CN115345229A - Fire-fighting risk dimension determination method - Google Patents
Fire-fighting risk dimension determination method Download PDFInfo
- Publication number
- CN115345229A CN115345229A CN202210942437.1A CN202210942437A CN115345229A CN 115345229 A CN115345229 A CN 115345229A CN 202210942437 A CN202210942437 A CN 202210942437A CN 115345229 A CN115345229 A CN 115345229A
- Authority
- CN
- China
- Prior art keywords
- fire
- fighting
- event
- risk
- inspection
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007689 inspection Methods 0.000 claims abstract description 56
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims abstract description 7
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 abstract description 8
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 6
- 238000012502 risk assessment Methods 0.000 description 5
- 235000019504 cigarettes Nutrition 0.000 description 4
- 239000002360 explosive Substances 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000000383 hazardous chemical Substances 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000004033 plastic Substances 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- RNFJDJUURJAICM-UHFFFAOYSA-N 2,2,4,4,6,6-hexaphenoxy-1,3,5-triaza-2$l^{5},4$l^{5},6$l^{5}-triphosphacyclohexa-1,3,5-triene Chemical compound N=1P(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP=1(OC=1C=CC=CC=1)OC1=CC=CC=C1 RNFJDJUURJAICM-UHFFFAOYSA-N 0.000 description 1
- 206010000369 Accident Diseases 0.000 description 1
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 244000025254 Cannabis sativa Species 0.000 description 1
- 244000082204 Phyllostachys viridis Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 239000011111 cardboard Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000003063 flame retardant Substances 0.000 description 1
- 238000011221 initial treatment Methods 0.000 description 1
- 239000003915 liquefied petroleum gas Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011087 paperboard Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention provides a fire-fighting risk dimension determination method, which belongs to the technical field of intelligent fire fighting and comprises the following steps: constructing a fire-fighting risk characteristic word set F, and scoring each item by using a chi-square statistic technology; ranking scores of the fire prevention feature words in the fire prevention feature word set F to obtain an event feature word set F1, and constructing a basic-level control fire inspection feature word dictionary; extracting text contents of events to be classified according to a TF-IDF numerical weight calculation method, and calculating scores of all categories; and sequencing according to the content scores of all the classifications, and selecting the fire-fighting risk dimension with the highest score as the event to be classified. The fire-fighting risk dimension determining method provided by the invention can automatically identify fire-fighting events reported by grid members and site fire-fighting inspection contents, and carry out fire-fighting risk dimension classification and deduction identification, thereby facilitating the scoring statistics of the fire-fighting risks of sites.
Description
Technical Field
The invention belongs to the technical field of intelligent fire fighting, and particularly relates to a fire fighting risk dimension determination method.
Background
Along with the continuous deepening of the primary social management, the examination of various places by the gridding management force is continuously refined, the examination and event handling records are continuously increased, the existing fire data is combined, how to further carry out risk assessment on the fire risk of the places is carried out, the grid force and all levels of supervision units are guided to carry out comprehensive examination and supervision on the existing places, the probability of fire accidents of the problem places is reduced, and the problem is faced by the primary social management.
Disclosure of Invention
The invention aims to provide a fire-fighting risk dimension determination method, and aims to solve the technical problems of deficiency and incompleteness of fire-fighting risk assessment in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that: the fire protection risk dimension determination method comprises the following steps:
step 1, constructing a fire-fighting risk characteristic word set F, and scoring each item in the fire-fighting risk characteristic word set F by using a chi-square statistic technology;
step 2, ranking the scores of all the fire-fighting risk characteristic words in the fire-fighting risk characteristic word set F to obtain an event characteristic word set F 1 And according to the event feature word set F 1 Constructing a basic level governing fire-fighting inspection feature word dictionary;
and 3, calculating the weight of each feature word in the primary control fire inspection feature word dictionary according to a TF-IDF numerical weight calculation method, wherein the TF-IDF numerical weight calculation formula is corrected as follows:
wherein: TF refers to the feature word t i In class C j The number of occurrences in (a); d(C j ) Finger class C j Number of events in, DF (t) i ，C j ) Finger class C j In the appearance of a feature word t i The number of events of (a); CF (t) i ) Indicating the presence of a feature word t i Number of event categories of (c), t i Is that the ith feature word in the feature word set F represents the total number of event classifications, C j Represents the jth class of all examination types;
step 4, extracting the text content of the event to be classified;
step 5, calculating scores of all categories according to the occurrence frequency of each feature word in the basic level control fire-fighting inspection feature word dictionary in the text content, wherein the calculation formula is as follows:
wherein f is ji Is a characteristic word t i Number of occurrences in the event content, CDT (t) i ，C j ) Is a characteristic word t i In correspondence with class C j C is class C j M is the classification C j The number of the feature words;
and 6, sequencing according to the content scores of the classifications, and selecting the highest score as the fire-fighting risk dimension of the event to be classified.
Preferably, the formula for scoring each item in the fire-fighting risk characteristic word set F is:
wherein:
wherein: t is t i Is the ith feature word in the feature word set F, M represents the total number of event classifications, C j Denotes the jth class, A, of all examination typesDenotes to belong to C j Class and contain t i B indicates not belonging to C j Class but contains t i The frequency of events of (C) represents belonging to C j Class but not containing t i The event frequency of D is not C j Nor t i N is the total number of events, x 2 (t i ，C j ) A chi-square statistic representing the feature words over the classes,
and taking the value with the maximum card statistic value of the feature words in all event classifications.
Preferably, step 1 comprises the steps of:
step 1.1, marking the fire control inspection event;
step 1.2, preprocessing the speech material by using a word segmentation tool;
step 1.3, a stop word dictionary is established, wherein the stop words comprise: adverbs, adjectives, conjunctions;
step 1.4, based on the marked fire-fighting inspection event, performing stop word processing on the preprocessed corpus according to the stop word dictionary to form a fire-fighting risk feature word set F;
and 1.5, scoring each item in the fire-fighting risk characteristic word set F by using a chi-square statistic technology.
Preferably, in step 1.1, all the inspection events are marked according to a standard inspection index type, which is counted as C in set, based on the existing fire inspection events.
Preferably, the word segmentation tool is a nod word segmentation.
Preferably, in the step 2, the scores of each fire risk characteristic word in the fire risk characteristic word set F are sorted in the order from high to low.
Preferably, in the step 2, the event feature word set F is selected from the event feature word set 1 And selecting the first L characteristic words to form a basic-level fire control inspection characteristic word dictionary.
Preferably, the events to be classified comprise daily patrol records and inspection records of function stations.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a method for determining a fire risk dimension as defined in any one of the preceding claims.
The invention also provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, characterized in that the computer program, when executed by the processor, implements a method for determining a fire risk dimension as defined in any one of claims 1 to 8.
The fire-fighting risk dimension determining method provided by the invention has the beneficial effects that: compared with the prior art, the fire-fighting risk dimension determining method can automatically identify fire-fighting events reported by grid members and site fire-fighting inspection contents, and carry out fire-fighting risk dimension classification and deduction identification, so that the fire-fighting risks of sites can be conveniently scored and counted.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flow chart of a fire fighting risk dimension determination method according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1, a method for determining a fire risk dimension according to the present invention will now be described. The fire-fighting risk dimension determination method comprises the following steps:
s1, constructing a fire risk feature word set F, and scoring each item in the fire risk feature word set F by using a chi-square statistic technology.
The implementation manner of step S1 may be:
s1.1, marking a fire control inspection event;
marking all fire fighting inspection events according to standard inspection index types based on the existing fire fighting inspection events, wherein the standard inspection index type set is marked as C. Such as: the description of the inspection event is 'electric bicycles are parked in the corridor', and the inspection event is marked as 'hidden danger of the electric bicycles'; the inspection event description is 'the cover of the distribution box is missing', and is marked as 'the distribution box, the electric switch, the electric wire line and the like are not properly protected'; the examination event description is "stub present beside the warehouse" and is marked as "smoking trace present, stub throw"; it should be noted that the inspection index types of the present invention also include various physical indexes, for example, the inspection event description is "warehouse temperature is too high" and is marked as "fire hazard exists".
S1.2, preprocessing the speech by using a word segmentation tool;
the word segmentation tool can be selected from HanLP, seoba segmentation, fudanNLP, LTP, THULAC, NLPIR, etc.
Illustratively, the corpus (e.g., event content) is segmented by a segmentation tool, i.e., a segmentation tool, to obtain the preprocessed corpus.
S1.3, establishing a stop word dictionary, wherein stop words comprise: adverbs, adjectives, conjunctions;
s1.4, based on the marked fire-fighting inspection event, stop-word processing is carried out on the preprocessed corpus according to a stop-word dictionary to form a fire-fighting risk feature word set F, and after stop-word processing is carried out on the preprocessed corpus according to the description of the inspection event, such as 'parking an electric bicycle in a corridor', 'missing an outer cover of a distribution box', 'existence of a cigarette stub beside a storeroom', corresponding feature words are 'corridor, parking, electric bicycle', 'distribution box, outer cover, missing', 'storeroom, existence of a cigarette stub' respectively;
s1.5, scoring each item in the compensation and risk prevention feature word set F by using a chi-square statistic technology. If the probability of the risk prevention feature word 'cigarette end' in all event classifications is counted and scored, the scoring formula is as follows:
wherein:
wherein: t is t i Is the ith feature word in the feature word set F, namely the cigarette end, M represents the total number of event classifications, C j Represents the jth class of all examination types, A represents belonging to C j Class and contain t i The frequency of events of (A), B represents not belonging to C j Class but contains t i The frequency of events of (C) represents belonging to (C) j Class but not containing t i The event frequency of D is not in C j Nor t i N is the total number of events, x 2 (t i ，C j ) A chi-square statistic representing the feature words over the classes,
and taking the value with the maximum card statistic value of the feature words in all event classifications.
S2, the scores of all fire protection risk feature words in the fire protection risk feature word set F are sorted to obtain an event feature word set F1, and a basic level control fire inspection feature word dictionary is constructed according to the event feature word set F1.
In this step, the scores of each fire risk prevention feature word in the fire risk prevention feature word set F are sorted from high to low. And (4) selecting the first L characteristic words from the event characteristic word set F1 to form a basic-level control fire-fighting inspection characteristic word dictionary.
S3, chi-square statistic can well describe the distribution information of the characteristic words among the categories, but the consideration of the low-frequency words and the condition that the characteristic words are uniformly distributed in the categories are ignored. Therefore, on the basis, the weight of each feature word in the basic-level governing fire inspection feature word dictionary in the event category is calculated by adopting a TF-IDF numerical weight calculation method, wherein the TF-IDF numerical weight calculation formula is corrected as follows:
wherein: TF means a feature word t i In class C j The number of occurrences in (1); d (C) j ) Finger class C j Number of events in, DF (t) i ，C j ) Finger class C j In-occurrence feature word t i The number of events of (a); CF (t) i ) Indicating the presence of a feature word t i Number of event categories of (c), t i Is that the ith feature word in the feature word set F represents the total number of event classifications, C j Representing the jth class of all exam types.
S4, extracting text contents of the events to be classified;
in this step, the events to be classified include daily patrol records, inspection records at function stations.
Based on the characteristics of basic level governance, the text content of the events to be classified is extracted, and the method comprises the following aspects:
direct inducement: including but not limited to the presence of smoking traces, butt throwaway; the electric appliance with high power, such as a quick heater, a warmer and the like, is used; the distribution box, the electrical switch, the electric wire and the like are not properly protected; the welding and cutting construction site is not protected by fire protection or nearby combustible materials are stored; the equipment and the device for producing flammable and explosive chemicals which are easy to generate static electricity have to be provided with static electricity removing facilities according to the regulations; the phenomenon of three-in-one place exists; hazardous chemicals and flammable and explosive gases are not stored in a closed manner, and are not stored by a special person, or are stacked excessively or illegally, and no fireproof and flame-retardant measures are set; bottled gas is used in the room of the employee dormitory; hidden troubles such as kitchen range, oil smoke pipeline and gas cylinder in the kitchen; liquefied petroleum gas or other fuels are not purchased from legitimate sources; during business period, construction and maintenance operations such as decoration, electrogas welding and the like are carried out; hidden danger of electric bicycles; illegal use, storage of flammable and explosive hazardous chemicals and the like.
Management factors: the method comprises but is not limited to that a comprehensive fire-fighting inspection is not organized once every month, and the found fire-fighting safety problems are not supervised and rectified in time; the daily fire protection patrol is not carried out, the fire protection patrol is not carried out at least every 2 hours in the business period, and the business field is not checked when the business is over; the personnel are not subjected to fire safety training and emergency drilling for at least one time every year; staff cannot be used for fire extinguishers and fire hydrants accurately and skillfully, and the evacuation duty of customers is not clear; a miniature fire station or volunteer fire-fighting power is not established; a sound production safety and fire safety accident hidden danger investigation and treatment system is not established and hidden danger investigation is carried out; the person responsible for safety production and fire safety management is not determined and the person is on the wall; the positions of doors, windows and balconies are provided with barriers such as anti-theft windows and the like (the barriers which need to be arranged can be opened from the inside); the fire control room attendant does not take charge of the duty, and does not implement the 24-hour duty system.
Fire-fighting equipment: the emergency exits, evacuation channels are occupied, locked or not kept unblocked; stacking articles under the fireproof rolling screen; the building fire fighting equipment is not maintained regularly and is not detected comprehensively every year; fire-fighting facilities and equipment cannot be kept intact and effective; the emergency lighting lamp can not be lighted; no fire extinguisher is equipped; the fire extinguisher regularly checks that the record card is not filled in; the ascending surface is occupied, etc.
Other factors: fire spacing, fire separation, explosion-proof design, historical accidents, and the like.
The site survey classification includes: retail furniture, bamboo article manufacturing, grass and other article manufacturing, real estate agency services, metal furniture manufacturing, home decoration and fitment, property management, wood furniture manufacturing, wholesale building materials, paper and cardboard container manufacturing, retail fuel for living, plastic part and other plastic article manufacturing, hotels in general, retail motor vehicle fuel, wholesale textiles, knits and raw material, and the like. And grid inspection projects of different classification places are set by an expert group by adopting a safety inspection table method according to a fire risk evaluation dimension index system.
It should be noted that the above-mentioned contents are merely for describing features of specific categories or attributes, but are not limited, and the contents are not considered to be necessary for each embodiment of the present application.
S5, calculating the scores of all subclasses in four major categories of direct causes, management factors, fire fighting facilities and other factors according to the occurrence frequency of each feature word in the basic-level administration fire-fighting inspection feature word dictionary in the text content, wherein the calculation formula is as follows:
wherein f is ji Is a characteristic word t i Number of occurrences in the event content, CDT (t) i ，C j ) Is a characteristic word t i In correspondence with class C j C is class C j M is the classification C j The number of the feature words;
and S6, sequencing according to the content scores of the classifications, and selecting the fire-fighting risk dimension with the highest score as the event to be classified.
Compared with the prior art, the fire-fighting risk dimension determining method provided by the invention can automatically identify the fire-fighting events reported by the grid staff and the fire-fighting inspection contents of the site, and can carry out fire-fighting risk dimension classification and deduction identification, thereby facilitating the scoring statistics of the fire-fighting risk of the site.
The invention provides a fire-fighting risk dimension determination method, which is characterized in that fire-fighting risk prevention and control are taken as the center, key places are taken as objects, inspection items are taken as veins, based on daily fire-fighting inspection projects of grid managers, the key places in the jurisdiction are periodically subjected to full coverage inspection, relevant data are recorded into a system, safety inspection records, dark visit records, event information, accident information and the like of the places are synthesized, fire-fighting risk type inspection contents are automatically identified, classification and scoring are carried out, the overall fire-fighting risk coefficient of the key places is evaluated, comprehensive ranking is carried out, and functional departments are reasonably arranged to carry out administrative intervention. Through the optimized site fire risk ranking, site fire closed-loop control from grid member training, grid inspection, fire risk assessment and department treatment in primary social management is realized.
The fire-fighting risks of places which are usually checked in regional basic administration are quantitatively ranked more effectively, and administrative strength can be reasonably arranged for effective intervention.
The fire risk dimension determination method provided by the invention effectively solves the problems that along with the continuous deep use of a basic social management information system, grid managers have more and more records on inspection items of places in basic management, and the fire risk based on the places is also more and more deeply managed. The existing disposal of the fire-fighting risk of the place only stays in a single-place patrol to find hidden dangers, and the disposal is self-processed or directly reported for processing, and no risk assessment and overall study and judgment are carried out afterwards. Based on the primary treatment inspection results of the same place at different times, an effective fire risk assessment means is lacked, and the corresponding fire risk of the place is analyzed; based on regional and industrial fire risks, an effective identification means is also lacked to obtain and evaluate the fire risk standardized index ranking of a regional place from a fire record of grid inspection, so that the problem of overall risk prevention and control is solved, and more specifically, the technical problems that in the prior art, events reported by a base layer cannot automatically identify fire risk classifications, some fire risk classifications have over-inspection, so that the inspection content cannot effectively perform fire risk statistics, and the fire risk scores of all places cannot truly reflect the relative risk degree of fire problems of different places are solved.
The invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of a method for determining a fire risk dimension as described in any one of the above.
The invention also provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, characterized in that the computer program, when executed by the processor, implements a fire risk dimension determination method as defined in any of the above.
The invention also provides a fire-fighting risk dimension determination system, which is characterized by comprising:
a mobile terminal;
a processor;
a memory;
and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the programs causing the computer to perform a fire risk dimension determination method as described above.
The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. A fire-fighting risk dimension determination method is characterized by comprising the following steps:
step 1, constructing a fire-fighting risk characteristic word set F, and scoring each item in the fire-fighting risk characteristic word set F by using a chi-square statistic technology;
step 2, ranking scores of all the fire-fighting risk characteristic words in the fire-fighting risk characteristic word set F to obtain an event characteristic word set F 1 And according to the event feature word set F 1 Constructing a basic-level control fire-fighting inspection feature word dictionary;
and 3, calculating the weight of each feature word in the primary control fire inspection feature word dictionary according to a TF-IDF numerical weight calculation method, wherein the TF-IDF numerical weight calculation formula is corrected as follows:
wherein: TF refers to the feature word t i In class C j The number of occurrences in (1); d (C) j ) Finger class C j Number of events in, DF (t) i ，C j ) Finger class C j In-occurrence feature word t i The number of events of (a); CF (t) i ) Indicating the presence of a feature word t i Number of event categories of (c), t i Is that the ith feature word in the feature word set F represents the total number of event classifications, C j Represents the jth class of all examination types;
step 4, extracting the text content of the event to be classified;
step 5, calculating scores of all categories according to the occurrence frequency of each feature word in the basic level control fire-fighting inspection feature word dictionary in the text content, wherein the calculation formula is as follows:
wherein f is ji Is a characteristic word t i Number of occurrences in the event content, CDT (t) i ，C j ) Is a characteristic word t i In correspondence with class C j C is class C j M is class C j The number of the feature words;
and 6, sequencing according to the content scores of the classifications, and selecting the highest score as the fire-fighting risk dimension of the event to be classified.
2. A fire risk dimension determination method as claimed in claim 1, wherein in step 1, the formula for scoring each item in the fire risk feature word set F is:
wherein:
wherein: t is t i Is the ith feature word in the feature word set F, M represents the total number of event classifications, C j Represents the jth class of all examination types, A represents belonging to C j Class and contain t i The frequency of events of (A), B represents not belonging to C j Class but contains t i The frequency of events of (C) represents belonging to (C) j Class but not containing t i The event frequency of D is not in C j Nor t i N is the total number of events, x 2 (t i ，C j ) A chi-square statistic value representing the feature words on the classification,
and taking the value with the maximum card statistic value of the feature words in all event classifications.
3. A fire risk dimension determination method as claimed in claim 1, characterized in that step 1 comprises the steps of:
step 1.1, marking the fire control inspection event;
step 1.2, preprocessing the speech material by using a word segmentation tool;
step 1.3, a stop word dictionary is established, wherein the stop words comprise: adverbs, adjectives, conjunctions;
step 1.4, based on the marked fire-fighting inspection event, performing stop word processing on the preprocessed corpus according to the stop word dictionary to form a fire-fighting risk feature word set F;
and 1.5, scoring each item in the fire-fighting risk characteristic word set F by using a chi-square statistic technology.
4. A fire risk dimension determination method as claimed in claim 3, characterized in that in step 1.1, all inspection events are marked according to a standard inspection index type, the set of standard inspection index types being C, based on existing fire inspection events.
5. A fire risk dimension determination method as defined in claim 3, wherein: the word segmentation tool is a Chinese word segmentation tool.
6. A fire risk dimension determination method as defined in claim 1, wherein: in the step 2, the scores of each fire-fighting risk characteristic word in the fire-fighting risk characteristic word set F are sorted from high to low.
7. A fire risk dimension determination method as defined in claim 1, wherein: in the step 2, F is selected from the event feature word set 1 And selecting the first L characteristic words to form a basic-level fire control inspection characteristic word dictionary.
8. A fire risk dimension determination method as defined in claim 1, wherein: the events to be classified comprise daily patrol records and inspection records of function stations.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of a method for fire risk dimension determination as claimed in any one of claims 1 to 8.
10. An electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, characterized in that the computer program, when executed by the processor, implements a method for fire risk dimension determination as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210942437.1A CN115345229A (en) | 2022-08-08 | 2022-08-08 | Fire-fighting risk dimension determination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210942437.1A CN115345229A (en) | 2022-08-08 | 2022-08-08 | Fire-fighting risk dimension determination method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345229A true CN115345229A (en) | 2022-11-15 |
Family
ID=83949994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210942437.1A Pending CN115345229A (en) | 2022-08-08 | 2022-08-08 | Fire-fighting risk dimension determination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345229A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040236620A1 (en) * | 2003-05-19 | 2004-11-25 | Chauhan S. K. | Automated utility supply management system integrating data sources including geographic information systems (GIS) data |
| JP2009003841A (en) * | 2007-06-25 | 2009-01-08 | Rakuten Inc | Information processing device and method, program, and information processing system |
| CN108573031A (en) * | 2018-03-26 | 2018-09-25 | 上海万行信息科技有限公司 | A kind of complaint sorting technique and system based on content |
| CN108764638A (en) * | 2018-04-25 | 2018-11-06 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of structural fire protection safety estimation system |
| CN110688481A (en) * | 2019-09-02 | 2020-01-14 | 贵州航天计量测试技术研究所 | Text classification feature selection method based on chi-square statistic and IDF |
| CN112182249A (en) * | 2020-10-23 | 2021-01-05 | 四川大学 | Automatic classification method and device for aviation safety report |
| CN112488576A (en) * | 2020-12-16 | 2021-03-12 | 思创数码科技股份有限公司 | Fire-fighting risk assessment method, system, computer equipment and readable storage medium |
-
2022
- 2022-08-08 CN CN202210942437.1A patent/CN115345229A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040236620A1 (en) * | 2003-05-19 | 2004-11-25 | Chauhan S. K. | Automated utility supply management system integrating data sources including geographic information systems (GIS) data |
| JP2009003841A (en) * | 2007-06-25 | 2009-01-08 | Rakuten Inc | Information processing device and method, program, and information processing system |
| CN108573031A (en) * | 2018-03-26 | 2018-09-25 | 上海万行信息科技有限公司 | A kind of complaint sorting technique and system based on content |
| CN108764638A (en) * | 2018-04-25 | 2018-11-06 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of structural fire protection safety estimation system |
| CN110688481A (en) * | 2019-09-02 | 2020-01-14 | 贵州航天计量测试技术研究所 | Text classification feature selection method based on chi-square statistic and IDF |
| CN112182249A (en) * | 2020-10-23 | 2021-01-05 | 四川大学 | Automatic classification method and device for aviation safety report |
| CN112488576A (en) * | 2020-12-16 | 2021-03-12 | 思创数码科技股份有限公司 | Fire-fighting risk assessment method, system, computer equipment and readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 张光德 等: "基于大数据的煤矿瓦斯事故关键要素分析" * |
| 张光德等: "基于大数据的煤矿瓦斯事故关键要素分析", 《煤炭经济研究》 * |
| 李解等: "基于文本挖掘的地铁施工安全风险事故致险因素分析", 《隧道建设》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Genton et al. | Spatio-temporal analysis of wildfire ignitions in the St Johns River water management district, Florida | |
| Rasbash et al. | Evaluation of fire safety | |
| Shafran | Risk externalities and the problem of wildfire risk | |
| Goetz | Organization as Class Bias in Local Law Enforcement: Arson-for-Profit as a" Nonissue" | |
| CN115345228A (en) | Fire-fighting risk identification method and system | |
| Ferguson et al. | Fundamentals of fire protection for the safety professional | |
| Chen et al. | Investigation and analysis of historical Domino effects statistic | |
| CN115345229A (en) | Fire-fighting risk dimension determination method | |
| CN113935571A (en) | Gas station security risk assessment grading method and system | |
| Whyte et al. | Regulation and corporate crime | |
| CN116862221A (en) | Dual management method and system for major hazard sources | |
| Mutua et al. | Safety and health assessment in Kenyan petrol stations: Case study of Thika-Nairobi highway stations | |
| Manes et al. | Closing data gaps and paving the way for Pan-European Fire Safety Efforts: Part II—Terminology of fire statistical variables | |
| Chen et al. | Comprehensive evaluation and optimization model of regional fire protection planning of major hazard sources based on multiobjective fuzzy theory | |
| CN113807638A (en) | Major safety risk quantification method for tailing pond | |
| Bromann | Fire protection for commercial facilities | |
| CN111080166A (en) | Social unit fire risk assessment method based on multi-level statistical evaluation | |
| Bulgakova | Protection of natural ecosystems using forest resources | |
| Akinwumi et al. | Analysis of the preparedness for fire outbreak in the central business district of Kaduna metropolis | |
| Thomas et al. | Social disorder, accidents, and municipal wildfires | |
| Wang et al. | Research on Safety Management of Explosive Hazardous Chemicals in Laboratories from the Perspective of Laws and Regulations | |
| KR102261360B1 (en) | System of security vulnerability assessment for chemcial facility | |
| Mitra | Assessment of Corporate Proactiveness Towards Fire Safety-A Case Study | |
| Lan et al. | Analysis on the current situation and countermeasures of elevator safety in China | |
| Grice | Fire Risk: Fire Safety Law and Its Practical Application |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221115 |