JUDGMENT RESULT ESTIMATION DEVICE, JUDGMENT RESULT ESTIMATION METHOD, AND PROGRAM
The determination result estimation device uses primary survey data and house characteristics to estimate secondary survey results, addressing delays and burdens in residential damage assessments by providing accurate probability values and images, thus reducing the need for on-site secondary surveys.
Patent Information
- Application Number
- JP2022550519
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2020-09-18
- Filing Date
- 2021-09-10
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2041-09-10
AI Technical Summary
Residential damage assessment surveys face delays and high burdens due to the need for secondary surveys, which often reverse primary survey results, and residents seek additional information leading to increased applications, affecting disaster victim certificate issuance.
A determination result estimation device and method that estimates secondary survey results based on primary survey data and house characteristics using a deep learning model, providing probability values and similar house images to reduce the need for on-site secondary surveys.
Enables accurate estimation of secondary survey results without conducting on-site secondary surveys, reducing delays and burdens on local governments and residents, while improving the accuracy of damage assessment.
Smart Images

Figure 0007577125000001 
Figure 0007577125000002 
Figure 0007577125000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a judgment result estimation device, a judgment result estimation method, and a program, and more particularly to a technique for judging the degree of damage to a house. [Background technology]
[0002] When a disaster occurs, the local government will carry out an investigation (residential damage certification investigation) to determine the extent of damage to affected houses in order to issue disaster certificates. Patent Document 1 describes a technology that can collect information required to certify the extent of damage to affected objects in disaster-stricken areas and send that information to unaffected locations. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2018-165906 A Summary of the Invention [Problem to be solved by the invention]
[0004] There are two types of residential damage assessment surveys: a primary survey, in which investigators determine the extent of damage based only on the exterior of the building, and a secondary survey, in which the interior conditions are also checked in the presence of residents to determine the extent of damage. If residents are not satisfied with the results of the primary residential damage assessment survey conducted by the local government, a secondary survey is conducted. However, secondary surveys take about twice as long as primary surveys, and conducting too many of them can lead to delays in the issuance of disaster certificates, placing a heavy burden on both local governments and residents. In addition, the results of the primary survey are overturned in about 30% of cases, depending on the type of disaster and the area.
[0005] On the other hand, from the residents' perspective, there is little information to judge the extent of damage to their homes, and the results of the assessment affect the amount of support money, so they often apply for a secondary survey. Therefore, the challenge is to provide residents with objective information about damage to their homes and reduce the number of cases that lead to applications for a secondary survey. However, Patent Document 1 does not state that the survey itself can be omitted and only the assessment results obtained.
[0006] The present invention has been made in consideration of the above circumstances, and aims to provide a judgment result estimation device, a judgment result estimation method, and a program for estimating the judgment results of a secondary survey without conducting a secondary survey on-site. [Means for solving the problem]
[0007] One aspect of a judgment result estimation device for achieving the above-mentioned object is a judgment result estimation device that includes a memory that stores instructions to be executed by a processor, and a processor that executes the instructions stored in the memory, wherein the processor acquires information about a house, acquires a judgment result of a primary survey of the house, extracts characteristic information of the house from the house information, estimates a judgment result of a secondary survey different from the primary survey of the house from the judgment result of the primary survey and the characteristic information of the house, and presents the estimated judgment result of the secondary survey.
[0008] According to this embodiment, the assessment result of the secondary survey is estimated from the assessment result of the primary survey and the characteristic information of the house, so that the assessment result of the secondary survey can be estimated without conducting a secondary survey on site.
[0009] The information on the house preferably includes at least one of latitude, longitude, age, material, area, and number of floors, which can improve the accuracy of the determination results of the second survey.
[0010] The processor preferably acquires address information of the house and acquires a result of a primary survey of the house based on the address information, thereby making it possible to appropriately acquire a result of a primary survey of the house.
[0011] The primary survey preferably includes at least one of the following: presence or absence of inclination, degree of damage to the eaves, degree of damage to the roof, degree of cracks in the walls, degree of peeling of the walls, and degree of curvature of the walls. This embodiment is suitable when such items are surveyed in the primary survey.
[0012] The result of the first investigation is preferably one of the following: total destruction, large-scale destruction, destruction, partial destruction, and no damage as the overall condition of the building. This embodiment is suitable for cases in which such a result is given in the first investigation.
[0013] The house characteristic information preferably includes house information coded as a numerical value and the determination result of the first survey coded as a numerical value, thereby improving the accuracy of the determination result of the second survey.
[0014] The processor preferably estimates the secondary inspection result of the house using a deep learning model trained on a secondary inspection house dataset in which the secondary inspection result is labeled with respect to the input feature information, thereby improving the accuracy of the secondary inspection result.
[0015] The processor preferably presents the probability value of each of the following as the judgment result of the secondary survey: total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage. This allows residents to recognize the probability value of each judgment result.
[0016] The processor preferably presents the result of the secondary survey and a countermeasure corresponding to the result with the highest probability value, thereby enabling residents to recognize the countermeasure.
[0017] The processor preferably presents images of houses previously determined to have suffered similar damage along with the results of the secondary survey, allowing residents to check images of houses previously determined to have suffered similar damage.
[0018] The processor preferably selects houses determined to have the same degree of damage from among houses with matching results of the first survey, houses with matching degrees of damage from the first survey, and houses made of matching materials. This allows appropriate selection of houses determined to have the same degree of damage.
[0019] It is preferable that the processor obtains additional information on the test items in the secondary survey and estimates the judgment result of the secondary survey from the additional information, thereby improving the accuracy of the judgment of the result of the secondary survey.
[0020] The additional information preferably includes the inclination of the columns, the damage rate of the foundation, and the damage rate of the interior walls. This embodiment is suitable when such items are surveyed in the second survey.
[0021] It is preferable that the second investigation is determined using the first information used in the determination of the first investigation and the second information different from the first information. This embodiment is suitable for such a second investigation.
[0022] One aspect of the judgment result estimation method for achieving the above-mentioned object is a judgment result estimation method comprising a house information acquisition process for acquiring information about the house, a primary survey result acquisition process for acquiring the judgment result of a primary survey of the house, an extraction process for extracting house characteristic information from the house information, an estimation process for estimating the judgment result of a secondary survey, which is different from the primary survey of the house, from the judgment result of the primary survey and the house characteristic information, and a presentation process for presenting the estimated judgment result of the secondary survey.
[0023] According to this embodiment, the assessment result of the secondary survey is estimated from the assessment result of the primary survey and the characteristic information of the house, so that the assessment result of the secondary survey can be estimated without conducting a secondary survey on site.
[0024] One aspect of a program for achieving the above object is a program for causing a computer to execute the above-mentioned determination result estimation method. This aspect may also include a computer-readable non-transitory storage medium on which the program is recorded.
[0025] According to this embodiment, the assessment result of the secondary survey is estimated from the assessment result of the primary survey and the characteristic information of the house, so that the assessment result of the secondary survey can be estimated without conducting a secondary survey on site. Effect of the Invention
[0026] According to the present invention, it is possible to estimate the judgment results of a secondary survey without conducting a secondary survey on-site. [Brief description of the drawings]
[0027] [Figure 1] FIG. 1 is a block diagram of a decision result estimation device. [Diagram 2] FIG. 2 is a functional block diagram of the decision result estimation device. [Diagram 3] FIG. 3 is a flowchart showing each step of the decision result estimation method. [Figure 4] FIG. 4 is an example of a screen displayed on the display. [Diagram 5] Figure 5 is an example of a screen displayed on a resident's smartphone. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0028] A preferred embodiment of the present invention will be described in detail below with reference to the attached drawings. Here, an example of estimating the result of an earthquake damage assessment survey of a house will be described. An earthquake damage assessment survey is carried out in two stages: a primary survey and a secondary survey. In the primary survey, assessment is made based on the appearance, the inclination, and the part. In addition, a secondary survey is carried out when an application is made by a resident of the house where the primary survey was carried out. In addition to the same survey as the primary survey, the secondary survey also assesses the interior of the house in the presence of the resident. In other words, the secondary survey is assessed using both the first information used in the assessment of the primary survey and the second information different from the first information.
[0029] [Configuration of the decision result estimation device] 1 is a block diagram of a decision result estimation device 10 according to this embodiment. The decision result estimation device 10 is realized by at least one computer. Here, an example in which a personal digital assistant is used as the computer will be described. As shown in FIG. 1, the decision result estimation device 10 includes a processor 12, a memory 14, a communication interface 16, an input interface 18, and a display 20.
[0030] The processor 12 executes instructions stored in the memory 14. The hardware structure of the processor 12 is various processors as shown below. The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and acts as various functional units, a GPU (Graphics Processing Unit), which is a processor specialized for image processing, a PLD (Programmable Logic Device), which is a processor whose circuit configuration can be changed after manufacture such as an FPGA (Field Programmable Gate Array), and a dedicated electric circuit, which is a processor having a circuit configuration designed specifically for executing specific processing such as an ASIC (Application Specific Integrated Circuit).
[0031] One processing unit may be configured with one of these various processors, or may be configured with two or more processors of the same or different types (for example, multiple FPGAs, or a combination of a CPU and an FPGA, or a combination of a CPU and a GPU). Also, multiple functional units may be configured with one processor. As an example of configuring multiple functional units with one processor, first, as represented by a computer such as a client or server, there is a form in which one processor is configured with a combination of one or more CPUs and software, and this processor acts as multiple functional units. Second, as represented by a SoC (System On Chip), there is a form in which a processor is used that realizes the functions of the entire system including multiple functional units with one IC (Integrated Circuit) chip. In this way, the various functional units are configured using one or more of the above various processors as a hardware structure.
[0032] Furthermore, the hardware structure of these various processors is, more specifically, an electric circuit that combines circuit elements such as semiconductor elements.
[0033] The memory 14 stores instructions to be executed by the processor 12. The memory 14 includes a RAM (Random Access Memory) and a ROM (Read Only Memory), not shown. The processor 12 uses the RAM as a working area, executes software using various programs and parameters, including a judgment result estimation program, stored in the ROM, and executes various processes of the judgment result estimation device 10 by using the parameters stored in the ROM, etc.
[0034] The communication interface 16 controls wired and wireless communications. The decision result estimation device 10 is connected to a communication network such as the Internet via the communication interface 16 so as to be able to transmit and receive data.
[0035] The input interface 18 is an input device that allows a user to input various information and desired instructions to the judgment result estimation device 10. The input interface 18 includes an input device such as a pointing device, such as a mouse, and an input device such as a keyboard.
[0036] The display 20 is a display device that allows a user to visually recognize information such as a judgment result. The display 20 displays a screen required for operations in the input interface 18, and functions as a part that realizes a GUI (Graphical User Interface). A touch panel display in which the input interface 18 and the display 20 are integrated may be applied.
[0037] Fig. 2 is a functional block diagram of the judgment result estimation device 10. As shown in Fig. 2, the judgment result estimation device 10 includes a house information acquisition unit 22, a primary investigation result acquisition unit 24, a primary investigation result storage unit 26, a house feature extraction unit 28, a similar house acquisition unit 30, a secondary investigation result acquisition unit 32, a secondary investigation result storage unit 34, a secondary investigation result estimation unit 36, and an estimation result display unit 38.
[0038] The functions of the house information acquisition unit 22, the primary survey result acquisition unit 24, the house feature extraction unit 28, the similar house acquisition unit 30, the secondary survey result acquisition unit 32, and the secondary survey result estimation unit 36 are realized by the processor 12. The functions of the primary survey result storage unit 26 and the secondary survey result storage unit 34 are realized by the memory 14. The functions of the primary survey result storage unit 26 and the secondary survey result storage unit 34 may be realized by a large-capacity storage device (not shown) communicatively connected to the judgment result estimation device 10. The function of the estimation result display unit 38 is realized by the display 20.
[0039] The house information acquisition unit 22 acquires information on the house for which the judgment result is to be estimated. The house information includes information on latitude, longitude, age, material, area, and number of floors. The house information is stored in a house information database consisting of the memory 14 or a large-capacity storage device (not shown).
[0040] The primary investigation result acquisition unit 24 acquires the results of the primary investigation of the house for which the judgment result is to be estimated from the primary investigation result storage unit 26. The primary investigation includes at least one item among the presence or absence of inclination, the degree of damage to the eaves, the degree of damage to the roof, the degree of cracks in the wall, the degree of peeling of the wall, and the degree of curvature of the wall. The primary investigation result acquisition unit 24 acquires the results of the primary investigation of the house from the primary investigation result storage unit 26 using the address information of the house as a search key. The results of the primary investigation are composed of scores for "presence or absence of inclination," "degree of damage to the eaves," "degree of damage to the roof," and "degree of cracks, peeling, and curvature of the wall." In addition, depending on the total score, one of the judgment results of "total destruction," "large-scale partial destruction," "partial destruction," "partial damage," and "no damage" is given as the condition of the entire building. The primary investigation result storage unit 26 stores the results of the primary investigation of multiple houses.
[0041] The house feature extraction unit 28 extracts house feature quantity data as house feature information from the house information acquired by the house information acquisition unit 22. The features include each attribute of the house information coded as a numerical value and each attribute of the results of the primary survey coded as a numerical value.
[0042] The similar house acquisition unit 30 acquires information on houses similar to the house for which the judgment result is estimated. The information on the houses similar to the house for which the judgment result is estimated is stored in the memory 14 or a large-capacity storage device (not shown). The houses similar to the house for which the judgment result is estimated may be houses with matching judgment results from a primary survey, houses with matching damage levels from a primary survey, or houses with matching materials.
[0043] The secondary survey result acquisition unit 32 acquires the results of the secondary survey of the house acquired by the similar house acquisition unit 30 from the secondary survey result storage unit 34. The secondary survey includes items of the primary survey and items different from the primary survey. The secondary survey result storage unit 34 stores the results of the secondary survey of multiple houses.
[0044] The secondary survey result estimation unit 36 includes a secondary survey result estimation model 36A. The secondary survey result estimation unit 36 inputs the house feature data extracted by the house feature extraction unit 28 to the secondary survey result estimation model 36A, and obtains an estimate of the secondary survey result as an output. Here, the estimate of the secondary survey result is a score of the class classification by the secondary survey result estimation model 36A, and is a probability value for each of "total destruction", "large scale partial destruction", "partial destruction", "partial damage", and "no damage".
[0045] The secondary survey result estimation model 36A is a known deep learning model. The deep learning model is trained in advance by a dataset of houses where a secondary survey has actually been conducted, in which the secondary survey results are labeled, in response to input of feature data including house information and the results of the primary survey (an example of a secondary surveyed house dataset).
[0046] The estimation result display unit 38 displays the estimated values of the results of the secondary survey estimated by the secondary survey result estimation unit 36.
[0047] [Determination result estimation method: First embodiment] 3 is a flowchart showing each step of a judgment result estimation method by the judgment result estimation device 10. The judgment result estimation method is realized by the processor 12 executing a judgment result estimation program stored in the memory 14. The judgment result estimation program may be provided by a computer-readable non-transitory storage medium. In this case, the judgment result estimation device 10 may read the judgment result estimation program from the non-transitory storage medium and store it in the memory 14.
[0048] Here, we explain an example of presenting an estimate of the results of a secondary survey in response to a secondary survey application from a resident. It is assumed that the primary housing damage certification survey has been completed by the local government, and the results of the primary survey have been stored in a database managed by the local government.
[0049] First, a resident A of a disaster-affected house visits a city hall to apply for a secondary residential damage certification survey (secondary survey) and tells the address of the house H1 to a person in charge. The person in charge inputs the address of the house H1 to the determination result estimation device 10 via the input interface 18.
[0050] In step S1 (an example of a house information acquisition process), the house information acquisition unit 22 acquires house information of the house H1 from the house information database using the input address information as a search key. The house information includes latitude and longitude, age, material, area, and number of floors.
[0051] In step S2 (an example of a primary survey result acquisition step), the primary survey result acquisition unit 24 acquires the results of the primary survey of the house H1 from the primary survey result storage unit 26 using the input address as a search key.
[0052] In step S3 (an example of an extraction step), the house feature extraction unit 28 extracts feature amount data of the house H1 from the house information acquired in step S1.
[0053] In step S4, the similar house acquisition unit 30 acquires information on houses similar to the house H1 based on the house information acquired in step S1. The similar house acquisition unit 30 searches for houses similar to the house H1 from houses that meet at least one of the following criteria: houses with a matching judgment result from the first investigation, houses with a matching degree of damage from the first investigation, and houses with a matching material. Here, the similar house acquisition unit 30 searches for houses similar to the house H1 from houses that meet all of the following criteria: houses with a matching judgment result from the first investigation, houses with a matching degree of damage from the first investigation, and houses with a matching material.
[0054] In step S5, the secondary survey result acquisition unit 32 acquires the results of the secondary survey of the house acquired in step S4 from the secondary survey result storage unit .
[0055] In step S6 (an example of an estimation process), the secondary survey result estimation unit 36 inputs the results of the primary survey of house H1 obtained in step S2 and the feature data of house H1 obtained in step S3 into the secondary survey result estimation model 36A, and obtains an estimate of the results of the secondary survey of house H1 as output.
[0056] In step S7 (an example of a presentation process), the estimation result display unit 38 displays the estimated value acquired in step S6 on the display 20. The similar house acquisition unit 30 also acquires images of houses previously determined to have the same level of damage as house H1. That is, from among the houses acquired in step S4, the similar house acquisition unit 30 acquires images of houses whose secondary survey results acquired in step S5 are similar to the secondary survey results estimated in step S6. The estimation result display unit 38 displays images of houses previously determined to have the same level of damage as house H1 acquired by the similar house acquisition unit 30 on the display 20.
[0057] Fig. 4 is an example of a screen displayed on the display 20 in step S7. As shown in Fig. 4, the display 20 displays a list T of estimated values resulting from the secondary survey of the house H1 and an image G1 of the house H1.
[0058] List T presents the probability values of each of the following as the judgment results of the secondary survey: total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage. Here, the probability value of total destruction is 0%, the probability value of large-scale partial destruction is 0%, the probability value of partial destruction is 5%, the probability value of partial damage is 94%, and the probability value of no damage is 1%. In this way, the judgment result estimation device 10 presents the probability value of each judgment result rather than finalizing the judgment result, so that resident A can have some discretion regarding the application for the secondary survey.
[0059] 4, images G2, G3, and G4 of houses that have been previously determined to have the same level of damage as house H1 are displayed on display 20. Here, house H1 has the highest probability of being partially damaged in list T, so the partially damaged house is selected as a house determined to have the same level of damage. In this way, images of houses determined to have the same level of damage as house H1 are displayed, which can increase resident A's sense of satisfaction with the determination result.
[0060] Second Embodiment In the second embodiment, an estimate of the results of the secondary survey is notified together with the results of the primary survey.
[0061] When notifying residents of the results of the primary investigation, the local government will attach the same information as the screen showing the results of the secondary investigation, as shown in Figure 4. In addition, the notification will present a response method according to the judgment result with the highest probability value.
[0062] Here, if the assessment result with the highest probability value is total destruction, large-scale partial destruction, or partial destruction, we suggest that you apply for a second on-site investigation. Also, if the assessment result with the highest probability value is partial damage, we suggest that you apply for a damage certificate using the self-assessment method. Furthermore, if the assessment result with the highest probability value is no damage, we suggest that no action is required.
[0063] In this way, by notifying Resident A of the results of the first survey along with instructions on how to respond to the application for the second survey, Resident A can use this as a reference for how to respond to the application for the second survey.
[0064] Third embodiment In a third embodiment, the results of the secondary survey are extrapolated including additional information from residents.
[0065] In the third embodiment, residents can obtain an estimate of the results of the secondary survey using their mobile terminal device such as their smartphone. At this time, residents input additional information related to the inspection items of the secondary survey along with the address of their house. The additional information is information on the condition of the interior of the house, including the inclination of the pillars, the damage rate of the foundation, and the damage rate of the interior walls.
[0066] Fig. 5 is an example of a screen displayed on the display 42 of the resident's smartphone 40. As shown in Fig. 5, the display 42 displays a text box B1 for inputting the inclination of the pillar [unit: cm], a text box B2 for inputting the foundation damage rate [unit: %], a text box B3 for inputting the interior wall damage rate [unit: %], and a confirm button B4.
[0067] The foundation damage rate and the interior wall damage rate are estimates per area. If the input contents are difficult for residents to understand, an explanation of how the values were calculated may be displayed. Residents can input desired values into text boxes B1, B2, and B3 using the input function of smartphone 40. Residents may omit inputting values for items for which they are unknown. After inputting values, residents can operate confirmation button B4 to transmit the inputted additional information together with the address of the house that has already been inputted from smartphone 40 to judgment result estimation device 10.
[0068] The judgment result estimation device 10 acquires the address of the house and additional information via the communication interface 16. The secondary investigation result estimation unit 36 inputs the additional information to the secondary investigation result estimation model 36A in addition to the feature amount data of the house. When there is additional information, the judgment result is estimated using the secondary investigation result estimation model 36A, which is a machine learning model trained by adding data corresponding to the additional information. When there is no additional information, the judgment result is estimated by the secondary investigation result estimation model 36A similar to the first embodiment.
[0069] The judgment result estimation device 10 transmits the judgment result of the secondary investigation to the smartphone 40 via the communication interface 16. The smartphone 40 displays on the display 42 a screen including a list of estimated values of the results of the secondary investigation similar to the screen shown in FIG.
[0070] In this way, by extrapolating the results of the secondary survey using additional information, the accuracy of the estimates can be improved.
[0071] 〔others〕 Here, the primary and secondary surveys for residential damage certification surveys have been explained as examples, but this is not limited to residential damage certification surveys and can be applied to cases where a secondary survey different from the primary survey is conducted after the primary survey.
[0072] The primary investigation may be conducted by a public institution, and the secondary investigation may be conducted by a private company. The primary investigation may be a residential damage certification investigation, and the secondary investigation may be a disaster insurance investigation. It is preferable that the secondary investigation is determined using the first information used in the determination of the primary investigation and second information different from the first information.
[0073] The technical scope of the present invention is not limited to the scope described in the above embodiments. The configurations and the like in each embodiment can be appropriately combined with each other without departing from the spirit of the present invention. [Explanation of symbols]
[0074] 10…Judgment result estimation device 12…Processor 14…Memory 16…Communication interface 18...Input interface 20…Display 22…House information acquisition department 24…First investigation results acquisition department 26…First investigation result storage section 28…House feature extraction section 30…Similar house acquisition department 32…Secondary Survey Results Acquisition Division 34…Secondary investigation result storage section 36…Secondary Survey Results and Estimation Section 36A…Secondary survey results estimation model 38…Estimation result display section 40. Smartphone 42…Display B1…Text box B2…Text box B3…Text box B4: Confirm button G1~G3…Images T…List S1 to S7: Each step of the judgment result estimation method
Claims
1. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the judgment result of the first investigation and the characteristic information of the house, a judgment result is estimated for a second investigation including investigation items different from those of the first investigation of the house; Present the estimated result of the secondary investigation; Judgment result estimation device.
2. The primary survey includes at least one of a judgment based on the appearance of the house, a judgment based on the inclination of the house, and a judgment based on a part of the house as a survey item, The second survey includes at least one of the same items as the first survey and a judgment of the interior of the house as survey items. The determination result estimation device according to claim 1 .
3. The information on the house includes at least one of latitude, longitude, age, material, area, and number of floors. The determination result estimation device according to claim 1 .
4. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the result of the primary survey and the characteristic information of the house, a result of a secondary survey different from the primary survey is estimated; A judgment result estimation device that presents the estimated judgment result of the secondary survey, The processor, Acquire address information of the house; obtaining a determination result of a first investigation of the house based on the address information; Judgment result estimation device.
5. The primary survey includes at least one of the following: presence or absence of inclination, degree of damage to the eaves, degree of damage to the roof, degree of cracks in the walls, degree of peeling of the walls, and degree of curvature of the walls; The determination result estimation device according to claim 1 .
6. The result of the primary investigation is to give the overall condition of the building one of the following: completely destroyed, partially destroyed, partially destroyed, partially damaged, or no damage. The determination result estimation device according to claim 1 .
7. The house characteristic information includes information about the house coded as a numerical value, and a result of the primary survey coded as a numerical value. The determination result estimation device according to claim 1 .
8. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the result of the primary survey and the characteristic information of the house, a result of a secondary survey different from the primary survey is estimated; A judgment result estimation device that presents the estimated judgment result of the secondary survey, The processor estimates a secondary inspection result of the house using a deep learning model trained on a secondary inspected house dataset in which the secondary inspection result is labeled for the input of the feature information. Judgment result estimation device.
9. The processor presents a probability value of each of total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage as a result of the determination of the secondary investigation. The determination result estimation device according to claim 1 .
10. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the result of the primary survey and the characteristic information of the house, a result of a secondary survey different from the primary survey is estimated; A judgment result estimation device that presents the estimated judgment result of the secondary survey, The processor presents a probability value of each of total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage as a result of the determination of the secondary investigation; The processor presents a response method according to the determination result having the highest probability value together with the determination result of the secondary investigation. Judgment result estimation device.
11. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the result of the primary survey and the characteristic information of the house, a result of a secondary survey different from the primary survey is estimated; A judgment result estimation device that presents the estimated judgment result of the secondary survey, The processor presents a probability value of each of total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage as a result of the determination of the secondary investigation; The processor presents images of houses previously determined to have suffered similar damage together with the results of the secondary investigation. Judgment result estimation device.
12. The processor selects the houses determined to have the same degree of damage from among houses having a matching determination result of the first survey, houses having a matching degree of damage in the first survey, and houses having a matching material. The determination result estimation device according to claim 11.
13. A memory that stores instructions to be executed by the processor; a processor for executing instructions stored in a memory; Equipped with The processor, Get information about the house, Obtaining a determination result of a primary investigation regarding the house; Extracting characteristic information of the house from the information of the house; From the result of the primary survey and the characteristic information of the house, a result of a secondary survey different from the primary survey is estimated; A judgment result estimation device that presents the estimated judgment result of the secondary survey, The processor, Obtain additional information related to the survey items of the secondary survey, A result of the second investigation is estimated from the result of the first investigation, the characteristic information of the house, and the additional information. Judgment result estimation device.
14. The additional information includes the inclination of the column, the damage rate of the foundation, and the damage rate of the interior wall; The determination result estimation device according to claim 13.
15. The second investigation is determined using first information used in the determination of the first investigation and second information different from the first information. The determination result estimation device according to claim 1 .
16. A computer functioning as a judgment result estimation device, A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; obtaining a result of extracting characteristic information of the house from the information of the house; A step of obtaining an estimate of a result of a secondary survey, which includes survey items different from those of the primary survey of the house, based on the result of the primary survey and characteristic information of the house; outputting the estimated result of the secondary investigation; A method for estimating a judgment result by executing the above.
17. The primary survey includes at least one of a judgment based on the appearance of the house, a judgment based on the inclination of the house, and a judgment based on a part of the house as a survey item, The second survey includes at least one of the same items as the first survey and a judgment of the interior of the house as survey items. The method for estimating a decision result according to claim 16.
18. A computer functioning as a judgment result estimation device, A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; obtaining a result of extracting characteristic information of the house from the information of the house; A process of obtaining an estimate of a result of a secondary survey of the house, which is different from the primary survey, based on the result of the primary survey and characteristic information of the house; a presentation step of outputting the estimated judgment result of the secondary survey; obtaining address information of the premises; Run The first investigation result acquisition step acquires a judgment result of a first investigation of the house based on the address information. Judgment result estimation method.
19. A computer functioning as a judgment result estimation device, comprising: A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; obtaining a result of extracting characteristic information of the house from the information of the house; A process of obtaining an estimate of a result of a secondary survey of the house, which is different from the primary survey, based on the result of the primary survey and characteristic information of the house; outputting the estimated result of the secondary investigation; Run The step of acquiring an estimated result of the judgment result of the secondary survey includes acquiring an estimated result of the judgment result of the secondary survey of the house using a deep learning model trained on a secondary surveyed house dataset in which the judgment result of the secondary survey is labeled with respect to the input of the feature information. Judgment result estimation method.
20. A computer functioning as a judgment result estimation device, comprising: A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; obtaining a result of extracting characteristic information of the house from the information of the house; A process of obtaining an estimate of a result of a secondary survey of the house, which is different from the primary survey, based on the result of the primary survey and characteristic information of the house; outputting a probability value of each of total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage as the estimated judgment result of the secondary investigation; outputting a response method corresponding to the determination result with the highest probability value together with the determination result of the secondary investigation; A method for estimating a judgment result by executing the above.
21. A computer functioning as a judgment result estimation device, comprising: A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; obtaining a result of extracting characteristic information of the house from the information of the house; A process of obtaining an estimate of a result of a secondary survey of the house, which is different from the primary survey, based on the result of the primary survey and characteristic information of the house; outputting a probability value of each of total destruction, large-scale partial destruction, partial destruction, partial damage, and no damage as the estimated judgment result of the secondary investigation; outputting images of houses previously determined to have suffered similar damage together with the results of the secondary survey; A method for estimating a judgment result by executing the above.
22. A computer functioning as a judgment result estimation device, comprising: A house information acquisition step of acquiring information about a house; A first investigation result acquisition step for acquiring a judgment result of a first investigation regarding the house; an extraction step of extracting characteristic information of the house from the information of the house; A process of obtaining an estimate of a result of a secondary survey of the house, which is different from the primary survey, based on the result of the primary survey and characteristic information of the house; obtaining additional information related to the survey items of the secondary survey; Run The step of acquiring an estimated result of the determination result of the secondary survey includes acquiring an estimated result of the determination result of the secondary survey from the determination result of the primary survey, the characteristic information of the house, and the additional information. Judgment result estimation method.
23. A program for causing a computer to execute the determination result estimation method according to any one of claims 16 to 22.
24. A non-transitory computer-readable recording medium having the program according to claim 23 recorded thereon.
Citation Information
Patent Citations
Earthquake disaster restoration support device, earthquake disaster restoration support system, earthquake disaster restoration support method and earthquake disaster restoration support program
JP2005208893A
Device for predicting, recording and comparing inspection data
JP2018113042A
Damage investigation system and method of application thereof
JP2018165906A
Disaster application support server and disaster application support system
JP2020052795A
Systems and methods for assessing damage to infrastructure assets
US20170337524A1
