CN116433032A - Intelligent assessment method based on web crawler mode - Google Patents

Intelligent assessment method based on web crawler mode Download PDF

Info

Publication number
CN116433032A
CN116433032A CN202310463992.0A CN202310463992A CN116433032A CN 116433032 A CN116433032 A CN 116433032A CN 202310463992 A CN202310463992 A CN 202310463992A CN 116433032 A CN116433032 A CN 116433032A
Authority
CN
China
Prior art keywords
resource
index
weight
occurrence
resources
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310463992.0A
Other languages
Chinese (zh)
Other versions
CN116433032B (en
Inventor
雷添杰
刘布春
李翔宇
朱宣谕
李昊阳
王赛鸽
杨晓娟
王麒粤
韩锐
季子琦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Environment and Sustainable Development in Agriculturem of CAAS
Original Assignee
Institute of Environment and Sustainable Development in Agriculturem of CAAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Environment and Sustainable Development in Agriculturem of CAAS filed Critical Institute of Environment and Sustainable Development in Agriculturem of CAAS
Priority to CN202310463992.0A priority Critical patent/CN116433032B/en
Publication of CN116433032A publication Critical patent/CN116433032A/en
Application granted granted Critical
Publication of CN116433032B publication Critical patent/CN116433032B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Databases & Information Systems (AREA)
  • Pure & Applied Mathematics (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Algebra (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an intelligent assessment method based on a web crawler mode, which comprises the following steps: step 1: according to the source type, constructing a network resource, screening a loss keyword related to a target disaster from each first sub-resource in the network resource, and establishing a loss evaluation system; step 2: respectively carrying out resource retrieval on all the first resources by adopting a web crawler mode; step 3: according to the resource retrieval result, counting the first occurrence probability of disaster events of different disaster types in the locking time period to serve as the first occurrence weight of the corresponding secondary index, and further determining the second occurrence weight of each tertiary index based on the corresponding secondary key index; step 4: and determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index.

Description

Intelligent assessment method based on web crawler mode
Technical Field
The invention relates to the technical field of intelligent evaluation, in particular to an intelligent evaluation method based on a web crawler mode.
Background
The GDP loss of the national people caused by the natural disasters reaches billions of yuan each year, and huge losses are brought to the social development, the urban development and the national economy of the country, so that the research on GDP loss evaluation of the national natural disasters has very important significance for the evaluation, the prejudgment and the prevention of the national natural disasters, and provides reference basis for disaster prevention and reduction projects in areas where the natural disasters easily occur in the country.
At present, no effective method and system for evaluating GDP loss related to natural disasters nationwide exist at home and abroad. The research direction of disaster assessment at home and abroad is usually mainly risk assessment, risk prediction, single disaster loss and overall disaster prevention and reduction capability assessment, and meanwhile, in the process of aiming at the risk assessment, a large amount of human factors are often doped to interfere the final risk assessment, so that the accuracy of an assessment result is poor.
Therefore, aiming at the problems, the invention provides an intelligent assessment method based on a web crawler mode for the first time. Firstly, network microblogs, network news, disaster reports, papers, network newspapers and the like are taken as platforms, key words of various natural disasters which cause loss to the GDP of China are determined, and an evaluation system of the natural disasters which cause loss to the GDP of China is established according to the key words obtained by crawlers. And counting the occurrence probability of each natural disaster event nationwide and taking the probability as the weight of each level of index in the evaluation system. The probability of each level of index appearance is counted, wherein the probability of each level of index appearance comprises the probability of each level of index in the third level of index and the conditional probability of each level of index in the second level of index, and the weights of the indexes are distributed by adopting a Bayesian network method on the basis of the probability, so that the loss caused by natural disasters to the national GDP is objectively evaluated. The method has the advantages that in the process of evaluating GDP loss of natural disasters nationwide, all data about the natural disasters are objective data, no influence of any human factors is caused, and compared with the traditional method, the method has the advantages that the interference of subjective factors on evaluation results is avoided, and the objectivity and scientificity of the evaluation results are improved.
Disclosure of Invention
The invention provides an intelligent assessment method based on a web crawler mode, which is characterized in that objective fact data is mainly utilized to count the weight of disaster events, and the objective weight of each level of index is further obtained by obtaining the occurrence probability of a third level index and the conditional probability of a second level index in the web resource crawler mode, so that the assessment of GDP loss of natural disasters nationwide is completed, and the assessment accuracy is improved.
The invention provides an intelligent assessment method based on a web crawler mode, which comprises the following steps:
step 1: according to source types, constructing network resources, screening loss keywords related to target disasters from first resources of each source type, and building a loss evaluation system;
step 2: respectively carrying out resource retrieval on all the first resources by adopting a web crawler mode;
step 3: according to the resource retrieval result, counting the first occurrence probability of disaster events of different disaster types in the locking time period to serve as the first occurrence weight of the corresponding secondary index, and further determining the second occurrence weight of each tertiary index based on the corresponding secondary key index;
step 4: determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index;
step 5: calculating to obtain a third appearance weight corresponding to the first-level index based on the index conditional probability and the set weight of the corresponding first-level index;
step 6: and acquiring and obtaining a disaster evaluation result based on each third occurrence weight and the matched disaster loss.
Preferably, further determining the second occurrence weight of each third level indicator based on the corresponding second level key indicator includes:
Figure BDA0004201763410000021
wherein P (A) 11 ) Representing three-level index A 11 Based on the corresponding secondary index A 1 Is a second occurrence weight of (2); p (A) 1 A 11 ) Representing the secondary index A 1 Is a first occurrence weight of (2); p (A) 1 |A 11 ) Representing the corresponding secondary index A 1 Is a probability of occurrence of a condition of (2).
Preferably, determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index includes:
Figure BDA0004201763410000031
wherein P' (A) k ) Index conditional probabilities representing respective secondary indexes; p (A) 1 |A 1k ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1k Appearance strip of (2)Probability of a piece; p (A) 1 |A 11 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 11 The occurrence probability of (2); p (A) 1 |A 12 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 12 The occurrence probability of (2); p (A) 1 |A 1j ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1j Is a probability of occurrence of a condition of (2).
Preferably, the calculating to obtain the third appearance weight corresponding to the first-level index based on the index conditional probability and the set weight of the corresponding first-level index includes:
Figure BDA0004201763410000032
wherein W is i ' represents a third appearance weight corresponding to the first-level indicator; p (P) i The index conditional probability of the corresponding first-level index is represented; w (W) i Representing the set weight of the corresponding first-level index; n represents the index number corresponding to the first-level index.
Preferably, the obtaining a disaster evaluation result based on each third occurrence weight and the matched disaster loss includes:
Figure BDA0004201763410000033
wherein G is i A disaster loss factor representing a corresponding first-level index; s represents the disaster evaluation result.
Preferably, constructing the network resource according to the source type includes:
acquiring a type code of each source type, and matching initial resources consistent with the type code from a resource database;
acquiring corresponding matching logs based on a retrieval tool of the resource database, performing cluster analysis on the matching logs to obtain cluster types corresponding to each cluster result, and determining a history matching window;
acquiring window codes and window use frequencies of each history matching window, and giving a first weight to the corresponding history matching window;
counting the total window use frequency of all history matching windows in the same cluster type and giving a second weight to the corresponding cluster type based on the resource duty ratio of the total matching resource of each matching resource in the same cluster type;
obtaining resource availability of the corresponding initial resource based on the first weight and the second weight;
sequencing the resource availability, fully reserving source types corresponding to the first n0 initial resources, and temporarily reserving source types corresponding to the rest initial resources;
judging whether the resource information corresponding to all reserved source types meets the resource construction standard;
if yes, the corresponding resource information is used as network resource;
if not, acquiring a resource relation network and a resource use network of each residual source type;
screening available resources from the matched residual initial resources according to the resource relation network and the resource use network;
constructing a first available function corresponding to the available resources, and simultaneously constructing a second available function meeting the resource construction standard;
and carrying out resource expansion on the second available function according to the first available function to obtain network resources.
Preferably, performing resource expansion on the second available function according to the first available function to obtain a network resource, including:
determining a first number of resource sources to which the first available function relates and determining a second number of resource sources to which the second available function relates;
calculating an adaptation coefficient of the first available function to the second available function according to the third number, the first number and the second number of temporarily reserved resource sources;
Figure BDA0004201763410000041
wherein P0 represents an adaptation coefficient; b1 represents all available resources determined based on the first available function; b2 represents all network resources determined based on the second available function; l n the sign of the logarithmic function; m3 represents a third number; m1 represents a first number; m2 represents a second number;
Figure BDA0004201763410000042
a first weight representing the number of sources involved in the first available function; />
Figure BDA0004201763410000056
A second weight representing the number of sources involved in the second available function;
when the adaptation coefficient is larger than or equal to a preset coefficient, supplementing the available resources related to the first available function into the network resources related to the second available function;
otherwise, determining the relevant resources existing in the source resources of each residual source, and supplementing the relevant resources into the network resources related to the second available function.
Preferably, a network resource is constructed according to a source type, and a loss keyword related to a target disaster is screened from each first sub-resource in the network resource, and a loss evaluation system is established, including:
screening out lost initial words in each first sub-resource, matching the lost initial words with a part-of-speech database, and marking the part-of-speech of each lost initial word, wherein each first sub-resource comprises n1 lost initial words;
per-lost initial word in each first sub-resource
Figure BDA0004201763410000051
Randomly combining to obtain ∈>
Figure BDA0004201763410000052
A plurality of combined arrays, wherein rand represents a random function; n1 represents the total number of lost initial words contained in the corresponding first sub-resource; []Representing a rounding function;
according to part-of-speech combinations of the combination array, a word analysis mode is called from a word analysis database, matching analysis is carried out on the corresponding part-of-speech combinations, the first two matching analysis results with the largest quantity are reserved, and a matching sub-matrix is constructed, wherein the matching sub-matrix is of 2 rows
Figure BDA0004201763410000053
A column;
constructing and obtaining an initial matrix based on all the matched submatrices, wherein the initial matrix is 2 multiplied by m4 columns
Figure BDA0004201763410000054
A column, wherein m4 represents the number of resources of the first sub-resource; />
Figure BDA0004201763410000055
Representing the maximum number of columns corresponding to all first sub-resources, and setting 0 for the idle position in the initial matrix;
and carrying out leave-one deletion on the consistent row vectors in the initial matrix to obtain a first matrix;
locking a first row of most effective elements in the first matrix, performing intersection matching on the first row and each other row respectively, and simultaneously locking first elements with the same elements with the number of occurrence times of columns being larger than a preset number;
determining a loss keyword according to the intersection matching result and the first element;
and integrating all the loss keywords to establish a loss evaluation system.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flowchart of an intelligent evaluation method based on a web crawler method in an embodiment of the present invention;
FIG. 2 is a diagram of a resource relationship network in an embodiment of the present invention;
FIG. 3 is a diagram of a resource usage network in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides an intelligent assessment method based on a web crawler mode, which is shown in fig. 1 and comprises the following steps:
step 1: according to source types, constructing network resources, screening loss keywords related to target disasters from first resources of each source type, and building a loss evaluation system;
step 2: respectively carrying out resource retrieval on all the first resources by adopting a web crawler mode;
step 3: according to the resource retrieval result, counting the first occurrence probability of disaster events of different disaster types in the locking time period to serve as the first occurrence weight of the corresponding secondary index, and further determining the second occurrence weight of each tertiary index based on the corresponding secondary key index;
step 4: determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index;
step 5: calculating to obtain a third appearance weight corresponding to the first-level index based on the index conditional probability and the set weight of the corresponding first-level index;
step 6: and acquiring and obtaining a disaster evaluation result based on each third occurrence weight and the matched disaster loss.
Preferably, further determining the second occurrence weight of each third level indicator based on the corresponding second level key indicator includes:
Figure BDA0004201763410000071
wherein P (A) 11 ) Representing three-level index A 11 Based on the corresponding secondary index A 1 Is a second occurrence weight of (2); p (A) 1 A 11 ) Representing the secondary index A 1 Is a first occurrence weight of (2); p (A) 1 |A 11 ) Representing the corresponding secondary index A 1 Is a probability of occurrence of a condition of (2).
Preferably, determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index includes:
Figure BDA0004201763410000072
wherein P' (A) k ) Index conditional probabilities representing respective secondary indexes; p (A) 1 |A 1k ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1k The occurrence probability of (2); p (A) 1 |A 11 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 11 The occurrence probability of (2); p (A) 1 |A 12 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 12 The occurrence probability of (2); p (A) 1 |A 1j ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1j Is a probability of occurrence of a condition of (2).
Preferably, the calculating to obtain the third appearance weight corresponding to the first-level index based on the index conditional probability and the set weight of the corresponding first-level index includes:
Figure BDA0004201763410000073
wherein W is i ' represents a third appearance weight corresponding to the first-level indicator; p (P) i The index conditional probability of the corresponding first-level index is represented; w (W) i Representing the set weight of the corresponding first-level index; n represents the index number corresponding to the first-level index.
Preferably, the obtaining a disaster evaluation result based on each third occurrence weight and the matched disaster loss includes:
Figure BDA0004201763410000081
wherein G is i A disaster loss factor representing a corresponding first-level index; s represents the disaster evaluation result.
In this embodiment, the network resource refers to resource information obtained by using the network as a basis, such as network news, microblog, network yearbook, paper, and the like.
In this embodiment, the loss evaluation system includes industrial loss, social loss, service loss, and agricultural loss, and the four losses are used as primary indexes, and the primary indexes may be decomposed into several secondary indexes, for example, industrial yield loss, factory blackout, worker loss, service practitioner drop, loss of service population, population disaster, economic loss, drought area, precipitation, agricultural irrigation rate, farmer income, grain yield, and the like.
In this embodiment, the web crawler may be a more commonly used free octopus crawler tool.
In this embodiment, the three-level index is a loss keyword corresponding to disaster, for example, for industrial yield loss, the three-level index may be finely divided again, for example, to yield loss of different areas.
In this embodiment, the natural disasters include: fire, flood disasters, drought, landslide, and the like.
In this embodiment, in the process of determining the second occurrence weight, for example, taking a fire as an example, the probability of occurrence of an event such as personnel loss, house loss, explosion, etc. caused by a fire event in a national range is the weight of the third level index relative to the second level index corresponding to the third level index. And analogically, respectively solving the weights of the secondary index and the tertiary index. The probability of various natural disaster events in recent years is counted, wherein the natural disasters comprise fire disasters, flood disasters, drought disasters, landslide and the like. The probability of each natural disaster event is the weight of the disaster event, namely the weight W of the secondary index 1 ＝P 1 /P 1 +P 2 +P 3 ...+P n . And respectively counting the weight of the three-level index relative to the corresponding two-level index, for example, taking fire as an example, and the probability of occurrence of personnel loss, house loss, explosion and other events caused by fire events in the whole country is the weight of the three-level index relative to the corresponding two-level index. And analogically, respectively solving the weights of the secondary index and the tertiary index.
In this embodiment, the loss caused by the natural disasters can be estimated by combining the loss caused by each disaster event with the weight thereof.
In this embodiment, the disaster assessment result is determined to be that the indexes are assigned with weights by using a bayesian network method on a sequential basis, so that the loss of the natural disaster to the national GDP is objectively assessed.
The beneficial effects of the technical scheme are as follows: the objective fact data is mainly utilized to count the weight of the disaster event, the occurrence probability of the three-level index and the conditional probability of the two-level index are obtained through a web resource crawler mode, the objective weight of each level of index is further obtained, the assessment of the GDP loss of the national natural disasters is completed, and the assessment accuracy is improved.
The invention provides an intelligent evaluation method based on a web crawler mode, which constructs network resources according to source types and comprises the following steps:
acquiring a type code of each source type, and matching initial resources consistent with the type code from a resource database;
acquiring corresponding matching logs based on a retrieval tool of the resource database, performing cluster analysis on the matching logs to obtain cluster types corresponding to each cluster result, and determining a history matching window;
acquiring window codes and window use frequencies of each history matching window, and giving a first weight to the corresponding history matching window;
counting the total window use frequency of all history matching windows in the same cluster type and giving a second weight to the corresponding cluster type based on the resource duty ratio of the total matching resource of each matching resource in the same cluster type;
obtaining resource availability of the corresponding initial resource based on the first weight and the second weight;
sequencing the resource availability, fully reserving source types corresponding to the first n0 initial resources, and temporarily reserving source types corresponding to the rest initial resources;
judging whether the resource information corresponding to all reserved source types meets the resource construction standard;
if yes, the corresponding resource information is used as network resource;
if not, acquiring a resource relation network and a resource use network of each residual source type;
screening available resources from the matched residual initial resources according to the resource relation network and the resource use network;
constructing a first available function corresponding to the available resources, and simultaneously constructing a second available function meeting the resource construction standard;
and carrying out resource expansion on the second available function according to the first available function to obtain network resources.
In this embodiment, the source types include: the network news, the microblog, the network yearbook and the paper types are different in codes, so that initial resources consistent with the codes can be called from a resource database, for example, the codes of the network news are 0000, at the moment, the codes are used as ties, and the resources coded into 0000 are called from the resource database, wherein the resource database contains all resources related to natural disasters under different years and months stored in different network platforms.
In the embodiment, each resource type has a matched search tool, so that the efficiency of resource matching is ensured, and the search tool is used for realizing information search service and conveniently realizing resource search.
In this embodiment, for example, the search tool encoded with 0000 is tool 1, and the matching log generated by tool 1 is based on the log information corresponding to the process of performing resource matching from the database according to encoded 0000.
In this embodiment, the clustering analysis refers to classifying the matching logs according to the content type of the log information to obtain a clustering result.
In this embodiment, the information type of the cluster center corresponding to each cluster result may be regarded as a corresponding cluster type, and the history matching window is determined based on a cluster type-window mapping table, where the mapping table includes cluster types of different matches and a matching sub-process of the cluster types, and an implementation window of the matching sub-process is a history matching window.
In this embodiment, for example, history matching windows with type coding 0000 are 1, 2, and 3, and the coding of window 1 is aaa1, the coding of window 2 is aaa2, and the coding of window 3 is aaa3, wherein the first weight formula is calculated as follows:
Figure BDA0004201763410000101
wherein Q is j A first weight representing a j-th history matching window; q j Representing the setting weight of the jth history matching window based on the code-setting mapping table; m01 represents the number of windows of the history window that match with a different window code under the same type code; p is p j Representing the jth history matchWindow usage frequency of the window;
in this embodiment, the code-setting mapping table includes different window codes and setting weights matched with the window codes, which are all set in advance, and each matching process is set by the program code in advance to perform the matching operation.
In this embodiment, the total window usage frequency refers to M01 mentioned above, the resource duty ratio is the same as the second weight, and the resource duty ratio=corresponds to each matching resource in the same cluster type/to the matching resource corresponding to all cluster types under the matching log, that is, the matching resource corresponding to all cluster types under the matching log is the total matching resource.
Figure BDA0004201763410000111
The average duty ratio of the resources refers to the average value of the duty ratios of all the resources under the same matching log; sum { Q j The expression is for all Q j Summing; sum represents the sign of the summation function;
in this embodiment, the sorting refers to sorting from large to small, n0 refers to selecting the first n0 from the resource availability corresponding to all the initial resources, and the total number of the initial resources is an integer greater than n0 and greater than or equal to 1.
In this embodiment, the total reservation refers to that the reserved resource can be used as a network resource, but before being used as a network resource, it is further required to determine whether the resource construction standard is met, where the resource construction standard refers to whether the reserved resource of the corresponding source type is complete, for example, the resource needs to include 3 information requirements, but only 2 information requirements are actually acquired, and at this time, it is determined that the resource construction standard is not met.
For example, the source types corresponding to the remaining initial resources are paper types, the resource relation network refers to resource conditions obtained from different platforms such as a knowledge network and a mastership, and further the network is constructed, wherein the resource use network refers to a network formed by useful natural disaster resources obtained from the knowledge network, useful natural disaster resources obtained from the mastership, and the like, and the resource use network can be constructed as effective resource use.
As shown in fig. 2 for a resource relationship network and in fig. 3 for a resource usage network.
In this embodiment, the available resources are available resources obtained by locking resources of the resource relation network and the resource usage network based on a resource screening mechanism, where the available resources are simply used to determine valuable contents existing in the resources, and the resource screening mechanism screens the valuable contents based on the network.
For example, there are resources 01, 02, and 03, and the locked 01 is in the known network, and the 01 has value, and in this case, the resource 01 is regarded as valuable content.
In this embodiment, the first available function is determined based on the available resources and a detailed source among the available resources' type sources, and the second available function is determined based on the type sources satisfying the resource construction criteria and the resources of the type sources.
A first available function = { fine source, valuable content };
the second available function = { } meets the type source, valuable content of the resource building criterion.
In this embodiment, the purpose of the resource extension is to supplement a portion of the valuable content in the first available function into the resource corresponding to the second available function.
The beneficial effects of the technical scheme are as follows: the method has the advantages that the type coding is convenient to match resources, the matching logs are subjected to clustering analysis to give weight to windows, the resource effectiveness is obtained through calculation, the rationality of the database matching resources is guaranteed, unreasonable matching is avoided, a function is built for reserved resources, a function is built for temporarily reserved resources, further the expansion of the resources is realized, the reliability of the resources is guaranteed, a foundation is provided for subsequent analysis of loss disasters, and the high efficiency of determining loss is guaranteed.
The invention provides an intelligent evaluation method based on a web crawler mode, which expands resources of a second available function according to the first available function to obtain network resources, and comprises the following steps:
determining a first number of resource sources to which the first available function relates and determining a second number of resource sources to which the second available function relates;
calculating an adaptation coefficient of the first available function to the second available function according to the third number, the first number and the second number of temporarily reserved resource sources;
Figure BDA0004201763410000121
wherein P0 represents an adaptation coefficient; b1 represents all available resources determined based on the first available function; b2 represents all network resources determined based on the second available function; l n the sign of the logarithmic function; m3 represents a third number; m1 represents a first number; m2 represents a second number;
Figure BDA0004201763410000131
a first weight representing the number of sources involved in the first available function; />
Figure BDA0004201763410000132
A second weight representing the number of sources involved in the second available function;
when the adaptation coefficient is larger than or equal to a preset coefficient, supplementing the available resources related to the first available function into the network resources related to the second available function;
otherwise, determining the relevant resources existing in the source resources of each residual source, and supplementing the relevant resources into the network resources related to the second available function.
In this embodiment, the sources related to the first available function are w1 and w2, where the first number is 2, the sources related to the second available function are w3, w4, and w5, where the second number is 3, and the third number is reserved sources including w1, w2, and w6, where the third number is 3.
In this embodiment, the preset coefficient has a value of 0.1.
In this embodiment, related resources refer to resources with high resource relevance among source resources of the remaining sources, and resources with high relevance refer to resources with a relevance coefficient greater than 0.8 in any two resources, or resources with relevance coefficients greater than 0.3 among all the resources.
The beneficial effects of the technical scheme are as follows: and the adaptation coefficient of the first available function to the second available function is calculated by determining the number of different resource sources, so that the supplement of network resources is realized, and the efficiency of subsequent analysis is ensured.
The invention provides an intelligent evaluation method based on a web crawler mode, which constructs network resources according to source types, screens out loss keywords related to a target disaster from each first sub-resource in the network resources, and establishes a loss evaluation system, and comprises the following steps:
screening out lost initial words in each first sub-resource, matching the lost initial words with a part-of-speech database, and marking the part-of-speech of each lost initial word, wherein each first sub-resource comprises n1 lost initial words;
per-lost initial word in each first sub-resource
Figure BDA0004201763410000133
Randomly combining to obtain ∈>
Figure BDA0004201763410000141
A plurality of combined arrays, wherein rand represents a random function; n1 represents the total number of lost initial words contained in the corresponding first sub-resource; []Representing a rounding function;
according to part-of-speech combinations of the combination array, a word analysis mode is called from a word analysis database, matching analysis is carried out on the corresponding part-of-speech combinations, the first two matching analysis results with the largest quantity are reserved, and a matching sub-matrix is constructed, wherein the matching sub-matrix is of 2 rows
Figure BDA0004201763410000142
A column;
constructing and obtaining an initial matrix based on all the matched submatrices, wherein the initial matrix is 2 multiplied by m4 columns
Figure BDA0004201763410000143
A column, wherein m4 represents the number of resources of the first sub-resource; />
Figure BDA0004201763410000144
Representing the maximum number of columns corresponding to all first sub-resources, and setting 0 for the idle position in the initial matrix;
and carrying out leave-one deletion on the consistent row vectors in the initial matrix to obtain a first matrix;
locking a first row of most effective elements in the first matrix, performing intersection matching on the first row and each other row respectively, and simultaneously locking first elements with the same elements with the number of occurrence times of columns being larger than a preset number;
determining a loss keyword according to the intersection matching result and the first element;
and integrating all the loss keywords to establish a loss evaluation system.
In this embodiment, the word analysis database includes different word analysis modes and combined parts of speech matched with the word analysis modes, and the combined parts of speech and the word analysis modes are in one-to-one correspondence and determined based on parts of speech included in the part of speech combination, and the part of speech combination is part of speech of all words in the combination array.
In this embodiment, the matching analysis is mainly based on the method to determine the matching relation between the words involved in the part-of-speech combination, and the matching relation is represented by numerical values, wherein the value range is [0,1], and the closer the matching relation is, the larger the corresponding value is.
In this embodiment, since there is a combination array associated with each lost initial word in the same first sub-resource, there are several rows in the combination array, and there are several values, and then the largest two values are filtered from all the values related to the first sub-resource and reserved to construct the matching sub-matrix.
In this embodiment, the first sub-resource refers to report content related to natural disasters, and the report content includes more than keywords, and various numerical results related to keywords exist, but at this time, the values need to extract related loss initial words, for example, building disaster areas caused by fires, agricultural disaster areas caused by fires, and the like, and at this time, the loss initial words are fire disasters, and the like.
In this embodiment, the part-of-speech database includes different disaster types, and the disaster types, such as flood and flood disaster sizes, fire and fire disaster sizes, hail disasters and disaster sizes, and the like, are respectively represented by corresponding parts-of-speech, and then the meaning represented by the loss initial word can be effectively known by marking the parts-of-speech.
In this embodiment, for example, the first sub-resource: [ loss initial word 1 loss initial word 2 loss initial word 3..], at this time, when there are 2 loss initial words, at this time, random combination is performed by 2 words, for example, taking the loss initial word 1 as an example, the random combination is: the penalty initial words 1 and 2, and the penalty initial words 1 and 3, i.e. with which penalty initial words are randomly combined, need to include the corresponding penalty initial words.
In this embodiment, for a combined array of penalty initial words 1, for example, there are 9 penalty initial words:
Figure BDA0004201763410000151
and the corresponding parts of speech combination is
Figure BDA0004201763410000152
That is, the parts of speech of the lost initial words 1, 2, 3 are analyzed and the corresponding matching submatrices +.>
Figure BDA0004201763410000153
In this embodiment, the initial matrix is to place all the matching sub-matrices sequentially according to the acquisition order, so as to obtain a matrix, since the number of row elements in some matching sub-matrices is large and the number of row elements in some matching sub-matrices is small, the number of row vectors with few elements needs to be uniformly complemented according to the number of row elements, and the complement content is 0.
In this embodiment, leave-one-out means that if there are 3 identical vectors, 2 remain 1.
In this embodiment, the most significant element refers to the number of remaining elements in the row vector excluding elements of 0.
In this embodiment, intersection matching refers to that the same lost initial word exists in the first line and each remaining line, and the intersection elements in each remaining line are first marked based on the elements of the first line to determine the number of marks and marked elements in each line.
In this embodiment, the first element refers to an element having a number of occurrences greater than a predetermined number in a column, and the columns are not necessarily the same column, but include one column element corresponding to each row.
Such as: first row: { element 1 element 2 element 3 element 4 element 5}
Line 1: { element 1 element 2 element 7};
line 2: { element 2 element 9};
line 3: { element 1 element 2 element 3}
At this time, the intersection matching result of the first row and the row 1 is { element 1, element 2}, and the intersection matching result of the first row and the row 2 is { element 2}; intersection matching result of the first row and the row 3 is { element 1 element 2 element 3};
for example, when the number of elements matched by intersection is greater than 2, element 7 of the corresponding row and elements 4 and 5 of the first row may be reserved;
wherein, the number of occurrences of the same element 1 is 3, the number of occurrences of the same element 2 is 4, the number of occurrences of the same element 3 is 3, the number of occurrences of the same element 4 is 1, the number of occurrences of the same element 5 is 1, and the number of occurrences of the same elements 7 and 9 is also 1.
In this embodiment, when the preset number of times is 2, the corresponding first elements are elements 1, 2, and 3.
The resulting loss keywords are: elements 1, 2, 3, 4, 5 and 7 are included, and all loss keywords are corresponding systems.
The beneficial effects of the technical scheme are as follows: the initial words of each sub resource are determined, matched with the database and labeled in part of speech, random combination is carried out, a matched sub matrix is constructed, a basis is provided for reserving reliable words, effective rows are conveniently reserved to avoid more than operation through matrix construction and matrix processing, double guarantee is provided for determining loss keywords through intersection matching and frequency comparison, construction rationality of a loss evaluation system is guaranteed, and further efficiency and accuracy of subsequent loss determination are guaranteed.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (8)

1. An intelligent assessment method based on a web crawler mode is characterized by comprising the following steps:
step 1: according to the source type, constructing a network resource, screening a loss keyword related to a target disaster from each first sub-resource in the network resource, and establishing a loss evaluation system;
step 2: respectively carrying out resource retrieval on all the first sub-resources by adopting a web crawler mode;
step 3: according to the resource retrieval result and the loss evaluation system, counting the first occurrence probability of disaster events of different disaster types in the locking time period to serve as the first occurrence weight of the corresponding secondary index, and further determining the second occurrence weight of each tertiary index based on the corresponding secondary key index;
step 4: determining the occurrence condition probability of each secondary index based on the first occurrence weight and the second occurrence weight, and further determining the index condition probability of the corresponding secondary index;
step 5: calculating to obtain a third appearance weight corresponding to the first-level index based on the index conditional probability and the set weight of the corresponding first-level index;
step 6: and acquiring and obtaining a disaster evaluation result based on each third occurrence weight and the matched disaster loss.
2. The method of claim 1, further comprising determining a second occurrence weight for each tertiary indicator based on a corresponding secondary key indicator, comprising:
Figure FDA0004201763400000011
wherein P (A) 11 ) Representing three-level index A 11 Based on the corresponding secondary index A 1 Is a second occurrence weight of (2); p (A) 1 A 11 ) Representing the secondary index A 1 Is a first occurrence weight of (2); p (A) 1 |A 11 ) Representing the corresponding secondary index A 1 Is a probability of occurrence of a condition of (2).
3. The web crawler-based intelligent assessment method according to claim 2, wherein determining the occurrence condition probability of each secondary indicator based on the first occurrence weight and the second occurrence weight, and further determining the indicator condition probability of the corresponding secondary indicator, comprises:
Figure FDA0004201763400000012
wherein P' (A) k ) Index conditional probabilities representing respective secondary indexes; p (A) 1 |A 1k ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1k Occurrence conditional probability of (a)；P(A 1 |A 11 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 11 The occurrence probability of (2); p (A) 1 |A 12 ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 12 The occurrence probability of (2); p (A) 1 |A 1j ) Representing the corresponding secondary index A 1 Based on the corresponding third index A 1j Is a probability of occurrence of a condition of (2).
4. The intelligent assessment method based on the web crawler method according to claim 3, wherein calculating the third occurrence weight of the corresponding primary index based on the index conditional probability and the set weight of the corresponding primary index comprises:
Figure FDA0004201763400000021
wherein W is i ' represents a third appearance weight corresponding to the first-level indicator; p (P) i The index conditional probability of the corresponding first-level index is represented; w (W) i Representing the set weight of the corresponding first-level index; n represents the index number corresponding to the first-level index.
5. The intelligent assessment method based on the web crawler method according to claim 4, wherein obtaining the disaster assessment result based on each third occurrence weight and the matched disaster loss comprises:
Figure FDA0004201763400000022
wherein G is i A disaster loss factor representing a corresponding first-level index; s represents the disaster evaluation result.
6. The intelligent assessment method based on the web crawler method according to claim 1, wherein constructing the network resource according to the source type comprises:
acquiring a type code of each source type, and matching initial resources consistent with the type code from a resource database;
acquiring corresponding matching logs based on a retrieval tool of the resource database, performing cluster analysis on the matching logs to obtain cluster types corresponding to each cluster result, and determining a history matching window;
acquiring window codes and window use frequencies of each history matching window, and giving a first weight to the corresponding history matching window;
counting the total window use frequency of all history matching windows in the same cluster type and giving a second weight to the corresponding cluster type based on the resource duty ratio of the total matching resource of each matching resource in the same cluster type;
obtaining resource availability of the corresponding initial resource based on the first weight and the second weight;
sequencing the resource availability, fully reserving source types corresponding to the first n0 initial resources, and temporarily reserving source types corresponding to the rest initial resources;
judging whether the resource information corresponding to all reserved source types meets the resource construction standard;
if yes, the corresponding resource information is used as network resource;
if not, acquiring a resource relation network and a resource use network of each residual source type;
screening available resources from the matched residual initial resources according to the resource relation network and the resource use network;
constructing a first available function corresponding to the available resources, and simultaneously constructing a second available function meeting the resource construction standard;
and carrying out resource expansion on the second available function according to the first available function to obtain network resources.
7. The intelligent assessment method based on the web crawler method according to claim 6, wherein the resource expansion is performed on the second available function according to the first available function, so as to obtain a network resource, including:
determining a first number of resource sources to which the first available function relates and determining a second number of resource sources to which the second available function relates;
calculating an adaptation coefficient of the first available function to the second available function according to the third number, the first number and the second number of temporarily reserved resource sources;
Figure FDA0004201763400000031
wherein P0 represents an adaptation coefficient; b1 represents all available resources determined based on the first available function; b2 represents all network resources determined based on the second available function; ln represents the sign of the logarithmic function; m3 represents a third number; m1 represents a first number; m2 represents a second number;
Figure FDA0004201763400000041
a first weight representing the number of sources involved in the first available function; />
Figure FDA0004201763400000042
A second weight representing the number of sources involved in the second available function;
when the adaptation coefficient is larger than or equal to a preset coefficient, supplementing the available resources related to the first available function into the network resources related to the second available function;
otherwise, determining the relevant resources existing in the source resources of each residual source, and supplementing the relevant resources into the network resources related to the second available function.
8. The intelligent assessment method based on the web crawler method according to claim 1, wherein a network resource is constructed according to a source type, and a loss keyword related to a target disaster is screened from each first sub-resource in the network resource, and a loss assessment system is established, comprising:
screening out lost initial words in each first sub-resource, matching the lost initial words with a part-of-speech database, and marking the part-of-speech of each lost initial word, wherein each first sub-resource comprises n1 lost initial words;
per-lost initial word in each first sub-resource
Figure FDA0004201763400000043
Randomly combining to obtain ∈>
Figure FDA0004201763400000044
A plurality of combined arrays, wherein rand represents a random function; n1 represents the total number of lost initial words contained in the corresponding first sub-resource; []Representing a rounding function;
according to part-of-speech combinations of the combination array, a word analysis mode is called from a word analysis database, matching analysis is carried out on the corresponding part-of-speech combinations, the first two matching analysis results with the largest quantity are reserved, and a matching sub-matrix is constructed, wherein the matching sub-matrix is of 2 rows
Figure FDA0004201763400000045
A column;
constructing and obtaining an initial matrix based on all the matched submatrices, wherein the initial matrix is 2 multiplied by m4 columns
Figure FDA0004201763400000046
A column, wherein m4 represents the number of resources of the first sub-resource; />
Figure FDA0004201763400000047
Representing the maximum number of columns corresponding to all first sub-resources, and setting 0 for the idle position in the initial matrix;
and carrying out leave-one deletion on the consistent row vectors in the initial matrix to obtain a first matrix;
locking a first row of most effective elements in the first matrix, performing intersection matching on the first row and each other row respectively, and simultaneously locking first elements with the same elements with the number of occurrence times of columns being larger than a preset number;
determining a loss keyword according to the intersection matching result and the first element;
and integrating all the loss keywords to establish a loss evaluation system.
CN202310463992.0A 2023-04-26 2023-04-26 Intelligent assessment method based on web crawler mode Active CN116433032B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310463992.0A CN116433032B (en) 2023-04-26 2023-04-26 Intelligent assessment method based on web crawler mode

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310463992.0A CN116433032B (en) 2023-04-26 2023-04-26 Intelligent assessment method based on web crawler mode

Publications (2)

Publication Number Publication Date
CN116433032A true CN116433032A (en) 2023-07-14
CN116433032B CN116433032B (en) 2024-04-09

Family

ID=87090719

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310463992.0A Active CN116433032B (en) 2023-04-26 2023-04-26 Intelligent assessment method based on web crawler mode

Country Status (1)

Country Link
CN (1) CN116433032B (en)

Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103985057A (en) * 2014-05-27 2014-08-13 煤炭科学研究总院 Coal mine safety risk evaluation or loss evaluation method and device
CN106529178A (en) * 2016-11-14 2017-03-22 东北电力大学 Landslide hazard risk assessment method
CN108134691A (en) * 2017-12-18 2018-06-08 广东欧珀移动通信有限公司 Model building method, Internet resources preload method, apparatus, medium and terminal
CN108280553A (en) * 2018-02-24 2018-07-13 中山大学 Regional Torrent Risk Zonation based on GIS- Artificial neural network ensembles and prediction technique
CN109547294A (en) * 2018-12-27 2019-03-29 中国人民解放军国防科技大学 Networking equipment model detection method and device based on firmware analysis
CN109858729A (en) * 2018-12-05 2019-06-07 广东电网有限责任公司 A kind of power distribution network methods of risk assessment and device
CN110377680A (en) * 2019-07-11 2019-10-25 中国水利水电科学研究院 The method of mountain flood database sharing and update based on web crawlers and semantics recognition
CN111144761A (en) * 2019-12-27 2020-05-12 成都理工大学 Railway route selection method based on typical underground geological disaster risk evaluation
CN111460252A (en) * 2020-03-16 2020-07-28 青岛智汇文创科技有限公司 Automatic search engine method and system based on network public opinion analysis
CN111651656A (en) * 2020-06-02 2020-09-11 重庆邮电大学 Method and system for dynamic webpage crawler based on agent mode
CN112231537A (en) * 2020-11-09 2021-01-15 张印祺 Intelligent reading system based on deep learning and web crawler
CN112749905A (en) * 2021-01-14 2021-05-04 黄河勘测规划设计研究院有限公司 Flood disaster assessment method based on big data mining
CN112801473A (en) * 2021-01-15 2021-05-14 北京城市系统工程研究中心 Disaster prediction method and system based on natural disaster chain
CN113570226A (en) * 2021-07-20 2021-10-29 中交第一公路勘察设计研究院有限公司 Method for evaluating occurrence probability grade of tunnel water inrush disaster in fault fracture zone
CN113824797A (en) * 2021-11-19 2021-12-21 南京好先生智慧科技有限公司 Self-adaptive synchronization method and device for teaching resources
CN113837549A (en) * 2021-08-27 2021-12-24 南京大学 Natech risk calculation method and system based on coupling probability model and information diffusion method
CN114254565A (en) * 2021-12-23 2022-03-29 国网陕西省电力有限公司 Low-voltage tripping device parameter optimization method for reducing load loss under voltage sag
CN114595581A (en) * 2022-03-11 2022-06-07 重庆地质矿产研究院 Regional geological disaster danger probability model based on influence factor dynamic weight
CN114943458A (en) * 2022-06-01 2022-08-26 海南绿色发展科技集团有限公司 Enterprise ESG (electronic service guide) rating method based on weight distribution model
CN114969513A (en) * 2022-05-07 2022-08-30 江苏吉高信息技术有限公司 Natural disaster active pushing method and system based on web crawler technology
WO2022242435A1 (en) * 2021-05-21 2022-11-24 浙江大学 Rapid evaluation method of site seismic liquefaction disaster based on artificial intelligence
CN115511250A (en) * 2022-07-13 2022-12-23 交通运输部路网监测与应急处置中心 Natural disaster risk evaluation method for highway disaster-bearing body

Patent Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103985057A (en) * 2014-05-27 2014-08-13 煤炭科学研究总院 Coal mine safety risk evaluation or loss evaluation method and device
CN106529178A (en) * 2016-11-14 2017-03-22 东北电力大学 Landslide hazard risk assessment method
CN108134691A (en) * 2017-12-18 2018-06-08 广东欧珀移动通信有限公司 Model building method, Internet resources preload method, apparatus, medium and terminal
CN108280553A (en) * 2018-02-24 2018-07-13 中山大学 Regional Torrent Risk Zonation based on GIS- Artificial neural network ensembles and prediction technique
CN109858729A (en) * 2018-12-05 2019-06-07 广东电网有限责任公司 A kind of power distribution network methods of risk assessment and device
CN109547294A (en) * 2018-12-27 2019-03-29 中国人民解放军国防科技大学 Networking equipment model detection method and device based on firmware analysis
CN110377680A (en) * 2019-07-11 2019-10-25 中国水利水电科学研究院 The method of mountain flood database sharing and update based on web crawlers and semantics recognition
CN111144761A (en) * 2019-12-27 2020-05-12 成都理工大学 Railway route selection method based on typical underground geological disaster risk evaluation
CN111460252A (en) * 2020-03-16 2020-07-28 青岛智汇文创科技有限公司 Automatic search engine method and system based on network public opinion analysis
CN111651656A (en) * 2020-06-02 2020-09-11 重庆邮电大学 Method and system for dynamic webpage crawler based on agent mode
CN112231537A (en) * 2020-11-09 2021-01-15 张印祺 Intelligent reading system based on deep learning and web crawler
CN112749905A (en) * 2021-01-14 2021-05-04 黄河勘测规划设计研究院有限公司 Flood disaster assessment method based on big data mining
CN112801473A (en) * 2021-01-15 2021-05-14 北京城市系统工程研究中心 Disaster prediction method and system based on natural disaster chain
WO2022242435A1 (en) * 2021-05-21 2022-11-24 浙江大学 Rapid evaluation method of site seismic liquefaction disaster based on artificial intelligence
CN113570226A (en) * 2021-07-20 2021-10-29 中交第一公路勘察设计研究院有限公司 Method for evaluating occurrence probability grade of tunnel water inrush disaster in fault fracture zone
CN113837549A (en) * 2021-08-27 2021-12-24 南京大学 Natech risk calculation method and system based on coupling probability model and information diffusion method
CN113824797A (en) * 2021-11-19 2021-12-21 南京好先生智慧科技有限公司 Self-adaptive synchronization method and device for teaching resources
CN114254565A (en) * 2021-12-23 2022-03-29 国网陕西省电力有限公司 Low-voltage tripping device parameter optimization method for reducing load loss under voltage sag
CN114595581A (en) * 2022-03-11 2022-06-07 重庆地质矿产研究院 Regional geological disaster danger probability model based on influence factor dynamic weight
CN114969513A (en) * 2022-05-07 2022-08-30 江苏吉高信息技术有限公司 Natural disaster active pushing method and system based on web crawler technology
CN114943458A (en) * 2022-06-01 2022-08-26 海南绿色发展科技集团有限公司 Enterprise ESG (electronic service guide) rating method based on weight distribution model
CN115511250A (en) * 2022-07-13 2022-12-23 交通运输部路网监测与应急处置中心 Natural disaster risk evaluation method for highway disaster-bearing body

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
LIU JINGFA等: ""Focused crawler method combining ontology and improved Tabu search for meteorological disaster"", 《JOURNAL OF COMPUTER APPLICATIONS》, vol. 40, no. 8, pages 2255 - 61 *
姜德良;张韧;葛珊珊;: "一种风险评估分样本定权方法――以港口自然灾害为例", 自然灾害学报, no. 03 *
李明;张韧;洪梅;: "基于加权贝叶斯网络的海洋灾害风险评估", 海洋通报, no. 02 *
王威;田杰;苏经宇;马东辉;: "基于贝叶斯随机评价方法的小城镇灾害易损性分析", 防灾减灾工程学报, no. 05 *
许金玲;孟庆福;刘婧;: "基于大数据的网络公开课标签库建设", 现代电子技术, no. 03 *

Also Published As

Publication number Publication date
CN116433032B (en) 2024-04-09

Similar Documents

Publication Publication Date Title
Rogot et al. Probabilistic methods in matching census samples to the National Death Index
Rahman et al. Mining weighted frequent sequences in uncertain databases
CN104346538B (en) Earthquake hazard assessment method based on three kinds of the condition of a disaster factor control
De Ruiter et al. A comparison of flood and earthquake vulnerability assessment indicators
Coudouel et al. Poverty measurement and analysis
Wan Predicting self-assessed health status: a multivariate approach.
CN111324657B (en) Emergency plan content optimization method and computer equipment
Jones et al. Vulnerability index construction: methodological choices and their influence on identifying vulnerable neighbourhoods
Golder et al. The use of cluster analysis for stratification
Anandalingam et al. A multi-stage multi-attribute decision model for project selection
Riedel et al. Macroscale vulnerability assessment of cities using association rule learning
Choi et al. Clustering-based disaster resilience assessment of South Korea communities building portfolios using open GIS and census data
Reinoso et al. Estimation of life vulnerability inside buildings during earthquakes
CN116433032B (en) Intelligent assessment method based on web crawler mode
Ulrich‐Schad et al. Preferences for economic and environmental goals in rural community development in the Western United States
Jin et al. Research on the evaluation model of rural information demand based on big data
Ferrante Developing an offender-based tracking system: The Western Australia INOIS project
Porter Tracking the mobility of crime: New methodologies and geographies in modeling the diffusion of offending
Szczyrba et al. A machine learning method to quantify the role of vulnerability in hurricane damage
CN111768031B (en) Method for predicting crowd gathering trend based on ARMA algorithm
Longford Statistical modelling of data from hierarchical structures using variance component analysis
CN110097126B (en) Method for checking important personnel and house missing registration based on DBSCAN clustering algorithm
Coudouel et al. Well-being measurement and analysis
Pita et al. Statistical tools for populating/predicting input data of risk analysis models
Lebowitz et al. Socioeconomic analysis of the Alameda County Health Department jurisdiction

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant