Male infertility factor multi-dimensional data processing system

Abstract

The invention relates to the technical field of data processing, in particular to a male infertility factor multi-dimensional data processing system which comprises an abnormal mode recognition module, a factor association analysis module, a factor influence evaluation module and an individual risk analysis module. According to the method, by comparing the deviation degree of the patient data and the normal data set, the abnormal data points are effectively marked, the sensitivity of abnormal recognition is enhanced, the analysis depth of data dimensions is increased by summarizing frequent co-occurrence factors in the data, the association between the factors is more obvious, and a basis is provided for subsequent risk assessment; by quantifying the influence of the factor combinations, allocating a clear influence weight for each combination and quantitatively evaluating the infertility risk of the individual patient, the infertility risks of different patients can be effectively measured and compared, the data utilization rate and the processing efficiency are improved, subsequent medical decision making is effectively assisted, and the medical service quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a multidimensional data processing system for male infertility factors. Background Art

[0002] The field of data processing technology covers a wide range of computing methods and processing mechanisms for organizing, managing, analyzing and transforming data to extract valuable information and knowledge. The field of data processing includes data storage and query technology, as well as data mining, machine learning, statistical analysis and big data technology. Data processing technology is used in a variety of industries, such as financial services, healthcare, biotechnology, e-commerce and social media. The key is how to effectively process and analyze massive data sets to support decision making, discover new insights and optimize business processes.

[0003] Among them, the multidimensional data processing system for male infertility factors is a technical solution for analyzing and processing multidimensional data sets related to male infertility. The system uses data analysis tools to integrate and analyze data collected from multiple sources, such as clinical data, genetic information, lifestyle data, etc. The main purpose of the system is to help doctors and researchers better understand the potential causes of infertility through in-depth analysis of data, thereby assisting in making treatment decisions and improving treatment outcomes.

[0004] Traditional processing systems have obvious deficiencies when dealing with complex and multi-dimensional data sets. Traditional systems usually rely on simple statistical analysis and linear processing. When dealing with complex biomedical problems such as male infertility, they cannot effectively identify and analyze potential patterns and complex associations in the data. For example, data analysis in existing technologies often ignores the potential associations between multi-source data, resulting in an inability to fully analyze the cause of the disease. In addition, existing methods are also incapable of verifying the integrity of data and detecting anomalies, which limits the assurance of data quality and increases research errors, which may lead to inaccurate treatment decisions and low recognition efficiency in actual operations. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a multidimensional data processing system for male infertility factors.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a multidimensional data processing system for male infertility factors, the system comprising:

[0007] The abnormal pattern recognition module is based on multi-source data of male patients, including physiological status data, genetic information and lifestyle data. It verifies the integrity of the data structure, extracts the mean and standard deviation of normal male data, evaluates the deviation between the current male patient data point and the normal data, marks the data points with abnormal deviation, and obtains the abnormal data identification list;

[0008] The factor association analysis module extracts the frequency of occurrence of factors in the data based on the abnormal data identification list and the data items related to the abnormal markers, and uses a cluster analysis method to summarize the frequently co-occurring factor combinations into dominant factor combinations, extracts the dominant factor combinations of the patients, and obtains dominant factor combination information;

[0009] The factor impact assessment module is based on the dominant factor combination information, according to the frequency of occurrence of the factor combination in the database and the influence on male infertility, and quantifies the risk impact value of the factor combination in combination with the type and number of the dominant factor combination of the patient, and generates risk impact information;

[0010] The individual risk analysis module assesses the patient's infertility risk based on the risk impact information and the patient's individual age.

[0011] The present invention is improved in that the method for extracting the mean value and standard deviation of normal male data is:

[0012] Based on the medical database, extract normal male data, which includes physiological status data, genetic information data and lifestyle data;

[0013] Based on the normal male data, by the formula:

[0014]

[0015] and

[0016]

[0017] Calculate the mean and standard deviation of normal male data to obtain the normal mean and standard deviation extraction results, where: is the average value, is the standard deviation, For the The weight of the data point, For the The value of the data point, is the total number of data points.

[0018] The present invention is improved in that the steps of obtaining the abnormal data identification list are:

[0019] Based on the normal mean and standard deviation extraction results, the multi-source data of the current male patient is extracted, and the multi-source data includes physiological state data, genetic information and lifestyle data. The multi-source data of the current male patient is compared with the mean and standard deviation of the normal male data, and the formula is used:

[0020]

[0021] Calculate the data deviation, where Representative The deviation of the data points, It is The actual observed value of the data points, is the average value, is the standard deviation;

[0022] Based on the data deviation, the data is compared with a preset deviation threshold, and data points whose deviation exceeds the preset threshold are marked to obtain an abnormal data identification list.

[0023] The present invention is improved in that the method for extracting the frequency and pattern of occurrence of factors in the data is:

[0024] Based on the abnormal data identification list, extracting data entries marked as abnormal from the database, the entries containing factors associated with the patient's infertility symptoms and status, and obtaining data entry extraction results;

[0025] Based on the data entry extraction results, data traversal is performed, the number of occurrences of each factor is recorded, a factor frequency table is constructed, each factor and its number of occurrences in the abnormal data are mapped, and the total number of occurrences of each factor in all abnormal entries is accumulated to obtain factor frequency information.

[0026] The present invention is improved in that the step of obtaining the dominant factor combination information is:

[0027] Based on the frequency information of the factors, the formula is:

[0028]

[0029] Calculate the weighted score for the factor combination, where Is a factor and The weighted score of co-occurrence, Is a factor and The number of co-occurrences, and The factors are and The number of independent occurrences of is the total number of data entries in the dataset;

[0030] Based on the weighted score of the factor combination, a comparison is made with a preset score threshold, and the factor combination whose weighted score exceeds the score threshold is marked as a dominant factor combination to obtain dominant factor combination information.

[0031] The present invention is improved in that the method for assigning corresponding influence weights to each factor combination is:

[0032] Based on the dominant factor combination information, the frequency of occurrence of each factor combination in male infertility treatment records is extracted from the database, and clinical impact data on male infertility associated with the factor combination is collected, including patient treatment response and infertility incidence, to obtain factor weight association data;

[0033] Based on the factor weights associated with the data, by the formula:

[0034]

[0035] Calculate the influence weight of the factor combination and obtain the influence weight distribution result, where: It is a combination of factors The influence weight of It is a combination of factors The frequency of occurrence in the database, It is a combination of factors Impact score on male infertility, Represents the combined set of all factors considered.

[0036] The present invention is improved in that the step of obtaining the risk impact information is:

[0037] Based on the dominant factor combination information and the impact weight allocation result, extract the impact weight corresponding to the dominant factor combination of the patient to obtain risk impact association data;

[0038] Based on the risk impact associated data, through the formula:

[0039]

[0040] Calculate the patient's risk impact value to obtain risk impact information, where: is the patient's risk impact value, Combination of factors The influence weight of Patient factor combination The frequency of occurrence, Combination of factors The clinical relevance coefficient, Combination of factors Stability indicators in the database, A combination of factors that are dominant for the patient.

[0041] The present invention is improved in that the steps of obtaining the individual infertility risk assessment result are:

[0042] Based on the risk impact information, extracting age data of individual patients to obtain infertility risk associated data;

[0043] Based on the infertility risk association data, the formula:

[0044]

[0045] Calculate the infertility risk score to assess the patient's infertility risk, including: is the infertility risk score, is the patient's risk impact value, is the patient's age, is the normalization constant.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are:

[0047] In the present invention, by comparing the deviation between patient data and normal data sets, abnormal data points are effectively marked, the sensitivity of abnormality identification is enhanced, and by summarizing the frequently co-occurring factors in the data, the analysis depth of the data dimension is increased, making the correlation between factors more obvious, which provides a basis for subsequent risk assessment. By quantifying the influence of the combination of factors, a clear influence weight is assigned to each combination, and the infertility risk of individual patients is quantitatively assessed. This can effectively measure and compare the infertility risks of different patients, improve data utilization and processing efficiency, effectively assist in subsequent medical decision-making, and improve the quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a system flow chart of the present invention;

[0049] Figure 2 Flow chart for extracting the mean and standard deviation of normal male data for the present invention;

[0050] Figure 3 A flowchart of obtaining an abnormal data identification list for the present invention;

[0051] Figure 4 A flow chart of the frequency of occurrence of factors in data extracted by the present invention;

[0052] Figure 5 A flow chart for obtaining dominant factor combination information of the present invention;

[0053] Figure 6 A flow chart of the present invention for allocating corresponding influence weights to each factor combination;

[0054] Figure 7 A flow chart for obtaining risk impact information for the present invention;

[0055] Figure 8 Flowchart for assessing the risk of infertility in an individual patient for the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0058] See also Figure 1 The present invention provides a technical solution: a multi-dimensional data processing system for male infertility factors, the system comprising:

[0059] The abnormal pattern recognition module is based on multi-source data of male patients, including physiological status data, genetic information and lifestyle data. It verifies the integrity of the data structure, extracts the mean and standard deviation of normal male data, evaluates the deviation between the current male patient data point and the normal data, marks the data points with abnormal deviation, and obtains the abnormal data identification list;

[0060] The factor association analysis module is based on the abnormal data identification list and the data items related to the abnormal markers, extracts the frequency of occurrence of factors in the data, and uses the cluster analysis method to summarize the frequently co-occurring factor combinations into the dominant factor combinations, extracts the dominant factor combinations of patients, and obtains the dominant factor combination information;

[0061] The factor impact assessment module is based on the dominant factor combination information. According to the frequency of occurrence of the factor combination in the database and its influence on male infertility, it assigns a corresponding impact weight to each factor combination. Combined with the type and number of the patient's dominant factor combination, it quantifies the risk impact value of the factor combination and generates risk impact information.

[0062] The individual risk analysis module assesses the patient's infertility risk based on risk impact information and the patient's individual age.

[0063] The abnormal data identification list includes the timestamp, deviation degree and data dimension identification of the data point. The dominant factor combination information includes the correlation strength, occurrence frequency and potential impact between factors. The risk impact information includes the impact weight, impact degree and corresponding probability value of each factor combination. The individual infertility risk assessment results include the individual risk level and recommended preventive measures.

[0064] See also Figure 2 , the method to extract the mean and standard deviation of normal male data is:

[0065] Based on the medical database, extract normal male data, which includes physiological status data, genetic information data and lifestyle data;

[0066] Based on normal male data, through the formula:

[0067]

[0068] and

[0069]

[0070] Calculate the mean and standard deviation of normal male data to obtain the normal mean and standard deviation extraction results, where: is the average value, is the standard deviation, For the The weight of the data point, For the The value of the data point, is the total number of data points.

[0071] formula:

[0072]

[0073] and

[0074]

[0075] Parameter meaning and acquisition method:

[0076] :This is the The weight of each data point. The weight is determined based on the reliability and importance of the data source. For example, data points obtained from core clinical trials will receive higher weights, while routine physical examination data will receive lower weights. The weights can be set through expert evaluation.

[0077] :This is the The actual observed values ​​of data points, such as heart rate, blood pressure, and testosterone levels, are obtained directly from the patient's clinical data through the medical record system.

[0078] : This is the total number of data points, which indicates the number of data points in the dataset under consideration. This value can be directly obtained by counting the number of records that meet the conditions in the database.

[0079] Calculation example:

[0080] There are three data points, and their specific values ​​and weights are as follows: , , , , , .

[0081] Calculation of the average value:

[0082]

[0083] Calculation of standard deviation:

[0084]

[0085]

[0086]

[0087]

[0088]

[0089] The calculated average It represents the average value of this set of data taking into account the reliability of the data source. The calculated standard deviation , which shows the dispersion of data points around the weighted mean. This approach takes into account the different importance of data by introducing weights, thereby more accurately reflecting the statistical characteristics of the data set.

[0090] See also Figure 3 , the steps to obtain the abnormal data identification list are:

[0091] Based on the normal mean and standard deviation extraction results, the multi-source data of the current male patients are extracted. The multi-source data includes physiological status data, genetic information and lifestyle data. The multi-source data of the current male patients are compared with the mean and standard deviation of the normal male data. The formula is:

[0092]

[0093] Calculate the data deviation, where Representative The deviation of the data points, It is The actual observed value of the data points, is the average value, is the standard deviation;

[0094] Based on the data deviation, it is compared with the preset deviation threshold, and the data points whose deviation exceeds the preset threshold are marked to obtain an abnormal data identification list.

[0095] formula:

[0096]

[0097] Parameter details and how to obtain them:

[0098] : No. The actual observed values ​​of a data point, such as heart rate, blood pressure, and testosterone levels. The data is usually obtained directly from medical records or health monitoring devices.

[0099] : Average value, calculated by the previous method.

[0100] : Standard deviation, calculated as above.

[0101] Calculation example:

[0102] Assume an observation with three data points , ,and , and the weighted average and weighted standard deviation . Set the deviation threshold .

[0103] Calculate the adjusted bias for each data point :

[0104]

[0105]

[0106]

[0107] In this case, the data points and The deviation of exceeds the set threshold and is therefore marked as an anomaly. This indicates that the data point deviates significantly from the average level of normal male data.

[0108] See also Figure 4 , the method to extract the frequency and pattern of factors in the data is:

[0109] Based on the abnormal data identification list, extracting data entries marked as abnormal from the database, the entries containing factors associated with the patient's infertility symptoms and status, and obtaining data entry extraction results;

[0110] Based on the data entry extraction results, data traversal is performed, the number of occurrences of each factor is recorded, a factor frequency table is constructed, each factor and its number of occurrences in the abnormal data are mapped, and the total number of occurrences of each factor in all abnormal entries is accumulated to obtain the factor frequency information.

[0111] See also Figure 5 , the steps to obtain the dominant factor combination information are:

[0112] Based on the factor frequency information, the formula is:

[0113]

[0114] Calculate the weighted score for the factor combination, where Is a factor and The weighted score of co-occurrence, Is a factor and The number of co-occurrences, and The factors are and The number of independent occurrences of is the total number of data entries in the dataset;

[0115] The weighted score of the factor combination is compared with a preset score threshold, and the factor combination whose weighted score exceeds the score threshold is marked as a dominant factor combination to obtain dominant factor combination information.

[0116] formula:

[0117]

[0118] Parameter details and how to obtain them:

[0119] :Indicates factors and The number of times they co-occur in the data set. and The factor can be calculated by the number of co-occurring events, for example, sleep abnormalities and androgen abnormalities.

[0120] and :Represents factors and The number of independent occurrences in the entire data set. Obtained by individually counting the frequency of each factor appearing in all abnormal data entries.

[0121] : Represents the total number of data entries in the entire dataset. This is the total number obtained by counting all the entries in the dataset.

[0122] Calculation example:

[0123] Suppose in a certain abnormal data set, the factor and appeared 50 times together ( ),factor Appeared 100 times independently ( ),factor Appeared 150 times independently ( ), the entire data set has a total of 1000 data ( ).

[0124] calculate :

[0125] formula:

[0126]

[0127]

[0128]

[0129]

[0130]

[0131]

[0132] Calculation results Indication factors and The co-occurrence frequency is significantly higher than the independent occurrence frequency. A high value of indicates that this co-occurrence is unlikely to occur by chance. Through this calculation method, we can identify the combination of factors in abnormal data that are more statistically significant than independent occurrences, which helps to discover potential correlations and influencing factors and provide data support for in-depth analysis and decision-making.

[0133] See also Figure 6 , the method of assigning corresponding influence weights to each factor combination is:

[0134] Based on the dominant factor combination information, the frequency of each factor combination in the male infertility treatment records was extracted from the database, and the clinical impact data of male infertility associated with the factor combination was collected, including patient treatment response and infertility incidence, to obtain factor weight association data;

[0135] Based on the factor weights, the data is associated with the formula:

[0136]

[0137] Calculate the influence weight of the factor combination and obtain the influence weight distribution result, where: It is a combination of factors The influence weight of It is a combination of factors The frequency of occurrence in the database, It is a combination of factors Impact score on male infertility, Represents the combined set of all factors considered.

[0138] formula:

[0139]

[0140] Parameter details and how to obtain them

[0141] : Indicates a combination of factors The frequency of occurrence in the database. It is calculated by the number of times the combination occurs.

[0142] : Indicates a combination of factors The impact score on male infertility. This score is derived from historical data and related research results, through expert evaluation or statistical analysis methods, and reflects the severity of the impact of this combination of factors on the condition.

[0143] Calculation example:

[0144] Set in the database, there are three factors combined , ,and The frequency and impact scores are as follows: , , , , , .

[0145] Calculate the impact weight of each factor combination:

[0146] Calculate the normalization factor:

[0147]

[0148]

[0149]

[0150]

[0151] Calculate separately , ,and Weight:

[0152]

[0153]

[0154]

[0155] Calculation results , and Displays the relative importance of each factor combination after considering its frequency and impact score on male infertility. The weights can be used for further analysis and decision making, helping the medical team prioritize and address factor combinations with higher impact.

[0156] See also Figure 7 , the steps to obtain risk impact information are:

[0157] Based on the dominant factor combination information and the impact weight allocation results, the impact weight corresponding to the dominant factor combination of the patient is extracted to obtain the risk impact association data;

[0158] Based on the risk impact correlation data, the formula is:

[0159]

[0160] Calculate the patient's risk impact value to obtain risk impact information, where: is the patient's risk impact value, Combination of factors The influence weight of Patient factor combination The frequency of occurrence, Combination of factors The clinical relevance coefficient, Combination of factors Stability indicators in the database, A combination of factors that are dominant for the patient.

[0161] formula:

[0162]

[0163] Parameter details and how to obtain them:

[0164] : Factor combination The influence weight of is calculated in the previous step.

[0165] : Combination of patient factors Frequency of occurrence. Calculated based on the number of times a combination of factors occurs in a patient's medical records.

[0166] : Factor combination The clinical relevance coefficient is determined by statistical analysis based on clinical trial results and patient treatment response data, and is used to adjust the weight of the combination of factors on the disease.

[0167] : Factor combination Stability index in the database. This is calculated by analyzing the variability of the frequency of occurrence of factor combinations at different times and in different patient groups, and is used to assess the volatility and reliability of the data.

[0168] : The patient's dominant factor combination set. This set is a combination of key factors identified based on the patient's medical records and historical treatment data, reflecting the factors that have the greatest impact on the patient's health status.

[0169] Calculation example:

[0170] Assume that the patient has a combination of three dominant factors , ,and , the parameter values ​​are as follows: , , , , , , , , , , , .

[0171] Calculate the contribution of each factor combination:

[0172]

[0173]

[0174]

[0175] Sum the contributions of all factor combinations to get the total risk impact value :

[0176]

[0177] Calculated total risk impact value It represents the patient's risk assessment of the combination of factors after considering the frequency of occurrence, clinical relevance and stability of the factor combination. This value can help the medical team determine the patient's health risk level, thereby conducting more accurate treatment planning and health management.

[0178] See also Figure 8 , the steps to obtain the individual infertility risk assessment results are:

[0179] Based on the risk impact information, the age data of individual patients was extracted to obtain the infertility risk association data;

[0180] Based on the infertility risk association data, the formula is:

[0181]

[0182] Calculate the infertility risk score to assess the patient's infertility risk, including: is the infertility risk score, is the patient's risk impact value, is the patient's age, is the normalization constant.

[0183] formula:

[0184]

[0185] Parameter details and how to obtain them:

[0186] : The patient’s risk impact value, calculated in the previous step.

[0187] : The patient’s age, which is obtained directly from the patient’s medical record. Age is an important parameter for adjusting risk assessment, reflecting physiological changes that may increase certain health risks with age.

[0188] : is a normalization constant used to adjust the calculated risk assessment results to keep them within a reasonable range. This constant is determined based on historical data and normalization needs.

[0189] Calculation Example

[0190] Set the patient's parameters as follows: (the total risk impact value calculated previously), (age of the patient), (normalization constant).

[0191] Calculate the logarithmic effect of age:

[0192]

[0193] calculate :

[0194]

[0195]

[0196]

[0197]

[0198] Calculated infertility risk assessment results , which represents the patient's infertility risk score for a given risk impact value and age. This value is low, indicating that the patient's infertility risk is relatively small given the current risk factors and age. This calculation provides a quantitative way to assess and interpret a patient's health risk, allowing the medical team to make more precise risk management and treatment decisions based on specific values.

[0199] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A multidimensional data processing system for male infertility factors, characterized in that: The system comprises: The abnormal pattern recognition module is based on multi-source data of male patients, including physiological status data, genetic information and lifestyle data. It verifies the integrity of the data structure, extracts the mean and standard deviation of normal male data, evaluates the deviation between the current male patient data point and the normal data, marks the data points with abnormal deviation, and obtains the abnormal data identification list; The factor association analysis module extracts the frequency of occurrence of factors in the data based on the abnormal data identification list and the data items related to the abnormal markers, and uses a cluster analysis method to summarize the frequently co-occurring factor combinations into dominant factor combinations, extracts the dominant factor combinations of the patients, and obtains dominant factor combination information; The factor impact assessment module is based on the dominant factor combination information, according to the frequency of occurrence of the factor combination in the database and the influence on male infertility, and quantifies the risk impact value of the factor combination in combination with the type and number of the dominant factor combination of the patient, and generates risk impact information; The individual risk analysis module assesses the patient's infertility risk based on the risk impact information and the patient's individual age.

2. The multidimensional data processing system for male infertility factors according to claim 1, characterized in that: The method for extracting the mean and standard deviation of normal male data is: Based on the medical database, extract normal male data, which includes physiological status data, genetic information data and lifestyle data; Based on the normal male data, by the formula: and ； Calculate the mean and standard deviation of normal male data to obtain the normal mean and standard deviation extraction results, where: is the average value, is the standard deviation, For the The weight of the data point, For the The value of the data point, is the total number of data points.

3. The multidimensional data processing system for male infertility factors according to claim 2, characterized in that: The steps for obtaining the abnormal data identification list are: Based on the normal mean and standard deviation extraction results, the multi-source data of the current male patient is extracted, and the multi-source data includes physiological state data, genetic information and lifestyle data. The multi-source data of the current male patient is compared with the mean and standard deviation of the normal male data, and the formula is used: ； Calculate the data deviation, where Representative The deviation of the data points, It is The actual observed value of the data points, is the average value, is the standard deviation; Based on the data deviation, the data is compared with a preset deviation threshold, and data points whose deviation exceeds the preset threshold are marked to obtain an abnormal data identification list.

4. The multidimensional data processing system for male infertility factors according to claim 1, characterized in that: The method for extracting the frequency and pattern of factors in the data is: Based on the abnormal data identification list, extracting data entries marked as abnormal from the database, the entries containing factors associated with the patient's infertility symptoms and status, and obtaining data entry extraction results; Based on the data entry extraction results, data traversal is performed, the number of occurrences of each factor is recorded, a factor frequency table is constructed, each factor and its number of occurrences in the abnormal data are mapped, and the total number of occurrences of each factor in all abnormal entries is accumulated to obtain factor frequency information.

5. The multidimensional data processing system for male infertility factors according to claim 4, characterized in that: The steps for obtaining the dominant factor combination information are as follows: Based on the frequency information of the factors, the formula is: ； Calculate the weighted score for the factor combination, where Is a factor and The weighted score of co-occurrence, Is a factor and The number of co-occurrences, and The factors are and The number of independent occurrences of is the total number of data entries in the dataset; Based on the weighted score of the factor combination, a comparison is made with a preset score threshold, and the factor combination whose weighted score exceeds the score threshold is marked as a dominant factor combination to obtain dominant factor combination information.

6. The multidimensional data processing system for male infertility factors according to claim 1, characterized in that: The method for assigning corresponding influence weights to each factor combination is: Based on the dominant factor combination information, the frequency of occurrence of each factor combination in male infertility treatment records is extracted from the database, and clinical impact data on male infertility associated with the factor combination is collected, including patient treatment response and infertility incidence, to obtain factor weight association data; Based on the factor weights associated with the data, by the formula: ； Calculate the influence weight of the factor combination and obtain the influence weight distribution result, where: It is a combination of factors The influence weight of It is a combination of factors The frequency of occurrence in the database, It is a combination of factors Impact score on male infertility, Represents the combined set of all factors considered.

7. The multidimensional data processing system for male infertility factors according to claim 6, characterized in that: The steps for obtaining the risk impact information are: Based on the dominant factor combination information and the impact weight allocation result, extract the impact weight corresponding to the dominant factor combination of the patient to obtain risk impact association data; Based on the risk impact associated data, through the formula: ； Calculate the patient's risk impact value to obtain risk impact information, where: is the patient's risk impact value, Factor combination The influence weight of Patient factor combination The frequency of occurrence, Representation factor combination The clinical relevance coefficient, Representation factor combination Stability indicators in the database, A combination of factors that are dominant for the patient.

8. The multidimensional data processing system for male infertility factors according to claim 1, characterized in that: The steps for obtaining the individual infertility risk assessment result are: Based on the risk impact information, extracting age data of individual patients to obtain infertility risk associated data; Based on the infertility risk association data, the formula: ； Calculate the infertility risk score to assess the patient's infertility risk, including: is the infertility risk score, is the patient's risk impact value, is the patient's age, is the normalization constant.

Images