a second management factor; The efficiency optimization unit is used to obtain a guided optimization set based on the second management factors of all target vehicles to optimize the corresponding first efficiency.

3. The intelligent guidance management platform according to claim 2, characterized in that: The frequency statistics unit includes: A situation statistics subunit is used to count the first selection frequency of the driving route corresponding to the best garbage bin by the drivers of all target vehicles, the second selection frequency of the driving route corresponding to the second best garbage bin by the drivers of all target vehicles, the first change frequency of changing from the driving route corresponding to the best garbage bin to the driving route corresponding to the second best garbage bin, the second change frequency of changing from the driving route corresponding to the second best garbage bin to the driving route corresponding to the best garbage bin, and the non-selection frequency of not selecting the guided driving route; The interference determination subunit is used to determine the driving interference factor from a multi-frequency combination-factor mapping table according to the first selection frequency, the second selection frequency, the first replacement frequency, the second replacement frequency and the unselected frequency.