Logic determination method and apparatus for hospital counseling algorithm using automatic counseling algorithm interface

Abstract

Disclosed is a logic determination apparatus for a hospital counseling algorithm using an automatic counseling algorithm interface. The present logic determination apparatus comprises: a memory storing one or more instructions; and at least one processor that executes the instructions stored in the memory, wherein the processor may: set conditions for executing a counseling algorithm that automatically generates messages according to a treatment type; list, in chronological order, preset automatically-generated messages of the counseling algorithm corresponding to the treatment type; when an item for modifying the chronologically listed automatically-generated messages is selected, display, in an editable state, an automatically-generated message corresponding to the selected item; and display an item for adding a new message between the chronologically listed automatically-generated messages. Therefore, user convenience can be improved.

Description

Method for determining the logic of a hospital consultation algorithm using an automatic consultation algorithm interface and a device therefor

[0001] The present disclosure relates to a technology for encouraging and communicating with customers in a hospital. More specifically, the present disclosure relates to a technology for determining the logic of a hospital consultation algorithm that encourages customer return visits by utilizing an automated consultation algorithm interface.

[0002] The content described below merely provides background information related to the present embodiment and does not constitute prior art.

[0003] Recently, the hospital industry has also been investing heavily in information system adoption, as medical and administrative services are increasingly based on electronic medical records. Furthermore, hospital-operated counseling systems require highly skilled counselors, making it difficult to handle a large volume of services with high quality. This variation in counselor skill levels can lead to inconsistent service delivery and even incorrect consultations.

[0004] Therefore, a method is needed to create a counseling algorithm that can provide accurate and standardized response services even if the counselor's skill level is somewhat low.

[0005] The problem that this disclosure seeks to solve is to provide a method for easily generating a consultation algorithm to improve consultation efficiency in a hospital.

[0006] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0007] In order to solve the above-described problem, a logic decision device of a hospital consultation algorithm utilizing an automatic consultation algorithm interface according to the present disclosure may include a memory storing one or more instructions; and at least one processor executing the instructions stored in the memory.

[0008] The one or more instructions, when executed by the at least one processor, may cause the logic decision unit to perform at least one operation.

[0009] The at least one operation may include: an operation of setting conditions for executing a counseling algorithm that automatically generates a message according to a treatment type; an operation of listing automatically generated messages of a preset counseling algorithm corresponding to the treatment type in a time-series manner; an operation of displaying an automatically generated message corresponding to the selected item in an editable state when an item for modifying the automatically generated message listed in a time-series manner is selected; and an operation of displaying an item for adding a new message between the automatically generated messages listed in a time-series manner.

[0010] The above automatically generated message may include at least one of text, image, video, event information, and notice information.

[0011] The action of displaying the automatically generated message in an editable state may include an action of providing an option to modify at least one of the name of the automatically generated message, information related to the treatment type, conditions displayed in the chat window with the customer, message sending conditions, and message type information.

[0012] The above-described time-series listing operation may include an operation of displaying performance information of the automatically generated messages listed time-series together.

[0013] The at least one action may include an action to disable the delete or modify function for automatically generated messages that must be included depending on the treatment type.

[0014] In addition, a method for determining the logic of a hospital consultation algorithm utilizing an automatic consultation algorithm interface performed by a processor according to the present disclosure may include a step of setting a condition for executing a consultation algorithm that automatically generates a message according to a treatment type; a step of listing automatically generated messages of a preset consultation algorithm corresponding to the treatment type in a time-series manner; a step of displaying an automatically generated message corresponding to a selected item in an editable state when an item for modifying the automatically generated message listed in a time-series manner is selected; and an operation of displaying an item for adding a new message between the automatically generated messages listed in a time-series manner.

[0015] The above automatically generated message may include at least one of text, image, video, event information, and notice information.

[0016] The step of displaying the automatically generated message in an editable state may include a step of providing an option to modify at least one of the name of the automatically generated message, information related to the treatment type, conditions displayed in a chat window with the customer, message sending conditions, and message type information.

[0017] The step of listing in a time series may include a step of displaying performance information of the automatically generated messages listed in a time series.

[0018] The above logic determination method may further include, after the step of listing in a time series manner, a step of disabling a deletion or modification function for automatically generated messages that must be included according to the treatment type.

[0019] In addition, a computer program stored in a computer-readable recording medium may be further provided to execute a method for implementing the present disclosure.

[0020] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0021] Through various embodiments of the present disclosure, a consultation algorithm based on automatically generated messages can be easily created to induce re-visits of hospital customers, thereby improving user convenience and increasing hospital sales.

[0022] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0023] FIG. 1 is a diagram schematically illustrating the processing of a logic decision device of a hospital consultation algorithm utilizing an automatic consultation algorithm interface according to the present disclosure.

[0024] FIG. 2 is a block diagram showing the configuration of a logic decision device of a hospital consultation algorithm utilizing an automatic consultation algorithm interface according to the present disclosure.

[0025] FIG. 3 is a sequence diagram illustrating a method for generating a counseling algorithm by utilizing an automatic counseling algorithm interface according to the present disclosure.

[0026] Figure 4 is a screen for evaluating the performance of a counseling algorithm generated according to the present disclosure.

[0027] FIG. 5 is a diagram illustrating a user interface for generating a specific consultation algorithm according to the present disclosure.

[0028] FIGS. 6 and 7 are diagrams for explaining a method of organizing a customer's hospital service information into a database and utilizing it for marketing purposes to induce a customer's re-visit according to the present disclosure.

[0029] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms 'part, module, element, block' used in the specification may mean executable software (or code, instructions, or programs). Alternatively, the 'part, module, element, block' may be implemented as hardware having a structure. According to embodiments, multiple 'parts, modules, elements, blocks' may be implemented as a single component, or a single 'part, module, element, block' may include multiple components.

[0030] Throughout the specification, when a part is said to be "connected" to another part, this not only means physical contact (or, connection), but also connection through another intervening entity. Accordingly, "connection" can mean not only a state of physical direct contact, but also a state in which another entity is intervening. Meanwhile, "connection" can also mean a "logical connection" in addition to a physical connection, which can also mean connection based on wireless communication.

[0031] When a part is said to "include" a component, this means that it can also include other components, unless otherwise stated.

[0032] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0033] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0034] Singular expressions may also have plural meanings unless the context clearly indicates otherwise.

[0035] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0036] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0037] Figure 1 is a drawing for schematically explaining the processing of a logic decision device (100, hereinafter referred to as “logic decision device”) of a hospital consultation algorithm utilizing an automatic consultation algorithm interface.

[0038] Referring to FIG. 1, the logic decision device (100) may be a device that provides various services to customers (e.g., patients, etc.) who have received or are scheduled to receive hospital services, and may be a hospital integration system that communicates with related terminals, related devices, and related systems.

[0039] The logic decision device (100) can determine the logic of the consultation algorithm used in the hospital's customer relationship management (CRM) system. The CRM system can be provided on a SaaS (software as a service) basis. The CRM system can separately manage information specific to a specific hospital, and can also utilize shared information that can be shared among various hospitals. Depending on the implementation example, the logic decision device (100) can also be equipped with the functions of a hospital's automatically generated message-based consultation service provider.

[0040] The logic decision device (100) can be equipped with multiple consultation algorithms and can guide response services so that even hospital staff without expertise can provide customized services to meet the needs of various customers.

[0041] The logic decision device (100) may be a device for comprehensively performing and managing reservations for consultation and / or visits to a hospital, and may analyze the performance of a consultation algorithm that is effective for customer satisfaction, customer revisit, etc., and may provide a user-friendly user interface for generating a consultation algorithm.

[0042] When guiding a response service, the logic decision device (100) can provide a treatment type manual and / or a response manual for customer messages, and can provide a chat screen that enables communication with the customer.

[0043] The logic decision device (100) can provide consultation and response services through an application. The logic decision device (100) can provide a consultation algorithm and performance information of the consultation algorithm, and can guide the installation of the application to a customer visiting offline for the first time through the hospital staff. In an embodiment, the logic decision device (100) can induce the download of the application by having the terminal of the customer visiting for the first time place a preset code (e.g., a QR code) within the shooting range of the terminal, and can provide a link for downloading the application to the customer's terminal. In case of providing a web-based consultation service, the link information can be provided to the customer's terminal, but the present disclosure is not limited thereto.

[0044] The logic decision device (100) can communicate with a plurality of terminals through an application, and at least some of the plurality of terminals can provide customer feedback to the logic decision device (100) and request reservations for consultation and / or visits.

[0045] The logic decision device (100) has multiple consultation algorithms and can provide customized consultation algorithms to hospital staff for each situation, and can guide response services to customer feedback messages.

[0046] The logic decision device (100) can analyze, among multiple counseling algorithms, an algorithm that improves the customer return rate, an algorithm that induces visits, an algorithm derived from customer feedback, etc., and can recommend a counseling algorithm based on the analysis.

[0047] The logic decision device (100) can recommend a counseling algorithm (S0), generate a counseling algorithm (S1), apply the counseling algorithm (S2), and evaluate the performance of the counseling algorithm (S3).

[0048] FIG. 2 is a block diagram showing the configuration of a logic decision device (100) according to the present disclosure.

[0049] Referring to FIG. 2, the logic decision device (100) may include a communication unit (110), an input unit (120), a display (130), a memory (150), and at least one processor (190). The components of the logic decision device (100) illustrated in FIG. 2 are not essential for implementing the logic decision device (100) according to the present disclosure, and thus, the logic decision device (100) described in this specification may have more or fewer components than the components listed above.

[0050] Among the above components, the communication unit (110) may include one or more components that enable communication with various devices equipped with a communication device, and may include, for example, at least one of a wired communication device, a cellular-based wireless communication device, an IEEE 802.11-based (e.g., may be named Wifi), a short-range communication-based (e.g., may be, but is not limited to, Bluetooth, Bluetooth low energy, UWB, Zigbee), and a location information module. For example, the logic decision device (100) may transmit and / or receive data to and from a server through the communication unit (110). Here, the server may provide the logic decision device (100) with data that causes at least some of the operations performed by the various embodiments of the present disclosure, as described above. For example, when the logic decision device (100) is implemented as a stand-alone type, those skilled in the art will understand that data transmission and / or reception between the logic decision device (100) and the server is not required. The communication unit (110) may include a transceiver, a communicator, etc.

[0051] The input unit (120) is for inputting image information (or signal), audio information (or signal), data, or information input from a user, and may include at least one camera, a touch input device equipped on a touch screen, and / or at least one microphone, but is not limited thereto. Touch input, voice data, and / or image data for the touch screen collected by the input unit (120) may be analyzed and processed as a user's control command. The input unit (120) may include various input devices (inputters).

[0052] The camera processes image frames, such as still images or moving images, obtained by the image sensor in shooting mode. The processed image frames may be displayed on a display (130, or the screen of the logic decision device (100) of the present disclosure) or stored in a memory (150).

[0053] A microphone (hereinafter referred to as "microphone") processes external acoustic signals into electrical voice data. The processed voice data can be utilized in various ways depending on the function (or application) being performed by the device. Meanwhile, the microphone can implement various noise-reduction algorithms to eliminate noise generated during the process of receiving external acoustic signals.

[0054] The output unit is for generating output related to visual, auditory, or tactile sensations, and may include at least one of a display (130), at least one speaker, a haptic module, and an optical output device. The display (130) may be formed as a layer structure with a touch input device or formed as an integral part, thereby implementing a touch screen. Such a touch screen may perform an output function and / or an input function. The output device may include a device (outputter) for various outputs.

[0055] According to an embodiment, the logic decision device (100) may include a sensor, and sense at least one of information associated with at least one entity included in the logic decision device (100), information about the surrounding environment of the logic decision device (100), and information about a user wearing (or carrying) the logic decision device (100), and provide a sensing signal corresponding thereto. The processor (190) may control the driving and / or operation of the logic decision device (100) based on the sensing signal, or perform data processing, functions, or operations related to an application program installed in the device.

[0056] The memory (150) can store at least one instruction that causes the execution of various functions of the logic decision device (100). The memory (150) can store data for content expression (e.g., music files, still images, moving images, etc.). The memory (150) can store at least one application program (or application) that causes the logic decision device (100) to perform operations performed by various embodiments of the present disclosure, and data and commands for the operation of the logic decision device (100). At least some of these application programs can be downloaded from an external server via wireless communication. The logic decision device (100) can, for example, download the application and store it in the memory (150). The logic decision device (100) can perform operations performed by various embodiments of the present disclosure by executing the application. Alternatively, the logic decision device (100) can temporarily download data that causes the logic decision device (100) to perform operations performed by various embodiments of the present disclosure from a server and store it in the memory (150).

[0057] The memory (150) may include a storage medium corresponding to at least one type of a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Those skilled in the art will understand that the memory (150) may also mean, for example, a cache memory for linking with the processor (190) and / or a cache memory and / or a register included in the processor (190). Additionally, the memory (150) may be a database that is separate from the logic decision device (100) but connected by wire or wirelessly, and may be implemented as a database system.

[0058] The processor (190) may include one or more processors and may include at least one core. The processor (190) may execute instructions stored in the memory (150). The processor (190) may be implemented with a memory that stores data regarding an algorithm for controlling the operation of components within the logic decision device (100) or a program that reproduces the algorithm, and at least one processor (not shown) that performs the aforementioned operations using the data stored in the memory. In this case, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0059] In an embodiment, the logic decision device (100) may provide various UIs in the form of web services based on a platform, such as a website or web application, but is not limited thereto. Furthermore, the platform may be provided in the form of a PC application, a mobile application, or the like, but the embodiment is not limited thereto. In this case, various user terminals may utilize the various UIs provided by the logic decision device (100) based on a platform.

[0060] The processor (190) controls the processing of input data according to predefined operating rules or artificial intelligence models stored in the memory (150). Alternatively, if one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0061] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rules or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0062] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0063] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that imitates human neurons (biological neurons) to enable machines to learn. Artificial intelligence methodologies can be categorized into supervised learning, in which input data and output data are provided together as training data depending on the learning method, so that the solution (output data) to the problem (input data) is determined; unsupervised learning, in which only input data is provided without output data, so that the solution (output data) to the problem (input data) is not determined; and reinforcement learning, in which a reward (Reward) is provided from an external environment whenever an action (Action) is taken in the current state (State), and learning is performed in a direction to maximize this reward. In addition, artificial intelligence methodologies can be categorized according to the architecture of the learning model. The architectures of widely used deep learning technologies can be categorized into convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs).

[0064] The present device and system may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired result (output) from an arbitrary input (input) by changing the weights of neurons through learning.

[0065] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The models of the neural network can include various types of models such as CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, etc., but are not limited thereto. The processor can include one or more processors for performing calculations according to the models of the neural network. For example, the neural network can be a deep neural network. It may include a deep neural network.

[0066] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), Generative Adversarial Network (GAN), Liquid State Machine (LSM), Extreme Learning Machine (ELM), It will be understood by those skilled in the art that any neural network may be included, including but not limited to ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), KN (Kohonen Network), and AN (Attention Network).

[0067] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms can be used, including but not limited to Optimization, Recommendation, and Data Creation.

[0068] At least one component may be added or deleted to correspond to the performance of the components illustrated in Figure 2. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the system.

[0069] Meanwhile, each component illustrated in FIG. 2 refers to software and / or hardware components such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0070] FIG. 3 is a sequence diagram illustrating a process for generating a consultation algorithm using the automatic consultation algorithm interface of the logic decision device (100) according to the present disclosure. FIG. 4 is a screen for evaluating the performance of the consultation algorithm according to the present disclosure. FIG. 5 is a diagram illustrating a user interface for generating a specific consultation algorithm according to the present disclosure.

[0071] At step S310, the logic decision device (100) can set conditions to execute a counseling algorithm that automatically generates a message according to the treatment type.

[0072] The processor (190) can distinguish treatment types based on tags, and tags can include treatment categories and treatment types that are subordinate to the treatment categories. Treatment categories can vary depending on each medical specialty, and treatment types can be subordinate concepts of the treatment categories and include products and / or processes required for treatment.

[0073] When a specific treatment type or treatment product is created, the processor (190) can categorize it by adding it under a specific treatment category, and the treatment type tag can be used as data for customer-specific characteristic analysis (e.g., consumption ability, consumption tendency, etc.) as it is linked to characteristic information of the type / product.

[0074] The processor (190) can set conditions for executing a counseling algorithm, and can decide to execute the counseling algorithm when a preset criterion is met.

[0075] For example, the processor (190) may set a situation in which there is no communication with a specific customer for a predetermined period of time as an execution condition of a specific consultation algorithm, may set a situation in which there is no next reservation for a specific customer as an execution condition of a specific consultation algorithm, and may set a preset period, time, or season as an execution condition of a specific consultation algorithm, but the embodiment is not limited thereto.

[0076] In an embodiment, the processor (190) may also consider cases where a counseling algorithm is executed by a counseling bot. Cases where the counseling bot is executed may occur outside of hospital staff's working hours or at the request of hospital staff, but the present disclosure is not limited thereto.

[0077] At step S320, the processor (190) can list automatically generated messages of preset counseling algorithms corresponding to treatment types in a time series manner.

[0078] Referring to FIG. 4, the processor (190) can generate a specific counseling algorithm when an algorithm addition item (330) is selected, but the generation of the specific counseling algorithm can be performed through various routes.

[0079] Referring to FIG. 5, when a command to generate a specific algorithm is received, the processor (190) can sequentially list (451, 461, 471, 481) an automatic generation message of a preset counseling algorithm corresponding to a treatment type in a specific area (AR6).

[0080] When receiving a command to generate a specific algorithm, the processor (190) may determine whether the algorithm is a consultation algorithm or a marketing algorithm. For example, as illustrated in FIG. 4, if the consultation algorithm (BB1) is selected, the processor (190) may receive a command to generate a consultation algorithm, and if the marketing algorithm is selected, the processor (190) may receive a notification that the marketing algorithm has been selected.

[0081] In an embodiment, the processor (190) may also receive information about the treatment type, thereby guiding the generation of a specific algorithm corresponding to the treatment type. The processor (190) may pre-store each treatment process and / or response process in the memory (150) for each treatment type. For example, after providing a notification message (451) related to a specific treatment, the processor (190) may pre-store in the memory (150) a message asking for the customer's well-being after visiting the hospital (461), a message after the first week of treatment (471), a message after the second week of treatment (481), etc.

[0082] In an embodiment, the processor (190) may sequentially list automatically generated messages according to treatment type, and may recommend automatically generated messages to be transmitted to customers in chronological order, expected feedback messages that may be received from customers, response messages to feedback messages, etc. based on previous consultation records, automatically generated messages that must be provided according to treatment type, customer feedback messages according to previously collected treatment types, etc.

[0083] At this time, the processor (190) can display performance information of the automatically generated message itself by using information such as actual customer feedback messages and number of reservation conversions while operating the corresponding consultation algorithm.

[0084] The processor (190) may preferentially display essential automatic generation messages and automatic generation messages with high performance scores according to automatic generation message transmission for each treatment type, and in the case of optional automatic generation messages, may display them when additional process items (IN1, IN3, IN5, etc.) are selected, but the embodiment is not limited thereto.

[0085] Here, the automatically generated message may include at least one of text, an image, a video, event information, and notice information. At least some of the text, image, video, event information, and notice information may be combined and transmitted by user operation.

[0086] The processor (190) can sort and display only the customer's feedback messages from among the previous consultation materials, and can recommend an automatically generated message that can respond to each of the sorted customer's feedback messages.

[0087] At step S330, when an item for modifying an automatically generated message listed in time series is selected (e.g., 461), the processor (190) may indicate (461B) that the automatically generated message corresponding to the selected item is in an editable state.

[0088] The processor (190) may provide an option to modify at least one of the name of the automatically generated message (441), information related to the treatment type (442), conditions displayed in the chat window with the customer (443), message sending conditions (444), and message type information (445, e.g., text, image, video, event, notice, etc.).

[0089] In an embodiment, the processor (190) may list automatically generated messages of a counseling algorithm, and then, based on the treatment type manual and response manual pre-stored in the memory (150), fill in the name of each automatically generated message (441), treatment type-related information (442), conditions displayed in a chat window with a customer (443), message sending conditions (444), and message type information (445) by default. If the processor (190) has a field that is difficult to fill in by default, it may leave it blank.

[0090] The processor (190) can display performance information of automatically generated messages listed in time series. For example, the processor (190) can display the number of recipients of the automatically generated message, response information, number of reservation conversions, etc. in the automatically generated message.

[0091] Additionally, the processor (190) may disable the deletion or modification function for automatically generated messages that must be included depending on the treatment type.

[0092] At step S340, the processor (190) may display an item for adding a new message between the automatically generated messages listed in time series.

[0093] Once the generation of a counseling algorithm is complete, the processor (190) can execute and operate the counseling algorithm according to preset execution conditions. Furthermore, the processor (190) can analyze the performance of the executed counseling algorithm.

[0094] Referring to FIG. 4, the results of the generated consultation algorithm can be displayed. The processor (190) can divide the main screen into multiple areas (AR1 to AR4), and can display screen window control menus (moving to previous screen, moving to next screen, refreshing, changing screen minimum, changing screen maximum, deleting screen, etc.) in the first area (AR1), and can display various menus in the second area (AR2), and the processor (190) can display menus for performing authority change, notification, administrator chat, consultation, customer management, algorithm-related (516), reservation management, employee management, notices, events, video content and settings, etc. in the second area (AR2).

[0095] When the algorithm-related (516) menu is selected, the processor (190) can display a consultation algorithm (consultation and / or marketing) in the third area (AR3), and can display the number of saved consultation algorithms by category (consultation / marketing) (e.g., BB1).

[0096] When a counseling algorithm (BB1) is selected, the processor (190) can display at least some of the counseling algorithms pre-registered based on tags in the fourth area (AR4) on an analysis screen according to criteria, and display information for determining the performance of the counseling algorithm displayed on the analysis screen.

[0097] Here, tags of multiple counseling algorithms may include treatment categories and treatment types belonging to the treatment categories.

[0098] For example, the processor (190) may map elasticity / wrinkle-related information to a treatment category for a specific consultation algorithm (310). The treatment categories may be diverse, such as skin-related, pigment-related, petite-related, hair removal-related, and lifting-related, and the embodiment is not limited thereto. The processor (190) may display, in the first area (AR4A) of the analysis screen, at least one piece of information among the number of target customers (312), the number of feedback provided (313), and the number of reservation conversions (18) related to the displayed consultation algorithm (310).

[0099] The processor (190) may deactivate a counseling algorithm according to item selection when the performance point of one of the plurality of counseling algorithms is less than a preset standard performance point (e.g., 320).

[0100] The processor (190) can display at least one of a consultation-related indicator, a hospital-related indicator, and an indicator for improving hospital operation efficiency in a second area (e.g., AR4B) of the analysis screen.

[0101] When displaying a counseling-related indicator, the processor (190) may display at least one of the number of times feedback is provided by treatment classification or treatment type, the number of times responses are provided by counselor, and the number of times reservations are converted.

[0102] Below, an embodiment of executing a plurality of generated consultation algorithms by a logic decision device (100) will be described.

[0103] The processor (190) of the logic decision device (100) can perform customer response using only a consultation algorithm whose performance is above a predetermined level.

[0104] The processor (190) can provide a customer with a message automatically generated by a counseling algorithm. The processor (190) can pre-register (e.g., store or use) one or more counseling algorithms. The counseling algorithms can be logic that recommends and provides automatically generated messages for counseling and / or responding to the customer's treatment.

[0105] Here, treatment can encompass a wide range of services a hospital can provide to customers, including treatment, care, and counseling. Automatically generated messages can include at least one of text, images, videos, event information, and announcement information, but the embodiments are not limited thereto.

[0106] The processor (190) can manage a consultation algorithm based on tags, and tags can include treatment categories (or procedure categories) and treatment types that fall under the treatment categories. Treatment categories can vary depending on each medical specialty, and treatment types can include sub-concepts of the treatment categories, or products and / or processes required for treatment within the treatment categories.

[0107] When a specific treatment type or treatment product is created, the processor (190) can categorize it by adding it under a specific treatment category, and the treatment type tag can be used as data for customer-specific characteristic analysis (e.g., consumption ability, consumption tendency, etc.) as it is linked to characteristic information of the type / product.

[0108] The processor (190) can set the logic execution time of each counseling algorithm. For example, the processor (190) can execute each counseling algorithm in the background and set the execution time in advance so that it is executed at a specific time.

[0109] The processor (190) can set the logic execution time of each counseling algorithm as well as the execution time of automatically generated messages recommended and / or suggested by each counseling algorithm (e.g., the time to send to the customer or the time to display on the main screen, etc.).

[0110] The processor (190) may provide a message encouraging the customer to visit and / or a marketing-related message to a terminal corresponding to the customer based on the customer's consultation record or visit record.

[0111] The processor (190) can display the customer's previous consultation history, and when a specific visit encouragement message was sent in the customer's previous consultation, if there was positive feedback or visit from the customer, the processor can provide a message encouraging the customer's visit and / or a marketing-related message to the terminal corresponding to the customer based on this.

[0112] In addition, the processor (190) may provide a message encouraging the customer to visit and / or a marketing-related message to a terminal corresponding to the customer based on the customer's visit record, if there is a treatment or process that is an extension of the treatment the customer has undergone.

[0113] In an embodiment, the processor (190) may execute each counseling algorithm in a process or thread manner, and may execute the counseling algorithm corresponding to a preset execution time. For example, the processor (190) may preset the conditions under which each counseling algorithm is to be executed, and may execute the counseling algorithm based on a specific time point, a specific cycle, etc., or may execute the counseling algorithm when a specific event occurs (e.g., an epidemic, a fine dust index exceeding a preset value, a preset temperature, humidity value, etc.), but the execution conditions are not limited to the present disclosure.

[0114] In an embodiment, the processor (190) can correspond the consultation algorithm to an unmanned consultation robot, and when the consultation algorithm is executed by the unmanned robot, the consultation algorithm cannot be interrupted by the operation of hospital staff (exceptions may apply), and the unmanned robot can proceed with the consultation. If there is a request by a user operation, the processor (190) can change the consultation subject from the unmanned robot to a hospital staff member.

[0115] In an embodiment, if a consultation is conducted by an unmanned consultation robot, the processor (190) may compile the consultation content into a log and store the consultation content in memory (150) so that an administrator can later evaluate the appropriateness of the consultation content. In addition, if a consultation is conducted by an unmanned consultation robot, the processor (190) may provide a notification to the relevant terminal.

[0116] The processor (190) can receive a customer feedback message for the automatically generated message.

[0117] The processor (190) can transmit various automatically generated messages to the customer's terminal to encourage the customer to return. The automatically generated messages may include greeting messages, messages related to the progress of treatment during a hospital visit, messages necessary or recommended regarding treatment during a previous visit, marketing messages, etc. The format of the automatically generated messages may include at least one of text, image, video, event information, and notice information, but the embodiments are not limited thereto.

[0118] The processor (190) can evaluate the performance of the consultation algorithm and the automatically generated message of the consultation algorithm by differentially assigning a score when a customer feedback message is received for an automatically generated message, when the customer feedback message is a positive message for consultation and / or visit, when the customer feedback message is a negative message for consultation and / or visit, or when the customer feedback message is not received for a specific period of time.

[0119] The processor (190) can evaluate the performance of each counseling algorithm based on the customer's feedback message and then reflect it in the counseling algorithm operation plan.

[0120] The processor (190) can guide response services for received customer feedback messages. Specifically, the processor (190) can provide a hospital treatment type manual and a response manual for the customer's message.

[0121] The treatment type manual may include treatment type information corresponding to various departments (e.g., dermatology, rehabilitation medicine, etc.), treatment methods corresponding to the treatment type, treatment products, treatment processes, treatment precautions, etc., but the examples are not limited thereto.

[0122] The treatment type manual can be implemented in dictionary form based on tags according to the patient's treatment type, and can be provided by expanding the treatment type manual area that requires customer guidance.

[0123] The response manual may include response directions, response methods, response messages, etc. according to customer messages, but the examples are not limited thereto.

[0124] The processor (190) can provide a customized treatment type manual and response manual based on a consultation algorithm based on the customer's consultation record or visit record.

[0125] In an embodiment, the processor (190) may cause information related to the customer's previous treatment type (including treatment classification and / or treatment type, etc.) to be placed at the top of the screen based on the customer's consultation record and / or visit record.

[0126] The processor (190) can display on the screen, based on the customer's consultation record and / or visit record, information related to treatment that needs to be performed after a previous consultation or visit, and can highlight and display the information.

[0127] The processor (190) can provide a customized response manual based on a consultation algorithm based on the customer's feedback message. The processor (190) can provide a response manual for positive customer feedback messages and a response manual for negative customer feedback messages.

[0128] The processor (190) may provide a phrase indicating an emotional state in a customer's feedback message using a pre-installed emotional state identification model. The emotional state identification model may include an emotional expression database and may be a model trained to output the corresponding emotional state when a phrase, emoticon, etc., contains an emotional state. To this end, the processor (190) may utilize a syntax analysis algorithm, a morphological analysis algorithm, etc., but the embodiment is not limited thereto.

[0129] The processor (190) can display consultation examples based on the customer's consultation records and / or visit records stored in the memory (150). When the processor (190) receives a feedback message corresponding to a specific treatment type of the customer, it can display a corresponding consultation example in cases where a positive outcome (e.g., a revisit, consultation progress, etc.) is achieved, and the hospital staff can proceed with the consultation with reference to this.

[0130] The processor (190) can automatically generate a response message to a customer's feedback message through a consultation algorithm based on the provided treatment type manual and response manual.

[0131] The processor (190) can display an automatically generated response message in a chat window with the customer.

[0132] The processor (190) can transmit a response message to a terminal corresponding to a customer by means of a transmission trigger operation. At this time, the automatically generated response message can be edited.

[0133] The processor (190) can recommend one or more response messages for each type of treatment corresponding to the customer based on a consultation algorithm, and can display a response message selected by user operation from among the recommended response messages in a chat window with the customer.

[0134] The processor (190) can output the main screen to the display (130).

[0135] The processor (190) can configure the main screen differently for each hospital. The processor (190) can separately manage information specific to each hospital, and can also utilize shared information that can be shared among various hospitals. The processor (190) can provide the main screen on a SaaS (software as a service) basis, but the present disclosure is not limited thereto.

[0136] The processor (190) can divide the main screen into multiple areas, and can display a screen window control menu (moving to the previous screen, moving to the next screen, refreshing, changing the screen minimum, changing the screen maximum, deleting the screen, etc.) in the first area, and can display various selection menus in the second area. The processor (190) can display menus for performing authority change, notification, administrator chat, consultation, customer management, algorithm-related (consultation and / or marketing), reservation management, employee management, notices, events, video content, and settings, etc. in the second area.

[0137] The processor (190) can display a message inbox in the third area. The processor (190) can display the status of messages (e.g., waiting, in progress, completed, total number of messages, etc.) and can prioritize customer messages and display them at the top of the third area. Furthermore, the processor (190) can display messages sorted based on various options (e.g., most recent conversations, top sales customers, etc.).

[0138] In an embodiment, the processor (190) may place messages received but not confirmed by a representative, messages from excellent customers, etc., at the top of the inbox, but the present disclosure is not limited thereto. Furthermore, the processor (190) may place messages requesting consultation or a visit at the top, and messages requesting general consultation at the bottom, but the present disclosure is not limited thereto.

[0139] The processor (190) can display a treatment type manual in the fourth area. For example, in the case of dermatology, the processor (190) can display skin booster, beauty (filler, etc.), botox, tattoo removal, skin correction laser, pore / wound laser, cryotherapy, beauty (lifting, etc.), thread lifting, high-frequency lifting, liftera lifting, foot care, etc. In the case of orthopedics, rehabilitation medicine, etc., the processor (190) can display various manual therapy programs, but the present disclosure is not limited thereto.

[0140] In an embodiment, the processor (190) may display guidance information related to tattoo removal (e.g., 'In the case of eyebrow or eyelash tattoo removal, please note that hair will turn white and fluff will start to grow back within about a month', 'Ice compresses are helpful for swelling and redness on the day of the procedure, and in severe cases, blisters may occasionally form. In this case, please note to visit a hospital for treatment') and display precautions.

[0141] At this time, the processor (190) can separately extract precautions from the guidance information related to tattoo removal. For example, the processor (190) can highlight information about the tattoo area, potential pain occurring at the tattoo area, symptom information, time-related information, etc., and when the send button is selected by the user, the corresponding precautions can be transmitted to the customer's terminal.

[0142] In this embodiment, the processor (190) may determine the customer's treatment type based on the customer's treatment history, consultation history, visit history, feedback messages, etc. The processor (190) may place information related to the determined treatment type at the top, and may proceed with a process of confirming whether the determined treatment type is a treatment type of interest during a chat with the customer.

[0143] If the customer's treatment type is not a determined treatment type, the processor (190) can ask the customer about the treatment type, and if the customer mentions the treatment type through a chat window via a feedback message, the processor (190) can display a treatment type manual related to the mentioned treatment type at the top of the screen.

[0144] In an embodiment, the processor (190) may display a treatment type manual and a response manual, and assist with consultation by highlighting portions that require mention during the consultation. For example, the processor (190) may highlight content that must be mentioned in a specific treatment type and reflect it in an automatically generated message. Furthermore, the processor (190) may highlight content that must be mentioned in a response message and reflect it in an automatically generated message.

[0145] The processor (190) can display a chat with a customer in the fifth area.

[0146] The processor (190) can activate or deactivate the automatic generation of response messages by the consultation algorithm. If the automatic message generation function is activated, the processor (190) displays the message, and when a transmission trigger command is input by a hospital staff member (e.g., clicking a transmission button), the processor transmits the message to the customer's terminal, indicating that the message was generated by the algorithm bot.

[0147] The processor (190) can transmit a response message and display information about the sender (e.g., 'Lee OO') when the automatic response message generation function is disabled or when the hospital staff intentionally does not use the automatic response message generation function.

[0148] In an embodiment, the processor (190) may store the consultation content of the consultation bot in the memory (150) when the consultation bot provides consultation.

[0149] In an embodiment, if the customer terminal does not receive the transmitted response message, the processor (190) can remove the response message from the chat window using the "Recall" function. The processor (190) can preset the management staff who can use the "Recall" function.

[0150] In an embodiment, the processor (190) may display automatically generated response messages in a chat window with the customer, and may provide a user interface that lists recommended messages by type within a response guide, allowing hospital staff to select a corresponding message and send the response message. In this case, the processor (190) may display and provide response messages that received a favorable response from the customer and / or response messages that had a high rate of return from the customer at the top of the recommended messages.

[0151] In an embodiment, the processor (190) can recognize a patient's feedback message and automatically recommend a recommended response message. The processor (190) can recommend the most effective response message to the patient's feedback message recognized among previously conducted consultation examples.

[0152] To this end, the processor (190) can analyze multiple response messages and feedback messages before sending a response message and display the response message with the highest customer revisit rate or the response message with positive customer feedback in the chat window.

[0153] After the processor (190) displays an automatically generated message, the transmission trigger for text guidance information and image information, etc. can be performed by user operation.

[0154] The processor (190) provides an area where the customer's previous treatment history can be checked, so that consultation can be conducted based on the provided information.

[0155] In addition, the processor (190) can secure the customer's treatment / procedure results through linkage with various EMRs (electronic medical records) and CRMs, etc., so that consultation services can be provided based on accurate previous medical records during consultation.

[0156] The processor (190) can display on the screen if a person in charge mapped to a customer is not specified.

[0157] The processor (190) can display a customer information / reservation information selection menu in the sixth area, and when customer information is selected, the customer's name, chart number, date of birth, gender, patient type (e.g., re-examination), and customer memo information. The customer memo information can include disease information, medication information, treatment type, treatment site, cost information, referral route information, contact type, etc.

[0158] The processor (190) can display a response manual. For example, the processor (190) can display a response manual necessary when the patient is dissatisfied with the treatment, when it is difficult to determine satisfaction / dissatisfaction, when the patient is satisfied with the treatment, etc., and the processor (190) can provide a response manual based on the type of treatment and the emotional state of the customer.

[0159] For example, if the processor (190) is dissatisfied with the treatment, it can guide the patient to confirm the dissatisfied part, to check the symptom and to visit the hospital for improvement, and to schedule the earliest visit, etc. If it is difficult to confirm satisfaction / dissatisfaction, the processor (190) can guide the patient to express empathy for the customer, to recommend consultation for improved effects on the area of ​​concern, and to schedule the earliest visit, etc. If the patient is satisfied, the processor (190) can guide the patient to express empathy, to express interest in the customer, and to decide whether to proceed with additional treatment, etc.

[0160] The processor (190) can select and display customer information or reservation information in the sixth area. When making a reservation, the processor (190) can recommend a recommended reservation time.

[0161] Additionally, when reservation information is selected, the processor (190) can display current reservation information and set a reservation time through a reservation menu. In an embodiment, the processor (190) can recommend reservations based on the recommended time for the procedure.

[0162] The processor (190) can provide a list of customers to be contacted and a customer analysis page to manage customer re-visits.

[0163] The processor (190) can store the name, date of birth, contact information, treatment type information, etc. of the customer who will receive the push message (automatically generated message), and then send the push message at a preset time and check whether it has been received. If the customer does not respond even after receiving the push message a preset number of times, the processor (190) can send the push message after a preset time or exclude the customer from the list of customers to whom the push message has been sent.

[0164] In an embodiment, the processor (190) may allow consultation algorithms corresponding to multiple treatment types within the same treatment category to compete. For example, the processor (190) may determine the marketing effectiveness of multiple consultation algorithms related to elasticity and wrinkles based on a predetermined period of time. The processor (190) may update the consultation algorithm with the highest marketing effectiveness by executing various algorithms for each treatment category, but the present disclosure is not limited thereto.

[0165] When generating a consultation algorithm, the processor (190) may recommend a consultation algorithm with the highest marketing score, and depending on the implementation example, the consultation algorithm may be selectively provided based on a billing process, but the present disclosure is not limited thereto.

[0166] FIGS. 6 and 7 are diagrams for explaining a method of organizing a customer's hospital service information into a database and utilizing it for marketing purposes to induce a customer's re-visit according to the present disclosure.

[0167] The processor (190) can build a database of the customer's hospital service information to encourage the customer to revisit, and the built database can be placed inside the hospital or in an authorized external location.

[0168] The processor (190) can build information on returning patients to effectively conduct the hospital's own marketing. The processor (190) can provide overall customer visitor information, recent customer visitor information, etc., and can manage customer treatment, visit purpose, and treatment performed / implemented information based on tags for marketing purposes.

[0169] For example, the processor (190) can update the customer's treatment / hospital services, services of interest, etc., using the classification information. The processor (190) can perform marketing activities based on the updated information.

[0170] The processor (190) can list all customer information and output it to the display (130). The processor (190) can sort all customers based on various filters, such as by excellent customers, by customers who responded effectively to feedback messages, by customers who recently visited, and by customers according to the type of procedure / treatment received. In addition, the processor (190) can list customer information in order of most recently registered or unregistered tags. In this way, the processor (190) can guide the hospital to perform its own marketing services using a pre-built database.

[0171] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0172] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0173] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. As a logic decision device of a hospital consultation algorithm utilizing an automatic consultation algorithm interface, Memory that stores one or more instructions; and At least one processor configured to execute the instructions stored in the memory, The one or more instructions, when executed by the at least one processor, cause the logic decision unit to perform at least one operation; At least one of the above actions: Actions that set conditions to run a counseling algorithm that automatically generates messages based on the type of treatment; An action of listing automatically generated messages of a preset counseling algorithm corresponding to the above treatment type in a time series manner; When an item for modifying the automatically generated message listed in the above time series is selected, an action of displaying the automatically generated message corresponding to the selected item in an editable state; and A logic decision device comprising an action for displaying an item for adding a new message between the automatically generated messages listed in the above time series.

2. In paragraph 1, The above auto-generated message is, A logic decision device comprising at least one of text, image, video, event information, and notice information.

3. In paragraph 2, The action of displaying the above auto-generated message in an editable state is: A logic decision device comprising an action that provides an option to modify at least one of the name of the automatically generated message, information related to the treatment type, conditions displayed in the chat window with the customer, message sending conditions, and message type information.

4. In paragraph 3, The above actions listed in time series are: A logic decision device comprising an operation for displaying performance information of automatically generated messages listed in the above time series.

5. In paragraph 4, At least one of the above actions: A logic decision device including an action for disabling the deletion or modification function for automatically generated messages that must be included according to the above treatment type.

6. A method for determining the logic of a hospital consultation algorithm using an automatic consultation algorithm interface performed by a processor. A step of setting conditions for executing a counseling algorithm that automatically generates messages depending on the type of treatment; A step of listing automatically generated messages of a preset counseling algorithm corresponding to the above treatment type in a time series manner; When an item for modifying the automatically generated message listed in the above time series is selected, a step of displaying the automatically generated message corresponding to the selected item in an editable state; and A logic decision method comprising the step of displaying an item for adding a new message between the automatically generated messages listed in the above time series.

7. In paragraph 6, The above auto-generated message is, A logic decision method comprising at least one of text, image, video, event information, and notice information.

8. In paragraph 7, The step where the above auto-generated message is displayed in an editable state is: A logic decision method comprising a step of providing an option to modify at least one of the name of the automatically generated message, information related to the treatment type, conditions displayed in the chat window with the customer, message sending conditions, and message type information.

9. In paragraph 8, The steps listed in the above chronological order are: A logic decision method comprising the step of displaying performance information of automatically generated messages listed in the above time series.

10. In paragraph 9, After the above chronological listing step, A logic decision method further comprising a step of disabling a deletion or modification function for automatically generated messages that must be included according to the above treatment type.

Images