Multidisciplinary knowledge fusion postpartum rehabilitation path generation method, system and product

Abstract

The invention provides a multidisciplinary knowledge fusion postpartum rehabilitation path generation method, system and product, and relates to the technical field of wisdom medical treatment.The method comprises the steps that the delivery mode, the number of postpartum days, the pelvic floor muscle strength rating, the rectus abdominis separation index, the pain score, the GLAZER score and the pelvic floor color ultrasound examination result of a postpartum patient are obtained; the information is matched with structured rules in a pre-constructed multidisciplinary decision rule base, so that a rehabilitation task set suitable for the current patient is accurately recognized, and a postpartum rehabilitation path diagram containing a time axis and rehabilitation tasks is generated based on a postpartum rehabilitation stage division standard; wherein the task sequence, the task intensity parameter, the stage switching condition and the rehabilitation target of each stage are determined by the structured rule, so that the precision, the structuring and the stage of the rehabilitation scheme are realized, and the individual suitability and the clinical performability of the postpartum rehabilitation path are improved.

Description

Technical Field

[0001] This invention relates to the field of smart healthcare technology, and in particular to a method, system, and product for generating postpartum rehabilitation pathways that integrates multidisciplinary knowledge. Background Technology

[0002] In the field of postpartum rehabilitation, traditional rehabilitation programs often rely on clinical experience from a single discipline, lacking a systematic integration of knowledge from multiple disciplines such as obstetrics, rehabilitation, and nutritional science. This leads to disciplinary barriers in the diagnosis and treatment process, making it difficult to achieve a balance between standardization and personalization. Existing technologies typically use fixed rehabilitation templates or guidelines based on simple rules, failing to dynamically generate personalized rehabilitation pathways based on the patient's specific circumstances, such as delivery method, postpartum days, pelvic floor muscle strength rating, degree of diastasis recti, and pain score. Furthermore, they lack mechanisms for continuous tracking of rehabilitation progress and pathway adjustment. In addition, current programs often neglect the synergistic relationships and priority conflict resolution among multidisciplinary interventions, easily resulting in unreasonable allocation of rehabilitation tasks. Summary of the Invention

[0003] This invention aims to solve the technical problems existing in the above-mentioned related technologies, and proposes a method, system and product for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge. It can automatically generate personalized postpartum rehabilitation pathways based on individualized clinical data of patients and through a decision rule base that integrates multidisciplinary expert consensus, so as to achieve standardization, intelligence and precision of rehabilitation programs.

[0004] The solution to the technical problem of this invention is as follows: This application provides a method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge, comprising the following steps: Obtain patient information for postpartum patients, including delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results; The patient information is matched with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient. Based on the rehabilitation task set, a postpartum rehabilitation path map containing a timeline and rehabilitation tasks is generated. The timeline is divided according to the postpartum recovery stage division criteria, and the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals of each stage are determined by the structured rules.

[0005] Furthermore, the construction process of the multidisciplinary decision rule base includes the following steps: Based on clinical guidelines, expert consensus, and evidence-based medicine literature from obstetrics, rehabilitation, nutrition, and radiology, a multidisciplinary joint knowledge graph including assessment indicators, intervention measures, indications, and contraindications is constructed. The medical logical relationships in the knowledge graph are converted into structured rules. Each structured rule includes a condition part, an action part, and a constraint part. The structured rules are assigned priorities based on evidence-based levels, which are determined by randomized controlled trials, expert consensus, and clinical experience. To address the conflicts between structured rules across different disciplines, a tiered conflict resolution mechanism is established. Conflicting rules are screened or replaced in the order of clinical safety, functional requirements, and optimization goals, and the basis for conflict resolution is recorded. The structured rules after conflict resolution are stored in a callable data format to form a multidisciplinary decision rule library that supports matching execution and automatic exclusion of taboo interventions.

[0006] Furthermore, the multidisciplinary decision rule base supports an evidence-based incremental update mechanism, which includes: Regularly obtain the latest clinical guidelines, expert consensus, or research literature published in the medical field, and extract newly added or revised rehabilitation-related rules from them; The extracted rules are evaluated for evidence-based status and updated incrementally to the multidisciplinary decision rule base after clinical validation, while the rules that are replaced are marked as invalid. The system provides change notifications for generated rehabilitation pathway association rules and retains historical versions of the rule base to support pathway tracing and effect verification.

[0007] Furthermore, the step of matching the patient information with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient includes the following steps: The patient information is subjected to standardized preprocessing to obtain a standardized patient dataset; The standardized patient dataset is input into the multidisciplinary decision rule base, and safety contraindication matching, functional assessment matching, and nutritional adaptation matching are performed sequentially to obtain a preliminary rehabilitation task set. Among them, the safety contraindication matching excludes intervention measures with contraindications based on obstetric and imaging safety rules; the functional assessment matching screens rehabilitation tasks that are suitable for the patient's current state based on rehabilitation department functional assessment indicators; and the nutritional adaptation matching generates a dietary coordination plan based on nutrition department rules and the patient's health needs. Interdisciplinary conflict detection and resolution were performed on the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set; The conflict-free rehabilitation task set is prioritized based on evidence level, clinical urgency, and core patient needs to obtain a priority-ordered rehabilitation task sequence, which is used to generate the timeline task arrangement in the postpartum rehabilitation pathway diagram.

[0008] Furthermore, the step of performing interdisciplinary conflict detection and resolution on the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set specifically includes: Detect security conflicts and perform task disabling and alternative handling; Detect functional conflicts and adjust task execution parameters based on patient physiological indicators; Detect optimization-related conflicts and resolve them through task scheduling or priority reordering; Among them, the safety-related conflict refers to a conflict between the rehabilitation task and the patient's safety contraindications; the functional conflict refers to a conflict between the rehabilitation task and the patient's functional needs or nutritional management rules; and the optimization-related conflict refers to an overlap in the execution time or resource allocation of multiple rehabilitation tasks.

[0009] Further, the step of generating a postpartum rehabilitation path map containing a timeline and rehabilitation tasks based on the rehabilitation task set includes: A timeline is constructed based on the postpartum recovery stage division criteria. The initiation condition for the first stage is that the patient's initial state meets the safety admission criteria for rehabilitation training. The stage switching conditions for subsequent stages include completing the preset rehabilitation goals of the previous stage and meeting the admission conditions of the next stage.

[0010] Furthermore, the method also includes: Receive patient feedback on their recovery progress; Based on the feedback information and patient information, the structured rules in the multidisciplinary decision rule base are re-matched; Based on the newly matched structured rules, adjust the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage of the postpartum rehabilitation pathway diagram.

[0011] On the other hand, this application provides a postpartum rehabilitation pathway generation system that integrates multidisciplinary knowledge, including an information acquisition module, a decision rule base module, a rule matching module, a pathway generation module, and a feedback receiving module; The information acquisition module is configured to acquire patient information of postpartum patients, including delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results. The decision rule base module is configured to build and store a multidisciplinary decision rule base; The rule matching module is configured to match the patient information with the structured rules in the multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient. The path generation module is configured to generate a postpartum rehabilitation path diagram containing a timeline and rehabilitation tasks based on the rehabilitation task set. The timeline is divided according to the postpartum recovery stage division criteria, and the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage are determined by the structured rules. The feedback receiving module is configured to receive patient rehabilitation progress feedback information, rematch the structured rules in the multidisciplinary decision rule base based on the feedback information and patient information, and adjust the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage in the postpartum rehabilitation path diagram according to the newly matched structured rules.

[0012] Furthermore, the system provides a graphical user interface, which includes a patient information collection unit, a path generation preview unit, a rule matching visualization unit, and a rehabilitation progress feedback unit. The patient information collection unit is used to receive delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score and imaging examination results. It supports structured input and attachment upload, and automatically verifies data integrity. The path generation preview unit is used to display personalized rehabilitation paths in the form of a phased timeline, divide task intervals according to the postpartum recovery stage, identify task types with different colors, and support clicking on task nodes to view execution parameters, contraindications and related evaluation indicators. The rule matching visualization unit is used to present the matching process between patient information and the multidisciplinary decision rule base in the form of an interactive flowchart, highlight the triggered rules and their evidence sources, and mark the rule priorities. The rehabilitation progress feedback unit is used to receive task completion status, re-examination data and patient subjective feedback, automatically generate rehabilitation progress charts, and trigger path adjustment suggestions based on feedback data, supporting the synchronous update of task parameter modification and path chart.

[0013] On the other hand, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge.

[0014] The beneficial effects of this invention are as follows: This application provides a method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge. By acquiring information such as the postpartum patient's delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results, this information is matched with structured rules in a pre-constructed multidisciplinary decision rule base. This accurately identifies the rehabilitation task set applicable to the current patient and generates a postpartum rehabilitation pathway diagram containing a timeline and rehabilitation tasks based on postpartum recovery stage division standards. The task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage are all determined by structured rules, achieving precision, structure, and staged implementation of the rehabilitation plan, thus improving the individual adaptability and clinical feasibility of the postpartum rehabilitation pathway. This application also provides corresponding systems and products, the beneficial effects of which are the same as those of the above method, and will not be elaborated upon here.

[0015] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0016] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0017] Figure 1 This is a flowchart of the postpartum rehabilitation pathway generation method that integrates multidisciplinary knowledge provided in this application; Figure 2 This is a structural diagram of the postpartum rehabilitation pathway generation system that integrates multidisciplinary knowledge, as provided in this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0020] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Postpartum rehabilitation refers to the process by which a woman's body returns to its pre-pregnancy state after childbirth, following a series of physiological changes. This includes, but is not limited to, comprehensive treatment encompassing pelvic floor muscle strength recovery, diastasis recti repair, pain management, and nutritional adjustments. Postpartum rehabilitation is crucial for improving women's quality of life and preventing long-term health problems.

[0023] Currently, postpartum rehabilitation primarily relies on the clinical practice of single disciplines such as obstetrics, rehabilitation, or nutrition, with rehabilitation plans typically developed by specialists based on their area of ​​expertise. These plans are largely based on the doctor's personal experience or general clinical guidelines, providing standardized or semi-standardized intervention recommendations for common postpartum issues such as pelvic floor dysfunction, diastasis recti, pain management, and nutritional adjustments. While some institutions have begun using electronic health management tools to record patient information and combine them with simple rule prompts for rehabilitation guidance, overall decision-making remains largely manual, lacking systematic integration.

[0024] Existing technologies suffer from significant disciplinary barriers, lacking deep integration of knowledge from multiple disciplines such as obstetrics, rehabilitation, and nutritional science. This results in fragmented and incomplete rehabilitation programs, hindering comprehensive and coordinated interventions. Rehabilitation pathways are often fixed templates with low personalization, failing to dynamically generate targeted plans based on individual patient characteristics (such as delivery method, postpartum stage, pelvic floor muscle strength, and pain level). The treatment process heavily relies on doctors' subjective experience, lacking standardized and replicable decision-making logic, leading to significant differences in treatment recommendations among different doctors and inconsistent quality. Furthermore, existing methods generally lack mechanisms for continuous tracking of rehabilitation progress and dynamic adjustment of pathways, making it impossible to optimize rehabilitation plans promptly based on follow-up feedback, hindering closed-loop management, and impacting rehabilitation outcomes and patient compliance.

[0025] To address the problems existing in postpartum rehabilitation technologies, such as disciplinary fragmentation, difficulty in balancing standardization and personalization, reliance on subjective experience, and lack of dynamic adjustment mechanisms, this application proposes a postpartum rehabilitation pathway generation method, system, and product based on multidisciplinary knowledge integration. By integrating multi-source clinical knowledge from obstetrics, rehabilitation, nutrition, and radiology departments to construct a structured decision rule base, and using objective indicators such as delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound results as inputs, it achieves accurate identification of individual patient rehabilitation task sets and automatically generates personalized pathway maps containing timelines, task sequences, intensity parameters, stage switching conditions, and rehabilitation goals based on postpartum recovery stage division standards. Simultaneously, it supports dynamic adjustment of the pathway based on patient rehabilitation feedback, thereby effectively breaking down disciplinary barriers, balancing standardization and personalization, reducing reliance on subjective experience, and establishing a closed-loop, iterative intelligent rehabilitation management mechanism.

[0026] First, the method for generating postpartum rehabilitation pathways that integrates multidisciplinary knowledge, as provided in the embodiments of this application, will be described in detail below with reference to the accompanying drawings.

[0027] Reference Figure 1 The implementation process of the postpartum rehabilitation pathway generation method integrating multidisciplinary knowledge provided in this application embodiment includes, but is not limited to, the following steps.

[0028] Step S110: Obtain patient information for postpartum patients.

[0029] The patient information includes delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound results.

[0030] In step S110, key clinical data of postpartum patients are collected to provide objective and comprehensive basic input for the generation of subsequent personalized rehabilitation pathways. The patient information acquired by the system includes delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results. These indicators reflect the patient's current status from multiple dimensions, including obstetric background, time process, muscle function, anatomical structure, subjective symptoms, and electrophysiology and imaging, forming a multidimensional and structured assessment starting point. This ensures that subsequent decisions are based on real, quantifiable, and clinically relevant data, avoiding reliance on vague descriptions or empirical speculation.

[0031] Step S120: Match patient information with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient.

[0032] In step S120, by matching the acquired patient information with structured rules in a pre-built multidisciplinary decision rule base, the system can automatically identify all rehabilitation tasks applicable to the current patient's specific conditions, forming a targeted and comprehensive set of rehabilitation tasks. This matching process essentially transforms fragmented clinical guidelines, expert consensus, and evidence-based knowledge into actionable logical judgments, enabling the selection of rehabilitation interventions to move beyond a single-disciplinary perspective and instead rely on comprehensive reasoning based on interdisciplinary rules, thereby improving the scientific rigor, safety, and suitability of task selection.

[0033] Step S130: Generate a postpartum rehabilitation path map containing a timeline and rehabilitation tasks based on the rehabilitation task set. The timeline is divided according to the postpartum recovery stage classification standard, and the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage are determined by structured rules.

[0034] In step S130, the abstract set of rehabilitation tasks is transformed into an intuitive, executable, and time-sequential rehabilitation plan. The system constructs a timeline based on clinically recognized postpartum recovery stage division standards and arranges specific rehabilitation tasks within each stage. Simultaneously, structured rules determine the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage. The resulting postpartum rehabilitation pathway map enables dynamic planning of the rehabilitation program, providing a clear, structured, and traceable postpartum rehabilitation pathway for clinical implementation and patients.

[0035] In some embodiments of this application, the postpartum days are typically used as the starting assessment point for generating the rehabilitation pathway in actual clinical applications, usually 42 days (6 weeks) postpartum. This time point is the postpartum follow-up time recommended by the National Basic Public Health Service Guidelines, and the patient has completed the physiological recovery of the puerperium and can safely undergo pelvic floor muscle strength assessment, GLAZER electromyography, and pelvic floor ultrasound examination.

[0036] In some embodiments of this application, the system first acquires patient information of a patient who delivered vaginally on the 42nd postpartum day, including the mode of delivery being vaginal delivery, postpartum days being 42 days, pelvic floor muscle strength rating of grade 2 (assessed using standardized manual methods), diastasis recti index of 3 fingers (confirmed by ultrasound or digital measurement), pain score of 1 point (VAS score), GLAZER pelvic floor electromyography showing a "fatigue-type" electromyographic pattern, and pelvic floor ultrasound showing increased bladder neck mobility (55 mm), but no significant pelvic organ prolapse (POP-Q stage ≤ stage I). The above data conforms to the routine data collection for clinical postpartum follow-up, indicating that the patient has passed the acute puerperium and meets the safe access conditions for conducting structured rehabilitation assessment and intervention.

[0037] Subsequently, the system inputs the standardized patient information into a pre-built multidisciplinary decision rule base. This rule base integrates obstetric safety rules (such as excluding active bleeding and infection), rehabilitation functional intervention rules (based on muscle strength and separation severity grading), nutritional support recommendations, and radiological contraindication judgment logic. After triple matching (safety contraindications → functional assessment → nutritional adaptation), a set of rehabilitation tasks suitable for the patient is identified, including: low-intensity pelvic floor electromyographic biofeedback combined training (frequency 30Hz, pulse width 200μs); transverse abdominis muscle activation exercises (supine isometric contraction, 2 sets × 10 repetitions daily); a high-protein balanced diet plan (protein intake 1.2g / kg / day); and activity guidance: avoid lifting heavy objects (>5kg) and prolonged standing.

[0038] Finally, based on the clinically recognized postpartum recovery stage division criteria (Stage 1: 6–12 weeks postpartum), the system generates a personalized rehabilitation pathway map with a timeline. The task sequence for this stage is: 15 minutes of pelvic floor muscle training daily, core stability exercises 3 times a week, and nutritional follow-up; task intensity parameters are automatically set by rules; the stage switching condition is "pelvic floor muscle strength improves to ≥3 and rectus abdominis diastasis ≤2 fingers"; the rehabilitation goals are "improving muscle endurance, reducing stress urinary incontinence symptoms, and enhancing core control ability".

[0039] In some embodiments of this application, the process of constructing a multidisciplinary decision rule base includes the following steps.

[0040] Step S210: Based on clinical guidelines, expert consensus and evidence-based medicine literature from obstetrics, rehabilitation, nutrition and radiology, construct a multidisciplinary joint knowledge graph that includes assessment indicators, intervention measures, indications and contraindications.

[0041] In step S210, authoritative medical knowledge from multiple disciplines is integrated to form a unified and systematic knowledge base. Specifically, key elements related to postpartum rehabilitation are extracted from clinical guidelines, expert consensus, and evidence-based medicine literature in obstetrics, rehabilitation, nutrition, and radiology. These elements include assessment indicators, intervention measures, indications, and contraindications. These elements are then organized into a comprehensive and clearly defined multidisciplinary joint knowledge graph. This knowledge graph not only preserves the professional logic of each discipline but also establishes semantic connections between disciplines, providing a clear, complete, and clinically reliable knowledge base for subsequent rule transformation.

[0042] Step S220: Convert the medical logical relationships in the knowledge graph into structured rules. Each structured rule includes a condition part, an action part, and a constraint part. The structured rules are assigned priority according to the evidence level, which is determined by randomized controlled trials, expert consensus, and clinical experience.

[0043] In step S220, the medical logic contained in the knowledge graph is transformed into a structured rule form that can be processed and executed by a computer. This step formalizes the medical relationships in the knowledge graph, ensuring that each rule explicitly includes a condition part, an action part, and a constraint part, thereby supporting automated reasoning and decision-making based on patient status. Simultaneously, based on different sources of evidence, such as randomized controlled trials, expert consensus, or clinical experience, each rule is assigned a corresponding level of evidence-based validity and prioritized accordingly. This ensures that suggestions with high evidence strength are given priority in rule application, improving the scientific rigor and reliability of the decision-making results.

[0044] Step S230: To address the conflicts between structured rules in different disciplines, a hierarchical conflict resolution mechanism is established. Conflicting rules are screened or replaced in the order of clinical safety, functional requirements, and optimization goals, and the basis for conflict resolution is recorded.

[0045] In step S230, the safety and rationality of the rehabilitation plan are ensured by resolving potential logical conflicts that may arise in the practical application of multidisciplinary rules. Because intervention goals and judgment criteria may differ across disciplines, their corresponding structured rules may contradict each other under specific patient conditions. This step establishes a hierarchical conflict resolution mechanism, prioritizing clinical safety, followed by functional needs, and then optimization goals. Conflicting rules are screened, replaced, or coordinated, with the conflict type and resolution basis recorded simultaneously. This mechanism ensures that the final rule combination is logically consistent, clinically feasible, and traceable.

[0046] Step S240: The structured rules after conflict resolution are stored in a callable data format to form a multidisciplinary decision rule library that supports matching execution and automatic exclusion of taboo interventions.

[0047] In step S240, the structured rules, after conflict resolution and priority labeling, are stored as decision resources that can be efficiently invoked by the system. This step stores the processed rules in a standardized, machine-readable data format, constructing a fully functional multidisciplinary decision rule base. This rule base not only supports rapid matching of applicable tasks during path generation but also automatically identifies and excludes interventions that conflict with patient contraindications during matching, thereby achieving safe, accurate, and efficient intelligent decision-making.

[0048] In some embodiments of this application, the construction of the multidisciplinary decision rule base is first based on expert consensus in the field of postpartum rehabilitation, postpartum rehabilitation guidelines, and high-quality randomized controlled trials and systematic reviews published in the past five years. It extracts assessment indicators for postpartum hemorrhage and wound healing from obstetrics, intervention measures for pelvic floor muscle training and core stability from rehabilitation, recommendations from nutritionists on protein intake and breast milk quality, and interpretation criteria for abnormal pelvic floor ultrasound structures from radiology, and constructs a multidisciplinary joint knowledge graph covering assessment indicators, intervention measures, indications and contraindications.

[0049] Subsequently, the system transforms the medical logical relationships extracted from the knowledge graph into structured decision rules. Each rule consists of three parts: Condition, Action, and Constraint, and is labeled with its evidence-based level and priority. For example, a typical rule might have the following conditions: "Diastasis recti index ≥ 2 fingers and postpartum days ≥ 42 days with no active bleeding or infection," Action: "Recommended low-intensity transverse abdominis activation training (such as supine isometric contraction)," and Constraint: "Sit-ups, crunches, high-impact jumps, and other actions that increase intra-abdominal pressure are prohibited."

[0050] During the rule integration process, the system detected a potential conflict between a nutrition rule ("Recommended daily intake of an additional 1500 kcal to support breastfeeding") and a rehabilitation rule ("Rapid weight gain should be avoided to prevent increased pelvic floor load"). Analysis using a stratified conflict resolution mechanism revealed that neither rule involved direct safety contraindications (such as bleeding, worsening of organ prolapse, etc.); however, rapid weight gain could reduce the effectiveness of pelvic floor muscle rehabilitation. Based on the pre-defined multidisciplinary collaborative principle—"Functional recovery takes precedence over metabolic optimization"—the system retained the rehabilitation rule as the primary strategy. Simultaneously, the nutritional recommendations were dynamically adjusted to: "While maintaining energy balance, prioritize increasing the proportion of high-quality protein intake (1.2–1.5 g / kg / day), rather than simply increasing total calories."

[0051] Ultimately, all structured rules that have undergone conflict resolution, priority labeling, and safety filtering are converted into standardized JSON format and stored in the rule engine database, forming a multidisciplinary decision rule base that supports real-time matching and automatic exclusion of contraindications. For example, when patient information includes "grade III cystocele," the system will automatically block all interventions that may aggravate pelvic organ prolapse, such as high-intensity jumping, squat jumps, and weight-bearing training, ensuring the safety boundaries of the rehabilitation plan.

[0052] In some embodiments of this application, the multidisciplinary decision rule base supports an evidence-based incremental update mechanism, which includes the following implementation steps.

[0053] Step S310: Regularly obtain the latest clinical guidelines, expert consensus or research literature published in the medical field, and extract newly added or revised rehabilitation-related rules from them.

[0054] In step S310, by regularly collecting the latest clinical guidelines, expert consensus, or research literature published in the medical field, new evidence, new recommendations, or revisions to existing interventions related to postpartum rehabilitation are systematically identified, and new or updated rehabilitation-related rules that can be incorporated into the rule system are extracted. This process enables the rule base to dynamically respond to the evolution of medical knowledge, avoiding rehabilitation programs from deviating from current best practices due to knowledge lag.

[0055] Step S320: The extracted rules are evaluated for evidence-based status and updated incrementally to the multidisciplinary decision rule base after clinical validation, while the rules to be replaced are marked as invalid.

[0056] In step S320, the rules extracted from the latest medical data undergo an evidence-based assessment, judging their credibility based on the quality and strength of their evidence sources. Only after passing necessary clinical validation are these rules incrementally integrated into the multidisciplinary decision-making rule base. Simultaneously, for old rules replaced by new rules, the system automatically marks them as invalid, preserving the integrity of rule evolution while preventing the misuse of outdated or low-evidence-level recommendations, thereby maintaining the rigor and security of the entire decision-making system.

[0057] Step S330: Provide a change prompt message for the generated rehabilitation path association rules, and retain historical versions of the rule base to support path tracing and effect verification.

[0058] In step S330, when the rule base is updated, the system automatically associates the corresponding rule change notification information with the rehabilitation pathways previously generated based on the old rules, enabling medical staff to promptly understand whether the protocols they use have been affected by new evidence. Simultaneously, the system fully retains historical versions of the rule base, allowing any historical pathway to be traced back to the set of rules upon which it was generated, providing reliable data support for clinical efficacy evaluation, quality improvement, and liability determination.

[0059] In some embodiments of this application, step S120 involves matching patient information with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient, including the following steps.

[0060] Step S410: Standardize and preprocess the patient information to obtain a standardized patient dataset.

[0061] In step S410, the original patient information is transformed into a unified, standardized data format that can be accurately parsed by the rule system. This step cleanses, normalizes, and encodes heterogeneous data such as delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound results. This eliminates inconsistencies caused by factors such as units, dimensions, expression methods, or missing values, thereby generating a standardized patient dataset with a clear structure and semantics. This lays the data foundation for accurate matching with a multidisciplinary decision rule base.

[0062] Step S420: Input the standardized patient dataset into the multidisciplinary decision rule base, and perform safety contraindication matching, functional assessment matching and nutritional adaptation matching in sequence to obtain a preliminary rehabilitation task set.

[0063] Among them, safety contraindication matching excludes interventions with contraindications based on obstetric and imaging safety rules; functional assessment matching selects rehabilitation tasks that are suitable for the patient's current state based on rehabilitation department functional assessment indicators; and nutritional adaptation matching generates a dietary coordination plan based on nutrition department rules and the patient's health needs.

[0064] In step S420, a hierarchical, multi-dimensional rule matching mechanism is used to initially screen rehabilitation intervention options that meet the patient's current condition in terms of safety, functional suitability, and nutritional support. This step sequentially inputs standardized patient data into a multidisciplinary decision rule base. First, safety contraindication matching is performed, excluding interventions with medical contraindications based on obstetric and imaging safety rules to ensure the bottom-line safety of the plan. Second, functional assessment matching is conducted, selecting rehabilitation tasks that match the patient's muscle strength, anatomical structure, and symptom level based on rehabilitation department functional assessment indicators. Finally, nutritional suitability matching is implemented, generating a corresponding dietary coordination plan by combining nutrition department rules with the patient's individual health needs. These three elements together constitute a preliminary rehabilitation task set covering safety, function, and nutrition.

[0065] Step S430: Perform interdisciplinary conflict detection and resolution on the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set.

[0066] In step S430, potential interdisciplinary logical contradictions or clinical infeasibility issues within the initial rehabilitation task set are identified and resolved. Since intervention recommendations from different disciplines may conflict under specific patient conditions—for example, a particular exercise training program and nutrition plan may be incompatible in terms of time or physiological load, or two rehabilitation tasks may exert opposing effects on the same body part—this step identifies these inconsistencies through a systematic conflict detection mechanism and resolves them according to pre-defined strategies, such as disabling high-risk tasks, adjusting parameters, or replacing alternatives. Ultimately, this results in an internally consistent, clinically executable, conflict-free rehabilitation task set.

[0067] Step S440: Prioritize the set of conflict-free rehabilitation tasks based on evidence level, clinical urgency, and core patient needs to obtain a priority-ordered sequence of rehabilitation tasks, which is used to generate the timeline task arrangement in the postpartum rehabilitation pathway diagram.

[0068] In step S440, the set of conflict-free rehabilitation tasks is prioritized clinically to form an ordered and schedulable task sequence to support the construction of the pathway map's timeline. This step comprehensively considers the evidence level, clinical urgency, and the patient's core rehabilitation needs for each task, quantifying the importance and urgency of the tasks and generating a priority-ordered sequence of rehabilitation tasks accordingly. This prioritization directly determines the arrangement order and temporal distribution of tasks in the postpartum rehabilitation pathway map, ensuring that tasks with high evidence strength, high risk control value, or the patient's most urgent needs are prioritized, thereby improving the clinical rationality and implementation efficiency of the rehabilitation pathway.

[0069] In some embodiments of this application, step S430 involves cross-disciplinary conflict detection and resolution of the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set, specifically including the following:

[0070] (1) Detecting safety-related conflicts and implementing task disabling and alternative handling. Safety-related conflicts refer to rehabilitation tasks that conflict with the patient's safety contraindications. Specifically, the system identifies rehabilitation tasks that conflict with the patient's known safety contraindications. For example, a pelvic floor muscle training exercise may pose a risk in the presence of severe pelvic organ prolapse or in the early postoperative healing stage. Once such a safety-related conflict is identified, the system will immediately disable the task and recommend a medically equivalent alternative intervention that complies with current safety constraints based on the alternative strategies in the rule base. This prevents potentially harmful rehabilitation procedures from being performed at the source.

[0071] (2) Detecting functional conflicts and adjusting task execution parameters based on patient physiological indicators. Functional conflicts refer to conflicts between rehabilitation tasks and patient functional needs or nutritional management rules. Specifically, it identifies inconsistencies between rehabilitation tasks and the patient's current functional needs or nutritional management rules, such as a mismatch between high-intensity core training and diastasis recti, or a high-protein diet recommendation that does not match the patient's renal function status. When such functional conflicts are found, the system does not directly delete the task, but dynamically adjusts the intensity, frequency, duration, or execution method of the task based on the patient's specific physiological indicators such as pelvic floor muscle strength rating, diastasis recti index, and pain score, so that the intervention measures strictly conform to the patient's individual functional capacity while maintaining the treatment goals.

[0072] (3) Detect optimization-type conflicts and resolve them through task scheduling or priority rearrangement. Optimization-type conflicts refer to the overlap of multiple rehabilitation tasks in terms of execution time or resource allocation. Specifically, the system identifies the overlap of multiple rehabilitation tasks in terms of execution time windows, human support, equipment use, or patient energy allocation. For example, pelvic floor electrical stimulation and nutritional assessment appointments may be scheduled at the same time, or the total daily task load may exceed the patient's reasonable workload. For such optimization-type conflicts that do not involve safety or functional adaptation issues but affect the smoothness of implementation, the system resolves them by rearranging the time distribution of tasks, staggering peak times, or adjusting the priority order of tasks in the sequence, thereby generating a logically clear, rhythmically reasonable, and patient-friendly rehabilitation execution plan.

[0073] In some embodiments of this application, step S130 generates a postpartum rehabilitation path map containing a timeline and rehabilitation tasks based on a set of rehabilitation tasks, including: constructing a timeline based on the postpartum recovery stage division criteria, wherein the starting condition for the first stage is that the patient's initial state meets the safety access criteria for rehabilitation training, and the stage switching conditions for subsequent stages include completing the preset rehabilitation goals of the previous stage and meeting the access conditions for the next stage.

[0074] Specifically, by constructing a timeline based on clinically recognized postpartum recovery stage division standards, the system establishes a time framework for the entire rehabilitation process that aligns with medical consensus, ensuring that the pathway design is consistent with the natural laws of postpartum physiological recovery. Based on this, the initiation of the first stage is not automatically triggered, but rather based on whether the patient's initial state meets the safety admission criteria for rehabilitation training, thus ensuring the safety of intervention from the outset. The advancement of subsequent stages relies on a dual judgment mechanism: on the one hand, it confirms that the preset rehabilitation goals of the previous stage have been achieved, demonstrating substantial progress; on the other hand, it verifies whether the patient's current state meets the admission criteria for the next stage, preventing premature entry into advanced training that could lead to risks. This mechanism enables the postpartum rehabilitation pathway map to not only present task content but also embed a dynamic, condition-driven stage evolution logic, achieving a leap from static plans to intelligent, phased closed-loop management.

[0075] In some embodiments of this application, the system divides the structured rehabilitation process into three stages based on clinically recognized postpartum recovery stage classification standards: the first stage is 6–12 weeks postpartum, the second stage is 12–24 weeks postpartum, and the third stage is 24–52 weeks postpartum. When generating a personalized rehabilitation pathway map, the system first obtains follow-up data from a patient who delivered vaginally on day 42 postpartum, including: no puerperal infection, complete healing of the perineal wound, a resting pain score (VAS) ≤2, a standardized manual assessment of pelvic floor muscle strength of grade 2, diastasis recti of 3 fingers, and a 72-hour urinary incontinence diary recording occasional stress urinary leakage (≤2 times / day). Pelvic floor ultrasound examination shows a slight increase in bladder neck mobility (45 mm), but no significant pelvic organ prolapse (POP-Q stage ≤ stage I). This information indicates that the patient has passed the acute puerperium and meets the safety admission criteria for rehabilitation training. Based on this, the system activates the first stage (6–12 weeks) rehabilitation task. The pre-set rehabilitation goals for this stage include: improving pelvic floor muscle strength to ≥3, reducing rectus abdominis diastasis to ≤2 fingers, and achieving urinary incontinence-free daily activities. The rehabilitation task set includes low-intensity pelvic floor muscle electrophysiological biofeedback training, isometric contraction exercises of the transverse abdominis muscle, basic core stability training, and a high-protein nutritional support program.

[0076] When the patient returned for a follow-up examination at 12 weeks postpartum, the system received her latest assessment data: pelvic floor muscle strength reached grade 3, rectus abdominis diastasis decreased to 2 fingers, the 72-hour urinary incontinence diary showed no urinary incontinence events, and there were no new contraindications (such as urinary tract infection, worsening of lumbosacral pain, etc.). Simultaneously, dynamic postural control testing showed that her core stability met the standards (e.g., standing on one leg for ≥20 seconds). Based on this, the system determined that she had completed all the goals of the first phase and met the entry requirements for the second phase (12–24 weeks), thus automatically triggering the phase switch and activating the second phase tasks on the pathmap, including advanced resistance training (e.g., resistance band bridge), dynamic postural control exercises (e.g., pelvic floor muscle synergistic activation during walking), and an individualized nutritional enhancement program (protein intake of 1.5 g / kg / day).

[0077] If a patient fails to achieve any core goal by week 12 (e.g., muscle strength remains grade 2 or diastasis recti > 2.5 fingers), the system will maintain the patient in Phase 1 and mark the unmet goal and possible reasons (e.g., insufficient training adherence, comorbid chronic cough) on the pathway map, prompting clinicians to intervene and adjust. The entire rehabilitation process strictly follows a time-series logic driven by the dual conditions of "goal achievement + admission permission," ensuring the safety, effectiveness, and individualization of the intervention.

[0078] In some embodiments of this application, the method further includes dynamic management of the postpartum recovery pathway map, specifically including the following steps.

[0079] Step S510: Receive feedback information on the patient's recovery progress.

[0080] In step S510, an information feedback channel is established between the patient and the rehabilitation system, enabling the rehabilitation process to have real-time sensing capabilities. This step transforms the originally static path generation model into a closed-loop system that can respond to the actual dynamics of rehabilitation by receiving various progress feedback information generated by the patient during the rehabilitation process, including task completion status, symptom changes, follow-up data, or subjective feelings. This feedback information serves as a key input reflecting the patient's current true state, providing an objective basis for subsequent path adjustments and ensuring that the rehabilitation plan always remains synchronized with the patient's actual situation.

[0081] Step S520: Based on the feedback information and patient information, re-match the structured rules in the multidisciplinary decision rule base.

[0082] In step S520, the multidisciplinary knowledge reasoning mechanism is reactivated using the latest patient status data. This step integrates the rehabilitation progress feedback information received in step S510 with the original patient information to form updated comprehensive assessment data. Based on this, it is then matched again with the structured rules in the pre-built multidisciplinary decision rule base. This process is not a simple repetition of the initial matching, but rather a re-identification of the currently applicable set of rehabilitation tasks, given that the patient's status has changed. This ensures that the recommended interventions always meet the patient's latest safety, functional level, and rehabilitation needs.

[0083] Step S530: Based on the newly matched structured rules, adjust the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage in the postpartum rehabilitation pathway diagram.

[0084] In step S530, based on the newly matched structured rules, key elements of the existing rehabilitation pathway are specifically adjusted, including the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage. This adjustment is not a localized patch, but a rule-driven overall optimization, enabling the rehabilitation pathway to flexibly expand and contract as the patient's recovery progresses. Through this mechanism, the system can continuously provide scientific, safe, and highly individualized guidance throughout the entire rehabilitation cycle, significantly improving rehabilitation outcomes and patient compliance.

[0085] In some embodiments of this application, the system receives feedback information on the rehabilitation progress of a patient 10 weeks postpartum, including data such as pelvic floor muscle strength level, degree of diastasis recti, and nutritional status. Based on this feedback information combined with the patient's basic information (such as age, delivery method, and history of complications), the system automatically re-matches structured rules in the multidisciplinary decision rule base. For example, it is found that although the patient's pelvic floor muscle strength has reached the expected target, the improvement in diastasis recti is not significant, and there is mild anemia. According to the newly matched structured rules, the system adjusts the task sequence of the second stage in the postpartum rehabilitation pathway diagram, bringing forward some core stability training originally scheduled for the third stage, and adding nutritional intervention measures for anemia. At the same time, the system also adjusts the task intensity parameters accordingly, such as reducing the proportion of high-intensity interval training and increasing the frequency of aerobic exercise and iron supplementation; for the stage switching conditions, the system adds the requirement that diastasis recti be reduced to within 2 fingers, and updates the rehabilitation goals, aiming to ensure that the patient can achieve the original rehabilitation goals while solving the specific problems they currently face, thereby realizing personalized and dynamic postpartum rehabilitation pathway planning. This process embodies a closed-loop management mechanism of "feedback-assessment-adjustment," which helps improve postpartum recovery outcomes.

[0086] Secondly, refer to Figure 2 This application provides a postpartum rehabilitation pathway generation system that integrates multidisciplinary knowledge, including an information acquisition module, a decision rule base module, a rule matching module, a pathway generation module, and a feedback receiving module.

[0087] The information acquisition module is configured to acquire postpartum patient information, including delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results. These data reflect the patient's obstetric background, recovery time, muscle function status, anatomical abnormalities, and subjective symptom levels, which together constitute the starting point for multidisciplinary assessment, ensuring that subsequent decisions are based on comprehensive and quantifiable clinical evidence.

[0088] The decision rule base module is configured to build and store a multidisciplinary decision rule base. By organizing authoritative medical knowledge from fields such as obstetrics, rehabilitation, nutrition, and radiology, a computationally achievable and reasonable intelligent decision rule base is formed. This rule base stores rules in a structured format that have undergone evidence-based level labeling and conflict resolution. Each rule clearly includes conditions, actions, and constraints, and supports the exclusion of safety contraindications and interdisciplinary collaborative judgment. It provides the system with scientific, consistent, and dynamically updatable knowledge support, forming the logical foundation for generating personalized rehabilitation pathways.

[0089] The rule matching module is configured to match patient information with structured rules in a multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient. This process transforms fragmented clinical guidelines and expert consensus into feasible intervention recommendations tailored to the specific patient condition, ensuring that the selected tasks comply with clinical norms in terms of safety, functional fit, and nutritional synergy.

[0090] The path generation module is configured to generate a postpartum rehabilitation path map containing a timeline and rehabilitation tasks based on the rehabilitation task set. The timeline is divided according to the postpartum recovery stage division criteria, and the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage are determined by structured rules.

[0091] The feedback receiving module is configured to receive patient recovery progress feedback information, rematch the feedback information with patient information using structured rules in a multidisciplinary decision rule base, and adjust the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage of the postpartum rehabilitation pathway based on the newly matched structured rules. This mechanism enables the system to continuously respond to changes in the patient's recovery status, ensuring that the rehabilitation plan remains synchronized with the individual's actual needs, and improving the accuracy and effectiveness of interventions.

[0092] In some embodiments of this application, the system provides a graphical user interface, which includes a patient information collection unit, a path generation preview unit, a rule matching visualization unit, and a rehabilitation progress feedback unit.

[0093] The patient information collection unit is used to receive delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and imaging examination results. It supports structured data entry and attachment upload, and automatically verifies data integrity and logical consistency to ensure that the data relied upon for subsequent decision-making is accurate, complete, and in compliance with clinical standards.

[0094] The path generation preview unit is used to display personalized rehabilitation paths in a phased timeline format. It divides task intervals according to postpartum recovery stages, identifies task types with different colors, and allows users to click on task nodes to view execution parameters, contraindications, and related evaluation indicators, thereby improving the transparency, comprehensibility, and operability of the plan.

[0095] The rule matching visualization unit is used to present the matching process between patient information and a multidisciplinary decision rule base in the form of an interactive flowchart. It highlights the triggered rules and their evidence sources, and marks the rule priorities, enabling medical staff to trace the medical basis of intervention recommendations and facilitate the review, verification or adjustment of decision results.

[0096] The rehabilitation progress feedback unit receives task completion status, follow-up data, and patient subjective feedback, automatically generates rehabilitation progress charts, and triggers path adjustment suggestions based on feedback data. It supports synchronous updates of task parameter modifications and path diagrams. Specifically, when significant changes are detected, the system proactively triggers path adjustment suggestions, while also allowing medical staff to directly modify task parameters. All changes are synchronized to the rehabilitation path diagram in real time, enabling dynamic evolution and individualized adaptation of the plan.

[0097] Furthermore, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge.

[0098] In summary, the postpartum rehabilitation pathway generation method, system, and product that integrates multidisciplinary knowledge provided in this application have the following technical effects.

[0099] This application's technical solution integrates authoritative knowledge from multiple disciplines, including obstetrics, rehabilitation, nutrition, and radiology, to construct a structured and computable decision rule base. It uses objective clinical indicators such as delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound results as input to accurately identify the rehabilitation needs of individual patients. Based on this, it automatically generates a time-sequential rehabilitation path map based on clinically recognized recovery stage division standards, clearly defining the task sequence, intensity parameters, switching conditions, and rehabilitation goals for each stage. Simultaneously, it supports dynamic adjustment of the path content based on the patient's actual rehabilitation feedback, forming a closed-loop, iterative intelligent management mechanism. This solution effectively breaks through the limitations of traditional postpartum rehabilitation, such as disciplinary fragmentation, reliance on experience, and static planning, balancing standardized norms with individualized adaptation, significantly improving the scientific rigor, safety, feasibility, and clinical applicability of rehabilitation programs.

[0100] It should be noted that in all specific embodiments of this application, all data processing activities related to user identity or personal characteristics, such as user information, user behavior data, historical data, and location information, will be conducted in accordance with the principles of legality, legitimacy, and necessity. All data collection, use, storage, and processing will be subject to compliance with applicable national and regional laws, regulations, and industry standards, and informed consent from users will be obtained in a clear and explicit manner before processing. For the processing of sensitive personal information, separate consent from users will be obtained through prominent means such as pop-up prompts and independent confirmation pages. If any processing conflicts with laws and regulations, the laws and regulations will prevail, and necessary data processing will only be carried out within the scope permitted by laws and regulations, ensuring that all data-based applications, analyses, and technical implementations are conducted within the scope permitted by laws and regulations.

[0101] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0102] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of ordinary skill of an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary skill. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0103] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0105] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Additionally, computer-readable media can even be paper or other suitable media on which programs can be printed, for example, by optically scanning the paper or other media, then editing, interpreting, or, if necessary, processing it in a suitable manner to obtain the program electronically, and then storing it in computer memory.

[0106] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0107] In the foregoing description of this specification, the reference to terms such as "one embodiment / implementation," "another embodiment / implementation," or "certain embodiments / implementations," etc., indicates that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in an embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0108] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0109] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for generating postpartum rehabilitation pathways that integrates multidisciplinary knowledge, characterized in that, Includes the following steps: Obtain patient information for postpartum patients, including delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results; The patient information is matched with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient. Based on the rehabilitation task set, a postpartum rehabilitation path map containing a timeline and rehabilitation tasks is generated. The timeline is divided according to the postpartum recovery stage division criteria, and the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals of each stage are determined by the structured rules.

2. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 1, characterized in that, The construction process of the multidisciplinary decision rule base includes the following steps: Based on clinical guidelines, expert consensus, and evidence-based medicine literature from obstetrics, rehabilitation, nutrition, and radiology, a multidisciplinary joint knowledge graph including assessment indicators, intervention measures, indications, and contraindications is constructed. The medical logical relationships in the knowledge graph are converted into structured rules. Each structured rule includes a condition part, an action part, and a constraint part. The structured rules are assigned priorities based on evidence-based levels, which are determined by randomized controlled trials, expert consensus, and clinical experience. To address the conflicts between structured rules across different disciplines, a tiered conflict resolution mechanism is established. Conflicting rules are screened or replaced in the order of clinical safety, functional requirements, and optimization goals, and the basis for conflict resolution is recorded. The structured rules after conflict resolution are stored in a callable data format to form a multidisciplinary decision rule library that supports matching execution and automatic exclusion of taboo interventions.

3. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 2, characterized in that, The multidisciplinary decision rule base supports an evidence-based incremental update mechanism, which includes: Regularly obtain the latest clinical guidelines, expert consensus, or research literature published in the medical field, and extract newly added or revised rehabilitation-related rules from them; The extracted rules are evaluated for evidence-based status and updated incrementally to the multidisciplinary decision rule base after clinical validation, while the rules that are replaced are marked as invalid. The system provides change notifications for generated rehabilitation pathway association rules and retains historical versions of the rule base to support pathway tracing and effect verification.

4. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 1, characterized in that, The step of matching the patient information with structured rules in a pre-built multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient includes the following steps: The patient information is subjected to standardized preprocessing to obtain a standardized patient dataset; The standardized patient dataset is input into the multidisciplinary decision rule base, and safety contraindication matching, functional assessment matching, and nutritional adaptation matching are performed sequentially to obtain a preliminary rehabilitation task set. Among them, the safety contraindication matching excludes intervention measures with contraindications based on obstetric and imaging safety rules; the functional assessment matching screens rehabilitation tasks that are suitable for the patient's current state based on rehabilitation department functional assessment indicators; and the nutritional adaptation matching generates a dietary coordination plan based on nutrition department rules and the patient's health needs. Interdisciplinary conflict detection and resolution were performed on the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set; The conflict-free rehabilitation task set is prioritized based on evidence level, clinical urgency, and core patient needs to obtain a priority-ordered rehabilitation task sequence, which is used to generate the timeline task arrangement in the postpartum rehabilitation pathway diagram.

5. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 4, characterized in that, The process of performing interdisciplinary conflict detection and resolution on the preliminary rehabilitation task set to obtain a conflict-free rehabilitation task set specifically includes: Detect security conflicts and perform task disabling and alternative handling; Detect functional conflicts and adjust task execution parameters based on patient physiological indicators; Detect optimization-related conflicts and resolve them through task scheduling or priority reordering; Among them, the safety-related conflict refers to a conflict between the rehabilitation task and the patient's safety contraindications; the functional conflict refers to a conflict between the rehabilitation task and the patient's functional needs or nutritional management rules; and the optimization-related conflict refers to an overlap in the execution time or resource allocation of multiple rehabilitation tasks.

6. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 1, characterized in that, The step of generating a postpartum rehabilitation path map containing a timeline and rehabilitation tasks based on the rehabilitation task set includes: A timeline is constructed based on the postpartum recovery stage division criteria. The initiation condition for the first stage is that the patient's initial state meets the safety admission criteria for rehabilitation training. The stage switching conditions for subsequent stages include completing the preset rehabilitation goals of the previous stage and meeting the admission conditions of the next stage.

7. The method for generating postpartum rehabilitation pathways by integrating multidisciplinary knowledge according to claim 1, characterized in that, Also includes: Receive patient feedback on their recovery progress; Based on the feedback information and patient information, the structured rules in the multidisciplinary decision rule base are re-matched; Based on the newly matched structured rules, adjust the task sequence, task intensity parameters, stage switching conditions, and rehabilitation goals for each stage of the postpartum rehabilitation pathway diagram.

8. A postpartum rehabilitation pathway generation system integrating multidisciplinary knowledge, characterized in that, It includes an information acquisition module, a decision rule base module, a rule matching module, a path generation module, and a feedback receiving module; The information acquisition module is configured to acquire patient information of postpartum patients, including delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score, and pelvic floor ultrasound examination results. The decision rule base module is configured to build and store a multidisciplinary decision rule base; The rule matching module is configured to match the patient information with the structured rules in the multidisciplinary decision rule base to identify a set of rehabilitation tasks applicable to the current patient. The path generation module is configured to generate a postpartum rehabilitation path diagram containing a timeline and rehabilitation tasks based on the rehabilitation task set. The timeline is divided according to the postpartum recovery stage division criteria, and the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage are determined by the structured rules. The feedback receiving module is configured to receive patient rehabilitation progress feedback information, rematch the structured rules in the multidisciplinary decision rule base based on the feedback information and patient information, and adjust the task sequence, task intensity parameters, stage switching conditions and rehabilitation goals of each stage in the postpartum rehabilitation path diagram according to the newly matched structured rules.

9. The postpartum rehabilitation pathway generation system integrating multidisciplinary knowledge according to claim 8, characterized in that, The system provides a graphical user interface, which includes a patient information collection unit, a path generation preview unit, a rule matching visualization unit, and a rehabilitation progress feedback unit. The patient information collection unit is used to receive delivery method, postpartum days, pelvic floor muscle strength rating, diastasis recti index, pain score, GLAZER score and imaging examination results. It supports structured input and attachment upload, and automatically verifies data integrity. The path generation preview unit is used to display personalized rehabilitation paths in the form of a phased timeline, divide task intervals according to the postpartum recovery stage, identify task types with different colors, and support clicking on task nodes to view execution parameters, contraindications and related evaluation indicators. The rule matching visualization unit is used to present the matching process between patient information and the multidisciplinary decision rule base in the form of an interactive flowchart, highlight the triggered rules and their evidence sources, and mark the rule priorities. The rehabilitation progress feedback unit is used to receive task completion status, re-examination data and patient subjective feedback, automatically generate rehabilitation progress charts, and trigger path adjustment suggestions based on feedback data, supporting the synchronous update of task parameter modification and path chart.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the postpartum rehabilitation pathway generation method that integrates multidisciplinary knowledge as described in any one of claims 1 to 7.

Images