Prediction system, prediction method, trained model, learning system, learning method, and program

Abstract

To provide a prediction system capable of predicting in advance demand for a medical device in a medical device lending system.SOLUTION: A prediction system uses learning data, including lending result data indicating a result of lending out a medical device and electronic medical record data in which information indicating the necessity of use of the lent medical device is described, to store a learned model that is machine-learned so as to input the electronic medical record data in which the information indicating the necessity of use of the medical device is described and to output a demand prediction result that is a prediction result of a demand of the medical device. The prediction system inputs, into the learned model, the electronic medical record data in which the information indicating the necessity of use of the medical device is described to acquire the demand prediction result, inputs an inventory prediction result that is a prediction result of the inventory of the medical device, which is predicted on the basis of the current inventory and reservation information, compares the acquired demand prediction result with the input inventory prediction result, and notifies a medical device lending system when the demand exceeds the inventory.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a prediction system, a prediction method, a trained model, a learning system, a learning method, and a program. [Background technology]

[0002] Patent Document 1 discloses an information processing device that adjusts a logistics base in response to a demand forecast. This information processing device creates product demand information indicating trends in demand for a product for each region based on the location where each user's product-related behavior took place and the number of behaviors taken at the location, and determines a logistics base for the product based on the product demand information. Furthermore, this information processing device creates a transportation plan for transporting a product to the logistics base for the product in advance based on the product demand information. Also, this information processing device creates an inventory transport plan for transferring product inventory from another logistics base where the product inventory is located to the logistics base for the product in advance based on the product demand information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-140273 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in a medical equipment rental system that rents out medical equipment, a situation occurs in which inventory is insufficient when the demand for rental of medical equipment increases suddenly. Therefore, it is desirable to predict the demand for rental of medical equipment in advance so that measures can be taken to secure inventory before inventory shortages occur. Note that the technology described in Patent Document 1 cannot predict the demand for rental of medical equipment in advance, and therefore cannot solve such a problem.

[0005] The present disclosure has been made to solve such problems, and provides a prediction system, a prediction method, a trained model, and a program capable of predicting in advance the demand for medical equipment in a medical equipment rental system, as well as a learning system, a learning method, and a program capable of generating such a trained model. [Means for solving the problem]

[0006] The prediction system according to the present disclosure is a prediction system for predicting demand for medical equipment in a medical equipment rental system, which uses learning data including rental record data showing the rental record of the medical equipment and electronic medical record data describing information indicating the need for use of the rented medical equipment, stores a trained model that has been machine-learned to input the electronic medical record data describing the information indicating the need for use of the medical equipment and output a demand prediction result that is a prediction result of the demand for the medical equipment, inputs the electronic medical record data describing the information indicating the need for use of the medical equipment into the trained model to obtain the demand prediction result, inputs an inventory prediction result that is a prediction result of the inventory of the medical equipment predicted based on the current inventory and reservation information, compares the obtained demand prediction result with the input inventory prediction result, and notifies the medical equipment rental system if the demand exceeds the inventory. With this configuration, the prediction system can predict the demand for medical equipment in the medical equipment rental system in advance, and can take measures to secure inventory before inventory shortage occurs.

[0007] The medical equipment rental system may include a reservation system for tentatively reserving rental of the medical equipment, and the rental record data may include data in which information indicating the medical equipment tentatively reserved in the reservation system is associated with information indicating actual rental based on the tentative reservation. In this way, the prediction system can predict the demand for the medical equipment in the medical equipment rental system in advance, while also dealing with tentative reservations in the medical equipment rental system.

[0008] The electronic medical record data may include information indicating that a medical staff member has decided to use the medical device, so that the prediction system can more accurately predict the demand for the medical device in advance, taking into account the track record of the medical staff member's decision to use the medical device.

[0009] The rental record data may include information indicating the end time of use or the return time of the medical device, so that the prediction system can predict the demand for the medical device more accurately in advance, taking into account the end time of actual use or the return time of the medical device.

[0010] The prediction method according to the present disclosure is a prediction method in which a computer predicts the demand for medical equipment in a medical equipment rental system, the computer uses learning data including rental record data showing the rental record of the medical equipment and electronic medical record data describing information indicating the need for use of the rented medical equipment to input the electronic medical record data describing the need for use of the medical equipment and stores a trained model that has been machine-learned to output a demand forecast result that is a forecast result of the demand for the medical equipment, the computer inputs the electronic medical record data describing the information indicating the need for use of the medical equipment into the trained model to obtain the demand forecast result, the computer inputs an inventory forecast result that is a forecast result of the inventory of the medical equipment predicted based on the current inventory and reservation information, the computer compares the acquired demand forecast result with the input inventory forecast result, and if the demand exceeds the inventory, notifies the medical equipment rental system. In the prediction method, the demand for medical equipment in the medical equipment rental system can be predicted in advance by such processing, and measures can be taken to secure inventory before inventory shortage occurs.

[0011] The medical equipment rental system may include a reservation system for tentatively reserving rental of the medical equipment, and the rental record data may include data in which information indicating the medical equipment tentatively reserved in the reservation system is associated with information indicating actual rental based on the tentative reservation. In this way, the prediction system can predict the demand for the medical equipment in the medical equipment rental system in advance, while also dealing with tentative reservations in the medical equipment rental system.

[0012] The electronic medical record data may include information indicating that a medical staff member has decided to use the medical device, so that the prediction system can more accurately predict the demand for the medical device in advance, taking into account the track record of the medical staff member's decision to use the medical device.

[0013] The rental record data may include information indicating the end time of use or the return time of the medical device, so that the prediction system can predict the demand for the medical device more accurately in advance, taking into account the end time of actual use or the return time of the medical device.

[0014] The program according to the present disclosure is a program for making a computer execute a prediction process for predicting the demand for medical equipment in a medical equipment rental system, the prediction process using learning data including rental record data showing the rental record of the medical equipment and electronic medical record data describing information indicating the necessity of using the rented medical equipment, inputting the electronic medical record data describing information indicating the necessity of using the medical equipment and storing a trained model that has been machine-learned to output a demand prediction result that is a prediction result of the demand for the medical equipment, inputting the electronic medical record data describing information indicating the necessity of using the medical equipment into the trained model to obtain the demand prediction result, inputting an inventory prediction result that is a prediction result of the inventory of the medical equipment predicted based on the current inventory and reservation information, comparing the obtained demand prediction result with the input inventory prediction result, and notifying the medical equipment rental system if the demand exceeds the inventory. In the above program, the demand for medical equipment in the medical equipment rental system can be predicted in advance by such processing, and measures can be taken to secure inventory before inventory shortage occurs.

[0015] The medical equipment rental system may include a reservation system for tentatively reserving rental of the medical equipment, and the rental record data may include data in which information indicating the medical equipment tentatively reserved in the reservation system is associated with information indicating actual rental based on the tentative reservation. In this way, the prediction system can predict the demand for the medical equipment in the medical equipment rental system in advance, while also dealing with tentative reservations in the medical equipment rental system.

[0016] The electronic medical record data may include information indicating that a medical staff member has decided to use the medical device, so that the prediction system can more accurately predict the demand for the medical device in advance, taking into account the track record of the medical staff member's decision to use the medical device.

[0017] The rental record data may include information indicating the end time of use or the return time of the medical device, so that the prediction system can predict the demand for the medical device more accurately in advance, taking into account the end time of actual use or the return time of the medical device.

[0018] The trained model according to the present disclosure is a trained model that is machine-learned to use training data including rental record data showing the rental record of medical equipment managed in a medical equipment rental system and electronic medical record data describing information indicating the necessity of use of the rented medical equipment, input the electronic medical record data describing information indicating the necessity of use of the medical equipment, and output a demand forecast result that is a forecast result of demand for the medical equipment. With such a configuration, the trained model makes it possible to predict in advance the demand for medical equipment in the medical equipment rental system.

[0019] The learning system according to the present disclosure inputs learning data, including rental record data showing the rental record of medical equipment managed in the medical equipment rental system and electronic medical record data describing information indicating the necessity of using the rented medical equipment, into an untrained learning model and executes machine learning to generate a trained model that inputs electronic medical record data describing information indicating the necessity of using the medical equipment and outputs a demand forecast result that is a forecast result of demand for the medical equipment. With such a configuration, the above learning system makes it possible to generate a trained model that can predict in advance the demand for medical equipment in the medical equipment rental system.

[0020] The learning method according to the present disclosure inputs learning data, including rental record data showing the rental record of medical equipment managed in a medical equipment rental system and electronic medical record data describing information indicating the necessity of using the rented medical equipment, into an untrained learning model and executes machine learning to generate a trained model that inputs electronic medical record data describing information indicating the necessity of using the medical equipment and outputs a demand forecast result that is a forecast result of demand for the medical equipment. In the above learning method, such processing makes it possible to generate a trained model that can predict in advance the demand for medical equipment in the medical equipment rental system.

[0021] The program according to the present disclosure is a program for causing a computer to execute a learning process in which learning data including rental record data indicating the rental record of medical equipment managed in a medical equipment rental system and electronic medical record data describing information indicating the necessity of using the rented medical equipment is input into an untrained learning model, and machine learning is executed to generate a trained model that inputs the electronic medical record data describing information indicating the necessity of using the medical equipment and outputs a demand forecast result that is a forecast result of demand for the medical equipment. With the above program, such processing makes it possible to generate a trained model that can predict in advance the demand for medical equipment in the medical equipment rental system. Effect of the Invention

[0022] According to the present disclosure, it is possible to provide a prediction system, a prediction method, a trained model, and a program capable of predicting in advance the demand for medical equipment in a medical equipment rental system, as well as a learning system, a learning method, and a program capable of generating such a trained model. [Brief description of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram for explaining an example of the overall configuration of a transportation system including a prediction system and an equipment rental system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a control block diagram illustrating an example of a transport system according to the present embodiment. [Diagram 3] 3 is a control block diagram showing an example of the equipment rental system of FIG. 2. [Figure 4] FIG. 3 is a control block diagram showing an example of the electronic medical record system of FIG. 2. [Diagram 5] 5 is a table showing an example of electronic medical record information stored in the electronic medical record system of FIG. 4. [Figure 6] 4 is a table showing an example of equipment rental information and provisional reservation information stored in the equipment rental system of FIG. 3. [Figure 7] 3 is a table showing an example of transported goods information stored in the upper level management device of FIG. 2. [Figure 8] FIG. 2 is a diagram showing an example of a movement path of a mobile robot. [Figure 9] FIG. 11 is a diagram showing another example of the movement path of the mobile robot. [Figure 10] 3 is a schematic diagram for explaining an example of a demand forecasting process in the upper level management device of FIG. 2; [Figure 11] FIG. 11 is a diagram showing an example of a demand forecast result outputted in the demand forecast process of FIG. [Figure 12] 2 is a flowchart showing a demand forecasting method according to the present embodiment. [Figure 13] A block diagram showing an example configuration of a learning system that generates a trained model used in the upper management device of Figure 2. [Figure 14] FIG. 14 is a schematic diagram showing an example of a trained model generated by the learning system of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] The present invention will be described below through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are necessarily essential as means for solving the problems.

[0025] <Embodiment> (Schematic configuration) The prediction system according to the present embodiment is a system for predicting demand for medical equipment in a medical equipment rental system, and predicts demand using a trained model. The trained model, the details of which will be described later, is a model that has been machine-learned to input electronic medical record data and output a demand prediction result using training data including rental record data and electronic medical record data.

[0026] The prediction system inputs electronic medical record data into the trained model to obtain a demand forecast result, and also inputs an inventory forecast result, which is a forecast result of the medical equipment inventory predicted based on the current inventory and reservation information. The reservation system compares the obtained demand forecast result with the input inventory forecast result, and if demand exceeds inventory, notifies the medical equipment rental system.

[0027] With this configuration, this prediction system can predict the demand for medical equipment in the medical equipment rental system in advance, and measures can be taken to secure inventory before inventory shortages occur.

[0028] First, an example of a transport system using a mobile robot into which the prediction system according to the present embodiment can be incorporated will be described. FIG. 1 is a conceptual diagram for explaining an example of the overall configuration of a transport system 1 including the prediction system and the equipment rental system according to the present embodiment. The transport system 1 according to the present embodiment is a system that transports an object using a mobile robot capable of autonomous movement. As the mobile robot, a mobile robot 20 as shown in FIG. 1 will be taken as an example for explanation, but the configuration and shape of the mobile robot 20 are not limited thereto.

[0029] The transport system 1 includes, in addition to the mobile robot 20, a host management device 10, a medical equipment rental system (hereinafter, equipment rental system) 30, an electronic medical record system 40, a network 600, a communication unit 610, and a user terminal 400.

[0030] The mobile robot 20 is a transport robot that performs the task of transporting an object. The mobile robot 20 travels autonomously to transport an object in a medical and welfare facility such as a hospital, a rehabilitation center, a nursing home, or an elderly person's home. The mobile robot 20 can be a mobile robot that moves autonomously by referring to a map. The mobile robot 20 can also be a mobile robot that moves autonomously in a preset area such as a part or whole area of ​​the above-mentioned map or an area indicated by latitude and longitude. However, the mobile robot 20 can be configured to be capable of autonomous movement while sensing the surroundings, for example, even outside a preset area, or even outside the entire area included in the map, or even in a form in which the movement range is not set.

[0031] A user U1, such as a user or assistant user of the transported item, or a manager of the transported item, requests the mobile robot 20 to transport the transported item. When making the transport request, the user U1 stores the transported item in the mobile robot 20 at the requested location, or at the recipient (transport origin) included in the transport request information. Of course, the storage of the transported item can also be performed by a storage robot or the like. Note that a mobile robot that carries and transports the transported item in an exposed state can also be used, but for the sake of simplicity of explanation, it is assumed that the transported item is stored in the mobile robot 20 and transported.

[0032] In this embodiment, it is sufficient that the mobile robot 20 is capable of transporting equipment to be lent as the transported object (hereinafter, lent equipment). However, the mobile robot 20 may also transport equipment other than the lent equipment or transported objects other than equipment, such as medicines, consumables such as packets, specimens, hospital food, stationery, and other supplies.

[0033] The user U1 can request the delivery of the rental equipment according to the rental schedule (rental schedule). As will be described later, this rental schedule can be managed by the equipment rental system 30, and can be referred to by the user U1 from the user terminal 400 for the transportation request, and can also be referred to by the upper management device 10.

[0034] The mobile robot 20 autonomously moves to the set destination and transports the rental equipment. That is, the mobile robot 20 executes a luggage transport task (hereinafter, simply called a task). In the following description, the location where the rental equipment is loaded is referred to as the transport origin, and the location where the rental equipment is delivered is referred to as the transport destination.

[0035] For example, the mobile robot 20 moves within a general hospital with multiple medical departments. The mobile robot 20 transports rental equipment between multiple medical departments. For example, the mobile robot 20 delivers the rental equipment from a nurse's station in one medical department to a nurse's station in another medical department. Alternatively, the mobile robot 20 delivers the rental equipment from its storage to the nurse's station in the medical department. In addition, when the destination is on a different floor, the mobile robot 20 may move using an elevator or the like.

[0036] Examples of loaned equipment include medical equipment such as testing equipment and medical instruments. Examples of medical equipment include bedsore prevention devices, blood pressure monitors, blood transfusion pumps, syringe pumps, and other drip equipment, foot pumps, nurse call devices, bed exit sensors, foot pumps, low-pressure continuous inhalers, electrocardiogram monitors, drug infusion controllers, enteral nutrition pumps, artificial ventilators, cuff pressure gauges, touch sensors, aspirators, nebulizers, pulse oximeters, blood pressure monitors, artificial resuscitators, sterilization devices, and echo devices. In addition to the above, other examples of medical equipment include various drip equipment and various vital monitors. Note that, for example, blood transfusion pumps with different flow rates may be loaned, and multiple models of each type of medical equipment may be loaned.

[0037] Some of the rental devices are provided with a stand. Examples of rental devices with stands include low pressure continuous suction devices, echo machines, electrocardiogram monitors (transmitters), electrocardiogram monitors (central monitors), electrocardiogram monitors (bedside monitors), artificial ventilators, and nebulizers. Many of the rental devices with stands are operated by connecting to a commercial power source rather than a battery, and compared to rental devices without stands, they are often stored in rental warehouses.

[0038] In addition, the above-mentioned rental devices do not require sterilization of the main body, or in many cases only a part of the device needs to be disinfected, and some rental devices can be equipped with disposable tools. Catheters, scalpels, scissors, etc. that require sterilization can also be handled as rental devices in this embodiment if the storage location and the place where sterilization is performed are the same or close to each other.

[0039] In this embodiment, as shown in FIG. 1, the equipment rental system 30, the electronic medical record system 40, the mobile robot 20, and the user terminal 400 are connected to the host management device 10 via a network 600. The mobile robot 20 and the user terminal 400 are connected to the network 600 via a communication unit 610. The network 600 is a wired or wireless LAN (Local Area Network) or WAN (Wide Area Network). Furthermore, the host management device 10 is connected to the network 600 by wire or wireless. The communication unit 610 is, for example, a wireless LAN unit installed in each environment. The communication unit 610 may be, for example, a general-purpose communication device such as a WiFi router.

[0040] The user terminal 400 is, for example, a tablet computer or a smartphone, but may also be a stationary computer. The user terminal 400 may be any information processing device capable of wireless or wired communication.

[0041] User U1 or user U2 can make a transport request using the user terminal 400. For example, user U1 can access the equipment rental system 30 from the user terminal 400 to refer to the schedule for the transport request (maybe via the host management device 10), and can make a transport request for the rental equipment to the host management device 10 based on the results of the reference. The host management device 10, which has received this transport request, can make a transport request to the mobile robot 20.

[0042] In this way, various signals transmitted from the user terminals 400 of the users U1 and U2 are first sent to the host management device 10 via the network 600, and then transferred from the host management device 10 to the target mobile robot 20. Similarly, various signals transmitted from the mobile robot 20 are first sent to the host management device 10 via the network 600, and then transferred from the host management device 10 to the target user terminal 400.

[0043] The host management device 10 is a server connected to each device and collects data from each device. The host management device 10 is not limited to a single physical device, and may include multiple devices that perform distributed processing. The host management device 10 may be distributed and disposed in edge devices such as mobile robots 20. For example, a part or the whole of the transport system 1 may be mounted on the mobile robot 20.

[0044] The equipment lending system 30 is a system that manages a lending schedule (management information) that indicates the lending date and time and the lending destination (usage location, user, etc.) for each piece of lending equipment. The equipment lending system 30 can be a server connected to the upper management device 10, and exchanges data with the upper management device 10. This allows the upper management device 10 to obtain the lending schedule of the lending equipment managed by the equipment lending system 30. The equipment lending system 30 may be distributed and disposed in the upper management device 10, or may be incorporated and disposed in the upper management device 10.

[0045] The electronic medical record system 40 is a system that stores and manages electronic medical record data including information about patients (also called patient information). For example, when a medical professional such as a doctor or a nurse inputs patient information using a user terminal 400, the patient information is stored in the memory of the electronic medical record system 40. Furthermore, the medical professional can view and update the patient information stored in the electronic medical record system 40 through the user terminal 400.

[0046] The electronic medical record system 40 can be a server connected to the host management device 10, and exchanges data with the host management device 10. This allows the host management device 10 to obtain electronic medical record data managed by the electronic medical record system 40. The electronic medical record system 40 can be distributed to the host management device 10, or can be incorporated into the host management device 10.

[0047] The upper level management device 10 can also be configured to read out medical conditions, surgery schedules, etc. from the electronic medical record data registered in the electronic medical record system 40, determine the equipment required for those data, and register the loan of loaned equipment and other accessories, etc. in the equipment loan system 30.

[0048] The user terminal 400 and the mobile robot 20 may transmit and receive signals without going through the higher level management device 10. For example, the user terminal 400 and the mobile robot 20 may transmit and receive signals directly by wireless communication. Alternatively, the user terminal 400 and the mobile robot 20 may transmit and receive signals via the communication unit 610.

[0049] User U1 or user U2 requests the transport of rental equipment using user terminal 400. In the following explanation, it is assumed that user U1 is the transport requester at the transport origin and user U2 is the intended recipient at the transport destination (destination). Of course, user U2 at the transport destination can also make the transport request. Also, a user at a location other than the transport origin or transport destination may make the transport request.

[0050] When user U1 makes a transportation request, he / she uses user terminal 400 to input the details of the loaned equipment, the recipient of the loaned equipment (hereinafter also referred to as the source of transportation), the delivery destination of the loaned equipment (hereinafter also referred to as the destination of transportation), the estimated time of arrival at the source of transportation (time of receipt of the loaned equipment), the estimated time of arrival at the destination of transportation (delivery deadline), etc. Hereinafter, this information is also referred to as transportation request information. In the case of loaned equipment that is the subject of transportation in this embodiment, the source of transportation may be the storage location (equipment management location) of the loaned equipment. The source of transportation may be the location where user U1 is located. The destination of transportation is the location where user U2 who is scheduled to use the equipment or the patient is located. User U1 can input transportation request information by operating the touch panel of user terminal 400.

[0051] Of the transport request information, the rental equipment can be specified by utilizing the rental schedule registered in the equipment rental system 30. For example, a user U1 specifies a rental equipment from the user terminal 400, loads it on the mobile robot 20 as necessary, and makes a transport request to the upper management device 10. The upper management device 10 that receives the transport request refers to the equipment rental system 30, determines a transport schedule so as to arrive in time for the start of use indicated in the rental schedule of the rental equipment, and makes a transport request to the mobile robot 20, so that the equipment is transported according to the transport schedule.

[0052] Alternatively, the user U1 makes a transport request from the user terminal 400 while referring to the lending schedule, the upper management device 10 determines a transport schedule by referring to the lending schedule, and makes a transport request to the mobile robot 20, so that transport is performed according to the transport schedule. In addition to these, various transport request methods can be adopted.

[0053] These examples are based on the premise that a transport request is made after a lending schedule is registered based on a lending request (a request for lending registration). On the other hand, lending equipment may be suddenly required, in which case a lending schedule for the required time for that lending equipment is not registered. In such a case, the user U1 can also send a transport request to the upper management device 10 from the user terminal 400. Based on this transport request, the upper management device 10 refers to the equipment lending system 30 to check whether there is an overlap in the lending period, and if there is no problem, registers it in the lending schedule and requests the mobile robot 20 to transport it. In this case, the loading of the lending equipment onto the mobile robot 20 can be performed, for example, before or after the transport request is sent from the user terminal 400.

[0054] In either case, as described above, the user terminal 400 can transmit the transport request information input by the user U1 to the host management device 10. The host management device 10 is a management system that manages a plurality of mobile robots 20, and transmits operation commands to each mobile robot 20 to execute the transport task. At this time, the host management device 10 determines the mobile robot 20 that will execute the transport task for each transport request. Then, the host management device 10 transmits a control signal including the operation command to the mobile robot 20. The mobile robot 20 moves from the transport source to the transport destination in accordance with the operation command.

[0055] For example, the host management device 10 assigns a transport task to a mobile robot 20 at or near the transport origin. Alternatively, the host management device 10 assigns a transport task to a mobile robot 20 heading toward the transport origin or its vicinity. The mobile robot 20 to which the task is assigned goes to the transport origin to pick up the rental equipment. The transport origin may be, for example, a storage location or a location where the user U1 who requested the task is located.

[0056] When the mobile robot 20 arrives at the destination, the user U1 or another staff member loads the rental equipment onto the mobile robot 20. The mobile robot 20 equipped with the rental equipment moves autonomously to the destination. The upper management device 10 transmits a signal to the user terminal 400 of the user U2 at the destination. This allows the user U2 to know that the rental equipment is being transported and the estimated arrival time. When the mobile robot 20 arrives at the set destination, the user U2 can receive the rental equipment stored in the mobile robot 20. In this manner, the mobile robot 20 executes the transport task.

[0057] In the overall configuration described above, the elements of the transport system can be distributed to the mobile robot 20, the user terminal 400, the equipment rental system 30, the electronic medical record system 40, and the host management device 10 to construct the transport system as a whole. Also, the substantial elements required to transport the rental equipment can be gathered in one device. The host management device 10 controls one or more mobile robots 20.

[0058] (Control system of transport system 1) Fig. 2 is a control block diagram showing an example of a control system of the transport system 1. As shown in Fig. 2, the transport system 1 can include a host management device 10, a mobile robot 20, an equipment rental system 30, an electronic medical record system 40, and an environmental camera 300.

[0059] The transport system 1 efficiently controls a plurality of mobile robots 20 while autonomously moving the mobile robots 20 within a given facility. For this purpose, a plurality of environmental cameras 300 are installed within the facility. For example, the environmental cameras 300 are installed in passageways, halls, elevators, entrances, etc. within the facility.

[0060] The environmental camera 300 captures images of the range in which the mobile robot 20 moves. In the transport system 1, the images captured by the environmental camera 300 and information based on the images are collected by the host management device 10. Alternatively, the images captured by the environmental camera 300 may be directly transmitted to the mobile robot. The environmental camera 300 may be a surveillance camera installed in a passageway or an entrance / exit in a facility. The environmental camera 300 may be used to obtain the distribution of congestion in the facility.

[0061] In the transportation system 1, the host management device 10 performs route planning based on transportation request information and generates route planning information. The route planning information can be generated as information that plans a transportation route corresponding to the above-mentioned transportation schedule. The host management device 10 instructs each mobile robot 20 on a destination based on the generated route planning information. Then, the mobile robot 20 moves autonomously toward the destination specified by the host management device 10. The mobile robot 20 moves autonomously toward the destination (destination) using sensors, floor maps, position information, etc. provided on the mobile robot.

[0062] For example, the mobile robot 20 runs so as not to come into contact with surrounding equipment, objects, walls, and people (hereinafter collectively referred to as surrounding objects). Specifically, the mobile robot 20 detects the distance to the surrounding objects, and runs while being at a certain distance (referred to as the distance threshold) or more away from the surrounding objects. When the distance to the surrounding object becomes equal to or less than the distance threshold, the mobile robot 20 slows down or stops. In this way, the mobile robot 20 can run without coming into contact with surrounding objects. As contact can be avoided, safe and efficient transportation becomes possible.

[0063] The upper management device 10 may include a calculation processing unit 11, a storage unit 12, a buffer memory 13, and a communication unit 14. The calculation processing unit 11 performs calculations for controlling and managing the mobile robot 20. The calculation processing unit 11 may be implemented as a device capable of executing a program, such as a central processing unit (CPU) of a computer. Various functions may also be realized by a program. Although only the demand forecast processing unit 110, the robot control unit 111, and the route planning unit 115, which are characteristic of the calculation processing unit 11, are shown in FIG. 2, other processing blocks may also be included.

[0064] The demand forecasting processing unit 110 inputs electronic medical record data containing information indicating the need for use of medical equipment into the trained model 120 stored in the memory unit 12, and obtains from the trained model 120 a demand forecast result, which is a forecast result of the demand for medical equipment after a specified period of time has elapsed (e.g., a specified date and time) or at the start date and time of use.

[0065] Here, information indicating the need for use of a medical device can refer to information indicating the medical device itself, information indicating the surgery required for the patient, information indicating the patient's symptoms, information indicating treatment for the patient, etc., or a combination of multiple of these pieces of information.

[0066] The demand forecast processing unit 110 also inputs an inventory forecast result, which is a forecast result of the inventory of the medical device after a predetermined period has elapsed or at the start date and time of use, which is forecast based on the current inventory and reservation information. Here, the demand forecast processing unit 110 may acquire the inventory forecast result using a trained model for inventory forecast (inventory estimation) not shown, or may receive an inventory forecast result from the equipment rental system 30, for example, where such a prediction has been made on the equipment rental system 30 side. The demand forecast result and the inventory forecast result can be obtained for each medical device.

[0067] The demand forecast processing unit 110 then compares the acquired demand forecast result with the input inventory forecast result, and if the demand after a predetermined period of time or at the start date and time of use exceeds the inventory, notifies the equipment rental system 30 via the communication unit 14. The notification content can include the fact that the demand exceeds the inventory, the medical equipment in question, the date and time when the demand will exceed the inventory, etc.

[0068] The robot control unit 111 performs calculations for remotely controlling the mobile robot 20 and generates a control signal. The robot control unit 111 generates the control signal based on route planning information 125, which will be described later, and the like. Furthermore, the control signal is generated based on various information obtained from the environmental camera 300 and the mobile robot 20. The control signal may include update information such as a floor map 121, robot information 123, and robot control parameters 122, which will be described later. In other words, when various information is updated, the robot control unit 111 generates a control signal according to the update information.

[0069] The route planning unit 115 plans a route for each mobile robot 20. When a transport task is input, the route planning unit 115 plans a route for transporting the rental equipment to a transport destination (destination) based on the transport request information. Specifically, the route planning unit 115 refers to route planning information 125 and robot information 123 already stored in the storage unit 12, and determines the mobile robot 20 that will execute the new transport task.

[0070] The starting point is the current location of the mobile robot 20, the destination of the previous transport task, the receiving destination of the rental equipment, etc. The destination is the destination of the rental equipment, but may be a waiting place, a charging place, etc. Here, the route planning unit 115 sets the passing points from the starting point of the mobile robot 20 to the destination. The route planning unit 115 sets the passing order of the passing points for each mobile robot 20. The passing points are set, for example, at branching points, intersections, lobbies in front of elevators, and the surrounding areas. In addition, in narrow passages, it may be difficult for the mobile robots 20 to pass each other. In such cases, a passing point may be set just before the narrow passage. Candidates for the passing points may be registered in the floor map 121 in advance.

[0071] The route planning unit 115 determines which mobile robot 20 will perform each transport task from among the multiple mobile robots 20 so that the tasks can be executed efficiently as a whole system. The route planning unit 115 preferentially assigns transport tasks to mobile robots 20 that are on standby or that are close to the transport source.

[0072] The route planning unit 115 sets pass points including a starting point and a destination point for the mobile robot 20 to which a transport task is assigned. For example, when there are two or more moving routes from the transport origin to the transport destination, the pass points are set so that the robot can travel in a shorter time. For this reason, the upper level management device 10 updates information indicating the congestion status of the passageway based on camera images, etc. Specifically, places where other mobile robots 20 are passing through and places with many people are highly crowded. Therefore, the route planning unit 115 sets pass points so as to avoid places with high congestion.

[0073] There are cases where the mobile robot 20 can move to the destination via either a left-handed or a right-handed movement route. In such cases, the route planning unit 115 sets a passing point so that the mobile robot 20 passes through the less congested movement route. By the route planning unit 115 setting one or more passing points on the way to the destination, the mobile robot 20 can move along a less congested movement route. For example, when the passageways are divided at a branch point or an intersection, the route planning unit 115 appropriately sets passing points at the branch point, intersection, corner, and their surroundings. This can improve the efficiency of transportation.

[0074] The route planning unit 115 may set the passing points in consideration of the congestion status of the elevators, the moving distance, and the like. Furthermore, the upper management device 10 may estimate the number of mobile robots 20 and the number of people at the scheduled time when the mobile robots 20 pass a certain location. Then, the route planning unit 115 may set the passing points according to the estimated congestion status. Furthermore, the route planning unit 115 may dynamically change the passing points according to the change in the congestion status. The route planning unit 115 sets the passing points in order for the mobile robots 20 to which the transportation task is assigned. The passing points may include the transportation origin and the transportation destination. As will be described later, the mobile robot 20 moves autonomously so as to pass through the passing points set by the route planning unit 115 in order.

[0075] The memory unit 12 is a memory unit that stores information necessary for managing and controlling the mobile robot 20, etc. In the example of Fig. 2, a trained model 120, a floor map 121, robot information 123, robot control parameters 122, route planning information 125, and transported item information 126 are shown, but other information may be stored in the memory unit 12. The calculation processing unit 11 performs calculations using the information stored in the memory unit 12 when performing various processes. In addition, the various information stored in the memory unit 12 can be updated to the latest information.

[0076] The trained model 120 is a learning model that has been machine-learned using learning data including rental record data indicating the rental record of the medical device and electronic medical record data describing information indicating the necessity of using the rented medical device. The trained model 120 is machine-learned to input electronic medical record data describing information indicating the necessity of using the medical device, and output a demand forecast result that is a forecast result of the demand for the medical device after a predetermined period has elapsed or at the time of the start of use. In other words, the trained model 120 is a model that is made up of an algorithm that predicts the demand forecast result from the electronic medical record data. The algorithm, etc., are not important as long as such a prediction is possible. The trained model 120 can be updated at a predetermined timing when operation progresses and data is accumulated.

[0077] Here, the rental record data is data showing the rental record of the medical equipment to be managed by the equipment rental system 30, and can be managed in the storage unit (storage unit 32 described later) of the equipment rental system 30. The end of the use of the medical equipment can be obtained, for example, based on an input from the user terminal 400 by the user U2, and the same applies to the start of the use of the medical equipment. In either case of the end of use or the start of use, the user terminal 400 can transmit the input result to the equipment rental system 30 directly or via the upper management device 10 via the network 600, and record it as rental record data together with the date and time. However, the start and end of the use of the medical equipment can be obtained by other methods as well. For example, if the medical equipment is an equipment that receives power from an outlet, the start and end of use of the medical equipment can be determined from the power consumption detected by a sensor or the like attached to the outlet at the rental location (use location), and the determination result can be transmitted to the equipment rental system 30 directly or via the upper management device 10 via the network 600, and recorded as rental record data together with the date and time. Alternatively, by performing communication between the medical device and a predetermined location as a lending location, it is possible to determine that the use of the medical device has started or ended by the approach or separation between the medical device and the predetermined location, respectively, and transmit the determination result to the device lending system 30 directly or via the upper management device 10 via the network 600, and record it as lending record data together with the date and time. The communication here can be realized, for example, by using a beacon that emits radio waves such as Bluetooth (registered trademark) or Bluetooth Low Energy (registered trademark) and a device that detects the radio waves, or by using an RFID (Radio Frequency IDentification) tag such as an NFC (Near field communication) tag and a tag reader. Note that either the medical device or the predetermined location may be the transmitting side or the receiving side, and the medical device may have such a communication function built in or may have an external device equipped with such a communication function.

[0078] The floor map 121 is map information of the facility in which the mobile robot 20 moves. This floor map 121 may be created in advance, may be generated from information obtained from the mobile robot 20, or may be a basic map created in advance to which map correction information generated from information obtained from the mobile robot 20 has been added.

[0079] The robot information 123 describes the ID, model number, specifications, etc. of the mobile robot 20 managed by the upper management device 10. The robot information 123 may include position information indicating the current position of the mobile robot 20. The robot information 123 may include information indicating whether the mobile robot 20 is executing a task or is waiting. The robot information 123 may also include information indicating whether the mobile robot 20 is in operation or out of order. The robot information 123 may also include information on rental equipment that can be transported and rental equipment that cannot be transported.

[0080] The robot control parameters 122 describe control parameters such as a threshold distance between the mobile robot 20 managed by the upper management device 10 and a surrounding object. The threshold distance is a margin distance for avoiding contact with a surrounding object including a person. Furthermore, the robot control parameters 122 may include information on the strength of the operation of the mobile robot 20, such as an upper limit of the moving speed of the mobile robot 20.

[0081] The robot control parameters 122 may be updated depending on the situation. The robot control parameters 122 may include information indicating the availability and usage of the storage space in the mobile robot 20. The robot control parameters 122 may include information on the rental equipment that can be transported and the rental equipment that cannot be transported. Of course, the robot control parameters 122 may also include information indicating whether or not it is possible to transport an item other than the rental equipment. The robot control parameters 122 associate the above various information with each mobile robot 20.

[0082] The route planning information 125 includes route planning information planned by the route planning unit 115. The route planning information 125 includes, for example, information indicating a transportation task. The route planning information 125 may include information such as an ID of the mobile robot 20 to which the task is assigned, a starting point, details of the rental equipment, a transportation destination, a transportation origin, an expected arrival time at the transportation destination, an expected arrival time at the transportation origin, and an arrival deadline. In the route planning information 125, the above-mentioned various information may be associated with each transportation task. The route planning information 125 may include at least a part of transportation request information input by a user U1 or the like.

[0083] Furthermore, the route planning information 125 may include information on pass points for each mobile robot 20 and each transport task. For example, the route planning information 125 includes information indicating the order of passing through pass points for each mobile robot 20. The route planning information 125 may include the coordinates of each pass point on the floor map 121 and information on whether or not the pass point has been passed.

[0084] The transported item information 126 is information about the rental equipment for which a transport request has been made. For example, it includes information such as the details (type) of the rental equipment, the origin of transport, and the destination of transport. Of course, the transported item information 126 may include information about items other than the rental equipment, and the same applies to items other than the transported item information 126 below. The transported item information 126 may include the ID of the mobile robot 20 in charge of transport. Furthermore, the transported item information 126 may include information indicating the status, such as being transported, before transport (before loading), and already transported. The transported item information 126 is associated with this information for each rental equipment. The transported item information 126 will be described later.

[0085] The route planning unit 115 formulates a route plan by referring to various information stored in the storage unit 12. The route planning unit 115 determines the mobile robot 20 that executes the task based on, for example, the floor map 121, the robot information 123, the robot control parameters 122, and the route planning information 125. The route planning unit 115 then sets pass points to the destination and the order of pass points by referring to the floor map 121 and the like. Candidates for pass points are registered in the floor map 121 in advance. The route planning unit 115 then sets the pass points according to the congestion situation and the like. In addition, when tasks are processed continuously, the route planning unit 115 may set the source and destination as pass points.

[0086] Also, two or more mobile robots 20 may be assigned to one transport task. For example, if the rental equipment is larger than the transportable capacity of the mobile robot 20, one rental equipment is divided into two pieces and mounted on two mobile robots 20. Alternatively, if the rental equipment is heavier than the transportable weight of the mobile robot 20, one rental equipment is divided into two pieces and mounted on two mobile robots 20. In this way, one transport task can be shared and executed by two or more mobile robots 20. Of course, when controlling mobile robots 20 of different sizes, route planning may be performed so that a mobile robot 20 capable of transporting the rental equipment receives the rental equipment.

[0087] Furthermore, one mobile robot 20 may perform two or more transport tasks in parallel. For example, one mobile robot 20 may simultaneously carry two or more rental devices and transport them sequentially to different destinations. Alternatively, one mobile robot 20 may carry one rental device while transporting another rental device. Furthermore, the destinations of the rental devices carried at different locations may be the same or different. In this way, tasks can be executed efficiently.

[0088] In such a case, the accommodation information indicating the usage status or availability of the accommodation space of the mobile robot 20 may be updated. That is, the upper management device 10 may manage the accommodation information indicating the availability and control the mobile robot 20. For example, when the loading or receiving of the rental equipment is completed, the accommodation information is updated. When the transport task is input, the upper management device 10 refers to the accommodation information and directs the mobile robot 20 that has the availability to load the rental equipment to the receiving location. In this way, it becomes possible for one mobile robot 20 to simultaneously execute multiple transport tasks, or for two or more mobile robots 20 to share and execute the transport task. For example, a sensor may be installed in the accommodation space of the mobile robot 20 to detect the availability. In addition, the capacity and weight of each rental equipment may be registered in advance.

[0089] The buffer memory 13 is a memory that accumulates intermediate information generated in the processing in the arithmetic processing unit 11. The communication unit 14 is a communication interface for communicating with a plurality of environmental cameras 300 and at least one mobile robot 20 provided in the facility where the transport system 1 is operated. The communication unit 14 can perform both wired and wireless communication. For example, the communication unit 14 transmits a control signal required for controlling each mobile robot 20 to each mobile robot 20 based on an instruction from the arithmetic processing unit 11. The communication unit 14 can also receive information collected by the mobile robot 20 and the environmental camera 300 and pass it to the arithmetic processing unit 11. The communication unit 14 can also receive information such as a rental schedule from the equipment rental system 30 and pass it to the arithmetic processing unit 11, or transmit information such as a rental schedule to the equipment rental system 30 for registration based on an instruction from the arithmetic processing unit 11. The communication unit 14 can also receive electronic medical record information from the electronic medical record system 40 and pass it to the arithmetic processing unit 11.

[0090] The mobile robot 20 may include a processor 21, a memory unit 22, a communication unit 23, a proximity sensor (e.g., a distance sensor group 24), a camera 25, a drive unit 26, a display unit 27, and an operation reception unit 28. Note that, although Fig. 2 shows only representative processing blocks included in the mobile robot 20, the mobile robot 20 also includes many other processing blocks that are not shown.

[0091] The communication unit 23 is a communication interface for communicating with the communication unit 14 of the higher-level management device 10. The communication unit 23 communicates with the communication unit 14 using, for example, wireless signals. The distance sensor group 24 is, for example, a proximity sensor, and outputs nearby object distance information indicating the distance to an object or person present around the mobile robot 20. The distance sensor group 24 may include, for example, a front-rear distance sensor and a left-right distance sensor, and may measure the distance to a surrounding object in the front-rear direction and the distance to a surrounding object in the left-right direction of the mobile robot 20.

[0092] The camera 25, for example, captures images for grasping the surroundings of the mobile robot 20. The camera 25, for example, captures an image of the area ahead in the traveling direction of the mobile robot 20. The camera 25 can also capture an image of a position marker provided on the ceiling of a facility, for example. The position marker may be used to allow the mobile robot 20 to grasp its own position.

[0093] The driving unit 26 drives the driving wheels provided on the mobile robot 20. The driving unit 26 may include an encoder that detects the number of rotations of the driving wheels or the driving motor. The mobile robot's own position (current position) may be estimated according to the output of the encoder. The mobile robot 20 detects its own current position and transmits it to the upper management device 10.

[0094] The display unit 27 and the operation reception unit 28 are realized by a touch panel display. The display unit 27 displays a user interface screen that serves as the operation reception unit 28. The display unit 27 may also display information indicating the destination of the mobile robot 20 and the state of the mobile robot 20. The operation reception unit 28 receives operations from the user. The operation reception unit 28 includes the user interface screen displayed on the display unit 27, as well as various switches provided on the mobile robot 20.

[0095] The arithmetic processing unit 21 performs calculations used to control the mobile robot 20. The arithmetic processing unit 21 can be implemented as a device capable of executing programs, such as a central processing unit (CPU) of a computer. Various functions can also be realized by the programs. The arithmetic processing unit 21 includes a movement command extraction unit 211 and a drive control unit 212. Note that while FIG. 2 shows only representative processing blocks included in the arithmetic processing unit 21, processing blocks not shown in the figure are also included. The arithmetic processing unit 21 may search for a route between passing points.

[0096] The movement command extraction unit 211 extracts a movement command from a control signal provided by the upper management device 10. For example, the movement command includes information on the next passing point. For example, the control signal may include coordinates of the passing point and information on the order of passing through the passing point. Then, the movement command extraction unit 211 extracts this information as a movement command.

[0097] Furthermore, the movement command may include information indicating that movement to the next passing point is now possible. If the passage width is narrow, the mobile robots 20 may not be able to pass each other. Also, there may be cases where the passage cannot be passed temporarily. In such cases, the control signal includes a command to stop the mobile robot 20 at a passing point just before the place where it should stop. Then, after another mobile robot 20 has passed or is able to pass, the upper management device 10 outputs a control signal to notify the mobile robot 20 that it is now able to move. This causes the mobile robot 20, which had been temporarily stopped, to resume movement.

[0098] The drive control unit 212 controls the drive unit 26 to move the mobile robot 20 based on the movement command given from the movement command extraction unit 211. For example, the drive unit 26 has a drive wheel that rotates according to a control command value from the drive control unit 212. The movement command extraction unit 211 extracts a movement command so that the mobile robot 20 moves toward the passing point received from the upper management device 10. Then, the drive unit 26 rotates and drives the drive wheel. The mobile robot 20 moves autonomously toward the next passing point. In this way, the mobile robot 20 passes through the passing points in order and arrives at the transport destination. In addition, the mobile robot 20 may estimate its own position and transmit a signal indicating that it has passed the passing point to the upper management device 10. This allows the upper management device 10 to manage the current position and transport status of each mobile robot 20.

[0099] Here, the drive control unit 212 can identify its own position and recognize surrounding objects by analyzing image data output by the camera 25 and detection signals output by the distance sensor group 24. Then, the drive control unit 212 can control the drive unit 26 to move the mobile robot 20 based on the result of the analysis and the above-mentioned movement command. At this time, the drive control unit 212 can recognize surrounding objects and identify its own position by referring to the floor map 221 and the robot control parameters 222.

[0100] The storage unit 22 stores a floor map 221, robot control parameters 222, and transported item information 226. Although FIG. 2 shows only a part of the information stored in the storage unit 22, the information stored in the storage unit 22 includes information other than the floor map 221, robot control parameters 222, and transported item information 226 shown in FIG. 2. The floor map 221 is map information of a facility in which the mobile robot 20 is moved. This floor map 221 is, for example, data obtained by downloading a part or the whole of the floor map 121 of the upper management device 10. The floor map 221 may be one that has been created in advance. The floor map 221 may be map information that partially includes an area to be moved, rather than map information of the entire facility.

[0101] The robot control parameters 222 are parameters for operating the mobile robot 20. The robot control parameters 222 include, for example, a distance threshold to a surrounding object. Furthermore, the robot control parameters 222 include an upper limit of the speed of the mobile robot 20.

[0102] The transported item information 226 includes information about the rental equipment, similar to the transported item information 126. It may include information about the rental equipment (type, i.e., model), the origin, and the destination. The transported item information 226 may include information indicating the status, such as being transported, before being transported (before being mounted), and already transported. The transported item information 226 is associated with this information for each rental equipment. The transported item information 226 only needs to include information about the rental equipment transported by the mobile robot 20. Therefore, the transported item information 226 becomes a part of the transported item information 126. In other words, the transported item information 226 does not need to include information about equipment transported by other mobile robots 20. The transported item information 126 will be described later.

[0103] The drive control unit 212 refers to the robot control parameters 222 and stops or decelerates the operation in response to the distance indicated by the distance information obtained from the distance sensor group 24 falling below the distance threshold. The drive control unit 212 controls the drive unit 26 so that the mobile robot 20 travels at a speed equal to or lower than the upper speed limit. The drive control unit 212 limits the rotation speed of the drive wheels so that the mobile robot 20 does not travel at a speed equal to or higher than the upper speed limit.

[0104] FIG. 3 is a control block diagram showing an example of an equipment rental system 30 in the transportation system 1 of FIG. 2. As shown in FIG. 3, the equipment rental system 30 can include a calculation processing unit 31, a storage unit 32, a buffer memory 33, and a communication unit 34. The calculation processing unit 31 performs calculations for generating and managing a schedule for rental equipment. The calculation processing unit 31 can be implemented as a device capable of executing a program, such as a central processing unit (CPU) of a computer. Various functions can also be realized by a program. In FIG. 3, only a registration unit 311 and a rental planning unit 312, which are characteristic of the calculation processing unit 31, are shown, but other processing blocks can also be included.

[0105] The registration unit 311 receives rental request information including the ID of the rental device, the start time of use, the end time of use, and the location of use, transmitted from the user terminal 400 in accordance with an operation by the user U1, via the communication unit 34, and accepts the registration.

[0106] The registration unit 311 also receives, via the communication unit 34, rental provisional reservation information including the ID of the rental device, the start time of use, the end time of use, and the location of use, for the rental device to be provisionally reserved, which is transmitted from the user terminal 400 in accordance with, for example, an operation by user U1, and accepts the provisional registration. The registration unit 311 also accepts, via the communication unit 34, a formal rental request or a cancellation request for the accepted provisional registration, which is transmitted from the user terminal 400 in accordance with, for example, an operation by user U1. However, this function of making a provisional reservation is not essential.

[0107] Based on the lending request information accepted by the registration unit 311, the lending planning unit 312 refers to the equipment lending information 324 indicating the already planned lending schedule, the provisional reservation information 325 indicating the already provisionally reserved lending schedule, and other lending request information and lending provisional reservation information requested at the same time, and also considers the cancellation request requested at the same time, and confirms that there is no overlap. Of course, in determining whether there is an overlap, if there is no other individual of the same type of medical equipment that is the lending target, it is processed as not overlapping. If there is no overlap, the lending planning unit 312 generates a lending schedule for the lending equipment based on the accepted lending request information and updates the equipment lending information 324. Note that, if the lending request information accepted by the registration unit 311 is information that overlaps in time with an existing lending schedule or the like (overlaps considering the transport time), the lending planning unit 312 makes the following reply. That is, the lending planning unit 312 returns a notification of the overlap to the sender of the lending request information (the user terminal 400 or the higher-level management device 10) via the communication unit .

[0108] The lending planning unit 312 also checks for overlaps with the lending tentative reservation information received by the registration unit 311, in the same way as with the lending request information, by referring to the lending schedule already planned based on the lending tentative reservation information. If there are no overlaps, the lending planning unit 312 generates a lending schedule for the lending equipment based on the received lending tentative reservation information, and updates the tentative reservation information 325. Note that the equipment lending information 324 and the tentative reservation information 325 can share information by using a flag indicating whether the reservation is an official lending or tentative reservation, or by adding a status indicating that the reservation is tentative.

[0109] Furthermore, in response to a formal request for provisional registration received by the registration unit 311, the lending planning unit 312 performs formal registration by moving the target information from the provisional reservation information 325 to the equipment lending information 324. In response to a cancellation request for provisional registration received by the registration unit 311, the lending planning unit 312 deletes the provisional reservation by deleting the target information from the provisional reservation information 325. As exemplified above by the registration unit 311 and the lending planning unit 312, the equipment lending system 30 can be provided with a reservation system that provisionally reserves the lending of medical equipment.

[0110] The memory unit 32 is a memory unit that stores information necessary for managing the rental of rental equipment and controlling the equipment rental system 30. In the example of Fig. 3, a floor map 321, mechanic information 322, equipment information 323, equipment rental information 324, and tentative reservation information 325 are shown, but information other than these may be stored in the memory unit 32. The calculation processing unit 31 performs calculations using the information stored in the memory unit 32 when performing various processes. In addition, the various information stored in the memory unit 32 can be updated to the latest information.

[0111] The equipment information 323 is information indicating the ID, model (product number), size, weight, etc. of the rental equipment, and includes information indicating whether the equipment is on loan or not (i.e., inventory information indicating the stock status), and may also include information indicating the time required for maintenance and the storage location. At least a part of the equipment information 323 necessary for transportation or all of the equipment information 323 can be registered in the upper management device 10 as part of the transport item information 126. Among these, the inventory information may not be included as part of the equipment information 323, or may be included as part of the equipment information 323 instead or in addition to being included as part of the equipment information 323 and as part of the equipment rental information 324.

[0112] The maintenance person information 322 is information associated with each rental device indicated by the device information 323, and can include information indicating the maintenance person who will maintain each rental device (such as the maintenance person's own ID or information indicating the type of maintenance person) and information indicating the notification destination for each maintenance person. There are cases where maintenance is performed before the next rental after the end of rental, and the maintenance person information 322 can be stored in order to notify the maintenance person for this maintenance. The calculation processing unit 11 can refer to the maintenance person information 322 and notify the maintenance person via the communication unit 14 when the medical device requiring maintenance is transported to the storage location after use. However, this notification can also be executed by the mobile robot 20. Such a notification allows the maintenance person to go to the storage location to which the rented medical device is transported as necessary for maintenance. Then, at the storage location, a maintenance person such as the user U2, for example, performs maintenance such as inspection, cleaning, and replacement of consumables in preparation for the next use as necessary. In addition, maintenance technicians include clinical laboratory technicians, radiological technologists, occupational therapists, physiotherapists, clinical engineers, doctors, nurses, licensed practical nurses, and also engineers from the manufacturers of the rental equipment.

[0113] The floor map 321 may be a part or the whole of the floor map 121. As described above, the equipment rental information 324 is information indicating a rental schedule for each rental equipment generated by the rental planning unit 312, and the provisional reservation information 325 is information indicating a provisional reservation for the rental equipment. The equipment rental information 324 and the provisional reservation information 325 will be described later.

[0114] The buffer memory 33 is a memory that accumulates intermediate information generated in the processing in the arithmetic processing unit 31. The communication unit 34 is a communication interface for communicating with the upper management device 10, and this communication interface can also be configured to communicate with the user terminal 400, the mobile robot 20, and the electronic medical record system 40. The communication unit 34 can perform both wired and wireless communication. For example, the communication unit 34 can receive information such as loan request information and loan tentative reservation information from the upper management device 10 or the user terminal 400 and pass it to the arithmetic processing unit 31, and can transmit information such as a loan schedule to the upper management device 10 based on an instruction from the arithmetic processing unit 31.

[0115] The communication unit 34 can also receive electronic medical record information from the electronic medical record system 40 and pass it to the arithmetic processing unit 31. In this case, the registration unit 311 of the arithmetic processing unit 31 can determine whether or not lending of medical equipment is necessary for surgery or other treatment based on the received electronic medical record information, and if necessary, generate lending request information or lending tentative reservation information for the medical equipment and pass it to the lending plan unit 312.

[0116] Here, when the electronic medical record information includes information directly indicating a medical device that needs to be lent out, the registration unit 311 can generate lending request information or lending provisional reservation information for generating the equipment lending information 324 from the electronic medical record information. On the other hand, when the registration unit 311 does not include information directly indicating such a medical device, the registration unit 311 can select a medical device corresponding to a symptom name or the like according to a predetermined rule and generate lending request information or lending provisional reservation information. In addition, the registration unit 311 can determine whether to generate lending request information or lending provisional reservation information according to a predetermined rule, and can generate lending provisional reservation information if the period until treatment is a predetermined period or more in the future, such as one month or one week, and can generate lending request information in other cases. Alternatively, the registration unit 311 can generate lending request information for medical devices related to a confirmed treatment, and can generate lending provisional reservation information in other cases.

[0117] The lending plan unit 312 registers equipment lending information 324 or provisional reservation information 325 based on the lending request information or provisional lending reservation information received in this manner.

[0118] Alternatively, the communication unit 34 can receive medical equipment rental request information, rental tentative reservation information, and the like based on electronic medical record information from the electronic medical record system 40, and pass them to the calculation processing unit 31. In this case, the registration unit 311 of the calculation processing unit 31 accepts the received rental request information or rental tentative reservation information, and registers equipment rental information 324 or tentative reservation information 325 based on the information accepted by the rental planning unit 312.

[0119] However, as in the example given in accordance with the operation by the user U1, registration by the registration unit 311 can be executed by a doctor, nurse, or the like determining the necessity and performing the operation.

[0120] FIG. 4 is a control block diagram showing an example of the electronic medical record system 40 of FIG. 2. As shown in FIG. 4, the electronic medical record system 40 can include a calculation processing unit 41, a storage unit 42, a buffer memory 43, and a communication unit 44. The calculation processing unit 41 performs calculations for generating and managing electronic medical record data. The calculation processing unit 41 can be implemented as a device capable of executing a program, such as a central processing unit (CPU) of a computer. Various functions can also be realized by a program. In FIG. 4, only a characteristic registration unit 411 is shown in the calculation processing unit 41, but other processing blocks can also be included.

[0121] The registration unit 411 receives chart registration request information including the patient's ID, symptoms, treatment (including surgery), treatment schedule, treatment location, etc., transmitted from the user terminal 400 in response to an operation by the user U1, via the communication unit 44, accepts the registration, and stores it as electronic chart information 420 in the storage unit 42. The chart registration request information can also include the patient's name, chart ID, the need for hospitalization and the schedule, and in the case of surgery, staff such as the surgeon or staff team.

[0122] The storage unit 42 is a storage unit that stores electronic medical record information 420 to be managed by the electronic medical record system 40 and other information necessary for controlling the electronic medical record system 40. In the example of Fig. 4, electronic medical record information 420 is shown, but other information may be stored in the storage unit 42. When performing various processes, the calculation processing unit 41 performs calculations using the other information stored in the storage unit 42. In addition, the various information stored in the storage unit 42 can be updated to the latest information.

[0123] The electronic medical record information 420 may include information requested to be registered as medical record registration request information. In addition, for example, the medical record ID and the patient ID of the electronic medical record information 420 may be automatically assigned according to a predetermined rule such as a sequential number. The electronic medical record information 420 will be described later.

[0124] The buffer memory 43 is a memory that accumulates intermediate information generated in the processing in the arithmetic processing unit 41. The communication unit 44 is a communication interface for communicating with the upper management device 10, and this communication interface can also be configured to communicate with the user terminal 400, the mobile robot 20, and the equipment rental system 30. The communication unit 44 can perform both wired and wireless communication. The communication unit 44 can receive medical record registration request information from the upper management device 10 or the user terminal 400 and pass it to the arithmetic processing unit 41, and can transmit electronic medical record information 420 to the upper management device 10 based on an instruction from the arithmetic processing unit 41.

[0125] In addition, the communication unit 44 can also transmit, for example, electronic medical record information 420, or medical equipment rental request information, rental tentative reservation information, etc. based on the electronic medical record information 420 to the equipment rental system 30 based on the instruction from the calculation processing unit 41. In the latter case, the calculation processing unit 41 refers to the electronic medical record information 420, judges whether or not rental of medical equipment is necessary for surgery or other treatment, and if necessary, passes an instruction to the communication unit 44 to transmit rental request information or rental tentative reservation information of medical equipment. Here, when the calculation processing unit 41 instructs, if the electronic medical record information 420 contains information directly indicating the medical equipment that needs to be rented, it can generate rental request information or rental tentative reservation information for generating equipment rental information 324 from the electronic medical record information 420. On the other hand, if the calculation processing unit 41 does not contain information directly indicating such medical equipment, it can select medical equipment corresponding to the symptom name, etc. according to a predetermined rule and generate rental request information or rental tentative reservation information.

[0126] The arithmetic processing unit 41 can also determine whether to generate loan request information or tentative loan reservation information according to a predetermined rule, and can generate loan tentative reservation information when the period until treatment is more than a predetermined period, such as one month or one week, and can generate loan request information in other cases. Alternatively, the arithmetic processing unit 41 can generate loan request information for medical equipment related to a confirmed treatment, and can generate loan tentative reservation information in other cases.

[0127] (Electronic Medical Record Information 420) Fig. 5 is a table showing an example of electronic medical record information 420 stored in the electronic medical record system 40 of Fig. 4. As described above, the electronic medical record information 420 can include information requested to be registered as medical record registration request information. For example, the electronic medical record information 420 can include a medical record ID, a patient ID, a patient name, symptoms, treatment (including surgery, medication, etc.), the date of the treatment, the location of the treatment, the necessity and date of hospitalization, the person scheduled to perform the treatment, etc. The electronic medical record information 420 can also include information indicating a prognosis, that is, information indicating the progress of symptoms after treatment.

[0128] Here, the symptoms may include a disease name (disease name), an image showing the location of the disease, and the like. In addition, in the case of surgery, the person scheduled to treat may be a staff member such as a surgeon or a team of staff members. In addition, in FIG. 5, the person scheduled to treat is exemplified as users U1 and U2 who perform the registration operation of the electronic medical record information 420, that is, as a person scheduled to use who arranges transportation and collection. However, for the sake of simplicity of explanation, the person scheduled to treat may be a person different from the person scheduled to use, and the person who performs the registration operation of the electronic medical record information 420 may not be the person scheduled to use or the person scheduled to treat. In addition, in the example of the table in FIG. 5, a link indicating the storage location of the file showing this image is described. Not limited to the example in FIG. 5, the electronic medical record information 420 may include information that should be included in a normal medical record. Furthermore, the electronic medical record information 420 may also include information directly indicating a medical device when a medical device is required for surgery or other treatment.

[0129] (Equipment rental information 324, provisional reservation information 325, and delivery item information 126) An example of processing of the transport system 1 according to the present embodiment will be described below by taking as an example a case where the information shown in Fig. 6 is stored as the equipment rental information 324 and the provisional reservation information 325. Fig. 6 is a table showing an example of the equipment rental information 324 and the provisional reservation information 325, and Fig. 7 is a table showing an example of the transported item information 126. Figs. 8 and 9 are diagrams showing examples of the movement route of a mobile robot.

[0130] As illustrated in Fig. 6, the equipment rental information 324 and the provisional reservation information 325 can include the ID (equipment management number) of the rental equipment, the name, whether maintenance is required, the type of maintenance person (or the maintenance person), the destination (place of use), the intended user, the start time of use, and the end time of use, as well as information indicating whether the equipment is officially rented or provisionally reserved. As illustrated in Fig. 6, this information can be linked by the rental management number and managed as a table. The equipment rental information 324 and the provisional reservation information 325 can be distinguished by the information indicating whether the equipment is officially rented or provisionally reserved.

[0131] The destination indicates the delivery destination (place of use) of the loaned equipment, and can be extracted from the loan request information along with the start and end times of use. The intended user indicates the person who will use the loaned equipment. For example, the intended user can be the name or ID of a patient, or the name and ID of a staff member such as a nurse or doctor. Of course, the intended user may include information on both patients and staff. The information on the need for maintenance and the type of mechanic (or mechanic) can be information indicating whether or not the loaned equipment requires maintenance (in this example, required or optional), and information indicating the type of mechanic who will perform maintenance (or information indicating the ID and name of the mechanic).

[0132] As described above, the equipment rental information 324 and the provisional reservation information 325 are generated based on the rental request information and the rental provisional reservation information, respectively, but at this time, they are generated by also referring to the equipment information 323 and the mechanic information 322. Note that the information on the mechanic type or the mechanic in the mechanic information 322 and the equipment rental information 324 is required when notifying the mechanic, and is therefore not necessary in an example in which notification is not performed.

[0133] The transported item information 126 may include the equipment management number, the name, whether maintenance is required, the type of maintenance person (or maintenance person) indicating the notification destination, the transport origin, the transport destination, the intended user, the robot ID of the person in charge of transport, the status, the start time of use, and the end time of use, as exemplified in Fig. 7. The transported item information 126 does not include information equivalent to the tentative reservation information 325. These pieces of information may be linked by the transport management number and managed as a table, as exemplified in Fig. 7.

[0134] The source of transport indicates the location where the mobile robot 20 will load the rental equipment. The destination of transport indicates the delivery location (location of use) of the rental equipment. Note that, although an example is given in which there is one storage location from which the rental equipment is transported, it goes without saying that the number of storage locations is not limited to one, and the number of destination locations is not limited to two. The intended user indicates the person who will use the rental equipment. For example, the intended user is the name or ID of a patient. Alternatively, the intended user may be the name or ID of a staff member such as a nurse or doctor. Of course, the intended user may include information on both the patient and the staff member.

[0135] As described above, the transport item information 126 is generated based on the transport request information. Therefore, the transport item information 126 can be generated based on information including the equipment rental information 324 (and information on other transport items) and the mobile robot 20 determined based on the equipment rental information 324 while taking into consideration the efficiency of task execution. The robot ID is the ID of the mobile robot 20 in charge of transporting the rental equipment. The robot ID is set based on a route plan that takes into consideration the efficiency of task execution. The status is information indicating whether the rental equipment is before transportation, during transportation, or already transported. The status is updated when the mobile robot 20 loads the rental equipment and when receipt of the rental equipment is completed.

[0136] The transported item information 126 is then transmitted to each mobile robot 20 in charge of transporting the rental equipment. For example, the transported item information 226 of a mobile robot 20 includes information on the rental equipment that the mobile robot 20 is responsible for transporting. In other words, the transported item information of the rental equipment with the robot ID "BBB" does not need to be transmitted to the mobile robot 20 with the robot ID "AAA".

[0137] The transportation of the rental device E001 in Fig. 6 and Fig. 7 will be described with reference to Fig. 8 and Fig. 9. Note that in Fig. 6 and Fig. 7, for convenience, the time is displayed as the current day, but in reality, the device is managed by date and time (year, month, date and time). For example, some devices may be rented out for several days or several months. Since the transportation usually starts from the storage location 800 (S001), Fig. 7 shows an example in which such a route is set. Also, the route itself is determined by the route planning unit 115 as described above, and is set in the corresponding mobile robot 20.

[0138] For the transport management number 001, as shown in FIG. 8, the mobile robot 20 (robot ID: AAA) first moves from pass point M1, which indicates the current time, toward pass point M2, which is the storage location 800 of the rental device E001. After that, the mobile robot 20 receives the rental device E001 at the storage location 800, and then moves through pass points M3 and M4 in order, taking route R to the destination G001 (M5). At the destination G001, the intended user U001 will receive the rental device E001. After that, the mobile robot 20 can move as necessary for other tasks.

[0139] The rental device E001 will be used at the delivery destination G001 until the end of use at 15:30. After that, the rental device E001 will be returned, but since the rental device E001 is a device that requires maintenance, the return destination can be, for example, the storage location 800. Rental devices that do not require maintenance or that require optional maintenance can be delivered to the next delivery destination and used.

[0140] When returning the rental device E001, another mobile robot 20 (for example, robot ID: BBB) can be used. In this case, as illustrated by route R in FIG. 9, the mobile robot 20 moves from a passing point M1 indicating the current time toward a usage location G001 of the rental device E001, and receives the rental device E001 at the usage location G001. At the usage location G001, a user such as a prospective user U001 loads the rental device E001 onto the mobile robot 20. After receiving the rental device E001, the mobile robot 20 returns it to the storage location 800. After that, the mobile robot 20 can move as necessary for other tasks. The same applies to the transportation and return of the rental device E002 and other rental devices in FIGS. 6 and 7.

[0141] (Demand forecasting process according to this embodiment) An example of the demand forecasting process of the present embodiment in the above-mentioned transportation system 1 will be described with reference to Fig. 10 and Fig. 11. Fig. 10 is a schematic diagram for explaining an example of the demand forecasting process in the upper level management device 10 in Fig. 2, and Fig. 11 is a diagram showing an example of the demand forecasting result outputted in the demand forecasting process in Fig. 10.

[0142] In the transportation system 1 of this embodiment, as described above, the electronic medical record information 420 is stored (registered) in the electronic medical record system 40, and information on some or all of the items of the electronic medical record information 420 can be transmitted to the host management device 10 or obtained from the host management device 10.

[0143] As described above, in the transport system 1 according to the present embodiment, management information including the rental schedule (including the start time and end time of use), the location of use, and the inventory status is stored (registered) for each of the rental equipment transported as a transported item by the mobile robot 20. This management information can be stored in the memory unit 32 of the equipment rental system 30 as part or all of the equipment rental information 324 and the tentative reservation information 325, and can also be stored in the memory unit 12 of the upper management device 10 as part or all of the transported item information 126.

[0144] As shown in Fig. 10, the demand forecast processing unit 110 inputs electronic medical record data such as electronic medical record information 420 to the trained model 120 stored in the storage unit 12, and obtains a demand forecast result, which is a forecast result of demand for medical equipment after a predetermined period of time has elapsed (e.g., a specified date and time) or at the start date and time of use, from the trained model 120. Fig. 10 shows an example in which a forecast demand (A) at time (t) is obtained as the demand forecast result.

[0145] Here, the input electronic medical record data is assumed to describe information indicating the necessity of using a medical device, and this information can refer to information indicating an operation required for a patient, information indicating a patient's symptoms, information indicating treatment for a patient, information indicating a medical device itself, or a combination of a plurality of these pieces of information. Therefore, when information indicating the necessity of using a medical device is implicitly or directly described in the electronic medical record information 420 as exemplified in the process of Fig. 5, the input electronic medical record data corresponds to the data of the electronic medical record information 420 itself, or data of the electronic medical record information 420 including the description.

[0146] However, the electronic medical record data input to the demand forecast processing unit 110 for prediction can be the current electronic medical record data, that is, the data excluding information about medical equipment that has been returned after loan has ended from the electronic medical record information 420.

[0147] The information predicted by the demand forecast processing unit 110 as the predicted demand (A) at time (t) can include, for example, information indicating the predicted use date and time and the number of units to be used for the necessary medical equipment for each patient, as shown for a certain patient α in FIG. 11. Of course, the information predicted as the predicted demand (A) is not limited to this, and may be information indicating the patient ID or patient name, the number of units, and the predicted use time for each medical equipment. In either case, the demand forecast result and the inventory forecast result described later can be obtained for each medical equipment. In addition, the type of information predicted as the predicted demand (A) can be changed by changing the settings of the output parameters when generating the trained model 120, or by performing a predetermined process such as summarizing data for each patient on the output results from the trained model 120.

[0148] Here, the trained model 120 is a model trained by machine learning by inputting training data, which is past data, into the untrained model 120a as illustrated in FIG. 10, as will be described later with reference to FIG. 13 and FIG. 14. Specifically, as described as the processing in the demand forecast processing unit 110, the trained model 120 is a model trained by machine learning using the above-mentioned training data to input electronic medical record data in which information indicating the necessity of using medical equipment is described and output demand forecast results. The trained model 120 can be updated by re-learning as needed. Here, the above-mentioned training data is teacher data including rental record data and electronic medical record data, as illustrated in the equipment rental information 324 and the electronic medical record information 420.

[0149] The rental history data included in the learning data may be data showing the rental history of the medical equipment, and may include information on the medical equipment that has been transported in the equipment rental information 324, and may also include information on the medical equipment that is being transported. The rental history data may be, for example, a part or all of the data of the equipment rental information 324. However, since the rental history data is data including information showing the rental history, it may be data consisting only of information in the equipment rental information 324 on which rental or rental and return have been completed. For example, the rental history data may not include a record corresponding to the provisional reservation information 325 (record with rental management number 003 in this example) among the equipment rental information 324 and the provisional reservation information 325 shown in FIG. 6, and the maintenance person type (or maintenance person) is not necessary. Furthermore, the rental history data may not include the planned user, and may not include whether maintenance is required. However, by including the planned user and the need for maintenance, it becomes possible to make a prediction that takes into account the progress or delay of collection, etc., caused by each planned user, and the time when the item cannot be rented out if maintenance is required. The rental record data can also be obtained by separately accumulating information on the completion of rental or rental and return from the transported item information 126.

[0150] However, the rental history data may also include provisional reservation information 325. To be more specific, as described above, the equipment rental system 30 may be equipped with a reservation system for provisionally reserving rental of medical equipment, and in such a configuration, the rental history data may include data in which information indicating medical equipment provisionally reserved in this reservation system (provisional reservation information 325) is associated with information indicating actual rental based on the provisional reservation (equipment rental information 324). This allows the trained model 120 to predict in advance the demand for medical equipment in the equipment rental system 30, in response to provisional reservations in the equipment rental system 30.

[0151] The electronic medical record data included in the learning data contains the same information items as the electronic medical record data input at the time of prediction, but it is not current electronic medical record data but past electronic medical record data that describes information indicating the need to use the loaned medical equipment. Here again, the loaned medical equipment may include not only medical equipment that has already been delivered but also medical equipment that is being delivered.

[0152] As illustrated in FIG. 10, the demand forecast processing unit 110 predicts the stock of the medical device after a predetermined period has elapsed or at the start date and time of use based on the stock information 323a indicating the current stock and the provisional reservation information 325, and obtains the stock forecast result, which is the prediction result. This prediction process can be executed by the stock forecasting unit 110b, for example, which can be provided in the demand forecast processing unit 110 or the equipment rental system 30. FIG. 10 also shows an example in which the predicted stock (B) at time (t) is obtained as the stock forecast result. In this way, the time after the predetermined period has elapsed or the start date and time of use that is the target of the stock forecast is the same as the time after the predetermined period has elapsed or the start date and time of use that was used for the demand forecast. The stock forecast result is a result of estimating the stock, so it can also be called a stock estimation result.

[0153] Here, as described above, the inventory information 323a can be included as information indicating whether or not a medical device is being rented in the equipment information 323 or the equipment rental information 324. The demand prediction processing unit 110 can obtain an inventory prediction result based on the provisional reservation information 325, as well as reservation information including information on medical devices that have not yet been rented out among the equipment rental information 324, that is, information on medical devices before transport, and the inventory information 323a.

[0154] Any specific method for predicting the inventory may be used. For example, the demand prediction processing unit 110 can perform prediction by simply calculating the inventory for each medical device by subtracting the number of items tentatively reserved from the number of items in inventory at time (t) (the number of items originally managed minus the number of items on loan or on loan and in transport) at time (t). Alternatively, the demand prediction processing unit 110 may receive from the equipment rental system 30 an inventory prediction result obtained by performing such a calculation on the equipment rental system 30 side. Alternatively, the demand prediction processing unit 110 may obtain an inventory prediction result by using a trained model for inventory prediction (not shown) for each medical device, or may receive from the equipment rental system 30 an inventory prediction result obtained by performing such a prediction on the equipment rental system 30 side.

[0155] Then, the demand forecast processing unit 110 compares the forecast demand (A) and forecast stock (B) acquired for time (t), and if the demand at time (t) exceeds the stock, that is, if A>B, it determines that there is a possibility that a specific medical device will be in short supply, and notifies the equipment rental system 30 via the communication unit 14. This notification can be executed by a notification processing unit 110c provided in the demand forecast processing unit 110, via the communication unit 14. The notification contents can include the fact that the demand has exceeded the stock, the medical device in question, the date and time of the exceedance, etc.

[0156] The equipment rental system 30 that receives this notification notifies at least one of the administrator and the rental staff. The notification destination may be registered in advance in the storage unit 32 as an e-mail address, a short message number, etc. Note that the equipment rental system may be constructed including these notification destinations, in which case these notification destinations become the notification destinations by the demand forecast processing unit 110.

[0157] With such a configuration, the upper management device 10 can predict the demand for medical equipment in the equipment rental system 30 in advance. This is for the following reasons. That is, the use of medical equipment is determined according to the symptoms and treatment of the patient, so it is possible to predict which medical equipment is likely to be used based on information on treatment and surgery recorded in the electronic medical record information 420, and information on nursing and progress. In addition, since actual use includes cases where it is determined by the judgment of a doctor or nurse, the demand cannot be predicted accurately only based on the information input to the electronic medical record information 420 before the use of the medical equipment. However, the upper management device 10 can predict the demand based on past rental records in addition to the electronic medical record information 420. In order to improve the prediction accuracy at any time, it is recommended to re-learn accumulated data and update the trained model 120.

[0158] The host management device 10, for example, refers to the electronic medical record information 420, and predicts the demand for medical equipment as described above and notifies the patient as necessary for each patient who is hospitalized or scheduled to be hospitalized, and each patient who is undergoing or scheduled to be treated. In fact, if the demand for lending medical equipment cannot be predicted in advance, a sudden increase in demand will cause a shortage of stock, but the host management device 10 according to this embodiment can predict the demand for lending, making it possible to take measures to secure stock before a shortage occurs.

[0159] Next, an example of the flow of the demand forecasting method according to this embodiment will be briefly described with reference to Fig. 12. Fig. 12 is a flowchart showing the demand forecasting method according to this embodiment.

[0160] First, the upper management device 10 acquires the electronic medical record information 420 by receiving it from the electronic medical record system 40, inputs it to the trained model 120, and acquires the demand forecast result (S1001). Next, the upper management device 10 inputs the inventory forecast result by receiving it from the equipment rental system 30 (S1002). The order of steps S1001 and S1002 does not matter, and the electronic medical record information 420 and inventory forecast result input in both steps include information for the same date and time and for the same medical equipment.

[0161] Next, the upper level management device 10 judges whether the demand indicated by the demand forecast result is greater than the stock indicated by the stock forecast result (S1003), and if it is greater (YES in S1003), notifies the equipment rental system 30 (S1004) and ends the process. On the other hand, if NO in step S1003, the upper level management device 10 ends the process as it is. Such a process can be executed for each medical equipment to be rented.

[0162] (Learning System) An example of the configuration of a learning system that generates the above-mentioned trained model and an example of processing in the learning system (an example of a learning method) will be described with reference to Figures 13 and 14. Figure 13 is a block diagram showing an example of the configuration of a learning system that generates a trained model used in the upper management device 10 of Figure 2. Figure 14 is a schematic diagram showing an example of a trained model generated by the learning system 80 of Figure 13. Note that the untrained model has the same configuration as shown in Figure 14, but is a model in which the weight coefficient is not determined.

[0163] 13 may include a control unit 81, an input unit 82, and a storage unit 83. The learning system 80 may be constructed using a computer such as a PC for AI (Artificial Intelligence) learning. However, the learning system 80 may be configured as a single device or may have functions distributed across multiple devices.

[0164] The control unit 81 controls the entire learning system 80. The control unit 81 can be realized, for example, by an integrated circuit, and can be realized, for example, by a processor, a working memory, and a non-volatile storage device. A control program executed by the processor is stored in this storage device, and the processor reads the program into the working memory and executes it, thereby fulfilling the function of the control unit 81. The control program includes a learning program that executes learning. Note that the storage device can also utilize the memory unit 83.

[0165] The input unit 82 can be configured with at least one of an interface for performing data input operations and a communication interface for inputting data from an external device via communication. The input unit 82 inputs a data set of learning data (teacher data) 84 required for learning, and stores it in the storage unit 83 so that it can be referenced during learning. The storage unit 83 can store this teacher data 84, and can store a learning model 85 as an unlearned model.

[0166] In the process performed by the learning system 80, the control unit 81 inputs the teacher data 84 into a learning model 85 as an unlearned model, executes machine learning based on the teacher data 84, and sets the learning model 85 as a trained model 120. The trained model 120 is generated as a machine-learned model that inputs electronic medical record data containing information indicating the need for use of medical equipment as described above and outputs a demand forecast result. With such a configuration, the trained model 120 is capable of predicting the demand for medical equipment in the equipment rental system 30 in advance.

[0167] The learning model 85 may use, for example, a neural network 120n as shown in Fig. 14. The neural network 120n in Fig. 14 may include an input layer 120na, a hidden layer (middle layer) 120nb, and an output layer 120nc, and may include a value corresponding to the output layer 120nc as the correct answer data 120nd. For the sake of simplicity, the middle layer 120nb will be described as one layer, but the middle layer 120nb may include two or more layers.

[0168] The input layer 120na includes input nodes that use explanatory variables x1, x2, x3, ... as input parameters. In the intermediate layer 120nb, a node indicated by a value y1 assigns a weighting coefficient w 1 11 The input parameter x2 is multiplied by the weighting coefficient w 1 21 multiplied by the weighting coefficient w 1 31 In the intermediate layer 120nb, the node indicated by the value y2 inputs the input parameter x1 with a weighting coefficient w 1 12 The input parameter x2 is multiplied by the weighting coefficient w 1 22 multiplied by the weighting coefficient w 1 32 The same applies to the other nodes in the intermediate layer 120nb.

[0169] The output layer 120nc includes output nodes that use the objective variables z1, z2, z3, ... as output parameters. In the output node of the output layer 120nc indicated by the value z1, a weighting coefficient w 2 11 The value y2 multiplied by the weighting factor w 2 21 The sum of these values ​​is calculated and compared with the value t1 of the corresponding correct answer data 120nd. In the output layer 120nc, the output node indicated by value z2 is weighted by a weighting coefficient w 2 12 The value y2 multiplied by the weighting factor w2 22 The sum of these is calculated and compared with the value t2 of the corresponding correct answer data 120nd. The same applies to the other output nodes of the output layer 120nc.

[0170] According to such a comparison, each weighting coefficient is calculated so that the comparison result becomes small, and the untrained neural network 120n is generated as the trained model 120. That is, when the performance is given as the correct answer data 120nd, the control unit 81 adjusts each weighting coefficient so as to minimize each error between the values ​​of the output nodes z1, z2, z3, ... of the output layer 120nc and the corresponding values ​​t1, t2, t3, ... of the correct answer data 120nd, and generates the trained model 120 as a result. Note that minimizing each error here can refer to, for example, minimizing the sum of each error or the sum of the squares of each error.

[0171] The teacher data 84 used when generating the trained model 120 can be a data set including electronic medical record data and loan record data as described above. Information of each item included in the electronic medical record data is input as input parameters x1, x2, x3, ..., and information of each item included in the loan record data can be set as values ​​t1, t2, t3, ... of the correct answer data 120nd. When performing the output illustrated in FIG. 11, the value of the correct answer data 120nd can include, for example, information indicating a medical device (for example, information indicating the type of medical device), the number of the medical devices, and a value indicating period information indicating the date and time or period of use, and at the time of prediction (operation), the value of the corresponding node in the output layer 120c indicates the demand forecast result. Also, as described above, the input parameters can include information directly indicating a medical device, but even if they do not include information, it is sufficient that they include information that metaphorically indicates the medical device, such as symptoms and treatment.

[0172] Although a simple example of the electronic medical record data is shown in FIG. 5, more detailed items can be included as shown below. For example, the electronic medical record data can include, as patient information, for example, a patient ID and / or name, age, sex, etc., which identify an individual patient, but can also include some of them. In addition, the electronic medical record data can include, as information on hospitalization among information on treatment, the date and time of admission, the department at the time of admission, the hospitalization ward, the attending physician, the attending nurse, the disease name (disease name), the purpose of hospitalization, the examination date, the examination name, the operation name, the operation date, etc. In addition, the electronic medical record data can include, for example, a medical classification (ADL: Activities of Daily Living), at least one of a nursing care plan and a nursing progress chart, and at least one of a clinical path and a path status. In addition, the electronic medical record data can include information directly indicating the use of medical equipment as described above, and can also include information indicating how many days have passed since a procedure such as surgery, information indicating the severity, information indicating the judgment of a doctor, etc. However, the electronic medical record data is not limited to including all of the above items, and can include only some of them, and further items can be added. In particular, in order to prevent a decrease in prediction accuracy due to spurious correlation, etc., items of information to be included in the electronic medical record data can be added or deleted as appropriate at the discretion of the person constructing the model.

[0173] As shown in FIG. 11, the rental history data may include information such as the type of medical equipment that may be used, the number required, and the expected time of use, but is not limited to this.

[0174] The trained model 120 thus generated is updated by updating the results and setting the updated results as the correct answer data 120nd, thereby adjusting each weighting coefficient so as to minimize the error between the value of the output node of the output layer 120nc and the corresponding results. In other words, the trained model 85 as the trained model 120 can be retrained based on a newly prepared data set when retraining is required.

[0175] Furthermore, the electronic medical record data included in the learning data and the electronic medical record data input when predicting demand can also include information indicating that the medical staff has decided to use the medical device. This allows the demand prediction processing unit 110 to predict the demand for the medical device more accurately in advance, taking into account the track record of the medical staff in deciding to use the medical device.

[0176] The rental history data may also include information indicating the end time of use or return time of the medical device. This information in the rental history data corresponds to the information indicating the end time of treatment in the electronic medical record data. Therefore, the demand prediction processing unit 110 can predict the demand for the medical device more accurately in advance, taking into account the end time of actual use or return time of the medical device.

[0177] In addition, the inventory prediction exemplified by the inventory prediction unit 110b in Fig. 10 can also be executed using a trained model, and in that case, the learning process is different only in terms of the algorithm, teacher data, etc., and a similar learning system can be used. In this case, past inventory prediction data and data showing the actual inventory performance at the corresponding date and time are input as learning data to an untrained model, and machine learning is executed to generate a trained model that outputs an inventory prediction result when current inventory prediction data is input.

[0178] (others) A part or all of the processes in the prediction system, the upper management device 10, the mobile robot 20, the equipment rental system 30, the electronic medical record system 40, the learning system 80, etc. described above can be realized as a computer program. Such a program includes a set of instructions (or software code) for making the computer perform one or more functions described in the embodiments when loaded into a computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disk (DVD), Blu-ray (registered trademark) disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0179] The present disclosure is not limited to the above-described embodiment, and can be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure includes implementation in which the examples in the above-described embodiment are appropriately combined.

[0180] For example, in the above embodiment, a system in which a mobile robot autonomously moves within a hospital has been described, but the above-mentioned transport system can transport items including equipment to be rented in hotels, restaurants, office buildings, event venues, or complexes as luggage, not limited to medical equipment. In other words, the prediction system according to the above embodiment can be used to predict demand for rental equipment other than medical equipment. In addition, the description was given on the premise of transporting equipment within one facility, but as long as the mobile robot is capable of moving between multiple facilities, it can also be applied to transport between multiple facilities. In addition, the above-mentioned transport system is not limited to the case of using the exemplified mobile robot 20, and mobile robots of various configurations can be used instead or in addition to it.

[0181] In addition, the prediction system according to this embodiment can also be applied to cases where medical equipment for loan is transported without using a mobile robot, and cases where other types of equipment for loan is transported without using a mobile robot. [Explanation of symbols]

[0182] 1. Transport system 10 Upper management device 11 Processing unit 12 Storage section 13 Buffer Memory 14 Communications Department 20 Mobile Robot 21 Processing unit 22 Memory section 23 Communications Department 24 Distance Sensor Group 25 Camera 26 Drive unit 27 Display section 28 Operation reception section 30 Equipment Rental System 31 Processing unit 32 Storage section 33 Buffer Memory 34 Communications Department 40 Electronic Medical Record System 41 Processing unit 42 Storage section 43 Buffer Memory 44 Communications Department 110 Demand forecast processing unit 111 Robot control unit 115 Route Planning Department 120 trained models 120a Untrained Model 120n Neural Network 120na input layer 120nb, hidden layer (middle layer) 120nc output layer 120th correct data 121 Floor Map 122 Robot Control Parameters 123 Robot Information 125 Route Planning Information 126 Delivery Information 211 Movement command extraction part 212 Drive control unit 221 Floor Map 222 Robot Control Parameters 226 Delivery Information 311 Registration Department 312 Loan Planning Department 321 Floor Map 322 Maintenance Information 323 Device information 324 Equipment Rental Information 325 Tentative Reservation Information 400 User terminals 411 Registration Department 420 Electronic medical record information 600 Network 610 Communication Unit

Claims

1. A prediction system for predicting demand for medical equipment in a medical equipment rental system, comprising: Using learning data including rental record data indicating the rental record of the medical device and electronic medical record data describing information indicating the necessity of using the rented medical device, a trained model is stored so as to input the electronic medical record data describing information indicating the necessity of using the medical device and output a demand forecast result which is a forecast result of demand for the medical device; The electronic medical record data, in which information indicating the need for use of the medical device is described, is input into the trained model to obtain the demand forecast result; Input an inventory forecast result, which is a forecast result of the inventory of the medical device predicted based on the current inventory and reservation information; comparing the acquired demand forecast result with the input inventory forecast result, and notifying the medical equipment rental system if the demand exceeds the inventory; Prediction system.

2. The medical equipment rental system includes a reservation system for provisionally reserving rental of the medical equipment, The rental record data includes data in which information indicating the medical equipment provisionally reserved in the reservation system is associated with information indicating actual rental based on the provisional reservation. The prediction system of claim 1 .

3. The electronic medical record data includes information indicating that a medical staff member has determined that the medical device is to be used. The prediction system according to claim 1 or 2.

4. The rental history data includes information indicating the end time of use or the return time of the medical device. The prediction system according to claim 1 or 2.

5. A method for predicting demand for medical equipment in a medical equipment rental system, comprising: The computer uses learning data including rental record data indicating the rental record of the medical device and electronic medical record data describing information indicating the necessity of use of the rented medical device, inputs the electronic medical record data describing information indicating the necessity of use of the medical device, and stores a trained model that has been machine-learned to output a demand forecast result that is a forecast result of demand for the medical device; The computer inputs the electronic medical record data, in which information indicating the need for use of the medical device is described, into the trained model to obtain the demand forecast result, The computer inputs an inventory forecast result, which is a forecast result of the inventory of the medical device predicted based on the current inventory and reservation information, The computer compares the acquired demand forecast result with the input inventory forecast result, and if the demand exceeds the inventory, notifies the medical equipment rental system. Forecasting methods.

6. The medical equipment rental system includes a reservation system for provisionally reserving rental of the medical equipment, The rental record data includes data in which information indicating the medical equipment provisionally reserved in the reservation system is associated with information indicating actual rental based on the provisional reservation. The prediction method according to claim 5.

7. The electronic medical record data includes information indicating that a medical staff member has determined that the medical device is to be used. The prediction method according to claim 5 or 6.

8. The rental history data includes information indicating the end time of use or the return time of the medical device. The prediction method according to claim 5 or 6.

9. A program for causing a computer to execute a prediction process for predicting demand for medical equipment in a medical equipment rental system, The prediction process includes: Using learning data including rental record data indicating the rental record of the medical device and electronic medical record data describing information indicating the necessity of using the rented medical device, a trained model is stored so as to input the electronic medical record data describing information indicating the necessity of using the medical device and output a demand forecast result which is a forecast result of demand for the medical device; The electronic medical record data, in which information indicating the need for use of the medical device is described, is input into the trained model to obtain the demand forecast result; Input an inventory forecast result, which is a forecast result of the inventory of the medical device predicted based on the current inventory and reservation information; comparing the acquired demand forecast result with the input inventory forecast result, and notifying the medical equipment rental system if the demand exceeds the inventory; program.

10. The medical equipment rental system includes a reservation system for provisionally reserving rental of the medical equipment, The rental record data includes data in which information indicating the medical equipment provisionally reserved in the reservation system is associated with information indicating actual rental based on the provisional reservation. The program according to claim 9.

11. The electronic medical record data includes information indicating that a medical staff member has determined that the medical device is to be used. The program according to claim 9 or 10.

12. The rental history data includes information indicating the end time of use or the return time of the medical device. The program according to claim 9 or 10.

13. A trained model that has been machine-learned using learning data including rental history data indicating the history of rental of medical equipment managed in a medical equipment rental system and electronic medical record data describing information indicating the need for use of the rented medical equipment, inputting the electronic medical record data describing information indicating the need for use of the medical equipment, and outputting a demand forecast result, which is a forecast result of demand for the medical equipment, to a computer.

14. The learning data includes rental record data showing the rental record of medical equipment managed by the medical equipment rental system and electronic medical record data describing the necessity of using the rented medical equipment, and is input into an untrained learning model to perform machine learning. Generate a trained model that inputs electronic medical record data describing information indicating the need for use of the medical device and outputs a demand forecast result that is a forecast result of demand for the medical device. Learning system.

15. The learning data includes rental record data showing the rental record of medical equipment managed by the medical equipment rental system and electronic medical record data describing the necessity of using the rented medical equipment, and is input into an untrained learning model to perform machine learning. Generate a trained model that inputs electronic medical record data describing information indicating the need for use of the medical device and outputs a demand forecast result that is a forecast result of demand for the medical device. How to learn.

16. On the computer, The learning data includes rental record data showing the rental record of medical equipment managed by the medical equipment rental system and electronic medical record data describing the necessity of using the rented medical equipment, and is input into an untrained learning model to perform machine learning. Generate a trained model that inputs electronic medical record data describing information indicating the need for use of the medical device and outputs a demand forecast result that is a forecast result of demand for the medical device. A program for executing the learning process.

Images