Sleep assistance method, device and system

Abstract

The present invention discloses a sleep assistance method, device, and system. The sleep assistance method comprises: obtaining a dynamic sleep assessment knowledge graph of a target user, and obtaining multimodal data related to sleep of the target user; determining a sleep assistance plan for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data; and obtaining the target user's subjective sleep data and objective sleep data during the execution of the sleep assistance plan, and adjusting the sleep assistance plan. The present invention determines a sleep assistance plan for the target user using the target user's dynamic sleep assessment knowledge graph and the target user's multimodal data related to sleep, and obtains the target user's subjective sleep data and objective sleep data during the execution of the sleep assistance plan, and adjusts the sleep assistance plan, thereby effectively improving the user's sleep quality.

Description

Technical Field

[0001] The present invention relates to the field of sleep assistance technology, and in particular to a sleep assistance method, device and system. Background Art

[0002] In today's society, sleep quality has become a key indicator of health and quality of life. Sleep is a crucial means for the body to repair and recover, but sleep quality issues are becoming increasingly prominent. Improving sleep quality can have a positive impact on a person's quality of life, especially in today's complex society. Many people can improve their work efficiency and enhance their motivation through high-quality sleep. Therefore, improving users' sleep quality is a pressing issue that needs to be addressed. Summary of the Invention

[0003] The present invention provides a sleep assistance method, aiming to effectively improve the sleep quality of a user.

[0004] To achieve the above objectives, the present invention provides a sleep assistance method, which comprises:

[0005] Obtaining a dynamic sleep assessment knowledge graph of a target user, and obtaining multimodal sleep-related data of the target user;

[0006] Determining a sleep assistance program for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data;

[0007] During the execution of the sleep assistance program, subjective sleep data and objective sleep data of the target user are obtained, and the sleep assistance program is adjusted.

[0008] Optionally, obtaining a dynamic sleep knowledge graph of a target user includes:

[0009] Acquiring sleep knowledge data, and constructing a sleep knowledge database based on the sleep knowledge;

[0010] Constructing a sleep assessment knowledge graph based on the sleep knowledge database;

[0011] After the sleep knowledge database is updated, the sleep assessment knowledge graph is updated based on the target user's satisfaction evaluation to obtain a dynamic sleep knowledge graph.

[0012] Optionally, constructing a sleep assessment knowledge graph based on the sleep knowledge database includes:

[0013] Extracting key sleep data from the sleep knowledge database based on prior knowledge, wherein the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data;

[0014] Performing text preprocessing on the key sleep data to obtain preprocessed text;

[0015] Sleep keywords are extracted from the preprocessed text, and each sleep keyword is categorized to obtain a main entity or guest entity corresponding to the sleep keyword; for a pair of entities to be associated, relationship extraction processing is performed based on rules or deep learning to obtain a relationship between the main entity and the guest entity, and the main entity and the guest entity are associated through the relationship to obtain a sleep entity pair, each sleep entity pair including a main entity, a guest entity, and a relationship between the main entity and the guest entity;

[0016] Based on the sleep entity pairs, a sleep assessment knowledge graph is constructed.

[0017] Optionally, the relationship extraction process for a pair of entities to be associated based on rules or deep learning includes:

[0018] For a pair of entities to be associated, determine whether the entity pair to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity;

[0019] If the entity pair to be associated is of a simple relationship type, relationship extraction processing is performed based on the rules;

[0020] If the entity pair to be associated is of a complex relationship type, relationship extraction processing is performed based on deep learning.

[0021] Optionally, the updating of the sleep assessment knowledge graph based on the target user's satisfaction evaluation to obtain a dynamic sleep knowledge graph includes:

[0022] Based on the satisfaction evaluation of the target user, target entity pairs with satisfaction lower than a preset satisfaction level are determined in the sleep assessment knowledge graph, and the target entity pairs are weighted and reviewed. After the review is passed, a dynamic sleep knowledge graph is obtained.

[0023] In a second aspect, an embodiment of the present invention further provides a sleep aid device, comprising:

[0024] An acquisition module, configured to acquire a dynamic sleep assessment knowledge graph of a target user and acquire multimodal sleep-related data of the target user;

[0025] a processing module, configured to determine a sleep assistance program for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data;

[0026] The adjustment module is configured to obtain the subjective sleep data and the objective sleep data of the target user during the execution of the sleep assistance program, and adjust the sleep assistance program.

[0027] Optionally, the acquisition module includes:

[0028] an acquisition submodule, configured to acquire sleep knowledge data and construct a sleep knowledge database based on the sleep knowledge;

[0029] A construction submodule, configured to construct a sleep assessment knowledge graph based on the sleep knowledge database;

[0030] The updating submodule is used to update the sleep assessment knowledge graph based on the satisfaction evaluation of the target user after the sleep knowledge database is updated to obtain a dynamic sleep knowledge graph.

[0031] Optionally, the construction submodule includes:

[0032] an extraction unit, configured to extract key sleep data from the sleep knowledge database based on prior knowledge, wherein the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data;

[0033] a first processing unit, configured to perform text preprocessing on the key sleep data to obtain a preprocessed text;

[0034] a second processing unit, configured to extract sleep keywords from the preprocessed text and perform category identification on each of the sleep keywords to obtain a main entity or a guest entity corresponding to the sleep keyword; perform relationship extraction processing based on rules or deep learning for a pair of entities to be associated to obtain a relationship between the main entity and the guest entity, and associate the main entity with the guest entity through the relationship to obtain a sleep entity pair, each sleep entity pair including a main entity, a guest entity, and a relationship between the main entity and the guest entity;

[0035] A construction unit is used to construct a sleep assessment knowledge graph based on the sleep entity pairs.

[0036] Optionally, the second processing unit includes:

[0037] A first processing sub-unit is configured to determine, for an entity pair to be associated, whether the entity pair to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity;

[0038] A second processing sub-unit is configured to perform relationship extraction processing based on rules if the entity pair to be associated is of a simple relationship type;

[0039] The third processing sub-unit is configured to perform relationship extraction processing based on deep learning if the entity pair to be associated is of a complex relationship type.

[0040] In a third aspect, an embodiment of the present invention further provides a sleep assistance system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the sleep assistance method as described in any one of the embodiments of the present invention.

[0041] The technical solution of the sleep assistance method of the present invention obtains a dynamic sleep assessment knowledge graph of the target user and multimodal data related to sleep of the target user; based on the dynamic sleep assessment knowledge graph and multimodal data, a sleep assistance plan for the target user is determined; during the execution of the sleep assistance plan, the target user's subjective sleep data and objective sleep data are obtained to adjust the sleep assistance plan. The present invention determines a sleep assistance plan for the target user through the dynamic sleep assessment knowledge graph of the target user and multimodal data related to sleep of the target user; during the execution of the sleep assistance plan, the target user's subjective sleep data and objective sleep data are obtained to adjust the sleep assistance plan, which can effectively improve the user's sleep quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a sleep assistance method according to an embodiment of the present invention;

[0043] Figure 2 A schematic structural diagram of a sleep aid device provided by an embodiment of the present invention;

[0044] Figure 3 This is a structural diagram of a sleep assistance system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0047] It should also be noted that when an element is referred to as being "fixed on" or "disposed on" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element.

[0048] In addition, the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0049] See Figure 1 , Figure 1 FIG. 1 is a flow chart of a sleep assistance method provided by an embodiment of the present invention. The sleep assistance method includes the following steps:

[0050] Step S10: Obtain the target user's dynamic sleep assessment knowledge graph and obtain the target user's sleep-related multimodal data.

[0051] In this embodiment, the target user may be understood as a user who needs to improve sleep.

[0052] The aforementioned knowledge graph is a structured knowledge representation framework based on semantic networks, constructing a domain knowledge system through nodes (entities / concepts) and edges (attributes / relationships). Through entity extraction, relationship reasoning, and semantic linking, knowledge graph technology can systematically construct a sleep diagnosis and treatment knowledge network, resolving information silos and logical gaps.

[0053] The dynamic sleep assessment knowledge graph is constructed from a sleep database. The sleep database includes key sleep indicators, sleep performance, and classifications. This dynamic sleep assessment knowledge graph is used to assess a user's sleep status and improve their sleep quality. It includes data on the user's sleep habits, environmental factors, physiological indicators, and other data. It is dynamically updated and can continuously learn and evolve over time.

[0054] The multimodal data includes user basic information, sleep environment data, physical and mental health data, sleep assessment data, and sleep support data. The user basic information includes information such as birthdate, age, gender, occupation, education level, sibling order, and whether a person has a regular lifestyle. The sleep environment data includes external factors such as lighting, noise, work stress, and whether they work night shifts. The physical and mental health data includes both physical and mental health data. Physical health data includes height, weight, BMI, tobacco, alcohol, coffee, and tea consumption, chronic disease history (such as hypertension, diabetes, coronary heart disease, prostatic hyperplasia, and autoimmune diseases), frequency of nocturia, and history of surgical trauma. The mental health data includes records of the user's mental health status and medical history. The user's mental health status can be assessed using tools such as the Patient Health Questionnaire-9 Depression Scale (PHQ-9) and the Generalized Anxiety Disorder Scale (GAD-7). The user's medical history includes a history or family history of anxiety, depression, mania, and other conditions, as well as a family history of sleep disorders. The above-mentioned sleep assessment data includes scale assessment data, sleep diary data, and objective sleep data. The above-mentioned scale assessment data is used to quantify the user's sleep quality; the above-mentioned sleep diary data is used to record the user's sleep conditions in the past 1-2 weeks, including sleep onset time, number of sleep interruptions, early awakening time, etc.; the above-mentioned objective sleep data includes deep sleep, light sleep, rapid eye movement sleep time, etc. Objective sleep data can be collected through wearable devices, such as body movement recorders. The above-mentioned sleep assistance data includes drug sleep assistance data, psychological sleep assistance data, and physical sleep assistance data.

[0055] Step S20: Determine a sleep assistance plan for the target user based on the dynamic sleep assessment knowledge graph and multimodal data.

[0056] In this embodiment, based on the target user's dynamic sleep assessment knowledge graph and the target user's sleep-related multimodal data, the key factors affecting the target user's sleep quality can be analyzed, the target user's sleep quality can be identified, and a sleep assistance program to improve sleep quality can be designed.

[0057] The above-mentioned sleep assistance program can be understood as a program to help improve sleep quality.

[0058] Step S30 : During the execution of the sleep assistance program, the subjective sleep data and the objective sleep data of the target user are obtained, and the sleep assistance program is adjusted.

[0059] In this embodiment, the subjective sleep data can be understood as the user's subjective sleep data for the past 1-2 weeks, including data such as time to bedtime, number of sleep interruptions, and early awakening time. This data can be collected through questionnaires or application input.

[0060] The objective sleep data described above can be understood as sleep data detected by a wearable device, including data on deep sleep, light sleep, and rapid eye movement sleep time. The wearable device described above can be an actigraph, etc.

[0061] In this embodiment, during the execution of a sleep assistance program, the effectiveness of the current sleep assistance program can be evaluated based on the target user's subjective and objective sleep data, possible problems or deficiencies can be identified, and the sleep assistance program can be adjusted accordingly. For example, if the target user's subjective and objective sleep data show that the user frequently wakes up late at night, the room temperature or lighting can be adjusted, or pre-bedtime activities can be altered. By personalizing the sleep assistance program, the present invention allows users to more effectively improve their sleep condition and thus improve their sleep quality.

[0062] In this embodiment, a dynamic sleep assessment knowledge graph and multimodal sleep-related data of the target user are obtained; a sleep assistance program for the target user is determined based on the dynamic sleep assessment knowledge graph and multimodal data; and during the execution of the sleep assistance program, the target user's subjective and objective sleep data are obtained to adjust the sleep assistance program. The present invention determines a sleep assistance program for the target user using the dynamic sleep assessment knowledge graph and multimodal sleep-related data of the target user, and during the execution of the sleep assistance program, the target user's subjective and objective sleep data are obtained to adjust the sleep assistance program, thereby effectively improving the user's sleep quality.

[0063] It is understandable that in the specific implementation of this application, user data, sleep data, medical data and other related data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as the training and use of various models need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0064] Optionally, in the step of obtaining the dynamic sleep knowledge graph of the target user, sleep knowledge data can be obtained, and a sleep knowledge database can be constructed based on the sleep knowledge; a sleep assessment knowledge graph can be constructed based on the sleep knowledge database; after the sleep knowledge database is updated, the sleep assessment knowledge graph can be updated based on the target user's satisfaction evaluation to obtain a dynamic sleep knowledge graph.

[0065] In an embodiment of the present invention, the sleep knowledge data includes sleep knowledge data collected from sleep assistance guidelines, research literature, monographs, clinical practice data, user feedback, and related materials.

[0066] The aforementioned sleep knowledge database is constructed based on sleep knowledge data, including collected key sleep indicators, sleep manifestations, and categories, such as sleep cycles, factors affecting sleep quality, common sleep problems, and their solutions. This sleep knowledge data includes medical-grade sleep knowledge data, which can be understood as verified and standardized sleep knowledge data derived from medical research and clinical practice.

[0067] The above sleep assessment knowledge graph is a knowledge graph used to evaluate the user's sleep condition and improve the user's sleep quality.

[0068] The above dynamic sleep assessment knowledge graph is dynamically updated and can continue to learn and evolve over time.

[0069] The aforementioned knowledge graph is a structured knowledge representation framework based on semantic networks, constructing a domain knowledge system through nodes (entities / concepts) and edges (attributes / relationships). Through entity extraction, relationship reasoning, and semantic linking, knowledge graph technology can systematically construct a sleep diagnosis and treatment knowledge network, resolving information silos and logical gaps.

[0070] Furthermore, as time goes by and technology develops, new sleep research literature, user feedback, etc. will continue to emerge. Therefore, it is necessary to regularly check and update the sleep knowledge database to ensure that the information in the sleep knowledge database is up to date.

[0071] The aforementioned satisfaction rating can be understood as a user's evaluation of a product, service, or experience based on their feelings and expectations. Examples include emotional feedback and feedback on expectations. User satisfaction ratings are a direct indicator of product or service effectiveness. The sleep assessment knowledge graph can be adjusted or updated based on user satisfaction ratings to create a dynamic sleep knowledge graph, ensuring it more accurately reflects user needs.

[0072] The above dynamic sleep knowledge graph can be optimized and improved based on direct feedback from users, providing users with more accurate and personalized suggestions for improving sleep quality.

[0073] It should be noted that the dynamic knowledge graph can improve its accuracy and user experience through continuous learning and adaptation.

[0074] Optionally, in the step of constructing a sleep assessment knowledge graph based on a sleep knowledge database, key sleep data can be extracted from the sleep knowledge database based on prior knowledge; text preprocessing is performed on the key sleep data to obtain preprocessed text; sleep keywords are extracted from the preprocessed text, and categories are identified for each sleep keyword to obtain the main entity or guest entity corresponding to the sleep keyword; for a pair of entities to be associated, relationship extraction processing is performed based on rules or deep learning to obtain the relationship between the main entity and the guest entity, the main entity and the guest entity are associated through the relationship to obtain a sleep entity pair, each sleep entity pair includes a main entity, a guest entity and the relationship between the main entity and the guest entity; based on the key sleep data, a sleep assessment knowledge graph is constructed.

[0075] In this embodiment, the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data. The sleep impact data can be understood as data that affects sleep, such as the impact of environmental factors and lifestyle habits on sleep. The sleep performance and classification data are used to describe and categorize different sleep states. The sleep intervention data is used to identify intervention measures to improve or regulate sleep. The sleep prognosis data is used to predict future sleep quality.

[0076] The above-mentioned prior knowledge can be understood as the knowledge or experience that has been accumulated and widely recognized to improve sleep quality before research or application.

[0077] The above-mentioned sleep assessment knowledge graph is a knowledge graph used to assess the user's sleep condition and improve the user's sleep quality.

[0078] In this embodiment, the sleep assessment knowledge graph of the present invention can provide personalized suggestions for improving sleep quality based on the user's personal situation, helping the user to improve sleep quality and thus improve the quality of life.

[0079] In this embodiment, each sleeping entity pair includes a primary entity, a secondary entity, and the relationship between the primary and secondary entities. The primary entity can be understood as the primary object of interest in the sleeping entity pair, an independent entity; the secondary entity can be understood as another entity that has some relationship with the primary entity. The relationship between the primary and secondary entities can be causal, collaborative, or other.

[0080] The above key sleep data include sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data.

[0081] The above text preprocessing can be understood as the process of normalizing and time-normalizing the raw text data. Normalization unifies the expression, for example, "can't sleep" → "difficulty falling asleep," "3 o'clock" → "03:00." Time normalization unifies the time format, for example, "two weeks" → 14 days, "last month" → 2025-01-01 to 2025-01-31, etc.

[0082] The entity recognition process can be understood as the process of identifying and classifying entities from text. Entities include time, place, task, event, etc.

[0083] The above-mentioned relationship extraction process can be understood as a process of identifying the relationship between entities in the text.

[0084] The above sleep assessment knowledge graph is a knowledge graph used to assess the user's sleep condition and improve the user's sleep quality.

[0085] In this embodiment, the present invention obtains preprocessed text by performing preprocessing such as denoising, word segmentation, and standardization, and performs entity recognition and relationship extraction on the preprocessed text to obtain sleep entity pairs. Based on the sleep entity pairs, a sleep assessment knowledge graph is constructed, which helps to deeply analyze how to improve sleep quality.

[0086] Optionally, in the step of performing entity recognition and relationship extraction on the preprocessed text to obtain sleep entity pairs, sleep keywords can be extracted from the preprocessed text, and categories can be identified for each sleep keyword to obtain the main entity or guest entity corresponding to the sleep keyword; for a pair of entities to be associated, relationship extraction can be performed based on rules or deep learning to obtain the relationship between the main entity and the guest entity, and the main entity and the guest entity can be associated through the relationship to obtain a sleep entity pair.

[0087] In this embodiment, the sleep keyword extraction can be understood as an extraction process of identifying sleep-related words from the pre-processed text, such as sleep time, sleep quality, and other sleep keywords.

[0088] The above-mentioned category identification can be understood as a process of classifying each sleep keyword.

[0089] The above-mentioned main entity can be understood as the main object of concern in the sleep keyword, which is an independent entity, and the object entity is other entities associated with the main entity.

[0090] The above rule-based methods are predefined. For example, "If the XX method mentions 'improving sleep quality,' then establish the 'XX → Assistance → Sleep' relationship." These rule-based methods can quickly and accurately determine the relationship between the subject and object entities.

[0091] The above deep learning-based approach can be understood as using deep learning models (such as the TransH model) to predict the probability of "stress → induction → poor sleep quality." Deep learning models process complex implicit relationships and can uncover relationships in text that are difficult to define using rules, thereby achieving comprehensive coverage and accurate recognition of relationships.

[0092] The above-mentioned relationship extraction process can be understood as the process of identifying and extracting semantic relationships between entities from text. The purpose of relationship extraction is to convert information in unstructured text into structured data.

[0093] The above association can be understood as a process of associating the subject entity with the guest entity through the relationship between the subject entity and the guest entity. By establishing an association relationship between the subject entity and the guest entity, the connection between the subject entity and the guest entity can be clarified, thereby obtaining a sleeping entity pair.

[0094] The sleep entity pair described above includes a principal entity, an object entity, and the relationship between the principal and object entities. In this embodiment, the present invention uses keyword extraction and category recognition to identify principal or object entities corresponding to sleep keywords in preprocessed text. Then, based on rules or deep learning, for each entity pair to be associated, the relationship between the principal and object entities is extracted from the entity pair to be associated. The principal and object entities are then associated through the relationship between the principal and object entities, thereby obtaining a sleep entity pair. This invention enables more accurate extraction and understanding of information related to improving sleep quality from text.

[0095] Optionally, in the step of performing relationship extraction processing based on rules or deep learning for a pair of entities to be associated, it can be determined whether the entity pair to be associated is a simple relationship type or a complex relationship type based on the frequency of entity occurrence and the complexity of the relationship; if the entity pair to be associated is a simple relationship type, relationship extraction processing is performed based on rules; if the entity pair to be associated is a complex relationship type, relationship extraction processing is performed based on deep learning.

[0096] In this embodiment, the entity occurrence frequency can be understood as the number of times or proportion that the entity appears in the text. Specifically, the entity occurrence frequency reflects the importance or representativeness of the entity in a given data set.

[0097] The above relationship complexity can be understood as the complexity of the relationship between entities.

[0098] The above simple relationship types can be understood as simple relationship types, such as one-to-one and one-to-many relationships.

[0099] The above complex relationship types can be understood as complex relationship types, such as many-to-many relationships.

[0100] The above-mentioned relationship extraction process can be understood as a process of identifying and extracting semantic relationships between entities from text.

[0101] In this embodiment, the present invention can determine the relationship type of the entity pairs to be associated based on the entity occurrence frequency and the relationship complexity, and select the corresponding relationship extraction method based on the relationship type of the entity pairs to be associated, thereby improving the accuracy and efficiency of relationship extraction.

[0102] It should be noted that, after the sleep knowledge database is updated, the present invention can include preset entity pairs in the newly added data of the sleep knowledge database, and then supplement the preset branches in the sleep assessment knowledge graph based on the preset entity pairs.

[0103] In this embodiment, the preset entity pair includes a preset entity and a preset relationship, and the preset branch is a branch where the preset entity pair is located.

[0104] The above-mentioned supplements can be understood as the process of adding more relevant information, correcting errors, improving descriptions, etc., to make the sleep assessment knowledge graph more complete and accurate.

[0105] In one possible embodiment, suppose that during an update of a sleep knowledge database, a new piece of data regarding children's advice is added: "For children aged 3-6, it is recommended that they sleep at least 10 hours per night." This new data includes the preset entity pair "child" and "specific sleep habits." Based on "For children aged 3-6, it is recommended that they sleep at least 10 hours per night," the preset branch for the preset entity pair "child" and "specific sleep habits" in the sleep knowledge database can be supplemented or improved to add advice on how to improve children's sleep quality.

[0106] In this embodiment, when the newly added data of the sleep knowledge database includes preset entity pairs, the preset branches in the sleep assessment knowledge graph can be supplemented according to the preset entity pairs. By supplementing the preset branches in the sleep assessment knowledge graph, the sleep assessment knowledge graph library can continuously update and improve itself, providing more accurate and comprehensive relevant information for improving sleep quality.

[0107] Optionally, in the step of updating the sleep assessment knowledge graph based on the target user's satisfaction evaluation to obtain a dynamic sleep knowledge graph, target entity pairs with satisfaction levels lower than a preset satisfaction level can be determined in the sleep assessment knowledge graph based on the target user's satisfaction evaluation, and the target entity pairs can be weighted and reviewed. After the review is passed, a dynamic sleep knowledge graph can be obtained.

[0108] In the embodiment of the present invention, the above-mentioned satisfaction evaluation is an evaluation made by a user on the object of contact based on his or her own feelings and expectations after using a product or service or receiving a certain experience.

[0109] The above preset satisfaction level is a predefined satisfaction threshold.

[0110] The above-mentioned weight adjustment can be understood as a process of readjusting the main entity weight and the guest entity weight in the target entity pair.

[0111] The above review can be understood as the process of reviewing the target entity pairs after the weight adjustment. Through the review, errors, omissions or irregularities can be discovered and corrected to ensure the authenticity and reliability of the information.

[0112] It can be reviewed by professionals. After the professional review is passed, the target entity pairs with adjusted weights are updated to the sleep knowledge graph to obtain a dynamic sleep knowledge graph.

[0113] The above-mentioned dynamic sleep knowledge graph can be optimized and improved based on direct feedback from users, providing users with more accurate and personalized suggestions for improving sleep quality.

[0114] It should be noted that, based on the target user's satisfaction rating, target entity pairs with satisfaction ratings below a preset satisfaction rating can be identified in the sleep assessment knowledge graph. These target entity pairs with satisfaction ratings below the preset satisfaction rating are then weighted and reviewed. Once the review passes, the weighted target entity pairs are updated to the sleep knowledge graph, resulting in a dynamic sleep knowledge graph.

[0115] like Figure 2 As shown, Figure 2 : is a structural diagram of a sleep aid device provided by an embodiment of the present invention, the sleep aid device comprising:

[0116] An acquisition module 201 is configured to acquire a dynamic sleep assessment knowledge graph of a target user and acquire multimodal sleep-related data of the target user;

[0117] A processing module 202 is configured to determine a sleep assistance program for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data;

[0118] The adjustment module 203 is configured to obtain the subjective sleep data and the objective sleep data of the target user during the execution of the sleep assistance program, and adjust the sleep assistance program.

[0119] Optionally, the acquisition module includes:

[0120] an acquisition submodule, configured to acquire sleep knowledge data and construct a sleep knowledge database based on the sleep knowledge;

[0121] A construction submodule, configured to construct a sleep assessment knowledge graph based on the sleep knowledge database;

[0122] The updating submodule is used to update the sleep assessment knowledge graph based on the satisfaction evaluation of the target user after the sleep knowledge database is updated to obtain a dynamic sleep knowledge graph.

[0123] Optionally, the construction submodule includes:

[0124] an extraction unit, configured to extract key sleep data from the sleep knowledge database based on prior knowledge, wherein the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data;

[0125] a first processing unit, configured to perform text preprocessing on the key sleep data to obtain a preprocessed text;

[0126] a second processing unit, configured to extract sleep keywords from the preprocessed text and perform category identification on each of the sleep keywords to obtain a main entity or a guest entity corresponding to the sleep keyword; perform relationship extraction processing based on rules or deep learning for a pair of entities to be associated to obtain a relationship between the main entity and the guest entity, and associate the main entity with the guest entity through the relationship to obtain a sleep entity pair, each sleep entity pair including a main entity, a guest entity, and a relationship between the main entity and the guest entity;

[0127] A construction unit is used to construct a sleep assessment knowledge graph based on the sleep entity pairs.

[0128] Optionally, the second processing unit includes:

[0129] A first processing sub-unit is configured to determine, for an entity pair to be associated, whether the entity pair to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity;

[0130] A second processing sub-unit is configured to perform relationship extraction processing based on rules if the entity pair to be associated is of a simple relationship type;

[0131] The third processing sub-unit is configured to perform relationship extraction processing based on deep learning if the entity pair to be associated is of a complex relationship type.

[0132] Optionally, the update submodule is used to determine, in the sleep assessment knowledge graph, target entity pairs whose satisfaction is lower than a preset satisfaction level based on the target user's satisfaction evaluation, adjust the weights of the target entity pairs and review them, and obtain a dynamic sleep knowledge graph after the review is passed.

[0133] The present invention also provides a sleep aid system, see Figure 3 , Figure 3 1 is a schematic diagram of the structure of a sleep assistance system in a hardware operating environment according to an embodiment of the present invention.

[0134] The sleep assistance system of the embodiment of the present invention can be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server. Figure 3 As shown, the sleep assistance system may include: a processor 1001 (e.g., a CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Communication bus 1002 is used to enable communication between these components. User interface 1003 may include a display and an input unit, such as a keyboard. Optionally, user interface 1003 may also include a standard wired interface or a wireless interface. Network interface 1004 may optionally include a standard wired interface or a wireless interface (e.g., a Wi-Fi interface). Memory 1005 may be high-speed RAM or non-volatile memory, such as disk storage. Memory 1005 may also optionally be a storage device independent of processor 1001.

[0135] Those skilled in the art will understand that Figure 3 The structure of the sleep assistance system shown in the figure does not constitute a limitation to the sleep assistance system, and the sleep assistance system may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0136] like Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and a computer program.

[0137] exist Figure 3 In the sleep assistance system shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the computer program stored in the memory 1005. When the computer program is called and executed by the processor 1001, the steps of the above-mentioned sleep assistance method are implemented.

[0138] Based on the computer program proposed in the aforementioned embodiment, the present invention further proposes a storage medium, which stores the computer program. When the computer program is executed by a controller, the sleep assistance method described in the aforementioned embodiment is implemented.

[0139] Since the sleep assistance system and storage medium of the present invention can implement the steps of the above sleep assistance method, they at least have all the beneficial effects brought by the technical solutions of the above sleep assistance method embodiments, which will not be described in detail here.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection of devices or modules through some interfaces, which can be electrical, mechanical or other forms.

[0141] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0142] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0143] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0144] The above description is only a partial or preferred embodiment of the present invention. Neither the text nor the drawings can limit the scope of protection of the present invention. Any equivalent structural transformation made by using the contents of the present invention specification and drawings under the overall concept of the present invention, or direct / indirect application in other related technical fields, is included in the scope of protection of the present invention.

Claims

1. A sleep aid method, characterized in that: The method comprises: Obtain a dynamic sleep assessment knowledge graph for a target user, and obtain multimodal sleep-related data for the target user; specifically, based on prior knowledge, extract key sleep data from a sleep knowledge database, wherein the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; perform text preprocessing on the key sleep data to obtain a preprocessed text; perform sleep keyword extraction on the preprocessed text, and perform category identification on each of the sleep keywords to obtain a main entity or guest entity corresponding to the sleep keyword; for a pair of entities to be associated, perform relationship extraction processing based on rules or deep learning to obtain a relationship between the main entity and the guest entity, associate the main entity with the guest entity through the relationship to obtain a sleep entity pair, wherein each sleep entity pair includes a main entity, a guest entity, and a relationship between the main entity and the guest entity; construct a sleep assessment knowledge graph based on the sleep entity pairs; Determining a sleep assistance program for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data; During the execution of the sleep assistance program, the subjective sleep data and objective sleep data of the target user are obtained, and the sleep assistance program is adjusted. Specifically, based on the satisfaction evaluation of the target user, target entity pairs with satisfaction levels lower than a preset satisfaction level are determined in the sleep assessment knowledge graph, and the target entity pairs are weighted and reviewed. After the review is passed, a dynamic sleep knowledge graph is obtained.

2. The sleep assistance method according to claim 1, characterized in that: The relationship extraction process for a pair of entities to be associated based on rules or deep learning includes: For a pair of entities to be associated, determine whether the entity pair to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity; If the entity pair to be associated is of a simple relationship type, relationship extraction processing is performed based on the rules; If the entity pair to be associated is of a complex relationship type, relationship extraction processing is performed based on deep learning.

3. A sleep aid device, characterized in that: The sleeping aid device comprises: An acquisition module is used to acquire a dynamic sleep assessment knowledge graph of a target user, and to acquire multimodal sleep-related data of the target user; specifically, based on prior knowledge, key sleep data is extracted from a sleep knowledge database, wherein the key sleep data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; text preprocessing is performed on the key sleep data to obtain a preprocessed text; sleep keywords are extracted from the preprocessed text, and categories are identified for each of the sleep keywords to obtain a main entity or a guest entity corresponding to the sleep keyword; for a pair of entities to be associated, relationship extraction processing is performed based on rules or deep learning to obtain a relationship between the main entity and the guest entity, and the main entity and the guest entity are associated through the relationship to obtain a sleep entity pair, wherein each sleep entity pair includes a main entity, a guest entity, and a relationship between the main entity and the guest entity; a sleep assessment knowledge graph is constructed based on the sleep entity pairs; a processing module, configured to determine a sleep assistance program for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data; An adjustment module is used to obtain the subjective sleep data and objective sleep data of the target user during the execution of the sleep assistance program and adjust the sleep assistance program. Specifically, based on the satisfaction evaluation of the target user, the adjustment module determines the target entity pairs whose satisfaction is lower than the preset satisfaction in the sleep assessment knowledge graph, adjusts the weights of the target entity pairs, and reviews them. After the review is passed, a dynamic sleep knowledge graph is obtained.

4. The sleeping aid device according to claim 3, wherein: The acquisition module includes: A first processing sub-unit is configured to determine, for an entity pair to be associated, whether the entity pair to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity; A second processing sub-unit is configured to perform relationship extraction processing based on rules if the entity pair to be associated is of a simple relationship type; The third processing sub-unit is configured to perform relationship extraction processing based on deep learning if the entity pair to be associated is of a complex relationship type.

5. A sleep assistance system, characterized in that: The sleep assistance system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the sleep assistance method according to claim 1 or 2 are implemented.

Images