Evaluation system and evaluation program

Abstract

To provide an evaluation system and an evaluation program that enable appropriate evaluation of an evaluation target space.SOLUTION: An evaluation system includes acquisition means for acquiring a captured image of an evaluation target space, and evaluation means for performing evaluation processing on the evaluation target space in the captured image based on the captured image acquired by the acquisition means and a trained evaluation model, with respect to a predetermined evaluation criterion. The evaluation means performs, as evaluation processing, processing relating to at least a first evaluation relating to determination of the evaluation target space satisfying the predetermined evaluation criterion, a second evaluation relating to determination of the evaluation target space not satisfying the predetermined evaluation criterion, a third evaluation relating to information being insufficient to perform determination regarding the predetermined evaluation criterion, and a fourth evaluation relating to the evaluation target space being not subject to the predetermined evaluation criterion.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an evaluation system and an evaluation program. [Background technology]

[0002] Conventionally, a technique for making a judgment regarding safety based on a captured image has been known (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-95391 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there has been a demand for a technique for appropriately evaluating a space to be evaluated.

[0005] The present invention has been made in view of the above circumstances, and has an object to provide an evaluation system and an evaluation program that are capable of appropriately evaluating a space to be evaluated. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the evaluation system described in claim 1 comprises an acquisition means for acquiring an evaluation target space image containing an evaluation target space, and an evaluation means for performing evaluation processing regarding predetermined evaluation criteria for the evaluation target space captured in the evaluation target space image based on the evaluation target space image acquired by the acquisition means and a first trained model, wherein the evaluation means performs, as the evaluation processing, at least processing regarding a first evaluation regarding determining that the evaluation target space satisfies the predetermined evaluation criteria, a second evaluation regarding determining that the evaluation target space does not satisfy the predetermined evaluation criteria, a third evaluation regarding insufficient information for making a judgment regarding the predetermined evaluation criteria, and a fourth evaluation regarding that the evaluation target space is not a judgment target for the predetermined evaluation criteria.

[0007] The evaluation system according to a second aspect of the present invention is the evaluation system according to the first aspect, wherein the evaluation means performs, as the evaluation process, a process of specifying the reliability of each of the first evaluation to the fourth evaluation.

[0008] The evaluation system described in claim 3 is the evaluation system described in claim 1, wherein the acquisition means further acquires evaluation target space related information regarding the evaluation target space, and the evaluation means performs the evaluation processing based on the first trained model, the evaluation target space related information acquired by the acquisition means, and the evaluation target space image.

[0009] The evaluation system described in claim 4 is the evaluation system described in claim 1, further comprising an output means for outputting information regarding the evaluation target space depicted in the evaluation target space image based on the result of the evaluation process by the evaluation means and a second trained model, wherein the second trained model is a model different from the first trained model.

[0010] The evaluation program described in claim 5 causes a computer to function as an acquisition means for acquiring an evaluation target space image containing an evaluation target space, and an evaluation means for performing evaluation processing regarding predetermined evaluation criteria with respect to the evaluation target space captured in the evaluation target space image based on the evaluation target space image acquired by the acquisition means and a first trained model, wherein the evaluation means performs, as the evaluation processing, processing regarding at least a first evaluation regarding a determination that the evaluation target space satisfies the predetermined evaluation criteria, a second evaluation regarding a determination that the evaluation target space does not satisfy the predetermined evaluation criteria, a third evaluation regarding a lack of information for making a determination regarding the predetermined evaluation criteria, and a fourth evaluation regarding a determination that the evaluation target space is not a target for judgment according to the predetermined evaluation criteria. [Effects of the Invention]

[0011] According to the evaluation system described in claim 1 and the evaluation program described in claim 5, by performing processing related to the first to fourth evaluations, for example, it is possible to perform a multifaceted evaluation, thereby making it possible to appropriately evaluate the space to be evaluated.

[0012] According to the evaluation system described in claim 2, by performing a process to identify the reliability of each of the first to fourth evaluations, for example, it is possible to grasp the reliability, thereby making it possible to appropriately evaluate the space to be evaluated.

[0013] According to the evaluation system described in claim 3, by performing evaluation processing based on the first trained model, the information related to the evaluation target space, and the evaluation target space image, it is possible to perform evaluation using, for example, useful information in the evaluation target space, thereby making it possible to appropriately evaluate the evaluation target space.

[0014] According to the evaluation system of claim 4, by outputting information about the evaluation target space, it becomes possible to allow the user to grasp information about the evaluation target space, for example. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram showing a functional concept of an information processing system according to an embodiment of the present invention; [Figure 2] FIG. 10 is a diagram illustrating an example of checklist information. [Figure 3] FIG. 10 is a diagram illustrating a captured image. [Figure 4] FIG. 10 is an explanatory diagram of the first to fourth evaluations. [Figure 5] 10 is a flowchart of a pointing out process. [Figure 6] 10 is a display example of each evaluation result display information. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, an embodiment of an evaluation system and an evaluation program according to the present invention will be described in detail with reference to the accompanying drawings. First, [I] the basic concept of the embodiment will be described, then [II] specific contents of the embodiment will be described, and finally, [III] modifications to the embodiment will be described. However, the present invention is not limited to the embodiment.

[0017] [I] Basic Concept of the Embodiment First, the basic concept of the embodiment will be described. The embodiment relates to an evaluation system and an evaluation program. The evaluation system according to the present invention is a system that performs processing related to various evaluations of a space to be evaluated.

[0018] "Space to be evaluated" is a concept that indicates the space that is the subject of evaluation, such as the space within a construction site, and as an example, the space inside and outside a building within a construction site. Furthermore, "space to be evaluated" may be interpreted as indicating, for example, the space outside the construction site, or any space unrelated to construction (for example, the space within a factory, a parking lot, or an apartment building).

[0019] In the following embodiment, the case will be described as an example in which the "evaluation target space" is a space within a building under construction at a construction site.

[0020] [II] Specific details of the embodiment Next, specific details of the embodiment will be described.

[0021] (composition) First, the configuration of the information processing system will be described. Fig. 1 is a block diagram showing the functional concept of the information processing system according to this embodiment. The information processing system 100 is a system including an evaluation system, and includes, for example, a terminal device 1 and a server device 2. Note that, although a plurality of terminal devices 1 are actually provided, this embodiment will be described focusing on the terminal device 1 in Fig. 1.

[0022] (Configuration - Terminal Device) 1 is a device used by a user (e.g., a user belonging to a prime contractor or a cooperating company), and is, for example, a tablet terminal. As a variation, the terminal device 1 may be another device such as a smartphone.

[0023] The terminal device 1 in FIG. 1 includes, for example, a communication unit 11, a touchpad 12, a display 13, an image capturing unit 14, a recording unit 15, and a control unit 16.

[0024] The communication unit 11 is a communication means for communicating with an external device (e.g., the server device 2). The touchpad 12 is an operation means for accepting various operation inputs from a user. The display 13 is an image display means for displaying various images, and for example, the touchpad 12 and the display 13 are integrally formed as a touch panel. The photographing unit 14 is a photographing means for taking still images or videos, and in this embodiment, for example, is configured using a camera for taking still images. The recording unit 15 is a recording means for recording programs and various data. The control unit 16 is a control means for controlling the terminal device 1, and is configured using, for example, internal memories such as a CPU, RAM, and ROM.

[0025] (Configuration - Server Device) The server device 2 in FIG. 1 is an evaluation system, and includes, for example, a communication unit 21, a recording unit 22, and a control unit 23.

[0026] (Configuration - Server Device - Communication Unit) The communication unit 21 in FIG. 1 is a communication means for communicating with an external device (for example, the terminal device 1, etc.).

[0027] (Configuration - Server Device - Recording Unit) 1 is a recording means for recording programs and various data required for the operation of the server device 2, and is configured using, for example, a flash memory as an external recording device. However, instead of or in addition to the flash memory, any other recording medium including a magnetic recording medium such as a hard disk or a magnetic disk, or an optical recording medium such as a DVD or a Blu-ray disc can be used (the same applies to the recording units of other devices).

[0028] The recording unit 22 stores, for example, checklist information.

[0029] Figure 2 is a diagram showing an example of checklist information. "Checklist information" is information that indicates evaluation criteria (predetermined evaluation criteria) for evaluating the evaluation target space. As shown in Figure 2, the checklist information is structured into, for example, major items, medium items, and minor items.

[0030] "Major items" indicate, for example, QCDSE (quality, cost, schedule (or construction period), safety, and environment), which are important elements in construction. "Medium items" indicate parts and measures, etc. "Small items" indicate the content of the evaluation criteria.

[0031] 2, for example, the evaluation criteria "Is there an opening?" and "Is the opening 1500 mm or higher?" are evaluation criteria related to "safety" and also evaluation criteria related to "openings." Although not specifically shown in FIG. 2, it is expected that there will be a large number of "minor items" (evaluation criteria) in this checklist information (for example, several hundred to several thousand, or more than one thousand, etc.).

[0032] The method for storing this checklist information is arbitrary, but for example, corresponding information may be generated based on predetermined laws and regulations, work experience, and other arbitrary circumstances, and then input into the server device 2 and stored.

[0033] (Configuration - Server Device - Control Unit) 2 is a control means for controlling the server device 2, and is specifically a computer including a CPU, various programs interpreted and executed on the CPU (including basic control programs such as an OS and application programs that are started on the OS and realize specific functions), and an internal memory such as a RAM for storing programs and various data (the same applies to control units of other devices). In particular, the program according to the embodiment is installed on the server device 2 via an arbitrary recording medium or a network, thereby substantially configuring each unit of the control unit 23 (the same applies to control units of other devices).

[0034] The control unit 23 conceptually includes, for example, an acquisition unit, an evaluation unit, and an output unit.

[0035] ===Acquisition method=== The "acquisition means" is a means for acquiring an evaluation target space image showing the evaluation target space.

[0036] ===Evaluation Method=== The "evaluation means" is a means for performing evaluation processing based on a predetermined evaluation criterion for the evaluation target space depicted in the evaluation target space image acquired by the acquisition means and the first trained model.

[0037] The evaluation means performs, as the evaluation process, for example, processes relating to at least the first evaluation, the second evaluation, the third evaluation, and the fourth evaluation. The evaluation means performs, as the evaluation process, for example, processes for determining the reliability of each of the first evaluation to the fourth evaluation.

[0038] ===Output Method=== The "output means" is a means for outputting information about the evaluation target space shown in the evaluation target space image based on the result of the evaluation process by the evaluation means and the second trained model.

[0039] ===Spatial image to be evaluated=== Fig. 3 is a diagram showing an example of a captured image. An "evaluation target space image" is an image showing the evaluation target space, such as the captured image of Fig. 3 showing the evaluation target space in a building under construction.

[0040] ===1st to 4th Rating=== Fig. 4 is an explanatory diagram of the first to fourth evaluations. In Fig. 4, the "Evaluation" and "Explanation" columns show examples of items related to the definition of each evaluation.

[0041] "First evaluation" is, for example, a concept indicating an evaluation regarding the judgment that the evaluation target space satisfies a specified evaluation criterion. "Second evaluation" is, for example, a concept indicating an evaluation regarding the judgment that the evaluation target space does not satisfy a specified evaluation criterion. "Third evaluation" is, for example, a concept indicating an evaluation regarding the lack of information to make a judgment regarding the specified evaluation criterion. "Fourth evaluation" is, for example, a concept indicating an evaluation regarding the evaluation target space not being subject to judgment according to the specified evaluation criterion.

[0042] In this embodiment, for example, the first to fourth evaluations will be described as being appropriately represented by the symbols "◯", "×", "△", and " / " as shown in the "Symbol" column in FIG.

[0043] Furthermore, the processing related to the first evaluation is a concept that includes, for example, a processing that makes a judgment corresponding to the first evaluation (a processing that "determines that the space to be evaluated satisfies a specified evaluation criterion"), or a processing that determines the reliability of the judgment.

[0044] "Reliability" is a concept that indicates the degree of reliability of the corresponding judgment, and in this embodiment, for example, a numerical value ranging from 0 to 1 is used, and a larger value indicates a higher degree of reliability.

[0045] The definitions of the process related to the second evaluation, the process related to the third evaluation, and the process related to the fourth evaluation are the same as the definition of the process related to the first evaluation.

[0046] In addition, in this embodiment, a case where processing is performed on four evaluations, the first evaluation to the fourth evaluation, will be described, but as a variation, for example, one or more evaluations different from these four evaluations may be added, so that processing is performed on five or more evaluations. Alternatively, any evaluation from the first evaluation to the fourth evaluation may be omitted, so that processing is performed on three or fewer evaluations.

[0047] (process) Next, the indication process executed by the information processing system 100 according to this embodiment will be described.

[0048] 5 is a flowchart of the indication process (hereinafter, each step will be referred to as "S"). The indication process is a process for evaluating the evaluation target space and outputting indications, and is a process executed by the server device 2, for example.

[0049] The timing of execution of this indication process is arbitrary, but for example, the process is started when the user performs a predetermined operation via the terminal device 1, and the description will begin from the point where the process is started.

[0050] Here, we will explain an example in which, for example, when a user patrols a building under construction, photographs the space to be evaluated with the photographing unit 14 of the terminal device 1, and then performs a predetermined operation, the terminal device 1 transmits the photographed image shown in Figure 3 (an image of the space to be evaluated showing the space to be evaluated) photographed by the photographing unit 14, and processing is initiated when the server device 2 receives the photographed image.

[0051] ===SA1=== 5, the control unit 23 acquires information. Specifically, the control unit 23 acquires the photographed image received when the indication process is started and the checklist information from the recording unit 22 (FIG. 1).

[0052] Here, for example, the photographed image in FIG. 3 and the checklist information in FIG. 2 are acquired.

[0053] ===SA2=== 5, the control unit 23 performs a process of evaluating the evaluation target space shown in the captured image based on the information acquired in SA1. Specifically, the process is arbitrary, but may be performed using, for example, a trained model for evaluation.

[0054] =Trained model for evaluation= A "trained model for evaluation" is a first trained model, specifically a model related to evaluation, for example, a machine-learned model generated by performing machine learning corresponding to an arbitrary learning method.

[0055] In this embodiment, for example, when a captured image and checklist information are input, the trained model for evaluation is configured to output information indicating the reliability of each of the first to fourth evaluations in Figure 4 as a result of making a judgment based on the input captured image regarding the contents of the evaluation criteria for all ``minor items'' included in the input checklist information.

[0056] This trained model for evaluation may be configured, for example, to be recorded in the recording unit 22 of the server device 2 and made available to the server device 2, or it may be configured to be recorded in an external device of the server device 2 (another server device (including so-called cloud)) and made available by the server device 2 communicating with the external device (the same applies to the "trained model for indication" described below).

[0057] The training method for the trained model for evaluation can also be arbitrary, and for example, a training method using a large amount of training data can be used (the same applies to the "trained model for criticism" described below). Note that the training data here may reflect the knowledge or experience of any subject, such as a veteran worker, foreman, or director on-site in the construction field, or may reflect various publicly available information (papers, testimonials, blog articles, etc.) (the same applies to the "trained model for criticism" described below).

[0058] In addition, the information output from the trained model for evaluation (information indicating the reliability of the judgments of each of the first to fourth evaluations) is the numerical information mentioned above (a numerical value between 0 and 1, with a larger value indicating a higher degree of reliability).

[0059] =Processing= Regarding the processing, the captured image and checklist information acquired in SA1 are input into the trained model for evaluation, and the reliability indicated by the information output from the trained model for evaluation is identified as the reliability of each evaluation.

[0060] Here, for example, when the captured image in Fig. 3 and the checklist information in Fig. 2 are input into the trained model for evaluation, the trained model for evaluation outputs information indicating the reliability of each of the first to fourth evaluations (i.e., the reliability of the four types of evaluations in Fig. 4) for "Is there an opening?" in Fig. 2, outputs information indicating the reliability of each of the first to fourth evaluations for "Is the opening 1500 mm or higher in height?" in Fig. 2, and outputs information indicating the reliability of each of the first to fourth evaluations for each evaluation criterion such as "Is a fall prevention net attached to the handrail?" in Fig. 4. The reliability indicated by this output information is then identified as the reliability of each evaluation for each corresponding evaluation criterion.

[0061] The processing results in SA2 (i.e., the reliability of each identified evaluation) may be displayed to the user. Specifically, they may be displayed as the following first to fourth evaluation result display information.

[0062] =Evaluation result display information= Fig. 6 shows an example of the display of each evaluation result display information. The first evaluation result display information 31 to the fourth evaluation result display information 34 are information indicating the reliability of each of the above-mentioned specified evaluations, and are information displayed for each evaluation criterion (such as "Is there an opening?" in Fig. 2).

[0063] The first evaluation result display information 31 indicates the reliability of the identified first evaluation, and includes a symbol corresponding to the first evaluation ("◯"), notification information for the user corresponding to the first evaluation ("YES" text information), and information representing a numerical value indicating the reliability (in FIG. 6, graph information in which a horizontal bar of a predetermined length is highlighted (hatched portion) for a length corresponding to a numerical value between 0 and 1). Note that the information representing the numerical value indicating the reliability may be any information other than graph information (for example, pie chart information, text information indicating a numerical value, etc.). The second evaluation result display information 32 to the fourth evaluation result display information 34 also have the same information representing the numerical value indicating the reliability, and therefore detailed description thereof will be omitted.

[0064] The second evaluation result display information 32 indicates the reliability of the second evaluation identified above, and includes a symbol ("X") corresponding to the second evaluation, notification information to the user corresponding to the second evaluation (text information of "NO"), and information representing a numerical value indicating the reliability.

[0065] The third evaluation result display information 33 indicates the reliability of the third evaluation identified above, and includes a symbol ("△") corresponding to the third evaluation, notification information for the user corresponding to the third evaluation (text information of "Caution required"), and information representing a numerical value indicating the reliability.

[0066] The fourth evaluation result display information 34 indicates the reliability of the aforementioned identified fourth evaluation, and includes a symbol (" / ") corresponding to the fourth evaluation, notification information to the user corresponding to the fourth evaluation (text information of "not applicable"), and information representing a numerical value indicating the reliability.

[0067] =Processing= In the process, based on the reliability of each evaluation identified above, information for displaying the first evaluation result display information 31 to the fourth evaluation result display information 34 for each evaluation criterion is transmitted to the terminal device 1, and displayed on the display 13. The display target is not limited to the terminal device 1, and may be any other terminal (for example, the screen of a personal computer installed in the management office, etc.).

[0068] Here, for example, four pieces of evaluation display information, namely, first evaluation result display information 31 to fourth evaluation result display information 34, are displayed for "Is there an opening?" in Figure 2, and four pieces of evaluation display information are displayed for "Is the opening 1500 mm or higher in height?" in Figure 2, and four pieces of evaluation display information are displayed for each of the evaluation criteria such as "Is a fall prevention net attached to the handrail?" in Figure 2.

[0069] ===SA3=== 5, the control unit 23 outputs a problem to be pointed out based on the processing result of SA2. Specifically, although it is optional, for example, the processing is performed using a trained model for suggestion.

[0070] =Points to note= "Points to be pointed out" are information about the space to be evaluated that is shown in the image of the space to be evaluated, and are, for example, points to be pointed out about the space to be evaluated. In this embodiment, "points to be pointed out" is a concept that includes, for example, points that any subject, such as a veteran worker, foreman, or director at a construction site, would normally point out about safety, quality, cost, process, environment, etc. (points that have been pointed out in the past).

[0071] =Trained model for pointing out= A "trained model for comments" is a second trained model, specifically, a model that is different from the trained model for evaluation described above, and is a model related to comments, for example, a machine-learned model generated by performing machine learning corresponding to an arbitrary learning method.

[0072] In this embodiment, for example, when information indicating the reliability of each evaluation for each evaluation criterion is input, the trained model for pointing out issues is configured to output information indicating points of concern derived from the reliability of each evaluation for each evaluation criterion indicated by the input information.

[0073] =Processing= In this process, information indicating the reliability of each evaluation for each evaluation criterion identified in SA2 is input to the trained model for remarks, the issues indicated by the information output from the trained model for remarks are identified, and the identified issues are displayed. Note that the display target is arbitrary, and for example, as in the case described above, it may be displayed on the terminal device 1, or it may be configured to be displayed on any other terminal. Furthermore, the output form of the information is not limited to display, and may be configured to be, for example, audio output (the same applies to the information indicating the reliability identified in SA2 described above).

[0074] Here, for example, suggested items such as "Install a single-pipe handrail" and "Commonize the ends" are output. Based on these suggested items, the user can take appropriate action regarding the photographed space to be evaluated.

[0075] (Effects of this embodiment) According to this embodiment, by performing the processes related to the first to fourth evaluations, for example, multifaceted evaluation can be performed, and therefore it becomes possible to appropriately evaluate the evaluation target space.

[0076] [III] Modifications to the embodiment Although the embodiments of the present invention have been described above, the specific configurations and means of the present invention can be modified and improved as desired within the scope of the technical ideas of the inventions set forth in the claims. Such modifications will be described below.

[0077] (About the problem to be solved and the effects of the invention) First, the problems that the invention aims to solve and the effects of the invention are not limited to those described above, and may vary depending on the implementation environment of the invention and the details of the configuration, and may solve only some of the problems described above or achieve only some of the effects described above.

[0078] (Regarding decentralization and integration) Furthermore, the electrical components described above are conceptual functional components and do not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distribution or integration of each part is not limited to that shown in the drawings, and all or part of them can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. For example, the configurations of the terminal device 1 and the server device 2 may be distributed or integrated. As an example, some of the functions of the terminal device 1 may be provided in the server device 2, or some of the functions of the server device 2 may be provided in the terminal device 1.

[0079] (shape, numbers, structure, time series) The components illustrated in the embodiments and drawings may be modified and improved as desired within the scope of the technical concept of the present invention in terms of shape, numerical value, or the structure or chronological relationship of multiple components.

[0080] (Regarding the spatial information to be evaluated) 1, the server device 2 may be configured to record evaluation target space related information in the recording unit 22, and to perform processing taking this information into consideration. For example, the aforementioned acquisition means may be configured to further acquire evaluation target space related information regarding the evaluation target space, and the aforementioned evaluation means may be configured to perform evaluation processing based on the first trained model, the evaluation target space related information acquired by the acquisition means, and the evaluation target space image.

[0081] ===Information related to the evaluation space=== "Information related to the space to be evaluated" refers to information related to the space to be evaluated, and may be interpreted as a concept including, for example, workplace work space information (examples include work information, space information, process information, space ID (ID that identifies the space), etc.), workplace building space information (examples include BIM information, design document information, construction drawing information, etc.), workplace environment information (examples include information indicating temperature, humidity, weather, road surface illuminance, brightness, noise, odor, unevenness, etc., information obtained from an acceleration sensor, and point cloud information), and information obtained from design documents and space ID (examples include information indicating the characteristics of the area, wind load, and ground strength, etc.). Specific examples of "information related to the space to be evaluated" are not limited to those listed above, and may be interpreted as including any information that meets the definition.

[0082] =Time element= For example, the information related to the space to be evaluated may store information indicating the time-based implementation plan of the process (e.g., information indicating a plan to implement process A from February 3rd to February 5th, process B from February 6th to February 7th, and process C from February 8th to February 9th).

[0083] Furthermore, when information indicating the date and time of the photographed image and information related to the space to be evaluated are additionally input as the trained model for evaluation, the model is configured to process using a model generated by learning using predetermined training data so that information indicating the reliability of the judgments of each of the first to fourth evaluations is output, taking into account the work process being carried out in the space to be evaluated that is captured on the date and time of the photograph and the processes preceding and succeeding that process.

[0084] 3, the terminal device 1 identifies the date and time of the image capture, and transmits information indicating the identified date and time of the image capture to the server device 2 together with the image capture.

[0085] Then, at SA1 in Figure 5, the control unit 23 receives and acquires, in addition to the captured image and checklist information, information indicating the date and time of capture transmitted from the terminal device 1, and also acquires information related to the evaluation target space from the recording unit 22 (not shown in Figure 1).

[0086] Next, at SA2 in Figure 5, the control unit 23 inputs the information acquired at SA1 (the captured image, checklist information, information indicating the date and time of shooting, and information related to the space to be evaluated) into the trained model for evaluation, and identifies the reliability indicated by the information output from the trained model for evaluation as the reliability of each evaluation.

[0087] By configuring in this way, it becomes possible to specify the reliability of each evaluation, for example, taking into consideration the time element related to the evaluation target space.

[0088] =Spatial elements= For example, the information related to the space to be evaluated stores information showing the spatial implementation plan of the process (for example, information showing a plan to carry out process A in the "A-2 work area" on the second floor and process B in the "A-3 work area" on the third floor (the work area directly above the "A-2 work area"). Note that the position of each work area, such as the "A-2 work area," can be identified by coordinates based on a specified coordinate system (such as a coordinate system consisting of longitude and latitude).

[0089] Furthermore, when information indicating the shooting position of the captured image (such as coordinate information based on the aforementioned specified coordinate system) and information related to the space to be evaluated are additionally input as the trained model for evaluation, the model is configured to process using a model generated by learning using specified training data so that information indicating the reliability of the judgments of each of the first to fourth evaluations is output, taking into account the process of the space to be evaluated that is shown in the image and the process of an adjacent construction section (such as the construction section directly above).

[0090] Furthermore, when the terminal device 1 captures the image of Figure 3, it is configured to identify the shooting location using a GPS system (not shown) or the like, and transmit information indicating the identified shooting location to the server device 2 together with the captured image.

[0091] Then, at SA1 in Figure 5, the control unit 23 receives and acquires, in addition to the captured image and checklist information, information indicating the shooting location transmitted from the terminal device 1, and also acquires information related to the evaluation target space from the recording unit 22 (not shown in Figure 1).

[0092] Next, at SA2 in Figure 5, the control unit 23 inputs the information acquired at SA1 (captured image, checklist information, information indicating the shooting location, and information related to the space to be evaluated) into the trained model for evaluation, and identifies the reliability indicated by the information output from the trained model for evaluation as the reliability of each evaluation.

[0093] By configuring in this way, it becomes possible to specify the reliability of each evaluation, for example, taking into consideration spatial factors related to the evaluation target space.

[0094] =Variations= Furthermore, the processing may be configured to take into consideration both the temporal and spatial elements. In this case, in addition to the captured image and checklist information, SA1 acquires information indicating the date and time of capture and information indicating the capture location, and SA2 inputs the information acquired in SA1 (the captured image, checklist information, information indicating the date and time of capture, information indicating the capture location, and information related to the space to be evaluated) into a trained model for evaluation, and the reliability indicated by the information output from the trained model for evaluation is identified as the reliability of each evaluation.

[0095] Furthermore, in the explanation of time elements, etc., information indicating a process was used as an example of the information related to the space to be evaluated, but this may be replaced with, for example, information indicating work, or with information indicating both a process and work.

[0096] Furthermore, the processing may be configured to take into consideration factors other than time and space (for example, the order in which the steps are performed).

[0097] (About the photographed images) Furthermore, the captured image may be an image captured by a device other than the terminal device 1. For example, a photographing function may be implemented in a mobile device such as a four-legged robot, a two-legged robot, or a drone, and an image captured by the device may be used as the captured image.

[0098] (Regarding the omission of some evaluations) Furthermore, in the above embodiment, the case where all of the first to fourth evaluations in FIG. 4 are performed has been described. However, this is not limiting and the following configuration may also be used. For example, with respect to each evaluation criterion shown in the "subitems" of FIG. 2, first, a process for determining the reliability of the fourth evaluation is performed. Next, if the numerical value indicating the reliability of the determined fourth evaluation is less than a predetermined threshold (if the reliability of the determination that the evaluation target space is not a judgment target of the predetermined evaluation criterion ("subitem") is relatively low, i.e., if the evaluation target space is likely to be a judgment target of the predetermined evaluation criterion), a process for determining the reliability of the first to third evaluations is performed. On the other hand, if the numerical value indicating the reliability of the determined fourth evaluation is equal to or greater than a predetermined threshold (if the reliability of the determination that the evaluation target space is not a judgment target of the predetermined evaluation criterion ("subitem") is relatively high, i.e., if the evaluation target space is likely to be a judgment target of the predetermined evaluation criterion), the process for determining the reliability of the first to third evaluations is not performed.

[0099] By configuring it in this way, for example, the process of determining the reliability of the first to third evaluations is performed only when there is a high possibility that the item is a diagnostic target, thereby making it possible to improve the overall processing speed.

[0100] Note that the specific realization method for performing the above-mentioned process is arbitrary, but for example, it may be realized using a predetermined machine-learned model, as in the case of SA2 in Fig. 5. In particular, it may be realized using two types of trained models: a trained model for first evaluation for performing the process of identifying the reliability of the fourth evaluation, and a trained model for second evaluation for performing the process of identifying the reliability of the first to third evaluations.

[0101] (Information about the evaluation space that is output) In the above embodiment, the output information about the evaluation target space is a recommendation, but this is not limiting. For example, the output information about the evaluation target space may be information such as suggestion information, guidance information, and warning information.

[0102] (About the photographed images) In addition, in the above embodiment, the captured image is a still image, but the captured image may be a moving image. In this case, each configuration of the above embodiment is partially modified to accommodate the moving image.

[0103] (About combinations) Furthermore, the features described in the embodiments or modifications may be combined in any manner. [Explanation of symbols]

[0104] 1. Terminal equipment 2. Server device 11 Communications Department 12 Touchpad 13. Display 14 Photography Department 15 Recording section 16 Control Unit 21 Communications Department 22 Recording section 23 Control Unit 31 First evaluation result display information 32 Second evaluation result display information 33 Third evaluation result display information 34 Fourth evaluation result display information 100 Information Processing Systems

Claims

1. an acquisition means for acquiring an evaluation target space image showing the evaluation target space; and an evaluation means for performing an evaluation process on the evaluation target space shown in the evaluation target space image based on the evaluation target space image acquired by the acquisition means and a first trained model, with respect to a predetermined evaluation criterion, The evaluation means includes at least a first evaluation relating to determining that the evaluation target space satisfies the predetermined evaluation criterion; a second evaluation relating to determining that the evaluation target space does not satisfy the predetermined evaluation criterion; a third evaluation regarding a lack of information to make a determination regarding the predetermined evaluation criteria; a fourth evaluation regarding the evaluation target space not being a judgment target of the predetermined evaluation criterion; and Rating system.

2. The evaluation means performing a process of specifying the reliability of each of the first evaluation to the fourth evaluation as the evaluation process; The evaluation system of claim 1 .

3. The acquisition means further acquires evaluation target space related information regarding the evaluation target space, The evaluation means performs the evaluation process based on the first trained model, the evaluation target space related information acquired by the acquisition means, and the evaluation target space image. The evaluation system of claim 1 .

4. Further provided is an output means for outputting information about the evaluation target space shown in the evaluation target space image based on a result of the evaluation process by the evaluation means and a second trained model, The second trained model is a model different from the first trained model. The evaluation system of claim 1 .

5. Computer, an acquisition means for acquiring an evaluation target space image showing the evaluation target space; and performing an evaluation process with respect to a predetermined evaluation criterion with respect to the evaluation target space shown in the evaluation target space image based on the evaluation target space image acquired by the acquisition means and a first trained model; The evaluation means includes at least a first evaluation relating to determining that the evaluation target space satisfies the predetermined evaluation criterion; a second evaluation relating to determining that the evaluation target space does not satisfy the predetermined evaluation criterion; a third evaluation regarding a lack of information to make a determination regarding the predetermined evaluation criteria; a fourth evaluation regarding the evaluation target space not being a judgment target of the predetermined evaluation criterion; and Evaluation program.

Images