A method, system, and storage medium for fertility guidance for individual users

Abstract

The application provides a method, system and storage medium for preconception guidance of individual users, which first acquires original multi-source data of a user terminal, obtains standardized user data by preprocessing the data, extracts key thresholds and performs priority sorting based on a historical data set through a machine learning model, and constructs a dynamic threshold chain with a hierarchical structure; then, the user data is compared with thresholds at all levels in a progressive manner according to the priority order of the threshold chain, the subsequent comparison path is dynamically activated and the comparison logic is adjusted according to the previous comparison result, and finally, multi-level comparison results are generated; finally, the comparison results are matched and combined based on an expert knowledge base to generate and output personalized preconception suggestions; thereby, fine and multi-level evaluation of the user state is realized, and the accuracy and individualization level of the preconception guidance are improved; meanwhile, through systematic data processing and intelligent decision-making processes, the scientificity and practicality of the guidance suggestions are ensured.

Description

Technical Field

[0001] This invention relates to the field of preconception guidance, and more specifically, to a method, system, and storage medium for preconception guidance for individual users. Background Technology

[0002] In the field of intelligent health management and assisted fertility technology, data-driven personalized fertility guidance has long faced numerous technical bottlenecks. First, traditional methods often rely on monitoring single-dimensional physiological parameters, lacking the fusion and analysis of multi-source data such as user psychological state and lifestyle habits. This results in a one-sided user profile, making it difficult to comprehensively assess the complex factors affecting conception. Second, in the data analysis stage, existing systems typically use fixed thresholds or static models for status judgment, failing to adaptively adjust based on individual user characteristics and dynamic changes, leading to discrepancies between the assessment results and the user's actual condition. Third, in the suggestion generation stage, existing solutions often rely on pre-set general templates, lacking an intelligent matching mechanism based on multi-level analysis results, resulting in insufficiently targeted and practical suggestions. Finally, traditional technical processes often lack an effective feedback optimization loop, failing to continuously learn and evolve from practical application effects, leading to a gradual decline in long-term effectiveness.

[0003] Therefore, there is an urgent need for a pre-pregnancy guidance technology that can realize a closed loop of data processing, intelligent analysis, decision output, and feedback optimization. Summary of the Invention

[0004] In view of the above problems, the purpose of this invention is to provide a method, system, and storage medium for individual users' pre-pregnancy guidance. By establishing a dynamic threshold chain and a chain comparison mechanism, it achieves refined, multi-level evaluation of the user's status, overcoming the limitations of traditional single-threshold judgment. Specifically, firstly, a systematic data preprocessing process achieves standardization and quality control of multi-source data; secondly, through the deep integration of machine learning and expert knowledge, intelligent threshold extraction and sorting are achieved, ensuring the scientific and practical nature of the threshold chain construction; thirdly, through a progressive threshold comparison logic, the evaluation process is dynamically adapted and the path optimized, enhancing the accuracy of personalized analysis; finally, through intelligent matching and suggestion combination from an expert knowledge base, efficient transformation from analysis results to actionable suggestions is achieved, improving the practical value of the guidance plan; furthermore, a feedback optimization mechanism is established to achieve continuous calibration and self-evolution of system parameters, ensuring long-term effectiveness.

[0005] The first aspect of this invention provides a method for providing pre-pregnancy guidance to individual users, the method comprising:

[0006] Obtain raw, multi-source data from the user's end;

[0007] A preset data preprocessing procedure is performed on the original multi-source data to obtain standardized user data;

[0008] Based on a preset threshold extraction and priority sorting mechanism, a dynamic threshold chain of associated threshold groups is obtained from historical user datasets.

[0009] Based on the standardized user data and the dynamic threshold chain, perform a chain threshold comparison process;

[0010] According to the priority order of the dynamic threshold chain, the user data is compared with the thresholds at each level of the associated threshold group to obtain the first comparison result;

[0011] Based on the first comparison result, the threshold comparison path of the dynamic threshold chain is activated to generate multi-level comparison results;

[0012] Based on the multi-level comparison results, and using a pre-defined expert knowledge base, the system performs suggested rule matching and combination processing to generate personalized pregnancy preparation suggestions and output them to the user.

[0013] In this solution, the pre-defined data preprocessing procedure for the original multi-source data specifically includes:

[0014] Based on preset data integrity rules and numerical range rules, data validation processing is performed on the original multi-source data to obtain a valid dataset.

[0015] Anomaly identification and cleaning processes are performed on the valid data set to obtain a cleaned data set;

[0016] Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset;

[0017] The standardized dataset is used to perform classification and storage processing, and the data is stored in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters, respectively.

[0018] In this scheme, the dynamic threshold chain of associated threshold groups is obtained based on a preset threshold extraction and priority ranking mechanism and historical user datasets, specifically including:

[0019] The historical user dataset is input into a pre-trained machine learning model to identify parameter patterns associated with successful conception;

[0020] Based on the parameter pattern, key threshold fields are determined, and multiple initial thresholds are extracted.

[0021] Based on a preset expert rule base, the initial thresholds are prioritized and sorted from high to low according to their impact on conception.

[0022] Based on the correlation and priority between thresholds, a dynamic threshold chain with a hierarchical structure is generated.

[0023] In this solution, the step of performing a chain threshold comparison process based on the standardized user data and the dynamic threshold chain specifically includes:

[0024] Based on the priority order of the dynamic threshold chain, the first-level threshold comparison process is performed, comparing the user data with the first-level threshold.

[0025] Based on the results of the first-level comparison, determine whether to activate the next-level threshold comparison;

[0026] If so, the threshold for the next level will be dynamically adjusted based on the comparison results of the first level.

[0027] If not, then based on the comparison results of all levels, a comprehensive status assessment process is performed to generate multi-level comparison results.

[0028] In this solution, the step of performing suggested rule matching and combination processing based on the multi-level comparison results and a preset expert knowledge base specifically includes:

[0029] Based on the multi-level comparison results, expert knowledge base matching is performed to obtain suggested rule entries;

[0030] Based on the matched suggestion rule entries, perform suggestion content combination processing to generate a preliminary suggestion set;

[0031] Based on the priority order triggered by the threshold comparison, the importance ranking of suggestions is performed to determine the display order of the initial set of suggestions;

[0032] It acquires users' personalized characteristics, optimizes suggestion descriptions based on preset suggestion rules, and generates personalized pregnancy preparation suggestions.

[0033] This plan also includes:

[0034] Obtaining user feedback on pre-pregnancy advice is based on data;

[0035] Based on the data provided, an effectiveness assessment is performed to obtain a recommended effectiveness score.

[0036] Based on historical comparison results and suggested effectiveness scores, and using a preset threshold chain optimization mechanism, the threshold values ​​and priorities are adjusted.

[0037] Based on the optimized threshold chain, perform subsequent chain threshold comparisons.

[0038] A second aspect of the present invention provides a fertility preparation guidance system for individual users, including a fertility preparation guidance method program for individual users, wherein the fertility preparation guidance method program for individual users, when executed by the processor, performs the following steps:

[0039] Obtain raw, multi-source data from the user's end;

[0040] A preset data preprocessing procedure is performed on the original multi-source data to obtain standardized user data;

[0041] Based on a preset threshold extraction and priority sorting mechanism, a dynamic threshold chain of associated threshold groups is obtained from historical user datasets.

[0042] Based on the standardized user data and the dynamic threshold chain, perform a chain threshold comparison process;

[0043] According to the priority order of the dynamic threshold chain, the user data is compared with the thresholds at each level of the associated threshold group to obtain the first comparison result;

[0044] Based on the first comparison result, the threshold comparison path of the dynamic threshold chain is activated to generate multi-level comparison results;

[0045] Based on the multi-level comparison results, and using a pre-defined expert knowledge base, the system performs suggested rule matching and combination processing to generate personalized pregnancy preparation suggestions and output them to the user.

[0046] In this solution, the pre-defined data preprocessing procedure for the original multi-source data specifically includes:

[0047] Based on preset data integrity rules and numerical range rules, data validation processing is performed on the original multi-source data to obtain a valid dataset.

[0048] Anomaly identification and cleaning processes are performed on the valid data set to obtain a cleaned data set;

[0049] Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset;

[0050] The standardized dataset is used to perform classification and storage processing, and the data is stored in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters, respectively.

[0051] In this scheme, the dynamic threshold chain of associated threshold groups is obtained based on a preset threshold extraction and priority ranking mechanism and historical user datasets, specifically including:

[0052] The historical user dataset is input into a pre-trained machine learning model to identify parameter patterns associated with successful conception;

[0053] Based on the parameter pattern, key threshold fields are determined, and multiple initial thresholds are extracted.

[0054] Based on a preset expert rule base, the initial thresholds are prioritized and sorted from high to low according to their impact on conception.

[0055] Based on the correlation and priority between thresholds, a dynamic threshold chain with a hierarchical structure is generated.

[0056] A third aspect of the present invention provides a computer-readable storage medium comprising a method program for guiding fertility preparation for an individual user, wherein when executed by a processor, the method program implements the steps of the method for guiding fertility preparation for an individual user as described in any of the preceding claims.

[0057] This invention provides a method, system, and storage medium for providing preconception guidance to individual users. First, it acquires raw, multi-source data from the user's end and preprocesses the data to obtain standardized user data. Simultaneously, based on historical datasets, it extracts key thresholds using a machine learning model and prioritizes them, constructing a hierarchical dynamic threshold chain. Then, according to the priority order of the threshold chain, it progressively compares the user data with each level of thresholds, dynamically activating subsequent comparison paths and adjusting the comparison logic based on the results of previous comparisons, ultimately generating multi-level comparison results. Finally, it uses an expert knowledge base to perform rule matching and combination processing on the comparison results, generating and outputting personalized preconception advice. This achieves refined, multi-level assessment of the user's status, improving the accuracy and personalization of preconception guidance. Furthermore, through systematic data processing and intelligent decision-making processes, it ensures the scientific validity and practicality of the guidance advice. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope.

[0059] Figure 1 A flowchart of a method for providing pre-pregnancy guidance to individual users according to the present invention is shown;

[0060] Figure 2 This invention provides a flowchart of preprocessing raw multi-source data for conception preparation.

[0061] Figure 3 A flowchart illustrating the generation process of a dynamic threshold chain according to an embodiment of the present invention is shown.

[0062] Figure 4 A block diagram of a pre-pregnancy guidance system for individual users according to the present invention is shown. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Unless otherwise defined, all terms (including technical and scientific terms) used in embodiments of this invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as being interpreted in an idealized or highly formalized sense, unless expressly defined in this embodiment of the invention.

[0065] The terms "first," "second," and similar words used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "an," "a," or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. Similarly, terms such as "including" or "comprising" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The steps preceding or following the steps in the method of the embodiments of this invention are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0066] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0067] Figure 1 A flowchart of a method for providing pre-pregnancy guidance to individual users according to the present invention is shown.

[0068] like Figure 1 As shown, the first aspect of this invention discloses a method for providing pre-pregnancy guidance to individual users, the method comprising:

[0069] S102, Obtain raw multi-source data from the user terminal;

[0070] S104, Perform a preset data preprocessing procedure on the original multi-source data to obtain standardized user data;

[0071] S106, Based on the preset threshold extraction and priority sorting mechanism, a dynamic threshold chain of associated threshold groups is obtained according to the historical user dataset.

[0072] S108, Perform a chain threshold comparison process based on the standardized user data and the dynamic threshold chain;

[0073] S110, according to the priority order of the dynamic threshold chain, the user data is compared with the thresholds of each level of the associated threshold group to obtain the first comparison result;

[0074] S112, Based on the first comparison result, activate the threshold comparison path of the dynamic threshold chain to generate multi-level comparison results;

[0075] S114. Based on the multi-level comparison results, and using a preset expert knowledge base, perform suggested rule matching and combination processing to generate personalized pregnancy preparation suggestions and output them to the user terminal.

[0076] It should be noted that in this embodiment, raw multi-source data, including physiological parameters, psychological parameters, and lifestyle parameters, is first acquired through the user terminal device. A preset data preprocessing process is then executed, including integrity verification of the raw data, outlier cleaning, and standardization transformation, ultimately resulting in standardized user data with a unified format and dimensions. Simultaneously, based on a preset threshold extraction and priority ranking mechanism, and according to parameter patterns related to successful conception concentrated in historical user data, a machine learning model identifies key features and extracts multiple initial thresholds. These thresholds are then prioritized according to their impact on conception outcomes, based on the judgment rules for the importance of each parameter in an expert rule base, thus constructing a dynamic threshold chain with hierarchical relationships. Next, the core sequential threshold comparison processing stage begins, comparing the standardized user data with each level of thresholds layer by layer according to the priority order of the dynamic threshold chain. After the first level comparison is completed, the activation of the next level threshold comparison path is dynamically determined based on the comparison results, and the comparison sensitivity of subsequent thresholds can be adjusted in real time based on the results of previous comparisons. This sequential and progressive comparison method ultimately generates multi-level comparison results reflecting various aspects of the user's state. Finally, based on the suggestion rules stored in the preset expert knowledge base, the multi-level comparison results are intelligently matched and combined with the rule entries in the knowledge base to generate personalized pregnancy preparation suggestions that fully consider individual user differences, and output to the user through the user interface. This embodiment achieves refined evaluation of the user's status by establishing a dynamic threshold chain and a chain comparison mechanism, thereby improving the accuracy and personalization of pregnancy preparation guidance. At the same time, a systematic data processing flow ensures the scientific validity and reliability of the guidance suggestions.

[0077] Figure 2The diagram illustrates a preprocessing flowchart for raw multi-source data for conception preparation provided by an embodiment of the present invention.

[0078] According to embodiments of the present invention, such as Figure 2 As shown, the preset data preprocessing procedure for the raw multi-source data specifically includes:

[0079] S202, based on preset data integrity rules and numerical range rules, performs data verification processing on the original multi-source data to obtain a valid data set;

[0080] S204, Perform abnormal data identification and cleaning processing on the valid data set to obtain a cleaned data set;

[0081] S206, Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset;

[0082] S208, Perform classification and storage processing based on the standardized dataset, and store the data in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters respectively.

[0083] It should be noted that in this application, the original multi-source data is first validated based on preset data integrity and numerical range rules. By checking the integrity and numerical rationality of data items, data that clearly does not conform to physiological common sense or exceeds the reasonable range is filtered out, resulting in a valid data set. Next, anomaly identification and cleaning are performed on the valid data set. Statistical analysis methods are used to identify anomaly data points that deviate from the normal distribution range, and these are processed through interpolation or elimination to ensure the accuracy and consistency of the data, resulting in a cleaned data set. Then, standardization transformation is performed on the cleaned data set. The original data from different sources and with different dimensions are converted into standard scores with unified dimensions using normalization methods, eliminating dimensional differences between parameters and making various parameters comparable, resulting in a standardized dataset. Finally, classification and storage processing is performed on the standardized dataset, dividing it into three categories according to data attributes: physiological parameters, psychological parameters, and lifestyle parameters, and storing them in the corresponding data tables of the user profile database to establish a structured user health profile. This embodiment adopts a hierarchical and progressive data preprocessing approach, which can effectively improve data quality and provide a reliable data foundation for subsequent threshold comparison analysis.

[0084] Figure 3 A flowchart illustrating the generation process of a dynamic threshold chain provided by an embodiment of the present invention is shown.

[0085] According to embodiments of the present invention, such as Figure 3 As shown, the dynamic threshold chain of associated threshold groups, obtained based on the preset threshold extraction and priority ranking mechanism and historical user dataset, specifically includes:

[0086] S302, The historical user dataset is input into a pre-trained machine learning model to identify parameter patterns related to successful conception;

[0087] S304, Based on the parameter pattern, determine the key threshold field and extract multiple initial thresholds;

[0088] S306, Based on a preset expert rule base, the initial thresholds are prioritized and sorted from high to low according to their impact on conception;

[0089] S308 generates a dynamic threshold chain with a hierarchical structure based on the correlation and priority between thresholds.

[0090] It should be noted that in this embodiment, the historical user dataset is first input into a pre-trained machine learning model. This model analyzes the correlation between parameter patterns and conception outcomes in a large amount of historical user data to identify key parameter patterns significantly associated with successful conception. Next, based on the identified parameter patterns, key threshold fields are determined; multiple initial thresholds reflecting different state critical points are extracted from the model parameters. Then, based on the professional knowledge stored in a pre-set expert rule base, the extracted initial thresholds are prioritized. They are arranged from highest to lowest according to the degree of influence of each parameter on the conception outcome, ensuring that the thresholds of key parameters are compared first. Finally, based on the correlation and priority order between the thresholds, a hierarchical linking algorithm generates a dynamic threshold chain with a hierarchical structure; the comparison results of higher-level thresholds directly affect the activation state of lower-level thresholds. This embodiment fully utilizes the ability of machine learning to mine patterns from big data and integrates the guidance of professional medical knowledge, making the generated threshold chain both data-driven and scientifically sound, and compliant with clinical practice requirements.

[0091] According to an embodiment of the present invention, the step of performing a chain threshold comparison process based on the standardized user data and the dynamic threshold chain specifically includes:

[0092] Based on the priority order of the dynamic threshold chain, the first-level threshold comparison process is performed, comparing the user data with the first-level threshold.

[0093] Based on the results of the first-level comparison, determine whether to activate the next-level threshold comparison;

[0094] If so, the threshold for the next level will be dynamically adjusted based on the comparison results of the first level.

[0095] If not, then based on the comparison results of all levels, a comprehensive status assessment process is performed to generate multi-level comparison results.

[0096] It should be noted that in this embodiment, the first-level threshold comparison process is performed according to the priority order of the dynamic threshold chain. The user's real-time data is compared with the first-level threshold to obtain a preliminary comparison result. Then, based on the first-level comparison result, a conditional judgment logic determines whether to activate the next-level threshold comparison. If the comparison result is within the threshold range, the next-level comparison is activated; if it exceeds the threshold range, a specific processing path may be triggered. When it is necessary to activate subsequent comparisons, the comparison standard or sensitivity of the next-level threshold is dynamically adjusted according to the deviation of the first-level comparison result, making the comparison process more closely reflect the user's current state. Finally, after all levels of comparison are completed, a comprehensive state assessment is performed. By integrating the comparison results and their deviations at each level, a multi-level comparison result that comprehensively reflects the user's physiological, psychological, and lifestyle state is generated. The chain-like threshold comparison mechanism provided in this embodiment, through hierarchical judgment logic, achieves a refined assessment of the user's state from superficial to profound, from primary to secondary aspects, ensuring assessment efficiency; it also enhances adaptability to individual differences through a dynamic adjustment mechanism.

[0097] According to an embodiment of the present invention, the step of performing suggested rule matching and combination processing based on the multi-level comparison results and a preset expert knowledge base specifically includes:

[0098] Based on the multi-level comparison results, expert knowledge base matching is performed to obtain suggested rule entries;

[0099] Based on the matched suggestion rule entries, perform suggestion content combination processing to generate a preliminary suggestion set;

[0100] Based on the priority order triggered by the threshold comparison, the importance ranking of suggestions is performed to determine the display order of the initial set of suggestions;

[0101] It acquires users' personalized characteristics, optimizes suggestion descriptions based on preset suggestion rules, and generates personalized pregnancy preparation suggestions.

[0102] It should be noted that in this embodiment, firstly, based on the threshold triggering states and parameter deviations recorded in the multi-level comparison results, an intelligent matching search is performed in a preset expert knowledge base to find suggestion rule entries corresponding to the current user's state. Next, based on the matched suggestion rule entries, suggestion content combination processing is performed; the rule engine dynamically combines and fills in parameters according to the user's specific situation, generating a preliminary suggestion set covering multiple dimensions such as menstrual cycle management, lifestyle adjustment, and psychological state regulation. Then, based on the priority order triggered during the threshold comparison process, suggestion importance ranking processing is performed; suggestions involving key physiological parameters are automatically arranged at the front of the display sequence to ensure that users prioritize the core suggestions that have the greatest impact on the success rate of conception. Finally, personalized feature data from the user profile is obtained, and based on preset suggestion expression optimization rules, the preliminary suggestions are personalized in terms of language style and level of detail, generating personalized conception suggestions that conform to medical standards and are close to the user's understanding. This embodiment utilizes a suggestion generation mechanism that employs multi-level rule matching and dynamic combination to achieve efficient transformation from data analysis to actionable suggestions. This ensures both the scientific rigor and comprehensiveness of the suggestions while enhancing user experience and compliance through personalized wording, thereby improving the actual effectiveness of pre-pregnancy guidance.

[0103] According to an embodiment of the present invention, it further includes:

[0104] Obtaining user feedback on pre-pregnancy advice is based on data;

[0105] Based on the data provided, an effectiveness assessment is performed to obtain a recommended effectiveness score.

[0106] Based on historical comparison results and suggested effectiveness scores, and using a preset threshold chain optimization mechanism, the threshold values ​​and priorities are adjusted.

[0107] Based on the optimized threshold chain, perform subsequent chain threshold comparisons.

[0108] It should be noted that in this embodiment, user compliance data for the pre-pregnancy advice is continuously acquired through the user interface, including the completion rate of advice implementation and subjective feedback. Then, based on the collected compliance data and subsequent user status change data, an effectiveness assessment is performed, calculating the advice effectiveness score by comparing the degree of parameter improvement before and after advice implementation. Next, based on the correlation analysis between historical comparison results and the advice effectiveness score, a preset threshold chain optimization mechanism is activated. Threshold values ​​in the dynamic threshold chain that deviate significantly from actual results are calibrated and adjusted, and their priority is reassessed based on their contribution to prediction accuracy. Finally, the optimized threshold chain is applied to subsequent user chain threshold comparisons, forming a continuously improving closed-loop optimization system. The feedback optimization mechanism provided in this embodiment, by collecting user feedback and effectiveness data in real time, continuously learns and adjusts from actual application results; it not only gradually improves the accuracy of status assessment but also makes the threshold settings more closely match the characteristics of real-world user groups. This ensures that the guidance advice can continuously evolve and improve with accumulated user experience, maintaining its effectiveness and adaptability in the long term.

[0109] It is worth mentioning that it also includes:

[0110] Based on user data from different collection channels, the data is aligned according to time series to establish a multi-source data sequence with a unified time benchmark.

[0111] Based on the multi-source data sequence, the correlation between physiological parameters and psychological parameters is fused to generate composite feature indicators;

[0112] Based on user lifestyle and menstrual cycle data, multidimensional cross-validation is performed to identify the degree of matching between data.

[0113] If the matching degree exceeds the preset security threshold, then an adaptive adjustment of the dynamic threshold chain is performed based on the fused composite feature index.

[0114] It should be noted that in this embodiment, time series alignment is first performed on user data from different collection channels with inconsistent timestamps. A multi-source data sequence with a unified time benchmark is established through time interpolation and synchronization algorithms to ensure the comparability of various parameters across time dimensions. Next, based on the aligned multi-source data sequence, correlation fusion processing of physiological and psychological parameters is performed. By analyzing the temporal correlation patterns between the two, a composite feature index that comprehensively reflects physical and mental state is generated. Then, multi-dimensional data cross-validation processing is performed using user lifestyle data and physiological cycle data; a consistency check algorithm is used to identify the degree of matching between data from different sources, verifying the reliability of the information provided by users. When the data matching degree exceeds a preset safety threshold, an adaptive adjustment process of the dynamic threshold chain is performed based on the composite feature index generated after fusion, incorporating the composite index into the threshold comparison system and optimizing the settings of each level of threshold accordingly. The fusion mechanism provided in this embodiment enhances the depth and breadth of data utilization through cross-parameter correlation analysis and cross-validation; it also captures comprehensive state characteristics that cannot be reflected by a single parameter through the application of composite indicators, thereby providing richer data support for precise guidance.

[0115] It is worth mentioning that it also includes:

[0116] Based on the user's historical data sequence and the periodic analysis of preset physiological parameters, the system identifies the user's individual physiological cycle pattern.

[0117] Based on the identified physiological cycle patterns, a user-specific physiological state prediction model is built by constructing and processing the model based on a preset trend prediction model.

[0118] The trend analysis results are obtained by inputting real-time collected user data into the prediction model.

[0119] Based on the trend analysis results, the suggestion pre-generation logic is executed to obtain pre-pregnancy suggestions.

[0120] It should be noted that in this embodiment, the user's historical data sequence is first acquired. Based on a preset physiological parameter periodic analysis algorithm, the unique physiological cycle patterns of each user are identified, including personalized patterns such as menstrual cycle length and ovulation characteristics. Next, based on the identified physiological cycle patterns, a trend prediction model is constructed. A user-specific physiological state prediction model is established using a time series prediction algorithm, enabling proactive prediction of future physiological state trends. Then, real-time collected user data is input into the trained prediction model to obtain trend analysis results, including predicted values ​​and their confidence intervals. Finally, based on the trend analysis results, a suggestion pre-generation logic is executed to generate corresponding proactive guidance plans, such as suggestions for preparing for pregnancy and reminders for lifestyle adjustments, based on the predicted future physiological state changes. The time series trend analysis mechanism provided in this embodiment mines regular patterns in user historical data. It upgrades traditional state assessment from static analysis to dynamic prediction, enabling users to understand their own state change trends in advance and make corresponding preparations, helping them better grasp the timing for preparing for pregnancy and thus increasing the probability of successful conception.

[0121] Figure 4 A block diagram of a pre-pregnancy guidance system for individual users according to the present invention is shown.

[0122] like Figure 4 As shown, a second aspect of the present invention discloses a fertility preparation guidance system 4 for individual users, including a memory 41 and a processor 42. The memory includes a fertility preparation guidance method program for individual users, which, when executed by the processor, performs the following steps:

[0123] Obtain raw, multi-source data from the user's end;

[0124] A preset data preprocessing procedure is performed on the original multi-source data to obtain standardized user data;

[0125] Based on a preset threshold extraction and priority sorting mechanism, a dynamic threshold chain of associated threshold groups is obtained from historical user datasets.

[0126] Based on the standardized user data and the dynamic threshold chain, perform a chain threshold comparison process;

[0127] According to the priority order of the dynamic threshold chain, the user data is compared with the thresholds at each level of the associated threshold group to obtain the first comparison result;

[0128] Based on the first comparison result, the threshold comparison path of the dynamic threshold chain is activated to generate multi-level comparison results;

[0129] Based on the multi-level comparison results, and using a pre-defined expert knowledge base, the system performs suggested rule matching and combination processing to generate personalized pregnancy preparation suggestions and output them to the user.

[0130] It should be noted that in this embodiment, raw multi-source data, including physiological parameters, psychological parameters, and lifestyle parameters, is first acquired through the user terminal device. A preset data preprocessing process is then executed, including integrity verification of the raw data, outlier cleaning, and standardization transformation, ultimately resulting in standardized user data with a unified format and dimensions. Simultaneously, based on a preset threshold extraction and priority ranking mechanism, and according to parameter patterns related to successful conception concentrated in historical user data, a machine learning model identifies key features and extracts multiple initial thresholds. These thresholds are then prioritized according to their impact on conception outcomes, based on the judgment rules for the importance of each parameter in an expert rule base, thus constructing a dynamic threshold chain with hierarchical relationships. Next, the core sequential threshold comparison processing stage begins, comparing the standardized user data with each level of thresholds layer by layer according to the priority order of the dynamic threshold chain. After the first level comparison is completed, the activation of the next level threshold comparison path is dynamically determined based on the comparison results, and the comparison sensitivity of subsequent thresholds can be adjusted in real time based on the results of previous comparisons. This sequential and progressive comparison method ultimately generates multi-level comparison results reflecting various aspects of the user's state. Finally, based on the suggestion rules stored in the preset expert knowledge base, the multi-level comparison results are intelligently matched and combined with the rule entries in the knowledge base to generate personalized pregnancy preparation suggestions that fully consider individual user differences, and output to the user through the user interface. This embodiment achieves refined evaluation of the user's status by establishing a dynamic threshold chain and a chain comparison mechanism, thereby improving the accuracy and personalization of pregnancy preparation guidance. At the same time, a systematic data processing flow ensures the scientific validity and reliability of the guidance suggestions.

[0131] According to an embodiment of the present invention, the step of performing a preset data preprocessing procedure on the original multi-source data specifically includes:

[0132] Based on preset data integrity rules and numerical range rules, data validation processing is performed on the original multi-source data to obtain a valid dataset.

[0133] Anomaly identification and cleaning processes are performed on the valid data set to obtain a cleaned data set;

[0134] Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset;

[0135] The standardized dataset is used to perform classification and storage processing, and the data is stored in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters, respectively.

[0136] It should be noted that in this application, the original multi-source data is first validated based on preset data integrity and numerical range rules. By checking the integrity and numerical rationality of data items, data that clearly does not conform to physiological common sense or exceeds the reasonable range is filtered out, resulting in a valid data set. Next, anomaly identification and cleaning are performed on the valid data set. Statistical analysis methods are used to identify anomaly data points that deviate from the normal distribution range, and these are processed through interpolation or elimination to ensure the accuracy and consistency of the data, resulting in a cleaned data set. Then, standardization transformation is performed on the cleaned data set. The original data from different sources and with different dimensions are converted into standard scores with unified dimensions using normalization methods, eliminating dimensional differences between parameters and making various parameters comparable, resulting in a standardized dataset. Finally, classification and storage processing is performed on the standardized dataset, dividing it into three categories according to data attributes: physiological parameters, psychological parameters, and lifestyle parameters, and storing them in the corresponding data tables of the user profile database to establish a structured user health profile. This embodiment adopts a hierarchical and progressive data preprocessing approach, which can effectively improve data quality and provide a reliable data foundation for subsequent threshold comparison analysis.

[0137] According to an embodiment of the present invention, the step of obtaining a dynamic threshold chain of associated threshold groups based on a preset threshold extraction and priority ranking mechanism and a historical user dataset specifically includes:

[0138] The historical user dataset is input into a pre-trained machine learning model to identify parameter patterns associated with successful conception;

[0139] Based on the parameter pattern, key threshold fields are determined, and multiple initial thresholds are extracted.

[0140] Based on a preset expert rule base, the initial thresholds are prioritized and sorted from high to low according to their impact on conception.

[0141] Based on the correlation and priority between thresholds, a dynamic threshold chain with a hierarchical structure is generated.

[0142] It should be noted that in this embodiment, the historical user dataset is first input into a pre-trained machine learning model. This model analyzes the correlation between parameter patterns and conception outcomes in a large amount of historical user data to identify key parameter patterns significantly associated with successful conception. Next, based on the identified parameter patterns, key threshold fields are determined; multiple initial thresholds reflecting different state critical points are extracted from the model parameters. Then, based on the professional knowledge stored in a pre-set expert rule base, the extracted initial thresholds are prioritized. They are arranged from highest to lowest according to the degree of influence of each parameter on the conception outcome, ensuring that the thresholds of key parameters are compared first. Finally, based on the correlation and priority order between the thresholds, a hierarchical linking algorithm generates a dynamic threshold chain with a hierarchical structure; the comparison results of higher-level thresholds directly affect the activation state of lower-level thresholds. This embodiment fully utilizes the ability of machine learning to mine patterns from big data and integrates the guidance of professional medical knowledge, making the generated threshold chain both data-driven and scientifically sound, and compliant with clinical practice requirements.

[0143] According to an embodiment of the present invention, the step of performing a chain threshold comparison process based on the standardized user data and the dynamic threshold chain specifically includes:

[0144] Based on the priority order of the dynamic threshold chain, the first-level threshold comparison process is performed, comparing the user data with the first-level threshold.

[0145] Based on the results of the first-level comparison, determine whether to activate the next-level threshold comparison;

[0146] If so, the threshold for the next level will be dynamically adjusted based on the comparison results of the first level.

[0147] If not, then based on the comparison results of all levels, a comprehensive status assessment process is performed to generate multi-level comparison results.

[0148] It should be noted that in this embodiment, the first-level threshold comparison process is performed according to the priority order of the dynamic threshold chain. The user's real-time data is compared with the first-level threshold to obtain a preliminary comparison result. Then, based on the first-level comparison result, a conditional judgment logic determines whether to activate the next-level threshold comparison. If the comparison result is within the threshold range, the next-level comparison is activated; if it exceeds the threshold range, a specific processing path may be triggered. When it is necessary to activate subsequent comparisons, the comparison standard or sensitivity of the next-level threshold is dynamically adjusted according to the deviation of the first-level comparison result, making the comparison process more closely reflect the user's current state. Finally, after all levels of comparison are completed, a comprehensive state assessment is performed. By integrating the comparison results and their deviations at each level, a multi-level comparison result that comprehensively reflects the user's physiological, psychological, and lifestyle state is generated. The chain-like threshold comparison mechanism provided in this embodiment, through hierarchical judgment logic, achieves a refined assessment of the user's state from superficial to profound, from primary to secondary aspects, ensuring assessment efficiency; it also enhances adaptability to individual differences through a dynamic adjustment mechanism.

[0149] According to an embodiment of the present invention, the step of performing suggested rule matching and combination processing based on the multi-level comparison results and a preset expert knowledge base specifically includes:

[0150] Based on the multi-level comparison results, expert knowledge base matching is performed to obtain suggested rule entries;

[0151] Based on the matched suggestion rule entries, perform suggestion content combination processing to generate a preliminary suggestion set;

[0152] Based on the priority order triggered by the threshold comparison, the importance ranking of suggestions is performed to determine the display order of the initial set of suggestions;

[0153] It acquires users' personalized characteristics, optimizes suggestion descriptions based on preset suggestion rules, and generates personalized pregnancy preparation suggestions.

[0154] It should be noted that in this embodiment, firstly, based on the threshold triggering states and parameter deviations recorded in the multi-level comparison results, an intelligent matching search is performed in a preset expert knowledge base to find suggestion rule entries corresponding to the current user's state. Next, based on the matched suggestion rule entries, suggestion content combination processing is performed; the rule engine dynamically combines and fills in parameters according to the user's specific situation, generating a preliminary suggestion set covering multiple dimensions such as menstrual cycle management, lifestyle adjustment, and psychological state regulation. Then, based on the priority order triggered during the threshold comparison process, suggestion importance ranking processing is performed; suggestions involving key physiological parameters are automatically arranged at the front of the display sequence to ensure that users prioritize the core suggestions that have the greatest impact on the success rate of conception. Finally, personalized feature data from the user profile is obtained, and based on preset suggestion expression optimization rules, the preliminary suggestions are personalized in terms of language style and level of detail, generating personalized conception suggestions that conform to medical standards and are close to the user's understanding. This embodiment utilizes a suggestion generation mechanism that employs multi-level rule matching and dynamic combination to achieve efficient transformation from data analysis to actionable suggestions. This ensures both the scientific rigor and comprehensiveness of the suggestions while enhancing user experience and compliance through personalized wording, thereby improving the actual effectiveness of pre-pregnancy guidance.

[0155] According to an embodiment of the present invention, it further includes:

[0156] Obtaining user feedback on pre-pregnancy advice is based on data;

[0157] Based on the data provided, an effectiveness assessment is performed to obtain a recommended effectiveness score.

[0158] Based on historical comparison results and suggested effectiveness scores, and using a preset threshold chain optimization mechanism, the threshold values ​​and priorities are adjusted.

[0159] Based on the optimized threshold chain, perform subsequent chain threshold comparisons.

[0160] It should be noted that in this embodiment, user compliance data for the pre-pregnancy advice is continuously acquired through the user interface, including the completion rate of advice implementation and subjective feedback. Then, based on the collected compliance data and subsequent user status change data, an effectiveness assessment is performed, calculating the advice effectiveness score by comparing the degree of parameter improvement before and after advice implementation. Next, based on the correlation analysis between historical comparison results and the advice effectiveness score, a preset threshold chain optimization mechanism is activated. Threshold values ​​in the dynamic threshold chain that deviate significantly from actual results are calibrated and adjusted, and their priority is reassessed based on their contribution to prediction accuracy. Finally, the optimized threshold chain is applied to subsequent user chain threshold comparisons, forming a continuously improving closed-loop optimization system. The feedback optimization mechanism provided in this embodiment, by collecting user feedback and effectiveness data in real time, continuously learns and adjusts from actual application results; it not only gradually improves the accuracy of status assessment but also makes the threshold settings more closely match the characteristics of real-world user groups. This ensures that the guidance advice can continuously evolve and improve with accumulated user experience, maintaining its effectiveness and adaptability in the long term.

[0161] It is worth mentioning that it also includes:

[0162] Based on user data from different collection channels, the data is aligned according to time series to establish a multi-source data sequence with a unified time benchmark.

[0163] Based on the multi-source data sequence, the correlation between physiological parameters and psychological parameters is fused to generate composite feature indicators;

[0164] Based on user lifestyle and menstrual cycle data, multidimensional cross-validation is performed to identify the degree of matching between data.

[0165] If the matching degree exceeds the preset security threshold, then an adaptive adjustment of the dynamic threshold chain is performed based on the fused composite feature index.

[0166] It should be noted that in this embodiment, time series alignment is first performed on user data from different collection channels with inconsistent timestamps. A multi-source data sequence with a unified time benchmark is established through time interpolation and synchronization algorithms to ensure the comparability of various parameters across time dimensions. Next, based on the aligned multi-source data sequence, correlation fusion processing of physiological and psychological parameters is performed. By analyzing the temporal correlation patterns between the two, a composite feature index that comprehensively reflects physical and mental state is generated. Then, multi-dimensional data cross-validation processing is performed using user lifestyle data and physiological cycle data; a consistency check algorithm is used to identify the degree of matching between data from different sources, verifying the reliability of the information provided by users. When the data matching degree exceeds a preset safety threshold, an adaptive adjustment process of the dynamic threshold chain is performed based on the composite feature index generated after fusion, incorporating the composite index into the threshold comparison system and optimizing the settings of each level of threshold accordingly. The fusion mechanism provided in this embodiment enhances the depth and breadth of data utilization through cross-parameter correlation analysis and cross-validation; it also captures comprehensive state characteristics that cannot be reflected by a single parameter through the application of composite indicators, thereby providing richer data support for precise guidance.

[0167] It is worth mentioning that it also includes:

[0168] Based on the user's historical data sequence and the periodic analysis of preset physiological parameters, the system identifies the user's individual physiological cycle pattern.

[0169] Based on the identified physiological cycle patterns, a user-specific physiological state prediction model is built by constructing and processing the model based on a preset trend prediction model.

[0170] The trend analysis results are obtained by inputting real-time collected user data into the prediction model.

[0171] Based on the trend analysis results, the suggestion pre-generation logic is executed to obtain pre-pregnancy suggestions.

[0172] It should be noted that in this embodiment, the user's historical data sequence is first acquired. Based on a preset physiological parameter periodic analysis algorithm, the unique physiological cycle patterns of each user are identified, including personalized patterns such as menstrual cycle length and ovulation characteristics. Next, based on the identified physiological cycle patterns, a trend prediction model is constructed. A user-specific physiological state prediction model is established using a time series prediction algorithm, enabling proactive prediction of future physiological state trends. Then, real-time collected user data is input into the trained prediction model to obtain trend analysis results, including predicted values ​​and their confidence intervals. Finally, based on the trend analysis results, a suggestion pre-generation logic is executed to generate corresponding proactive guidance plans, such as suggestions for preparing for pregnancy and reminders for lifestyle adjustments, based on the predicted future physiological state changes. The time series trend analysis mechanism provided in this embodiment mines regular patterns in user historical data. It upgrades traditional state assessment from static analysis to dynamic prediction, enabling users to understand their own state change trends in advance and make corresponding preparations, helping them better grasp the timing for preparing for pregnancy and thus increasing the probability of successful conception.

[0173] A third aspect of the present invention provides a computer-readable storage medium comprising a method program for guiding fertility preparation for an individual user, wherein when executed by a processor, the method program implements the steps of the method for guiding fertility preparation for an individual user as described in any of the preceding claims.

[0174] In summary, this invention provides a method, system, and storage medium for providing pre-pregnancy guidance to individual users. First, it acquires raw, multi-source data from the user's end and preprocesses the data to obtain standardized user data. Simultaneously, based on historical datasets, it extracts key thresholds using a machine learning model and prioritizes them, constructing a hierarchical dynamic threshold chain. Then, according to the priority order of the threshold chain, it progressively compares the user data with each level of thresholds, dynamically activating subsequent comparison paths and adjusting the comparison logic based on the results of previous comparisons, ultimately generating multi-level comparison results. Finally, it uses an expert knowledge base to perform rule matching and combination processing on the comparison results, generating and outputting personalized pre-pregnancy advice. This achieves refined, multi-level assessment of the user's status, improving the accuracy and personalization of pre-pregnancy guidance. Furthermore, through systematic data processing and intelligent decision-making processes, it ensures the scientific validity and practicality of the guidance advice.

[0175] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they 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 portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions 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 described in 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.

[0176] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for providing pre-pregnancy guidance to individual users, characterized in that, The method includes: Obtain raw multi-source data from the user terminal; the raw multi-source data includes physiological parameters, psychological parameters, and lifestyle parameters; A preset data preprocessing procedure is performed on the original multi-source data to obtain standardized user data; Based on a preset threshold extraction and priority ranking mechanism, a dynamic threshold chain of associated threshold groups is obtained according to a historical user dataset. Specifically, this includes: inputting the historical user dataset into a pre-trained machine learning model to identify parameter patterns related to successful conception; determining key threshold fields based on the parameter patterns and extracting multiple initial thresholds; prioritizing the initial thresholds based on a preset expert rule base, arranging them from high to low according to their impact on conception; and generating a hierarchical dynamic threshold chain based on the correlation and priority between the thresholds. Based on the standardized user data and the dynamic threshold chain, a chain threshold comparison process is performed, specifically including: performing a first-level threshold comparison process according to the priority order of the dynamic threshold chain, comparing the user data with the first-level threshold; determining whether to activate the next-level threshold comparison based on the first-level comparison result; if yes, dynamically adjusting the next-level threshold based on the first-level comparison result; if no, performing a comprehensive state evaluation process based on the comparison results of all levels to generate multi-level comparison results. Based on the multi-level comparison results, and using a preset expert knowledge base, a suggestion rule matching and combination process is performed to generate personalized pregnancy preparation suggestions and output them to the user. Specifically, this includes: performing expert knowledge base matching based on the multi-level comparison results to obtain suggestion rule entries; performing suggestion content combination processing based on the matched suggestion rule entries to generate a preliminary suggestion set; performing suggestion importance sorting processing based on the priority order triggered by threshold comparison to determine the display order of the preliminary suggestion set; obtaining user personalized characteristics, optimizing suggestion expression based on preset suggestion rules, and generating personalized pregnancy preparation suggestions.

2. The method for providing pre-pregnancy guidance to individual users according to claim 1, characterized in that, The preset data preprocessing procedure for the raw multi-source data specifically includes: Based on preset data integrity rules and numerical range rules, data validation processing is performed on the original multi-source data to obtain a valid dataset. Anomaly identification and cleaning processes are performed on the valid data set to obtain a cleaned data set; Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset; The standardized dataset is used to perform classification and storage processing, and the data is stored in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters, respectively.

3. The method for providing pre-pregnancy guidance to individual users according to claim 1, characterized in that, Also includes: Obtaining user feedback on pre-pregnancy advice is based on data; Based on the data provided, an effectiveness assessment is performed to obtain a recommended effectiveness score. Based on historical comparison results and suggested effectiveness scores, and using a preset threshold chain optimization mechanism, the threshold values ​​and priorities are adjusted. Based on the optimized threshold chain, perform subsequent chain threshold comparisons.

4. A pregnancy preparation guidance system for individual users, characterized in that, The system includes a memory and a processor. The memory includes a program for a method of guiding fertility preparation for individual users. When executed by the processor, the method of guiding fertility preparation for individual users performs the following steps: Obtain raw multi-source data from the user terminal; the raw multi-source data includes physiological parameters, psychological parameters, and lifestyle parameters; A preset data preprocessing procedure is performed on the original multi-source data to obtain standardized user data; Based on a preset threshold extraction and priority ranking mechanism, a dynamic threshold chain of associated threshold groups is obtained according to a historical user dataset. Specifically, this includes: inputting the historical user dataset into a pre-trained machine learning model to identify parameter patterns related to successful conception; determining key threshold fields based on the parameter patterns and extracting multiple initial thresholds; prioritizing the initial thresholds based on a preset expert rule base, arranging them from high to low according to their impact on conception; and generating a hierarchical dynamic threshold chain based on the correlation and priority between the thresholds. Based on the standardized user data and the dynamic threshold chain, a chain threshold comparison process is performed, specifically including: performing a first-level threshold comparison process according to the priority order of the dynamic threshold chain, comparing the user data with the first-level threshold; determining whether to activate the next-level threshold comparison based on the first-level comparison result; if yes, dynamically adjusting the next-level threshold based on the first-level comparison result; if no, performing a comprehensive state evaluation process based on the comparison results of all levels to generate multi-level comparison results. Based on the multi-level comparison results, and using a preset expert knowledge base, a suggestion rule matching and combination process is performed to generate personalized pregnancy preparation suggestions and output them to the user. Specifically, this includes: performing expert knowledge base matching based on the multi-level comparison results to obtain suggestion rule entries; performing suggestion content combination processing based on the matched suggestion rule entries to generate a preliminary suggestion set; performing suggestion importance sorting processing based on the priority order triggered by threshold comparison to determine the display order of the preliminary suggestion set; obtaining user personalized characteristics, optimizing suggestion expression based on preset suggestion rules, and generating personalized pregnancy preparation suggestions.

5. A pregnancy preparation guidance system for individual users according to claim 4, characterized in that, The preset data preprocessing procedure for the raw multi-source data specifically includes: Based on preset data integrity rules and numerical range rules, data validation processing is performed on the original multi-source data to obtain a valid dataset. Anomaly identification and cleaning processes are performed on the valid data set to obtain a cleaned data set; Perform a standardization transformation on the cleaned dataset to obtain a standardized dataset; The standardized dataset is used to perform classification and storage processing, and the data is stored in the user profile database according to physiological parameters, psychological parameters, and lifestyle parameters, respectively.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium includes a method program for guiding fertility preparation for individual users, which, when executed by a processor, implements the steps of the method for guiding fertility preparation for individual users as described in any one of claims 1 to 3.

Images