Apparatus and method of evaluation for memory

Abstract

A memory evaluation device is disclosed, comprising: setting a target word to be used for memory evaluation and a target image representing said target word; displaying said target image in one area of ​​said learning page; setting a distraction image representing a distraction word having a different meaning from said target word; setting an alternative image representing said target word or said distraction word, which has at least a partially different form from said target image or said distraction image; displaying at least two images among said target image, said distraction image, and said alternative image so that said target image can be selected on a first evaluation page; displaying a plurality of partitioned areas of said learning page so that an area where said target image is displayed can be selected on a second evaluation page; and evaluating at least one of visual memory, spatial memory, and verbal memory based on the learning of said target image according to the selection result of said target image and the selection result of any one of said partitioned areas.

Description

Technology Field

[0001] The present disclosure relates to an apparatus and method for evaluating memory. More specifically, it relates to an apparatus and method for evaluating visual, spatial, and verbal memory. Background Technology

[0002] Memory is broadly divided into short-term and long-term memory, which are further classified into verbal memory and visuospatial memory (non-verbal memory). The memory process consists of the input, storage, and retrieval of information, and the exercise of appropriate attention is required for efficient information processing at each stage. Attention encompasses the ability to maintain concentration for extended periods to achieve a given goal, discriminate specific stimuli among various stimuli, and appropriately allocate limited processing capacity. Furthermore, working memory, which maintains and manipulates input information during the information processing process, is crucial; working memory refers to the ability to solve problems by integrating and organizing verbal or visuospatial information.

[0003] Since memory function, particularly the recall and learning of numbers, language, and shapes, is a cognitive function closely linked to daily living abilities, memory decline is a cognitive symptom commonly reported not only by patients with dementia or brain injury but also by those with psychiatric disorders such as depression or anxiety, as well as by the general public. Regular diagnostic evaluations, treatment strategies, and prognosis assessments regarding memory functions across various domains are subjects of significant interest not only from a psychiatric perspective but also from legal and socioeconomic viewpoints.

[0004] Dementia is a condition characterized by an acquired decline in cognitive functions across various domains, such as memory, language, and judgment, which prevents the proper performance of daily activities. Starting with early forgetfulness, symptoms intensify as cognitive functions—including language, spatial orientation, and calculation—deteriorate sequentially. Furthermore, changes in personality and emotions increase the likelihood of experiencing emotional disorders like depression, thereby increasing the burden on caregivers and impairing the overall quality of life. Given the nature of these impairments, detecting symptoms and intervening with treatment at the early stages—when signs of cognitive decline appear even if the condition has not yet developed into dementia—is paramount for dementia prevention. Particularly for the elderly and dementia patients, a lack of knowledge and insight into cognitive decline means that subjective complaints of memory problems are highly likely to fail to adequately reflect the objective level of memory loss. Therefore, for successful prevention and rehabilitation, it is essential to evaluate the level of memory decline accurately and objectively through regular checkups.

[0005] General tests evaluating memory are more often based on verbal modalities than on visual modalities. This is because tests based on verbal modalities are easier to administer. A representative test evaluating episodic memory based on verbal modalities is the word list learning test, in which a series of words is typically presented to the subject one by one, after which the subject is instructed to learn the list. After the learning process, the subject may be asked to recall the list to verify whether they correctly encoded and stored the words, or other interfering words may be presented to ask if they were present in the learned list. However, it is difficult to fully evaluate episodic memory using such verbal modal tests because episodic memories are retained as spatiotemporal information rather than being stored as language in daily life. Furthermore, patients with mild cognitive impairment (MCI) who performed poorly on visual recognition tests showed poor performance on verbal recall tests even when provided with cues. This suggests that the recognition function of visual memory is important in detecting early cognitive decline. Therefore, it is necessary to evaluate episodic memory based on visual modalities as well as linguistic ones. Consequently, many neuropsychological tests have developed visual memory tests; however, due to the inherent limitations of these tests, it is currently difficult to use them as comprehensive visual memory assessments.

[0006] The first limitation is that even if many tests are designed to be visual memory tests, they are often not entirely visual memory tests. For instance, even if the form presented is visual, the mode of memory itself that the user remembers is a verbal mode, so it cannot be considered a complete visual memory test.

[0007] Secondly, to overcome these limitations, there are attempts to present stimuli using abstract methods so that the test stimuli themselves are not verbalized. However, these attempts themselves suffer from low ecological validity because excessive abstraction fails to reflect the everyday stimuli encountered in real life. Furthermore, the problem that verbalization is possible even with abstraction still persists.

[0008] Finally, visual memory can be divided into visual identity and spatial information regarding location. However, existing tests evaluating visual memory often fail to consider these aspects. In reality, memory is divided into two systems: the Anterior Temporal (AT) system, which processes object identity and content information, and the Posterior Medial (PM) system, which processes spatial and contextual information. The functional and anatomical classification of these two systems is integrated in the entorhinal cortex (EC). The EC acts as a hub that processes object and contextual information separately and integrates them; the integrated information is then transmitted to the hippocampus (HC) to form episodic memory. However, damage to the hippocampus impairs the ability to correctly combine object identity and location, which severely impacts memory integration and recall.

[0009] In such conventional memory evaluation systems, there is a need to develop a method capable of integrated evaluation of visual, spatial, and verbal memory. Prior art literature

[0010] Published Patent 10-2014-0133412(2014.11.19) The problem to be solved

[0011] The purpose of the embodiments disclosed in this disclosure is to provide a memory evaluation device and method that enable not only verbal memory tests but also visual and spatial memory tests to be performed naturally.

[0012] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0013] An apparatus according to the present disclosure for achieving the technical objectives described above comprises: a display; and a processor that performs memory evaluation by displaying a learning page and a plurality of evaluation pages through the display. The processor sets a target word to be used for memory evaluation and a target image representing the target word, displays the target image in one area of ​​the learning page, sets a distraction image representing a distraction word having a different meaning from the target word, sets an alternative image representing the target word or the distraction word, and has at least a partially different form from the target image or the distraction image, displays at least two images among the target image, the distraction image, and the alternative image so that the target image can be selected in a first evaluation page, displays a plurality of partitioned areas of the learning page so that an area where the target image is displayed can be selected in a second evaluation page, and evaluates at least one of visual memory, spatial memory, and verbal memory based on the learning of the target image according to the selection result of the target image and the selection result of any one of the plurality of partitioned areas.

[0014] Meanwhile, the first evaluation page displays the target image, a first alternative image having at least some form different from the target image, and an icon for selecting the case where the target image is not present, and the processor evaluates visual memory or verbal memory as a first type when the target image is selected through the first evaluation page, evaluates visual memory as a second type or verbal memory as a first type when the first alternative image is selected through the first evaluation page, and evaluates visual memory or verbal memory as a second type when the icon is selected through the first evaluation page.

[0015] Additionally, the first evaluation page displays the interference image, a second alternative image having at least some form different from the interference image, and the icon, and the processor evaluates the visual memory or language memory as a second type when the interference image or the second alternative image is selected through the first evaluation page, and evaluates the visual memory or language memory as a first type when the icon is selected through the first evaluation page.

[0016] In addition, the first evaluation page may alternately provide a first object recognition evaluation screen displaying the target image, the first alternative image, and the icon, and a second object recognition evaluation screen displaying the interference image, the second alternative image, and the icon.

[0017] Additionally, the processor may evaluate the spatial memory as a first type when the area among the plurality of partition areas where the target image is displayed is selected through the second evaluation page, and evaluate the spatial memory as a second type when the area among the plurality of partition areas different from the area where the target image is displayed is selected through the second evaluation page.

[0018] Additionally, the processor includes a database in which words are classified and stored by a plurality of categories, sets a category among the plurality of categories to be used for memory evaluation, and can set a target word based on a typicality value indicating the degree to which a word classified into the set category represents the set category.

[0019] In addition, the processor may set multiple target words belonging to different categories, and may set the multiple target words as words having different typicality values.

[0020] Additionally, the processor may set a word classified into the same category as the target word as the interfering word, or set a word classified into a different category from the target word as the interfering word.

[0021] Additionally, the processor may generate a target word set by setting a plurality of target words belonging to different categories and a plurality of interference words corresponding to each of the plurality of target words, wherein some of the plurality of interference words are set as words classified in the same category as their respective corresponding target words, and the remaining portions of the plurality of interference words are set as words classified in a different category from their respective corresponding target words.

[0022] Meanwhile, the method according to the present disclosure comprises a memory evaluation method performed by a memory evaluation device, the method including: a step of setting a target word to be used for memory evaluation and a target image representing the target word; a step of displaying the target image in one area of ​​a learning page; a step of setting a distracting word having a different meaning from the target word and a distracting image representing the distracting word; a step of setting an alternative image representing the target word or the distracting word, having at least a partially different form from the target image or the distracting image; a step of displaying at least two images among the target image, the distracting image, and the alternative image so that the target image can be selected on a first evaluation page; a step of displaying a plurality of partitioned areas of the learning page so that an area where the target image is displayed on a second evaluation page can be selected; and a step of integratively evaluating visual memory, spatial memory, and verbal memory based on the learning of the target image according to the selection result of the target image and the selection result of any one of the plurality of partitioned areas.

[0023] In addition to this, a computer program stored on a computer-readable recording medium for executing the present disclosure may be further provided.

[0024] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided. Effects of the invention

[0025] According to the aforementioned means for solving the problem of the present disclosure, the evaluation of verbal memory, visual memory, and spatial memory can be performed integrally, thereby enabling a more accurate assessment of the subject's overall cognitive ability. In particular, it has the advantageous effect of overcoming the limitations of conventional memory evaluation methods, which ultimately result in an evaluation of verbal memory, by allowing the evaluation of visual memory and spatial memory to be performed naturally simultaneously with the evaluation of verbal memory.

[0026] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0027] FIG. 1 is a conceptual diagram of a memory evaluation system according to one embodiment of the present disclosure. FIG. 2 is a control block diagram of a device according to one embodiment of the present disclosure. FIG. 3 is a flowchart of a memory evaluation method according to one embodiment of the present disclosure. FIG. 4 is a detailed flowchart of step S10 illustrated in FIG. 3, and FIG. 5 is an example of a learning page according to one embodiment of the present disclosure. FIG. 6 is a detailed flowchart of step S20 illustrated in FIG. 3, FIG. 7 is an example of a target image and a interference image according to one embodiment of the present disclosure, FIG. 8 is an example of a target image and a replacement image according to one embodiment of the present disclosure, and FIG. 9 is an example of a first evaluation page according to one embodiment of the present disclosure. FIG. 10 is a detailed flowchart of step S30 illustrated in FIG. 3, and FIG. 11 is an example of a second evaluation page according to one embodiment of the present disclosure. FIGS. 12 to 14 are detailed flowcharts of step S40 shown in FIG. 3. Specific details for implementing the invention

[0028] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0029] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0030] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0031] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0032] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0033] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0034] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0035] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0036] In this specification, the term "device according to the present disclosure" includes all various devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include all of a computer, a server device, and a portable terminal, or may be in the form of any one of these.

[0037] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0038] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0039] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0040] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the 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.

[0042] FIG. 1 is a conceptual diagram of a memory evaluation system according to one embodiment of the present disclosure.

[0043] Referring to FIG. 1, a memory evaluation system (10) according to one embodiment of the present disclosure may include a device (100) and a user terminal (200).

[0044] The device (100) can provide a memory evaluation service according to the present disclosure.

[0045] The memory evaluation service according to the present disclosure may provide a learning process for target words, evaluate visual memory naturally while evaluating linguistic memory after the learning process, and subsequently provide a process for evaluating spatial memory. That is, the memory evaluation service according to the present disclosure executes a recognition evaluation process divided into object recognition evaluation and location recognition evaluation after the learning process, and the recognition evaluation process may be configured so that not only linguistic memory but also visual memory regarding the object itself, excluding linguistic memory, can be naturally evaluated simultaneously. Meanwhile, the memory evaluation service according to the present disclosure may further include a memory evaluation training function.

[0046] The user terminal (200) can be connected to the device (100) via a network and can receive a memory evaluation service according to the present disclosure from the device (100).

[0047] For example, a user terminal (200) may access a website or install an application to receive a service according to the present disclosure. The user terminal (200) may exchange data through the website or the application.

[0048] A memory evaluation system (10) according to one embodiment of the present disclosure has the advantageous effect of enabling the evaluation of verbal memory, visual memory, and spatial memory to be performed in an integrated manner, thereby allowing for a more accurate assessment of the subject's overall cognitive ability, and in particular, enabling the evaluation of visual memory and spatial memory to be performed naturally at the same time as the evaluation of verbal memory, so as to overcome the limitations of conventional memory evaluation methods which ultimately result in the evaluation of verbal memory.

[0050] FIG. 2 is a control block diagram of a device according to one embodiment of the present disclosure.

[0051] Referring to FIG. 2, a memory evaluation device (100) according to one embodiment of the present disclosure may include a processor (110), a communication module (120), a memory (130), and a display (140) (140).

[0052] The components illustrated in FIG. 2 are not essential for implementing the device (100) according to the present disclosure, so the device (100) described in this specification may have more or fewer components than the components listed above.

[0053] The processor (110) can perform a memory evaluation process according to the present disclosure.

[0054] The processor (110) may be implemented with a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the device, and at least one processor (not shown) that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0055] In addition, the processor (110) can control one or more of the components described above in combination to implement various embodiments according to the present disclosure described in the drawings below on the device (100).

[0056] The processor (110) can perform memory evaluation by displaying a learning page and a plurality of evaluation pages through the display (140).

[0057] The processor (110) sets a target word to be used for memory evaluation and a target image representing the target word, displays the target image in one area of ​​the learning page, sets a disruptive word having a different meaning from the target word and a disruptive image representing the disruptive word, sets an alternative image representing the target word or the disruptive word, but having at least some different form from the target image or the disruptive image, displays at least two images among the target image, the disruptive image, and the alternative image so that the target image can be selected on the first evaluation page, displays a plurality of partitioned areas of the learning page so that the area where the target image is displayed on the second evaluation page can be selected, and can perform an integrated evaluation of visual memory, spatial memory, and verbal memory based on the learning of the target image according to the selection result of the target image and the selection result of any one of the plurality of partitioned areas.

[0058] The first evaluation page displays the target image, a first alternative image having at least some form different from the target image, and an icon for selecting the case where the target image is not present.

[0059] The processor (110) may evaluate both visual memory and language memory as Type 1 when the target image is selected through the first evaluation page, evaluate visual memory as Type 2 and language memory as Type 1 when the first alternative image is selected through the first evaluation page, and evaluate both visual memory and language memory as Type 2 when the icon is selected through the first evaluation page.

[0060] The first evaluation page displays the interference image, a second alternative image having at least some different form from the interference image, and the icon, and the processor (110) evaluates both visual memory and language memory as a second type when the interference image or the second alternative image is selected through the first evaluation page, and evaluates both visual memory and language memory as a first type when the icon is selected through the first evaluation page.

[0061] The first evaluation page above may alternately provide a first object recognition evaluation screen displaying the target image, the first alternative image, and the icon, and a second object recognition evaluation screen displaying the interference image, the second alternative image, and the icon.

[0062] The processor (110) can evaluate the spatial memory as a first type when the area among the plurality of partition areas where the target image is displayed is selected through the second evaluation page, and evaluate the spatial memory as a second type when the area among the plurality of partition areas different from the area where the target image is displayed is selected through the second evaluation page.

[0063] The processor (110) includes a database in which words are classified and stored by a plurality of categories, sets a category among the plurality of categories to be used for memory evaluation, and can set a target word based on a typicality value indicating the degree to which a word classified into the set category represents the set category.

[0064] The processor (110) may set multiple target words belonging to different categories, and may set the multiple target words as words having different typicality values.

[0065] The processor (110) may set a word classified into the same category as the target word as the interfering word, or set a word classified into a different category from the target word as the interfering word.

[0066] The processor (110) may generate a target word set by setting a plurality of target words belonging to different categories and a plurality of interference words corresponding to each of the plurality of target words, wherein some of the plurality of interference words are set as words classified in the same category as each corresponding target word, and the remaining portions of the plurality of interference words are set as words classified in a different category from each corresponding target word.

[0067] The communication module (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0068] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0069] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0070] The wireless communication module may include a wireless communication interface comprising an antenna and a transmitter that transmit a mobile communication signal. Additionally, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor (110) through the wireless communication interface into an analog wireless signal under the control of the processor (110).

[0071] A short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0072] The location information module is a module for obtaining the location (or current location) of the device according to the present disclosure, and representative examples thereof include a Global Positioning System (GPS) module or a Wireless Fidelity (WiFi) module. For example, if a GPS module is utilized, the location of the device can be obtained using signals sent from GPS satellites. As another example, if a Wi-Fi module is utilized, the location of the device can be obtained based on information from a Wireless Access Point (AP) that transmits or receives wireless signals from the Wi-Fi module. If necessary, the location information module may perform any of the functions of other modules of the communication unit to obtain data regarding the location of the device, either substituted or additionally. The location information module is a module used to obtain the location (or current location) of the device, and is not limited to a module that directly calculates or obtains the location of the device.

[0073] The memory (130) can store data supporting various functions of the device and programs for the operation of the processor (110), and can store input / output data, and can store a number of application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0074] Such memory (130) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (130) may be a database that is separated from the device but connected via wired or wireless connection.

[0075] The display (140)(140) displays (outputs) information processed by the device (100). For example, the display (140)(140) may display execution screen information of an application (e.g., an application) running on the device (100), or UI (User Interface) and GUI (Graphic User Interface) information based on such execution screen information.

[0076] At least one component may be added or removed in response to the performance of the components shown in FIG. 2. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0077] Meanwhile, each component illustrated in Figure 2 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0079] FIG. 3 is a flowchart of a memory evaluation method according to one embodiment of the present disclosure.

[0080] A memory evaluation method according to one embodiment of the present disclosure may be performed by the device (100) shown in FIG. 2, and with reference to FIG. 3, may include a learning page display step (S10), a first evaluation page display step (S20), a second evaluation page display step (S30), and a memory evaluation step (S40).

[0081] The processor (110) can display a learning page through the display (140) (S10).

[0082] The learning page is a page designed to facilitate the learning of at least one target image. Through this page, the subject can learn and remember the visual features of the target image; at this time, they may also verbalize the target image to remember it as a target word.

[0083] The processor (110) can induce the learning of a target image representing at least one target word through these learning pages. A specific description regarding this will be provided later with reference to FIGS. 4 and FIGS. 5.

[0084] The processor (110) can display the first evaluation page through the display (140) (S20).

[0085] The first evaluation page is a page for evaluating object recognition of a target image and can be divided into a first object recognition evaluation screen and a second object recognition evaluation screen. The first object recognition evaluation screen displays multiple images including the target image, while the second object recognition evaluation screen may display multiple images excluding the target image. The first evaluation page may alternately display the first object recognition evaluation screen and the second object recognition evaluation screen, or display them randomly. Through the first object recognition evaluation screen or the second object recognition evaluation screen, the subject may select the target image remembered as learned among the multiple images, or select "no target image."

[0086] The processor (110) evaluates the object recognition of the subject by checking whether the target image is selected through this first evaluation page, and can also simultaneously evaluate whether the target image has been verbalized and remembered. A detailed explanation regarding this will be provided later with reference to FIGS. 6 to 9.

[0087] The processor (110) can display a second evaluation page through the display (140) (S30).

[0088] The second evaluation page is a page for evaluating location recognition of a target image, and the subject can select the display location of the target image remembered as learned through the second evaluation page.

[0089] The processor (110) can evaluate location recognition for the learning of the target image by checking whether the display area of ​​the target image on the learning page is selected through this second evaluation page. A detailed explanation regarding this will be described later with reference to FIGS. 10 and FIGS. 11.

[0090] The processor (110) can evaluate the visual, spatial, and verbal memory of the subject based on the subject's selection results through the first evaluation page and the second evaluation page (S40).

[0091] The processor (110) can evaluate visual and verbal memory regarding the learning of a target image based on the subject's selection result through the first evaluation page, and then evaluate spatial memory regarding the learning of a target image based on the subject's selection result through the second evaluation page. A detailed explanation regarding this will be provided later with reference to FIGS. 12 to 14.

[0092] The processor (110) can provide the integrated evaluation results of visual, spatial, and linguistic memory through the user terminal (200).

[0094] FIG. 4 is a detailed flowchart of step S10 illustrated in FIG. 3, and FIG. 5 is an example of a learning page according to one embodiment of the present disclosure.

[0095] Referring to FIG. 4, the step (S10) of the processor (110) displaying a learning page may include a target word setting step (S11), a target image setting step (S12), a target image display area setting step (S13), and a target image display step (S14) in the target image display area.

[0096] The processor (110) can set at least one target word to be used for memory evaluation (S11).

[0097] The processor (110) may include a database in which words are classified and stored by multiple categories. For example, the multiple categories may include bathroom supplies, fruits, kitchenware, school supplies, animals, means of transportation, personal belongings, clothes, and food.

[0098] The processor (110) can set at least one category among a plurality of categories to be used for memory evaluation. Hereinafter, the processor (110) will be described as setting nine categories, such as bathroom supplies, fruit, kitchenware, school supplies, animals, means of transportation, personal belongings, clothes, and food.

[0099] For example, the processor (110) can set categories to be used for memory evaluation by considering at least one of the subject's gender, age, place of residence, level of education, language ability, lifestyle pattern and occupation.

[0100] The processor (110) can collect at least one of the subject's gender, age, residential area, education level, language ability, lifestyle pattern and occupation as training data, label the collected data by assigning an Object ID to each data, and store the labeled data in an XML format.

[0101] The processor (110) can generate each of the stored labeled data into a data set for category setting analysis and learn the generated data set using an artificial intelligence learning algorithm.

[0102] The processor (110) can set hyperparameters for the optimization of an artificial intelligence learning model, and can set the number of classes, learning rate, cost function, activation function, etc. Here, the number of classes is the number of objects detected through the learning model, the learning rate is the learning rate required when the neural network model reduces the error using Stochastic Gradient Descent (SGD), and the activation function is used when moving from a node in a layer to a node in the next layer. A non-linear function neural network model is trained to reduce the error of the operation required for the probability of being classified into classes. The training of the artificial intelligence learning model can be optimized by classifying the dataset into a training dataset, a validation dataset, and a test dataset, inputting the training dataset into the completed artificial intelligence learning model to proceed with training according to the neural network layers and hyperparameters, verifying the learning model using the validation dataset to evaluate accuracy, and if a low value is measured, optimizing the learning model by adjusting the number of hidden layers and hyperparameters. This optimized AI learning model is updated in real-time and can be utilized for multiple category settings.

[0103] The processor (110) can set multiple categories by inputting at least one of the subject's gender, age, residential area, education level, language ability, lifestyle pattern, and occupation into such an artificial intelligence learning model.

[0104] Meanwhile, the processor (110) can calculate the stress level of the subject and reset multiple categories according to the subject's stress level. That is, the processor (110) can reset the categories to be used for memory evaluation according to the subject's stress level, based on the fact that words in a specific category may not be remembered better or, conversely, may be remembered better depending on the stress level.

[0105] For example, the processor (110) can calculate the stress level and the degree of stress based on the stress level by utilizing indicators such as heart rate, skin conduction response, breathing pattern, and hormone levels. At this time, the method for calculating the stress level is a widely known technique, so a specific description thereof will be omitted.

[0106] The processor (110) can pre-set categories to be excluded or added in the memory evaluation depending on the stress level (low, medium, high, etc.). For example, categories related to social or interpersonal relationships, environments, and daily life may be difficult to remember as the stress level increases; therefore, it is desirable to set the categories to be excluded when the stress level is calculated to be high. Additionally, categories related to events and negative emotions may be recalled more easily as the stress level increases; therefore, it is desirable to set the categories to be added when the stress level is calculated to be high.

[0107] The processor (110) can expect to improve the accuracy of the test by resetting multiple categories to be used for memory evaluation according to the stress level of the test subject.

[0108] Meanwhile, the processor (110) can set target words in each of the multiple categories it has set.

[0109] For example, the processor (110) can obtain a typicality score for each word classified into each category. The typicality score is a value indicating the degree to which the word represents the category, and can be pre-calculated and provided for each word based on a typicality survey performed by multiple subjects. For example, the typicality survey may be a method that asks subjects to rate on a scale from 1 to 7 how well they feel each word represents the category.

[0110] The processor (110) may set multiple target words belonging to different categories among the set multiple categories, and may set multiple target words as words having different typicality values.

[0111] For example, the processor (110) may set toothbrush, strawberry, and kettle as target words with high typicality values ​​(e.g., 6 or more) in the three categories of bathroom supplies, fruit, kitchen supplies, school supplies, animals, means of transportation, personal belongings, clothes, and food among the nine categories of bathroom supplies, fruit, kitchen supplies, school supplies, animals, and means of transportation, respectively; set scissors, lion, and airplane as target words with medium typicality values ​​(e.g., 3 or more, less than 6) in the three categories of school supplies, animals, and means of transportation, respectively; and set ring, hat, and ice cream as target words with low typicality values ​​(e.g., less than 3) in the three categories of personal belongings, clothes, and food.

[0112] The processor (110) can set an image representing a target word as the target image (S12).

[0113] For example, the processor (110) can pre-set and store images that serve as target stimuli for each target word, and can set the target images using this.

[0114] The processor (110) can set the target image display area on the learning page (S13).

[0115] For example, referring to FIG. 5, the learning page (3) may include a plurality of partitioned areas (30) partitioned in a 3x3 grid shape. The processor (110) may arbitrarily set an area (31) among the plurality of partitioned areas where the target image (11) is to be displayed.

[0116] The processor (110) can set a target image display area (31) for each of the multiple target images (11).

[0117] The processor (110) can display the target image in the target image display area (S14).

[0118] For example, the processor (110) can generate and provide a learning page (3) in which, in a plurality of partitioned areas (30) partitioned in a 3x3 grid shape, each target image (11) is displayed sequentially for 2 seconds in a target image display area (31) set for each of the plurality of target images (11), and this process is repeated a total of 3 times.

[0119] Meanwhile, the processor (110) may omit the learning guide text that induces the memory of the shape or location of the target image when providing the learning page, or provide the guide text that induces simple memory of the target image, or furthermore, verbalization of the target image so that the subject cannot predict in advance the evaluation of object recognition or location recognition through the first evaluation page and the second evaluation page, thereby increasing the evaluation discrimination ability.

[0121] FIG. 6 is a detailed flowchart of step S20 illustrated in FIG. 3, FIG. 7 is an example of a target image and a interference image according to one embodiment of the present disclosure, FIG. 8 is an example of a target image and a replacement image according to one embodiment of the present disclosure, and FIG. 9 is an example of a first evaluation page according to one embodiment of the present disclosure.

[0122] Referring to FIG. 6, the step (S20) of the processor (110) displaying the first evaluation page may include a step of setting a disruptive word (S21), a step of setting a disruptive image (S22), a step of setting first and second alternative images (S23), a step of displaying a target image, a first alternative image and no learning image selection icon (S24), and a step of displaying a disruptive image, a second alternative image and no learning image selection icon (S25).

[0123] The processor (110) can set a disruptive word that has a different meaning for each set target word (S21).

[0124] The processor (110) can set a word classified in the same category as the target word as a disruptive word, or a word classified in a different category from the target word as a disruptive word.

[0125] For example, the processor (110) can set a disruptive word based on the typicality value of words classified into a set category, in the same way as the target word setting method.

[0126] The processor (110) can generate a set of target words by setting multiple target words belonging to different categories and multiple interference words corresponding to each of the multiple target words.

[0127] For example, the processor (110) may set words classified into five identical categories—bathroom supplies, fruit, kitchen supplies, school supplies, and animals—among the nine categories to which the target word belongs—bathroom supplies, fruit, kitchen supplies, school supplies, and animals, and set words classified into four other categories—vegetables, furniture, flowers, and reading material—which are independent of the remaining four categories of transportation, belongings, clothes, and food, as disruptive words.

[0128] That is, the processor (110) can set the disruptive words toilet paper, green grapes, chopsticks, brush, and chicken in the categories of bathroom supplies, fruits, kitchen supplies, school supplies, and animals, respectively, which are the same as the category to which the target word belongs, and the disruptive words eggplant, clothes hanger, sunflower, and calendar in the categories of vegetables, furniture, flowers, and reading material, respectively, which are independent of the category to which the target word belongs.

[0129] The processor (110) can set an image representing a disruptive word as a disruptive image (S22).

[0130] For example, the processor (110) can pre-set and store an image that serves as a target stimulus for each disruptive word, and can set the disruptive image using this.

[0131] Referring to FIG. 7, the processor (110) can set a target image (11) and a interference image (13). As shown in FIG. 7 (a), the target image (11) is an image representing the target word, lion, and as shown in FIG. 7 (b), the interference image (13) may be an image representing the interference word, chicken.

[0132] As such, the target image and the distraction image represent words with different meanings and will have clearly different visual characteristics; given that these target image and the distraction image can be remembered by verbalizing their meanings or by their visual characteristics, respectively, verbal and visual memory can be evaluated through the identification of the target image and the distraction image.

[0133] The processor (110) can set a first replacement image that represents a target word but has a different shape from the target image and a second replacement image that represents a disruptive word but has a different shape from the disruptive image (S23).

[0134] For example, the processor (110) can set the first and second alternative images by pre-setting and storing a first alternative image that serves as a visual discrimination stimulus for each target word, and pre-setting and storing a second alternative image that serves as a visual discrimination stimulus for each interference word.

[0135] The first and second alternative images each have the same meaning as the target word and the distraction word, and are stimuli that are visually distinguishable from the target image and the distraction image by being different from at least some parts of the target image and the distraction image, and can be defined as same-name alternatives.

[0136] For example, the first and second replacement images may each be images that differ from the target image and the interference image in at least one aspect of color, angle, direction, size, and specific detail.

[0137] Referring to FIG. 8, for example, the target image (11) and the first replacement image (15) both have the meaning of 'airplane', but can have different shapes to have visual distinctiveness.

[0138] In this way, the target image and the first alternative image represent the same meaning but will have clearly different visual characteristics; and since these target image and the first alternative image can be remembered solely by their visual characteristics, and the images cannot be identified when their meanings are verbalized and remembered, verbal and visual memory can be evaluated.

[0139] Meanwhile, although the identification of the distracting image and the second replacement image is not significant in memory evaluation, it can be used to maintain consistency in the overall evaluation page.

[0140] The processor (110) may display a first object recognition evaluation screen including a target image, a first alternative image, and a no-learning-image selection icon (S24), or a second object recognition evaluation screen including a distraction image, a second alternative image, and a no-learning-image selection icon (S25).

[0141] The first evaluation page is a page for evaluating object recognition for a target image, and can be divided into a first object recognition evaluation screen and a second object recognition evaluation screen.

[0142] The "No training image" selection icon may be used to select cases where there is no target image.

[0143] Referring to FIG. 9, the first object recognition evaluation screen (5) may display a target image (11), a first alternative image (15), and a no-learning-image selection icon (17). The second object recognition evaluation screen may display a distraction image instead of the target image (11) in the screen shown in FIG. 9, and display a second alternative image instead of the first alternative image (15).

[0144] The processor (110) may configure the first evaluation page by alternately displaying the first object recognition evaluation screen and the second object recognition evaluation screen, or by displaying them randomly. Through the first object recognition evaluation screen or the second object recognition evaluation screen, the subject may select a target image (11) that is remembered as having been learned among several images, or select the "no learned image" selection icon (17).

[0146] FIG. 10 is a detailed flowchart of step S30 illustrated in FIG. 3, and FIG. 11 is an example of a second evaluation page according to one embodiment of the present disclosure.

[0147] Referring to FIG. 10, the step (S30) of the processor (110) displaying a second evaluation page may include a target image display step (S31) and a partition area display step (S32).

[0148] The processor (110) displays a target image (S31) and can display a section area of ​​the learning page so that the target image display area where the target image appears on the learning page can be selected (S32).

[0149] Referring to FIG. 11, the second evaluation page (5) can display a target image (11) and a partition area (30). The subject can select a display area in the partition area (30) where the target image (11) appears through the second evaluation page.

[0150] When identifying the target image (11) display area in the partition area (30) through such a second evaluation page (5), the subject may be evaluated as having remembered the target image (11) not only verbally but also by its spatial characteristics.

[0152] FIGS. 12 to 14 are detailed flowcharts of step S40 shown in FIG. 3.

[0153] Referring to FIG. 12, the step (S40) in which the processor (110) evaluates the visual, spatial, and verbal memory of a subject in an integrated manner is provided with a first object recognition evaluation screen in which a target image is displayed on a first evaluation page (S411). When the target image is selected by the subject (S412), the visual memory and verbal memory are determined to be normal (S413). When an alternative image is selected by the subject (S414), the visual memory is determined to be abnormal and the verbal memory normal (S415). When the "no learning image" selection icon is selected (S414), the visual memory and verbal memory are determined to be abnormal (S416).

[0154] Among the first evaluation pages, the first object recognition evaluation screen may receive a selection of any one of the target image, the first alternative image, and the no training image selection icon. Additionally, in this embodiment, normal may be classified as Type 1, and abnormal may be classified as Type 2.

[0155] When a target image is selected in the first object recognition evaluation screen, the processor (110) can determine that the subject's visual memory and verbal memory are normal by determining that the subject remembered the target image not only verbally but also identified it with a substitute image as a visual feature.

[0156] When an alternative image is selected on the first object recognition evaluation screen, the processor (110) can determine that the subject's visual memory is abnormal and verbal memory is normal, judging that the subject only remembered the target image verbally and not by its visual features, given that the alternative image has the same meaning as the target image.

[0157] When the learning image selection icon is selected on the first object recognition evaluation screen, the processor (110) can determine that the subject not only failed to verbalize and remember the target image but also failed to remember its visual features, and thus determine that both the subject's visual memory and verbal memory are abnormal.

[0158] Referring to FIGS. 12 and 13, the step (S40) in which the processor (110) evaluates the visual, spatial, and verbal memory of a subject in an integrated manner is provided with a second object recognition evaluation screen in which a distracting image is displayed instead of a target image on the first evaluation page (S411). If the distracting image or a substitute image is selected by the subject (S421), the visual memory and verbal memory are determined to be abnormal (S422), and if the no learning image selection icon is selected by the subject (S421), the visual memory and verbal memory are determined to be normal (S423).

[0159] In the first evaluation page, the second object recognition evaluation screen may receive one of the following selection icons: distracting image, second alternative image, and no training image.

[0160] When a interference image or a second alternative image of an interference image is selected on the second object recognition evaluation screen, the processor (110) can determine that the interference image and the second alternative image are different from the target image in both meaning and shape, and thus determine that the subject not only failed to verbalize and remember the target image but also failed to remember it by its visual characteristics, thereby determining that there is an abnormality in visual memory and verbal memory.

[0161] When the processor (110) selects the "no learning image" selection icon on the second object recognition evaluation screen, it can determine that the subject remembers the target image by verbalizing it or remembers it by visual features, and thus determine that the visual memory and verbal memory are normal.

[0162] Referring to FIG. 14, the step (S40) in which the processor (110) evaluates the visual, spatial, and verbal memory of the subject in an integrated manner may determine that the spatial memory is normal (S432) when the target image display area is selected on the second evaluation page (S431), and determine that the spatial memory is abnormal (S433) when an area other than the target image display area is selected on the second evaluation page (S431).

[0163] The second evaluation page displays multiple section areas of the target image and the learning page, allowing the selection of a target image display area remembered as where the target image appeared.

[0164] When the processor (110) selects a display area of ​​the currently displayed target image among a plurality of partition areas, it can determine that spatial memory is normal, as it not only remembers the target image by verbalizing it or remembers it by its visual characteristics, but also identifies the location where the target image is displayed when the target is stimulated.

[0165] If the processor (110) does not select the display area of ​​the currently displayed target image among the multiple partition areas, it may determine that spatial memory is abnormal, as it appears that the target image was not verbalized or remembered, or its visual features were not remembered, and the location where the target image was displayed was not identified when the target was stimulated.

[0167] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0168] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0169] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0171] 10: Memory Evaluation System 100: Device 200: User terminal

Claims

Claim 1 A memory evaluation device comprising: a display; and a processor that performs a memory evaluation by displaying a learning page and a plurality of evaluation pages through the display; wherein the processor sets a target word to be used for the memory evaluation and a target image representing the target word, displays the target image in one area of ​​the learning page, sets a distraction image representing a distraction word having a different meaning from the target word, sets an alternative image representing the target word or the distraction word, and has at least a partially different form from the target image or the distraction image, displays at least two images among the target image, the distraction image, and the alternative image so that the target image can be selected on a first evaluation page, displays a plurality of partitioned areas of the learning page so that an area where the target image is displayed on a second evaluation page can be selected, and evaluates at least one of visual memory, spatial memory, and verbal memory based on the learning of the target image according to the result of selecting an image on the first evaluation page and the result of selecting one of the portions of the plurality of partitioned areas. Claim 2 A memory evaluation device according to claim 1, wherein the first evaluation page displays the target image, a first alternative image having at least some different form from the target image, and an icon for selecting the case where the target image is not present, and the processor evaluates visual memory or verbal memory as a first type when the target image is selected through the first evaluation page, evaluates visual memory as a second type or verbal memory as a first type when the first alternative image is selected through the first evaluation page, and evaluates visual memory or verbal memory as a second type when the icon is selected through the first evaluation page. Claim 3 A memory evaluation device according to paragraph 2, wherein the first evaluation page displays the interference image, a second alternative image having at least some different form from the interference image, and the icon, and the processor evaluates the visual memory or language memory as a second type when the interference image or the second alternative image is selected through the first evaluation page, and evaluates the visual memory or language memory as a first type when the icon is selected through the first evaluation page. Claim 4 In paragraph 3, the memory evaluation device, wherein the first evaluation page alternately provides a first object recognition evaluation screen displaying the target image, the first alternative image, and the icon, and a second object recognition evaluation screen displaying the interference image, the second alternative image, and the icon. Claim 5 A memory evaluation device according to paragraph 3, wherein the processor evaluates the spatial memory as a first type when the area among the plurality of partition areas where the target image is displayed is selected through the second evaluation page, and evaluates the spatial memory as a second type when the area among the plurality of partition areas different from the area where the target image is displayed is selected through the second evaluation page. Claim 6 A memory evaluation device according to claim 1, wherein the processor includes a database in which words are classified and stored by a plurality of categories, sets a category among the plurality of categories to be used for memory evaluation, and sets a target word based on a typicality value indicating the degree to which a word classified by the set category represents the set category. Claim 7 In claim 6, the memory evaluation device, wherein the processor sets a plurality of target words belonging to different categories, and sets the plurality of target words as words having different typicality values. Claim 8 In claim 6, the memory evaluation device, wherein the processor sets a word classified into the same category as the target word as the interfering word, or sets a word classified into a different category from the target word as the interfering word, and sets the interfering word based on a typicality value indicating the degree to which the word classified into the set category represents the set category. Claim 9 A memory evaluation device according to claim 8, wherein the processor generates a target word set by setting a plurality of target words belonging to different categories and a plurality of interference words corresponding to each of the plurality of target words, wherein some of the plurality of interference words are set as words classified in the same category as each corresponding target word, and the remaining portions of the plurality of interference words are set as words classified in a different category from each corresponding target word to generate the target word set. Claim 10 A memory evaluation method performed by a memory evaluation device, comprising: a step of setting a target word to be used for memory evaluation and a target image representing the target word; a step of displaying the target image in one area of ​​a learning page; a step of setting a distraction image representing a distraction word having a different meaning from the target word; a step of setting an alternative image representing the target word or the distraction word, having at least a partially different form from the target image or the distraction image; a step of displaying at least two images among the target image, the distraction image, and the alternative image so that the target image can be selected on a first evaluation page; a step of displaying a plurality of partitioned areas of the learning page so that an area where the target image is displayed on a second evaluation page can be selected; and a step of evaluating at least one of visual memory, spatial memory, and verbal memory based on the learning of the target image according to the result of selecting an image on the first evaluation page and the result of selecting one of the plurality of partitioned areas.

Images