Intelligent analysis and care system for middle-aged and elderly pain symptoms

Abstract

The application discloses an intelligent analysis and accompanying system for middle-aged and old pain symptoms, relates to the medical technical field, and has the technical scheme as follows: basic information of middle-aged and old pain symptoms is collected, including subjective pain description data, objective description data and historical diagnosis and treatment data, wherein the objective description data includes steps, heart rate, sleep, blood oxygen saturation and body position change, etc., pain data sets are obtained by extracting pain related data of the basic information; comparison results sets are obtained by comparing symptom description conditions of different pain types in the pain data sets and corresponding semantic information of voice question and answer; target pain symptom types are screened out according to corresponding comparison results in the comparison results sets, relevant data sets are screened out from the pain data sets according to the target pain symptom types, and individualized disease conditions and psychological characteristics are intelligently analyzed; and the effect is to match the accompanying conditions according to the change of pain semantic characteristics.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and more specifically, to an intelligent analysis and care system for pain symptoms in middle-aged and elderly people. Background Technology

[0002] The identification and effective care of pain symptoms in the field of health management for middle-aged and elderly people remains a critical challenge that urgently needs to be addressed. With age, the physical functions of middle-aged and elderly individuals decline, leading to frequent and complex pain problems, including various types such as joint pain and back pain. Furthermore, individual differences in description and cognitive biases often result in discrepancies between symptom descriptions and actual conditions. Traditional care models rely on manual information collection and experience-based judgment, which suffers from difficulties in data integration, shallow semantic understanding, and delayed care responses. On the one hand, medical staff often overlook crucial details when manually sorting through basic pain information, and the statistical analysis and data extraction of different pain types lack a systematic approach, making it difficult to form a comprehensive and accurate pain data set. On the other hand, insufficient semantic analysis of pain-related voice questions and answers fails to deeply connect symptom descriptions with patients' actual feelings, resulting in inaccurate selection of target pain symptom types and a lack of scientific basis for care plan development. Summary of the Invention

[0003] In view of the shortcomings of existing technologies, the purpose of this invention is to provide an intelligent analysis and care system for pain symptoms in middle-aged and elderly people.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A smart pain symptom analysis and care system for middle-aged and elderly people, including:

[0006] Data Acquisition and Extraction Module: Collects basic information on pain symptoms in middle-aged and elderly individuals, and extracts pain-related data from the basic information to obtain a pain data set;

[0007] Comparison module: Compares the symptom descriptions of different pain types within the pain dataset with the semantic information of the corresponding voice questions and answers to obtain a comparison result set;

[0008] Filtering module: Filters out target pain symptom types based on the corresponding comparison results in the comparison result set, and filters out relevant data sets from the pain data set based on the target pain symptom types;

[0009] Analysis and extraction module: Performs semantic difference analysis on the comparison results in the comparison result set to obtain associated semantic data, and extracts the first target associated data from the relevant data set based on the associated semantic data;

[0010] Analysis module: Analyzes the primary target-related data, target pain symptom types, and pain data sets within a historical time period to obtain a set of accompanying care conditions;

[0011] Acquisition module: Acquires the current semantic feature information set of all data related to the target pain symptom type in the pain data set within the current time period;

[0012] Companionship scheduling module: Based on the current set of semantic feature information, it matches and determines the companionship status from the companionship status set, and schedules companionship resources for the pain symptoms of middle-aged and elderly people in the current time period based on the determined companionship status.

[0013] Preferably, the accompanying care status set is obtained by analyzing the first target-related data, target pain symptom types, and pain data sets within a historical time period, specifically including the following steps:

[0014] The first companion status is obtained by statistically analyzing the data related to the first target and the companion status information of the target pain symptom type within a historical time period.

[0015] Second-target related data in historical time periods are filtered out from the pain dataset, and the second-target related data are processed and analyzed to obtain the second care status;

[0016] Among them, the combination of the first care condition and the second care condition constitutes the care condition set.

[0017] Preferably, the pain-related data of the basic information is extracted to obtain a pain dataset, specifically including the following steps:

[0018] The basic information was analyzed to obtain symptom statistics for various types of pain.

[0019] Pain-related data were extracted from the symptom statistics to obtain a pain data set.

[0020] Preferably, a comparison result set is obtained by comparing the symptom descriptions of different pain types within the pain dataset with the semantic information of the corresponding voice questions and answers, specifically including the following steps:

[0021] Collect historical symptom datasets for each type of pain from a historical time period;

[0022] The voice question-and-answer set is obtained by statistically analyzing the voice questions and answers for each pain type in the pain dataset.

[0023] The historical semantic information dataset is obtained by collecting actual semantic information from voice question-and-answer sets over historical time periods.

[0024] A comparison result set is obtained by performing a corresponding semantic comparison between the historical symptom dataset and the historical semantic information dataset.

[0025] Preferably, the target pain symptom type is selected based on the corresponding comparison results in the comparison result set, specifically including the following steps:

[0026] The first comparison result that shows a difference between the historical symptom dataset and the historical semantic information dataset is selected from the comparison result set;

[0027] Extract the corresponding target pain symptom type that matches the first comparison result from the pain dataset.

[0028] Preferably, the relevant dataset is selected from the pain dataset based on the target pain symptom type, specifically including the following steps:

[0029] Based on the target pain symptom type, pain data associated with the target pain symptom type are filtered from the pain dataset to obtain the associated dataset;

[0030] A second comparison result was selected from the comparison result set, in which there was no difference between the historical symptom dataset and the historical semantic information dataset.

[0031] Extract the relevant data set corresponding to the second comparison result from the associated data set.

[0032] Preferably, semantic difference analysis is performed on the comparison results in the comparison result set to obtain associated semantic data, specifically including the following steps:

[0033] The semantic differences of the first comparison results are compared to obtain the first semantic difference status.

[0034] The second semantic difference status is obtained by calculating the semantic difference of the second comparison result.

[0035] Among them, the first semantic difference situation and the second semantic difference situation are combined into a semantic difference situation set;

[0036] Select related semantic data that fall within the semantic difference correlation interval from the set of semantic difference conditions.

[0037] Preferably, the second accompanying condition is obtained by processing and analyzing the data associated with the second target, specifically including the following steps:

[0038] Semantic feature information of target pain symptom type and second target association data are collected within a historical time period to obtain a set of semantic feature information.

[0039] The second care status of pain symptoms in middle-aged and elderly people is obtained by judging the set of semantic feature information.

[0040] Preferably, the accompanying care status is determined by matching the current set of semantic feature information from the set of accompanying care statuses, specifically including the following steps:

[0041] Within the current time period, semantic feature information of the target pain symptom type and semantic feature information of all data related to the target pain symptom type in the pain data set are collected to obtain the current semantic feature information set.

[0042] Select the set of matching semantic features that best matches the current set of semantic features from the set of semantic feature reference information;

[0043] The corresponding caregiving status is determined by filtering from the caregiving status set based on the set of matching semantic feature information.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] This invention employs a data acquisition and extraction module to classify, statistically analyze, and extract basic information, ensuring a comprehensive and accurate pain dataset. A comparison module delves into the semantics of symptom descriptions and voice-based question-and-answer sessions, uncovering potential differences and correlations to accurately identify pain types. A filtering module focuses on target pain types and related data based on the comparison results, narrowing the analysis scope and improving data relevance. An analysis and extraction module extracts key related data from semantic differences, leading to an accurate understanding of pain characteristics.

[0046] The analysis module integrates historical data to generate a set of accompanying care statuses, including past accompanying care experiences corresponding to different pain characteristics. The acquisition module collects current semantic features in real time, and the accompanying care scheduling module matches current accompanying care strategies with historically effective solutions. By matching appropriate accompanying care statuses based on changes in pain semantic features, it provides scientific decision-making references for medical staff and caregivers, making accompanying care measures more aligned with the actual development and needs of pain in middle-aged and elderly patients, improving the timeliness and effectiveness of pain intervention, reducing blind trial and error, and optimizing the allocation of nursing resources. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the module of the intelligent analysis and care system for pain symptoms in middle-aged and elderly people proposed in this invention;

[0048] Figure 2 This is a schematic diagram of the comparison result set obtained in the intelligent analysis and care system for pain symptoms in middle-aged and elderly people proposed in this invention;

[0049] Figure 3 This is a schematic diagram illustrating the relevant data set obtained in the intelligent analysis and care system for pain symptoms in middle-aged and elderly people proposed in this invention.

[0050] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0054] Reference Figures 1-3 .

[0055] The embodiments further illustrate the intelligent analysis and care system for pain symptoms in middle-aged and elderly people proposed in this invention.

[0056] A smart pain symptom analysis and care system for middle-aged and elderly people, including:

[0057] Data Acquisition and Extraction Module: Collects basic information on pain symptoms in middle-aged and elderly individuals, and extracts pain-related data from the basic information to obtain a pain data set;

[0058] Comparison module: Compares the symptom descriptions of different pain types within the pain dataset with the semantic information of the corresponding voice questions and answers to obtain a comparison result set;

[0059] Filtering module: Filters out target pain symptom types based on the corresponding comparison results in the comparison result set, and filters out relevant data sets from the pain data set based on the target pain symptom types;

[0060] Analysis and extraction module: Performs semantic difference analysis on the comparison results in the comparison result set to obtain associated semantic data, and extracts the first target associated data from the relevant data set based on the associated semantic data;

[0061] Analysis module: Analyzes the primary target-related data, target pain symptom types, and pain data sets within a historical time period to obtain a set of accompanying care conditions;

[0062] Acquisition module: Acquires the current semantic feature information set of all data related to the target pain symptom type in the pain data set within the current time period;

[0063] Companionship scheduling module: Based on the current set of semantic feature information, it matches and determines the companionship status from the companionship status set, and schedules companionship resources for the pain symptoms of middle-aged and elderly people in the current time period based on the determined companionship status.

[0064] The data collection and extraction module comprehensively collects basic information on pain symptoms in middle-aged and elderly people, such as the time, location, and nature of pain onset, and extracts pain-related data to form a pain data set.

[0065] The comparison module compares the symptom descriptions of different pain types within the pain dataset with the semantic information of the corresponding voice questions and answers. For example, it matches and analyzes the textual symptom of a patient describing "stabbing pain in the knee" with the semantic information of "my knee feels like it's being pricked with needles when I walk" in the voice questions and answers, thereby generating a set of comparison results showing the differences and consistency of the records.

[0066] The filtering module identifies the comparison results where there are differences between the historical symptom dataset and the semantic information based on the comparison result set, thereby determining the target pain symptom type. Then, it filters out related data from the original pain dataset based on the target pain type, and further extracts related datasets by combining the comparison results where there are no differences.

[0067] The analysis and extraction module performs semantic analysis on the results of the comparison set, identifying discrepancies between the discrepancies and those without. For results with discrepancies, semantic differences are compared to clarify contradictions such as "description of mild pain versus record of severe symptoms." For results without discrepancies, semantic consistency is assessed. Finally, a set of semantic discrepancies is formed, from which relevant semantic data that fits a preset range is selected, and the first target relevant data is extracted.

[0068] The analysis module performs a comprehensive analysis based on historical time period data, statistically analyzes the first target-related data and the accompanying care information of the target pain type, such as past nursing plans and effects; it filters the second target-related data from the pain data set for historical time periods, and combines semantic feature analysis to obtain the second accompanying care status. The two are combined to form a complete set of accompanying care statuses.

[0069] The acquisition module collects semantic feature information of the target pain symptom type and related data in real time within the current time period, such as the frequency of keywords and tone intensity of the patient's current description of "intensified pain", forming a set of current semantic feature information that is updated in real time.

[0070] Finally, the companionship scheduling module uses a semantic feature matching mechanism to dynamically compare the current semantic feature information with historical data in the companionship status set, selects the most matching companionship status, such as "acute pain attack requiring emergency intervention", and schedules corresponding resources accordingly, such as pushing emergency plans and coordinating medical staff to follow up, so as to realize the whole process management from data collection to resource scheduling.

[0071] The accompanying care status set is obtained by analyzing the primary target-related data, target pain symptom types, and pain data sets within a historical time period. This process includes the following steps:

[0072] The first companion status is obtained by statistically analyzing the data related to the first target and the companion status information of the target pain symptom type within a historical time period.

[0073] Second-target related data in historical time periods are filtered out from the pain dataset, and the second-target related data are processed and analyzed to obtain the second care status;

[0074] Among them, the combination of the first care condition and the second care condition constitutes the care condition set.

[0075] This application targets the first target-related data and the target pain symptom type, acquiring information on the accompanying care process over a historical period to obtain historical accompanying care patterns directly related to the target pain symptoms. From the pain data set, second target-related data within the same historical period are selected. This data includes supplementary information such as the patient's basic health information and pain trigger-related data. The relationship between this data and the development of pain symptoms, the suitability of accompanying care measures, etc., is determined, thus deriving a second accompanying care status. The first and second accompanying care statuses are integrated to form a complete accompanying care status set. This provides a comprehensive historical reference for subsequent matching of accompanying care plans and resource allocation based on current pain data, allowing accompanying care decisions to be based on rich and diverse historical accompanying care experience, improving the accuracy and effectiveness of accompanying care for pain symptoms in middle-aged and elderly individuals.

[0076] The pain-related data from the basic information is extracted to obtain a pain dataset, which specifically includes the following steps:

[0077] The basic information was analyzed to obtain symptom statistics for various types of pain.

[0078] Basic information includes subjective pain description data, objective description data, and historical medical data. Objective description data includes steps, heart rate, sleep, blood oxygen saturation, and changes in body position.

[0079] Basic information includes subjective pain description data (composed of the middle-aged and elderly people's own descriptions of the pain, location, nature, etc.), objective description data (steps, heart rate, sleep, blood oxygen saturation, and changes in body position, etc.), and historical medical data.

[0080] After collecting basic information, the process moves to the extraction stage. Based on this basic information, various pain symptom statistics are conducted, such as distinguishing between different categories like joint pain, muscle pain, and neuralgia. The manifestations of each type of symptom are then analyzed, and based on this, pain-related data is accurately extracted to form a pain data set.

[0081] This study compares the symptom descriptions (detailed portrayals of subjective feelings) of different pain types based on a pain dataset and the semantic information of corresponding voice Q&A (semantic interpretations of pain expressions during communication). It also incorporates historical symptom datasets (accumulated data on similar or identical pain experiences from the past), voice Q&A sets (historical communication records), and their actual semantic information datasets (historical semantic interpretations) for corresponding semantic comparisons. This cross-time-period, multi-dimensional comparison uncovers the semantic similarities and differences between current and historical pain data, producing a comparative result set that provides a basis for selecting target pain symptom types.

[0082] The target pain symptom type is screened based on the comparison result set. First, a comparison result showing a difference between the historical symptom dataset and the historical semantic information dataset is identified. Pain types matching this difference are extracted from the pain dataset. Next, relevant datasets are screened, utilizing associated datasets related to the target pain type, combined with a second comparison result showing no difference (the semantic fit between historical and current data), to extract key data surrounding the target pain type. Simultaneously, semantic differences are assessed in the comparison results, and the semantic difference status is calculated to screen related semantic data. First target related data is extracted from the relevant dataset to further explore the intrinsic relationships between pain data.

[0083] The first care status is obtained by statistically analyzing the care information corresponding to the target pain symptom type (such as past nursing measures for this pain, effect feedback, etc.); the second care status is obtained by filtering the second target-related data (data associated with historical care) from the pain data set for a historical period. The two are combined to form a care status set, which provides historical reference schemes for matching the current care strategy.

[0084] This process acquires a set of current semantic features (the semantic and feature presentation of pain descriptions, physiological data, etc.) for the target pain symptom type and related data within the current time period. It then matches this set with a set of accompanying care conditions. First, relevant semantic features are collected. The most matching set is then selected from a semantic feature reference set (a semantic feature library built based on historical data). Based on this, the accompanying care conditions are determined from the accompanying care condition set. According to these conditions, accompanying care resources are allocated to address the current pain symptoms in middle-aged and elderly individuals, enabling targeted pain accompanying care intervention.

[0085] Intelligent analysis of individualized disease and psychological characteristics involves collecting psychological data based on basic information (subjective pain description, objective signs, and medical history). On one hand, subjective psychological feedback is obtained through intelligent questionnaires; on the other hand, behavioral data from wearable devices and smart terminals is used to mine potential psychological states (such as long-term fragmented sleep potentially associated with anxiety, and a sudden decrease in social activity reflecting depressive tendencies). This data is then integrated with basic pain-related information to construct a multidimensional dataset containing both disease symptoms (pain and related physiological indicators) and psychological characteristics.

[0086] Machine learning algorithms (such as decision trees and random forests) are used to mine potential association rules between pain data (type, intensity, attack patterns, etc.) and psychological characteristic data (emotional state, stress level, psychological resilience indicators, etc.) as input variables. For example, the correlation between anxiety index and pain threshold and attack frequency in patients with chronic joint pain can be determined. Natural language processing technology is used to deeply analyze the psychological needs implied in subjective pain descriptions, enabling intelligent association judgment between individualized symptoms (pain dimension) and psychological characteristics, and outputting analysis results that include the trend of disease development and the influence weight of psychological state.

[0087] Based on the above analysis, a psychological characteristic matching dimension was added to the matching process for accompanying care situations. The psychological assessment results of individualized illnesses were compared with labeled data of "illness + psychological characteristics" in the historical accompanying care case database to select accompanying care situations that matched both the pain condition (e.g., a step-by-step analgesia plan for joint pain) and the psychological state (e.g., psychological reassurance and cognitive intervention strategies for anxious patients). For example, for patients with depressive tendencies due to long-term pain, in addition to routine pain care (physical therapy, medication reminders), psychological support resources (regular online communication with psychological counselors, recommendations for patient support groups) were matched. Personalized accompanying care resources covering physiological care and psychological support were allocated through multi-dimensional characteristic matching.

[0088] Pain-related data were extracted from the symptom statistics to obtain a pain data set.

[0089] This application first processes the basic information on pain symptoms collected from middle-aged and elderly patients. This basic information covers various aspects related to the patient's pain, such as the location, frequency, and description of the pain. The system then statistically analyzes these symptoms based on different pain types, such as joint pain, back pain, and muscle pain. For example, it statistically analyzes the frequency and specific characteristics of joint pain symptoms in a certain number of middle-aged and elderly patients; and the duration and triggering factors of back pain symptoms. Through this categorized statistical analysis, symptom statistics are obtained, clearly showing the distribution and characteristics of different pain types. Next, based on these symptom statistics, data closely related to pain are further extracted, including pain intensity levels, duration, and correlation with daily activities. This filtered and refined data is then integrated to construct a pain dataset.

[0090] The comparison result set is obtained by comparing the symptom descriptions of different pain types and the semantic information of corresponding voice questions and answers within the pain dataset. This process includes the following steps:

[0091] Collect historical symptom datasets for each type of pain from a historical time period;

[0092] The voice question-and-answer set is obtained by statistically analyzing the voice questions and answers for each pain type in the pain dataset.

[0093] The historical semantic information dataset is obtained by collecting actual semantic information from voice question-and-answer sets over historical time periods.

[0094] A comparison result set is obtained by performing a corresponding semantic comparison between the historical symptom dataset and the historical semantic information dataset.

[0095] This application extracts historical symptom datasets corresponding to various pain types from a pain dataset within a set historical time period. These datasets cover symptom records of different types of pain in the past (such as joint pain, back pain, etc.), including the frequency of pain attacks, duration, and specific descriptions of the sensations.

[0096] We statistically analyzed the voice Q&A associated with each pain type in the pain dataset and compiled them into a voice Q&A set. This set includes the voice content of patients describing their pain, as well as the Q&A information exchanged between them and healthcare professionals, comprehensively covering all pain-related communication content.

[0097] The semantic information actually conveyed by these voice Q&As is collected to construct a historical semantic information dataset. This step will use semantic analysis technology to extract key semantics from the natural language content of the voice Q&As, such as the patient's expressed pain level and the impact on their life.

[0098] The system performs a semantic comparison between historical symptom datasets and historical semantic information datasets. This involves matching and analyzing the objective descriptions in symptom records and the subjective expressions of patients in voice-based question-and-answer sessions for the same type of pain. The comparison identifies points of convergence and divergence at the semantic level. Based on these comparisons, a set of comparison results is generated, providing a basis for subsequent operations such as selecting target pain symptom types and helping the system more accurately identify pain-related features and problems.

[0099] The target pain symptom type is selected based on the corresponding comparison results in the comparison result set, specifically including the following steps:

[0100] The first comparison result that shows a difference between the historical symptom dataset and the historical semantic information dataset is selected from the comparison result set;

[0101] Extract the corresponding target pain symptom type that matches the first comparison result from the pain dataset.

[0102] This application filters out the content where there are differences between the historical symptom dataset and the historical semantic information dataset, and marks these parts that show differences as the first comparison result. The difference here may be that the pain characteristics objectively presented in the symptom records are inconsistent with the patient's subjective pain description obtained from the voice question-and-answer semantic analysis. For example, the symptom dataset shows that the pain is "persistent and severe", but the semantic information describes it as "occasional mild pain".

[0103] Pain-related data matching the initial comparison results are extracted from the pain dataset, and the corresponding target pain symptom types are identified based on this data. By tracing the source of the discrepancies, specific pain categories that match the differences in data and semantic features are found. These may be pain types highlighted by discrepancies between the patient's subjective experience and the objective symptom records. This allows for the identification of specific focus areas for further analysis of the care needs associated with this type of pain.

[0104] The process of filtering relevant datasets from a pain dataset based on the target pain symptom type includes the following steps:

[0105] Based on the target pain symptom type, pain data associated with the target pain symptom type are filtered from the pain dataset to obtain the associated dataset;

[0106] A second comparison result was selected from the comparison result set, in which there was no difference between the historical symptom dataset and the historical semantic information dataset.

[0107] Extract the relevant data set corresponding to the second comparison result from the associated data set.

[0108] Based on the target pain symptom type, this application selects pain data that are related to it from the overall pain data set. These data cover various aspects such as the symptoms, triggering factors, and historical development of the pain type.

[0109] The second comparison result is the portion of the historical symptom dataset and the historical semantic information dataset where no differences exist. This portion of the result demonstrates the consistency between symptom records and semantic expressions at the data level.

[0110] Using the second comparison result as a screening criterion, relevant data is extracted from the associated dataset to form a related dataset. This layered screening and progressively focusing approach extracts data that is correlated with the target pain symptom type and shares consistent data characteristics. This provides high-quality, highly relevant data support for subsequent in-depth analysis of the pain symptom and the development of companion care plans. It ensures that subsequent analyses and decisions based on this data are more aligned with the actual situation of the target pain symptom, improving the accuracy and effectiveness of the companion care system in managing pain symptoms in middle-aged and elderly individuals.

[0111] Semantic difference analysis is performed on the comparison results in the comparison result set to obtain associated semantic data, specifically including the following steps:

[0112] The semantic differences of the first comparison results are compared to obtain the first semantic difference status.

[0113] The second semantic difference status is obtained by calculating the semantic difference of the second comparison result.

[0114] Among them, the first semantic difference situation and the second semantic difference situation are combined into a semantic difference situation set;

[0115] Select related semantic data that fall within the semantic difference correlation interval from the set of semantic difference conditions.

[0116] This application compares the semantic differences of the first comparison results, sorting out differences such as the symptom description "joint stinging" and the semantic expression "joint dull pain", to form the first semantic difference status; and conducts semantic difference analysis on the second comparison results (historical symptoms and semantics without difference), such as quantifying the subtle differences in the semantics of the text record of "lower back pain lasting 2 hours" and the voice question and answer to obtain the second semantic difference status.

[0117] These two semantic difference scenarios are integrated to construct a semantic difference set, encompassing various semantic differences in different pain data. Finally, based on preset semantic difference correlation intervals, relevant semantic data that meet the criteria are selected from the set. These data, falling within reasonable semantic correlation intervals, reflect the semantic connections between pain symptom data, providing crucial semantic evidence for subsequent extraction of target relevant data from related datasets and analysis of accompanying care conditions.

[0118] The second target-related data is processed and analyzed to determine the second accompanying condition, specifically including the following steps:

[0119] Semantic feature information of target pain symptom type and second target association data are collected within a historical time period to obtain a set of semantic feature information.

[0120] The second care status of pain symptoms in middle-aged and elderly people is obtained by judging the set of semantic feature information.

[0121] This application collects semantic feature information from the target pain symptom type and the second target related data within a set historical time period. This semantic feature information includes the semantic tendency of the descriptions related to pain symptoms (such as the degree of pain reflected in the expression and the semantic connotation of its impact on life), and the semantic logic related to pain in the associated data (such as semantic association points like pain triggers and development trends). These collected semantic feature information are integrated to form a semantic feature information set, comprehensively presenting the semantic characteristics of the target pain symptom type and its corresponding associated data.

[0122] By analyzing the correlation and fit between semantic features and the essential characteristics of pain they reflect, and combining professional knowledge and experience in pain care for middle-aged and elderly people, we can determine the care needs, potential problems, and appropriate care directions corresponding to these semantic features, and finally determine the second care status of pain symptoms in middle-aged and elderly people.

[0123] The determination of companionship status is based on matching the current set of semantic feature information from the set of companionship statuses. The specific steps include:

[0124] Within the current time period, semantic feature information of the target pain symptom type and semantic feature information of all data related to the target pain symptom type in the pain data set are collected to obtain the current semantic feature information set.

[0125] Select the set of matching semantic features that best matches the current set of semantic features from the set of semantic feature reference information;

[0126] The corresponding caregiving status is determined by filtering from the caregiving status set based on the set of matching semantic feature information.

[0127] This application collects two parts of semantic feature information: first, the semantic features of the target pain symptom type itself, such as the description of pain as "stabbing pain" or "dull pain", and related descriptions of the frequency of attacks; second, the semantic features of all data in the pain dataset that are associated with the target pain symptom type, such as the semantic content of pain triggers (e.g., "onset after prolonged sitting") and descriptions of the development of similar symptoms in the past. By integrating this collected information, a current semantic feature information set is constructed to comprehensively present the semantic features of the current target pain symptom and related data.

[0128] Based on a semantic feature reference information set (which stores various historical or standard pain semantic feature patterns), the set of matching semantic feature information that best fits the current semantic feature information set is selected. This process involves comparing the similarity of semantic features, such as the consistency of pain intensity descriptions and the fit of trigger-related semantics, to find the reference content that is closest to the current situation in terms of semantic patterns.

[0129] Based on the selected set of matching semantic features, the corresponding care status is identified in the set of care conditions. This clarifies the appropriate care strategy and resource requirements for the current target pain symptoms, allowing care work to be carried out in an orderly manner based on the accurate matching results, thereby improving the targeting and effectiveness of care for pain symptoms in middle-aged and elderly people.

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent analysis and care system for pain symptoms in middle-aged and elderly people, characterized in that: include: Data Acquisition and Extraction Module: Collects basic information on pain symptoms in middle-aged and elderly individuals, and extracts pain-related data from the basic information to obtain a pain data set; Comparison module: Compares the symptom descriptions of different pain types within the pain dataset with the semantic information of the corresponding voice questions and answers to obtain a comparison result set; Filtering module: Based on the corresponding comparison results in the comparison result set, the target pain symptom type is filtered out. This includes the following steps: The first comparison result that shows a difference between the historical symptom dataset and the historical semantic information dataset is selected from the comparison result set; Extract the corresponding target pain symptom types that match the first comparison result from the pain dataset; The process of filtering relevant datasets from a pain dataset based on the target pain symptom type includes the following steps: Based on the target pain symptom type, pain data associated with the target pain symptom type are filtered from the pain dataset to obtain the associated dataset; A second comparison result was selected from the comparison result set, in which there was no difference between the historical symptom dataset and the historical semantic information dataset. Extract the relevant data set corresponding to the second comparison result from the associated data set; Analysis and Extraction Module: Performs semantic difference analysis on the comparison results in the comparison result set to obtain associated semantic data, specifically including the following steps: The first semantic difference status is obtained by comparing the historical symptom dataset and the historical semantic information dataset included in the first comparison result; The second semantic difference status is obtained by calculating the semantic difference between the historical symptom dataset and the historical semantic information dataset included in the second comparison result. Among them, the first semantic difference situation and the second semantic difference situation are combined into a semantic difference situation set; Filter out associated semantic data that falls within the semantic difference correlation interval from the set of semantic difference conditions; Extract the first target related data from the relevant dataset based on the related semantic data; Analysis module: Analyzes the primary target-related data, target pain symptom types, and pain data sets within a historical time period to obtain a set of accompanying care conditions; Acquisition module: Acquires the current semantic feature information set of all data related to the target pain symptom type in the pain data set within the current time period; Companionship scheduling module: Based on the current set of semantic feature information, it matches and determines the companionship status from the companionship status set, and schedules companionship resources for the pain symptoms of middle-aged and elderly people in the current time period based on the determined companionship status.

2. The intelligent analysis and care system for pain symptoms in middle-aged and elderly people according to claim 1, characterized in that, The accompanying care status set is obtained by analyzing the primary target-related data, target pain symptom types, and pain data sets within a historical time period. This process includes the following steps: The first companion status is obtained by statistically analyzing the data related to the first target and the companion status information of the target pain symptom type within a historical time period. Second-target correlation data were selected from the pain dataset within a historical time period. The second-target correlation data was then processed and analyzed to determine the second care status. The second-target correlation data included the patient's basic health information and data related to pain triggers. Among them, the combination of the first care condition and the second care condition constitutes the care condition set.

3. The intelligent analysis and care system for pain symptoms in middle-aged and elderly people according to claim 2, characterized in that, The pain-related data from the basic information is extracted to obtain a pain dataset, which specifically includes the following steps: The basic information was analyzed to obtain symptom statistics for various types of pain. Pain-related data were extracted from the symptom statistics to obtain a pain data set.

4. The intelligent analysis and care system for pain symptoms in middle-aged and elderly people according to claim 3, characterized in that, The comparison result set is obtained by comparing the symptom descriptions of different pain types and the semantic information of corresponding voice questions and answers within the pain dataset. This process includes the following steps: Collect historical symptom datasets for each type of pain from a historical time period; The voice question-and-answer set is obtained by statistically analyzing the voice questions and answers for each pain type in the pain dataset. The historical semantic information dataset is obtained by collecting actual semantic information from voice question-and-answer sets over historical time periods. A comparison result set is obtained by performing a corresponding semantic comparison between the historical symptom dataset and the historical semantic information dataset.

5. The intelligent analysis and care system for pain symptoms in middle-aged and elderly people according to claim 4, characterized in that, The second target-related data is processed and analyzed to determine the second accompanying condition, specifically including the following steps: Semantic feature information of target pain symptom type and second target association data are collected within a historical time period to obtain a set of semantic feature information. The second care status of pain symptoms in middle-aged and elderly people is obtained by judging the set of semantic feature information.

6. The intelligent analysis and care system for pain symptoms in middle-aged and elderly people according to claim 5, characterized in that, The determination of companionship status is based on matching the current set of semantic feature information from the set of companionship statuses. The specific steps include: Within the current time period, semantic feature information of the target pain symptom type and semantic feature information of all data related to the target pain symptom type in the pain data set are collected to obtain the current semantic feature information set. Select the set of matching semantic features that best matches the current set of semantic features from the set of semantic feature reference information; The corresponding caregiving status is determined by filtering from the caregiving status set based on the set of matching semantic feature information.

Images