An episodic memory training system for preventing and treating Alzheimer's disease

Abstract

The present invention discloses an episodic memory training system for preventing and treating Alzheimer's disease, the device comprising: a server, including an episodic recording module, for acquiring individual life data and corresponding location data, extracting and storing episodes; a training device, connected to the server in communication, including a training module, generating questions based on the extracted episodes, and outputting the questions; and a device for receiving individual answers and judging whether they are correct. By acquiring the life data of the elderly individual, automatically identifying the episodes and storing them, the individual memory can be effectively trained through episodic memory training.

Description

Technical Field

[0001] The present invention belongs to the technical field, and in particular relates to an episodic memory training system for preventing and treating Alzheimer's disease. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] According to medical imaging findings, Alzheimer's disease is an irreversible and continuous pathophysiological process once it occurs. The key lies in early prevention, early detection, and early intervention. Control of risk factors can delay or slow the progression of the disease.

[0004] For the rehabilitation treatment of Alzheimer's patients, commonly used intelligent training therapies include memory rehabilitation methods, attention rehabilitation methods, calculation ability training methods, language training methods and thinking ability training methods. For example, the invention patent application CN111768841A discloses a language training auxiliary system and method based on the residual memory of Alzheimer's disease. The residual memory is used to retrieve the "jingles", "poems", "songs" and so on with good connection functions stored in long-term memory, and the patient is trained in language expression. Without increasing the language workload, the language expression ability is trained, thereby reducing the mental pressure and nervousness caused by language barriers. Patent CN210402747U discloses a memory medical training auxiliary device for Alzheimer's patients, which trains the memory of digital recall for Alzheimer's patients; CN211634797U discloses a thinking training device for Alzheimer's patients. The patient adjusts the angle of the thinking training disk so that the marbles in the device pass through the channel of the dense grid rotating ring until the marbles reach the dense grid rotating ring in the middle position. The above operations can well train the patient's mental judgment and reaction ability.

[0005] However, all of the above technical solutions are applied to the training of patients who have already developed the disease. Studies have found that patients will be subjectively aware of their individual episodic memory loss some time before the onset of the disease. Episodic memory training during this period is helpful for the prevention of Alzheimer's disease. However, there is currently no operational technology for training episodic memory. As for plot extraction technology, most of them are currently based on extracting summaries or storylines from video data, such as patent CN102902756B, and there is no recognition of plots in the daily lives of the elderly. Summary of the invention

[0006] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides an episodic memory training system for preventing and treating Alzheimer's disease, which can effectively train individual memory by acquiring life data of elderly individuals, automatically identifying and storing episodes, and through episodic memory training.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0008] An episodic memory training system for preventing and treating Alzheimer's disease, comprising:

[0009] The server includes a plot recording module for obtaining individual life data and corresponding location data, extracting and storing plots;

[0010] The training device is connected to the server in communication, and includes a training module, which generates questions based on the extracted plots and outputs the questions; and is used to receive individual answers and determine whether they are correct.

[0011] Furthermore, extracting and storing the plot includes: performing event recognition on the video data and location data acquired in real time, and determining the event category to which it belongs; and classifying and storing the events and related video clips according to the event category.

[0012] Furthermore, when it is identified that there is a person object whose distance from the individual is less than a set threshold and there is a conversation with the individual, it is determined that a social event has occurred, and the event, time, place and conversation object are recorded.

[0013] Furthermore, when an individual is identified as leaving home and exceeding a set range based on location data, a travel event is considered to have occurred and local map data is obtained; when an individual is identified as returning home, the destination of this trip is determined by combining the travel trajectory and map data; the travel time, return time, destination and travel trajectory of this trip are recorded.

[0014] Furthermore, videos from multiple days are compared synchronously. If the same behavior appears multiple times in the same time period, it is judged as a daily behavior event, and the time, location and specific behavior object of the behavior are recorded.

[0015] Furthermore, generating questions based on the extracted plot specifically includes: taking one or more of the time, place, characters, etc. involved in the plot as questions.

[0016] Furthermore, the training module also includes a plot reminder submodule, which plays a corresponding part or all of the video clip as a reminder when the individual fails to give a correct answer within the set time.

[0017] Furthermore, the training module also includes an evaluation submodule for recording the completion time of each question and, when a set number of questions are completed, recording the total completion time.

[0018] Furthermore, the training module is also used to generate a report based on the results of the episodic memory training over a period of time.

[0019] Furthermore, the system also includes a data acquisition device for acquiring individual life data and corresponding location data, and sending them to the server.

[0020] One or more of the above technical solutions have the following beneficial effects:

[0021] The above technical solutions can intervene in potential populations before the onset of Alzheimer's disease. By obtaining the life data of individual elderly people, the plots can be automatically identified and stored, and the individual memory can be effectively trained through episodic memory training.

[0022] The above technical solution provides a method for automatically identifying and recording life events specifically for the elderly. Through video data and location data, it can accurately identify individual social, travel, daily behavior and other events. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 This is a framework diagram of the episodic memory training system described in Embodiment 1 of the present invention;

[0025] Figure 2 This is a framework diagram of the training module described in Example 1 of the present invention. DETAILED DESCRIPTION

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0028] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0029] Embodiment 1

[0030] This embodiment discloses an episodic memory training system for preventing and treating Alzheimer's disease. Figure 1-2As shown, it includes: a data acquisition device, a training device and a server.

[0031] The data acquisition device can be a wearable device such as glasses or watches, or a mobile terminal such as a mobile phone or a tablet, as long as it can achieve the acquisition and transmission of audio or video data, and the positioning of the position, and is not limited here. In this embodiment, glasses are used as the data acquisition device, which includes hardware structures such as a camera, a memory card, and a transmission port. The training device can be a computer, a mobile phone, etc., and is not limited here.

[0032] The data acquisition device is used to call the video recording function, acquire individual life data and corresponding location data, and send them to the server. The data acquisition device can be turned on and off according to the user's needs.

[0033] The server is configured to include a user information management module, a plot recording module, a video storage module and a training record storage module.

[0034] User management module, used to manage the personal information and login passwords of registered users;

[0035] The plot recording module extracts and stores the plot based on the life data; wherein the plot includes time, place, and event. The event may be a conversation with one or more characters, taking a certain means of transportation to a certain place, picking up certain items, etc. In this embodiment, the event includes social events, daily behavior events, travel events, etc.

[0036] As a specific implementation method, the plot extraction based on the life data is real-time extraction, which specifically includes:

[0037] (1) Perform event recognition on the video data and location data acquired in real time and determine the event category to which it belongs;

[0038] Preset the extraction and storage rules of various events. Specifically,

[0039] ① When a person object is identified whose distance from an individual is less than a set threshold and who is talking to the individual, it is judged as a social event and the event, time, place and conversation partner are recorded.

[0040] ② The client obtains the current location and uploads the location to the server in a timely manner to record the user's behavior trajectory. When the individual is identified as leaving home and exceeding the set range based on the location data, it is considered that a travel event has occurred and local map data is obtained; when the individual is identified as returning home, the destination of this trip is determined by combining the travel trajectory and map data; the travel time, return time, destination and travel trajectory of this trip are recorded, where the travel trajectory includes a series of location data.

[0041] As a further implementation, the travel speed can be calculated based on the location information in the travel event to determine the travel mode, such as bicycle, bus, etc. Of course, the video data can also be combined to more accurately determine the travel mode.

[0042] ③ By comparing the frequency and time of user behaviors in the video, if it is found that it appears multiple times or the actions are similar in the same time, it is regarded as a daily behavior. Specifically, the videos of multiple days are compared synchronously. If the same behavior appears multiple times in the same time period, it is judged as a daily behavior event, and the time and location of the behavior are recorded; then the behavior is specifically identified to determine whether it is eating, drinking tea, watching TV, sleeping, etc. Furthermore, specific objects can be identified and recorded. For example, if it is a meal behavior, the type of food is also identified.

[0043] In addition, a schedule can be generated based on daily behavioral events to remind users.

[0044] (2) Store the event and related video clips.

[0045] As a specific implementation method, the plot is classified and stored in the database according to the event category, the data acquisition device realizes the video upload function, stores the video resources in the cloud server, and stores the video key in the database. The database includes data tables for multiple event categories and video clip collections. Each event category includes one or more data tables. For social events, the time, location, and social object are recorded; for daily behavior events, the time, location, and behavior are recorded; for travel time, the time, travel tool, travel start point, and destination are recorded.

[0046] Since the people that the elderly come into contact with are relatively fixed, the images of the individual's family and friends can be obtained in advance and pre-labeled. When the plot is extracted, when the relevant person is captured, it can be automatically identified and recorded. Of course, in order not to infringe on the privacy of others, the acquisition of the above videos and images is carried out with the consent of the relevant persons. Of course, the geographical scope of video shooting and storage can also be set, such as only within the family.

[0047] The video storage module is used to store recorded video data. In the background of the program, the recorded video files are uploaded to the cloud storage for subsequent medical viewing. In addition, in order to enhance the user experience, CDN acceleration is used when viewing the video to ensure the smoothness of the video.

[0048] The training record storage module is used to store individual episodic memory training records for subsequent statistical analysis.

[0049] The training device can be a common device such as a mobile phone, a computer, a tablet, etc., which is not limited here. The training device includes a personal information management module, a scenario recording module and a training module.

[0050] The personal information management module is used to store the user's personal information, including age, home address and other frequently visited places, medical records, etc. After collecting the user's personal information, the personal information management module also stores the user information in the database and caches it to the redis server to implement functions such as user login and identity information verification.

[0051] The training module is configured to include a questioning submodule, a scenario reminder submodule, an answer recognition submodule, an evaluation submodule and a report generation submodule.

[0052] The questioning submodule calls the server to obtain the plot record, generates questions based on the extracted plot, and displays the questions on a display screen or plays them through a speaker to guide the individual to recall the corresponding plot.

[0053] The generation of questions based on the extracted plot specifically includes: taking one or more of the time, place, characters, etc. involved in the plot as questions. For example, given a specific time and a specific place, ask the individual what person he talked to, or given a specific time and a specific place, ask the individual what activities he participated in, etc. The time period of the plot record obtained from the server can be specified by the user, such as the last week, the last month, January-March 2021, etc., which is not limited here. Of course, the system default value can also be set. When the user does not specify, the plot record of a certain period of time is retrieved by default.

[0054] The answer recognition submodule is used to accept the answer input by the individual via an input device (including but not limited to a touch screen, voice), and determine whether the answer is correct. In order to be more humane, a fault tolerance mechanism can be provided, for example, for date questions, it can recognize multiple date formats.

[0055] The plot reminder submodule is used to remind the event. Specifically, the duration can be set. When the individual does not give the correct answer within the set duration, the reminder is given. If it is a social event or daily behavior event, a selection or all of the corresponding video clips are played; if it is a travel time, the travel trajectory and corresponding map data are obtained and superimposed and displayed.

[0056] The evaluation submodule is used to record the completion time of each question; when a set number of questions are completed, the total completion time is recorded. In addition, the training device uploads the completion time and answer correctness data to the server. As a specific implementation method, the evaluation submodule also gives a score based on the completion time and answer correctness.

[0057] The report generation submodule is used to generate a report based on the evaluation results and give professional suggestions.

[0058] As a specific implementation method, since the evaluation result of a certain time cannot reflect the overall training effect, the evaluation report also includes a trend chart of the episodic memory results over a period of time. The report and corresponding suggestions are stored in the personal information management module to reflect the training effect over a period of time.

[0059] Embodiment 2

[0060] The purpose of this embodiment is to provide an episodic memory training device for preventing and treating Alzheimer's disease. For specific implementation methods, please refer to the corresponding part of Example 1.

[0061] One or more of the above embodiments guide individuals to recall life events, perform information pairing, complete episodic memory training, stimulate the intercellular pathways of memory neurons with the hippocampus as the core, continuously form new synapses, enhance the adaptability of the body, especially the hippocampus, in structure and function, prevent pathological and physiological changes in the brain, and thus achieve the effect of preventing and treating the occurrence of senile dementia.

[0062] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0063] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An episodic memory training system for preventing and treating Alzheimer's disease, characterized in that: include: The server includes a plot recording module for obtaining individual life data and corresponding location data, extracting and storing plots; A training device, connected to the server in communication, includes a training module, generates questions based on the extracted plots, and outputs the questions; and, for receiving the individual's answer and determining whether it is correct; The personal information management module is used to store the user's personal information, including age, home address and other frequently visited places, and medical records. After collecting the user's personal information, the personal information management module also stores the user information in the database and caches it on the server to realize the user login and identity information verification functions; the images of the individual's family and friends are obtained in advance and pre-labeled, and when the relevant persons are captured during the plot extraction, they are automatically identified and recorded; The extracting and storing of the plot includes: Event recognition is performed on the video data and location data acquired in real time, and the event category to which it belongs is determined; extraction and storage rules for various types of events are pre-set. Specifically, when a person object is identified whose distance from an individual is less than a set threshold and who has a conversation with the individual, it is determined that a social event has occurred, and the event, time, location, and conversation object are recorded; when an individual is identified to have left home based on location data and is beyond a set range, a travel event is considered to have occurred, and local map data is obtained; when an individual is identified to have returned home, the destination of this trip is determined by combining the travel trajectory and map data; the travel time, return time, destination, and travel trajectory of this trip are recorded; videos of multiple days are compared synchronously, and if the same behavior occurs multiple times in the same time period, it is determined that a daily behavior event has occurred, and the behavior time, location, and specific behavior object are recorded; Classify and store events and related video clips according to event categories; The generating of questions based on the extracted plot specifically includes: taking one or more of the time, place, and characters involved in the plot as questions; The training module also includes a plot reminder submodule with a preset duration. When the individual does not give a correct answer within the set duration, the corresponding part or all of the video clip is played as a reminder. Specifically, when the event is a social event or a daily behavior event, an excerpt or all of the corresponding video clip is played; when the event is a travel event, the travel trajectory and corresponding map data are obtained and superimposed and displayed.

2. The episodic memory training system according to claim 1, characterized in that: The training module also includes an evaluation submodule for recording the completion time of each question and, when a set number of questions are completed, recording the total completion time.

3. The episodic memory training system according to claim 1, characterized in that: The training module is also used to generate a report based on the results of the episodic memory training over a period of time.

4. The episodic memory training system according to claim 1, characterized in that: The system also includes a data acquisition device for acquiring individual life data and corresponding location data, and sending the data to the server.

Images