Information processing system, operating method, and computer program for automating basic evaluation of elderly welfare facility

Abstract

A method for operating an information processing system for automating a basic evaluation of a beneficiary of a welfare facility may comprise the steps of: acquiring state data of the beneficiary of the welfare facility; acquiring service provision history for the beneficiary; inputting the state data of the beneficiary and the service provision history to an artificial neural network model; acquiring state change pattern data of the beneficiary output by the artificial neural network model; and generating basic evaluation data on the basis of the state change pattern data.

Description

Information processing system, method of operation, and computer program for automating basic evaluation of elderly welfare facilities

[0001] The present disclosure relates to an information processing system, a method of operation, and a computer program for automating the basic evaluation of recipients of elderly welfare facilities.

[0002] Welfare facilities are places that provide various services to meet the physical, cognitive, and emotional needs of their beneficiaries. These services must be tailored to the individual circumstances of the recipients, and staff members need to respond promptly and accurately to their demands. In particular, the provision of services for the elderly who are physically frail or have experienced cognitive decline often requires detailed adjustments based on individual situations, rather than simply adhering to standardized procedures.

[0003] In this process, staff must systematically provide services according to a given schedule and record the details. However, this process of service provision and recording is not simple. This is because services can change immediately due to changes in the recipient's condition or urgent requests, and corresponding records must be made in real time. This continuous task of service provision and recording can place a significant workload on staff.

[0004] Previously, these service records were primarily managed through manual documentation. However, this method consumed a significant amount of time and effort for staff while failing to guarantee record accuracy. Since staff had to manually record service details every time, a time delay could occur between service provision and recording, increasing the likelihood of important information being omitted or recorded inaccurately. Consequently, there was a risk that the consistency and reliability of service provision within elderly welfare facilities would be compromised.

[0005] While the introduction of computerized systems resolved some issues, limitations still existed in terms of real-time management and data accuracy. In computerized systems, manual work was required during the data entry process, and real-time updates were often difficult. Furthermore, even with the use of computerized systems, the time burden on employees was not reduced because they had to manually input records, and the possibility of errors during data entry remained. These problems could ultimately lead to a decline in the quality of service provision.

[0006] For this reason, the need for a new system for more effective and efficient management is emerging.

[0007] The aforementioned background technology is one that the inventor possessed or acquired in the process of deriving the contents of the disclosure of the present application, and it cannot be considered as prior art disclosed to the general public prior to the filing of this application.

[0008] One objective according to the embodiments of the present disclosure is to provide an information processing system, a method of operation, and a computer program for automating the basic evaluation of a recipient of a welfare facility.

[0009] The objective according to the embodiments of the present disclosure is to provide an information processing system, a method of operation, and a computer program that can improve the reliability and efficiency of a basic assessment by automatically generating a basic assessment suitable for the physical, cognitive, and emotional state of the recipient.

[0010] A method of operation of an information processing system for automating a basic evaluation of a recipient of a welfare facility according to one embodiment may include: a step of acquiring status data of a recipient of the welfare facility; a step of acquiring a history of service provision for the recipient; a step of inputting the status data and the history of service provision of the recipient into an artificial neural network model; a step of acquiring status change pattern data of the recipient output by the artificial neural network model; and a step of generating basic evaluation data based on the status change pattern data.

[0011] In one embodiment, the state data may include data on at least one of the recipient's health status, cognitive function, and emotional state.

[0012] In one embodiment, the state change pattern data may include a short-term pattern and a long-term pattern regarding the state change of the recipient.

[0013] In one embodiment, an artificial neural network model learns the correlation between the state data of the recipient and the service provision history, and can output the short-term pattern and the long-term pattern regarding the change in the recipient's state based on the correlation.

[0014] In one embodiment, the artificial neural network model may include at least one of a Long Short-Term Memory (LSTM) model and a Temporal Convolutional Network (TCN) model.

[0015] In one embodiment, the artificial neural network model may further include a weighting mechanism that assigns weights to specific time zones or specific services related to the service provision history.

[0016] In one embodiment, a customized service provision plan for the recipient can be generated based on the basic evaluation data.

[0017] In one embodiment, the step of generating the customized service provision plan may include: a step of applying classification or regression to the basic evaluation data to grade or quantify the status of the recipient; and a step of generating the customized service provision plan based on the grade or quantification.

[0018] In one embodiment, the artificial neural network module may include the step of obtaining feedback data of the recipient regarding the service provided according to the customized service provision plan; and the step of performing reinforcement learning on the artificial neural network model based on the feedback data.

[0019] In one embodiment, based on the customized service provision plan, the method may further include the step of generating a service provision list for each employee of the welfare facility.

[0020] In one embodiment, each recipient of the welfare facility has a corresponding recipient terminal and each employee has an employee terminal, and the step of obtaining a service provision history for the recipient may include the step of generating a service provision history actually provided to the recipient based on a log generated when one of the recipient terminals and one of the employee terminals approach within a predetermined distance.

[0021] In one embodiment, the step of inputting the recipient's state data and service provision history into an artificial neural network model includes the step of inputting natural language data, including natural language spoken by the recipient, into the artificial neural network model, and the recipient's state change pattern data can be output by the artificial neural network model based on the state data, the service provision history, and the natural language data.

[0022] In one embodiment, the computer program may be stored on a computer-readable recording medium to execute the above-described method of operation on a computer.

[0023] In one embodiment, an information processing system for automating a basic evaluation of a recipient of a welfare facility comprises: a memory; and a processor connected to the memory and configured to execute at least one computer-readable program included in the memory, wherein the at least one program may include instructions for acquiring state data of a recipient of a welfare facility, acquiring a history of service provision to the recipient, inputting the state data and the history of service provision of the recipient into an artificial neural network model, acquiring state change pattern data of the recipient output by the artificial neural network model, and generating basic evaluation data based on the state change pattern data.

[0024] An information processing system, a method of operation, and a computer program for automating the basic evaluation of a welfare facility according to one embodiment can provide effective and reliable basic evaluation data by using an artificial neural network model to acquire data on the state change pattern of a recipient and automatically generating basic evaluation data suitable for the recipient based thereon.

[0025] In addition, an information processing system, a method of operation, and a computer program according to one embodiment can generate a customized service provision plan for each recipient using generated basic evaluation data, and provide services according to the generated customized service provision plan, thereby providing effective services that more accurately reflect the needs of the recipients.

[0026] The effects of the information processing system, operation method, and computer program of the welfare facility according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by a person skilled in the art from the description below.

[0027] The following drawings attached to this specification illustrate preferred embodiments of the present disclosure and serve to further enhance understanding of the technical concept of the present disclosure together with the detailed description of the invention; therefore, the present disclosure should not be interpreted as being limited only to the matters described in such drawings.

[0028] FIG. 1 is a diagram illustrating the overall environment of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0029] FIG. 2 is a hardware configuration diagram of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0030] FIG. 3 is a flowchart of the operation method of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0031] FIG. 4 is a diagram illustrating an exemplary Long Short-Term Memory (LSTM) model applicable to one embodiment of the present disclosure.

[0032] FIG. 5 is a diagram illustrating an exemplary Temporal Convolutional Network (TCN) model applicable to one embodiment of the present disclosure.

[0033] FIG. 6 is a flowchart of an operation method related to the generation of service provision details of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0034] FIG. 7 is a diagram illustrating the service provision history of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0035] FIG. 8 is a flowchart of an operation method related to the generation of service provision details of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0036]

[0037] The various embodiments described in this specification are illustrative for the purpose of clearly explaining the technical concept of this disclosure and are not intended to limit it to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments optionally combined from all or part of each embodiment described in this specification. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0038] Terms used in this specification, including technical or scientific terms, may have the meaning generally understood by those skilled in the art to which this disclosure pertains, unless otherwise defined.

[0039] Expressions used herein such as “comprising,” “may compose,” “possessing,” “possessing,” “having,” and “possessing” imply the existence of the subject feature (e.g., function, operation, or component, etc.) and do not exclude the existence of other additional features. That is, such expressions should be understood as open-ended terms implying the possibility of including a second embodiment.

[0040] In this specification, singular expressions include plural expressions unless the context clearly specifies them as singular. Additionally, plural expressions include singular expressions unless the context clearly specifies them as plural. Throughout the specification, when a part is described as including a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0041] Additionally, the terms 'module' or 'part' as used in the specification refer to software or hardware components, and the 'module' or 'part' performs certain roles. However, the meaning of 'module' or 'part' is not limited to software or hardware. The 'module' or 'part' may be configured to reside in an addressable storage medium or configured to run on one or more processors. Thus, as an example, the 'module' or 'part' may include components such as software components, object-oriented software components, class components, and task components, and at least one of processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. The components and the functions provided within the 'module' or 'part' may be combined into a smaller number of components and 'modules' or 'parts', or further separated into additional components and 'modules' or 'parts'.

[0042] According to one embodiment of the present disclosure, a ‘module’ or ‘part’ may be implemented as a processor and memory. The term ‘processor’ should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the term ‘processor’ may refer to an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. The term ‘processor’ may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a DSP core, or any other combination of such configurations. Additionally, the term ‘memory’ should be broadly interpreted to include any electronic component capable of storing electronic information. 'Memory' may refer to various types of processor-readable media, such as Random Access Memory (RAM), Read-Only Memory (ROM), Non-Volatile Random Access Memory (NVRAM), Programmable Read-Only Memory (PROM), Erasable-Programmable Read-Only Memory (EPROM), Electrically Erasable PROM (EEPROM), Flash Memory, Magnetic or Optical Data Storage Devices, Registers, etc. If a processor can read information from memory and / or write information to memory, the memory is said to be in an electronic communication state with the processor. Memory integrated into a processor is in an electronic communication state with the processor.

[0043] Expressions such as "first," "second," or "first," "second" as used in this specification are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated in the context, and do not limit the order or importance of said objects.

[0044] Expressions used herein such as “A, B, and C,” “A, B, or C,” “A, B, and / or C,” or “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” “at least one selected from A, B, and C,” “at least one selected from A, B, or C,” “at least one selected from A, B, and / or C,” etc., may mean each of the listed items or all possible combinations of the listed items. For example, “at least one selected from A and B” may refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, and (8) all of A and B.

[0045] As used herein, the expression “based on” is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing such expression, and such expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0046] As used in this specification, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the said certain component is not only directly connected or connected to the said other component, but is also connected or connected through a new other component (e.g., a third component).

[0047] As used herein, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." Such expression is not limited to the meaning of "specifically designed in hardware," and, for example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software.

[0048] Various embodiments of the present disclosure will be described below with reference to the accompanying drawings. In the accompanying drawings and the description thereof, identical or substantially equivalent components may be given the same reference numerals. Furthermore, in the description of the various embodiments below, the description of identical or corresponding components may be omitted, but this does not mean that such components are not included in the embodiments.

[0049]

[0050] FIG. 1 is a drawing illustrating the overall environment of an information processing system of a welfare facility according to one embodiment of the present disclosure.

[0051] Referring to FIG. 1, the overall environment of an information processing system of a welfare facility according to one embodiment of the present disclosure may include an information processing system (100), an employee terminal (200), a recipient terminal (250), and a network (400).

[0052] Here, the information processing system of the welfare facility illustrated in FIG. 1 is exemplary, and its components are not limited to the embodiment illustrated in FIG. 1 and may be added, changed, or deleted as needed.

[0053] The welfare facilities described in this specification may include elderly welfare facilities that serve the elderly. However, they are not limited thereto and may be understood as various social welfare facilities and medical service providers.

[0054] In one embodiment, the information processing system (100) may be, for example, a server and may be connected to an employee terminal (200), a recipient terminal (250), and an administrator terminal (300) through a network (400).

[0055] Here, a terminal may refer to any form of entity(s) in a system having a mechanism for communicating with an information processing system (100). For example, such a terminal may include a PC (personal computer), a notebook, a mobile terminal, a smartphone, a tablet PC, and a wearable device, and may include any type of terminal capable of connecting to a wired or wireless network. Additionally, the terminal may include any computing device implemented by at least one of an agent, an API (Application Programming Interface), and a plug-in. Additionally, the terminal (200) may include an application source and / or a client application.

[0056] The employee terminal (200) may include a terminal used by an employee working at a welfare facility. The recipient terminal (250) may include a terminal used by a recipient receiving services at a welfare facility. The administrator terminal (300) may include a terminal used by an administrator managing a welfare facility. The employee terminal (200), the recipient terminal (250), and / or the administrator terminal (300) may be designated in advance or used only by specific users based on authentication, but are not limited thereto.

[0057] Additionally, the network (400) may refer to a connection structure capable of exchanging information between each node, such as multiple terminals and servers. For example, the network (400) may include a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired / wireless data network, a telephone network, a wired / wireless television network, a Controller Area Network (CAN), and Ethernet.

[0058] Wireless data communication networks may include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0059] More specifically, the information processing system (100) can manage data for accident prevention based on accident prevention information of the welfare facility. For example, the information processing system (100) can receive information about a recipient from at least one of an employee terminal (200) and a manager terminal (300).

[0060] The recipient's information is specific information related to the recipient and may include, for example, the recipient's diagnosis, condition, age, medical history, and gender. As another example, the recipient's information may include basic evaluation data including at least one of the recipient's health status, cognitive function, or emotional state. Such basic evaluation data of the recipient may be generated and obtained through surveys and self-reports of the recipient, observational evaluations by staff, physical and health examinations performed by medical professionals, cognitive function tests and psychological tests performed by the recipient, but is not limited thereto; it may also be obtained using an electronic health record system from existing medical records or health records issued by a hospital. For example, the basic evaluation data may be obtained through at least one of a staff terminal (200) and an administrator terminal (300), provided that the present embodiment is not limited by the terminal being verified.

[0061] The information processing system (100) can generate basic evaluation data by performing a basic evaluation of the recipient. The information processing system (100) can establish a customized service provision plan for each recipient using the generated basic evaluation data. The information processing system (100) can provide the customized service provision plan to the employee terminal (200) so that the customized service is provided.

[0062] In one embodiment, the information processing system (100) can obtain status data of a recipient of a welfare facility. For example, the information processing system (100) can obtain status data of a recipient from at least one of an employee terminal (200), a recipient terminal (250), and a manager terminal (300). The recipient's status data is data containing information regarding the recipient's status, and for example, the recipient's status data may include at least one of a physical status (e.g., health status), a cognitive status (e.g., cognitive function), and an emotional status (e.g., emotional status).

[0063] Such status data may be generated and acquired through surveys and self-reports of recipients, observational evaluations by staff, physical and health examinations performed by medical professionals, and cognitive function and psychological tests performed by recipients, but is not limited thereto; existing medical records or health records issued by hospitals may also be acquired through an electronic health record system.

[0064] In one embodiment, the information processing system (100) can obtain a history of service provision to a recipient. The history of service provision to a recipient may include a history of services provided to the recipient by a welfare facility.

[0065] According to one embodiment, service provision details may be stored in advance within a database. In this case, the information processing system (100) may obtain service provision details for a recipient from the database. Refer to FIGS. 6 and FIGS. 7 for details regarding operations stored within the database.

[0066] In one embodiment, the information processing system (100) may input the recipient's state data and service provision history into an artificial neural network model. The artificial neural network model learns the correlation between the recipient's state data and the service provision history, and based on the correlation, may output the short-term pattern and the long-term pattern regarding the recipient's state change.

[0067] The artificial neural network model may include, for example, at least one of a Long Short-Term Memory (LSTM) model and a Temporal Convolutional Network (TCN) model.

[0068] In this case, the information processing system (100) may input the recipient's status data and service provision history into at least one of the LSTM (Long Short-Term Memory) model and the TCN (Temporal Convolutional Network) model. The data input into the LSTM model and the TCN model may include data output through an Autoencoder model, but is not limited thereto.

[0069] According to one embodiment, the LSTM model can reflect short-term state changes by learning the temporal dependency between the recipient's state change and the service provision history. For a more specific explanation regarding the LSTM model, refer to FIG. 4.

[0070] The TCN model is an artificial neural network model designed for data processing in chronological order. According to the embodiment, the TCN model can predict long-term behavioral patterns and service demands by learning long-term service provision patterns. For a more specific explanation regarding the TCN model, refer to Fig. 5.

[0071] The information processing system (100) can obtain the recipient's state change pattern data output by the artificial neural network model.

[0072] In one embodiment, the artificial neural network model may further include a weighting mechanism that assigns weights to specific time periods or specific services related to service provision history. The weighting mechanism may aggregate data output from the artificial neural network model to assign more weight to specific time periods or specific services than to other time periods or other services. Through the weighting mechanism, important information regarding changes in the recipient's state can be emphasized, and the accuracy of the basic evaluation data generated through the information processing system (100) can be improved.

[0073] According to one embodiment, the weighting mechanism may be referred to as an attention layer, but is not limited to such terms.

[0074] In one embodiment, the information processing system (100) may perform preprocessing before inputting data into the artificial neural network model described above. For example, the information processing system (100) may preprocess the acquired state data through processes such as missing value processing and normalization to convert it into a form suitable for training the artificial neural network model.

[0075] According to one embodiment, an information processing system (100) can use an Autoencoder model to compress high-dimensional data into low dimensions and extract important features. Here, the Autoencoder model is an unsupervised learning method and is an artificial neural network model that efficiently encodes input data and restores it back to the original data. The information processing system (100) can use the Autoencoder model to extract key information from various state data of a recipient and utilize it as input to the artificial neural network model described above.

[0076] If both the Autoencoder model and the aforementioned LSTM model and / or TCN model are used, the Autoencoder model may be referred to as the first artificial neural network model, and the LSTM model and / or TCN model may be referred to as the second artificial neural network model, but are not limited to these terms.

[0077] In one embodiment, the information processing system (100) can obtain state change pattern data of a recipient output by an artificial neural network model. The information processing system (100) can obtain state change pattern data including short-term and long-term patterns of the recipient's state change by using at least one of an LSTM model and a TCN model.

[0078] In one embodiment, the information processing system (100) may input natural language data, including natural language spoken by a recipient, into an artificial neural network model. Alternatively, the natural language data may include natural language input by a recipient, input by an employee, or spoken by an employee. That is, the type of natural language data is not limited.

[0079] In one embodiment, the recipient's state change pattern data can be output by an artificial neural network model based on state data, service provision history, and natural language data.

[0080] In one embodiment, the information processing system (100) can generate basic evaluation data based on state change pattern data. For example, the information processing system (100) can generate basic evaluation data by evaluating the recipient's health status and service needs according to the state change pattern data.

[0081] According to the embodiment, the configuration for generating basic evaluation data of the information processing system (100) may be referred to as a Dense layer, but is not limited to such terms.

[0082] In one embodiment, the information processing system (100) can generate a customized service provision plan for a recipient based on basic evaluation data. The customized service provision plan may refer to a service provision plan that is identified as being more suitable for the recipient as a result of analyzing the basic evaluation data.

[0083] In one embodiment, the information processing system (100) may classify or quantify the status of a recipient by applying classification or regression to basic evaluation data. The information processing system (100) may generate a customized service provision plan based on the classification or quantification.

[0084] In one embodiment, the artificial neural network module of the information processing system (100) can acquire feedback data from a recipient regarding a service provided according to a customized service provision plan. Reinforcement learning can be performed on the artificial neural network model based on the feedback data. Through reinforcement learning, the prediction accuracy of the artificial neural network module can be improved. In addition, continuous updates to the artificial neural network model can be performed through reinforcement learning to output better results.

[0085] In one embodiment, the information processing system (100) may generate a service provision list for each employee of a welfare facility based on a customized service provision plan. The service provision list may include information recording services that the employee is to provide to the recipient. The information processing system (100) may transmit the service provision list to an employee terminal (200). In some cases, the information processing system (100) may transmit the service provision list to a manager terminal (300). When the service provision list is provided to the manager terminal (300), the employee's work may be managed by the manager terminal (300).

[0086] In one embodiment, each recipient of a welfare facility may have a corresponding recipient terminal (250). Each employee may have an employee terminal (200). When one of the recipient terminals (250) and one of the employee terminals (200) approach within a predetermined distance, a log may be generated. A log may refer to data in which information is recorded. The log may include information regarding the date and time when the access was detected, the details of the services provided through the access, etc. The information processing system (100) may generate details of the services actually provided to the recipient based on the log. A more specific explanation regarding this may be made by referring to FIGS. 6 and FIGS. 7.

[0087] In one embodiment, the information processing system (100) may provide a user interface (UI). For example, the information processing system (100) may provide a user interface including a customized service provision plan to an employee terminal (200) or a manager terminal (300).

[0088]

[0089] FIG. 2 is a hardware configuration diagram of an information processing system of a welfare facility according to one embodiment of the present disclosure.

[0090] Referring to FIG. 2, an information processing system (100) according to another embodiment of the present disclosure may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 2 illustrates only the components related to the embodiments of the present disclosure. Accordingly, a person skilled in the art to which the present disclosure pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 2.

[0091] The processor (110) controls the overall operation of each component of the information processing system (100). The processor (110) may be configured to include a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphic Processing Unit), or any form of processor well known in the art of the present disclosure.

[0092] Additionally, the processor (110) may perform operations for at least one application or program for executing the method according to the embodiments of the present disclosure, and the information processing system (100) may have one or more processors.

[0093] In one embodiment, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0094] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present disclosure. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0095] The bus (130) provides communication functions between components of the information processing system (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0096] The communication interface (140) supports wired and wireless internet communication of the information processing system (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present disclosure. In some embodiments, the communication interface (140) may be omitted.

[0097] Storage (150) can store computer programs (151) non-temporarily. When generating basic evaluation data of a welfare facility through an information processing system (100), storage (150) can store various information necessary to generate basic evaluation data. For example, storage (150) can store the service provision history described in FIG. 1. In this case, storage (150) may include the database described in FIG. 1.

[0098] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0099] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present disclosure when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present disclosure by executing the one or more instructions.

[0100] In one embodiment, the computer program (151) may include one or more instructions for performing steps of: acquiring status data of a recipient of a welfare facility; acquiring service provision history for the recipient; inputting the recipient's status data and service provision history into an artificial neural network model; acquiring the recipient's status change pattern data output by the artificial neural network model; and generating basic evaluation data based on the status change pattern data.

[0101] The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0102] The components of the present disclosure may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present disclosure may be executed as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors. A method for accident prevention management of a welfare facility performed by an information processing system (100) will be described below.

[0103]

[0104] FIG. 3 is a flowchart of the operation method of an information processing system of a welfare facility according to one embodiment of the present disclosure.

[0105] Referring to FIG. 3, in step S110, an information processing system (e.g., the information processing system (100) of FIG. 1) can obtain status data of a recipient of a welfare facility. The status data may include data on at least one of the recipient's health status, cognitive function, and emotional status.

[0106] The information processing system may obtain status data from at least one of an employee terminal or a manager terminal. An employee is a person who provides services at a welfare facility; for example, an employee may be a person who provides care services to a recipient of a welfare facility, but is not limited thereto. An employee terminal may be a terminal used by such an employee. A manager is a person who manages a welfare facility; they may be an employee with management authority, but are not limited thereto. A manager terminal may be a terminal used by such an employee.

[0107] In step S120, the information processing system can obtain service provision details for the recipient. For example, the information processing system can obtain service provision details for the recipient from a database. Service provision details may be stored in the database. For specific operations on storing service provision details in the database, refer to FIGS. 6 and FIGS. 7.

[0108] In step S130, the information processing system can input the recipient's status data and service provision history into an artificial neural network model.

[0109] In one embodiment, the artificial neural network model may have learned the correlation between the recipient's state data and the service provision history. Based on the correlation, when at least one of the recipient's state data and the service provision history is input, the artificial neural network model can output short-term and long-term patterns regarding the recipient's state change.

[0110] In one embodiment, the artificial neural network model may include at least one of an LSTM model and a TCN model. The information processing system can identify short-term pattern data regarding changes in the recipient's state using the LSTM model. The information processing system can identify long-term pattern data regarding changes in the recipient's state using the TCN model.

[0111] In step S140, the information processing system can acquire state change pattern data of the recipient output by the artificial neural network model. The state change pattern data may include data for at least one of a short-term pattern and a long-term pattern regarding the recipient's state change.

[0112] In one embodiment, the information processing system can output state change pattern data that reflects both short-term and long-term patterns by using an LSTM model and a TCN model.

[0113] In one embodiment, the artificial neural network model of the information processing system may further include a weighting mechanism that assigns weights to specific time periods or specific services related to service provision history. The specific time periods or specific services to which weights are assigned may be identified as important. In this case, the information processing system can improve the accuracy of state change pattern data and ultimately improve the accuracy of the basic evaluation data described below by using the artificial neural network model to emphasize important information.

[0114] In step S150, the information processing system can generate basic evaluation data based on state change pattern data. The information processing system can generate basic evaluation data that reflects the state change pattern data. The state change pattern data may be information unique to the recipient derived for each recipient. The information processing system can generate basic evaluation data representing the physical, cognitive, and emotional state of the recipient that reflects the state change pattern data.

[0115] In one embodiment, the information processing system may generate a customized service provision plan using basic evaluation data and provide information regarding it. A more specific explanation regarding this may be made by referring to FIG. 8.

[0116]

[0117] FIG. 4 is a diagram illustrating an exemplary Long Short-Term Memory (LSTM) model applicable to one embodiment of the present disclosure.

[0118] The LSTM model is a type of RNN (Recurrent Neural Network) model developed to solve the gradient vanishing and long-term dependency problems of RNNs. Unlike RNNs, the LSTM model demonstrates excellent performance in processing long sequences of input.

[0119] RNNs have the disadvantage that their performance degrades as the time gap increases. In other words, RNNs are effective only for relatively short sequences. To compensate for this, LSTMs [add] cell states (C in Fig. 4) to the hidden states of the RNN t-1 , C t ) was added.

[0120] The LSTM model has a multi-input structure and may be a multi-task trained model. Here, the multi-input structure is a structure designed to receive different types of data as inputs, and multi-task training may involve performing optimization separately for each feature by using a separate task-specific loss function at the final output stage of the LSTM model so that multiple tasks can be performed depending on the type of input data.

[0121] Regarding LSTM models, various known contents other than those described in this specification may be applied, and the embodiments of this specification are not limited thereto.

[0122]

[0123] FIG. 5 is a diagram illustrating an exemplary Temporal Convolutional Network (TCN) model applicable to one embodiment of the present disclosure.

[0124] The TCN model is an artificial neural network model designed for processing data in chronological order. As a type of Convolutional Neural Network (CNN), the TCN model offers higher accuracy in processing time-series data compared to RNN-based models and has the advantage of operating effectively even with long sequences.

[0125] The TCN model is a causal model, meaning that for the predicted value at time t, input variables are available only up to time t. Due to this causality, it does not rely on information from previous time steps. In other words, during the convolution operation of the TCN model, only elements from time t and the preceding time step t-1 are used to generate the output at step t. Therefore, elements from time steps earlier or later than t and t-1 do not affect the output value at time t.

[0126] TCN models can utilize dilated convolution. In such cases, they can cover a wide temporal range. Due to this characteristic of TCN models, they can be usefully employed in tasks requiring a large number of time steps.

[0127] With respect to the TCN model, various known contents other than those described in this specification may be applied, and the embodiments of this specification are not limited thereto.

[0128]

[0129] FIG. 6 is a flowchart of an operation method related to the generation of service provision details of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure.

[0130] In step S610, the information processing system (e.g., the information processing system (100) of FIG. 1) can obtain a log generated when one of the recipient terminals and one of the worker terminals approach within a predetermined distance.

[0131] The log may be a contact log generated based on Bluetooth communication as, for example, an employee terminal (e.g., employee terminal (200) of FIG. 1) and a recipient terminal (e.g., recipient terminal (250) of FIG. 1) come into contact. The contact log may include information such as identification information, contact time, and contact location, but is not limited thereto.

[0132] In step S620, the information processing system can generate a history of services actually provided to the recipient based on the log.

[0133] In one embodiment, when an information processing system acquires a log, it can generate a history of actual service provision based on past data. For example, the information processing system can verify information regarding the past logs for each of the history of past service provision. The information processing system can verify the past log corresponding to the acquired log by comparing the past log with the acquired log. The information processing system can generate the history of service provision of the acquired log from the history of service provision of the identified past log.

[0134] In one embodiment, the log acquired by the information processing system may include information about the provided service. The information processing system may generate a history of service provision based on identifying the acquired log.

[0135] In step S630, the information processing system can store the service provision history within the database.

[0136] The information processing system can store the generated service provision history in a database. The database may be included in the storage (150) of FIG. 2, but is not limited thereto and may be implemented as a storage device outside the information processing system.

[0137]

[0138] FIG. 7 is a diagram illustrating the service provision history of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure. In FIG. 7, content that overlaps with the content described in FIG. 6 may be omitted.

[0139] Referring to FIG. 7, a log may be generated when the worker terminal (200) and the recipient terminal (250) are located within a specific distance range. For example, the log between the worker terminal (202) and the recipient terminal (201) may be a contact log generated based on Bluetooth communication as the worker terminal (202) and the recipient terminal (201) come into contact, and such a contact log may include information such as identification information, contact time, and contact location, but is not limited thereto.

[0140] The information processing system (100) can obtain logs. The information processing system (100) can obtain logs from at least one of the employee terminal (200) and the recipient terminal (250).

[0141] When the information processing system (100) acquires a log, it can verify the acquired log. Based on verifying the log, the information processing system (100) can generate a service provision history. The service provision history may refer to the history of services provided by an employee to a recipient.

[0142] In one embodiment, the log may contain information regarding the details of services provided by the recipient to the worker. In this case, the information processing system (100) may extract service details from the various information included in the log to generate service provision details.

[0143] In one embodiment, the information processing system (100) can generate a service provision history by comparing a log included in past data with an acquired log. For example, the information processing system (100) can identify the log most similar to the acquired log among the logs included in past data (hereinafter referred to as past log). The information processing system (100) can verify the service provision history corresponding to the past log and generate the same service provision history as the service provision history corresponding to the acquired log.

[0144] The information processing system (100) can store service provision history in a database. The database may be a component included in the information processing system (100), but is not limited thereto and may be implemented as a separate external component.

[0145]

[0146] FIG. 8 is a flowchart of an operation method related to the generation of service provision details of an information processing system for automating the basic evaluation of a welfare facility according to one embodiment of the present disclosure. FIG. 8 is a flowchart showing an example of an operation after step S350 of FIG. 3.

[0147] Referring to FIG. 8, in step S810, the information processing system can generate a customized service provision plan based on basic evaluation data. The customized service provision plan may include a service provision plan that is identified as being more suitable for the recipient as a result of analyzing the basic evaluation data.

[0148] In one embodiment, the information processing system may classify or quantify the status of a recipient by applying classification or regression to basic evaluation data. The information processing system may generate a customized service provision plan based on the classification or quantification.

[0149] For example, an information processing system can determine appropriate services based on the graded or quantified status of a recipient. The information processing system can generate information regarding appropriate services by grade or quantification as a customized service provision plan.

[0150] In step S820, the information processing system can generate a list of services provided based on a customized service provision plan.

[0151] The information processing system can generate a service provision list that includes a customized service provision plan. The customized service provision plan can be generated for each recipient, and accordingly, the service provision list can also be generated for each recipient.

[0152] In step S830, the information processing system may provide a service provision list to an employee terminal. According to an embodiment, the information processing system may provide the service provision list to a manager terminal. The manager terminal may manage employees using the service provision list.

[0153] In an embodiment, the information processing system may acquire feedback data from a recipient regarding a service provided according to a customized service provision plan. The feedback data may be provided from a recipient terminal, but is not limited thereto.

[0154] Information processing systems can perform reinforcement learning on artificial neural network models based on feedback data. For example, an information processing system can perform reinforcement learning by inputting feedback data into an artificial neural network model. When reinforcement learning is performed in this way, the artificial neural network model can be improved to generate output values ​​more accurately.

[0155] An information processing system according to the embodiments of the present disclosure can improve the reliability and efficiency of the basic assessment by automatically evaluating the condition of the recipient and providing a customized needs assessment tailored thereto.

[0156] In addition, the information processing system according to the embodiments of the present disclosure enables the establishment of data-based customized service plans by analyzing temporal patterns and long-term dependencies through LSTM and TCN. This allows for the provision of services that are more appropriate and have higher necessity to the recipient.

[0157] In addition, the information processing system according to the embodiments of the present disclosure can reduce the workload by minimizing manual work by automatically generating basic evaluation data.

[0158] FIG. 9 is a drawing illustrating the overall environment of an accident prevention management system for a welfare facility according to one embodiment of the present disclosure.

[0159] Referring to FIG. 9, an accident prevention management system for a welfare facility according to one embodiment of the present disclosure may include an accident prevention management system (100), an employee terminal (200), a manager terminal (300), and a network (400).

[0160] Here, the accident prevention management system of the welfare facility illustrated in FIG. 9 is exemplary, and its components are not limited to the embodiment illustrated in FIG. 9 and may be added, changed, or deleted as needed.

[0161] The welfare facilities described in this specification may include elderly welfare facilities that serve the elderly. However, they are not limited thereto and may be understood as various social welfare facilities and medical service providers.

[0162] In one embodiment, the accident prevention management system (100) may be a server that manages accident prevention in a welfare facility. In one embodiment, the accident prevention management system (100) may be connected to an employee terminal (200) and an administrator terminal (300) through a network (400).

[0163] Here, a terminal may refer to any form of entity(s) in a system having a mechanism for communicating with an accident prevention management system (100). For example, such a terminal may include a PC (personal computer), a notebook, a mobile terminal, a smartphone, a tablet PC, and a wearable device, and may include any type of terminal capable of connecting to a wired or wireless network. Additionally, the terminal may include any computing device implemented by at least one of an agent, an API (Application Programming Interface), and a plug-in. Additionally, the terminal (200) may include an application source and / or a client application.

[0164] The employee terminal (200) may include a terminal used by an employee working at a welfare facility. The manager terminal (300) may include a terminal used by a manager who manages the welfare facility. The employee terminal (200) and / or manager terminal (300) may be designed in advance or used only by specific users based on authentication, but are not limited thereto.

[0165] Additionally, the network (400) may refer to a connection structure capable of exchanging information between each node, such as multiple terminals and servers. For example, the network (400) may include a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired / wireless data network, a telephone network, a wired / wireless television network, a Controller Area Network (CAN), and Ethernet.

[0166] Wireless data communication networks may include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0167] More specifically, the accident prevention management system (100) can manage data for accident prevention based on accident prevention information of the welfare facility. For example, the accident prevention management system (100) can receive information about a recipient from at least one of an employee terminal (200) and a manager terminal (300). However, the method of obtaining information about a recipient can be expanded in various ways and is not limited thereto.

[0168] For example, the recipient's information may be unique information related to the recipient, such as the recipient's diagnosis, condition, age, medical history, and gender. As another example, according to an embodiment, the recipient's information may include basic evaluation data including at least one of the recipient's health status, cognitive function, or emotional state. Such basic evaluation data of the recipient may be generated and acquired through surveys and self-reports of the recipient, observational evaluations by staff, physical and health examinations performed by medical professionals, cognitive function tests and psychological tests performed by the recipient, but is not limited thereto; it may also be acquired using an electronic health record system from existing medical records or health records issued by a hospital. For example, the basic evaluation data may be acquired through at least one of a staff terminal (200) and an administrator terminal (300), but is not limited to the terminal serving as the acquisition path.

[0169] In one embodiment, the accident prevention management system (100) can classify or distinguish recipients based on recipient information and accident prevention information. The accident prevention management system (100) can generate recipient classification information based on classifying / distinguishing recipients.

[0170] In one embodiment, accident prevention information may include at least one of seven types of beneficiaries, one type of worker, and one type of facility. The seven types of beneficiaries may include, for example, beneficiaries with violent tendencies, beneficiaries at risk of falls, beneficiaries at risk of disease, beneficiaries at risk of falling and escaping, beneficiaries at risk of airway obstruction, beneficiaries at risk of diabetes, and beneficiaries at risk of fractures. The one type of worker may include, for example, workers with violent tendencies. The one type of facility may include, for example, facility inspection types. However, these types of beneficiaries, workers, and facilities are not limited to these, and specific types may be added or omitted as needed.

[0171] For example, if the first recipient is at risk of falling, the recipient classification information may include the 'recipient at risk of falling' type. Accordingly, by matching the recipient classification information within the data related to the first recipient, more appropriate measures can be taken for the first recipient when providing services related to them.

[0172] In one embodiment, the accident prevention management system (100) can manage welfare facility management data based on accident prevention information classified into a plurality of types. Here, the welfare facility management data may be collected from an employee terminal (200) and / or a manager terminal (300), but is not limited thereto, and may include, for example, data already stored in the accident prevention management system (100).

[0173] In one embodiment, the accident prevention management system (100) may receive welfare facility management data from an employee terminal (200) or a manager terminal (300). For example, the accident prevention management system (100) may obtain information from the employee terminal (200) regarding the behavior, meals, supervision matters, or facility management of a recipient that occurred on a specific date. As another example, the accident prevention management system (100) may obtain information from the manager terminal (300) regarding training content, precautions, or instructions.

[0174] In one embodiment, the accident prevention management system (100) can generate a management log for a recipient based on welfare facility management data and recipient classification information. The management log can be generated for each recipient, with each recipient classified based on the recipient classification information. For example, the accident prevention management system (100) can generate a management log for a first recipient that includes various data related to the first recipient (the first recipient's accident records, response records, education content, disease, condition, etc.) by matching the recipient classification information for the first recipient.

[0175] In one embodiment, the accident prevention management system (100) can store a management log and transmit the management log to an administrator terminal (300).

[0176] In one embodiment, the accident prevention management system (100) can generate instruction information related to the type of recipient based on accident prevention information. The accident prevention management system (100) can transmit the generated instructions to an employee terminal (200).

[0177] In another embodiment, the accident prevention management system (100) may receive instruction information related to the type of recipient from a manager terminal (300). The accident prevention management system (100) may transmit the received instruction information to an employee terminal (200). The instruction information may be related to accident prevention information.

[0178] In one embodiment, the accident prevention management system (100) may acquire emergency situation data from an employee terminal (200). The emergency situation data may include data related to accidents occurring in the welfare facility. For example, the emergency situation data may include information regarding whether an accident has occurred, the target of the accident, the cause of the accident, the details of the response, and the progress of the accident. The accident prevention management system (100) may provide a warning notification to the manager terminal (300) in response to the acquisition of the emergency situation data. Through this, the accident prevention management system (100) can monitor emergency situations (or accident situations) related to the welfare facility and enable immediate response by providing a real-time warning notification to the manager terminal (300) when a problem occurs.

[0179] In one embodiment, the accident prevention management system (100) may provide a user interface (UI) (e.g., FIG. 13 to 37).

[0180]

[0181] FIG. 10 is a hardware configuration diagram of an accident prevention management system for a welfare facility according to one embodiment of the present disclosure.

[0182] Referring to FIG. 10, an accident prevention management system (100) according to another embodiment of the present disclosure may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 10 illustrates only the components related to the embodiments of the present disclosure. Accordingly, a person skilled in the art to which the present disclosure pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 10.

[0183] The processor (110) controls the overall operation of each component of the accident prevention management system (100). The processor (110) may be configured to include a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphic Processing Unit), or any form of processor well known in the art of the present disclosure.

[0184] Additionally, the processor (110) may perform operations for at least one application or program for executing the method according to the embodiments of the present disclosure, and the accident prevention management system (100) may have one or more processors.

[0185] In one embodiment, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0186] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present disclosure. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0187] The bus (130) provides communication functions between components of the accident prevention management system (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0188] The communication interface (140) supports wired and wireless internet communication of the accident prevention management system (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present disclosure. In some embodiments, the communication interface (140) may be omitted.

[0189] Storage (150) can store computer programs (151) non-temporarily. When performing an accident prevention management process of a welfare facility through an accident prevention management system (100), storage (150) can store various information necessary to provide the accident prevention management process.

[0190] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0191] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present disclosure when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present disclosure by executing the one or more instructions.

[0192] In one embodiment, the computer program (151) may include one or more instructions for performing the steps of: verifying information of a recipient from at least one of an employee terminal and a manager terminal; classifying a recipient using the verified information and accident prevention information to generate recipient classification information; verifying welfare facility management data from the employee terminal or the manager terminal; and generating a management log for the recipient based on the verified welfare facility management data and the recipient classification information.

[0193] The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0194] The components of the present disclosure may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present disclosure may be executed as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors. The following describes an accident prevention management method for a welfare facility performed by an accident prevention management system (100).

[0195]

[0196] FIG. 11 is a flowchart of the operation method of an accident prevention management system for a welfare facility according to one embodiment of the present disclosure.

[0197] Referring to FIG. 11, in step S1110, an accident prevention management system (e.g., accident prevention management system (100) of FIG. 9) can receive information about the recipient and accident prevention information from at least one of an employee terminal (e.g., employee terminal (200) of FIG. 9) and a manager terminal (e.g., manager terminal (300) of FIG. 9).

[0198] Here, the beneficiary is a person receiving services from a welfare facility, and may, for example, be an elderly patient receiving services from a welfare facility, but is not limited thereto. Depending on the embodiment, the beneficiary may be referred to as a patient, but is not limited to such terms.

[0199] The recipient's information may include identification information for identifying the recipient, such as a resident registration number, date of birth, or name. Additionally, depending on the case, the recipient's information may include various information related to the recipient, such as health status information, personality, age, and characteristics. The recipient's information may be obtained based on input by a user of an employee terminal or a user of an administrator terminal. Depending on the embodiment, the recipient's information may be obtained based on communication with another device (e.g., an external server), but is not limited thereto.

[0200] A worker is a person who provides services at a welfare facility; for example, a worker may be, but is not limited to, a person who provides care services to a recipient of a welfare facility. A worker terminal may be a terminal used by such a worker.

[0201] A manager is a person who manages a welfare facility and may be, but is not limited to, an employee with management authority. A manager terminal may be a terminal used by such an employee.

[0202] In step S1120, the accident prevention management system can generate recipient classification information to classify / categorize recipients based on the recipient information and accident prevention information received through step S1110.

[0203] Here, accident prevention information may include pre-classified category information based on accidents that may occur or have a history of occurring at welfare facilities (or facility care and home care long-term care institutions).

[0204] For example, accident prevention information may include at least one of seven types of beneficiaries, one type of worker, and one type of facility. The seven types of beneficiaries may include, for example, beneficiaries with a violent tendency, beneficiaries at risk of falls, beneficiaries at risk of disease, beneficiaries at risk of falling and escaping, beneficiaries at risk of airway obstruction, beneficiaries at risk of diabetes, and beneficiaries at risk of fractures.

[0205] To explain with more specific examples, a recipient with violent tendencies may refer to a category of recipients who exhibit violent tendencies. A recipient at risk of falls may refer to a category of recipients who are at risk of injury from falling or tripping. A recipient at risk of disease may refer to a category of recipients who are at risk of contracting a disease due to weakened immunity or underlying conditions. A recipient at risk of falling or escaping may refer to a category of recipients who have the potential to fall or escape from the welfare facility. A recipient at risk of airway obstruction may refer to a category of recipients who have the potential for airway obstruction due to various factors such as limited mobility or advanced age. A recipient at risk of diabetes may refer to a category of recipients who have diabetes or have been identified as having a high probability of developing diabetes. A recipient at risk of fracture may refer to a category of recipients who have a high probability of fractures due to various factors such as advanced age.

[0206] One type of worker may include, for example, workers with violent tendencies. Workers with violent tendencies may include a separate category for workers working in welfare facilities who are identified as exhibiting violent tendencies in the course of their work. Unlike the preceding seven types of beneficiaries, the worker type may be intended to distinguish workers.

[0207] One facility type may include, for example, a facility inspection type. The facility inspection type may include categories requiring inspection due to damage to facilities included in the welfare facility or the arrival of the facility's periodic inspection cycle. Unlike the employee type and beneficiary type described earlier, the facility type may be related to the facilities of the welfare facility.

[0208] Once a recipient's information is verified, the accident prevention management system analyzes the verified information to identify categories relevant to the recipient among those included in the accident prevention information. The accident prevention management system can generate recipient classification information to include the verified category information. In this case, recipient classification information can be generated for each individual recipient residing in the welfare facility.

[0209] In such cases, appropriate management can be implemented for each beneficiary staying at the welfare facility. In other words, accidents can be effectively prevented by identifying and preparing for potential incidents with a high probability of occurring for each beneficiary in advance. If an accident does occur, appropriate measures can be promptly taken because information about the beneficiary can be quickly obtained based on the classification data.

[0210] In step S1130, the accident prevention management system may receive welfare facility management data from an employee terminal or the manager terminal. The welfare facility management data may include various data obtained in real time from the welfare facility. For example, the welfare facility management data may include at least one of precautions for recipients, instructions regarding precautions, supervision matters regarding accidents, details of response to accidents, training details, and facility inspection report details.

[0211] In some cases, welfare facility management data may additionally include various information such as the condition of the beneficiary, the work status of the staff, the condition of the facility, and the date, in relation to each of the aforementioned precautions, instructions, supervision matters, response details, training details, and facility inspection report details.

[0212] In step S1140, the accident prevention management system can generate management logs for beneficiaries. The accident prevention management system can generate management logs for beneficiaries based on verified welfare facility management data and beneficiary classification information.

[0213] In one embodiment, an accident prevention management system can generate a management log by matching recipient classification information of a recipient using a welfare facility with welfare facility management data regarding the recipient. For example, the accident prevention management system can identify data related to a first recipient within the welfare facility management data. The accident prevention management system can classify the identified data according to the recipient classification information and match the data related to the recipient classification information. If data unrelated to the recipient classification information is included, the accident prevention management system can manage the data unrelated to the recipient classification information separately.

[0214] Management logs are accessible via employee terminals or administrator terminals and can be freely checked as needed.

[0215]

[0216] FIGS. 12 and 13 are flowcharts illustrating other examples of the operation method of an accident prevention management system for a welfare facility according to one embodiment of the present disclosure.

[0217] FIG. 12 shows an example of transmitting instructions to an employee terminal after step S1140 of FIG. 11, and FIG. 13 shows another example of transmitting instructions to an employee terminal after step S1140.

[0218] Referring to Fig. 12, in step S1210, the accident prevention management system generates instruction information related to the type of recipient based on accident prevention information, and the generated instruction information can be verified as welfare facility management data.

[0219] For example, the accident prevention management system can generate instruction information related to each category of accident prevention information. As another example, the accident prevention management system can generate instruction information suitable for the type of accident prevention information related to the recipient information identified in step S1110. More specifically, if the identified recipient information corresponds to the type of recipient at risk of diabetes, the accident prevention management system can generate instruction information appropriate for the recipient at risk of diabetes.

[0220] In this case, instruction information may be generated using information pre-stored in the accident prevention management system, but is not limited thereto. For example, the accident prevention management system may acquire information by type of accident prevention information based on communication with other external devices and generate instruction information using the acquired information.

[0221] The accident prevention management system can verify the generated instruction information as welfare facility management data.

[0222] In step S1220, the accident prevention management system can transmit the generated instruction information to the employee terminal. Based on the transmission of the instruction information to the employee terminal, the instruction information can be displayed on the employee terminal. A more specific example related to this can be referenced in FIG. 19.

[0223] In some cases, the accident prevention management system may transmit generated instruction information to a manager terminal and an employee terminal. The employee terminal may provide the accident prevention management system with input regarding the results of performing tasks according to the instructions. The accident prevention management system may provide the above result input to the manager terminal. In such cases, the user of the manager terminal can check the results of the employee's work according to the instruction information. In this regard, examples of screens displayed on the manager terminal can be referenced in FIGS. 14 to 18.

[0224] Referring to FIG. 13, in step S1310, the accident prevention management system receives instruction information related to the type of recipient from the administrator terminal and can verify the received instruction information as welfare facility management data. The instruction information may be generated by the administrator terminal, but is not limited thereto.

[0225] The accident prevention management system can verify the generated instruction information as welfare facility management data.

[0226] In step S1320, the accident prevention management system can transmit instruction information to an employee terminal. Based on the transmission of instruction information to the employee terminal, instruction information can be displayed on the employee terminal. A more specific example related to this can be referenced in FIG. 20.

[0227] In some cases, the accident prevention management system may transmit generated instruction information to a manager terminal and an employee terminal. The employee terminal may provide the accident prevention management system with input regarding the results of performing tasks according to the instructions. The accident prevention management system may provide the above result input to the manager terminal. In such cases, the user of the manager terminal can check the results of the employee's work according to the instruction information. In this regard, examples of screens displayed on the manager terminal can be referenced in FIGS. 14 to 18.

[0228] In Figures 12 and 13, general instruction information is exemplified as welfare facility management data, but it is not limited thereto, and the instruction information may be replaced with precautions for recipients, instructions regarding precautions, supervision regarding accidents, details of response to accidents, educational content, or facility inspection report content.

[0229] Although not explicitly stated, the accident prevention management system may acquire emergency situation data from employee terminals. In such cases, the accident prevention management system may provide warning notifications to administrator terminals in response to the acquisition of emergency situation data. Emergency situations may include, but are not limited to, accidents involving contractors.

[0230] According to the embodiments of the present disclosure, the accident prevention management system can enable real-time sharing of management data of welfare facilities, including beneficiaries, between a manager terminal and an employee terminal. In addition, the accident prevention management system can enable systematic management by generating logs based on data obtained from the manager terminal and the employee terminal, thereby storing history related to the welfare facility. The accident prevention management system can improve the reliability of welfare facility operations by ensuring that welfare facilities are managed consistently and transparently.

[0231] The accident prevention management system according to the embodiments of the present disclosure can enable systematic accident prevention and management by logging direct instructions regarding precautions, supervisory matters, and response details. Furthermore, the accident prevention management system can ensure that legal liability is more clearly fulfilled, such as by utilizing management logs as evidence in the event of legal issues related to the operation of a welfare facility.

[0232]

[0233] FIGS. 14 to 17 show examples of screens (or user interfaces (UI)) related to instructions displayed on an administrator terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0234] Figure 14 shows an example of a screen of a manager terminal displaying information regarding instructions provided from an accident prevention management system to an employee terminal.

[0235] Instruction information delivered to the worker's terminal can be displayed by the date the instruction information was provided. Clicking on a date can display more detailed instruction information. Additionally, the completion rate of the instructions can be displayed, along with information regarding the subjects and participants related to the instructions.

[0236] In one embodiment, the screen of FIG. 14 may be output. When the accident prevention management system receives an input to output the screen of FIG. 14 from an administrator terminal, it may determine the output screen by modifying instruction information according to a pre-specified format. The screen of FIG. 14 may proceed to output as the determined output screen. For examples of the output screen, refer to FIG. 16 and FIG. 17.

[0237] Referring to FIG. 15, the accident prevention management system can provide instruction information to an employee terminal according to accident prevention information. For example, the accident prevention management system can provide instruction information to an employee terminal according to each of the following: an inmate at risk of falling, an inmate at risk of falling and escaping (or an inmate at risk of escaping and falling), and an inmate with a violent tendency. As shown in FIG. 15, where instruction information is provided to the employee terminal, detailed instruction information content may be displayed in the first area (301) of the manager terminal.

[0238] There may be multiple employees working in an elderly care facility, and in such cases, there may also be multiple employee terminals. When instruction information is provided to multiple employee terminals, the accident prevention management system can identify whether each of the multiple employee terminals has checked the instruction information. The accident prevention management system can provide the manager terminal with information regarding whether each of the multiple employee terminals has checked the instruction information. In such cases, as shown in FIG. 15, the confirmation status for each employee may be displayed in the second area (302) of the manager terminal. As illustrated, the confirmation date and time may be displayed along with the confirmation status for each employee, but is not limited thereto.

[0239] Figures 16 and 17 show examples of output screens related to the previously described instruction information. Specifically, Figure 16 shows a screen where recipient classification information is matched according to accident prevention information. Figure 17 shows a screen related to an employee who has verified the instruction information.

[0240]

[0241] Figure 18 shows an example of a screen displayed on an employee terminal when instruction information is transmitted from an accident prevention management system to an employee terminal.

[0242] Referring to Fig. 18, resident information by type of accident prevention information can be displayed on the employee terminal. Although not illustrated, the employee terminal can check more detailed instructions by clicking on the accident prevention information type section.

[0243]

[0244] FIGS. 19 to 24 show examples of screens related to educational content displayed on an administrator terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0245] Figure 19 shows an example of a screen displaying training information transmitted from an accident prevention management system to an employee terminal by date. If you click on a date on the screen of Figure 19, you can view the detailed training content as shown in Figure 20.

[0246] The fact that accident prevention training has been conducted can serve as important evidence in the event of a future accident. If such evidence is stored and managed within an accident prevention management system, the stored data can be effectively utilized in the event of an accident.

[0247] Figure 21 shows an example of an output screen when educational content is output. As illustrated, the output screen may include educational content by date, completion rate of educational items, etc.

[0248] Figures 22 and 23 show examples of output screens in which training content by date is displayed in more detail.

[0249] Figure 24 shows an example of an output screen displaying a list of employees who have checked the training content by date.

[0250] FIGS. 25 and 26 show examples of screens related to training content displayed on an employee terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0251] FIGS. 25 and 26 show examples of training content displayed on an employee's screen. This training content may include accident cases, precedents, and emergency response manuals.

[0252] FIGS. 27 to 30 show examples of screens related to supervision matters displayed on an administrator terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0253] FIG. 27 shows an example of a screen that can classify and manage reports received from an employee terminal into recipients and facilities. When each item on the screen is clicked, the user can move to a screen displaying more detailed information.

[0254] FIG. 28 shows an example of a screen for registering or deleting a recipient receiving services at a welfare facility. Information regarding registered or deleted recipients may be included in instructions and provided to an employee's terminal.

[0255] Figure 29 shows an example of an output screen when registered report content by date is output by setting a period.

[0256] Figure 30 shows an example of an output screen displaying reports and supervision details by date. The supervision details can be displayed as high, medium, low, or X depending on the degree of overlap. That is, the highest degree of overlap is displayed as high, and the lowest degree is displayed as X.

[0257] FIGS. 31 and 32 show examples of screens related to supervision matters displayed on an employee terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0258] Figure 31 shows an example of a screen displaying recipient-related report content that an employee can select. Referring to Figure 31, types included in accident prevention information may be displayed on the employee terminal. If one of the displayed types is selected, input for that type can be performed.

[0259] For example, if an inmate at risk of fracture is selected, a screen for entering information about the inmate at risk of fracture may be displayed as shown in Fig. 32. Referring to Fig. 32, the information about the inmate at risk of fracture may include, but is not limited to, name, age, and date of entry. Such information may be classified as information about the recipient, but is not limited thereto.

[0260] FIGS. 33 to 35 show examples of screens related to facility inspection reports displayed on an administrator terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0261] FIG. 33 shows an example of a screen for checking facility-related reports received from an employee terminal and entering or registering actions. The screen of FIG. 33 may be displayed on an administrator terminal, but is not limited thereto.

[0262] Referring to Fig. 33, details regarding facility malfunctions and inspections may be recorded in the memo column. When the facility inspection is completed, information regarding the inspection date and time and corrective actions may be entered as a facility inspection report.

[0263] Figures 34 and 35 show examples of output screens when printing facility inspection report contents.

[0264] FIGS. 36 and 37 show examples of screens related to facility inspection reports displayed on an employee terminal by an accident prevention management system according to one embodiment of the present disclosure.

[0265] FIGS. 36 and 37 show examples of facility-related report content being displayed on an employee terminal. The user of the employee terminal can input information for facility inspection reporting through the screen.

[0266] FIGS. 36 and 37 illustrate the case where natural language is directly input at the worker terminal, but are not limited thereto and may be implemented in the form of selecting natural language.

[0267]

[0268] As explained above, a person skilled in the art to which this disclosure pertains will understand that this disclosure may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of this disclosure is defined by the claims set forth below rather than by the detailed description, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included within the scope of this disclosure.

[0269] The features and advantages described herein are not all included, and in particular, many additional features and advantages will become apparent to those skilled in the art by considering the drawings, the specification, and the claims. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes and may not be chosen to describe or limit the subject matter of this disclosure.

[0270] The foregoing description of the embodiments of the present disclosure is provided for illustrative purposes only. It is not intended to limit the present disclosure to the exact form disclosed or to make it incomplete. Those skilled in the art will understand that many modifications and variations are possible in light of the foregoing disclosure.

[0271] Therefore, the scope of the present disclosure is not limited by the detailed description but by any of the claims of the application based thereon. Accordingly, the disclosure of embodiments of the present disclosure is illustrative and does not limit the scope of the present disclosure as set forth in the following claims.

Claims

1. As a method of operation of an information processing system for automating the basic evaluation of beneficiaries of a welfare facility, A step of obtaining status data of a recipient of the above welfare facility; A step of obtaining service provision details for the above-mentioned recipient; A step of inputting the above status data of the above recipient and the above service provision history into an artificial neural network model; A step of acquiring state change pattern data of the recipient output by the artificial neural network model; and A method of operation comprising the step of generating basic evaluation data based on the above-mentioned state change pattern data.

2. In Paragraph 1, A method of operation in which the above-mentioned state data includes data on at least one of the recipient's health status, cognitive function, and emotional status.

3. In Paragraph 1, A method of operation in which the above state change pattern data includes a short-term pattern and a long-term pattern regarding the state change of the recipient.

4. In Paragraph 3, A method of operation in which the artificial neural network model learns the correlation between the state data of the recipient and the service provision history, and outputs the short-term pattern and the long-term pattern regarding the state change of the recipient based on the correlation.

5. In Paragraph 1, A method of operation in which the artificial neural network model comprises at least one of an LSTM (Long Short-Term Memory) model and a TCN (Temporal Convolutional Network) model.

6. In Paragraph 5, The above artificial neural network model further includes a weighting mechanism that assigns weights to specific time zones or specific services related to the service provision history, in a method of operation.

7. In Paragraph 1, A method of operation further comprising the step of generating a customized service provision plan for the recipient based on the above basic evaluation data.

8. In Paragraph 7, The step of generating the above customized service provision plan is, A step of classifying or quantifying the status of the recipient by applying classification or regression to the above-mentioned basic evaluation data; and A method of operation comprising the step of generating a customized service provision plan based on the above-mentioned grading or quantification.

9. In Paragraph 8, A step of obtaining feedback data from the recipient regarding the service provided according to the above customized service provision plan; A method of operation further comprising the step of performing reinforcement learning on the artificial neural network model based on the feedback data.

10. In Paragraph 7, A method of operation further comprising the step of generating a list of services provided for each employee of the welfare facility based on the above customized service provision plan.

11. In Paragraph 1, Each beneficiary of the above welfare facility has a corresponding beneficiary terminal, Each of the above-mentioned workers has a worker terminal, The step of obtaining the service provision history for the above-mentioned recipient is, A method of operation comprising the step of generating a record of the actual service provided to the recipient based on a log generated when one of the recipient terminals and one of the worker terminals approach within a predetermined distance.

12. In Paragraph 1, The step of inputting the above-mentioned status data of the above-mentioned recipient and the above-mentioned service provision history into an artificial neural network model is, The method includes the step of inputting natural language data, including natural language spoken by the aforementioned recipient, into an artificial neural network model. A method of operation in which the state change pattern data of the above-mentioned recipient is output by the above-mentioned artificial neural network model based on the above-mentioned state data, the above-mentioned service provision history, and the above-mentioned natural language data.

13. A computer program stored on a computer-readable recording medium for executing a method of operation according to any one of paragraphs 1 through 12 on a computer.

14. In an information processing system for automating the basic evaluation of beneficiaries of welfare facilities, Memory; and A processor connected to the memory and configured to execute at least one computer-readable program contained in the memory. Includes, The above at least one program is, Acquire status data of beneficiaries at welfare facilities, and Obtain the service provision history for the above-mentioned recipient, and Input the above status data of the above recipient and the above service provision history into an artificial neural network model, and Acquire the state change pattern data of the recipient output by the artificial neural network model, and An information processing system comprising instructions for generating basic evaluation data based on the above-mentioned state change pattern data.

Images