Information processing device, information processing method, and program

Abstract

Provided are an information processing device, an information processing method, and a program which enable effective usage of search results by calculating the degree of reliability of the search results. In an information processing device (10) provided with a processor, the processor acquires a search query, acquires a first result of search carried out on a database on the basis of the search query, acquires meta information of the search query, acquires a second result of search carried out, on the basis of the search query, on the database filtered using the meta information, and calculates the degree of reliability of the first result of search on the basis of the second result of search.

Description

Information processing device, information processing method, and program

[0001] The present disclosure relates to an information processing device, an information processing method, and a program.

[0002] Traditionally, facility managers have outsourced inspection work to construction consultants, and inspectors with specialized knowledge inspect various structures (also called buildings, structures, structures, or infrastructure) such as bridges, roads, tunnels, dams, and buildings.

[0003] In Patent Document 1, first inspection results are obtained, second inspection results are searched for from a database based on image features contained in the first inspection results, specific inspection results corresponding to the building conditions are searched for from the searched second inspection results, and the specific inspection results are displayed preferentially on the display unit.

[0004] International Publication No. 2017 / 056804

[0005] In recent years, rising costs and labor shortages have led to a growing need for inspections by non-experts. However, the accuracy of search results obtained by executing a search query can be low, and the search results may contain results that are not relevant to the search target. This makes it difficult for non-experts to use the search results.

[0006] The present invention has been made in consideration of the above circumstances, and aims to provide an information processing device, an information processing method, and a program that enable effective use of search results by determining the reliability of the search results.

[0007] In an information processing device having a processor of the first aspect, the processor acquires a search query, acquires a first search result based on the search query from a database, acquires meta information of the search query, acquires a second search result based on the search query from a database filtered by the meta information, and calculates the reliability of the first search result based on the second search result.

[0008] In the information processing device of the second aspect, the processor obtains a second search result based on the search query from the database that has been filtered stepwise by the meta information.

[0009] In the information processing device of the third aspect, the processor calculates the similarity when determining the reliability.

[0010] In the information processing device of the fourth aspect, when determining the reliability, the processor calculates the similarity based on a method selected from the group consisting of cosine similarity, deviation pattern similarity, Jaccard coefficient, Dice coefficient, Simpson coefficient, Pearson's correlation coefficient, Spearman's correlation coefficient, Earth Mover's Distance, Euclidean distance, weighted Euclidean distance, Hamming distance, Mahalanobis distance, and Canberra distance.

[0011] In the information processing device of the fifth aspect, when calculating the reliability, the processor calculates statistical information for the first search result or the second search result based on the first search result or the second search result, and determines whether the statistical information is within a threshold range.

[0012] In the information processing device of the sixth aspect, the processor outputs the reliability.

[0013] In the information processing device of the seventh aspect, the processor feeds back the reliability to the acquisition of the first search result.

[0014] In the information processing device of the eighth aspect, the meta information includes information relating to the structure.

[0015] In the information processing device of the ninth aspect, the information about the structure in the meta information includes at least one selected from the group consisting of a damage image, specifications, damage information, repair information, surrounding area information, weather information, and statistical information.

[0016] In the information processing device of the tenth aspect, the search query includes information about a structure.

[0017] In the information processing device of the eleventh aspect, the information about the structure in the search query includes at least one selected from the group consisting of damage images, specifications, damage information, repair information, surrounding information, weather information, and statistical information.

[0018] An information processing method executed using a processor of a twelfth aspect, comprising: acquiring a search query; acquiring first search results based on the search query from a database; acquiring meta information for the search query; acquiring second search results based on the search query from a database filtered by the meta information; and determining the reliability of the first search results based on the second search results.

[0019] A program for executing an information processing method executed by a processor of the thirteenth aspect, which executes the following steps: acquiring a search query; acquiring first search results based on the search query from a database; acquiring meta information for the search query; acquiring second search results based on the search query from a database filtered by the meta information; and determining the reliability of the first search results based on the second search results.

[0020] According to the present invention, the reliability of the search results is calculated, so that the search results can be used effectively.

[0021] FIG. 1 is a schematic diagram of an information processing device. FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device. FIG. 3 is a block diagram showing processing functions implemented by a CPU. FIG. 4 is a diagram showing a database stored in a storage unit. FIG. 5 is a flow diagram showing an information processing method. FIG. 6 is a diagram for explaining an example of a display screen displaying a search query. FIG. 7 is a diagram for explaining an example of a display screen displaying first search results. FIG. 8 is a diagram for explaining an example of a display screen displaying meta information. FIG. 9 is a diagram for explaining an example of a display screen displaying second search results. FIG. 10 is a diagram for explaining an example of a method of calculating reliability. FIG. 11 is a diagram for explaining an example of a display screen displaying reliability. FIG. 12 is a flow diagram showing a first embodiment. FIG. 13 is a flow diagram showing a second embodiment.

[0022] Hereinafter, preferred embodiments of an information processing device, an information processing method, and a program according to the present invention will be described with reference to the accompanying drawings. In this specification, the term "structure" includes buildings, such as civil engineering structures, for example, bridges, tunnels, and dams, as well as buildings, houses, and architectural structures such as walls, pillars, and beams of buildings.

[0023] Fig. 1 is a schematic diagram of an information processing device 10. The information processing device 10 is connected to an operation unit 18 and a display device 30. As shown in Fig. 1, a user obtains the inspection results of a structure 1 via a camera 3 or a mobile terminal 5.

[0024] The mobile terminal 5 is preferably any of various mobile terminals having a photographing function and an information input function, such as a smartphone, a tablet terminal, and a portable personal computer.

[0025] The user inputs a search query based on the inspection results to the information processing device 10 via the operation unit 18. The information processing device 10 acquires the input search query. The information processing device 10 acquires the results of a first search performed on the database 40 based on the search query. The database 40 contains, for example, past inspection results for structures.

[0026] The information processing device 10 acquires meta information of the search query, and acquires the results of a second search based on the search query from the database 40 filtered by the meta information.

[0027] Next, the information processing device 10 calculates the reliability of the first search result based on the second search result, and further displays the first search result and the reliability on the display device 30.

[0028] This embodiment will be described in detail below.

[0029] [Hardware Configuration of Information Processing Apparatus] FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing apparatus according to the embodiment.

[0030] A computer or a workstation can be used as the information processing device 10 shown in Fig. 2. The information processing device 10 mainly includes an input / output interface 12, a storage unit 16, an operation unit 18, a CPU (Central Processing Unit) 20, a RAM (Random Access Memory) 22, a ROM (Read Only Memory) 24, and a display control unit 26. A display device 30 that constitutes a display is connected to the information processing device 10. Under the command of the CPU 20 and under the control of the display control unit 26, the display device 30 displays various information.

[0031] The input / output interface 12 can input various data (information) to the information processing device 10. For example, data to be stored in the storage unit 16 is input via the input / output interface 12.

[0032] The CPU (processor) 20 reads out various programs stored in the storage unit 16 or the ROM 24, etc., and loads them into the RAM 22 to perform calculations, thereby executing various processes of the information processing device 10.

[0033] FIG. 3 is a block diagram showing the processing functions realized by the CPU 20. As shown in FIG.

[0034] The CPU 20 mainly includes a search query acquisition unit 51, a first search result acquisition unit 52, a meta information acquisition unit 53, a filtering unit 54, a second search result acquisition unit 55, a reliability calculation unit 56, and an output unit 57, and executes the processing of each unit. The processing functions of each unit will be described later.

[0035] 2, the storage unit (memory) 16 is composed of non-transitory storage media such as a hard disk drive and various semiconductor memories, and its control unit. The storage unit 16 stores programs that operate the information processing device 10, such as an operating system and a program that executes an information processing method. The storage unit 16 also stores information used in the embodiments described below.

[0036] The operation unit 18 includes a keyboard and a mouse, and a user can use these devices to cause the information processing device 10 to perform necessary processing. By using a touch panel type device, the display device 30 can also serve as the operation unit 18.

[0037] The display device 30 is, for example, a device such as a liquid crystal display, and displays various information from the information processing device 10 .

[0038] 4 is a diagram illustrating a database 40 stored in the storage unit 16. In the embodiment, the database 40 includes inspection data 41, which is inspection results of structures acquired through past inspections.

[0039] 4, the inspection data 41 includes information about the structure, for example, at least one selected from the group consisting of "specifications," "damage information," "repair information," "surrounding area information," "weather information," "statistical information," and "damage image." The "specifications," "damage information," "repair information," "surrounding area information," "weather information," and "statistical information" are text data 42, and the "damage image" is image data 43. The inspection data 41 may further include text data such as "inspection date and time," "photograph date and time," and "repair date and time."

[0040] "Specifications" include at least one of the following: age, structural type, component name, or material. ・Examples of age include the number of years since completion or service start date. ・In the case of a bridge, examples of structural type include girder bridge, rigid frame bridge, truss bridge, arch bridge, cable-stayed bridge, or suspension bridge. ・In the case of a bridge, examples of component name include deck, pier, abutment, or girder. ・Examples of material include steel, reinforced concrete, or PC (Prestressed Concrete).

[0041] "Damage information" includes at least one of damage type, damage level, soundness, or countermeasure classification. ・Damage type can be exemplified by the type of damage that occurs in a structure, such as cracks, water leaks, corrosion, fractures, or peeling. ・Damage level is information that indicates the objective state of the damage for each type of damage, and is classified according to size, depth, and type, and displayed, for example, as a to d. ・The soundness index can be exemplified by an index that shows the diagnosis results on a four-level scale, I to IV, as described in the inspection guidelines established by the Ministry of Land, Infrastructure, Transport and Tourism. ・Countermeasure classification can be exemplified by the countermeasure classification as described in the inspection guidelines established by the Ministry of Land, Infrastructure, Transport and Tourism.

[0042] The "repair information" may be, for example, details of past repairs.

[0043] Examples of "surrounding area information" include traffic volume (per day, per month, per year, cumulative, etc.) or location (distance from the sea).

[0044] Examples of "weather information" include average temperature, average humidity, rainfall, and snowfall.

[0045] The "statistical information" may be, for example, a percentage by type of damage or by the size of damage.

[0046] 4 illustrates a case where the database 40 is stored in the storage unit 16. However, the database 40 may be stored in an external storage device as long as the information processing device 10 can access the database 40 via a wired or wireless network.

[0047] <Information Processing Method> Fig. 5 is a flow diagram showing an information processing method using the information processing device 10. As shown in Fig. 5, the information processing method, for example, includes a step of acquiring a search query (step S1), a step of acquiring first search results (step S2), a step of acquiring meta information of the search query (step S3), a step of filtering a database based on the meta information (step S4), a step of acquiring second search results (step S5), a step of calculating reliability of the first search results based on the second search results (step S6), and a step of outputting the reliability (step S7).

[0048] <Step of Acquiring a Search Query> In the step of acquiring a search query (step S1), the search query acquisition unit 51 acquires a search query. A user inputs the search query to the information processing device 10, for example, via the operation unit 18. In this case, the search query is created by the user based on the inspection results of the structure 1. Then, the search query acquisition unit 51 acquires the search query. As another method, the user may create the search query using the mobile terminal 5. As a further method, the search query may be automatically created from the inspection results. Here, the search query includes information for identifying a search target and is a type of processing request to the information processing device 10.

[0049] The search query may include, for example, text data and / or image data. When the target is the structure 1, the search query includes at least one selected from the group of "specifications," "damage information," "repair information," "surrounding area information," "weather information," "statistical information," and "damage image." "Specifications," "damage information," "repair information," "surrounding area information," "weather information," and "statistical information" are examples of text data, and "damage image" is an example of image data. The search query is not limited to the above-mentioned text data and / or image data.

[0050] It is preferable that the image data and text data included in the search query are of the same type as the image data 43 and text data 42 included in the inspection data 41 .

[0051] Fig. 6 shows an example of a display screen displaying a search query. The display screen 100 shown in Fig. 6 is displayed on the display device 30 under the control of the display control unit 26. The display screen 100 includes an input display screen 102 and a result display screen 104.

[0052] The input display screen 102 displays the search query Qu acquired by the search query acquisition unit 51, and also displays the words "search query" in the type area 106. If the search query Qu includes image data, the image data ID is displayed on the input display screen 102, allowing the user to confirm the image data ID. If the search query Qu includes text data, the text data TD is displayed on the input display screen 102, allowing the user to confirm the text data TD. The user can input the search query Qu (image data ID and / or text data TD) from the input display screen 102, and the input search query Qu is acquired by the search query acquisition unit 51.

[0053] 6, meta information, which will be described later, can be displayed or input. In the area for displaying or inputting meta information, the word "meta information" is displayed in the type area 107.

[0054] The input display screen 102 includes an execute button 108. When the execute button 108 is operated, the process proceeds to the next step. In Fig. 6, the process proceeds to step S2, where the first search result is acquired.

[0055] <Step of Obtaining First Search Results> In the step of obtaining the first search results (step S2), the first search result obtaining unit 52 obtains the first search results obtained from the database 40 based on the search query Qu. As shown in FIG. 7 , the first search result obtaining unit 52 obtains, for example, inspection data 41 obtained from the database 40 based on the search query Qu. The obtained inspection data 41 is an example of the first search results. In FIG. 7 , the search query Qu including text data TD and image data ID is displayed. The search query Qu may include at least one of the text data TD and the image data ID.

[0056] When the search query Qu includes an image data ID, the first search result acquisition unit 52 acquires image data 43 from the database 40 based on the image data ID. The first search result acquisition unit 52 calculates feature amounts of the image data ID and the image data 43 using an image recognition algorithm, a machine learning model, or the like. Next, the first search result acquisition unit 52 compares the feature amounts of the image data ID with the feature amounts of the image data 43, and acquires the image data 43 corresponding to the image data ID as a first search result performed based on the search query Qu.

[0057] When the search query Qu includes text data TD, the first search result acquisition unit 52 acquires text data 42 based on the text data TD from the database 40. The first search result acquisition unit 52 compares the text data TD with the text data 42 using a text search algorithm, a machine learning model, or the like, and acquires the text data 42 corresponding to the text data TD of the search query Qu as the first search result performed based on the search query Qu.

[0058] Furthermore, in this specification, "based on a search query" means that some processing is performed on the database 40 using information from the search query, and includes, for example, searching. Searching includes concepts such as "match," "similar," "dissimilar," and "rating" (for example, "closest order" or "farthest order").

[0059] 7, the first search result obtained by the first search result obtaining unit 52 is displayed on the result display screen 104 under the control of the display control unit 26. When the search query Qu is an image data ID, the image data 43 corresponding to the image data ID is displayed on the result display screen 104. In addition, the text data 42 associated with the image data 43 on the database 40 is also displayed.

[0060] When the search query Qu is text data TD, text data 42 corresponding to the text data TD is displayed on the result display screen 104. In addition, image data 43 associated with the text data 42 on the database 40 is also displayed.

[0061] 7 shows the image data ID and the text data TD as the search query Qu, but as described above, the search query Qu may include at least one of the image data ID and the text data TD. Furthermore, the first search result acquisition unit 52 may acquire the first search result based on a search query that combines the image data ID and the text data TD.

[0062] In addition, the first search result may be obtained by applying technologies such as those described in International Publication No. 2020 / 071216, International Publication No. 2020 / 255227, Japanese Patent Application Laid-Open No. 2018-165926, or Japanese Patent Application Laid-Open No. 2017-167987.

[0063] Next, the process flow proceeds to step S3, in which meta information of the search query Qu is acquired.

[0064] <Step of Acquiring Meta Information of Search Query> In the step of acquiring meta information of the search query Qu (step S3), the meta information acquisition unit 53 acquires the meta information of the search query Qu. Fig. 8 shows an example of a display screen 100 displaying meta information Me, and the acquired meta information Me is displayed on the input display screen 102. In Fig. 8, the first search result acquired in step S2 is displayed on the result display screen 104.

[0065] Like the search query Qu, the meta information Me can include text data TD and / or image data ID, and for example, includes at least one selected from the group of "specifications," "damage information," "repair information," "peripheral information," "weather information," "statistical information," and "damage image." "Specifications," "damage information," "repair information," "peripheral information," "weather information," and "statistical information" are examples of text data TD, and "damage image" is an example of an image data ID. The search query Qu and the meta information Me can include common types of image data ID and text data TD. However, the information included in the meta information Me is not limited. FIG. 8 shows meta information Me including text data TD and image data ID. However, the meta information Me may include either text data TD or image data ID.

[0066] Here, the meta information Me is not the search query Qu itself but information that is said to be related to the search query Qu.

[0067] Next, combinations of search queries Qu and meta information Me are shown. Table 1 shows examples of combinations of search queries Qu and meta information Me. When the target is a structure, the following combinations can be exemplified. No. 1 indicates that the search query Qu is image data (damage image), and the meta information Me is text data (specifications, damage information, repair information, statistical information, etc.). No. 2 indicates that the search query Qu is text data (specifications, damage information, repair information, statistical information, etc.), and the meta information Me is image data (damage image). No. 3 indicates that the search query Qu is image data (damage image), and the meta information Me is image data (damage image). In No. 3, when the search query Qu and the meta information Me each contain a damage image as image data, a damage image different from the search query Qu is applied as the damage image of the meta information Me. Examples of the damage image of the meta information Me include an image that is completely different from the search query Qu, a past image, a slightly edited image, an image taken remotely, etc.

[0068] Table 1 shows an example of a combination of a search query Qu and meta information Me, but is not limited to this.

[0069]

[0070] The meta information acquisition unit 53 can automatically acquire meta information Me of the search query Qu. For example, if the search query Qu is image data, the meta information acquisition unit 53 automatically acquires Exif (Exchangeable Image File Format) as the meta information Me. Exif is information attached to image data when it is captured, and includes information such as the circumstances and settings at the time of capture. Furthermore, if the image data of the search query Qu is captured in a GPS reception environment, the meta information Me may include location information, latitude and longitude, altitude, etc.

[0071] Furthermore, when the image data of the search query Qu is a "damage image," the meta information Me can be acquired using a machine-learned learning model. For example, based on the "damage image" of the search query Qu, the learning model can identify "damage information." The identified "damage information" is acquired as the meta information Me by the meta information acquisition unit 53.

[0072] The meta information Me can be manually input into the information processing device 10 by the user. FIG. 8 is an example of a display screen showing an example of input of meta information Me. The display screen 100 of FIG. 8 allows the user to check the acquired meta information Me and input the meta information Me. That is, the user can manually input image data ID and / or text data TD as the meta information Me into the input display screen 102 of the display screen 100. The input meta information Me is acquired by the meta information acquisition unit 53. FIG. 8 shows a case where the image data ID and text data TD are input as the meta information Me, and the image data ID and the text data TD are displayed. The user can input either the text data TD or the image data ID as the meta information Me.

[0073] When manually inputting meta information Me, the user associates the search query Qu with the meta information Me. For example, when inputting the meta information Me, the user displays the search query Qu on the input display screen 102 and performs a process of linking the meta information Me, thereby associating the search query Qu with the meta information Me. The user can associate the search query Qu with the meta information Me in any way.

[0074] Even when the meta information Me is acquired automatically, the input display screen 102 can display the meta information Me under the control of the display control unit 26, allowing the user to check the meta information Me.

[0075] When the execute button 108 on the input display screen 102 is operated, the process flow proceeds to step S4, which filters the database 40. Furthermore, following step S4, the process flow can proceed to step S5, which acquires second search results.

[0076] <Database Filtering Step> In the database filtering step (step S4), the filtering unit 54 executes filtering on the database 40 based on the meta-information Me.

[0077] The filtering unit 54 filters the database 40 based on the image data ID or text data TD included in the meta information Me. The filtering unit 54 compares the text data TD or image data ID of the meta information Me with the text data 42 or image data 43 of the database 40.

[0078] When the meta information Me is text data TD, the filtering unit 54 can filter the database 40 by, for example, extracting only the text data 42 that is the same as the text data TD of the meta information Me or other data.

[0079] Furthermore, the filtering unit 54 can filter the database 40 according to the analysis results of the meta information Me. For example, if the meta information Me is the damage type, the filtering unit 54 can calculate the proportion of the damage type as the analysis result, compare it with statistical information on the proportion of the damage type in the database 40, and filter the database 40. Furthermore, if the meta information is the magnitude of the damage type, the filtering unit 54 can calculate the proportion of the magnitude of the damage type as the analysis result, compare it with statistical information on the proportion of the magnitude of the damage type in the database 40, and filter the database 40. These filtering methods are examples of filtering.

[0080] Furthermore, the filtering unit 54 may filter the database 40 in stages. For example, if the meta information Me includes multiple types of text data TD, the filtering unit 54 may filter by "years since purchase" and then by "name of component." The staged filtering is not particularly limited.

[0081] As a result of filtering, the population of the database 40 may or may not be narrowed down.

[0082] The process flow proceeds to step S5 where a second search result is acquired.

[0083] <Step of Obtaining Second Search Results> In the step of obtaining second search results (step S5), the second search result obtaining unit 55 obtains second search results based on the search query from the filtered database 40. The second search result obtaining unit 55 obtains, for example, inspection data 41 obtained based on the search query from the filtered database 40.

[0084] The difference between the acquisition of second search results by the second search result acquisition unit 55 based on a search query and the acquisition of first search results by the first search result acquisition unit 52 based on a search query is that the second search result acquisition unit 55 targets the filtered database 40, whereas the first search result acquisition unit 52 targets the unfiltered database 40. Except for this point, the second search result acquisition unit 55 acquires the second search results using the same method as the first search result acquisition unit 52.

[0085] Fig. 9 shows an example of the case where the second search result is displayed on the result display screen 104. As shown in Fig. 9, the second search result obtained by the second search result acquisition unit 55 is displayed on the result display screen 104 under the control of the display control unit 26. Fig. 9 shows an example of the second search result in the present invention. For example, when the second search result shown in Fig. 9 is compared with the first search result shown in Fig. 7, the displayed results are different because the database 40 has been filtered.

[0086] Next, when the execute button 108 is operated, the process flow proceeds to step S6 for calculating the reliability, and the reliability calculation unit 56 calculates the reliability of the first search result.

[0087] 9 shows a case where the second search result is displayed on the display screen 100, but the second search result does not have to be displayed on the display screen 100. That is, the processing flow may proceed to step S6 of executing reliability processing for determining the reliability of the first search result after step S5 of obtaining the second search result.

[0088] <Step of determining reliability of first search result> In the step of determining reliability of the first search result (step S6), the reliability calculation unit 56 determines the reliability of the first search result based on the second search result. By determining the reliability of the first search result, it is possible to improve the accuracy of the first search result.

[0089] A preferred method for calculating the reliability will now be described. To calculate the reliability, the reliability calculation unit 56 determines the application conditions for the first search result and the second search result. The reliability calculation unit 56 can calculate the reliability from each of the application conditions.

[0090] For example, the reliability calculation unit 56 determines the indexes (so-called similarity rankings) of the database 40 for the first search result and the second search result as application conditions for calculating reliability. FIG. 10 is a diagram conceptually explaining the case where the index is the target. 10A in FIG. 10 shows an example of the first search result, in which four data items A, B, C, and D are acquired from the database 40 as the first search result. The four data items A to D are numerically indicated by their similarity rankings with respect to the search query. The smaller the number, the more similar the data items are to the search query. In other words, the first search result indicates that the results are most similar to the search query in the order of D, A, B, and C.

[0091] 10B shows an example of the second search result. In the second search result, two pieces of data A and D are obtained from the filtered database 40. The two pieces of data A and D are numerically ranked according to their similarity to the search query. That is, in the second search result, D is most similar to the search query, followed by A.

[0092] The reliability calculation unit 56 calculates the reliability of the first search result (including the index) based on the second search result (including the index). For example, in the example of Fig. 10, the order of D, A in the second search result matches the order of D, A in the first search result, and the reliability calculation unit 56 calculates that the reliability of the first search result is 100%.

[0093] From another perspective, the reliability calculation unit 56 can use the top N (N is a natural number) results of the first search result and the top N (N is a natural number) results of the second search result as application conditions. In this case, meta-information attached to the search results may also be included. The reliability calculation unit 56 can calculate the reliability of the first search result (including the top N results) based on the second search result (including the top N results).

[0094] The reliability calculation unit 56 may calculate similarity or distance in the process of calculating reliability. The reliability calculation unit 56 can calculate similarity or distance by applying a method selected from the group consisting of cosine similarity, deviation pattern similarity, Jaccard coefficient, Dice coefficient, Simpson coefficient, Pearson's correlation coefficient, Spearman's correlation coefficient, Earth Mover's Distance, Euclidean distance, weighted Euclidean distance, Hamming distance, Mahalanobis distance, and Canberra distance. The methods shown here are already known techniques, so their explanations are omitted.

[0095] Furthermore, when the first search result (including the top N results) is used as the application condition based on the second search result (including the top N results), the reliability calculation unit 56 can calculate statistical information for the first search result or the second search result based on the first search result or the second search result, determine whether the statistical information is within a threshold value, and calculate the reliability.

[0096] As statistical information, the reliability calculation unit 56 calculates the proportion of specific information included in the top N second search results that is also included in the top N first search results. The reliability calculation unit 56 determines whether the proportion is within a preset threshold, and can ultimately determine the reliability.

[0097] As statistical information, the reliability calculation unit 56 calculates the proportion of specific information included in the top N of the first search results that is also included in the top N of the second search results. The reliability calculation unit 56 determines whether or not this proportion is within a preset threshold, and can ultimately determine the reliability.

[0098] Once the reliability is calculated by the reliability calculation unit 56, the process flow proceeds to step S7 where the reliability is output.

[0099] <Step of outputting reliability> In the step of outputting the reliability (step S7), the output unit 57 outputs the reliability to the display device 30 via the display control unit 26. FIG. 11 is an example of a display screen on which the reliability is output. As shown in FIG. 11, the reliability is displayed in a column on the result display screen 104. In FIG. 11, the reliability and the first search results are simultaneously displayed on the display device 30. Because the reliability for the first search results is displayed, the user can refer to the reliability to determine whether or not the past inspection results can be used from the first search results.

[0100] Although the example has been given in which the output unit 57 displays the reliability on the display device 30, the output unit 57 can output the reliability to a printing device, or can output it as electronic data in various data formats.

[0101] When the output unit 57 outputs the reliability, the processing flow ends.

[0102] <Preferred Embodiment> A preferred embodiment will now be described.

[0103] First Embodiment In the first embodiment, the reliability is compared with a preset threshold X, and the processing flow is executed while changing the search query until the reliability satisfies the threshold X.

[0104] 11, the display screen 100 displays that the reliability is 80%. The user can determine that the reliability of the first search result is high. On the other hand, it is also possible that the reliability calculation unit 56 calculates the reliability of the first search result as 20%.

[0105] Therefore, the reliability calculation unit 56 determines whether the reliability is equal to or greater than a preset threshold value X, and can execute a processing flow according to the reliability.

[0106] Fig. 12 is a flow diagram of the first embodiment, in which step S6A of determining the reliability is added to the flow of Fig. 5. The differences from Fig. 5 will be mainly described.

[0107] As described above, the CPU 20 of the information processing device 10 executes steps S1 to S6. After the reliability calculation unit 56 calculates the reliability, the process proceeds to a determination step (step S6A). In step S6A, it is determined whether the reliability is equal to or greater than a preset threshold value X.

[0108] If it is determined that the reliability is less than the threshold X, i.e., if step S6A is "No", the process proceeds to the step of acquiring a search query (step S1). In this step of acquiring a search query (step S1), the search query whose reliability of the first search result is determined not to satisfy the threshold X is modified. The modified search query is acquired by the search query acquisition unit 51, and steps S1 to S6A are repeated until it is determined that the reliability is equal to or greater than the threshold X.

[0109] When the search query is image data, changing the search query may be, for example, changing the image data to image data taken from a different angle. The change of the search query may be performed automatically or manually. However, the change of the search query is not limited to this example.

[0110] If the reliability is determined to be equal to or greater than the threshold value X, i.e., if the answer is "Yes" in step S6A, the process proceeds to a step of outputting the reliability (step S7), and the processing flow ends when the output unit 57 outputs the reliability.

[0111] In the first embodiment, first search results with a reliability equal to or greater than the threshold X are output, so that the user can refer to the reliability and use past inspection results based on the first search results.

[0112] Second Embodiment In a second embodiment, the reliability result is fed back to the acquisition of the first search result, thereby improving the accuracy of the first search result.

[0113] 13 is a flow diagram of the second embodiment, showing a flow in which step S6B of feeding back the reliability result to the acquisition of the first search result is added. The differences from FIG. 5 will be mainly described.

[0114] As described above, the CPU 20 of the information processing device 10 executes steps S1 to S6. When the reliability calculation unit 56 calculates the reliability, the process proceeds to a step (step S6B) of feeding back the reliability result to the acquisition of the first search result.

[0115] When the first search result acquisition unit 52 uses a machine learning model, parameters of the machine learning model may be optimized by machine learning using the first search result and the second search result as training data. By using the optimized machine learning model, the accuracy of the first search result acquired by the first search result acquisition unit 52 is improved.

[0116] The method of feeding back the reliability result to obtain the first search result is not limited to the above method.

[0117] <Others> In the above embodiment, the hardware structure of the processing unit that executes various processes is the following various processors: The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and functions as various processing units, a programmable logic device (PLD), such as an FPGA (Field Programmable Gate Array), whose circuit configuration can be changed after manufacture, and a dedicated electrical circuit, such as an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing specific processes.

[0118] A single 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 (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, multiple processing units can be configured with a single processor. Examples of multiple processing units configured with a single processor include: a first configuration, as typified by client or server computers, in which a single processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units; a second configuration, as typified by system-on-chip (SoC), in which a processor is used to realize the functions of an entire system including multiple processing units on a single IC (Integrated Circuit) chip; and a hardware configuration, in which the various processing units are configured with one or more of the above-mentioned various processors.

[0119] Furthermore, the hardware structure of these various processors is, more specifically, an electric circuit made up of a combination of circuit elements such as semiconductor elements.

[0120] The above-described configurations and functions can be realized by any hardware, software, or a combination of both. For example, the present invention can be applied to a program that causes a computer to execute the above-described processing steps (processing procedures), a computer-readable storage medium (non-transitory storage medium) that stores such a program, or a computer on which such a program can be installed.

[0121] Although examples of the present invention have been described above, it goes without saying that the present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the present invention.

[0122] REFERENCE SIGNS LIST 1 Structure 3 Camera 5 Portable terminal 10 Information processing device 12 Input / output interface 16 Storage unit 18 Operation unit 20 CPU 22 RAM 24 ROM 26 Display control unit 30 Display device 40 Database 41 Inspection data 42 Text data 43 Image data 51 Search query acquisition unit 52 First search result acquisition unit 53 Meta information acquisition unit 54 Filtering unit 55 Second search result acquisition unit 56 Reliability calculation unit 57 Output unit 100 Display screen 102 Input display screen 104 Result display screen 106 Type area 107 Type area 108 Execute button ID Image data TD Text data Me Meta information Qu Search query

Claims

1. An information processing device having a processor, wherein the processor: acquires a search query; acquires first search results based on the search query from a database; acquires meta information of the search query; acquires second search results based on the search query from the database filtered by the meta information; and calculates the reliability of the first search results based on the second search results.

2. The information processing device according to claim 1, wherein the processor obtains the second search result based on the search query from the database that has been filtered stepwise by the meta information.

3. The information processing device according to claim 1 or 2, wherein the processor calculates a similarity when determining the reliability.

4. The information processing device according to claim 3, wherein when determining the reliability, the processor calculates the similarity based on a method selected from the group consisting of cosine similarity, deviation pattern similarity, Jaccard coefficient, Dice coefficient, Simpson coefficient, Pearson's correlation coefficient, Spearman's correlation coefficient, Earth Mover's Distance, Euclidean distance, weighted Euclidean distance, Hamming distance, Mahalanobis distance, and Canberra distance.

5. An information processing device according to claim 1 or 2, wherein when calculating the reliability, the processor calculates statistical information for the first search result or the second search result based on the first search result or the second search result, and determines whether the statistical information is within a threshold range.

6. The information processing device according to claim 1 or 2, wherein the processor outputs the reliability.

7. The information processing device according to claim 1 or 2, wherein the processor feeds back the reliability to the acquisition of the first search result.

8. The information processing device according to claim 1 or 2, wherein the meta information includes information about a structure.

9. The information processing device according to claim 8, wherein the information about the structure in the meta information includes at least one selected from the group consisting of damage images, specifications, damage information, repair information, surrounding area information, weather information, and statistical information.

10. The information processing device according to claim 1 or 2, wherein the search query includes information about a structure.

11. The information processing device according to claim 10, wherein the information about the structure in the search query includes at least one selected from the group consisting of damage images, specifications, damage information, repair information, surrounding information, weather information, and statistical information.

12. An information processing method executed by a processor, comprising: acquiring a search query; acquiring first search results based on the search query from a database; acquiring meta information for the search query; acquiring second search results based on the search query from the database filtered by the meta information; and determining the reliability of the first search results based on the second search results.

13. A program for executing an information processing method to be executed by a processor, the program causing the processor to perform the following steps: acquire a search query; acquire first search results based on the search query from a database; acquire meta information for the search query; acquire second search results based on the search query from the database filtered by the meta information; and calculate the reliability of the first search results based on the second search results.

14. A non-transitory computer-readable recording medium on which the program according to claim 13 is recorded.

Images