Information processing apparatus, information processing method, and program

Abstract

To provide an information processor, an information processing method and a program for improving the efficiency of the whole tree diagnostic task while accurately acquiring data related with tree diagnosis at a job site.SOLUTION: The information processing apparatus 10 includes a reception unit 113 that receives diagnosis data including a plurality of pieces of image data and a plurality of pieces of sound data related to a tree to be diagnosed from the worker terminal 30 and registers the diagnosis data in a storage unit, a provision unit 110 that provides the diagnosis data to the diagnoser terminal 40, an acquisition unit 114 that acquires a diagnosis result regarding the soundness of the tree from the diagnoser terminal 40, and an output unit 115 that outputs the diagnosis result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] In recent years, trees planted during postwar urban development have grown taller and older, and the occurrence of tree-falling accidents due to natural disasters such as typhoons has become a problem. Traditionally, tree diagnosis has been carried out by tree doctors and other tree diagnosis experts to determine the risk of trees, such as roadside trees, falling. However, the number of tree doctors is limited compared to the vast number of trees, making it difficult to carry out the necessary tree diagnosis.

[0003] In the field of tree diagnosis, for example, a system has been proposed to diagnose roadside trees that require caution. Patent Document 1 discloses a method of diagnosing whether or not there are trees that require caution, based on a vegetation index calculated using a video captured by a near-infrared camera mounted on a vehicle. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-108582 Summary of the Invention [Problem to be solved by the invention]

[0005] The warning tree diagnosis system described in Patent Document 1 can efficiently find warning trees among the vegetation along roadsides such as highways without relying on human eyes, but it was not possible to improve the efficiency of tree diagnosis work while maintaining the accuracy of information collected on-site, as has been done in the past.

[0006] Therefore, an object of the present invention is to provide an information processing device, an information processing method, and a program that can improve the efficiency of the entire tree diagnosis process while accurately acquiring data related to tree diagnosis on-site. [Means for solving the problem]

[0007] According to one aspect of the present disclosure, an information processing device communicatively connected to an operator terminal and a diagnostician terminal includes a receiving unit that receives diagnostic data including multiple image data and multiple audio data related to the tree to be diagnosed from the operator terminal and registers the data in a memory unit, a providing unit that provides the diagnostic data to the diagnostician terminal, an acquiring unit that acquires diagnostic results regarding the health of the tree from the diagnostician terminal, and an output unit that outputs the diagnostic results.

[0008] According to this aspect, the information processing device acquires diagnostic data necessary for diagnosis from the worker terminal and provides the acquired diagnostic data to the diagnoser terminal, thereby improving the efficiency of tree diagnosis work. By leaving the acquisition of diagnostic data to the worker, the work of the diagnoser can be reduced, and the efficiency of the entire tree diagnosis work can be improved.

[0009] The information processing device may further include a request unit that requests a diagnosis from a diagnostician terminal in response to registration of diagnostic data. According to this aspect, the diagnostic data can be provided to an appropriate diagnostician in a timely manner.

[0010] The information processing device may further include an ordering unit that receives an order request including the identification information of the tree, the identification information of the worker, and the identification information of the diagnostician from the manager terminal and registers the order request in the storage unit, and the ordering unit requests work from the worker terminal based on the identification information of the worker. According to this aspect, the information processing device can provide work information to the appropriate worker in a timely manner.

[0011] The information processing device may further include a transmitting unit that transmits image information and / or audio information recommended for performing an appropriate tree diagnosis according to the type of tree to the worker terminal. According to this aspect, the information processing device can support a worker who is not an arborist in obtaining appropriate diagnostic data.

[0012] In the information processing device, the output unit may further output a diagnosis result map including a visual display showing the corresponding diagnosis result at the position of each tree on the map. According to this aspect, the information processing device can assist in determining the risk of tree falling or the like based on the condition of not only a specific tree but also multiple trees included in the map, and in formulating future tree diagnosis plans.

[0013] A method according to another aspect of the present disclosure includes an information processing device communicatively connected to an operator terminal and a diagnostician terminal receiving diagnostic data from the operator terminal, the diagnostic data including multiple image data and multiple audio data related to the tree to be diagnosed, and registering the diagnostic data in a memory unit; providing the diagnostic data to the diagnostician terminal; obtaining a diagnostic result regarding the health of the tree from the diagnostician terminal; and outputting the diagnostic result.

[0014] A program according to another aspect of the present disclosure causes an information processing device communicatively connected to an operator terminal and a diagnosing terminal to perform the following processes: receive diagnostic data including multiple image data and multiple audio data related to the tree to be diagnosed from the operator terminal and register the data in a memory unit; provide the diagnostic data to the diagnosing terminal; obtain a diagnostic result regarding the health of the tree from the diagnosing terminal; and output the diagnostic result.

[0015] According to another aspect of the present disclosure, an information processing device communicatively connected to a worker terminal includes a receiving unit that receives diagnostic data from the worker terminal, the diagnostic data including multiple image data and multiple audio data related to a tree to be diagnosed, and registers the data in a memory unit; a diagnosing unit that infers which of multiple diagnostic levels indicating the health of the tree the tree belongs to based on the diagnostic data; and an output unit that outputs the inference result of the diagnosing unit.

[0016] According to this aspect, the information processing device acquires diagnostic data necessary for diagnosis from the operator terminal, and infers which of a plurality of diagnostic levels indicating the health of the tree the tree belongs to based on the acquired diagnostic data, thereby improving the efficiency of tree diagnosis work. By entrusting part of the tree diagnosis to the diagnosis department, the work of the diagnoser can be reduced, and the efficiency of the entire tree diagnosis work can be improved.

[0017] In the information processing device, the diagnosis unit infers the health of a tree by inputting a plurality of image data and a plurality of audio data into a trained model, and the trained model may be a trained model trained to estimate the health of a tree from a plurality of image data of the tree and a plurality of audio data including sounds of tapping on the tree. According to this aspect, the information processing device can obtain an inference result with a desired accuracy.

[0018] A method according to another aspect of the present disclosure includes an information processing device communicatively connected to a worker terminal receiving diagnostic data from the worker terminal, the diagnostic data including multiple image data and multiple audio data related to a tree to be diagnosed, and registering the data in a memory unit; inferring, based on the diagnostic data, which diagnostic level the tree belongs to among multiple diagnostic levels indicating the health of the tree; and outputting the inferred result.

[0019] A program according to another aspect of the present disclosure causes an information processing device communicatively connected to a worker terminal to perform the following processes: receive diagnostic data from the worker terminal, including multiple image data and multiple audio data related to the tree to be diagnosed, and register the data in a memory unit; infer, based on the diagnostic data, which of multiple diagnostic levels indicating the health of the tree the tree belongs to; and output the inferred results.

[0020] In another aspect of the present disclosure, a terminal device communicatively connected to a server device includes an imaging unit that captures an image of a tree to be diagnosed and generates image data of the captured image, an audio input unit that inputs audio data including the sound of tapping on the tree, a display control unit that displays a screen on which multiple image data generated by the imaging unit and multiple audio data input by the audio input unit can be specified, and a transmission unit that transmits the multiple image data and multiple audio data specified on the screen to the server device.

[0021] A program according to another aspect of the present disclosure causes a terminal device communicatively connected to a server device to perform the following processes: capturing an image of a tree to be diagnosed, generating image data of the captured image, inputting audio data including the sound of hitting the tree, displaying a screen on which multiple image data and multiple audio data can be specified, and transmitting the multiple image data and multiple audio data specified on the screen to the server device. [Effects of the Invention]

[0022] According to the present invention, it is possible to provide an information processing device, an information processing method, and a program that can improve the efficiency of the entire tree diagnosis process while accurately acquiring data related to tree diagnosis on-site. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram illustrating an example of the configuration of a tree diagnosis system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating an example of a configuration of a server device according to an embodiment of the present invention. [Figure 3] FIG. 2 is a diagram illustrating an example of the configuration of a worker terminal according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of a server device according to an embodiment of the present invention. [Figure 5] FIG. 2 is a diagram illustrating an example of a hardware configuration of an administrator terminal according to an embodiment of the present invention. [Figure 6]FIG. 2 is a diagram illustrating an example of a hardware configuration of a worker terminal according to an embodiment of the present invention. [Figure 7] FIG. 2 is a diagram illustrating an example of a hardware configuration of a diagnostician terminal according to an embodiment of the present invention. [Figure 8] FIG. 2 is a diagram illustrating an example of a diagnostic database according to an embodiment of the present invention. [Figure 9] 10 is a flowchart illustrating a process of a server device according to an embodiment of the present invention. [Figure 10] 10 is a flowchart illustrating processing of a server device and an operator terminal according to an embodiment of the present invention. [Figure 11] 10 is a flowchart illustrating a process of a server device according to an embodiment of the present invention. [Figure 12] 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present invention. [Figure 13] FIG. 1 is a diagram illustrating an example of the configuration of a learning device according to an embodiment of the present invention. [Figure 14] FIG. 2 is a diagram illustrating an example of a configuration of a server device according to an embodiment of the present invention. [Figure 15] 10 is a flowchart illustrating the processing of a learning device according to an embodiment of the present invention. [Figure 16] 10 is a flowchart illustrating a process of a server device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] Embodiments of the present invention will be described with reference to the accompanying drawings. Note that the following embodiments are intended to facilitate understanding of the present invention and are not intended to limit the present invention. Furthermore, the present invention can be modified in various ways without departing from the gist of the present invention. Furthermore, those skilled in the art can adopt embodiments in which the elements described below are replaced with equivalents, and such embodiments are also included in the scope of the present invention.

[0025] First Embodiment [System Configuration] First, an overview of the present invention will be described using Fig. 1. Fig. 1 is a diagram illustrating the configuration of a tree diagnostic system according to one embodiment of the present invention. The tree diagnostic system 1 includes a server device 10, which is configured to communicate with an administrator terminal 20, an operator terminal 30, and a diagnoser terminal 40 via a network N.

[0026] Tree diagnosis system 1 is a system that enables efficient tree diagnosis without requiring an arborist, an expert in tree diagnosis, to travel to the site. An administrator of tree diagnosis system 1 can connect to server device 10 via administrator terminal 20 to save and view various data required for tree diagnosis. Specifically, the administrator can use administrator terminal 20 to determine which trees to diagnose and request a local worker to diagnose the trees. One example of the administrator is a management employee of a local government that has jurisdiction over street trees. The local worker is a user who uses worker terminal 30 to acquire diagnostic data related to trees on-site, and one example is a worker from a landscaping company or a local government employee that has been commissioned by the local government to manage street trees.

[0027] The worker terminal 30 is a terminal used by a field worker, and may be, for example, a tablet terminal or a smartphone. The field worker connects to the server device 10 via the worker terminal 30 to obtain basic data on the tree to be diagnosed and to register diagnostic data obtained on-site. In this embodiment, the diagnostic data includes image data and percussion sound data of the tree. The image data may be a still image or a moving image.

[0028] Once the diagnostic data is registered, the server device 10 transmits a request for tree diagnosis to the diagnoser terminal 40. The diagnoser terminal 40 is a terminal used by an arborist, and may be, for example, a PC (personal computer). The arborist can connect to the server device 10 via the diagnoser terminal 40, obtain basic data and diagnostic data for the tree to be diagnosed, and register the diagnosis results.

[0029] After the diagnostic results are registered, the administrator can connect to the server device 10 via the administrator terminal 20 and view the diagnostic results.

[0030] [Function Configuration] (Server device) Next, an example of the configuration of the server device 10 will be described with reference to Fig. 2. Note that Fig. 2 assumes a single server device 10 and shows only the necessary functional configuration, but the server device 10 can also be configured as part of a multi-functional distributed system consisting of multiple computer systems. The server device 10 can be, for example, a server device installed in a local government.

[0031] The server device 10 has, as functional components, for example, a site providing unit 110, an ordering unit 111, a screen transmission unit 112, a diagnostic data receiving unit 113, a diagnostic result acquisition unit 114, a diagnostic request unit 1141, a diagnostic result receiving unit 1142, an output unit 115, an email transmission unit 116, and a memory unit 100. The memory unit 100 stores, for example, a road tree database 101, an administrator database 102, a worker database 103, a diagnostician database 104, a map database 105, and a diagnostic database 106. Each functional component is described below.

[0032] The roadside tree database 101 stores basic information about roadside trees. In one embodiment, the roadside tree database 101 preferably includes a tree ID, tree name, type, planting date, location, etc. The tree ID is information for uniquely identifying a tree. The tree name, type, planting date, and location store various data about the tree.

[0033] The administrator database 102 stores information about administrators who use the tree diagnosis service site provided by the server device 10. In one embodiment, the administrator database 102 preferably includes an administrator ID, an administrator name, an email address, etc. The administrator ID is information for uniquely identifying a user of the tree diagnosis service site.

[0034] The worker database 103 stores information about local workers who use a tree diagnosis service application for workers (hereinafter also referred to as the "tree diagnosis service app for workers") provided by the server device 10. In one embodiment, the worker database 103 preferably includes a worker ID, a worker name, an email address, and the like. The worker ID and worker name may store the ID and name of a landscaping company, or the ID and name of a local government employee. The worker ID is information for uniquely identifying a user of the tree diagnosis service app for workers.

[0035] The diagnoser database 104 stores information about diagnosers who use the tree diagnosis service site provided by the server device 10. In one embodiment, the diagnoser database 104 preferably includes a diagnoser ID, a diagnoser name, an email address, etc. The diagnoser ID is information for uniquely identifying a user of the tree diagnosis service site.

[0036] Map information is stored in the map database 105. Note that the map information may be acquired from an external service such as a map API (Application Programming Interface).

[0037] The diagnostic database 106 stores information related to tree diagnoses. In one embodiment, as shown in FIG. 8, the diagnostic database 106 preferably includes a diagnosis ID, administrator ID, tree ID, work date, worker ID, diagnosis date, diagnoser ID, image data, audio data, overall diagnosis, item diagnosis, status, etc. In this embodiment, a record is registered for each tree ID of a specific diagnosis ID in association with the diagnosis ID and tree ID. The diagnostic ID is information for uniquely identifying a tree diagnosis. The work date is information indicating the scheduled date on which the worker will acquire diagnostic data or the date on which the worker acquired diagnostic data. The diagnosis date is information indicating the date on which the diagnoser registered the diagnostic results.

[0038] In this embodiment, the diagnostic database 106 stores a plurality of image data 1-4 and a plurality of audio data 1-4. In one embodiment, image data 1, 2, 3, and 4 store image data of a base image, a trunk image, a leaf image, and an entire image, respectively. Additionally, audio data 1, 2, 3, and 4 store audio data of a base percussion sound 1, a base percussion sound 2, a trunk percussion sound 1, and a trunk percussion sound 2, respectively. The specific examples of image data and audio data are merely examples, and image data and audio data can be stored for any other part, and any number of image data and audio data can be stored.

[0039] The comprehensive diagnosis is information indicating the results of a comprehensive diagnosis of the tree. In one example, the comprehensive diagnosis stores information indicating any of "1: No abnormalities," "2: Observation required," "3: Treatment required," and "4: Removal required." The specific example of the comprehensive diagnosis is just an example, and any information selected from any number of options may be stored. In this embodiment, the diagnosis database 106 stores item diagnoses 1 to 2. In one embodiment, item diagnoses 1 and 2 store information indicating the presence or absence of pests and information indicating the presence or absence of mushrooms, respectively. The specific example of the item diagnosis is just an example, and item diagnoses can be stored for any other item, and any number of item diagnoses can be stored. The status is information indicating the progress of the tree diagnosis. In one example, the status stores information indicating any of "1: Ordered," "2: Work completed," "3: Diagnosed," and "4: Confirmed."

[0040] The site provider 110 provides the tree diagnosis service site provided by the server device 10 on a network N, such as the Internet. Data related to tree diagnosis can be registered and viewed on this website. To this end, the site provider 110 transmits web pages written in HTML (HyperText Markup Language) or the like to the administrator terminal 20 or the diagnoser terminal 40, and receives input results and the like by users from the administrator terminal 20 or the diagnoser terminal 40.

[0041] In response to input from the user, the site providing unit 110 creates a corresponding web page and transmits it to the administrator terminal 20 or the diagnoser terminal 40. Specifically, the site providing unit 110 transmits to the administrator terminal 20 or the diagnoser terminal 40 various web pages, such as an order request screen for ordering a tree diagnosis and a diagnosis result registration screen for registering the diagnosis result.

[0042] The ordering unit 111 registers order information for tree diagnosis in response to an order request from the manager terminal 20, and transmits a work request for tree diagnosis to the worker terminal 30. In this embodiment, the order request includes the manager ID, tree ID, work date, worker ID, diagnoser ID, etc., and the ordering unit 111 generates a diagnosis ID and registers the order information for tree diagnosis in the diagnosis database 106 based on the order request. The status of the diagnosis database 106 is saved as "1: Ordered."

[0043] After completing the registration of the order information for the tree diagnosis, the order unit 111 acquires an email address associated with the worker ID from the worker database 103 based on the worker ID included in the order request, and requests the email sending unit 116, which will be described later, to send a work request for the tree diagnosis to that email address. The work request includes the diagnosis ID.

[0044] In response to input from the user of the worker terminal 30, the screen transmission unit 112 creates corresponding screen information of the worker tree diagnosis service app and transmits it to the worker terminal 30. Specifically, the screen transmission unit 112 transmits to the worker terminal 30, for example, a road tree map screen including location information of road trees, a diagnostic data registration screen for registering diagnostic data, and the like.

[0045] The diagnostic data receiving unit 113 receives and registers diagnostic data from the worker terminal 30. In this embodiment, the diagnostic data includes a diagnostic ID, a tree ID, a work date, image data of the tree, and percussion sound data, and the diagnostic data receiving unit 113 saves various data in the work date, image data, and audio data in the diagnostic database 106 based on the diagnostic ID and tree ID included in the received diagnostic data, and updates the status to "2: Work completed."

[0046] The diagnosis result acquisition unit 114 includes a diagnosis request unit 1141 and a diagnosis result reception unit 1142 . The diagnosis request unit 1141 transmits a diagnosis request for tree diagnosis to the diagnoser terminal 40. In this embodiment, when diagnostic data is registered in the diagnostic database 106, the diagnosis request unit 1141 obtains an email address associated with the diagnoser ID from the diagnoser database 104 based on the diagnoser ID in the diagnostic database 106, and requests the email sending unit 116 to send a diagnosis request for tree diagnosis to the email address. In this embodiment, the diagnosis request unit 1141 requests the email sending unit 116 when the status of all records having the diagnostic ID of the registered diagnostic data is "2: Work Completed," and the diagnosis ID is included in the diagnosis request. In another embodiment, the diagnosis request unit 1141 may request the email sending unit 116 to send a diagnosis request including the diagnostic ID and tree ID of the registered diagnostic data, regardless of the status of other records.

[0047] The diagnostic result receiving unit 1142 receives and registers diagnostic results from the diagnoser terminal 40. In this embodiment, the diagnostic results include a diagnostic ID, a tree ID, a diagnostic date, a comprehensive diagnosis, item diagnosis 1, and item diagnosis 2, and the diagnostic result receiving unit 1142 stores various data in the diagnostic date, comprehensive diagnosis, item diagnosis 1, and item diagnosis 2 in the diagnostic database 106 based on the diagnostic ID and tree ID included in the received diagnostic results, and updates the status to "3: Diagnosed." As mentioned above, the comprehensive diagnosis stores information indicating one of "1: No abnormality," "2: Observation required," "3: Treatment required," and "4: Removal required."

[0048] After the registration of the diagnostic result is completed, the diagnostic result receiving unit 1142 obtains an email address associated with the administrator ID from the administrator database 102 based on the administrator ID in the diagnostic database 106, and requests the email sending unit 116 to send a confirmation request for the diagnostic result to that email address. In this embodiment, the diagnostic result receiving unit 1142 requests the email sending unit 116 if the status of all records having the diagnostic ID of the registered diagnostic result is "3: Diagnosed," and the confirmation request includes the diagnostic ID. In another embodiment, the diagnostic result receiving unit 1142 may request the email sending unit 116 to send a confirmation request including the diagnostic ID of the registered diagnostic result and the tree ID, regardless of the status of other records.

[0049] The output unit 115 outputs the diagnostic result. In this embodiment, the output unit 115 refers to the diagnostic database 106 in response to an output instruction from the administrator terminal 20, and acquires and outputs the diagnostic result corresponding to the diagnostic ID included in the output instruction. In this embodiment, when the administrator ID included in the output instruction matches the administrator ID of the diagnostic database 106, the output unit 115 updates the status of the diagnostic database 106 to "4: Confirmed."

[0050] The email sending unit 116 sends an email to a specified address. In this embodiment, the email sending unit 116 sends an email to a specified address in response to a request from the order unit 111, the diagnosis request unit 1141, or the diagnosis result receiving unit 1142. Note that the email sending unit 116 is an example of a notification means, and the server device 10 can send a notification to a desired address using any other notification means.

[0051] (Worker terminal) Next, an example of the configuration of the worker terminal 30 will be described with reference to Fig. 3. The worker terminal 30 is held by a local worker, such as a worker of a landscaping company entrusted with managing roadside trees by the local government, or an employee of the local government. The worker terminal 30 has, as functional components, for example, a map acquisition unit 310, a display control unit 311, an imaging unit 312, an audio input unit 313, a diagnostic data transmission unit 314, and a storage unit 300. Each functional component will be described below.

[0052] The map acquisition unit 310 acquires a street tree map from the server device 10. In this embodiment, the map acquisition unit 310 transmits a map acquisition request including a diagnosis ID to the server device 10, and acquires from the server device 10 a street tree map including location information corresponding to one or more tree IDs associated with the diagnosis ID.

[0053] The display control unit 311 displays a screen according to an input from a user of the worker terminal 30 or an input from the server device 10. In this embodiment, the display control unit 311 displays a street tree map screen acquired from the server device 10. The display control unit 311 also displays a diagnostic data registration screen for registering diagnostic data.

[0054] The imaging unit 312 captures an image of the tree to be diagnosed in response to an input from the user of the operator terminal 30, and generates image data of the captured image.

[0055] The voice input unit 313 receives voice data including the sound of a mallet hitting a tree to be diagnosed in response to an input from the user of the worker terminal 30 .

[0056] The diagnostic data transmission unit 314 transmits the diagnostic data to the server device 10. In this embodiment, as described above, the diagnostic data includes a diagnosis ID, a work date, image data of the tree, percussion sound data, and the like.

[0057] [Hardware configuration] (Server device) Next, an example of the hardware configuration of the server device 10 will be described with reference to Fig. 4. In the example of Fig. 4, the server device 10 may include a processor 10a such as a CPU (Central Processing Unit) or a GPU (Graphics Processor Unit) corresponding to an arithmetic unit, a RAM (Random Access Memory) 10b, a ROM (Read Only Memory) 10c, a communication device 10d, a storage device 10e, an input device 10f, and a display device 10g. These components are connected via a bus so as to be able to transmit and receive data to and from each other.

[0058] The processor 10a functions as a control unit that performs data calculations and processing by loading programs stored in the ROM 10c or the storage device 10e into the RAM 10b and executing them. The processor 10a receives various input data from the communication device 10d or the input device 10f, and outputs the results of calculations on the input data from the communication device 10d or the display device 10g or stores them in the RAM 10b or the storage device 10e.

[0059] In this embodiment, the processor 10a is configured to be able to realize the above-described tree diagnosis-related processing by executing a program stored in the ROM 10c or the storage device 10e. For example, the site providing unit 110, the ordering unit 111, the screen transmitting unit 112, the diagnostic data receiving unit 113, the diagnostic result acquiring unit 114, the diagnostic request unit 1141, the diagnostic result receiving unit 1142, the output unit 115, and the email transmitting unit 116 shown as functional components in Fig. 2 are realized by executing a program on the processor 10a. The program may be provided by being stored in a computer-readable storage medium such as the RAM 10b or the ROM 10c, or may be provided via the network N connected by the communication device 10d.

[0060] RAM 10b is made up of, for example, semiconductor memory elements, and stores rewritable data. RAM 10b temporarily stores part or all of the data in storage unit 100, as well as the code included in the program. ROM 10c is made up of, for example, semiconductor memory elements, and stores readable but non-rewritable data. ROM 10c stores various data necessary for the program and processing related to tree diagnosis, such as data in storage unit 100.

[0061] The communication device 10d is a device for performing data communication with external devices including the manager terminal 20, the worker terminal 30, and the diagnoser terminal 40 via a wired or wireless network N.

[0062] The storage device 10e is a non-volatile storage medium such as a hard disk drive (HDD), and stores programs and data of the storage unit 100.

[0063] The input device 10f is a device for receiving operations from the user, and can be realized by a keyboard, a mouse, a touch panel, or the like.

[0064] The display device 10g is a device for displaying information, and can be realized by an organic EL display, a liquid crystal display, or the like.

[0065] (Administrator terminal) Next, an example of the hardware configuration of the administrator terminal 20 will be described with reference to Fig. 5. In the example of Fig. 5, the administrator terminal 20 may include a processor 20a such as a CPU or GPU, which corresponds to a computing device, a RAM 20b, a ROM 20c, a communication device 20d, a storage device 20e, an input device 20f, and a display device 20g. These components are connected via a bus so as to be able to send and receive data to and from each other.

[0066] The processor 20a functions as a control unit that performs calculations and processing of data by loading programs stored in the ROM 20c or the storage device 20e into the RAM 20b and executing them. The processor 20a receives various input data from the communication device 20d and the input device 20f, and outputs the results of calculations on the input data from the communication device 20d and the display device 20g, or stores them in the RAM 20b and the storage device 20e.

[0067] In this embodiment, the processor 20a is configured to implement a browser by executing a program stored in the storage device 20e. The browser is an application program that enables a user to view various websites on the communication network N, including websites provided by the server device 10. Note that in this embodiment, various requests are sent to the server device 10 in accordance with user operations on the browser installed in the administrator terminal 20, and the processing results are received and displayed on the browser. However, in other embodiments, various requests may be sent to the server device 10 by a function implemented by executing an application for a tree diagnosis service for administrators stored in the administrator terminal 20, and the processing results may be received and displayed.

[0068] The RAM 20b is made up of, for example, a semiconductor memory element and stores rewritable data. The RAM 20b temporarily stores the code included in the program as well as some or all of the data required for processing related to tree diagnosis. The ROM 20c is made up of, for example, a semiconductor memory element and stores readable but non-rewritable data. The ROM 20c stores the program and various data.

[0069] The communication device 20d is a device for performing data communication with external devices including the server device 10 via a wired or wireless network N.

[0070] The storage device 20e is a non-volatile storage medium such as a HDD, and stores the browser program and various data.

[0071] The input device 20f is a device for receiving operations from the user, and can be realized by a keyboard, a mouse, a touch panel, or the like.

[0072] The display device 20g is a device for displaying information, and can be realized by an organic EL display, a liquid crystal display, or the like.

[0073] (Worker terminal) Next, an example of the hardware configuration of the worker terminal 30 will be described with reference to Fig. 6. Similar to the manager terminal 20, the worker terminal 30 has a processor 30a such as a CPU or GPU, which corresponds to a computing device, a RAM 30b, a ROM 30c, a communication device 30d, a storage device 30e, an input device 30f, and a display device 30g. The worker terminal 30 also has a sensor 30h, an imaging device 30i, and a voice input device 30j. These components are connected via a bus so that they can send and receive data to and from each other.

[0074] In this embodiment, the processor 30a is configured to realize a map acquisition unit 310, a display control unit 311, an imaging unit 312, an audio input unit 313, and a diagnostic data transmission unit 314 by executing a program stored in the storage device 30e.

[0075] Note that RAM 30b, ROM 30c, communication device 30d, storage device 30e, input device 30f, and display device 30g have the same configurations as RAM 20b, ROM 20c, communication device 20d, storage device 20e, input device 20f, and display device 20g, respectively, and therefore detailed explanations thereof will be omitted.

[0076] The sensor 30h is configured to collect various information relating to the surrounding environment of the information processing device 10, convert it into an electrical signal, and output it, and can be realized by, for example, a GPS (Global Positioning System) sensor or the like.

[0077] The imaging device 30i is a device for capturing an image of a subject and acquiring image data, and can be realized by a camera.

[0078] The voice input device 30j is a device for acquiring voice data, and can be realized by a microphone.

[0079] (diagnostician terminal) Next, an example of the hardware configuration of the diagnostician terminal 40 will be described with reference to Fig. 7. Similar to the administrator terminal 20, the diagnostician terminal 40 has a processor 40a such as a CPU or GPU, which corresponds to an arithmetic unit, a RAM 40b, a ROM 40c, a communication device 40d, a storage device 40e, an input device 40f, and a display device 40g. The diagnostician terminal 40 also has an audio output device 40h. These components are connected via a bus so that they can send and receive data to and from each other.

[0080] In this embodiment, the processor 40a is configured to implement a browser and an audio output unit by executing a program stored in the storage device 40e. The browser is an application program that enables a user to browse various websites on the communication network N, including websites provided by the server device 10. The audio output unit outputs audio included in the diagnostic data.

[0081] In this embodiment, various requests are sent to the server device 10 in accordance with user operations on a browser implemented in the diagnoser terminal 40, and the processing results are received and displayed on the browser. However, in other embodiments, various requests may be sent to the server device 10 and the processing results may be received and displayed using a function realized by executing an application for a tree diagnosis service for diagnosers stored in the diagnoser terminal 40.

[0082] Note that RAM 40b, ROM 40c, communication device 40d, storage device 40e, input device 40f, and display device 40g have the same configuration as RAM 20b, ROM 20c, communication device 20d, storage device 20e, input device 20f, and display device 20g, respectively, and therefore detailed explanations thereof will be omitted.

[0083] The audio output device 40h is a device for outputting audio, and can be realized by a speaker.

[0084] (Server equipment ordering process) Next, the flow of the ordering process of the server device 10 will be described with reference to Figure 9. Here, an example will be described in which User X, a local government administrative staff member, orders a tree diagnosis with User Y as the worker and User Z as the diagnoser. Note that User X and User Z have been registered as users on the tree diagnosis service site in advance, and data including an administrator ID "0101", an administrator name "User X", an email address "kanrix@...", etc. is registered in the administrator database 102, and data including a diagnoser ID "0401", a diagnoser name "User Z", an email address "shindanz@...", etc. is registered in the diagnoser database 104.

[0085] It is assumed that user Y has been registered in advance as a user of the tree diagnosis service app for workers, and that data including worker ID "0301," worker name "User Y," email address "sagyoy@...," etc., is registered in worker database 103. In addition, in this embodiment, it is assumed that various data are stored in roadside tree database 101 and map database 105 under the management of the administrator of server device 10 before the process described in Fig. 9 is started.

[0086] When user X accesses a tree diagnosis service site provided by server device 10 using the browser on administrator terminal 20, site provider 110 of server device 10 sends a web page corresponding to the accessed URL to administrator terminal 20 (S101).

[0087] For example, when a request to order a tree diagnosis is sent from the administrator terminal 20 to the server device 10 in response to an operation by user X on the browser, such as user X selecting a "new order" control displayed on the browser, the site providing unit 110 sends a web page of an order request screen to the administrator terminal 20 (S102). In this embodiment, it is assumed that the site providing unit 110 has sent to the administrator terminal 20 a web page corresponding to the order request screen on which the administrator ID, tree ID, work date, worker ID, diagnoser ID, etc. can be specified.

[0088] After inputting each data item on the order request screen, the administrator terminal 20 sends an order request to the server device 10 in response to a browser operation by user X, such as selecting a "Register" control on the browser. The order unit 111 of the server device 10 registers order information for tree diagnosis based on the order request (S103). In this embodiment, the order request includes an administrator ID, a tree ID, a work date, a worker ID, a diagnostician ID, etc., and the order unit 111 generates a diagnosis ID and registers the order information for tree diagnosis in the diagnostic database 106 based on the order request. In this example, the order request includes an administrator ID "0201," tree IDs "A001-A020," a work date "2024 / 7 / 1," a worker ID "0301," a diagnostician ID "0401," etc., and as shown in FIG. 8, the order unit 111 generates a diagnosis ID "00001" and registers 20 records in the diagnostic database 106.

[0089] After the registration of the tree diagnosis order information is completed, the ordering unit 111 obtains the email address associated with the worker ID from the worker database 103 based on the worker ID included in the order request, and requests the email sending unit 116 of the server device 10 to send the tree diagnosis work request to that email address (S104).

[0090] In response to a request from the order unit 111, the email sending unit 116 sends a work request for tree diagnosis to a specified destination (S105). In this embodiment, the email sending unit 116 sends a work request including a diagnosis ID. Here, it is assumed that the email sending unit 116 has sent a work request including the diagnosis ID "00001" to the email address "sagyoy@···" associated with the worker ID "0301."

[0091] (Server device diagnostic data registration process) Next, a flow of diagnostic data registration processing of the server device 10 and the worker terminal 30 will be described with reference to Fig. 10. Here, an example will be described in which user Y who has received a work request registers diagnostic data.

[0092] On the actual work day, when user Y arrives at a location near the tree to be diagnosed, user Y transmits a map acquisition request from the worker terminal 30 (S201). For example, in response to user Y's operation, such as starting the tree diagnosis service app for workers and selecting the "Get Map" control associated with the desired work on the displayed work list screen, the map acquisition unit 310 of the worker terminal 30 transmits a map acquisition request including the diagnosis ID to the server device 10. Here, it is assumed that the map acquisition unit 310 transmits a map acquisition request including the diagnosis ID "00001" to the server device 10.

[0093] When a map acquisition request is sent from the worker terminal 30 to the server device 10 (S202), the screen transmission unit 112 of the server device 10 creates street tree map screen information including position information of the street trees (S203) and transmits it to the worker terminal 30 (S204). In this embodiment, the screen transmission unit 112 acquires the tree ID associated with the diagnosis ID from the diagnosis database 106, and creates street tree map screen information based on the position information of the acquired tree ID and the map information in the map database 105. Here, it is assumed that the screen transmission unit 112 created the street tree map screen information based on 20 pieces of position information corresponding to the 20 tree IDs associated with the diagnosis ID "00001" and the map information in the map database 105.

[0094] When the street tree map screen information is transmitted from the screen transmission unit 112 (S205), the display control unit 311 of the worker terminal 30 displays the street tree map screen on the display device 30g based on the street tree map screen information (S206). In this embodiment, the display control unit 311 displays the street tree map screen including the current position acquired from the sensor 30h on the display device 30g.

[0095] When receiving the instruction to register the diagnostic data of the desired tree, the display control unit 311 displays a diagnostic data registration screen for registering the diagnostic data on the display device 30g (S207). For example, in response to an operation by the user Y, such as selecting a specific road tree among the diagnostic targets on the displayed road tree map screen, the display control unit 311 displays the diagnostic data registration screen for registering the diagnostic data on the display device 30g. Information on the diagnostic data registration screen may be obtained from the server device 10.

[0096] In this embodiment, the worker can specify a diagnosis ID, a tree ID, a work date, multiple pieces of image data, and multiple pieces of audio data on the diagnostic data registration screen. Specifically, the worker can specify, as image data, image data of a base image, an image of a trunk image, an image of a leaf image, and an image of the entire tree, and can specify, as audio data, audio data of a root percussion sound 1, a root percussion sound 2, a trunk percussion sound 1, and a trunk percussion sound 2. Here, it is assumed that user Y specifies, on the diagnostic data registration screen, image data generated by the imaging unit 312 of the worker terminal 30, and audio data input by the audio input unit 313 of the worker terminal 30.

[0097] The diagnostic data registration screen may be displayed so that recommended items for performing an appropriate tree diagnosis can be specified depending on the type of tree in question. For example, for one type of tree, image data of the base, trunk, leaves, and entire tree can be specified, and for another type of tree, image data of the junction of the trunk and branches can be specified in addition to the base, trunk, leaves, and entire tree.

[0098] In addition, the diagnostic data registration screen may include a guide explaining where the worker should stand when taking an image, or may highlight items that are not specified, in order to support the acquisition of image data and audio data that are more appropriate for diagnosis. Furthermore, the diagnostic data registration screen may be displayed so that environmental items such as the temperature and humidity during work, the presence or absence of pests that damage branches and trunks, and the presence or absence of mushrooms that are indicators of tree decay can be specified.

[0099] When user Y completes the registration of diagnostic data on the diagnostic data registration screen, the diagnostic data transmission unit 314 of the worker terminal 30 transmits the diagnostic data to the server device 10 (S208). For example, in response to an operation by user Y, such as selecting the "send" control on the diagnostic data registration screen, the diagnostic data transmission unit 314 transmits the diagnostic data to the server device 10. Here, it is assumed that the diagnostic data transmission unit 314 transmits diagnostic data including the diagnostic ID "00001" and the tree ID "A001" to the server device 10.

[0100] When the diagnostic data is transmitted from the worker terminal 30 to the server device 10 (S209), the diagnostic data receiving unit 113 of the server device 10 updates the diagnostic database 106 based on the received diagnostic data (S210). In this embodiment, the diagnostic data includes a diagnostic ID, a tree ID, a work date, multiple image data, and multiple audio data, and the diagnostic data receiving unit 113 saves various data in the work date, image data, and audio data of the diagnostic database 106 based on the diagnostic ID and tree ID included in the received diagnostic data, and updates the status to "2: Work completed."

[0101] When the diagnostic data is registered in the diagnostic database 106, the diagnosis request unit 1141 of the server device 10 obtains an email address associated with the diagnoser ID from the diagnoser database 104 based on the diagnoser ID in the diagnostic database 106, and requests the email sending unit 116 to send a diagnosis request for tree diagnosis to the email address (S211). In this embodiment, the diagnosis request unit 1141 requests the email sending unit 116 when the status of all records having the diagnostic ID of the registered diagnostic data is "2: Work completed."

[0102] In response to a request from the diagnosis request unit 1141, the email sending unit 116 sends a diagnosis request for a tree diagnosis to a specified destination (S212). In this embodiment, the email sending unit 116 sends a diagnosis request including a diagnosis ID. Here, it is assumed that the email sending unit 116 has sent a diagnosis request including the diagnosis ID "00001" to the email address "shindanz@···" associated with the diagnoser ID "0401."

[0103] (Server device diagnostic result acquisition process) Next, the flow of the diagnostic result acquisition process of the server device 10 will be described with reference to Fig. 11. Here, an example will be described in which a user Z who has received a diagnostic request provides a diagnostic result.

[0104] When user Z accesses the tree diagnosis service site provided by server device 10 using the browser on diagnoser terminal 40, site provider 110 of server device 10 sends a web page corresponding to the accessed URL to diagnoser terminal 40 (S301).

[0105] For example, when a request to confirm diagnostic data is sent from the diagnosing operator terminal 40 to the server device 10 in response to an operation by user Z on the browser, such as when user Z selects a "Confirm diagnostic data" control associated with a specific tree on a diagnosis list screen displayed on the browser, the site providing unit 110 sends a web page of the diagnostic data confirmation screen to the diagnosing operator terminal 40 (S302). In this embodiment, it is assumed that a request including the diagnostic ID "00001" and the tree ID "A001" is sent, and the site providing unit 110 sends to the diagnosing operator terminal 40 a web page corresponding to the diagnostic data confirmation screen on which the diagnostic ID, tree ID, work date, multiple image data, multiple audio data, etc. can be confirmed.

[0106] After checking the diagnostic data, user Z operates the browser, for example, by selecting a "Diagnosis Result Registration" control on the diagnostic data confirmation screen displayed on the browser. In response to this, a request to register the diagnostic results is sent from the diagnosing operator terminal 40 to the server device 10. In response, the site providing unit 110 transmits a web page of the diagnostic result registration screen to the diagnosing operator terminal 40 (S303). In this embodiment, a request including the diagnostic ID "00001" and the tree ID "A001" is transmitted, and the site providing unit 110 transmits a web page corresponding to the diagnostic result registration screen to the diagnosing operator terminal 40, on which the diagnosing date, comprehensive diagnosis, item diagnosis 1, item diagnosis 2, etc. can be specified. Note that the diagnostic result registration screen may include a free field in which the diagnosing operator can freely input their own impressions, in addition to the comprehensive diagnosis indicating "1: No abnormality," "2: Observation required," "3: Treatment required," or "4: Removal required," the item diagnosis 1 indicating the presence or absence of pests, and the item diagnosis 2 indicating the presence or absence of mushrooms.

[0107] After inputting each piece of data on the diagnostic result registration screen, the diagnostic result is transmitted from the diagnoser terminal 40 to the server device 10 in response to a browser operation by user Z, such as selecting a "Register" control on the browser. The diagnostic result receiving unit 1142 of the server device 10 then registers the diagnostic result (S304). In this embodiment, the diagnostic result includes a diagnostic ID, a tree ID, a diagnostic date, a comprehensive diagnosis, item diagnosis 1, and item diagnosis 2. Based on the diagnostic ID and tree ID included in the received diagnostic result, the diagnostic result receiving unit 1142 stores various data in the diagnostic date, comprehensive diagnosis, item diagnosis 1, and item diagnosis 2 in the diagnostic database 106 and updates the status to "3: Diagnosed." As described above, the comprehensive diagnosis stores information indicating one of "1: No abnormality," "2: Observation required," "3: Treatment required," and "4: Removal required."

[0108] After the registration of the diagnostic result is completed, the diagnostic result receiving unit 1142 acquires an email address associated with the administrator ID from the administrator database 102 based on the administrator ID in the diagnostic database 106, and requests the email sending unit 116 to send a request to confirm the diagnostic result to the email address (S305). In this embodiment, the diagnostic result receiving unit 1142 requests the email sending unit 116 when the status of all records having the diagnostic ID of the registered diagnostic result is "3: Diagnosed."

[0109] In response to a request from the diagnosis request unit 1141, the email sending unit 116 sends a confirmation request for the diagnosis result to a specified destination (S306). In this embodiment, the email sending unit 116 sends a confirmation request including the diagnosis ID and the tree ID. Here, it is assumed that the email sending unit 116 has sent a confirmation request including the diagnosis ID "00001" to the email address "kanrix@···" associated with the administrator ID "0101."

[0110] Thereafter, when user X, who has received the confirmation request, uses the browser on the administrator terminal 20 to access the tree diagnosis service site provided by the server device 10, the site providing unit 110 of the server device 10 sends the web page corresponding to the accessed URL to the administrator terminal 20 (S307).

[0111] For example, when a request to check the diagnosis results is sent from the administrator terminal 20 to the server device 10 in response to an operation by user X on the browser, such as when user X selects a "Confirm Diagnosis Result" control associated with a specific tree on a diagnosis result list screen displayed on the browser, the site providing unit 110 sends a web page of the diagnosis result confirmation screen to the administrator terminal 20 (S308). In this embodiment, it is assumed that a request including the diagnosis ID "00001" and the tree ID "A001" is sent, and the site providing unit 110 sends to the administrator terminal 20 a web page corresponding to the diagnosis result confirmation screen on which the diagnosis ID, tree ID, work date, worker ID, diagnosis date, diagnoser ID, overall diagnosis, item diagnosis 1, item diagnosis 2, etc. can be checked.

[0112] After confirming the diagnosis result, when an instruction indicating that the diagnosis result has been confirmed is sent from the administrator terminal 20 to the server device 10 in response to an operation by user X on the browser, such as user X selecting the "Confirm" control on the diagnosis result confirmation screen displayed on the browser, the site providing unit 110 updates the status of the diagnosis database 106 to "4: Confirmed" (S309). In this embodiment, it is assumed that an instruction including the diagnosis ID "00001" and the tree ID "A001" is sent, and the site providing unit 110 updates the status of the corresponding record.

[0113] 11, the site providing unit 110 can transmit a web page for checking desired diagnostic data or diagnostic results in response to a request from the administrator terminal 20 or the diagnoser terminal 40. For example, the site providing unit 110 may transmit a web page for checking past diagnostic results for a tree corresponding to a predetermined tree ID, or may transmit a web page that allows checking diagnostic data for each part, such as the trunk or roots, for multiple trees belonging to a predetermined type.

[0114] Furthermore, the site providing unit 110 may transmit a web page displaying the diagnosis results acquired by the output unit 115 in map format in response to a request from the administrator terminal 20 or the diagnoser terminal 40. For example, the site providing unit 110 may transmit a web page of a diagnosis result map screen including a visual display such as an icon indicating one of "1: No abnormality," "2: Observation required," "3: Treatment required," and "4: Removal required" at the location of roadside trees on the map. In addition to the comprehensive diagnosis of the trees, the diagnosis result map screen may also include information that allows visual confirmation of the presence or absence of pests or mushrooms acquired during work.

[0115] As described above, according to this embodiment, the server device 10 can improve the efficiency of tree diagnosis work by acquiring diagnostic data necessary for diagnosis from the worker terminal 30 and providing the acquired diagnostic data to the diagnoser terminal 40. By leaving the acquisition of diagnostic data to the worker, the work of the diagnoser can be reduced, and the efficiency of the entire tree diagnosis work can be improved.

[0116] In addition to the diagnostic data of this embodiment, the server device 10 may acquire information such as tree height and trunk diameter, which allows the growth of the tree to be understood, from the worker terminal 30. In one embodiment, the server device 10 can determine and provide the growth rate of the tree based on this additional information.

[0117] Furthermore, in response to the registration of diagnostic data, the server device 10 requests a diagnosis from the diagnostician terminal 40 of the diagnostician who will make a diagnosis based on the diagnostic data, thereby enabling the diagnostic data to be provided to the appropriate diagnostician in a timely manner.

[0118] Furthermore, in response to an order request from the administrator terminal 20, the server device 10 can provide work information to the appropriate worker in a timely manner by requesting work from the worker terminal 30 of the worker specified in the order request.

[0119] Furthermore, the server device 10 can assist workers who are not arborists in obtaining appropriate diagnostic data by sending recommended image information and / or audio information to the worker terminal 30 depending on the type of tree being diagnosed.

[0120] <Second embodiment> [System Configuration] In the first embodiment, an example was described in which a diagnosing arborist provides a diagnostic result via a diagnosing terminal 40. In the second embodiment, an example is described in which a server device 10 provides a diagnostic result using diagnostic data. FIG. 12 is a diagram illustrating the configuration of an information processing system according to the second embodiment. Unlike the first embodiment, the server device 10 is configured to communicate with a learning device 50 via a network N, and does not include a diagnosing terminal 40.

[0121] The learning device 50 learns a machine learning model based on the learning data and generates a trained model. The learning device 50 according to this embodiment includes a machine learning model, but the machine learning model may be provided in a device separate from the learning device 50.

[0122] Here, a machine learning model is a model that has a predetermined model structure and processing parameters that vary through a learning process, and that improves classification accuracy by optimizing the processing parameters based on experience gained from training data. That is, a machine learning model is a model that learns optimal processing parameters through a learning process. The algorithm of a machine learning model may be, for example, a support vector machine, a logistic regression, a neural network, or the like, but the type is not particularly limited. The machine learning model that performs this learning may be one that has already undergone some kind of learning using training data, or one that has not yet been trained.

[0123] A trained model is a machine learning model based on an arbitrary machine learning algorithm that has been trained in advance using appropriate training data. However, a trained model does not necessarily mean that it will not undergo further training, and additional training can also be performed.

[0124] The learning device 50 according to this embodiment receives a set of multiple image data and multiple audio data as input data and is equipped with a machine learning model that classifies the data into one of "normal," "observation required," "treatment required," and "removal required." The learning device 50 uses the machine learning model to classify the input data set, and trains the machine learning model so as to minimize the error between the predicted result and the ground truth data labeled in the learning data.

[0125] The server device 10 performs inference using the trained model acquired from the learning device 50. Here, acquiring the trained model means acquiring information necessary to reproduce the function of the trained model in the server device 10. For example, when a neural network is used as the machine learning model, acquiring the trained model means acquiring information at least regarding the number of layers of the neural network, the number of nodes for each layer, weight parameters of links connecting nodes, bias parameters for each node, and the functional form of the activation function for each node.

[0126] The server device 10 according to this embodiment uses the trained model acquired from the learning device 50 to infer whether the tree to be diagnosed belongs to the category of "normal," "requires observation," "requires treatment," or "requires removal."

[0127] In this embodiment, an example is described in which the input data set is classified into one of four diagnostic levels indicating the health of the tree: "No abnormalities," "Requires observation," "Requires treatment," and "Requires removal." However, in other embodiments, the data may be classified into any number of other diagnostic levels.

[0128] [Function Configuration] (Learning device) Next, an example of the configuration of the learning device 50 will be described using Figure 13. Note that Figure 13 assumes a single learning device 50 and shows only the necessary functional configuration, but the learning device 50 can also be configured as part of a multi-functional distributed system consisting of multiple computer systems. The learning device 50 can be, for example, a server device installed at a company that provides tree diagnosis services to local governments.

[0129] The learning device 50 has, as functional components, for example, a learning unit 510, a classification unit 511, a model output unit 512, and a storage unit 500. The storage unit 500 stores, for example, a training database 501 and a trained model 502. Each functional component will be described below.

[0130] The training database 501 stores training data used for training the machine learning model M, which will be described later. In this embodiment, the training database 501 stores a set of multiple image data and multiple audio data, each of which is labeled as correct answer data with a diagnostic level of "normal," "observation required," "treatment required," or "removal required."

[0131] The trained model 502 stores a trained model trained by a training unit 510 (described later). In this embodiment, the trained model 502 stores a trained model that receives a set of multiple image data and multiple audio data as input data and classifies the trees into any of the following: trees without abnormalities, trees requiring observation, trees requiring treatment, and trees requiring removal.

[0132] The learning unit 510 trains the machine learning model M using the training data stored in the training database 501. In this embodiment, the learning unit 510 inputs a set of multiple image data and multiple audio data, each labeled with a diagnostic level of "normal," "observation required," "treatment required," or "removal required" as correct answer data, to a classification unit 511, which will be described later, and trains the machine learning model M.

[0133] The classification unit 511 receives an input of a set of multiple image data and multiple voice data, and classifies the data into one of the diagnostic levels: "no abnormality", "observation required", "treatment required", or "removal required". In this embodiment, the classification unit 511 receives an input of a set of multiple image data and multiple voice data, and uses the machine learning model M to output the confidence levels of "no abnormality", "observation required", "treatment required", and "removal required".

[0134] The machine learning model M is a machine learning model that receives a set of multiple image data and multiple audio data as input data and classifies the data into one of the diagnostic levels of "normal," "observation required," "treatment required," and "removal required." In this embodiment, an example of the machine learning model M will be described, in which a convolutional neural network (CNN) is used that receives a set of multiple image data and multiple audio data as input data and outputs a classification of the input data set. However, CNN is merely one example of the machine learning model M, and the learning device 50 may use other configurations as the machine learning model M.

[0135] The learning unit 510 trains the machine learning model M so as to minimize the error between the result predicted by the machine learning model M and the correct answer data labeled in the training data.

[0136] When the learning of the machine learning model M is completed, the model output unit 512 outputs the learned model obtained by learning the machine learning model M to the storage unit 500. Note that the learning unit 510 may complete the learning after training the machine learning model M using a predetermined number of training data, for example, or may complete the learning when the accuracy of classification predicted using the machine learning model M satisfies a predetermined condition.

[0137] (Server device) Next, an example of the configuration of the server device 10 will be described with reference to Fig. 14. In the second embodiment, the storage unit 100 of the server device 10 further stores a trained model 107.

[0138] The trained model 107 stores a trained model used for inference. In this embodiment, the trained model 107 stores a trained model that receives image data of trees and audio data of percussion sounds as input data and classifies the trees into one of normal trees, trees requiring observation, trees requiring treatment, and trees requiring removal. In this embodiment, an example of the trained model 107 will be described, in which a convolutional neural network (CNN) is used that receives image data of trees and audio data of percussion sounds as input data and classifies the trees into one of normal trees, trees requiring observation, trees requiring treatment, and trees requiring removal. However, CNN is merely one example of the trained model 107, and the server device 10 may use other configurations for the trained model 107.

[0139] The diagnosis result acquisition unit 114 of the server device 10 includes a diagnosis unit 1143 and a registration unit 1144 , and the server device 10 further includes a model acquisition unit 117 .

[0140] The model acquisition unit 117 acquires a trained model to be used for inference and stores it in the trained model 107. In this embodiment, the model acquisition unit 117 acquires a trained model from the learning device 50 and stores it in the trained model 107.

[0141] The diagnosing unit 1143 infers a diagnosis of the tree based on the diagnostic data received by the diagnostic data receiving unit 113. In this embodiment, the diagnosing unit 1143 inputs the diagnostic data to the trained model 107, obtains the confidence level for each of the diagnostic levels "no abnormality," "observation required," "treatment required," and "removal required," and obtains the diagnostic level with the highest confidence level as the inference result for the comprehensive diagnosis. Note that the diagnosing unit 1143 may input the diagnostic data received by the diagnostic data receiving unit 113 to other prediction models to predict the presence or absence of pests or mushrooms.

[0142] The registration unit 1144 registers the diagnosis result including the inference result acquired by the diagnosis unit 1143. In this embodiment, the diagnosis result includes a diagnosis ID, a tree ID, a diagnosis date, a comprehensive diagnosis, an item diagnosis, etc., and the registration unit 1144 stores various data in the diagnosis date, comprehensive diagnosis, and item diagnosis in the diagnosis database 106 based on the diagnosis ID and tree ID included in the diagnosis result, and updates the status to "3: Diagnosed." As described above, the comprehensive diagnosis stores information indicating one of "1: No abnormality," "2: Observation required," "3: Treatment required," and "4: Removal required."

[0143] After the registration of the diagnostic result is completed, the registration unit 1144 refers to the administrator database 102 based on the administrator ID of the diagnostic database 106, and requests the email sending unit 116 to send a confirmation request for the diagnostic result to the email address associated with the administrator ID. In this embodiment, the diagnostic result receiving unit 1142 requests the email sending unit 116 if the status of all records having the diagnostic ID of the registered diagnostic result is "3: Diagnosed," and the confirmation request includes the diagnostic ID. In another embodiment, the diagnostic result receiving unit 1142 may request the email sending unit 116 to send a confirmation request including the diagnostic ID and tree ID of the registered diagnostic result, regardless of the status of other records.

[0144] [Hardware configuration] (Learning device) Next, we will explain an example of the hardware configuration of the learning device 50. Similar to the server device 10, the learning device 50 has a processor 50a such as a CPU or GPU, which corresponds to a computing device, a RAM 50b, a ROM 50c, a communication device 50d, a storage device 50e, an input device 50f, and a display device 50g. These components are connected via a bus so that they can send and receive data to and from each other.

[0145] The processor 50a in this embodiment is configured to be able to implement a learning unit 510, a classification unit 511, and a model output unit 512 by executing a program stored in the storage device 50e.

[0146] Note that RAM 50b, ROM 50c, communication device 50d, storage device 50e, input device 50f, and display device 50g have the same configurations as RAM 10b, ROM 10c, communication device 10d, storage device 10e, input device 10f, and display device 10g, respectively, and therefore detailed explanations thereof will be omitted.

[0147] (Learning process of the learning device) The learning process of the learning device according to an embodiment of the present invention will be described in detail with reference to Fig. 15. In this embodiment, before the learning process described in Fig. 15 is performed, learning data is stored in the learning database 501 under the management of an administrator of the learning device 50. Note that the process shown in Fig. 15 is executed, for example, by the administrator inputting an instruction to execute a process for generating a trained model via the input device 50f.

[0148] The learning unit 510 of the learning device 50 uses the learning data stored in the learning database 501 to train the machine learning model M (S401). In this embodiment, the learning unit 510 inputs a set of multiple image data and multiple audio data, each of which is labeled as correct data with a diagnostic level of "normal," "observation required," "treatment required," or "removal required," to the classification unit 511, and trains the machine learning model M.

[0149] The machine learning model M is a machine learning model that receives a set of multiple image data and multiple audio data as input data and classifies the data into one of the diagnostic levels of "normal," "observation required," "treatment required," and "removal required." In this embodiment, an example of the machine learning model M will be described, in which a convolutional neural network (CNN) is used that receives a set of multiple image data and multiple audio data as input data and outputs a classification of the input data set. However, CNN is merely one example of the machine learning model M, and the learning device 50 may use other configurations as the machine learning model M.

[0150] The learning unit 510 trains the machine learning model M so as to minimize the error between the result predicted by the machine learning model M and the correct answer data labeled in the training data.

[0151] When the learning of the machine learning model M is completed, the model output unit 512 of the learning device 50 outputs the learned model obtained by learning the machine learning model M to the storage unit 500 (S402). Note that the learning unit 510 may complete the learning after training the machine learning model M using a predetermined number of training data, for example, or may complete the learning when the accuracy of classification predicted using the machine learning model M satisfies a predetermined condition.

[0152] (Server device diagnostic result acquisition process) Next, the flow of the diagnostic result acquisition process of the server device 10 will be described with reference to Figure 16. In this embodiment, the order process is performed according to Figure 9, followed by the diagnostic data registration process from S201 to S210 according to Figure 10, and then the process shown in Figure 16 starts after S210. Note that before the process shown in Figure 16 starts, it is assumed that the trained model acquired from the learning device 50 is stored in the trained model 107 under the management of the administrator of the server device 10.

[0153] The diagnosing unit 1143 of the server device 10 infers the diagnosis level of the tree based on the diagnostic data received by the diagnostic data receiving unit 113 (S501). In this embodiment, the diagnosing unit 1143 inputs the diagnostic data to the trained model 107, obtains the confidence level of each diagnostic level: "No abnormality," "Requires observation," "Requires treatment," and "Requires removal," and obtains the diagnostic level with the highest confidence level as the inference result of the comprehensive diagnosis. In addition, the diagnosing unit 1143 inputs the diagnostic data received by the diagnostic data receiving unit 113 to other prediction models, predicts the presence or absence of pests and mushrooms, and obtains the inference result of the item diagnosis.

[0154] Next, the registration unit 1144 of the server device 10 registers the diagnosis result including the inference result acquired by the diagnosis unit 1143 (S502). In this embodiment, the diagnosis result includes a diagnosis ID, a tree ID, a diagnosis date, a comprehensive diagnosis, and an item diagnosis, and the registration unit 1144 stores various data in the diagnosis date, comprehensive diagnosis, and item diagnosis in the diagnosis database 106 based on the diagnosis ID and tree ID included in the diagnosis result, and updates the status to "3: Diagnosed." As described above, the comprehensive diagnosis stores information indicating one of "1: No abnormality," "2: Observation required," "3: Treatment required," and "4: Removal required."

[0155] After the registration of the diagnostic result is completed, the registration unit 1144 acquires an email address associated with the administrator ID from the administrator database 102 based on the administrator ID of the diagnostic database 106, and requests the email sending unit 116 to send a request to confirm the diagnostic result to the email address (S503). In this embodiment, the registration unit 1144 requests the email sending unit 116 when the status of all records having the diagnostic ID of the registered diagnostic result is "3: Diagnosed".

[0156] In response to a request from the registration unit 1144, the email sending unit 116 sends a confirmation request for the diagnosis result to a specified destination (S504). In this embodiment, the email sending unit 116 sends a confirmation request including a diagnosis ID. Here, it is assumed that the email sending unit 116 has sent a confirmation request including the diagnosis ID "00001" to the email address "kanrix@···" associated with the administrator ID "0101."

[0157] Thereafter, confirmation processing is performed by the administrator in accordance with steps S505 to S507, but as these are similar to steps S307 to S309 in FIG. 11, detailed description thereof will be omitted.

[0158] As described above, according to this embodiment, the server device 10 acquires diagnostic data necessary for diagnosis from the operator terminal 30, and infers which of a plurality of diagnostic levels indicating the health of a tree a tree belongs to based on the acquired diagnostic data, thereby improving the efficiency of tree diagnosis work. By entrusting part of the tree diagnosis to the diagnosing unit 1143, the work of the diagnoser can be reduced, and the efficiency of the entire tree diagnosis work can be improved. [Explanation of symbols]

[0159] 10...server device (information processing device), 10a...processor, 10b...RAM, 10c...ROM, 10d...communication device, 10e...storage device, 10f...input device, 10g...display device, 100...storage unit, 101...street tree database, 102...administrator database, 103...worker database, 104...diagnostician database, 105...map database, 106...diagnosis database, 110...site providing unit (providing unit, output unit), 111 ...Ordering unit, 112...Screen transmission unit (transmission unit), 113...Diagnostic data receiving unit (reception unit), 114...Diagnostic result acquisition unit (acquisition unit), 1141...Diagnosis request unit (request unit), 1142...Diagnosis result receiving unit, 115...Output unit, 116...Email transmission unit (request unit), 117...Model acquisition unit, 20...Administrator terminal, 20a...Processor, 20b...RAM, 20c...ROM, 20d...Communication device, 20e...Storage device, 20f...Input device, 20g...Display device, 3 0...worker terminal (terminal device), 30a...processor, 30b...RAM, 30c...ROM, 30d...communication device, 30e...storage device, 30f...input device, 30g...display device, 30h...sensor, 30i...imaging device, 30j...voice input device, 300...storage unit, 310...map acquisition unit, 311...display control unit, 312...imaging unit, 313...voice input unit, 314...diagnostic data transmission unit, 40...diagnostician terminal, 40a...processor, 40b...RAM, 40c...ROM, 40d...communication device, 40e...storage device, 40f...input device, 40g...display device, 40h...audio output device, 50...learning device, 50a...processor, 50b...RAM, 50c...ROM, 50d...communication device, 50e...storage device, 50f...input device, 50g...display device, 500...storage unit, 501...learning database, 502...trained model, 510...learning unit, 511...classification unit, 512...model output unit, N...network

Claims

1. An information processing device communicably connected to an operator terminal and a diagnoser terminal, a receiving unit that receives diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registers the diagnostic data in a storage unit; a providing unit that provides the diagnostic data to the diagnostician terminal; an acquisition unit that acquires a diagnosis result regarding the health of the tree from the diagnoser terminal; an output unit that outputs the diagnosis result; An information processing device comprising:

2. a request unit that requests a diagnosis from the diagnostician terminal in response to the registration of the diagnostic data; The information processing device according to claim 1 , further comprising:

3. the information processing device is further communicably connected to an administrator terminal, an ordering unit that receives an order request including the identification information of the tree, the identification information of the worker, and the identification information of the diagnostician from the manager terminal and registers the order request in the storage unit; Furthermore, the ordering unit requests the worker terminal to perform the work based on the worker's identification information; The information processing device according to claim 1 .

4. a transmission unit that transmits image information and / or audio information recommended for performing an appropriate tree diagnosis according to the type of tree to the worker terminal; The information processing device according to claim 1 , further comprising:

5. The information processing device according to claim 1 , wherein the output unit further outputs a diagnosis result map including a visual display showing the corresponding diagnosis result at the position of each tree on the map.

6. an information processing device communicably connected to the operator terminal and the diagnoser terminal, receiving diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registering the diagnostic data in a storage unit; providing the diagnostic data to the diagnostician terminal; acquiring a diagnosis result regarding the health of the tree from the diagnoser terminal; outputting the diagnosis result; A method comprising:

7. An information processing device communicably connected to the operator terminal and the diagnoser terminal, receiving diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registering the diagnostic data in a storage unit; a process of providing the diagnostic data to the diagnostician terminal; a process of acquiring a diagnosis result regarding the health of the tree from the diagnoser terminal; A process of outputting the diagnosis result; A program that executes the following.

8. An information processing device communicably connected to a worker terminal, a receiving unit that receives diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registers the diagnostic data in a storage unit; a diagnostic unit that infers, based on the diagnostic data, to which diagnostic level the tree belongs among a plurality of diagnostic levels indicating the health of the tree; an output unit that outputs the inference result of the diagnosis unit; An information processing device comprising:

9. the diagnosing unit infers the health of the tree by inputting the plurality of image data and the plurality of audio data into a trained model; The trained model is a trained model trained to estimate the health of the tree from a plurality of image data of the tree and a plurality of audio data including sounds of the tree being struck. The information processing device according to claim 8 .

10. an information processing device communicably connected to the worker terminal, receiving diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registering the diagnostic data in a storage unit; inferring, based on the diagnostic data, to which diagnostic level the tree belongs from among a plurality of diagnostic levels indicating the health of trees; outputting the inferred result; A method comprising:

11. An information processing device communicably connected to the worker terminal, receiving diagnostic data including a plurality of image data and a plurality of audio data related to a tree to be diagnosed from the operator terminal and registering the diagnostic data in a storage unit; a process of inferring, based on the diagnostic data, to which of a plurality of diagnostic levels indicating the health of trees the tree belongs; A process of outputting the inferred result; A program that executes the following.

12. A terminal device communicably connected to a server device, an imaging unit that captures an image of a tree to be diagnosed and generates image data of the captured image; a voice input unit for inputting voice data including the sound of hitting the tree; a display control unit that displays a screen on which a plurality of pieces of image data generated by the imaging unit and a plurality of pieces of audio data input by the audio input unit can be designated; a transmitting unit that transmits the plurality of image data and the plurality of audio data designated on the screen to the server device; A terminal device comprising:

13. A terminal device connected to the server device so as to be able to communicate with the server device A process of capturing an image of a tree to be diagnosed and generating image data of the captured image; a process of inputting audio data including the sound of hitting the tree; A process of displaying a screen on which a plurality of image data and a plurality of audio data can be designated; a process of transmitting the plurality of image data and the plurality of audio data designated on the screen to the server device; A program that executes the following.

Images