Method and system for geological hazard early warning in tunnel construction by drill-and-blast method

Abstract

A method and system for geological hazard early warning in tunnel construction by a drill-and-blast method. The method comprises: acquiring construction information of historical tunnels constructed by a drill-and-blast method, and determining risk levels thereof; constructing individual bag-of-words models of the construction information under different risk levels, and constructing a shared-vocabulary bag-of-words model and a full-vocabulary bag-of-words model; calculating the word frequency of each vocabulary item in the full-vocabulary bag-of-words model and the word frequency thereof in each individual bag-of-words model, and constructing a full-vocabulary word frequency table and a risk-level-vocabulary word frequency table; on the basis of the risk-level-vocabulary word frequency table, calculating the risk-level word frequency quotient of each vocabulary item, so as to determine the score of each vocabulary item; and removing, from a bag-of-words model to be tested, vocabulary items in the shared-vocabulary bag-of-words model to obtain a feature bag-of-words model, calculating the word frequency of each vocabulary item in the feature bag-of-words model to obtain a vocabulary word frequency table to be tested, and calculating the word frequency quotient of the vocabulary word frequency table to be tested and the full-vocabulary word frequency table to obtain a hazard early-warning risk level of a tunnel to be tested in a construction period, thereby providing timely hazard early warning for a tunnel under construction.

Description

Drilling and blasting tunnel construction geological disaster early warning method and system

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202411307806.5, filed on September 19, 2024, and entitled "Drilling and blasting tunnel construction geological disaster early warning method and system", the entire contents of which are incorporated herein by reference and form a part of the present application for all purposes. TECHNICAL FIELD

[0003] The present application relates to the field of tunnel disaster early warning, in particular to a drilling and blasting tunnel construction geological disaster early warning method and system. BACKGROUND

[0004] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0005] In tunnel engineering construction, disasters such as water gushing, collapse, and large deformation frequently occur, which pose great risks and serious threats to the project. In order to ensure the safety of tunnel construction and the safety of personnel's life and property, timely detection of potential disaster hazards, taking preventive measures, reducing safety accidents, improving work efficiency, and completing the construction task with quality and quantity, disaster monitoring and early warning are particularly important.

[0006] Currently, drilling and blasting tunnel construction geological disaster early warning often relies on experienced engineers to comprehensively analyze geological information, geophysical information, monitoring information, and drilling information, etc., to give disaster grades. Engineers need to analyze text reports that reflect disaster state and damage degree, which is time-consuming and laborious, low in efficiency, and difficult to deal with massive tunnel construction information. On the other hand, over-reliance on engineers' subjective experience may lead to false alarms due to differences in subjective factors among different engineers. SUMMARY

[0007] To solve the above problems, the present application provides a drilling and blasting tunnel construction geological disaster early warning method and system, which is based on TF-IDF (term frequency-inverse document frequency) keyword extraction technology to provide timely disaster early warning for tunnel construction during construction period, assist experts in evaluation, reduce human subjective factor interference, and timely and accurately predict tunnel construction disasters through keyword frequency analysis of tunnel construction information.

[0008] To achieve the above purpose, the present application adopts the following technical solutions:

[0009] The first aspect of the present application provides a geological disaster early warning method for drill-and-blast tunnel construction, comprising:

[0010] Construction information of a drill-and-blast tunnel is obtained to determine the risk level thereof;

[0011] A bag-of-words model of construction information under different risk levels is constructed, and a common vocabulary bag-of-words model and an all-vocabulary bag-of-words model are constructed based on the bag-of-words model;

[0012] The frequency of each vocabulary in the all-vocabulary bag-of-words model and the frequency in each bag-of-words model are calculated, thereby constructing an all-vocabulary frequency table and a risk level vocabulary frequency table; the risk level frequency quotient of each vocabulary is calculated based on the risk level vocabulary frequency table, and the score of each vocabulary is determined;

[0013] A to-be-tested bag-of-words model is constructed based on the construction information of a to-be-tested tunnel; a feature bag-of-words model is obtained by removing the vocabulary in the common vocabulary bag-of-words model from the to-be-tested bag-of-words model; a to-be-tested vocabulary frequency table is obtained by calculating the frequency of each vocabulary in the feature bag-of-words model; and the frequency quotient of the to-be-tested vocabulary frequency table and the all-vocabulary frequency table is calculated;

[0014] The disaster early warning risk level of the to-be-tested tunnel during the construction period is obtained based on the frequency quotient and the score of each vocabulary.

[0015] As an optional implementation, construction information with the same risk level is combined, thereby constructing a bag-of-words model of construction information under different risk levels, and the common vocabulary bag-of-words model is composed of the vocabulary commonly contained in the bag-of-words model, and the all-vocabulary bag-of-words model is composed of all the vocabulary in the bag-of-words model without deduplication.

[0016] As an optional implementation, the frequency F Ai of each vocabulary in the risk level vocabulary frequency table in each bag-of-words model is:

[0017] wherein n 1i is the number of times each vocabulary appears in the ith bag-of-words model; n 2i is the total number of words in the ith bag-of-words model without deduplication; n 3i is the number of tunnels corresponding to each vocabulary in the ith bag-of-words model; and n 4i is the number of tunnels under the risk level corresponding to the ith bag-of-words model.

[0018] As an optional implementation, the risk level frequency quotient P Ai of each vocabulary is:

[0019] The score K of each vocabulary is:

[0020] wherein F Ai is the word frequency of each vocabulary in the i-th bag-of-words model, Aj is the word frequency of each vocabulary in the j-th bag-of-words model.

[0021] As an alternative embodiment, the word frequency of each vocabulary in the all-vocabulary word frequency table is the ratio of the total number of occurrences of each vocabulary in each bag-of-words model to the total number of words without deduplication in all bag-of-words models.

[0022] As an alternative embodiment, the word frequency of each vocabulary in the feature bag-of-words model is the ratio of the number of occurrences of each vocabulary in the feature bag-of-words model to the total number of words without deduplication in the feature bag-of-words model.

[0023] As an alternative embodiment, the word frequency quotient of the test vocabulary word frequency table and the all-vocabulary word frequency table is the ratio of the word frequency of each vocabulary in the test vocabulary word frequency table to the word frequency of each vocabulary in the all-vocabulary word frequency table.

[0024] As an alternative embodiment, the disaster early warning score X of the test tunnel during the construction period is obtained according to the word frequency quotient and the score of each vocabulary, and the disaster early warning risk level of the test tunnel during the construction period is obtained according to the disaster early warning score.

[0025] wherein n is the total number of words in the test bag-of-words model, P i is the word frequency quotient of the i-th vocabulary, K i is the score of the i-th vocabulary.

[0026] In a second aspect, the present application provides a drilling and blasting method tunnel construction geological disaster early warning system, comprising:

[0027] The acquisition module is configured to acquire construction information of a drilling and blasting method historical construction tunnel to determine the risk level thereof;

[0028] The bag-of-words model construction module is configured to construct bag-of-words models of construction information under different risk levels, and to construct a common vocabulary bag-of-words model and an all-vocabulary bag-of-words model therefrom;

[0029] The first calculation module is configured to calculate the word frequency of each vocabulary in the all-vocabulary bag-of-words model and the word frequency in each bag-of-words model, thereby constructing an all-vocabulary word frequency table and a risk level vocabulary word frequency table; calculate the risk level word frequency quotient of each vocabulary according to the risk level vocabulary word frequency table, and determine the score of each vocabulary therefrom;

[0030] The second calculation module is configured to construct a to-be-tested bag-of-words model according to the to-be-tested tunnel construction information, remove the words in the common word bag-of-words model from the to-be-tested bag-of-words model to obtain a feature bag-of-words model, calculate the word frequency of each word in the feature bag-of-words model to obtain a to-be-tested word frequency table, and calculate the word frequency quotient of the to-be-tested word frequency table and all word frequency tables;

[0031] The evaluation module is configured to obtain the disaster early warning risk level of the to-be-tested tunnel in the construction period according to the word frequency quotient and the score of each word.

[0032] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, and computer instructions stored in the memory and running on the processor, when the computer instructions are run by the processor, the method of the first aspect is completed.

[0033] In a fourth aspect, the present application provides a computer readable storage medium for storing computer instructions, when the computer instructions are executed by the processor, the method of the first aspect is completed.

[0034] In a fifth aspect, the present application provides a computer program product comprising a computer program, when the computer program is executed by the processor, the method of the first aspect is completed.

[0035] Compared with the prior art, the present application has the following beneficial effects:

[0036] The present application provides a drilling and blasting method tunnel construction geological disaster early warning method and system, which is based on TF-IDF keyword extraction technology, provides timely disaster early warning for the tunnel in the construction period, assists experts in evaluation, reduces the interference of human subjective factors, and can timely and accurately predict the tunnel construction disaster through word frequency analysis of the tunnel construction information keywords without relying on artificial experience for on-site decision-making.

[0037] The advantages of the additional aspects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be known by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only belong to the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0039] Fig. 1 is a drilling and blasting method tunnel construction geological disaster early warning method flow chart provided by the embodiment 1 of the present application;

[0040] Fig. 2 is a flow chart of a typical tunnel bag calculation according to an embodiment of the present application;

[0041] Fig. 3 is a flow chart of a tunnel bag calculation to be tested according to an embodiment of the present application;

[0042] Fig. 4 is a flow chart of a tunnel risk evaluation according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] The present application will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0045] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0046] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0047] Embodiment 1

[0048] The present embodiment provides a drilling and blasting method tunnel construction geological disaster early warning method based on TF-IDF keyword extraction. In the case where the decision cannot be made by relying on manual experience on site, the tunnel construction disaster early warning can be made timely and accurately.

[0049] As shown in Fig. 1, it specifically comprises:

[0050] Construction information of a drilling and blasting method historical construction tunnel is acquired to determine the risk level thereof;

[0051] A word bag model of construction information under different risk levels is constructed, and a common vocabulary word bag model and an all-vocabulary word bag model are constructed based thereon;

[0052] The word frequency of each word in all word bag models and the word frequency in each word bag model are calculated, thereby constructing the word frequency table of all words and the word frequency table of risk level words; the risk level word frequency quotient of each word is calculated according to the word frequency table of risk level words, and the score of each word is determined;

[0053] The word bag model to be tested is constructed according to the tunnel construction information to be tested, the feature word bag model is obtained by removing the words in the common word bag model from the word bag model to be tested, the word frequency of each word in the feature word bag model is calculated to obtain the word frequency table to be tested, and the word frequency quotient of the word frequency table to be tested and the word frequency table of all words is calculated;

[0054] The disaster early warning risk level of the tunnel to be tested in the construction period is obtained according to the word frequency quotient and the score of each word.

[0055] In this embodiment, first of all, an expert evaluation system is constructed;

[0056] The construction information is obtained from the typical tunnel construction cases of different risk types of drill and blast method in historical construction projects, including geological information, geophysical prospecting information, monitoring information and drilling information, etc.

[0057] According to the geological factor grading standard, the evaluation indexes are determined, including the development degree of rock mass structure, the completeness of rock mass, the underground water level, the tunnel burial depth, the surrounding rock grade, the water outflow condition of the tunnel face and the block falling condition of the tunnel face, etc.

[0058] The importance degree of the above-mentioned 7 evaluation indexes is sorted by using the analytic hierarchy process, the weight of each evaluation index is calculated according to the sorting result, each evaluation index in each case is weighted according to the corresponding weight, thereby the construction period disaster risk score of different tunnels is calculated, the interval is 1-4 points, and the risk level thereof is determined according to the construction period disaster risk score, including low, medium, high and extremely high.

[0059] In this embodiment, as shown in FIG. 2, the typical tunnel construction information of the same risk level is combined, thereby constructing the word bag models A1-A4 of typical construction period tunnel construction information under different risk levels, the words commonly contained in the word bag models A1-A4 are composed into the common word bag model C, and all the words in the word bag models A1-A4 are not removed to form the word bag model D of all words.

[0060] The word frequency of each word in all word bag models D is calculated, thereby forming the word frequency table of all words, wherein the word frequency F1 of each word is:

[0061] Wherein, n1 is the total number of times each word appears in each word bag model; n2 is the total number of words without removing all word bag models.

[0062] The word frequency of each vocabulary in the word bag model A1-A4 is calculated in all vocabulary bag models D, thereby forming a risk level vocabulary word frequency table, wherein the word frequency F of each vocabulary in the ith word bag model Ai is:

[0063] wherein n 1i is the number of occurrences of each vocabulary in the ith word bag model; n 2i is the total number of words in the ith word bag model without deduplication; n 3i is the number of tunnels corresponding to each vocabulary in the ith word bag model, and the total number of tunnels in which the vocabulary exists is n 4i is the number of tunnels in the risk level corresponding to the ith word bag model, and the total number of tunnels is

[0064] According to the risk level vocabulary word frequency table, the risk level word frequency quotient P of each vocabulary is calculated Ai : and the score K of each vocabulary is calculated based on the word frequency quotient: and K must be a real number in [1, 4].

[0065] wherein F Ai represents the word frequency of each vocabulary in the ith word bag model in the word bag models A1-A4, F Aj represents the word frequency of each vocabulary in the jth word bag model in the word bag models A1-A4, P Ai represents the word frequency quotient of each vocabulary with respect to the ith word bag in the word bag models A1-A4.

[0066] In this embodiment, in the process of constructing the word bag models of the construction period tunnels under four risk levels, the redundant search results in the risk level tunnel logs are removed, and each remaining search result is preprocessed to obtain the word bag models of different risk levels.

[0067] The preprocessing of each remaining search result includes: sequentially performing word segmentation and cleaning processing on each remaining search result, and unifying English letters to lowercase form, screening keywords and high-frequency words as the bag basis, and not performing deduplication processing on these words, i.e. ensuring that the number of occurrences of each vocabulary in a construction report is completely presented, thereby obtaining the word bag models of the construction period tunnels under four risk levels.

[0068] In the embodiment, as shown in FIG. 3, when the tunnel construction requiring construction period disaster warning is carried out, the to-be-tested bag-of-words model E is obtained according to the to-be-tested tunnel construction information, the feature bag-of-words model G is obtained by subtracting the words in the common word bag-of-words model C from the to-be-tested bag-of-words model E, the word frequency of each word in the feature bag-of-words model G is calculated, and the to-be-tested word frequency table is formed, wherein the word frequency F2 of each word is:

[0069] wherein n5 is the number of times each word in the feature bag-of-words model G appears, and n6 is the total number of words in the feature bag-of-words model G without deduplication.

[0070] The word frequency quotient P of the to-be-tested word frequency table F2 and the word frequency table F1 of all words is calculated, that is, the quotient of the word frequency of each word in the to-be-tested word frequency table F2 and the word frequency of each word in the word frequency table F1 of all words;

[0071] wherein n7 is the total number of words in the feature bag-of-words model G after deduplication.

[0072] In the embodiment, it is judged whether the to-be-tested bag-of-words model E contains the same words as the common word bag-of-words model C. If all the words are the same, there is no risk at present, and the detection is automatically exited.

[0073] In the embodiment, as shown in FIG. 4, according to the word frequency quotient and the score of each word, the disaster warning score X of the to-be-tested tunnel in the construction period is obtained:

[0074] wherein n is the total number of words in the to-be-tested bag-of-words model, P i is the word frequency quotient of the i-th word, K i is the score of the i-th word; the single item P i *K i ∈ [1, 4]: when the single item P i *K i > 4, the value = 4, the single item P i *K i < 1, the value = 1.

[0075] According to the disaster warning score, the risk level (low, medium, high, and extremely high) of the to-be-tested tunnel is determined, so as to carry out the construction disaster warning evaluation of the to-be-tested tunnel.

[0076] Verification example

[0077] Step S1: Select n4 typical tunnel construction cases of different risk types in historical construction projects, obtain their geological information, geophysical information, monitoring information and drilling information (hereinafter referred to as construction information), as shown in Table 1; according to the geological factor classification standard, determine the rock mass structure development degree, rock mass integrity degree, groundwater level, tunnel depth, surrounding rock grade, face water outflow condition, face spalling condition and other 7 indexes; invite experts to sort the importance of the 7 indexes according to the relevant laws of analytic hierarchy process, calculate the weight of each index according to the sorting, and calculate the construction period disaster risk score of different tunnels by weighting the scores of each index, with the interval being 1-4 points, and determine the risk level according to the score, which is divided into "low, medium, high and extremely high" four levels, and the number of tunnels of the four risk levels is n 4i (i∈{1,2,3,4}) and

[0078] Table 1: Geological factor classification standard

[0079] Step S2: As shown in Figure 2, the tunnel construction information of the four different risk level tunnels in Table 1 is obtained respectively, the same scoring typical tunnel construction information is combined, and the redundant search results in the tunnel log of the same risk level are removed.

[0080] The search results are sequentially subjected to word segmentation processing and cleaning processing, and the English letters are unified into lowercase form, and the keywords and high-frequency words are selected as the bag-of-words basis, and these words are not subjected to deduplication processing, that is, the number of times each word appears in all construction reports is completely presented.

[0081] The bag-of-words models A1-A4 of the four risk levels of the construction period tunnels are obtained respectively, the common words in A1-A4 form the common word bag-of-words model C, and all the words in A1-A4 form the all-word bag-of-words model D, that is, C=A1∩A2∩A3∩A4, and deduplication; D=A1∪A2∪A3∪A4, without deduplication.

[0082] The word frequency, word frequency quotient and score of each word in the all-word bag-of-words model D existing in the 1-4 point risk level bag-of-words models A1-A4 are calculated.

[0083] Specifically:

[0084] Select each word in the all-word bag-of-words model D in turn, and count the number n 1i (i∈{1,2,3,4}) and The total number n 2i (i∈{1,2,3,4}) and Calculate the word frequency table F1 of all words, where the word frequency of each word is

[0085] Count the number of tunnels n in which each word exists in the 1-4 risk level bag-of-words models A1-A4 3i (i∈{1,2,3,4}), then the total number of tunnels in which the word exists is Calculate the word frequency of each word in the 1-4 risk level bag-of-words models A1-A4 in turn, and form the risk level word frequency table as: Calculate the risk level word frequency quotient P of each word Ai (P A1 -P A4 ):

[0086] Calculate the score of each word in the bag-of-words model D: and K must be a real number in [1, 4].

[0087] Step S3: As shown in FIG. 3, when a tunnel construction requiring a construction period disaster warning is performed, obtain the construction information of the tunnel to be detected, sort the key information in the log such as the development degree of rock mass structure, the completeness of rock mass, groundwater level, tunnel depth, surrounding rock grade, face water outflow condition, face spalling condition, and other key information in tunnel construction, perform word segmentation processing and cleaning processing on the log, and unify the English letters to lowercase form, screen the keywords and high-frequency words as the bag-of-words basis, and do not remove duplicates for these words, that is, ensure that the number of times each word appears in the current construction report is completely presented.

[0088] Obtain the test bag-of-words model E, compare the bag-of-words model E with the common word bag-of-words model C, and determine whether the test bag-of-words model contains the same words as the common word bag-of-words model C. If all the words are the same, there is no risk, and the detection is automatically exited. This operation means that when the words contained in the test bag-of-words model are all common words of the four risks (i.e., safe words), the risk level of the tunnel is very low, and there is no need to continue detection.

[0089] Subtract the words in the common word bag-of-words model C from the test bag-of-words model E to obtain the feature bag-of-words model G, and count the total number of non-removed words n6 in the bag-of-words. The corresponding total number of removed words is n7. In turn, select each word in the feature bag-of-words model G, and count the number of times n5 that the word appears in the model G. Calculate the word frequency table F2 of the test words, where the word frequency of each word is

[0090] Select all the words in the feature bag model G, calculate the word frequency table F2 of all the words and the corresponding word frequency of the words in the word frequency table F1, and the word frequency quotient P is the quotient of the word frequency in the word frequency table F2 and the word frequency in the word frequency table F1, that is

[0091] Step S4: As shown in FIG. 4, calculate the tunnel disaster warning score X during construction period: Single P i *K i ∈[1,4]: When single P i *K i >4, the value = 4, single P i *K i <1, the value = 1, so: X∈{1,2,3,4} is an integer from 1 to 4, corresponding to the corresponding risk level.

[0092] According to the score, the tunnel to be detected is evaluated for construction disaster warning, that is, the value of X, which is an integer from 1 to 4, is used to correspond the tunnel to be detected to the corresponding risk level.

[0093] And the relevant staff in the construction disaster perception and disaster elimination practice of the tunnel to be detected in the construction disaster warning risk level parameter value of the above-mentioned tunnel to be detected in the construction period.

[0094] Embodiment 2

[0095] The embodiment provides a drilling and blasting method tunnel construction geological disaster warning system, comprising:

[0096] The acquisition module is configured to acquire construction information of a drilling and blasting method historical construction tunnel to determine the risk level thereof;

[0097] The bag-of-words model construction module is configured to construct a bag-of-words model of construction information under different risk levels, and to construct a common word bag-of-words model and an all-word bag-of-words model therefrom;

[0098] The first calculation module is configured to calculate the word frequency of each word in the all-word bag-of-words model and the word frequency in each bag-of-words model, thereby constructing an all-word frequency table and a risk level word frequency table; according to the risk level word frequency table, calculate the risk level word frequency quotient of each word, and determine the score of each word therefrom;

[0099] The second calculation module is configured to construct a to-be-detected bag-of-words model according to the construction information of the to-be-detected tunnel, remove the words in the common word bag-of-words model from the to-be-detected bag-of-words model to obtain a feature bag-of-words model, calculate the word frequency of each word in the feature bag-of-words model to obtain a to-be-detected word frequency table, and calculate the word frequency quotient of the to-be-detected word frequency table and the all-word frequency table;

[0100] The evaluation module is configured to obtain the disaster early warning risk level of the tunnel under test during the construction period according to the word frequency quotient and the score of each vocabulary.

[0101] It should be noted that the above modules correspond to the steps described in Embodiment 1, and the above modules have the same examples and application scenarios as the corresponding steps, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules can be executed in a computer system such as a set of computer executable instructions as part of the system.

[0102] In more embodiments, there are also provided:

[0103] An electronic device includes a memory and a processor, and computer instructions stored on the memory and running on the processor, when the computer instructions are executed by the processor, the method described in Embodiment 1 is completed. For brevity, it will not be described here.

[0104] It should be understood that in the embodiments, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSPs, application-specific integrated circuits ASICs, ready-to-program gate arrays FPGA or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0105] The memory can include read-only memory and random access memory, and provide instructions and data to the processor, and a part of the memory can also include non-volatile random access memory. For example, the memory can also store device type information.

[0106] A computer readable storage medium for storing computer instructions, when the computer instructions are executed by the processor, the method described in Embodiment 1 is completed.

[0107] The method in Embodiment 1 can be directly embodied as a hardware processor to complete, or a combination of hardware and software modules in the processor to complete. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0108] A computer program product includes a computer program, when the computer program is executed by the processor, the method described in Embodiment 1 is implemented.

[0109] The present application also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer executable instructions, for example, instructions embodied in program modules, executed by devices at the target real or virtual processor to perform the processes / methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules can be combined or split between program modules as desired in various embodiments. Machine executable instructions for program modules can be executed within a local or distributed device. In a distributed device, program modules can be located in local and remote memory storage devices.

[0110] Computer program code for carrying out operations of the present application can be written in one or more programming languages. These computer program codes can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program codes, when executed by the computer or other programmable data processing apparatus, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program codes can be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0111] In the context of the present application, the computer program code or related data can be carried by any suitable carrier to enable the device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, and the like. Examples of signals can include electrical, optical, radio, sound or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

[0112] Those skilled in the art can understand that the units and algorithm steps of the examples described in conjunction with the embodiments can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0113] The above describes the specific embodiments of the present application in conjunction with the accompanying drawings, but is not a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications or variations made by those skilled in the art on the basis of the technical solutions of the present application without inventive labor are still within the scope of protection of the present application.

Claims

1. A geological disaster early warning method for drill-and-blast tunnel construction, characterized in that, The method comprises the following steps: obtaining construction information of a historical tunnel constructed by the drill and blast method, and determining a risk level thereof; constructing a bag-of-words model of the construction information under different risk levels, and constructing a common word bag-of-words model and an all-word bag-of-words model based on the bag-of-words model; calculating the word frequency of each word in the all-word bag-of-words model and the word frequency in each bag-of-words model, and thereby constructing an all-word frequency table and a risk level word frequency table; calculating the risk level word frequency quotient of each word based on the risk level word frequency table, and determining the score of each word based on the risk level word frequency quotient; constructing a test bag-of-words model based on the construction information of a tunnel to be tested, removing the words in the common word bag-of-words model from the test bag-of-words model to obtain a feature bag-of-words model, calculating the word frequency of each word in the feature bag-of-words model to obtain a test word frequency table, and calculating the word frequency quotient of the test word frequency table and the all-word frequency table; obtaining the disaster early warning risk level of the tunnel to be tested during the construction period based on the word frequency quotient and the score of each word.

2. The geological disaster early warning method for drill-and-blast tunnel construction of claim 1, wherein, The construction information with the same risk level is combined to construct the bag-of-words model of the construction information under different risk levels, the words commonly included in the bag-of-words model are combined to form the common word bag-of-words model, and all the words in the bag-of-words model are combined without duplication to form the all-word bag-of-words model.

3. The geological disaster early warning method for drill-and-blast tunnel construction of claim 1, wherein, Frequency of each vocabulary in the risk level vocabulary word frequency table in each bag-of-words model F Ai To: wherein n 1i is the number of occurrences of each vocabulary in the ith bag-of-words model; n 2i is the total number of words without deduplication in the ith bag-of-words model; n 3i is the number of tunnels corresponding to each vocabulary in the ith bag-of-words model; and n 4i is the number of tunnels in the risk level corresponding to the ith bag-of-words model.

4. The geological disaster early warning method for drill-and-blast tunnel construction of claim 1, wherein, A risk level word frequency quotient P for each vocabulary Ai To: The score K for each vocabulary is: where F Ai is the word frequency of each vocabulary within the ith bag-of-words model, Aj is the word frequency of each vocabulary within the jth bag-of-words model.

5. The geological disaster early warning method for drill-and-blast tunneling according to claim 1, characterized in that, The word frequency of each word in the all-word frequency table is the ratio of the total number of times each word appears in each bag-of-words model to the total number of words without duplication in all the bag-of-words models; The word frequency of each word in the feature bag-of-words model is the ratio of the number of times each word appears in the feature bag-of-words model to the total number of words without duplication in the feature bag-of-words model; The word frequency quotient of the test word frequency table and the all-word frequency table is the ratio of the word frequency of each word in the test word frequency table to the word frequency of each word in the all-word frequency table.

6. The geological disaster early warning method for drill-and-blast tunneling according to claim 1, characterized in that, According to the word frequency quotient and the score of each vocabulary, a disaster early warning score X of the to-be-tested tunnel in the construction period is obtained, and according to the disaster early warning score, a disaster early warning risk level of the to-be-tested tunnel in the construction period is obtained. where n is the total number of words in the bag-of-words model to be tested, P i is the word frequency quotient of the i-th word, K i is the score of the i-th word.

7. A geological disaster early warning system for drill and blast tunnel construction, characterized in that, The method comprises the following steps: an obtaining module configured to obtain construction information of a historical tunnel constructed by the drill and blast method, and determine a risk level thereof; a bag-of-words model construction module configured to construct a bag-of-words model of the construction information under different risk levels, and construct a common word bag-of-words model and an all-word bag-of-words model based on the bag-of-words model; a first calculating module configured to calculate the word frequency of each word in the all-word bag-of-words model and the word frequency in each bag-of-words model, and thereby construct an all-word frequency table and a risk level word frequency table; a second calculating module configured to calculate the risk level word frequency quotient of each word based on the risk level word frequency table, and determine the score of each word based on the risk level word frequency quotient; a second calculating module configured to construct a test bag-of-words model based on the construction information of a tunnel to be tested, remove the words in the common word bag-of-words model from the test bag-of-words model to obtain a feature bag-of-words model, calculate the word frequency of each word in the feature bag-of-words model to obtain a test word frequency table, and calculate the word frequency quotient of the test word frequency table and the all-word frequency table; an evaluation module configured to obtain the disaster early warning risk level of the tunnel to be tested during the construction period based on the word frequency quotient and the score of each word.

8. An electronic device, comprising: The computer program product comprises a memory and a processor, and computer instructions stored in the memory and run on the processor, and when the computer instructions are run by the processor, the method of any one of claims 1-6 is completed.

9. A computer-readable storage medium, characterized in that, A computer program product for storing computer instructions which, when executed by a processor, perform the method of any one of claims 1-6.

10. A computer program product, characterised in that, A computer program for implementing the method of any one of claims 1-6 when executed by a processor.

Images