WO2021017607A1 - 灾害风险预警方法、装置、计算机设备及存储介质 - Google Patents

灾害风险预警方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2021017607A1
WO2021017607A1 PCT/CN2020/093166 CN2020093166W WO2021017607A1 WO 2021017607 A1 WO2021017607 A1 WO 2021017607A1 CN 2020093166 W CN2020093166 W CN 2020093166W WO 2021017607 A1 WO2021017607 A1 WO 2021017607A1
Authority
WO
WIPO (PCT)
Prior art keywords
risk
event
information
preset
early warning
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.)
Ceased
Application number
PCT/CN2020/093166
Other languages
English (en)
French (fr)
Inventor
赵素群
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2021017607A1 publication Critical patent/WO2021017607A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G08—SIGNALLING
    • G08B—SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
    • G08B29/18—Prevention or correction of operating errors
    • G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system

Definitions

  • This application relates to the field of computer technology, in particular to a disaster risk early warning method, device, computer equipment and storage medium.
  • the existing information can be used to warn the risk of future risk events. Since the probability of occurrence of a risk event is related to the time interval between the last occurrence of a risk event, the prior art uses a calculation model to provide early warning of the risk of a risk event. The inventor realized that the calculation model did not include time. A reference factor that leads to insufficient accuracy in early warning of the risk of a risk event, and can only provide early warning of the risk of a current risk event but not the risk of a risk event that occurs at a certain time in the future. Therefore, the existing early warning methods have the problem that they cannot accurately early warning the risks of risk events.
  • the embodiments of the present application provide a disaster risk early warning method, device, computer equipment, and storage medium, aiming to solve the problem of large deviations in the disaster risk early warning method in the prior art method when performing risk early warning.
  • an embodiment of the present application provides a disaster risk early warning method, which includes:
  • the target risk event matching the risk warning request in the risk event reorganization information is obtained, wherein the risk warning request includes geographic location information, risk type information, and time information ;
  • the early warning prompt information corresponding to the risk early warning request is generated.
  • an embodiment of the present application provides a disaster risk early warning device, which includes:
  • the event information acquiring unit is used to crawl information matching the preset risk keywords in the webpage corresponding to the preset network address to obtain event information containing multiple risk events;
  • the event information merging and reorganizing unit is used to merge and reorganize the risk events contained in the event information according to preset event factors to obtain risk event reorganization information, where the event factors include name, time, location, risk type, degree;
  • the target risk event obtaining unit is configured to, if a risk warning request input by the user is received, obtain target risk events matching the risk warning request in the risk event reorganization information, wherein the risk warning request includes a geographic location Information, risk type information, time information;
  • the risk type information judging unit is used to judge whether the risk type information of the risk early warning request contains multiple risk types
  • a risk coefficient calculation unit configured to calculate the target risk event according to a preset risk coefficient calculation model and the judgment result to obtain a risk coefficient corresponding to the risk early warning request;
  • An early warning prompt information generating unit is used to generate early warning prompt information corresponding to the risk early warning request according to a preset early warning prompt model and the risk coefficient.
  • an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and running on the processor, and the processor executes the computer
  • the program implements the disaster risk early warning method described in the first aspect above.
  • the embodiments of the present application also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the above-mentioned On the one hand, the disaster risk early warning method.
  • the embodiments of the present application provide a disaster risk early warning method, device, computer equipment, and storage medium.
  • Execute information crawling program to obtain risk events, merge and reorganize risk events according to the time factor to obtain risk event reorganization information, obtain target risk events matching the risk warning request in the risk event reorganization information, and target the target according to the preset risk coefficient calculation model
  • the risk event is calculated to obtain the risk coefficient, and the warning prompt information corresponding to the risk coefficient and the risk warning request is obtained.
  • Figure 1 is a schematic flowchart of a disaster risk early warning method provided by an embodiment of the application
  • Figure 2 is a schematic diagram of a sub-process of the disaster risk early warning method provided by an embodiment of the application
  • FIG. 3 is a schematic diagram of a sub-process of a disaster risk early warning method provided by an embodiment of the application
  • FIG. 4 is a schematic diagram of another sub-process of the disaster risk early warning method provided by an embodiment of the application.
  • FIG. 5 is a schematic diagram of another sub-process of the disaster risk early warning method provided by an embodiment of the application.
  • Figure 6 is a schematic block diagram of a disaster risk early warning device provided by an embodiment of the application.
  • FIG. 7 is a schematic block diagram of subunits of the disaster risk early warning device provided by an embodiment of the application.
  • FIG. 8 is a schematic block diagram of another subunit of the disaster risk early warning device provided by an embodiment of the application.
  • FIG. 9 is a schematic block diagram of another subunit of the disaster risk early warning device provided by an embodiment of the application.
  • FIG. 10 is a schematic block diagram of another subunit of the disaster risk early warning device provided by an embodiment of the application.
  • FIG. 11 is a schematic block diagram of a computer device provided by an embodiment of the application.
  • FIG. 1 is a schematic flowchart of a disaster risk early warning method provided by an embodiment of the present application.
  • the disaster risk early warning method is applied to a user terminal, and the method is executed by application software installed in the user terminal.
  • the user terminal is a terminal device used to execute the disaster risk early warning method to early warn the risk of disaster occurrence, such as a desktop Computer, laptop, tablet or mobile phone, etc.
  • the method includes steps S110 to S160.
  • the parameter values include preset network addresses and preset risk keywords. By crawling the information matching the risk keywords in the webpage corresponding to the network address, you can get multiple risks. Event information of the event.
  • the preset network address may be the network address of a weather station website, a seismic station website, and a news media website;
  • the preset risk keywords may be keywords related to typhoons, earthquakes, floods, wildfires, etc.
  • the acquired event information contains multiple risk events, which are specific information about natural disasters such as typhoons, earthquakes, floods, and wildfires that occur in a certain location.
  • a certain risk event is: super typhoon "risk event A”, which passed through Shenzhen on September 16, 2018, and the maximum wind force near the center was 14 levels.
  • Super typhoon "risk event A” is the basic information of the risk event, and the rest is the description information of the risk event.
  • S120 Merging and reorganizing the risk events included in the event information according to preset event factors to obtain risk event reorganization information.
  • the risk events included in the event information are merged and reorganized according to preset event factors to obtain risk event reorganization information. Since different websites may all record the same risk, and the same risk event may be recorded multiple times in a certain website, it is necessary to merge multiple duplicate records corresponding to a risk event in the event information through event factors Reorganization means that only the first record among multiple duplicate records corresponding to a risk event is retained to obtain the risk event reorganization information. Specifically, it is necessary to first obtain the corresponding key event information from each risk event according to the event factor, and merge and reorganize the risk event based on the key event information.
  • the event factor includes the name, time, location, risk type, and degree.
  • step S120 includes sub-steps S121 and S122.
  • the key event information corresponding to each risk event is extracted from the event information according to the preset event factor.
  • Event factors include name, time, location, risk type, and degree. According to the event factors, obtain the corresponding name information, time information, location information, type information, and degree information of a risk event to get the event corresponding to the risk event. Key information, the key event information corresponding to each risk event can be obtained through the above methods.
  • the key event information of the risk event obtained from the above example according to the event factor is shown in Table 1.
  • the risk events are merged and reorganized according to the key event information to obtain risk event reorganization information. Specifically, judge whether there are multiple duplicate records of the same risk event based on the key event information. If the name information, time information, location information, and type information of the two risk events are the same, it indicates that the two risk events mentioned above are certain Two duplicate records corresponding to the risk event, otherwise the above two risk events are records corresponding to two independent risk events.
  • the risk event does not need to be merged and reorganized; if there are multiple duplicate records for a risk event, the risk event needs to be merged and reorganized, that is, only the risk is retained For the first record among multiple duplicate records corresponding to the event, all risk events are merged and reorganized according to the above method to obtain risk event reorganization information.
  • the target risk event matching the risk warning request in the risk event reorganization information is obtained, wherein the risk warning request includes geographic location information, risk type information, and time information .
  • the risk warning request is the information entered by the user to issue corresponding warning prompts for the threat of a risk event at a certain time.
  • the risk warning request includes geographic location information, that is, the specific location where risk warning is required;
  • the warning request also includes risk type information.
  • the risk type information can contain only one type of risk, that is, the corresponding warning prompt information can be issued for the threat of a certain risk type corresponding to the risk event, and the risk type information can also Contains a variety of different risk types, that is, a corresponding early warning message is issued for the overall threat of risk events corresponding to multiple risk types; the risk warning request also includes time information, which can be the current time or a certain time in the future point.
  • S140 Determine whether the risk type information of the risk warning request includes multiple risk types to obtain a judgment result.
  • the risk type information of the risk warning request contains multiple risk types to obtain the judgment result. Because in the specific application process, the risk type information may include only one type of risk or multiple different risks. Type, for the number of risk types contained in the risk warning request is one or more, different methods need to be used to obtain the corresponding risk coefficient. Therefore, before obtaining the risk coefficient of the risk warning request, the risk type information of the risk warning request must be obtained first Whether it contains multiple risk types for judgment.
  • the target risk event is calculated according to the preset risk coefficient calculation model and the judgment result to obtain the risk coefficient corresponding to the risk early warning request.
  • step S150 includes sub-steps S151 and S152.
  • the risk coefficient calculation model includes risk distance scoring rules, population density scoring rules, risk event classification rules, and risk coefficient calculation formulas.
  • the risk coefficient calculation model is the model used to calculate the risk coefficient corresponding to the risk warning request. Specifically, the risk coefficient calculation model includes risk distance scoring rules, population density scoring rules, risk event classification rules, and risk coefficient calculation formulas.
  • the distance scoring rule can be used to obtain the risk distance score corresponding to the risk warning request; the population density scoring rule can be used to obtain the population density score corresponding to the risk warning request; the risk event classification rule is used to classify the specific level of risk events Rules, after classifying the risk events of different risk types, the risk events of different risk types can be quantitatively analyzed; the risk coefficient calculation formula is the formula used to calculate the risk coefficient.
  • step S151 includes sub-steps S1511, S1512, S1513, S1514, S1515, S1516 and S1517.
  • the risk distance score E corresponding to the risk warning request is obtained according to the risk distance scoring rule, where the risk distance scoring rule includes risk area information and risk distance score mapping information.
  • the risk area information contains the risk area corresponding to each risk type, that is, the risk event can correspond to the corresponding risk area according to its type;
  • the risk distance score mapping information is the geographic location information used in the risk warning request The mapping information for scoring the distance to the corresponding target risk area. The distance between different geographic location information and the target risk area is different, and the probability of disaster risk is different. Therefore, the risk distance scoring mapping information can be used to obtain and risk warning Request the corresponding risk distance score.
  • step S1511 includes sub-steps S1511a, S1511b, and S1511c.
  • the risk area information contains the risk area corresponding to each type of risk. According to the risk type in the risk warning request, the risk area matching the risk type can be obtained as the target risk area.
  • the target risk area corresponding to the risk type "flood” is rivers and lakes
  • the target risk area corresponding to the risk type "earthquake” is earthquake zone
  • the target risk area corresponding to the risk type "typhoon” is the coast.
  • the target risk area corresponding to the risk type of "mountain fire” is mountainous area.
  • S1511b Acquire risk distance information between the target risk area and the geographic location information according to the geographic location information in the risk early warning request. If the geographic location information in the risk warning request is in the risk area, the risk distance information between the target risk area and the geographic location information is "0"; if the geographic location information in the risk warning request is not in the risk area, the target The risk distance information between the risk area and the geographic location information is the actual distance between the geographic location information and the edge of the target risk area.
  • the risk distance scoring mapping information contains multiple mapping intervals, and each mapping interval corresponds to a score value.
  • the score value corresponding to a mapping interval matching the risk distance information can be obtained according to the risk distance information, and the score value obtained is the risk Distance score E.
  • the risk distance score mapping information is shown in Table 2.
  • a certain risk distance information is 63Km, and the risk distance score E is 6 according to the risk distance score mapping information in Table 2.
  • the population density score P corresponding to the risk warning request is obtained according to the population density scoring rule, wherein the population density scoring rule includes population density information and population density score mapping information.
  • the population density information contains the population density value corresponding to each geographic location information.
  • the population density score mapping information is the mapping information used to score the population density value corresponding to the geographic location information in the risk warning request. Areas with different population density values , The hazards of the same disaster risk are also different, so the population density score corresponding to the risk warning request can be obtained through the population density score mapping information.
  • step S1512 includes sub-steps S1512a and S1512b.
  • S1512a Obtain a population density value corresponding to the geographic location information in the population density information according to the geographic location information in the risk early warning request.
  • the population density information contains the population density value corresponding to each geographic location information, and the population density value corresponding to the geographic location information can be obtained according to the geographic location information in the risk warning request.
  • the population density value is mapped according to the population density score mapping information to obtain the population density score P corresponding to the risk warning request.
  • the population density score mapping information includes multiple mapping intervals, and each mapping interval corresponds to a score value.
  • the score value corresponding to a mapping interval matching the population density value can be obtained according to the population density value, and the score value obtained is the population Density score P.
  • the population density score mapping information is shown in Table 3.
  • the population density score P is 4.5.
  • the target risk event is classified according to the risk event classification rule to obtain event quantity information including the target risk event quantity of each level.
  • each level of target risk event corresponds to a grading value.
  • the risk event grading rules are rules for grading target risk events.
  • the risk event grading rules include specific rules for grading risk events of each type of risk. After grading all target risk events, you can get the number of events including the number of target risk events at each level. For example, the risk type of the target risk event is "typhoon", and the classification rules corresponding to this risk type are shown in Table 4.
  • Table 5 shows the number of events obtained after grading all target risk events.
  • the target risk event with a classification value of "10" is not the same as the time information month
  • the target risk event with a classification value of "9” is the same as the time information month
  • the obtained information is the same as the time information month
  • the classification value Dmax of the highest level target risk event is 9.
  • the first preset value is 5, and the number of target risk events with the same month as the time information and the classification value greater than 5 in the event number information in Table 5 is 4.
  • the second preset value is 7, the most recent occurrence time of the target risk event with a classification value greater than 7 in the event quantity information in Table 5 is acquired, and the year F between the occurrence time and the time information is acquired as 3.
  • the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the risk coefficient corresponding to the risk early warning request .
  • the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the risk coefficient corresponding to the risk warning request.
  • the overall risk coefficient of multiple risk types can be calculated according to the above method. Specifically, the target risk event corresponding to each risk type can be calculated separately through the risk coefficient calculation model. Calculate, and use the average value of the calculation results corresponding to all risk types obtained by calculation as the risk coefficient corresponding to the risk warning request.
  • step S152 includes sub-steps S1521, S1522, S1523 and S1524.
  • S1521 according to the risk distance scoring rule, obtain a risk distance score corresponding to each risk type in the risk warning request to obtain risk distance score information.
  • risk distance score corresponding to each risk type in the risk warning request according to the risk distance scoring rule to obtain risk distance score information, wherein the risk distance scoring rule includes risk area information and risk distance score mapping information .
  • the population density score corresponding to the risk warning request is obtained according to the population density scoring rule, where the population density scoring rule includes population density information and population density score mapping information.
  • the target risk event corresponding to each risk type is classified to obtain the event classification quantity information including each risk type.
  • S160 Generate early warning information corresponding to the risk early warning request according to the preset early warning prompt model and the risk coefficient.
  • the early warning prompt information corresponding to the risk early warning request is generated.
  • the pre-warning reminder model can be used to obtain the warning reminder information corresponding to the risk warning request.
  • the warning reminder model contains multiple warning levels, and each warning level corresponds to a risk coefficient interval.
  • the warning level corresponding to the risk factor is generated, and the warning message including the warning level is generated.
  • the generated warning message can enhance the function of prompting the user.
  • step S160 includes substeps S161 and S162.
  • the early warning prompt model contains multiple prompt levels, and each prompt level corresponds to a risk coefficient interval.
  • each prompt level corresponds to a risk coefficient interval.
  • multiple reminder levels can be distinguished by different reminder colors, different reminder texts, and different reminder frequencies.
  • the display colors corresponding to the prompt levels can be distinguished by using four colors of green, blue, yellow, and red.
  • the risk warning request that is, the warning level information, corresponding warning prompt information is generated.
  • the risk warning request includes geographic location information, risk type information, and corresponding early warning information can be generated based on the geographic location information, risk type information, and early warning level information contained therein. After the user receives the early warning information, the user can clarify what it contains Geographic location information, risk type information and the threat of corresponding risk events.
  • the information crawling program is executed to obtain risk events, the risk events are merged and reorganized according to the time factor to obtain risk event reorganization information, and the risk event reorganization information is obtained to match the risk early warning request
  • the target risk event is calculated to obtain the risk coefficient
  • the early warning information corresponding to the risk coefficient and the risk early warning request is obtained.
  • the embodiment of the present application also provides a disaster risk early warning device, which is used to implement any embodiment of the foregoing disaster risk early warning method.
  • FIG. 6, is a schematic block diagram of a disaster risk early warning device provided by an embodiment of the present application.
  • the disaster risk early warning device can be configured in the user terminal.
  • the disaster risk early warning device 100 includes an event information acquiring unit 110, an event information merging and reorganizing unit 120, a target risk event acquiring unit 130, a risk type information judging unit 140, a risk coefficient calculation unit 150, and an early warning information generating unit 160.
  • the event information acquiring unit 110 is configured to crawl information matching a preset risk keyword in a web page corresponding to a preset network address to obtain event information containing multiple risk events.
  • the parameter values include preset network addresses and preset risk keywords. By crawling the information matching the risk keywords in the webpage corresponding to the network address, you can get multiple risks. Event information of the event.
  • the preset network address may be the network address of a weather station website, a seismic station website, and a news media website;
  • the preset risk keywords may be keywords related to typhoons, earthquakes, floods, wildfires, etc.
  • the acquired event information contains multiple risk events, which are specific information about natural disasters such as typhoons, earthquakes, floods, and wildfires that occur in a certain location.
  • the event information merging and reorganizing unit 120 is configured to merge and reorganize the risk events contained in the event information according to preset event factors to obtain risk event reorganization information.
  • the risk events included in the event information are merged and reorganized according to preset event factors to obtain risk event reorganization information. Since different websites may all record the same risk, and the same risk event may be recorded multiple times in a certain website, it is necessary to merge multiple duplicate records corresponding to a risk event in the event information through event factors Reorganization means that only the first record among multiple duplicate records corresponding to a risk event is retained to obtain the risk event reorganization information. Specifically, it is necessary to first obtain the corresponding key event information from each risk event according to the event factor, and merge and reorganize the risk event based on the key event information.
  • the event factor includes the name, time, location, risk type, and degree.
  • the event information merging and reorganization unit 120 includes sub-units: an event key information extraction unit 121 and an event reorganization information acquisition unit 122.
  • the key event information extraction unit 121 is configured to extract key event information corresponding to each risk event from the event information according to the event factor.
  • the key event information corresponding to each risk event is extracted from the event information according to the preset event factor.
  • Event factors include name, time, location, risk type, and degree. According to the event factors, obtain the corresponding name information, time information, location information, type information, and degree information of a risk event to get the event corresponding to the risk event. Key information, the key event information corresponding to each risk event can be obtained through the above methods.
  • the event reorganization information acquisition unit 122 is configured to merge and reorganize the risk events according to the key event information to obtain risk event reorganization information.
  • the risk events are merged and reorganized according to the key event information to obtain risk event reorganization information. Specifically, judge whether there are multiple duplicate records of the same risk event based on the key event information. If the name information, time information, location information, and type information of the two risk events are the same, it indicates that the two risk events mentioned above are certain Two duplicate records corresponding to the risk event, otherwise the above two risk events are records corresponding to two independent risk events.
  • the risk event does not need to be merged and reorganized; if there are multiple duplicate records for a risk event, the risk event needs to be merged and reorganized, that is, only the risk is retained For the first record among multiple duplicate records corresponding to the event, all risk events are merged and reorganized according to the above method to obtain risk event reorganization information.
  • the target risk event obtaining unit 130 is configured to obtain a target risk event matching the risk early warning request in the risk event reorganization information if a risk warning request input by the user is received.
  • the target risk event matching the risk warning request in the risk event reorganization information is obtained, wherein the risk warning request includes geographic location information, risk type information, and time information .
  • the risk warning request is the information entered by the user to issue corresponding warning prompts for the threat of a risk event at a certain time.
  • the risk warning request includes geographic location information, that is, the specific location where risk warning is required;
  • the warning request also includes risk type information.
  • the risk type information can contain only one type of risk, that is, the corresponding warning prompt information can be issued for the threat of a certain risk type corresponding to the risk event, and the risk type information can also Contains a variety of different risk types, that is, a corresponding early warning message is issued for the overall threat of risk events corresponding to multiple risk types; the risk warning request also includes time information, which can be the current time or a certain time in the future point.
  • the risk type information judging unit 140 is used to judge whether the risk type information of the risk warning request includes multiple risk types to obtain the judgment result.
  • the risk type information of the risk warning request contains multiple risk types to obtain the judgment result. Because in the specific application process, the risk type information may include only one type of risk or multiple different risks. Type, for the number of risk types contained in the risk warning request is one or more, different methods need to be used to obtain the corresponding risk coefficient. Therefore, before obtaining the risk coefficient of the risk warning request, the risk type information of the risk warning request must be obtained first Whether it contains multiple risk types for judgment.
  • the risk coefficient calculation unit 150 is configured to calculate the target risk event according to a preset risk coefficient calculation model and the judgment result to obtain a risk coefficient corresponding to the risk warning request.
  • the target risk event is calculated according to the preset risk coefficient calculation model and the judgment result to obtain the risk coefficient corresponding to the risk early warning request.
  • the risk coefficient calculation unit 150 includes sub-units: a first risk coefficient calculation unit 151 and a second risk coefficient calculation unit 152.
  • the first risk coefficient calculation unit 151 is configured to, if the judgment result is that the risk type information does not include multiple risk types, calculate the target risk event according to a preset risk coefficient calculation model to obtain the risk The risk coefficient corresponding to the risk type in the early warning request.
  • the risk coefficient calculation model includes risk distance scoring rules, population density scoring rules, risk event classification rules, and risk coefficient calculation formulas.
  • the risk coefficient calculation model is the model used to calculate the risk coefficient corresponding to the risk warning request. Specifically, the risk coefficient calculation model includes risk distance scoring rules, population density scoring rules, risk event classification rules, and risk coefficient calculation formulas.
  • the distance scoring rule can be used to obtain the risk distance score corresponding to the risk warning request; the population density scoring rule can be used to obtain the population density score corresponding to the risk warning request; the risk event classification rule is used to classify the specific level of risk events Rules, after classifying the risk events of different risk types, the risk events of different risk types can be quantitatively analyzed; the risk coefficient calculation formula is the formula used to calculate the risk coefficient.
  • the first risk coefficient calculation unit 151 includes sub-units: a risk distance score acquisition unit 1511, a population density score acquisition unit 1512, an event number information acquisition unit 1513, and a maximum rating value acquisition unit 1511. Unit 1514, event number statistics unit 1515, year information acquisition unit 1516, and risk coefficient calculation unit 1517.
  • the risk distance score obtaining unit 1511 is configured to obtain the risk distance score E corresponding to the risk early warning request according to the risk distance scoring rule.
  • the risk distance score E corresponding to the risk warning request is obtained according to the risk distance scoring rule, where the risk distance scoring rule includes risk area information and risk distance score mapping information.
  • the risk area information contains the risk area corresponding to each risk type, that is, the risk event can correspond to the corresponding risk area according to its type;
  • the risk distance score mapping information is the geographic location information used in the risk warning request The mapping information for scoring the distance to the corresponding target risk area. The distance between different geographic location information and the target risk area is different, and the probability of disaster risk is different. Therefore, the risk distance scoring mapping information can be obtained and risk warning Request the corresponding risk distance score.
  • the risk distance score obtaining unit 1511 includes subunits: a target risk area matching unit 1511a, a risk distance information obtaining unit 1511b, and a risk distance information mapping unit 1511c.
  • the target risk area matching unit 1511a is configured to obtain a target risk area matching the risk type in the risk area information according to the risk type in the risk early warning request.
  • the risk area information contains the risk area corresponding to each type of risk. According to the risk type in the risk warning request, the risk area matching the risk type can be obtained as the target risk area.
  • the risk distance information acquiring unit 1511b is configured to acquire the risk distance information between the target risk area and the geographic location information according to the geographic location information in the risk early warning request.
  • the risk distance information between the target risk area and the geographic location information is "0"; if the geographic location information in the risk warning request is not in the risk area, the target The risk distance information between the risk area and the geographic location information is the actual distance between the geographic location information and the edge of the target risk area.
  • the risk distance information mapping unit 1511c is configured to map the risk distance information according to the risk distance score mapping information to obtain the risk distance score E corresponding to the risk warning request.
  • the risk distance information is mapped according to the risk distance score mapping information to obtain the risk distance score E corresponding to the risk warning request.
  • the risk distance scoring mapping information contains multiple mapping intervals, and each mapping interval corresponds to a score value.
  • the score value corresponding to a mapping interval matching the risk distance information can be obtained according to the risk distance information, and the score value obtained is the risk Distance score E.
  • the population density score obtaining unit 1512 is configured to obtain the population density score P corresponding to the risk warning request according to the population density scoring rule.
  • the population density score P corresponding to the risk warning request is obtained according to the population density scoring rule, wherein the population density scoring rule includes population density information and population density score mapping information.
  • the population density information contains the population density value corresponding to each geographic location information.
  • the population density score mapping information is the mapping information used to score the population density value corresponding to the geographic location information in the risk warning request. Areas with different population density values , The hazards of the same disaster risk are also different, so the population density score corresponding to the risk warning request can be obtained through the population density score mapping information.
  • the population density score obtaining unit 1512 includes sub-units: a population density value obtaining unit 1512a and a population density value mapping unit 1512b.
  • the population density value obtaining unit 1512a is configured to obtain the population density value corresponding to the geographic location information in the population density information according to the geographic location information in the risk early warning request.
  • the population density information includes the population density value corresponding to each geographic location information, and the population density value corresponding to the geographic location information can be obtained according to the geographic location information in the risk warning request.
  • the population density value mapping unit 1512b is configured to map the population density value according to the population density score mapping information to obtain the population density score P corresponding to the risk warning request.
  • the population density score mapping information includes multiple mapping intervals, and each mapping interval corresponds to a score value.
  • the score value corresponding to a mapping interval matching the population density value can be obtained according to the population density value, and the score value obtained is the population Density score P.
  • the event quantity information acquiring unit 1513 is configured to classify the target risk event according to the risk event classification rule to obtain event quantity information including the target risk event quantity of each level.
  • the target risk event is classified according to the risk event classification rule to obtain event quantity information including the target risk event quantity of each level.
  • each level of target risk event corresponds to a grading value.
  • the risk event grading rules are rules for grading target risk events.
  • the risk event grading rules include specific rules for grading risk events of each type of risk. After grading all target risk events, you can get the number of events including the number of target risk events at each level.
  • the maximum classification value obtaining unit 1514 is configured to obtain the classification value Dmax of the highest-level target risk event that is the same month as the time information in the event quantity information.
  • the event number statistics unit 1515 is configured to obtain the target risk event number N in the event number information that is the same month as the time information and has a grading value greater than a first preset value.
  • the year information acquiring unit 1516 is configured to acquire the year F between the most recent occurrence time of the target risk event whose classification value is greater than the second preset value in the event quantity information and the time information, wherein the second The preset value is greater than the first preset value.
  • the second risk coefficient calculation unit 152 is configured to: if the judgment result is that the risk type information includes multiple risk types, the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the sum The risk coefficient corresponding to the risk warning request.
  • the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the risk coefficient corresponding to the risk warning request.
  • the overall risk coefficient of multiple risk types can be calculated according to the above method. Specifically, the target risk event corresponding to each risk type can be calculated separately through the risk coefficient calculation model. Calculate, and use the average value of the calculation results corresponding to all risk types obtained by calculation as the risk coefficient corresponding to the risk warning request.
  • the second risk coefficient calculation unit 152 includes subunits: a risk distance score information acquisition unit 1521, a population density score acquisition unit 1522, an event classification number information acquisition unit 1523, and a risk coefficient average calculation unit 1524.
  • the risk distance score information acquiring unit 1521 is configured to acquire the risk distance score corresponding to each risk type in the risk warning request according to the risk distance score rule to obtain risk distance score information.
  • risk distance score corresponding to each risk type in the risk warning request according to the risk distance scoring rule to obtain risk distance score information, wherein the risk distance scoring rule includes risk area information and risk distance score mapping information .
  • the population density score obtaining unit 1522 is configured to obtain a population density score corresponding to the risk warning request according to the population density scoring rule.
  • the population density score corresponding to the risk warning request is obtained according to the population density scoring rule, where the population density scoring rule includes population density information and population density score mapping information.
  • the event classification quantity information acquiring unit 1523 is configured to classify the target risk event corresponding to each risk type according to the risk event classification rule to obtain event classification quantity information including each risk type.
  • the target risk event corresponding to each risk type is classified to obtain the event classification quantity information including each risk type.
  • the average risk coefficient calculation unit 1524 is configured to input the time information in the risk early warning request, the risk distance scoring information, and the event classification quantity information into the risk coefficient calculation formula, so as to obtain the same as the risk early warning request The average value corresponding to multiple risk types to obtain the risk coefficient.
  • the early warning prompt information generating unit 160 is configured to generate early warning prompt information corresponding to the risk early warning request according to a preset early warning prompt model and the risk coefficient.
  • the early warning prompt information corresponding to the risk early warning request is generated.
  • the pre-warning reminder model can be used to obtain the warning reminder information corresponding to the risk warning request.
  • the warning reminder model contains multiple warning levels, and each warning level corresponds to a risk coefficient interval.
  • the warning level corresponding to the risk factor is generated, and the warning message including the warning level is generated.
  • the generated warning message can enhance the function of prompting the user.
  • the warning prompt information generating unit 160 includes sub-units: a prompt level information acquiring unit 161 and a prompt information generating unit 162.
  • the prompt level information obtaining unit 161 is configured to obtain prompt level information corresponding to the risk coefficient in the early warning prompt model.
  • the early warning prompt model contains multiple prompt levels, and each prompt level corresponds to a risk coefficient interval.
  • each prompt level corresponds to a risk coefficient interval.
  • the prompt information generating unit 162 is configured to generate corresponding early warning information according to the risk early warning request, that is, the early warning level information.
  • the risk warning request that is, the warning level information, corresponding warning prompt information is generated.
  • the risk warning request includes geographic location information, risk type information, and corresponding early warning information can be generated based on the geographic location information, risk type information, and early warning level information contained therein. After the user receives the early warning information, the user can clarify what it contains Geographic location information, risk type information and the threat of corresponding risk events.
  • the disaster risk early warning device provided in this embodiment of the application is used to implement the above disaster risk early warning method, execute an information crawling program to obtain risk events, merge and reorganize risk events according to time factors to obtain risk event reorganization information, and obtain risk event reorganization information
  • For the target risk event that matches the risk warning request calculate the target risk event according to the preset risk coefficient calculation model to obtain the risk factor, and obtain the warning prompt information corresponding to the risk factor and the risk warning request.
  • the above disaster risk early warning device can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in FIG. 11.
  • FIG. 11 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • the computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
  • the non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032.
  • the processor 502 can execute the disaster risk early warning method.
  • the processor 502 is used to provide calculation and control capabilities, and support the operation of the entire computer device 500.
  • the internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503.
  • the processor 502 can execute the disaster risk early warning method.
  • the network interface 505 is used for network communication, such as providing data information transmission.
  • the structure shown in FIG. 11 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied.
  • the specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
  • the processor 502 is configured to run a computer program 5032 stored in the memory to realize the following function: crawl the information that matches the preset risk keyword in the webpage corresponding to the preset network address to obtain the Event information of a risk event; according to preset event factors, the risk events contained in the event information are merged and reorganized to obtain risk event reorganization information, where the event factors include name, time, location, risk type, degree If the risk warning request input by the user is received, the target risk event matching the risk warning request in the risk event reorganization information is acquired, wherein the risk warning request includes geographic location information, risk type information, and time Information; determine whether the risk type information of the risk warning request includes multiple risk types to obtain the judgment result; calculate the target risk event according to the preset risk coefficient calculation model and the judgment result to obtain the risk The risk coefficient corresponding to the early warning request; the early warning prompt information corresponding to the risk early warning request is generated according to the preset early warning prompt model and the risk coefficient.
  • the processor 502 when the processor 502 performs the step of merging and reorganizing the risk events contained in the event information according to preset event factors to obtain risk event reorganization information, the following operations are performed: The key event information corresponding to each risk event is extracted from the event information; the risk events are merged and reorganized according to the key event information to obtain risk event reorganization information.
  • the processor 502 performs the following operations when performing the step of calculating the target risk event according to the preset risk coefficient calculation model and the judgment result to obtain the risk coefficient corresponding to the risk warning request : If the judgment result is that the risk type information does not contain multiple risk types, calculate the target risk event according to a preset risk coefficient calculation model to obtain the risk coefficient corresponding to the risk type in the risk warning request If the judgment result is that the risk type information contains multiple risk types, the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the risk coefficient corresponding to the risk warning request.
  • the processor 502 performs the following operations when performing the step of calculating the target risk event according to a preset risk coefficient calculation model to obtain the risk coefficient corresponding to the risk type in the risk warning request:
  • the risk distance scoring rule obtains the risk distance score E corresponding to the risk warning request;
  • the population density score P corresponding to the risk warning request is obtained according to the population density scoring rule;
  • the target risk events are graded to obtain event quantity information including the number of target risk events at each level, where each level of target risk event corresponds to a grading value; the highest number of events in the event quantity information that is the same as the time information month The grading value Dmax of the first-level target risk event; acquiring the target risk event number N in the event number information that is the same month as the time information and the grading value is greater than the first preset value; acquiring the event number information in the grading value The year F between the last occurrence time of the target risk event of the second preset value and the time information, wherein the second preset value is greater than
  • the processor 502 when the processor 502 executes the step of generating the warning message corresponding to the risk warning request according to the preset warning warning model and the risk coefficient, the processor 502 performs the following operations: obtaining the warning warning model and Early warning level information corresponding to the risk coefficient; corresponding early warning prompt information is generated according to the risk early warning request, that is, the early warning level information.
  • the embodiment of the computer device shown in FIG. 11 does not constitute a limitation on the specific configuration of the computer device.
  • the computer device may include more or less components than those shown in the figure. Or combine certain components, or different component arrangements.
  • the computer device may only include a memory and a processor. In such embodiments, the structures and functions of the memory and the processor are the same as those of the embodiment shown in FIG. 11, which will not be repeated here.
  • the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.
  • a computer-readable storage medium may be non-volatile or volatile.
  • the computer-readable storage medium stores a computer program, where the computer program, when executed by the processor, implements the following steps: crawling the information that matches the preset risk keyword in the webpage corresponding to the preset network address to obtain the Event information of risk events; merge and reorganize the risk events contained in the event information according to preset event factors to obtain risk event reorganization information, where the event factors include name, time, location, risk type, and degree; If the risk warning request input by the user is received, the target risk event matching the risk warning request in the risk event reorganization information is obtained, wherein the risk warning request includes geographic location information, risk type information, and time information ; Determine whether the risk type information of the risk warning request includes multiple risk types to obtain the judgment result; calculate the target risk event according to the preset risk coefficient calculation model and the judgment result to obtain the risk warning Request a corresponding risk coefficient; according to a preset early warning prompt
  • the step of merging and reorganizing the risk events included in the event information according to a preset event factor to obtain risk event reorganization information includes: extracting from the event information according to the event factor Obtain key event information corresponding to each risk event; merge and reorganize the risk events according to the key event information to obtain risk event reorganization information.
  • the step of calculating the target risk event according to the preset risk coefficient calculation model and the judgment result to obtain the risk coefficient corresponding to the risk warning request includes: if the judgment result is Because the risk type information does not include multiple risk types, the target risk event is calculated according to a preset risk coefficient calculation model to obtain the risk coefficient corresponding to the risk type in the risk warning request; if the judgment result Because the risk type information includes multiple risk types, the average value obtained by calculating the target risk event according to a preset risk coefficient calculation model is used as the risk coefficient corresponding to the risk early warning request.
  • the step of calculating the target risk event according to a preset risk coefficient calculation model to obtain the risk coefficient corresponding to the risk type in the risk warning request includes: according to the risk distance scoring rule Obtain the risk distance score E corresponding to the risk warning request; acquire the population density score P corresponding to the risk warning request according to the population density scoring rule; classify the target risk event according to the risk event classification rule To obtain event quantity information including the number of target risk events at each level, wherein each level of target risk event corresponds to a grading value; obtain the highest level target risk event information in the event quantity information that is the same month as the time information Grading value Dmax; acquiring the target risk event number N in the event number information that is the same month as the time information and having a grading value greater than a first preset value; acquiring the event number information with a grading value greater than a second preset value The year F between the most recent occurrence time of the target risk event and the time information, wherein the second preset value is greater than the first preset value;
  • the step of generating early warning information corresponding to the risk early warning request according to a preset early warning prompt model and the risk coefficient includes: obtaining information corresponding to the risk coefficient in the early warning prompt model Early warning level information; generating corresponding early warning prompt information according to the risk early warning request, that is, the early warning level information.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Computer Security & Cryptography (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geology (AREA)
  • Emergency Management (AREA)
  • Alarm Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种灾害风险预警方法、装置、计算机设备及存储介质，可以通过智慧城市中的智慧安防实现。方法包括：对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息（S110），根据时间因子对风险事件进行归并重组得到风险事件重组信息（S120），获取风险事件重组信息中与风险预警请求相匹配的目标风险事件（S130），根据预置风险系数计算模型对目标风险事件进行计算得到风险系数，获取与风险系数及风险预警请求对应的预警提示信息。基于大数据处理技术，可对任意时间发生风险事件的风险进行预警，并在预警过程中综合了地理位置信息、时间信息等因素，提高了对发生风险事件的风险进行预警的准确性。

Description

灾害风险预警方法、装置、计算机设备及存储介质
本申请要求于2019年07月31日提交中国专利局、申请号为2019107020545，发明名称为“灾害风险预警方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，尤其涉及一种灾害风险预警方法、装置、计算机设备及存储介质。
背景技术
为避免因极端天气等潜在风险对人员或物资造成损伤，可通过现有信息对未来发生风险事件的风险进行预警。由于风险事件的发生概率与上一次发生风险事件所间隔的时间存在关联，现有技术均是通过计算模型对发生风险事件的风险进行预警，发明人意识到，由于计算模型中并未纳入时间这一参考因子，导致在对风险事件的风险进行预警时准确性不足，且仅能对当前发生风险事件的风险进行预警而无法对将来某一时间发生风险事件的风险进行预警。因而，现有的预警方法存在无法对发生风险事件的风险进行准确预警的问题。
发明内容
本申请实施例提供了一种灾害风险预警方法、装置、计算机设备及存储介质，旨在解决现有技术方法中的灾害风险预警方法在进行风险预警时存在较大偏差的问题。
第一方面，本申请实施例提供了一种灾害风险预警方法，其包括：
对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；
根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果；
根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
第二方面，本申请实施例提供了一种灾害风险预警装置，其包括：
事件信息获取单元，用于对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；
事件信息归并重组单元，用于根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
目标风险事件获取单元，用于若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
风险类型信息判断单元，用于判断所述风险预警请求的风险类型信息中是否包含多个风险类型；
风险系数计算单元，用于根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
预警提示信息生成单元，用于根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
第三方面，本申请实施例又提供了一种计算机设备，其包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述第一方面所述的灾害风险预警方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，其中所述计算机可读存储介质存储有计算机程序，所述计算机程序当被处理器执行时使所述处理器执行上述第一方面所述的灾害风险预警方法。
本申请实施例提供了一种灾害风险预警方法、装置、计算机设备及存储介质。执行信息爬取程序获取风险事件，根据时间因子对风险事件进行归并重组得到风险事件重组信息，获取风险事件重组信息中与风险预警请求相匹配的目标风险事件，根据预置风险系数计算模型对目标风险事件进行计算得到风险系数，并获取与风险系数及风险预警请求对应的预警提示信息。通过上述方法，可对任意时间发生风险事件的风险进行预警，并在预警过程中综合了地理位置信息、时间信息等因素，提高了对发生风险事件的风险进行预警的准确性。
附图说明
图1为本申请实施例提供的灾害风险预警方法的流程示意图；
图2为本申请实施例提供的灾害风险预警方法的子流程示意图；
图3为本申请实施例提供的灾害风险预警方法的子流程示意图；
图4为本申请实施例提供的灾害风险预警方法的另一子流程示意图；
图5为本申请实施例提供的灾害风险预警方法的另一子流程示意图；
图6为本申请实施例提供的灾害风险预警装置的示意性框图；
图7为本申请实施例提供的灾害风险预警装置的子单元示意性框图；
图8为本申请实施例提供的灾害风险预警装置的另一子单元示意性框图；
图9为本申请实施例提供的灾害风险预警装置的另一子单元示意性框图；
图10为本申请实施例提供的灾害风险预警装置的另一子单元示意性框图；
图11为本申请实施例提供的计算机设备的示意性框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”和“包含”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
请参阅图1，图1是本申请实施例提供的灾害风险预警方法的流程示意图。该灾害风险预警方法应用于用户终端中，该方法通过安装于用户终端中的应用软件进行执行，用户终端即是用于执行灾害风险预警方法以对灾害发生的风险进行预警的终端设备，例如台式电脑、笔记本电脑、平板电脑或手机等。
如图1所示，该方法包括步骤S110～S160。
S110、对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息。
对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息，其中，所述事件信息包括事件基本信息及事件描述信息，基本信息即是风险事件的种类及名称等信息，事件描述信息即是对事件进行具体描述的详细信息。执行已配置参数值的信息爬取程序，参数值包括预置网络地址及预置风险关键字，对网络地址所对应网页中与风险关键字相匹配的信息进行爬取即可得到包含多个风险事件的事件信息。具体的，为对某一地区发生风险事件的可能性进行计算分析，需从互联网中爬取该地区所发生的历史风险事件，信息爬取程序中的参数值可由用户预先进行配置。具体的，预置的网络地址可以是气象台网站、地震台网站及新闻媒体网站的网络地址；预置风险关键字可以是与台风、地震、洪水、山火等相关的关键字。所获取到的事件信息中包含多个风险事件，风险事件也即是某一地点所发生的台风、地震、洪水、山火等自然灾害的具体信息。
例如，某一风险事件为：超强台风“风险事件A”，2018年9月16日过境深圳，中心附近最大风力14级。超强台风“风险事件A”为该风险事件的基本信息，其余部分为该风险事件的描述信息。
S120、根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风 险事件重组信息。
根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息。由于不同网站可能均会对同一风险进行记录，同一风险事件也可能会在某一网站中被多次记录，因此需通过事件因子对事件信息中针对某一风险事件对应的多个重复记录进行归并重组，也即是仅保留一个风险事件对应的多个重复记录中的第一个记录以得到风险事件重组信息。具体的，需先根据事件因子从每一风险事件中获取对应的事件关键信息，并基于事件关键信息对风险事件进行归并重组，其中，事件因子包括名称、时间、地点、风险类型、程度。
在一实施例中，如图2所示，步骤S120包括子步骤S121和S122。
S121、根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息。
根据预置事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息。事件因子包括名称、时间、地点、风险类型、程度，根据事件因子分别获取某一风险事件中对应包含的名称信息、时间信息、地点信息、类型信息及程度信息即可得到该风险事件对应的事件关键信息，通过上述方法即可获取得到每一风险事件对应的事件关键信息。
例如，根据事件因子从上述示例中获取得到该风险事件的事件关键信息如表1所示。
名称 时间 地点 风险类型 程度
风险事件A 2018年9月16日 深圳 台风 14级
表1
S122、根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。具体的，根据事件关键信息对同一风险事件是否存在多个重复记录进行判断，若两个风险事件的名称信息、时间信息、地点信息、类型信息均相同，则表明上述两个风险事件为某一风险事件所对应的两个重复记录，否则上述两个风险事件为两个相互独立的风险事件分别对应的记录。若某一风险事件不存在多个重复记录，则无需对该风险事件进行归并重组；若某一风险事件存在多个重复记录，则需对该风险事件进行归并重组，也即是仅保留该风险事件对应的多个重复记录中的第一个记录，根据上述方法对所有风险事件进行归并重组以得到风险事件重组信息。
S130、若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件。
若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息。风险预警请求即是用户所输入的对某一时间出现风险事件的威胁性发出相应预警提示信息的请求信息，风险预警请求中包括地理位置信息，也即是所需进行风险预警的具体地点；风险预警请求中还包括风险类型信息，风险类型信息中可以仅包含一种风险类型，也即是可以对某一种风险类型对应风险事件的威胁性发出相应的预警提示信息，风险 类型信息中还可以包含多种不同的风险类型，也即是针对多种风险类型对应风险事件的整体威胁性发出相应的预警提示信息；风险预警请求中还包括时间信息，时间信息可以是当前时间或未来某一时间点。
S140、判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果。
对所述风险预警请求的风险类型信息中是否包含多个风险类型进行判断以得到判断结果，由于具体应用过程中，风险类型信息中可以仅包含一种风险类型，也可以包含多种不同的风险类型，针对风险预警请求中所包含风险类型的数量为一个或多个，需采用不同方法获取对应的风险系数，因此在获取风险预警请求的风险系数之前，需先对风险预警请求的风险类型信息中是否包含多个风险类型进行判断。
S150、根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数。
根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数。
在一实施例中，如图3所示，步骤S150包括子步骤S151和S152。
S151、若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数。
若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数，其中，所述风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式。风险系数计算模型即是用于对风险预警请求对应的风险系数进行计算的模型，具体的，风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式，风险距离评分规则即可用于获取风险预警请求对应的风险距离评分；人口密度评分规则即可用于获取风险预警请求对应的人口密度评分；风险事件分级规则即是用于对风险事件的具体等级进行分级的规则，将不同风险类型的风险事件进行分级后，可对不同风险类型的风险事件进行量化分析；风险系数计算公式即是用于对风险系数进行计算的公式。
在一实施例中，如图4所示，步骤S151包括子步骤S1511、S1512、S1513、S1514、S1515、S1516和S1517。
S1511、根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E。
根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E，其中，所述风险距离评分规则中包括风险区域信息及风险距离评分映射信息。风险区域信息中包含每一种风险类型对应的风险区域，也即是风险事件根据其类型可与相应的风险区域相对应；风险距离评分映射信息即是用于对风险预警请求中的地理位置信息与相应目标风险区域之间的距离进行评分的映射信息，不同地理位置信息与目标风险区域之间的距离不同， 发生灾害风险的几率也不相同，因此可通过风险距离评分映射信息获取与风险预警请求对应的风险距离评分。
在一实施例中，步骤S1511包括子步骤S1511a、S1511b和S1511c。
S1511a、根据所述风险预警请求中的风险类型获取所述风险区域信息中与所述风险类型相匹配的目标风险区域。风险区域信息中包含每一种风险类型对应的风险区域，根据风险预警请求中的风险类型即可获取与该风险类型相匹配的风险区域作为目标风险区域。
例如，“洪水”这一风险类型对应的目标风险区域是河流、湖泊，“地震”这一风险类型对应的目标风险区域是地震带，“台风”这一风险类型对应的目标风险区域是海岸，“山火”这一风险类型对应的目标风险区域是山区。
S1511b、根据所述风险预警请求中的地理位置信息获取所述目标风险区域与所述地理位置信息之间的风险距离信息。若风险预警请求中的地理位置信息处于风险区域中，则目标风险区域与地理位置信息之间的风险距离信息为“0”；若风险预警请求中的地理位置信息不处于风险区域中，则目标风险区域与地理位置信息之间的风险距离信息为地理位置信息与该目标风险区域边缘的实际距离。
S1511c、根据所述风险距离评分映射信息对所述风险距离信息进行映射以获取与所述风险预警请求对应的风险距离评分E。风险距离评分映射信息包含多个映射区间，每一映射区间对应一个评分值，可根据风险距离信息获取与该风险距离信息相匹配的一个映射区间对应的评分值，所得到的评分值即为风险距离评分E。
例如，风险距离评分映射信息如表2所示。
Figure PCTCN2020093166-appb-000001
表2
某一风险距离信息为63Km，根据表2中的风险距离评分映射信息对应得到风险距离评分E为6。
S1512、根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P。
根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P，其中，所述人口密度评分规则中包括人口密度信息及人口密度评分映射信息。人口密度信息中包含每一地理位置信息对应的人口密度值，人口密度评分映射信息即是用于对风险预警请求中的地理位置信息对应人口密度值进行评分的映射信息，不同人口密度值的地区，发生相同灾害风险的危害性也不相同，因此可通过人口密度评分映射信息获取与风险预警请求对应的人口密度评分。
在一实施例中，步骤S1512包括子步骤S1512a和S1512b。
S1512a、根据所述风险预警请求中的地理位置信息获取人口密度信息中与所述地理位置信息对应的人口密度值。
人口密度信息中包含每一地理位置信息对应的人口密度值，根据风险预警请求中的地 理位置信息即可获取与该地理位置信息相对应的人口密度值。
S1512b、根据所述人口密度评分映射信息对所述人口密度值进行映射以获取与所述风险预警请求对应的人口密度评分P。
根据所述人口密度评分映射信息对所述人口密度值进行映射以获取与所述风险预警请求对应的人口密度评分P。人口密度评分映射信息包含多个映射区间，每一映射区间对应一个评分值，可根据人口密度值获取与该人口密度值相匹配的一个映射区间对应的评分值，所得到的评分值即为人口密度评分P。
例如，人口密度评分映射信息如表3所示。
Figure PCTCN2020093166-appb-000002
表3
某一人口密度值为1.55万人/km2，根据表3中的人口密度评分映射信息对应得到人口密度评分P为4.5。
S1513、根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息。
根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息。其中，每一级目标风险事件对应一个分级值，风险事件分级规则即是用于对目标风险事件进行分级的规则，风险事件分级规则中包含对每一种风险类型的风险事件进行分级的具体规则，对所有目标风险事件进行分级后，即可得到包含每一级目标风险事件数量的事件数量信息。例如，目标风险事件的风险类型为“台风”，与该风险类型相对应的分级规则如表4所示。
程度(级) 15及以上 14 13 12 11 10 9 8 7 6
分级值 10 9 8 7 6 5 4 3 2 1
表4
对所有目标风险事件进行分级后得到的事件数量信息如表5所示。
分级值 数量
10 1
9 1
8 4
7 3
6 6
5 8
4 3
3 1
2 3
1 0
表5
S1514、获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax。
例如，表5的事件数量信息中分级值为“10”的目标风险事件与时间信息月份不相同，分级值为“9”的目标风险事件与时间信息月份相同，获取得到与该时间信息月份相同的最高一级目标风险事件的分级值Dmax为9。
S1515、获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N。
例如，第一预设数值为5，对表5的事件数量信息中与时间信息月份相同且分级值大于5的目标风险事件数量为4。
S1516、获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值。
获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间，并获取该发生时间与时间信息之间间隔的年份F，其中，第二预设数值大于第一预设数值。
例如，第二预设数值为7，获取表5的事件数量信息中分级值大于7的目标风险事件最近一次的发生时间，并获取该发生时间与时间信息之间间隔的年份F为3。
S1517、根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。具体的，在使用风险系数计算公式之前，还将对风险系数计算公式进行训练以对公式中所包含的权重值进行调整。根据上述方法即可计算得到与风险预警请求对应的风险系数，风险系数的数值越大，则表明在风险预警请求中对应地点及对应时间发生风险事件的风险越大。
例如，经训练后所得到的风险系数计算公式为Dv＝0.12×E+0.16×Dmax+0.41×N+0.33×F+0.20×P，根据上述信息计算得到对应的风险系数Dv＝0.12×6+0.16×9+0.41×4+0.33×3+0.20×4.5＝5.69。
S152、若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。若风险类型信息中包含多个风险类型，则可根据上述方法对多种风险类型的总体风险系数进行计算，具体的，可通过风险系数计算模型对每一种风险类型对应的目标风险事件分别进行计算，并将计算所得到的所有风险类型对应计算结果的平均值作为该风险预警请求对 应的风险系数。
在一实施例中，步骤S152包括子步骤S1521、S1522、S1523和S1524。
S1521、根据所述风险距离评分规则获取与所述风险预警请求中每一风险类型对应的风险距离评分以得到风险距离评分信息。
根据所述风险距离评分规则获取与所述风险预警请求中每一风险类型对应的风险距离评分以得到风险距离评分信息，其中，所述风险距离评分规则中包括风险区域信息及风险距离评分映射信息。
S1522、根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分。
根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分，其中，所述人口密度评分规则中包括人口密度信息及人口密度评分映射信息。
S1523、根据所述风险事件分级规则对每一风险类型对应的目标风险事件进行分级以得到包含每一风险类型的事件分级数量信息。
根据所述风险事件分级规则对每一风险类型对应的目标风险事件进行分级以得到包含每一风险类型的事件分级数量信息。
S1524、将所述风险预警请求中的时间信息、所述风险距离评分信息及所述事件分级数量信息输入所述风险系数计算公式，以获取与所述风险预警请求中多个风险类型对应的平均值以得到风险系数。
将所述风险预警请求中的时间信息、所述风险距离评分信息及所述事件分级数量信息输入所述风险系数计算公式，以获取与所述风险预警请求中多个风险类型对应的平均值以得到风险系数。
S160、根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。可通过预置的预警提示模型获取与风险预警请求对应的预警提示信息，具体的，预警提示模型中包含多个提示等级，每一提示等级对应一个风险系数区间，根据预警提示模型即可获取与风险系数对应的提示等级，并生成包含提示等级的预警提示信息，所生成的预警提示信息即可增强对用户进行提示的作用。
在一实施例中，如图5所示，步骤S160包括子步骤S161和S162。
S161、获取所述预警提示模型中与所述风险系数对应的提示等级信息。
获取所述预警提示模型中与所述风险系数对应的提示等级信息。预警提示模型中包含多个提示等级，每一提示等级对应一个风险系数区间，将风险系数与多个风险系数区间进行匹配，即可获取该风险系数所落入的某一风险系数区间，获取该风险系数区间对应的提示等级即可得到对应的提示等级信息。
具体的，预警提示模型中可通过不用提示颜色、不同提示文字、不同提示频率对多个提示等级进行区分。例如，可将提示等级对应的显示颜色采用绿色、蓝色、黄色及红色四种颜色进行区分。
S162、根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。风险预警请求包括地理位置信息、风险类型信息，可根据其中所包含的地理位置信息、风险类型信息及预警等级信息生成对应的预警提示信息，用户收到预警提示信息后即可明确其中所包含的地理位置信息、风险类型信息及发生相应风险事件的威胁性。
在本申请实施例所提供的灾害风险预警方法中，执行信息爬取程序获取风险事件，根据时间因子对风险事件进行归并重组得到风险事件重组信息，获取风险事件重组信息中与风险预警请求相匹配的目标风险事件，根据预置风险系数计算模型对目标风险事件进行计算得到风险系数，并获取与风险系数及风险预警请求对应的预警提示信息。通过上述方法，可对任意时间发生风险事件的风险进行预警，并在预警过程中综合了地理位置信息、时间信息等因素，提高了对发生风险事件的风险进行预警的准确性。
本申请实施例还提供一种灾害风险预警装置，该灾害风险预警装置用于执行前述灾害风险预警方法的任一实施例。具体地，请参阅图6，图6是本申请实施例提供的灾害风险预警装置的示意性框图。该灾害风险预警装置可以配置于用户终端中。
如图6所示，灾害风险预警装置100包括事件信息获取单元110、事件信息归并重组单元120、目标风险事件获取单元130、风险类型信息判断单元140、风险系数计算单元150和预警提示信息生成单元160。
事件信息获取单元110，用于对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息。
对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息，其中，所述事件信息包括事件基本信息及事件描述信息，基本信息即是风险事件的种类及名称等信息，事件描述信息即是对事件进行具体描述的详细信息。执行已配置参数值的信息爬取程序，参数值包括预置网络地址及预置风险关键字，对网络地址所对应网页中与风险关键字相匹配的信息进行爬取即可得到包含多个风险事件的事件信息。具体的，为对某一地区发生风险事件的可能性进行计算分析，需从互联网中爬取该地区所发生的历史风险事件，信息爬取程序中的参数值可由用户预先进行配置。具体的，预置的网络地址可以是气象台网站、地震台网站及新闻媒体网站的网络地址；预置风险关键字可以是与台风、地震、洪水、山火等相关的关键字。所获取到的事件信息中包含多个风险事件，风险事件也即是某一地点所发生的台风、地震、洪水、山火等自然灾害的具体信息。
事件信息归并重组单元120，用于根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息。
根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息。由于不同网站可能均会对同一风险进行记录，同一风险事件也可能会在某一网站中被多次记录，因此需通过事件因子对事件信息中针对某一风险事件对应的多个重复记录进行归并重组，也即是仅保留一个风险事件对应的多个重复记录中的第一个记录以得到 风险事件重组信息。具体的，需先根据事件因子从每一风险事件中获取对应的事件关键信息，并基于事件关键信息对风险事件进行归并重组，其中，事件因子包括名称、时间、地点、风险类型、程度。
其他发明实施例中，如图7所示，所述事件信息归并重组单元120包括子单元：事件关键信息提取单元121和事件重组信息获取单元122。
事件关键信息提取单元121，用于根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息。
根据预置事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息。事件因子包括名称、时间、地点、风险类型、程度，根据事件因子分别获取某一风险事件中对应包含的名称信息、时间信息、地点信息、类型信息及程度信息即可得到该风险事件对应的事件关键信息，通过上述方法即可获取得到每一风险事件对应的事件关键信息。
事件重组信息获取单元122，用于根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。具体的，根据事件关键信息对同一风险事件是否存在多个重复记录进行判断，若两个风险事件的名称信息、时间信息、地点信息、类型信息均相同，则表明上述两个风险事件为某一风险事件所对应的两个重复记录，否则上述两个风险事件为两个相互独立的风险事件分别对应的记录。若某一风险事件不存在多个重复记录，则无需对该风险事件进行归并重组；若某一风险事件存在多个重复记录，则需对该风险事件进行归并重组，也即是仅保留该风险事件对应的多个重复记录中的第一个记录，根据上述方法对所有风险事件进行归并重组以得到风险事件重组信息。
目标风险事件获取单元130，用于若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件。
若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息。风险预警请求即是用户所输入的对某一时间出现风险事件的威胁性发出相应预警提示信息的请求信息，风险预警请求中包括地理位置信息，也即是所需进行风险预警的具体地点；风险预警请求中还包括风险类型信息，风险类型信息中可以仅包含一种风险类型，也即是可以对某一种风险类型对应风险事件的威胁性发出相应的预警提示信息，风险类型信息中还可以包含多种不同的风险类型，也即是针对多种风险类型对应风险事件的整体威胁性发出相应的预警提示信息；风险预警请求中还包括时间信息，时间信息可以是当前时间或未来某一时间点。
风险类型信息判断单元140，用于判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果。
对所述风险预警请求的风险类型信息中是否包含多个风险类型进行判断以得到判断结果，由于具体应用过程中，风险类型信息中可以仅包含一种风险类型，也可以包含多种不 同的风险类型，针对风险预警请求中所包含风险类型的数量为一个或多个，需采用不同方法获取对应的风险系数，因此在获取风险预警请求的风险系数之前，需先对风险预警请求的风险类型信息中是否包含多个风险类型进行判断。
风险系数计算单元150，用于根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数。
根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数。
其他发明实施例中，如图8所示，所述风险系数计算单元150包括子单元：第一风险系数计算单元151和第二风险系数计算单元152。
第一风险系数计算单元151，用于若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数。
若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数，其中，所述风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式。风险系数计算模型即是用于对风险预警请求对应的风险系数进行计算的模型，具体的，风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式，风险距离评分规则即可用于获取风险预警请求对应的风险距离评分；人口密度评分规则即可用于获取风险预警请求对应的人口密度评分；风险事件分级规则即是用于对风险事件的具体等级进行分级的规则，将不同风险类型的风险事件进行分级后，可对不同风险类型的风险事件进行量化分析；风险系数计算公式即是用于对风险系数进行计算的公式。
其他发明实施例中，如图8所示，所述第一风险系数计算单元151包括子单元：风险距离评分获取单元1511、人口密度评分获取单元1512、事件数量信息获取单元1513、最大分级值获取单元1514、事件数量统计单元1515、年份信息获取单元1516和风险系数计算单元1517。
风险距离评分获取单元1511，用于根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E。
根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E，其中，所述风险距离评分规则中包括风险区域信息及风险距离评分映射信息。风险区域信息中包含每一种风险类型对应的风险区域，也即是风险事件根据其类型可与相应的风险区域相对应；风险距离评分映射信息即是用于对风险预警请求中的地理位置信息与相应目标风险区域之间的距离进行评分的映射信息，不同地理位置信息与目标风险区域之间的距离不同，发生灾害风险的几率也不相同，因此可通过风险距离评分映射信息获取与风险预警请求对应的风险距离评分。
其他发明实施例中，所述风险距离评分获取单元1511包括子单元：目标风险区域匹配 单元1511a、风险距离信息获取单元1511b和风险距离信息映射单元1511c。
目标风险区域匹配单元1511a，用于根据所述风险预警请求中的风险类型获取所述风险区域信息中与所述风险类型相匹配的目标风险区域。
根据所述风险预警请求中的风险类型获取所述风险区域信息中与所述风险类型相匹配的目标风险区域。风险区域信息中包含每一种风险类型对应的风险区域，根据风险预警请求中的风险类型即可获取与该风险类型相匹配的风险区域作为目标风险区域。
风险距离信息获取单元1511b，用于根据所述风险预警请求中的地理位置信息获取所述目标风险区域与所述地理位置信息之间的风险距离信息。
根据所述风险预警请求中的地理位置信息获取所述目标风险区域与所述地理位置信息之间的风险距离信息。若风险预警请求中的地理位置信息处于风险区域中，则目标风险区域与地理位置信息之间的风险距离信息为“0”；若风险预警请求中的地理位置信息不处于风险区域中，则目标风险区域与地理位置信息之间的风险距离信息为地理位置信息与该目标风险区域边缘的实际距离。
风险距离信息映射单元1511c，用于根据所述风险距离评分映射信息对所述风险距离信息进行映射以获取与所述风险预警请求对应的风险距离评分E。
根据所述风险距离评分映射信息对所述风险距离信息进行映射以获取与所述风险预警请求对应的风险距离评分E。风险距离评分映射信息包含多个映射区间，每一映射区间对应一个评分值，可根据风险距离信息获取与该风险距离信息相匹配的一个映射区间对应的评分值，所得到的评分值即为风险距离评分E。
人口密度评分获取单元1512，用于根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P。
根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P，其中，所述人口密度评分规则中包括人口密度信息及人口密度评分映射信息。人口密度信息中包含每一地理位置信息对应的人口密度值，人口密度评分映射信息即是用于对风险预警请求中的地理位置信息对应人口密度值进行评分的映射信息，不同人口密度值的地区，发生相同灾害风险的危害性也不相同，因此可通过人口密度评分映射信息获取与风险预警请求对应的人口密度评分。
其他发明实施例中，所述人口密度评分获取单元1512包括子单元：人口密度值获取单元1512a和人口密度值映射单元1512b。
人口密度值获取单元1512a，用于根据所述风险预警请求中的地理位置信息获取人口密度信息中与所述地理位置信息对应的人口密度值。
人口密度信息中包含每一地理位置信息对应的人口密度值，根据风险预警请求中的地理位置信息即可获取与该地理位置信息相对应的人口密度值。
人口密度值映射单元1512b，用于根据所述人口密度评分映射信息对所述人口密度值进行映射以获取与所述风险预警请求对应的人口密度评分P。
根据所述人口密度评分映射信息对所述人口密度值进行映射以获取与所述风险预警请 求对应的人口密度评分P。人口密度评分映射信息包含多个映射区间，每一映射区间对应一个评分值，可根据人口密度值获取与该人口密度值相匹配的一个映射区间对应的评分值，所得到的评分值即为人口密度评分P。
事件数量信息获取单元1513，用于根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息。
根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息。其中，每一级目标风险事件对应一个分级值，风险事件分级规则即是用于对目标风险事件进行分级的规则，风险事件分级规则中包含对每一种风险类型的风险事件进行分级的具体规则，对所有目标风险事件进行分级后，即可得到包含每一级目标风险事件数量的事件数量信息。
最大分级值获取单元1514，用于获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax。
事件数量统计单元1515，用于获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N。
年份信息获取单元1516，用于获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值。
获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间，并获取该发生时间与时间信息之间间隔的年份F，其中，第二预设数值大于第一预设数值。
风险系数计算单元1517，用于根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。具体的，在使用风险系数计算公式之前，还将对风险系数计算公式进行训练以对公式中所包含的权重值进行调整。根据上述方法即可计算得到与风险预警请求对应的风险系数，风险系数的数值越大，则表明在风险预警请求中对应地点及对应时间发生风险事件的风险越大。
第二风险系数计算单元152，用于若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。若风险类型信息中包含多个风险类型，则可根据上述方法对多种风险类型的总体风险系数进行计算，具体的，可通过风险系数计算模型对每一种风险类型对应的目标风险事件分别进行计算，并将计算所得到的所有风险类型对应计算结果的平均值作为该风险预警请求对 应的风险系数。
其他发明实施例中，所述第二风险系数计算单元152包括子单元：风险距离评分信息获取单元1521、人口密度评分获取单元1522、事件分级数量信息获取单元1523和风险系数平均值计算单元1524。
风险距离评分信息获取单元1521，用于根据所述风险距离评分规则获取与所述风险预警请求中每一风险类型对应的风险距离评分以得到风险距离评分信息。
根据所述风险距离评分规则获取与所述风险预警请求中每一风险类型对应的风险距离评分以得到风险距离评分信息，其中，所述风险距离评分规则中包括风险区域信息及风险距离评分映射信息。
人口密度评分获取单元1522，用于根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分。
根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分，其中，所述人口密度评分规则中包括人口密度信息及人口密度评分映射信息。
事件分级数量信息获取单元1523，用于根据所述风险事件分级规则对每一风险类型对应的目标风险事件进行分级以得到包含每一风险类型的事件分级数量信息。
根据所述风险事件分级规则对每一风险类型对应的目标风险事件进行分级以得到包含每一风险类型的事件分级数量信息。
风险系数平均值计算单元1524，用于将所述风险预警请求中的时间信息、所述风险距离评分信息及所述事件分级数量信息输入所述风险系数计算公式，以获取与所述风险预警请求中多个风险类型对应的平均值以得到风险系数。
将所述风险预警请求中的时间信息、所述风险距离评分信息及所述事件分级数量信息输入所述风险系数计算公式，以获取与所述风险预警请求中多个风险类型对应的平均值以得到风险系数。
预警提示信息生成单元160，用于根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。可通过预置的预警提示模型获取与风险预警请求对应的预警提示信息，具体的，预警提示模型中包含多个提示等级，每一提示等级对应一个风险系数区间，根据预警提示模型即可获取与风险系数对应的提示等级，并生成包含提示等级的预警提示信息，所生成的预警提示信息即可增强对用户进行提示的作用。
其他发明实施例中，如图10所示，所述预警提示信息生成单元160包括子单元：提示等级信息获取单元161和提示信息生成单元162。
提示等级信息获取单元161，用于获取所述预警提示模型中与所述风险系数对应的提示等级信息。
获取所述预警提示模型中与所述风险系数对应的提示等级信息。预警提示模型中包含多个提示等级，每一提示等级对应一个风险系数区间，将风险系数与多个风险系数区间进 行匹配，即可获取该风险系数所落入的某一风险系数区间，获取该风险系数区间对应的提示等级即可得到对应的提示等级信息。
提示信息生成单元162，用于根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。风险预警请求包括地理位置信息、风险类型信息，可根据其中所包含的地理位置信息、风险类型信息及预警等级信息生成对应的预警提示信息，用户收到预警提示信息后即可明确其中所包含的地理位置信息、风险类型信息及发生相应风险事件的威胁性。
在本申请实施例所提供的灾害风险预警装置用于执行上述灾害风险预警方法，执行信息爬取程序获取风险事件，根据时间因子对风险事件进行归并重组得到风险事件重组信息，获取风险事件重组信息中与风险预警请求相匹配的目标风险事件，根据预置风险系数计算模型对目标风险事件进行计算得到风险系数，并获取与风险系数及风险预警请求对应的预警提示信息。通过上述方法，可对任意时间发生风险事件的风险进行预警，并在预警过程中综合了地理位置信息、时间信息等因素，提高了对发生风险事件的风险进行预警的准确性。
上述灾害风险预警装置可以实现为计算机程序的形式，该计算机程序可以在如图11所示的计算机设备上运行。
请参阅图11，图11是本申请实施例提供的计算机设备的示意性框图。
参阅图11，该计算机设备500包括通过系统总线501连接的处理器502、存储器和网络接口505，其中，存储器可以包括非易失性存储介质503和内存储器504。
该非易失性存储介质503可存储操作系统5031和计算机程序5032。该计算机程序5032被执行时，可使得处理器502执行灾害风险预警方法。
该处理器502用于提供计算和控制能力，支撑整个计算机设备500的运行。
该内存储器504为非易失性存储介质503中的计算机程序5032的运行提供环境，该计算机程序5032被处理器502执行时，可使得处理器502执行灾害风险预警方法。
该网络接口505用于进行网络通信，如提供数据信息的传输等。本领域技术人员可以理解，图11中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备500的限定，具体的计算机设备500可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
其中，所述处理器502用于运行存储在存储器中的计算机程序5032，以实现如下功能：对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果； 根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
在一实施例中，处理器502在执行根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息的步骤时，执行如下操作：根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息；根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
在一实施例中，处理器502在执行根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数的步骤时，执行如下操作：若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数；若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
在一实施例中，处理器502在执行根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数的步骤时，执行如下操作：根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E；根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P；根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息，其中，每一级目标风险事件对应一个分级值；获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax；获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N；获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值；根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
在一实施例中，处理器502在执行根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息的步骤时，执行如下操作：获取所述预警提示模型中与所述风险系数对应的预警等级信息；根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
本领域技术人员可以理解，图11中示出的计算机设备的实施例并不构成对计算机设备具体构成的限定，在其他实施例中，计算机设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，在一些实施例中，计算机设备可以仅包括存储器及处理器，在这样的实施例中，存储器及处理器的结构及功能与图11所示实施例一致，在此不再赘述。
应当理解，在本申请实施例中，处理器502可以是中央处理单元(Central Processing Unit，CPU)，该处理器502还可以是其他通用处理器、数字信号处理器(Digital Signal  Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中，通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在本申请的另一实施例中提供计算机可读存储介质。所述计算机可读存储介质可以是非易失性，也可以是易失性。该计算机可读存储介质存储有计算机程序，其中计算机程序被处理器执行时实现以下步骤：对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果；根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
在一实施例中，所述根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息的步骤，包括：根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息；根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
在一实施例中，所述根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数的步骤，包括：若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数；若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
在一实施例中，所述根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数的步骤，包括：根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E；根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P；根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息，其中，每一级目标风险事件对应一个分级值；获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax；获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N；获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值；根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均 为权重值。
在一实施例中，所述根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息的步骤，包括：获取所述预警提示模型中与所述风险系数对应的预警等级信息；根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (20)

  1. 一种灾害风险预警方法，其中，包括：
    对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；
    根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
    若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
    判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果；
    根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
    根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
  2. 根据权利要求1所述的灾害风险预警方法，其中，所述根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，包括：
    根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息；
    根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
  3. 根据权利要求1所述的灾害风险预警方法，其中，所述根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数，包括：
    若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数；
    若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
  4. 根据权利要求3所述的灾害风险预警方法，其中，所述风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式，所述根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数，包括：
    根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E；
    根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P；
    根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息，其中，每一级目标风险事件对应一个分级值；
    获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值 Dmax；
    获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N；
    获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值；
    根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
  5. 根据权利要求1所述的灾害风险预警方法，其中，所述根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息，包括：
    获取所述预警提示模型中与所述风险系数对应的预警等级信息；
    根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
  6. 根据权利要求1-5任一项所述的灾害风险预警方法，其中，所述事件信息包括事件基本信息、事件描述信息，其中，所述事件基本信息包括风险事件的种类、名称，所述事件描述信息是对事件进行具体描述的信息。
  7. 根据权利要求1-6任一项所述的灾害风险预警方法，其中，所述预置网络地址包括气象台网站、地震台网站及新闻媒体网站的网络地址；所述预置风险关键字包括台风、地震、洪水、山火。
  8. 一种灾害风险预警装置，其中，包括：
    事件信息获取单元，用于对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；
    事件信息归并重组单元，用于根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
    目标风险事件获取单元，用于若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
    风险类型信息判断单元，用于判断所述风险预警请求的风险类型信息中是否包含多个风险类型；
    风险系数计算单元，用于根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
    预警提示信息生成单元，用于根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
  9. 一种计算机设备，其中，包括存储器和处理器，所述处理器、和所述存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器用于执行所述存储器的所述程序指令，其中：
    对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多 个风险事件的事件信息；
    根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
    若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
    判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果；
    根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
    根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
  10. 根据权利要求8所述的计算机设备，其中，所述处理器用于：
    根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息；
    根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
  11. 根据权利要求8所述的计算机设备，其中，所述处理器用于：
    若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数；
    若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
  12. 根据权利要求10所述的计算机设备，其中，所述风险系数计算模型包括风险距离评分规则、人口密度评分规则、风险事件分级规则及风险系数计算公式，所述处理器用于：
    根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E；
    根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P；
    根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息，其中，每一级目标风险事件对应一个分级值；
    获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax；
    获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N；
    获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值；
    根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
  13. 根据权利要求8所述的计算机设备，其中，所述处理器用于：
    获取所述预警提示模型中与所述风险系数对应的预警等级信息；
    根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
  14. 根据权利要求8-12任一项所述的计算机设备，其中，所述事件信息包括事件基本信息、事件描述信息，其中，所述事件基本信息包括风险事件的种类、名称，所述事件描述信息是对事件进行具体描述的信息。
  15. 根据权利要求8-13任一项所述的计算机设备，其中，所述预置网络地址包括气象台网站、地震台网站及新闻媒体网站的网络地址；所述预置风险关键字包括台风、地震、洪水、山火。
  16. 一种计算机可读存储介质，其中，所述计算机可读存储介质存储有计算机程序，所述程序指令被处理器执行时，用于实现以下步骤：
    对预置网络地址所对应网页中与预置风险关键字相匹配的信息进行爬取以得到包含多个风险事件的事件信息；
    根据预置事件因子对所述事件信息中所包含的风险事件进行归并重组以得到风险事件重组信息，其中，所述事件因子包括名称、时间、地点、风险类型、程度；
    若接收到用户所输入的风险预警请求，获取所述风险事件重组信息中与所述风险预警请求相匹配的目标风险事件，其中，所述风险预警请求包括地理位置信息、风险类型信息、时间信息；
    判断所述风险预警请求的风险类型信息中是否包含多个风险类型以得到判断结果；
    根据预置风险系数计算模型及所述判断结果对所述目标风险事件进行计算以获取与所述风险预警请求对应的风险系数；
    根据预置预警提示模型及所述风险系数生成与所述风险预警请求对应的预警提示信息。
  17. 根据权利要求16所述的计算机可读存储介质，其中，所述程序指令被处理器执行时，还用于实现以下步骤：
    根据所述事件因子从所述事件信息中提取得到每一风险事件对应的事件关键信息；
    根据所述事件关键信息对所述风险事件进行归并重组以得到风险事件重组信息。
  18. 根据权利要求16所述的计算机可读存储介质，其中，所述程序指令被处理器执行时，还用于实现以下步骤：
    若所述判断结果为所述风险类型信息中不包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算以获取与所述风险预警请求中风险类型对应的风险系数；
    若所述判断结果为所述风险类型信息中包含多个风险类型，根据预置风险系数计算模型对所述目标风险事件进行计算所得的平均值作为与所述风险预警请求对应的风险系数。
  19. 根据权利要求18所述的计算机可读存储介质，其中，所述程序指令被处理器执行时，还用于实现以下步骤：
    根据所述风险距离评分规则获取与所述风险预警请求对应的风险距离评分E；
    根据所述人口密度评分规则获取与所述风险预警请求对应的人口密度评分P；
    根据所述风险事件分级规则对所述目标风险事件进行分级以得到包含每一级目标风险事件数量的事件数量信息，其中，每一级目标风险事件对应一个分级值；
    获取所述事件数量信息中与所述时间信息月份相同的最高一级目标风险事件的分级值Dmax；
    获取所述事件数量信息中与所述时间信息月份相同且分级值大于第一预设数值的目标风险事件数量N；
    获取所述事件数量信息中分级值大于第二预设数值的目标风险事件最近一次的发生时间与所述时间信息之间间隔的年份F，其中，所述第二预设数值大于第一预设数值；
    根据所述风险系数计算公式Dv＝w1×E+w2×Dmax+w3×N+w4×F+w5×P确定与所述风险预警请求对应的风险系数Dv，其中，w1、w2、w3、w4、w5均为权重值。
  20. 根据权利要求16所述的计算机可读存储介质，其中，所述程序指令被处理器执行时，还用于实现以下步骤：
    获取所述预警提示模型中与所述风险系数对应的预警等级信息；
    根据所述风险预警请求即所述预警等级信息生成对应的预警提示信息。
PCT/CN2020/093166 2019-07-31 2020-05-29 灾害风险预警方法、装置、计算机设备及存储介质 Ceased WO2021017607A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910702054.5A CN110544013B (zh) 2019-07-31 2019-07-31 灾害风险预警方法、装置、计算机设备及存储介质
CN201910702054.5 2019-07-31

Publications (1)

Publication Number Publication Date
WO2021017607A1 true WO2021017607A1 (zh) 2021-02-04

Family

ID=68709947

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/093166 Ceased WO2021017607A1 (zh) 2019-07-31 2020-05-29 灾害风险预警方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN110544013B (zh)
WO (1) WO2021017607A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781778A (zh) * 2022-02-23 2022-07-22 中国电子科技集团公司第二十八研究所 一种社会安全风险监测预警方法
CN115640999A (zh) * 2022-10-26 2023-01-24 杭州余杭大数据经营有限公司 山体地质灾害预警处理方法、装置、计算机设备及存储介质
CN115983630A (zh) * 2022-12-12 2023-04-18 厦门市美亚柏科信息股份有限公司 一种基于xxl定时调度的潜在风险人员预警系统
CN116028798A (zh) * 2023-02-21 2023-04-28 煤炭科学技术研究院有限公司 水害预警数据处理方法、装置、计算机设备和存储介质
CN117704292A (zh) * 2023-11-27 2024-03-15 国家石油天然气管网集团有限公司 一种基于油气管网的管网预警系统及预警方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110544013B (zh) * 2019-07-31 2024-03-05 平安科技（深圳）有限公司 灾害风险预警方法、装置、计算机设备及存储介质
CN111815105A (zh) * 2020-05-18 2020-10-23 深圳市第一反应信息科技有限公司 一种用于提供风险评估地图信息的方法与设备
CN114023049B (zh) * 2021-11-25 2022-08-16 西安理工大学 一种山洪灾害预警指标检验复核方法及系统
CN114814888B (zh) * 2022-06-30 2022-09-13 南京源兴智达信息科技有限公司 一种基于北斗三号的手持终端设备
CN115311355B (zh) * 2022-09-20 2023-07-07 中国铁建电气化局集团有限公司 接触网异物风险预警方法、装置、设备及存储介质
CN117035406B (zh) * 2023-07-31 2024-06-18 北京华夏电通科技股份有限公司 审判流程智能管控方法、装置和设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130035859A1 (en) * 2010-01-19 2013-02-07 Swiss Reinsurance Company Ltd. Method and system for automated location dependent natural disaster forecast
CN107169598A (zh) * 2017-05-05 2017-09-15 上海斐讯数据通信技术有限公司 一种基于深度学习的天气预测方法及系统
CN107316163A (zh) * 2017-07-18 2017-11-03 海南师范大学 一种区域灾害风险评估方法
JP6333755B2 (ja) * 2015-02-23 2018-05-30 リズム時計工業株式会社 緊急災害情報受信機
CN109086935A (zh) * 2018-08-07 2018-12-25 中国地质环境监测院 一种区域地质灾害趋势预测方法
CN110544013A (zh) * 2019-07-31 2019-12-06 平安科技（深圳）有限公司 灾害风险预警方法、装置、计算机设备及存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050071217A1 (en) * 2003-09-30 2005-03-31 General Electric Company Method, system and computer product for analyzing business risk using event information extracted from natural language sources
JP2012098820A (ja) * 2010-10-29 2012-05-24 Techno Management Solutions:Kk プロセスリスクアセスメント支援装置
CN103854064B (zh) * 2012-11-29 2017-01-25 中国科学院计算机网络信息中心 一种面向特定区域的事件发生风险预测并预警方法
EP3631365A2 (en) * 2017-05-30 2020-04-08 Nauto Global Limited Systems and methods for safe route determination
CN108304580A (zh) * 2018-03-05 2018-07-20 上海思贤信息技术股份有限公司 一种面向城市网格化管理的重大事件预警方法和系统
CN108876600B (zh) * 2018-08-20 2023-09-05 平安科技（深圳）有限公司 预警信息推送方法、装置、计算机设备和介质
CN109064052A (zh) * 2018-08-20 2018-12-21 国家海洋信息中心 海洋灾害风险事件分类方法及装置
CN109711656B (zh) * 2018-08-20 2023-10-03 云上广济(贵州)信息技术有限公司 多系统关联预警方法、装置、设备及计算机可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130035859A1 (en) * 2010-01-19 2013-02-07 Swiss Reinsurance Company Ltd. Method and system for automated location dependent natural disaster forecast
JP6333755B2 (ja) * 2015-02-23 2018-05-30 リズム時計工業株式会社 緊急災害情報受信機
CN107169598A (zh) * 2017-05-05 2017-09-15 上海斐讯数据通信技术有限公司 一种基于深度学习的天气预测方法及系统
CN107316163A (zh) * 2017-07-18 2017-11-03 海南师范大学 一种区域灾害风险评估方法
CN109086935A (zh) * 2018-08-07 2018-12-25 中国地质环境监测院 一种区域地质灾害趋势预测方法
CN110544013A (zh) * 2019-07-31 2019-12-06 平安科技（深圳）有限公司 灾害风险预警方法、装置、计算机设备及存储介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114781778A (zh) * 2022-02-23 2022-07-22 中国电子科技集团公司第二十八研究所 一种社会安全风险监测预警方法
CN115640999A (zh) * 2022-10-26 2023-01-24 杭州余杭大数据经营有限公司 山体地质灾害预警处理方法、装置、计算机设备及存储介质
CN115983630A (zh) * 2022-12-12 2023-04-18 厦门市美亚柏科信息股份有限公司 一种基于xxl定时调度的潜在风险人员预警系统
CN116028798A (zh) * 2023-02-21 2023-04-28 煤炭科学技术研究院有限公司 水害预警数据处理方法、装置、计算机设备和存储介质
CN117704292A (zh) * 2023-11-27 2024-03-15 国家石油天然气管网集团有限公司 一种基于油气管网的管网预警系统及预警方法

Also Published As

Publication number Publication date
CN110544013B (zh) 2024-03-05
CN110544013A (zh) 2019-12-06

Similar Documents

Publication Publication Date Title
WO2021017607A1 (zh) 灾害风险预警方法、装置、计算机设备及存储介质
Champ et al. Living in a tinderbox: wildfire risk perceptions and mitigating behaviours
CA2984904C (en) Social media events detection and verification
US8990346B2 (en) System and method for location monitoring based on organized geofeeds
Lam et al. Improving social media use for disaster resilience: challenges and strategies
US20130297694A1 (en) Systems and methods for interactive presentation and analysis of social media content collection over social networks
US20130297581A1 (en) Systems and methods for customized filtering and analysis of social media content collected over social networks
US9563850B2 (en) Method and interface for displaying locations associated with annotations
CN106570144A (zh) 推荐信息的方法和装置
CN112738102B (zh) 资产识别方法、装置、设备和存储介质
US11531718B2 (en) Visualization of entity profiles
US7756739B2 (en) System and method for aggregating a measure over a non-additive account dimension
CN110135978A (zh) 用户金融风险评估方法、装置、电子设备和可读介质
CN111783107B (zh) 一种多源可信数据接入方法、装置及设备
Snyder et al. Situational awareness enhanced through social media analytics: A survey of first responders
Moanga et al. The space–time cube as an approach to quantifying future wildfires in California
CN111598714A (zh) 一种基于二阶段无监督的团伙识别方法、装置及电子设备
CN114648316B (zh) 基于稽查标签库的数字化处理方法及系统
Coulson et al. The accuracy of urban nesting gull censuses
TW201945960A (zh) 資訊處理裝置、控制方法及程式產品
CN113535038A (zh) 前端菜单树生成方法、装置、计算机设备及存储介质
CN108376155A (zh) 一种地理位置信息确定方法及装置
de Vicente et al. A new wildland fire danger index for a Mediterranean region and some validation aspects
CN118521398A (zh) 风险预测方法及装置、设备、存储介质和程序产品
CN113468437A (zh) 一种社群挖掘方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20846734

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20846734

Country of ref document: EP

Kind code of ref document: A1