Sleep assisting method, device and system

Abstract

The invention discloses a sleep assistance method, device and system, and the method comprises the steps: obtaining a dynamic sleep evaluation knowledge graph of a target user, and obtaining the sleep-related multi-modal data of the target user; based on the dynamic sleep assessment knowledge graph and the multi-modal data, determining a sleep assistance scheme for the target user; in the process of executing the sleep assistance scheme, subjective sleep data and objective sleep data of the target user are obtained, and the sleep assistance scheme is adjusted. According to the method, the sleep assistance scheme for the target user is determined through the dynamic sleep evaluation knowledge graph of the target user and the sleep-related multi-modal data of the target user, and the subjective sleep data and the objective sleep data of the target user are acquired in the process of executing the sleep assistance scheme, so that the sleep assistance scheme is adjusted, and the sleep assistance efficiency is improved. And the sleep quality of the user can be effectively improved.

Description

Technical Field

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

[0002] In today's society, sleep quality has become one of the important indicators of people's health and quality of life. Sleep is an important means for the human body to repair and recover itself. However, the problem of people's sleep quality is becoming increasingly prominent nowadays. Improving sleep quality can have a positive impact on people's quality of life. Especially in today's complex society, many people can improve work efficiency and enhance the enthusiasm for life through high-quality sleep. Therefore, how to improve the sleep quality of users is an urgent problem to be solved at present. Summary of the Invention

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

[0004] To achieve the above object, the sleep assistance method proposed by the present invention includes: Obtaining a dynamic sleep assessment knowledge graph of a target user, and obtaining multi-modal data related to sleep of the target user; Based on the dynamic sleep assessment knowledge graph and the multi-modal data, determining a sleep assistance plan for the target user; During the execution of the sleep assistance plan, obtaining subjective sleep data and objective sleep data of the target user, and adjusting the sleep assistance plan.

[0005] Optionally, the obtaining of the dynamic sleep knowledge graph of the target user includes: Obtaining sleep knowledge data, and constructing a sleep knowledge database based on the sleep knowledge; Constructing a sleep assessment knowledge graph based on the sleep knowledge database; After the sleep knowledge database is updated, updating the sleep assessment knowledge graph based on the satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph.

[0006] Optionally, the constructing of the sleep assessment knowledge graph based on the sleep knowledge database includes: Extracting sleep key data from the sleep knowledge database based on prior knowledge, where the sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; Performing text preprocessing on the sleep key data to obtain preprocessed text; Extract sleep keywords from the preprocessed text, and identify the category of each sleep keyword to obtain the 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 the relationship between the main entity and the guest entity, and associate the main entity and the guest entity through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity; Construct a sleep assessment knowledge graph based on the sleep entity pairs.

[0007] Optionally, the performing relationship extraction processing based on rules or deep learning for a pair of entities to be associated includes: For a pair of entities to be associated, determine whether the pair of entities to be associated is a simple relationship type or a complex relationship type according to the entity appearance frequency and relationship complexity; If the pair of entities to be associated is a simple relationship type, perform relationship extraction processing based on rules; If the pair of entities to be associated is a complex relationship type, perform relationship extraction processing based on deep learning.

[0008] Optionally, the updating the sleep assessment knowledge graph based on the satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph includes: Based on the satisfaction evaluation of the target user, determine target entity pairs with a satisfaction lower than a preset satisfaction in the sleep assessment knowledge graph, adjust the weights of the target entity pairs and conduct a review, and after the review is passed, obtain a dynamic sleep knowledge graph.

[0009] In a second aspect, an embodiment of the present invention further provides a sleep assistance device, where the sleep assistance device includes: An acquisition module, configured to acquire a dynamic sleep assessment knowledge graph of a target user, and acquire multi-modal data related to the sleep of the target user; A processing module, configured to determine a sleep assistance plan for the target user based on the dynamic sleep assessment knowledge graph and the multi-modal data; An adjustment module, configured to acquire subjective sleep data and objective sleep data of the target user during the execution of the sleep assistance plan, and adjust the sleep assistance plan.

[0010] Optionally, the acquisition module includes: An acquisition sub-module, configured to acquire sleep knowledge data according to and construct a sleep knowledge database based on the sleep knowledge; A construction sub-module, configured to construct a sleep assessment knowledge graph based on the sleep knowledge database; An update sub-module, configured to update the sleep assessment knowledge graph based on the satisfaction evaluation of the target user after the sleep knowledge database is updated, so as to obtain a dynamic sleep knowledge graph.

[0011] Optionally, the construction sub-module includes: An extraction unit, configured to extract sleep key data from the sleep knowledge database based on prior knowledge, where the sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; A first processing unit, configured to perform text preprocessing on the sleep key data to obtain preprocessed text; A second processing unit, configured to extract sleep keywords from the preprocessed text, and perform category recognition on each sleep keyword to obtain the 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 the relationship between the main entity and the guest entity, and associate the main entity and the guest entity through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity; A construction unit, configured to construct a sleep assessment knowledge graph based on the sleep entity pairs.

[0012] Optionally, the second processing unit includes: A first processing sub-unit, configured to determine whether the pair of entities to be associated is a simple relationship type or a complex relationship type according to the entity appearance frequency and relationship complexity for a pair of entities to be associated; A second processing sub-unit, configured to perform relationship extraction processing based on rules if the pair of entities to be associated is a simple relationship type; A third processing sub-unit, configured to perform relationship extraction processing based on deep learning if the pair of entities to be associated is a complex relationship type.

[0013] In a third aspect, an embodiment of the present invention further provides a sleep assistance system, where the sleep assistance system includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the computer program is executed by the processor, the steps of the sleep assistance method as described in any one of the embodiments of the present invention are implemented.

[0014] The technical solution of the sleep assistance method of the present invention is to obtain the dynamic sleep assessment knowledge graph of the target user and the multi-modal data related to the sleep of the target user; based on the dynamic sleep assessment knowledge graph and the multi-modal data, determine the sleep assistance plan for the target user; during the execution of the sleep assistance plan, obtain the subjective sleep data and objective sleep data of the target user, and adjust the sleep assistance plan. The present invention determines the sleep assistance plan for the target user through the dynamic sleep assessment knowledge graph of the target user and the multi-modal data related to the sleep of the target user, and during the execution of the sleep assistance plan, obtains the subjective sleep data and objective sleep data of the target user, and adjusts the sleep assistance plan, which can effectively improve the sleep quality of the user. Description of the Drawings

[0015] Figure 1 It is a schematic flowchart of the sleep assistance method provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of the sleep assistance device provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of the sleep assistance system provided by an embodiment of the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] It should be noted that all the directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0018] It should also be noted that when an element is referred to as "fixed to" or "disposed on" another element, it can be directly on the other element or there may be an intermediate element at the same time. When an element is referred to as "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time.

[0019] In addition, the descriptions involving "first", "second", etc. in the present invention are for descriptive purposes only, and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] Refer to Figure 1 , Figure 1 which is a schematic flowchart of the sleep assistance method provided by an embodiment of the present invention. The sleep assistance method includes the following steps: Step S10, obtain the dynamic sleep assessment knowledge graph of the target user, and obtain the multi-modal data related to the sleep of the target user.

[0021] In this embodiment, the above-mentioned target user can be understood as a user who needs to improve sleep.

[0022] The above-mentioned knowledge graph is a structured knowledge representation framework based on a semantic network, and constructs a domain knowledge system through nodes (entities / concepts) and edges (attributes / relationships). Through entity extraction, relationship reasoning and semantic linking, the knowledge graph technology can systematically construct a sleep diagnosis and treatment knowledge network to solve the problems of information islands and logical breaks.

[0023] The above-mentioned dynamic sleep assessment knowledge graph is a dynamic sleep assessment knowledge graph constructed by a sleep database. The above-mentioned sleep database includes key indicators, sleep performance, classifications, etc. related to sleep. The above-mentioned dynamic sleep assessment knowledge graph is a knowledge graph for evaluating the sleep status of users and improving the sleep quality of users. The above-mentioned dynamic sleep assessment knowledge graph includes data such as the sleep habits, environmental factors, and physiological indicators of users. The above-mentioned dynamic sleep assessment knowledge graph is dynamically updated and can continuously learn and evolve over time.

[0024] The above-mentioned multimodal data includes multimodal data such as user basic information, sleep environment data, physical and mental health data, sleep assessment data, and sleep assistance data. The above-mentioned user basic information includes basic information such as name, age, gender, occupation, education level, sibling ranking, and whether the lifestyle is regular. The above-mentioned sleep environment data includes external incentives such as light, noise, work pressure, and whether it is a night shift. The above-mentioned physical and mental health data includes physical health data and mental health data. The above-mentioned physical health data includes data such as height, weight, BMI index, use of tobacco, alcohol, coffee, and tea, history of chronic diseases (such as hypertension, diabetes, coronary heart disease, prostatic hyperplasia, autoimmune diseases), frequency of nocturia at night, and history of surgery and trauma. The above-mentioned mental health data includes data such as records of the user's mental health status and the user's medical history. The above-mentioned user's mental health status can be evaluated by assessment tools such as the Patient Health Questionnaire - 9 (PHQ - 9) and the Generalized Anxiety Disorder Scale (GAD - 7). The above-mentioned user's medical history includes whether there is a history of diseases such as anxiety, depression, mania, or family history, and whether there is 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 situation in the recent 1 - 2 weeks, including the time of falling asleep, the number of sleep interruptions, the time of waking up early, etc.; the above-mentioned objective sleep data includes deep sleep, light sleep, rapid eye movement sleep time, etc., and the objective sleep data can be collected through wearable devices, and the wearable device can be an actigraph, etc. The above-mentioned sleep assistance data includes drug sleep assistance data, psychological sleep assistance data, and physical sleep assistance data.

[0025] Step S20: Based on the dynamic sleep assessment knowledge graph and the multimodal data, determine a sleep assistance plan for the target user.

[0026] In this embodiment, according to the dynamic sleep assessment knowledge graph of the target user and the multimodal data related to sleep of the target user, the key factors affecting the sleep quality of the target user can be analyzed, the sleep quality of the target user can be identified, and a sleep assistance plan for improving the sleep quality can be designed.

[0027] The above-mentioned sleep assistance plan can be understood as a plan to assist in improving sleep quality.

[0028] Step S30: During the execution of the sleep assistance plan, obtain the subjective sleep data and objective sleep data of the target user, and adjust the sleep assistance plan.

[0029] In this embodiment, the above-mentioned subjective sleep data can be understood as the sleep data that the user subjectively feels in the recent 1 - 2 weeks, including data such as the time of falling asleep, the number of sleep interruptions, and the time of waking up early. It can be collected through questionnaire surveys or input through applications.

[0030] The above objective sleep data can be understood as sleep data detected by a wearable device, including data such as deep sleep, light sleep, and rapid eye movement sleep time. The above wearable device can be an actigraph, etc.

[0031] In this embodiment, during the execution of the sleep assistance plan, the effect of the current sleep assistance plan can be evaluated based on the subjective sleep data and objective sleep data of the target user, and possible problems or deficiencies can be identified, and then the sleep assistance plan can be adjusted accordingly. For example, if the subjective sleep data and objective sleep data of the target user show that the user often wakes up late at night, then the room temperature or light can be adjusted, or the activities before going to bed can be changed. By personalizing the adjustment of the sleep assistance plan, the user can more effectively improve their sleep condition, thereby improving the sleep quality.

[0032] In this embodiment, a dynamic sleep assessment knowledge graph of the target user is obtained, and multimodal data related to the sleep of the target user is obtained; based on the dynamic sleep assessment knowledge graph and the multimodal data, a sleep assistance plan for the target user is determined; during the execution of the sleep assistance plan, the subjective sleep data and objective sleep data of the target user are obtained, and the sleep assistance plan is adjusted. By using the dynamic sleep assessment knowledge graph of the target user and the multimodal data related to the sleep of the target user, the present invention determines a sleep assistance plan for the target user, and during the execution of the sleep assistance plan, the subjective sleep data and objective sleep data of the target user are obtained, and the sleep assistance plan is adjusted, which can effectively improve the sleep quality of the user.

[0033] It can be understood that in the specific implementation of this application, data related to user data, sleep data, medical data, etc. 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 the relevant laws, regulations, and standards of relevant countries and regions.

[0034] 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 satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph.

[0035] In the embodiment of the present invention, the above sleep knowledge data includes sleep assistance guidelines, research literature, treatises, clinical practice data, user feedback, and sleep knowledge data collected from relevant materials.

[0036] The above sleep knowledge database is constructed based on sleep knowledge data, including key indicators, sleep performance, and classifications related to sleep that have been collected, such as sleep cycles, factors affecting sleep quality, common sleep problems and their solutions, etc. The sleep knowledge data includes medical-grade sleep knowledge data. The above medical-grade sleep knowledge data can be understood as sleep knowledge data that comes from medical research and clinical practice and has been verified and standardized.

[0037] 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.

[0038] The above dynamic sleep assessment knowledge graph is dynamically updated and can continuously learn and evolve over time.

[0039] The above Knowledge Graph is a structured knowledge representation framework based on semantic networks, which constructs 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 to solve the problems of information silos and logical breaks.

[0040] 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.

[0041] The above satisfaction evaluation can be understood as an evaluation made by users on the objects they come into contact with based on their feelings and expectations after using products, services, or receiving a certain experience. For example, it can be emotional feedback, expectation feedback, etc. The user's satisfaction score is a direct indicator to measure the effect of products or services. The sleep assessment knowledge graph can be adjusted or updated according to the user's satisfaction score to obtain a dynamic sleep knowledge graph to ensure that the dynamic sleep knowledge graph can more accurately reflect the user's needs.

[0042] The above dynamic sleep knowledge graph can be optimized and improved according to the user's direct feedback, providing users with more accurate and personalized suggestions for improving sleep quality.

[0043] It should be noted that the dynamic knowledge graph can improve the accuracy and user experience of the dynamic knowledge graph through continuous learning and adaptation.

[0044] Optionally, in the step of constructing a sleep assessment knowledge graph based on the sleep knowledge database, sleep key data can be extracted from the sleep knowledge database based on prior knowledge; the sleep key data is preprocessed to obtain preprocessed text; sleep keywords are extracted from the preprocessed text, and category recognition is performed on each sleep keyword to obtain the main entity or guest entity corresponding to the sleep keyword; for a pair of entities to be associated, relation extraction processing is 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 are associated through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity; a sleep assessment knowledge graph is constructed based on the sleep key data.

[0045] In this embodiment, the above sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data. The above sleep impact data can be understood as data that affects sleep, such as data on environmental factors and living habits that affect sleep status. The above sleep performance and classification data are used to describe and classify different sleep states. The above sleep intervention data are data on intervention measures for improving or regulating sleep. The above sleep prognosis data are used to predict future sleep quality.

[0046] The above prior knowledge can be understood as knowledge or experience that has been accumulated and widely recognized before research or application for improving sleep quality.

[0047] The above sleep assessment knowledge graph is a knowledge graph used to evaluate the sleep status of users and improve the sleep quality of users.

[0048] In this embodiment, the sleep assessment knowledge graph of the present invention can provide personalized suggestions for improving sleep quality according to the personal situation of users, helping users improve sleep quality and thus improve the quality of life.

[0049] In this embodiment, each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity. The above main entity can be understood as the object mainly concerned in the sleep entity pair, which is an independent entity; the guest entity can be understood as another entity having a certain relationship with the main entity. The relationship between the main entity and the guest entity can be a causal relationship, a cooperative relationship, etc.

[0050] The above sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data.

[0051] The above text preprocessing can be understood as a process of processing the original text data by performing operations such as standardization and time normalization. The standardization process is to unify the expression form. For example, "can't fall asleep" → "difficulty falling asleep", "3 o'clock" → "03:00". The time normalization process is to unify the time form. For example, "two weeks" → 14 days, "last month" → from January 1st, 2025 to January 31st, 2025, etc.

[0052] The above entity recognition processing can be understood as a process of identifying and classifying entities from the text. Entities include entities such as time, location, task, event, etc.

[0053] The above relationship extraction processing can be understood as a process of identifying the relationships between entities in the text.

[0054] The above sleep assessment knowledge graph is a knowledge graph used to evaluate the user's sleep status and improve the user's sleep quality.

[0055] In this embodiment, the present invention performs preprocessing such as denoising, word segmentation, and standardization on the text to obtain the preprocessed text, and performs entity recognition processing and relationship extraction processing on the preprocessed text to obtain sleep entity pairs, and constructs a sleep assessment knowledge graph based on the sleep entity pairs, which helps to deeply analyze how to improve sleep quality.

[0056] Optionally, in the step of performing entity recognition processing and relationship extraction processing on the preprocessed text to obtain sleep entity pairs, sleep keyword extraction can be performed on the preprocessed text, and category recognition can be performed on 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 based on deep learning to obtain the relationship between the main entity and the guest entity, and the main entity and the guest entity are associated through the relationship to obtain sleep entity pairs.

[0057] In this embodiment, the above sleep keyword extraction can be understood as a process of extracting words related to sleep from the preprocessed text. For example, sleep keywords such as sleep time and sleep quality.

[0058] The above category recognition can be understood as a process of performing category recognition on each sleep keyword.

[0059] The above main entity can be understood as the object mainly concerned in the sleep keyword, which is an independent entity, and the guest entity is other entities associated with the main entity.

[0060] The above rule-based is pre-defined rules. For example, "if the XX method mentions 'improve sleep quality', then establish the relationship 'XX → assist → sleep'". The above rule-based can quickly and accurately determine the relationship between the main entity and the guest entity.

[0061] The above-mentioned based on deep learning can be understood as using a deep learning model (such as the TransH model) to predict the probability of "stress → inducement → poor sleep quality". The deep learning model processes complex implicit relationships and can mine relationships that are difficult to define by rules in the text, thereby achieving comprehensive coverage and accurate identification of relationship extraction.

[0062] The above-mentioned relationship extraction process can be understood as a process of identifying and extracting the semantic relationship between entities from the text. The purpose of the relationship extraction process is to convert the information in the unstructured text into structured data.

[0063] The above-mentioned association can be understood as a process of associating the main entity with the guest entity through the relationship between the main entity and the guest entity. By establishing an association relationship between the main entity and the guest entity, the connection between the main entity and the guest entity can be clarified, and thus the sleep entity pair is obtained.

[0064] The above-mentioned sleep entity pair includes the main entity, the guest entity, and the relationship between the main entity and the guest entity. In this embodiment, the present invention identifies the main entity or the guest entity corresponding to the sleep keyword in the preprocessed text through keyword extraction and category recognition; then, based on rules or deep learning, for a pair of entities to be associated, the relationship between the main entity and the guest entity is extracted from the pair of entities to be associated, and the main entity and the guest entity are associated through the relationship between the main entity and the guest entity, thereby obtaining the sleep entity pair. The present invention can more accurately extract and understand the information related to improving sleep quality from the text.

[0065] Optionally, in the step of performing relationship extraction processing based on rules or deep learning for a pair of entities to be associated, for a pair of entities to be associated, according to the entity occurrence frequency and the relationship complexity, it is determined whether the pair of entities to be associated is a simple relationship type or a complex relationship type; if the pair of entities to be associated is a simple relationship type, then relationship extraction processing is performed based on rules; if the pair of entities to be associated is a complex relationship type, then relationship extraction processing is performed based on deep learning.

[0066] In this embodiment, the above-mentioned entity occurrence frequency can be understood as the number or proportion of times the entity appears in the text. Specifically, the entity occurrence frequency reflects the importance or representativeness of the entity in the given dataset.

[0067] The above-mentioned relationship complexity can be understood as the complexity of the relationship between entities.

[0068] The above-mentioned simple relationship type can be understood as a simple relationship type, for example, one-to-one, one-to-many relationships.

[0069] The above-mentioned complex relationship type can be understood as a complex relationship type, for example, many-to-many relationships.

[0070] The above-mentioned relation extraction process can be understood as a process of identifying and extracting the semantic relations between entities from the text.

[0071] In this embodiment, the present invention can determine the relation type of the entity pairs to be associated according to the entity occurrence frequency and the relation complexity, and select the corresponding relation extraction method according to the relation type of the entity pairs to be associated, so as to improve the accuracy and efficiency of relation extraction.

[0072] It should be noted that after the sleep knowledge database is updated, when the newly added data in the sleep knowledge database includes a preset entity pair, the preset branch in the sleep assessment knowledge graph is supplemented based on the preset entity pair.

[0073] In this embodiment, the above-mentioned preset entity pair includes a preset entity and a preset relation, and the above-mentioned preset branch is the branch where the preset entity pair is located.

[0074] The above-mentioned supplementation can be understood as a process of adding more relevant information, correcting errors, perfecting descriptions, etc., so as to make the sleep assessment knowledge graph more complete and accurate.

[0075] In a possible embodiment, it is assumed that in an update of the sleep knowledge database, a piece of data about a suggestion for children is newly added: "For children aged 3 - 6, it is recommended that the sleep time per night is not less than 10 hours." The newly added data includes the preset entity pair "children" and "specific sleep habits". The preset branch of the preset entity pair of "children" and "specific sleep habits" in the sleep knowledge database can be supplemented or perfected according to "For children aged 3 - 6, it is recommended that the sleep time per night is not less than 10 hours", and suggestions on how to improve the sleep quality of children are added.

[0076] In this embodiment, when the newly added data in the sleep knowledge database includes a preset entity pair, the preset branch in the sleep assessment knowledge graph can be supplemented according to the preset entity pair. By supplementing the preset branch in the sleep assessment knowledge graph, the sleep assessment knowledge graph database can continuously self-update and improve, providing more accurate and comprehensive information related to improving sleep quality.

[0077] Optionally, in the step of updating the sleep assessment knowledge graph based on the satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph, the target entity pairs with a satisfaction lower than the preset satisfaction can be determined in the sleep assessment knowledge graph based on the satisfaction evaluation of the target user, the weights of the target entity pairs are adjusted and audited, and after the audit is passed, a dynamic sleep knowledge graph is obtained.

[0078] In an embodiment of the present invention, the above satisfaction evaluation is an evaluation made by a user on the object contacted according to his own feelings and expectations after using a product, service or receiving a certain experience.

[0079] The above preset satisfaction is a predefined satisfaction threshold.

[0080] The above weight adjustment can be understood as a processing process of readjusting the weights of the main entity and the guest entity in the target entity pair.

[0081] The above review can be understood as a processing process of reviewing the target entity pair after weight adjustment. Through the review, errors, omissions or non-standardities can be found and corrected to ensure the authenticity and reliability of the information.

[0082] It can be reviewed by professionals. After the review by professionals is passed, the target entity pair after weight adjustment is updated to the sleep knowledge graph to obtain a dynamic sleep knowledge graph.

[0083] The above dynamic sleep knowledge graph can be optimized and improved according to the direct feedback of the user, and provide more accurate and personalized suggestions for improving sleep quality for the user.

[0084] It should be noted that, according to the satisfaction evaluation of the target user, target entity pairs with satisfaction lower than the preset satisfaction can be determined in the sleep assessment knowledge graph. And the weight of the target entity pair with satisfaction lower than the preset satisfaction is adjusted and reviewed. After the review is passed, the target entity pair after weight adjustment is updated to the sleep knowledge graph to obtain a dynamic sleep knowledge graph.

[0085] Such as Figure 2 shown, Figure 2 is a structural diagram of a sleep assistance device provided by an embodiment of the present invention. The sleep assistance device includes: An acquisition module 201, configured to acquire a dynamic sleep assessment knowledge graph of a target user, and acquire multi-modal data related to sleep of the target user; A processing module 202, configured to determine a sleep assistance plan for the target user based on the dynamic sleep assessment knowledge graph and the multi-modal data; An adjustment module 203, configured to acquire subjective sleep data and objective sleep data of the target user during the execution of the sleep assistance plan, and adjust the sleep assistance plan.

[0086] Optionally, the acquisition module includes: An acquisition sub-module, configured to acquire sleep knowledge data and construct a sleep knowledge database based on the sleep knowledge; A construction sub-module, configured to construct a sleep assessment knowledge graph based on the sleep knowledge database; An update sub-module, configured to update the sleep assessment knowledge graph based on the satisfaction evaluation of the target user after the sleep knowledge database is updated, so as to obtain a dynamic sleep knowledge graph.

[0087] Optionally, the construction sub-module includes: An extraction unit, configured to extract sleep key data from the sleep knowledge database based on prior knowledge, where the sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; A first processing unit, configured to perform text preprocessing on the sleep key data to obtain preprocessed text; A second processing unit, configured to extract sleep keywords from the preprocessed text, and perform category recognition on each sleep keyword to obtain a main entity or a guest entity corresponding to the sleep keyword; for a pair of entities to be associated, perform relation extraction processing based on rules or based on deep learning to obtain a relationship between the main entity and the guest entity, and associate the main entity and the guest entity through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity; A construction unit, configured to construct a sleep assessment knowledge graph based on the sleep entity pairs.

[0088] Optionally, the second processing unit includes: A first processing sub-unit, configured to determine whether the pair of entities to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and the relationship complexity for a pair of entities to be associated; A second processing sub-unit, configured to perform relation extraction processing based on rules if the pair of entities to be associated is a simple relationship type; A third processing sub-unit, configured to perform relation extraction processing based on deep learning if the pair of entities to be associated is a complex relationship type.

[0089] Optionally, the update sub-module is configured to determine target entity pairs with a satisfaction lower than a preset satisfaction in the sleep assessment knowledge graph based on the satisfaction evaluation of the target user, adjust the weights of the target entity pairs and perform an audit, and obtain a dynamic sleep knowledge graph after the audit passes.

[0090] The present invention also proposes a sleep assistance system. Refer to Figure 3 , Figure 3 which is a schematic structural diagram of a sleep assistance system in a hardware operating environment involved in an embodiment solution of the present invention.

[0091] The sleep assistance system according to an embodiment of the present invention may be a computing device such as a desktop computer, a notebook, a palm computer, and a server. As Figure 3 shown, the sleep assistance system may include: a processor 1001 (such as a CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection communication between these components. The user interface 1003 may include a display screen (Display) and an input unit, such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0092] Those skilled in the art can understand that Figure 3 the structure of the sleep assistance system shown in

[0093] does not constitute a limitation on the sleep assistance system, and may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. 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.

[0094] In Figure 3 the sleep assistance system shown, the network interface 1004 is mainly used to connect to a background server and communicate data with the background server; the user interface 1003 is mainly used to connect to a client (user side) and communicate data with the client; and the processor 1001 may 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 aforementioned sleep assistance method are implemented.

[0095] Based on the computer program proposed in the foregoing embodiments, the present invention also proposes a storage medium. The storage medium stores a computer program. When the computer program is executed by a controller, the sleep assistance method recorded in the foregoing embodiments is implemented.

[0096] Since the sleep assistance system and the storage medium of the present invention can both 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 elaborated herein one by one.

[0097] In several embodiments provided by the present application, it should be understood that the disclosed methods and apparatuses can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another apparatus, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the apparatus or module can be in an electrical, mechanical or other form.

[0098] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, in each embodiment of the present invention, the functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0100] If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this 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, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs that can store program codes.

[0101] The above are only partial or preferred embodiments of the present invention. Neither the text nor the drawings can limit the scope of protection of the present invention. All equivalent structural transformations made by using the content of the specification and drawings of the present invention under the overall concept of the present invention, or direct / indirect applications in other related technical fields are included in the scope of protection of the present invention.

Claims

1. A sleep assistance method, characterized in that, The method includes: Obtaining a dynamic sleep assessment knowledge graph of a target user, and obtaining multimodal data related to the 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; During the execution of the sleep assistance plan, obtaining subjective sleep data and objective sleep data of the target user, and adjusting the sleep assistance plan.

2. The sleep assistance method according to claim 1, wherein The obtaining of the dynamic sleep knowledge graph of the target user includes: Obtaining sleep knowledge data, and constructing a sleep knowledge database based on the sleep knowledge; Constructing a sleep assessment knowledge graph based on the sleep knowledge database; After the sleep knowledge database is updated, updating the sleep assessment knowledge graph based on the satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph.

3. The sleep assistance method according to claim 2, wherein, The constructing of the sleep assessment knowledge graph based on the sleep knowledge database includes: Extracting sleep key data from the sleep knowledge database based on prior knowledge, where the sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; Performing text preprocessing on the sleep key data to obtain preprocessed text; Extracting sleep keywords from the preprocessed text, and performing category recognition on each sleep keyword to obtain a main entity or an objective entity corresponding to the sleep keyword; for a pair of entities to be associated, performing relationship extraction processing based on rules or based on deep learning to obtain the relationship between the main entity and the objective entity, and associating the main entity and the objective entity through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, an objective entity, and the relationship between the main entity and the objective entity; Constructing a sleep assessment knowledge graph based on the sleep entity pairs.

4. The sleep assistance method according to claim 3, wherein The performing of relationship extraction processing on a pair of entities to be associated based on rules or based on deep learning includes: For a pair of entities to be associated, determining whether the pair of entities to be associated is a simple relationship type or a complex relationship type according to the entity appearance frequency and the relationship complexity; If the pair of entities to be associated is a simple relationship type, performing relationship extraction processing based on rules; If the pair of entities to be associated is a complex relationship type, performing relationship extraction processing based on deep learning.

5. The sleep assistance method according to any one of claims 2 to 4, characterized in that, The updating of the sleep assessment knowledge graph based on the satisfaction evaluation of the target user to obtain a dynamic sleep knowledge graph includes: Based on the satisfaction evaluation of the target user, determining target entity pairs with a satisfaction lower than a preset satisfaction in the sleep assessment knowledge graph, adjusting the weights of the target entity pairs and auditing them, and after the audit passes, obtaining a dynamic sleep knowledge graph.

6. A sleep assistance device, characterized in that, The sleep assistance device includes: An acquisition module, configured to acquire a dynamic sleep assessment knowledge graph of a target user, and acquire multimodal data related to the sleep of the target user; A processing module, configured to determine a sleep assistance plan for the target user based on the dynamic sleep assessment knowledge graph and the multimodal data; An adjustment module, configured to obtain subjective sleep data and objective sleep data of the target user during the execution of the sleep assistance scheme, and adjust the sleep assistance scheme.

7. The sleep assistance device according to claim 6, characterized in that The obtaining module includes: An obtaining sub-module, configured to obtain sleep knowledge data and construct a sleep knowledge database based on the sleep knowledge; A constructing sub-module, configured to construct a sleep assessment knowledge graph based on the sleep knowledge database; An updating sub-module, configured to update the sleep assessment knowledge graph based on the satisfaction evaluation of the target user after the sleep knowledge database is updated, so as to obtain a dynamic sleep knowledge graph.

8. The sleep assistance device according to claim 7, wherein The constructing sub-module includes: An extracting unit, configured to extract sleep key data from the sleep knowledge database based on prior knowledge, where the sleep key data includes sleep impact data, sleep performance and classification data, sleep intervention data, and sleep prognosis data; A first processing unit, configured to perform text preprocessing on the sleep key data to obtain preprocessed text; A second processing unit, configured to extract sleep keywords from the preprocessed text, identify the category of each sleep keyword, and obtain the 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 the relationship between the main entity and the guest entity, and associate the main entity and the guest entity through the relationship to obtain a sleep entity pair, where each sleep entity pair includes a main entity, a guest entity, and the relationship between the main entity and the guest entity; A constructing unit, configured to construct a sleep assessment knowledge graph based on the sleep entity pair.

9. The sleep assistance device according to claim 8, characterized in that, The second processing unit includes: A first processing sub-unit, configured to determine whether the pair of entities to be associated is a simple relationship type or a complex relationship type according to the entity occurrence frequency and relationship complexity for a pair of entities to be associated; A second processing sub-unit, configured to perform relationship extraction processing based on rules if the pair of entities to be associated is a simple relationship type; A third processing sub-unit, configured to perform relationship extraction processing based on deep learning if the pair of entities to be associated is a complex relationship type.

10. A sleep assistance system, characterized in that, The sleep assistance system includes a memory, a processor, and a computer program stored on 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 any one of claims 1 to 5 are implemented.

Images