Generative ai-based past image generation method and apparatus using recollection data of elderly

Abstract

The present invention relates to a generative AI-based past image generation method and apparatus using recollection data of the elderly. The method performed by a server may comprise the steps of: receiving user information including utterance data spoken by an elderly user while recollecting the past; analyzing the utterance data so as to extract object information and time information for generating a past image; and generating the past image of the user on the basis of the object information and the time information, wherein the past recollected by the user can be generated as an image by using the utterance data spoken by the user.

Description

Method and device for generating past images using recollection data of elderly people based on generative AI

[0001] The present invention relates to a method and device for generating past images using recollection data of an elderly person based on generative AI, and more particularly, to a method and device for generating past images using recollection data of an elderly person based on generative AI, which can generate past images using speech data of a user speaking while reminiscing about the past.

[0002] The population of people aged 60 and over is rapidly increasing, and the number of people living alone or suffering from various diseases, including dementia, is on the rise. Dementia in the elderly, in particular, is a painful condition that not only affects the individual but also their spouse and children. Therefore, there is a need for measures to assess memory in older adults, diagnose dementia early, and delay the worsening of symptoms.

[0003] Furthermore, no matter how much local governments or the central government manage a region's history and culture, there are inevitably aspects that are overlooked. This will only worsen with each passing generation. For example, there's the problem of inadequate preservation of useful materials, such as those passed down orally or based on the experiences of the elderly, that aren't included in history books or cultural materials. Therefore, there's a need to document the experiences and memories of the elderly to further develop and pass down regional history and culture.

[0004] (Prior literature)KR10-2019-0093953 A

[0005] The present invention provides a method and device for generating past images using recollection data of an elderly person based on generative AI, which can generate images of the past as recalled by an elderly person using speech data spoken by the elderly person.

[0006] The present invention provides a method and device for generating past images using generative AI-based recollection data of the elderly, which can generate public content that can be used to supplement and correct content needed by the elderly or the history and culture of a region using past images.

[0007] The problems to be solved by the present invention 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.

[0008] A method and device for generating a past image using recollection data of an elderly person based on generative AI according to an embodiment of the present invention is a method for generating a past image using recollection data of an elderly person based on generative AI performed by a server, the method including: a process of receiving user information including speech data of an elderly person speaking while reminiscing about the past; a process of analyzing the speech data to extract object information and time information for generating a past image; and a process of generating a past image of the user based on the object information and the time information.

[0009] The above speech data includes voice data, and the process of receiving the user information may further include a process of receiving at least one of image data and text data that enable the user to recall the past.

[0010] The above object information may include at least one of place information, person information, building information, animal information, plant information, and object information.

[0011] The process of generating the above-mentioned past image may include a process of generating a basic image using the object information; and a process of correcting the basic image using the time information.

[0012] The method further includes a process of collecting auxiliary information for correcting the basic image, and the process of collecting the auxiliary information may collect at least one of public image information, crawling information, and user feedback information related to at least one of the object information and the time information.

[0013] The process of correcting the above-mentioned basic image may include a process of supplementing the above-mentioned basic image using the above-mentioned auxiliary information corresponding to the above-mentioned timing information.

[0014] The process of collecting the above auxiliary information includes a process of collecting reference auxiliary information corresponding to the time information, previous auxiliary information corresponding to a previous time based on the time information, and subsequent auxiliary information corresponding to a subsequent time, and the process of supplementing the basic image includes, when the reference auxiliary information is absent, supplementing the basic image using the auxiliary information of a time closest to the time information among the previous auxiliary information and the subsequent auxiliary information.

[0015] A device for generating past images using recollection data of an elderly person based on generative AI according to an embodiment of the present invention comprises: a user terminal capable of acquiring user information including speech data of an elderly person speaking while reminiscing about the past; and a management server capable of receiving the user information and generating a past image of the user based on the speech data; wherein the management server analyzes the speech data to extract object information and time information for generating a past image, and generates a past image recalled by the user based on the object information and the time information.

[0016] The method for generating past images using the elderly's recall data based on generative AI according to an embodiment of the present invention can be performed by a computer program stored in a computer-readable recording medium coupled with a computer as hardware.

[0017] Other specific details of the present invention are included in the detailed description and drawings.

[0018] According to the present invention, speech data from an elderly user can be used to generate images of the user's past memories. Furthermore, the generated past images can be used to create personalized content, such as albums or memoirs, and to create public content that complements and enhances local history and culture. In particular, past images and personalized content generated using them can be utilized to enhance the user's cognitive function, prevent dementia, and even help the user remember the past after death.

[0019] Additionally, users can provide resources to complement and preserve historical data by uniquely personalizing past images, thereby generating revenue.

[0020] 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.

[0021] Figure 1 is a conceptual diagram of a past image generation device utilizing the recollection data of an elderly person based on generative AI according to an embodiment of the present invention.

[0022] Figure 2 is a block diagram for explaining the detailed configuration of the management server illustrated in Figure 1.

[0023] FIG. 3 is a block diagram schematically showing a method for generating past images using recollection data of an elderly person based on generative AI according to an embodiment of the present invention.

[0024] FIG. 4 is a diagram showing an example of generating a past image using a past image generation method using the recollection data of an elderly person based on generative AI according to an embodiment of the present invention.

[0025] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined solely by the scope of the claims.

[0026] The terminology used herein is for the purpose of describing embodiments only and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like components throughout the specification, and "and / or" includes each and any combination of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms. These terms are only used to distinguish one component from another. Therefore, it should be understood that a first component mentioned below may also be a second component within the technical spirit of the present invention.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in their common sense to those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0028] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0029] FIG. 1 is a conceptual diagram of a past image generation device utilizing the recollection data of an elderly person based on generative AI according to an embodiment of the present invention, and FIG. 2 is a block diagram for explaining the detailed configuration of the management server illustrated in FIG. 1.

[0030] As illustrated in FIGS. 1 and 2, a device for generating past images using the recollection data of an elderly person based on generative AI according to an embodiment of the present invention may include a user terminal (10), a management server (20), and an administrator terminal (30). In this case, the administrator terminal (30) may be omitted.

[0031] Here, the user terminal (10), management server (20), and administrator terminal (30) can be synchronized in real time using a wireless communication network to transmit and receive data. Wireless communication networks can support various long-distance communication methods, such as Wireless LAN (WLAN), Digital Living Network Alliance (DLNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (EV-DO), Wideband CDMA (WCDMA), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTEA), Wireless Mobile Broadband Service (WMBS), Bluetooth Low Energy (BLE), Zigbee, and Radio Frequency (RF). Various communication methods such as LoRa (Long Range), LoRa (Frequency), etc. can be applied, but are not limited to these, and various widely known wireless communication or mobile communication methods can also be applied.

[0032] First, the past image generation device using the recollection data of the elderly based on the generative AI according to this embodiment can generate the past image that the user is reminiscing about based on the speech data that the user speaks while reminiscing about the past.

[0033] To this end, the user terminal (10) can input speech data spoken by the user and transmit the input speech data to the management server (20) using a communication network. Here, the speech data may include voice data. In addition, the user terminal (10) is linked to the management server (20) in the form of an app or web, such as a smart phone or a computer, and can input and transmit to the management server (20) not only additional information such as text data and image data held by the user, but also personal information such as the user's gender, age, and health status. Hereinafter, information input or provided by the user, such as speech data and additional information, is referred to as user information.

[0034] In addition, the user terminal (10) can receive past images, user-customized content, etc. generated using speech data or user information from the management server (20) and visualize them so that the user can check them.

[0035] The user terminal (10) is a terminal possessed by the user, and can operate using an application program (or application) in the present disclosure, and the application program can be downloaded from an external server or management server (20) via wireless communication. For example, the user terminal (10) may include various terminals such as a smart phone, a PDA (Personal Digital Assistant), a tablet, a wearable device (e.g., a smartwatch, a smart glass, a head mounted display (HMD), etc.), a desktop, and various IoT (Internet of Things) terminals, but is not limited thereto.

[0036] The management server (20) receives user information transmitted from the user terminal (10) and, utilizing generative AI, can generate user information, particularly speech data, into past images of the past that the user recalls. Furthermore, the management server (20) can generate user-customized content using the generated past images.

[0037] Referring to FIG. 2, the management server (20) may include a data transmission / reception unit (21), a data analysis unit (22), a database unit (23), a data collection unit (24), a matching unit (25), an image generation unit (26), and a content generation unit (76). Such a management server (20) may be implemented by a hardware circuit (e.g., a CMOS-based logic circuit), firmware, software, or a combination thereof. For example, it may be implemented by utilizing transistors, logic gates, and electronic circuits in the form of various electrical structures.

[0038] The data transmission and reception unit (21) can be connected to a user terminal (10) via a communication network and can receive user information transmitted from the user terminal (10). In addition, the data transmission and reception unit (21) can receive an image generation request from the user terminal (10) and transmit the generated image, such as a basic image, an intermediate image, a past image, etc., to the user terminal (10). Here, the basic image refers to an image initially generated using the user information received from the user terminal (10), and the past image refers to an image requested from the user terminal (10), such as a final image. In addition, the intermediate image is an image generated in an intermediate process of generating a past image after generating the basic image, and may or may not be generated as needed.

[0039] The data analysis unit (22) can extract object information and time information necessary for past image generation from user information based on an image generation request. Here, object information may refer to people, places, things, buildings, actions, food, animals, plants, etc., and time information may refer to a time before the present that the user recalls. For example, object information may include me, mom, teacher, school, beach, Seoul Station, Bulguksa Temple, landmark, park, market, funeral home, swimming, sleep, meal, bulgogi, dog, cat, ginkgo tree, etc., and time information may include 1981, 1999, 2010, etc. In addition, time information may include seasons such as spring, summer, fall, and winter, and specifically, may include a specific year, month, and date.

[0040] This data analysis unit (22) may include a natural language analysis module (not shown). The data analysis unit (22) may use the natural language analysis results of user information, particularly user comments included in speech data, when determining image generation conditions based on an image generation request. The natural language analysis is performed by the natural language analysis module and may include lexical analysis, syntactic analysis, and semantic analysis. For example, the data analysis unit (22) may use the natural language analysis results of speech data such as "I remember going to Haeundae Beach with my wife and daughter and swimming in August 1995" to extract "me," "wife," "daughter," "Haeundae Beach," and "swimming" as object information, and may extract "August 1995" as time information.

[0041] Object information and time information extracted from the data analysis unit (22) can be stored in the database unit (23).

[0042] The data collection unit (24) can collect auxiliary information necessary for generating past images, in addition to object information and time information. For example, the data collection unit (24) can collect auxiliary information for generating a background necessary for generating past images. The auxiliary information may include public image information, crawling information, etc. For example, public image information may include old movies and dramas related to the subject matter without copyright issues, and crawling information may include building registers, etc.

[0043] The auxiliary information collected in the data collection unit (24) can be analyzed in the data analysis unit (22), classified by subject, and stored in the database unit (23). Here, the subject is defined through entity recognition, and the auxiliary information can be classified by matching it with object information such as people, places, objects, buildings, etc. For example, if the collected auxiliary information is an "image of Haeundae Beach," it can be classified under the subject of "beach."

[0044] The data analysis unit (22) may include an image analysis module (not shown) for analyzing collected auxiliary information. The image analysis module may include a color profile method, texture and pattern distribution, a YOLO model capable of object detection and recognition, a CNN (Convolutional Neural Network) model, etc. For example, the image analysis module may classify images according to a predetermined topic by finding features within the auxiliary information and calculating a correlation distance between them.

[0045] The database section (23) may include a user information DB (231), auxiliary information DB (232), basic image DB (233), and content DB (234).

[0046] The user information DB (231) can store user information received from the user terminal (10) and object information and time information extracted from the data analysis unit (22) by matching them with each other. In addition, the user information DB (231) can store images generated using not only user information but also auxiliary information, such as basic images, intermediate images, and past images.

[0047] The auxiliary information DB (232) can store auxiliary information, such as images, collected through the data collection unit (24) and analyzed and classified by the data analysis unit (22). At this time, the auxiliary information DB (232) can store auxiliary information by classifying it by subject.

[0048] The basic image database (233) contains images prepared in advance for generating images based on object and time information, and may include images that are publicly available and not subject to copyright. This basic image database (233) can store images, such as basic images, categorized by subject matter such as people, locations, and seasons.

[0049] The content database (234) can store user-customized content, historical data content, etc., created using past images generated using user information and auxiliary information. For example, user-customized content may include albums, memoirs, etc., and historical data content may include the evolution of local cultural assets. In this case, historical data content can be used as public content.

[0050] The matching unit (25) can match data stored in the database unit (23) with each other according to object information and time information for past image generation. For example, the matching unit (25) can select and match basic images stored in the basic image DB (233) and auxiliary information stored in the auxiliary information DB (232) according to object information and time information.

[0051] The image generation unit (26) can generate a past image using the basic image and auxiliary information selected and matched by the matching unit (25). The image generation unit (26) can generate a basic image according to object information and time information, and can generate a past image by generating a background on the basic image using the auxiliary information. At this time, the past image can be a final image or an intermediate image. That is, the image generation unit (26) can generate a basic image, generate a background, and transmit the generated image to the user terminal (10) through the data transmission / reception unit (21). In addition, feedback information can be received from the user terminal (10) through the data transmission / reception unit (21). If the feedback information includes a user's request for modification, the corresponding image can become an intermediate image. Thereafter, if the image generation unit (26) uses the feedback information to modify and supplement the intermediate image, the corresponding image can become a final image, which is a past image. On the other hand, if the feedback information includes a user's request for approval, the corresponding image can become a final image, which is a past image.

[0052] This image generation unit (26) may include an image generation module (not shown) capable of generating an image according to image generation conditions such as object information, time information, and auxiliary information. At this time, the image generation module may include a generative AI model. For example, the image generation module may generate a basic image according to object information and time information by utilizing various techniques such as vector drawing techniques and machine learning techniques. In addition, the image generation module may generate a past image using the basic image and auxiliary information by utilizing the StyleGAN model.

[0053] The content creation unit (76) can create user-customized content such as albums, memoirs, etc., or public content such as historical data, etc., using past images created by the image creation unit (26) upon user request. Various contents created by the content creation unit (76) can be stored in the user information DB (231).

[0054] The administrator terminal (30) is a separate terminal possessed by an administrator, and can transmit and receive data in real time by synchronizing with the user terminal (10) and the management server (20) using a wireless communication network. At this time, the administrator terminal (30) can transmit and receive data using an application program (or application).

[0055] Such an administrator terminal (30) may include various portable electronic communication devices that support communication with a user terminal (10) and a management server (20). For example, as a separate smart device, it may include various terminals such as a smart phone, a PDA (Personal Digital Assistant), a tablet, a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display (HMD), etc.), and various IoT (Internet of Things) terminals, but is not limited thereto.

[0056] Below, a method for generating past images using generative AI-based recall data of the elderly, according to an embodiment of the present invention, is described. The method for generating past images using generative AI-based recall data of the elderly, according to an embodiment of the present invention, can be performed using the aforementioned generative AI-based recall data-based device for generating past images.

[0057] FIG. 3 is a block diagram schematically showing a method for generating past images using recollection data of an elderly person based on generative AI according to an embodiment of the present invention, and FIG. 4 is a drawing showing an example of generating past images using a method for generating past images using recollection data of an elderly person based on generative AI according to an embodiment of the present invention.

[0058] Referring to FIG. 3, a method for generating a past image using recollection data of an elderly person based on generative AI according to an embodiment of the present invention may include a process of receiving user information including speech data spoken by the user while reminiscing about the past, a process of analyzing the speech data to extract object information and time information for generating a past image, and a process of generating a past image of the user based on the object information and the time information.

[0059] Here, the user's age may vary, but is described as an elderly person or senior citizen aged 60 or older.

[0060] When a request for generating a past image is received from a user terminal (10), the management server (20) may request the user terminal (10) to transmit user information via the data transmission / reception unit (21). At this time, the user information may include personal information such as the user's age, gender, and address, as well as speech data spoken while reminiscing about the past. For example, the speech data may be a sentence such as "I remember going to Haeundae Beach with my wife and daughter and swimming in August 1995." At this time, the user is currently reminiscing about the summer of 30 years ago, for example, in July 2024. In addition, the user information may further include various data such as text data and video data held by the user. At this time, the video data may include past photos / videos and current photos / videos of the user.

[0061] When user information is received from a user terminal (10), the data analysis unit (22) of the management server (20) can analyze the speech data to extract object information and time information. At this time, the object information may be "me," "wife," "daughter," "Haeundae Beach," or "beach," and the time information may be "August 1995."

[0062] In this way, when object information and time information are extracted, the extracted information can be stored in the user information DB (231) of the database section (23).

[0063] In addition, the data collection unit (24) can collect auxiliary information necessary for generating an image. For example, the data collection unit (24) can collect images of Haeundae Beach from 5 to 10 years before and 5 to 10 years after August 1995. The auxiliary information can include reference auxiliary information corresponding to the past time period information recalled by the user, previous auxiliary information corresponding to a time period before the time period information, and subsequent auxiliary information corresponding to a time period after the time period information.

[0064] When auxiliary information is collected, the data analysis unit (22) can analyze the auxiliary information collected through the image analysis module, such as images of Haeundae Beach, to select images suitable for object information and time information and store them in the auxiliary information DB (232).

[0065] Afterwards, the matching unit (25) can match object information, time information, and auxiliary information required to create a past image.

[0066] And the image generation unit (26) can generate a basic image using object information and can generate a past image using auxiliary information matching the time information. At this time, if there is no standard auxiliary information matching the time information, the auxiliary information closest to the time information among the previous auxiliary information and the subsequent auxiliary information can be used. For example, if there is no image of Haeundae Beach in August 1995, but there are images of Haeundae Beach in August 1994, July 1995, and October 1995, the image of Haeundae Beach in July 1995, which is the closest time to August 1995, can be used as auxiliary information.

[0067] Referring to Fig. 4, the image generation unit (26) can generate a basic image of a past recollection period recalled by the user using object information. In addition, an intermediate image can be generated by merging at least one of the images prior to the past recollection period and the images after the past recollection period among the collected auxiliary information. At this time, at least one of the images prior to the past recollection period and the images after the past recollection period can be used to generate a background for the basic image or to supplement the generated background.

[0068] In this way, when an intermediate image is generated, the intermediate image can be transmitted to the user terminal (10) via the data transmission / reception unit (21). And when a signal approving the image is transmitted from the user terminal (10), the image, for example, the intermediate image, can be set as the final image, that is, the past image.

[0069] On the other hand, if a signal (feedback) requesting modification or supplementation of the image without approving it is transmitted from the user terminal (10), the image may be modified or supplemented as an intermediate image using auxiliary information and the user's feedback information to generate a final image, which is a past image. For example, since the feedback information may indicate that a specific building that the user recalls is not present in the intermediate image, a request may be made to add an image of a specific building to the image according to the corresponding period. In this case, auxiliary information including the user's past recall period, for example, building register information for the specific building requested by the user, may be additionally collected, and an image of the building may be additionally collected through a street view search, etc. Once the image of the building is collected, the collected image may be stored in the auxiliary information DB (232). In addition, the image of the building may be added to the intermediate image through the image generation unit (26) to generate a final image, which is a past image.

[0070] This method can increase user satisfaction by creating more accurate past images using various data.

[0071] In this way, when a past image is created, the created image can be stored in the user information DB (231) and transmitted to the user terminal (10) through the data transmission / reception unit (21).

[0072] Additionally, upon user request, the content generation unit (76) can generate user-customized content, public content, etc. using past images. At this time, the content generation unit (76) can also generate albums, memoirs, etc. at the user's request, and can be used as public data to supplement historical data. For example, if a user passes away, the generated album can be used to recreate the deceased's past appearances or produce a retrospective video in the form of an autobiography. This can help the bereaved family receive deeper emotion and comfort through the retrospective video.

[0073] Historical images and customized content generated in this way can be used to verify the memory of users, such as the elderly, and as tools for dementia diagnosis. Furthermore, images generated during the dementia diagnosis process can be used to provide paid diagnostic services, sell the images generated during diagnosis to families, or generate revenue by providing customized services linked to dementia management programs. Furthermore, public content can be utilized as material for historical films, documentaries, and historical education, based on the memories of elderly users. Combining historical images with AR / VR technology during public content production can have the advantage of enhancing viewer engagement.

[0074] The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present invention pertains.

[0075] While the embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will appreciate that the present invention can be implemented in other specific forms without altering the technical concept or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

[0076] The present invention can generate revenue by providing data for supplementing and preserving historical data by uniquely creating an image of the past as recalled by the user using speech data of an elderly user.

Claims

1. A method for generating past images using the elderly's recall data based on generative AI performed by a server. A process of receiving user information including speech data of an elderly user reminiscing about the past; A process of extracting object information and time information to generate past images by analyzing the above speech data; and A method for generating past images using the recollection data of the elderly based on generative AI, including a process for generating past images of the user based on the object information and the time information.

2. In claim 1, The above speech data includes voice data, A method for generating past images using recollection data of an elderly person based on generative AI, wherein the process of receiving the user information further includes a process of receiving at least one of image data and text data provided by the user.

3. In claim 1, The above object information is a method for generating past images using the recollection data of the elderly based on generative AI, which includes at least one of place information, person information, building information, animal information, plant information, and object information.

4. In claim 1, The process of creating the above past image is: A process of creating a basic image using the above object information; and A method for generating past images using recollection data of the elderly based on generative AI, including a process of correcting the basic image using the above-mentioned time information.

5. In claim 4, Further comprising a process of collecting auxiliary information for correcting the above basic image, A method for generating past images using the elderly's recall data based on generative AI, wherein the process of collecting the above auxiliary information comprises collecting at least one of public image information, crawling information, and user feedback information related to at least one of the object information and the time information.

6. In claim 5, A method for generating past images using the elderly's recall data based on generative AI, wherein the process of correcting the above-mentioned basic image includes a process of supplementing the above-mentioned basic image using the above-mentioned auxiliary information corresponding to the above-mentioned time information.

7. In claim 6, The process of collecting the above auxiliary information includes a process of collecting reference auxiliary information corresponding to the time information, previous auxiliary information corresponding to a previous time based on the time information, and subsequent auxiliary information corresponding to a subsequent time. The process of supplementing the above basic image is a method for generating past images using the elderly's recall data based on generative AI, which supplements the basic image by using the supplementary information of the time closest to the time information among the previous and subsequent supplementary information when the above reference auxiliary information is absent.

8. A device for generating past images using the elderly's recollection data based on generative AI. A user terminal capable of acquiring user information including speech data of an elderly user reminiscing about the past; and A management server capable of receiving the above user information and generating a past image of the user based on the above speech data; The above management server, A device for generating past images using the recollection data of the elderly based on generative AI, which extracts object information and time information for generating past images by analyzing the above speech data, and can generate past images recalled by the user based on the object information and time information.

9. A computer program stored on a computer-readable recording medium, which is combined with a computer as hardware and enables the computer to perform the method of any one of claims 1 to 7.

Images