Traditional Chinese medicine information packet clustering method, device and equipment and computer storage medium

Abstract

The present application relates to artificial intelligence technology, disclose a kind of traditional Chinese medicine information grouping clustering method, comprising: the history information of the generated traditional Chinese medicine medical system is extracted to feature, obtain the medical project label of the traditional Chinese medicine medical system;The medical project label is carried out primary clustering, obtain the primary grouping label of the medical project label;According to the primary grouping label determines grouping project, generates the patient matrix of the grouping project, calculates the clustering index of the patient matrix, using the clustering index is optimized to the preset grouping clustering model, obtain the optimized grouping clustering model, using the optimized grouping clustering model is grouped and clustered to target information.In addition, the present application also relates to blockchain technology, and data list can be stored in the node of blockchain.The present application also proposes a kind of traditional Chinese medicine information grouping clustering device, electronic equipment and storage medium.The present application can improve the efficiency of traditional Chinese medicine information grouping clustering.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for grouping and clustering traditional Chinese medicine information. Background Technology

[0002] While Western medicine's diagnosis-related group (DRG) payment system is relatively mature, TCM's DRG payment system is still in the exploratory stage. The most crucial aspect of building a TCM DRG payment system is how to group TCM patients in the same way as Western medicine. Currently, TCM treatment systems can be broadly divided into 10 categories, such as external TCM treatments, prepared Chinese medicines, and herbal decoctions, with each category encompassing dozens or even hundreds of treatment sub-items.

[0003] Currently, the grouping of TCM diseases is based on the idea of ​​"similar clinical characteristics and similar resource consumption," which mainly relies on empiricism to group TCM information. This makes it difficult to avoid information omissions and duplications during the grouping process, and may also lead to incorrect information grouping. Therefore, how to improve the efficiency of TCM information grouping and clustering has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method, apparatus, and computer-readable storage medium for grouping and clustering traditional Chinese medicine information, with the main purpose of solving the problem of low efficiency in grouping and clustering traditional Chinese medicine information.

[0005] To achieve the above objectives, the present invention provides a method for grouping and clustering traditional Chinese medicine information, comprising:

[0006] Generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system;

[0007] The medical item tags are clustered in a first-level manner according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags;

[0008] The grouping items of the TCM medical system are determined based on the primary grouping labels, and one of the items in the grouping items is selected as the target item.

[0009] A patient matrix for the target project is generated based on the preset patient identity identifier and the first-level group label. The clustering index of the patient matrix is ​​calculated, and the preset grouping clustering model is optimized using the clustering index to obtain the optimized grouping clustering model.

[0010] The target information in the TCM medical system is obtained, and the optimized grouping clustering model is used to group and cluster the target information to obtain the grouped and clustered target information.

[0011] Optionally, the step of extracting features from the historical information to obtain medical item tags for the traditional Chinese medicine medical system includes:

[0012] The historical information is cleaned to obtain standard information of the historical information;

[0013] The standard information is segmented into words to obtain the information words of the standard information;

[0014] The information is segmented into words and then vectorized to obtain the word segmentation vectors.

[0015] The word segmentation vectors are concatenated to obtain the medical item tags of the traditional Chinese medicine medical system.

[0016] Optionally, the step of performing first-level clustering of the medical item tags according to a preset grouping clustering model to obtain first-level grouping tags for the medical item tags includes:

[0017] The medical item labels are assigned numbers to obtain the item numbers of the medical item labels;

[0018] The objective function, decision variables, and constraints for grouping and clustering the project numbers are determined according to the preset grouping and clustering model.

[0019] The project numbers are grouped and clustered according to the objective function, the decision variables, and the constraints to obtain the initial group numbers of the project numbers, and the medical project labels corresponding to the initial group numbers are determined as the first-level group labels.

[0020] Optionally, the objective function is as follows:

[0021]

[0022] Where, min L is the minimum difference in information among patients in the same primary group label, c represents the total number of groups for the primary group label, i is the identifier of the primary group label, n represents the total number of patients, and k is the identifier of the patient. It is an outlier function, and... It depends on the value. Indicates selection The larger of the two, and 0. This represents the total information value of each patient under the first-level group label of the i-th group, m represents the total number of medical item labels, j is the identifier of the medical item label, and ub i It is an indicator that measures the degree of clustering of the total information values ​​of each patient under the primary group label of the i-th group, w ijX represents the affiliation between the j-th medical item label and the i-th group. jk This represents the information value of the medical item label for the k-th patient in the j-th case.

[0023] Optionally, calculating the clustering index of the patient matrix includes:

[0024] Based on the patient matrix, the information values ​​of the patient's medical item tags are sorted to obtain a sequence list of the information values;

[0025] The information value is quartile-marked according to the sequence list to obtain multiple quartile groups of the information value;

[0026] The clustering index of the patient matrix is ​​calculated based on the quartile group of the information value and a preset quartile distance algorithm.

[0027] Optionally, calculating the clustering index of the patient matrix includes:

[0028] The clustering index of the patient matrix is ​​calculated using the following quartile distance algorithm:

[0029]

[0030] Where i is the identifier of the target project, ub i It is the clustering index of the patient matrix, x i This is the patient matrix for each patient under the target item in the i-th group. This represents the matrix mean of all the patients mentioned under the target item. Let l represent the matrix variance of all patients under the target item, where l is the total number of target items.

[0031] Optionally, optimizing the preset grouping clustering model using the clustering index to obtain an optimized grouping clustering model includes:

[0032] S11. Determine the first-level outliers when performing first-level clustering using the preset grouping clustering model based on the clustering index, and perform iterative clustering on the first-level grouping labels based on the first-level outliers;

[0033] S12. When the first-level outlier is greater than or equal to the preset threshold, repeat step S11. When the first-level outlier is less than the preset threshold, stop the iterative clustering of the first-level group labels.

[0034] S13. Generate anomaly functions based on outliers at each level during iterative clustering according to the first-level grouping labels;

[0035] S14. The constraint conditions are used as a penalty term for the objective function to modify the objective function, thereby obtaining the modified objective function;

[0036] S15. Optimize the preset grouping clustering model according to the modified objective function and the abnormal function to obtain the optimized grouping clustering model.

[0037] To address the above problems, the present invention also provides a traditional Chinese medicine information grouping and clustering device, the device comprising:

[0038] The feature extraction module is used to generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system.

[0039] The first-level clustering module is used to perform first-level clustering on the medical item tags according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags;

[0040] The grouping item module is used to determine the grouping items of the TCM medical system based on the first-level grouping labels, and select one of the grouping items as the target item;

[0041] The model optimization module is used to generate a patient matrix for the target project based on the preset patient identity identifier and the first-level grouping label, calculate the clustering index of the patient matrix, and optimize the preset grouping clustering model using the clustering index to obtain the optimized grouping clustering model.

[0042] The grouping and clustering module is used to obtain target information from the TCM medical system, and to group and cluster the target information using the optimized grouping and clustering model to obtain the grouped and clustered target information.

[0043] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0044] At least one processor; and,

[0045] A memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the TCM information grouping and clustering method described above.

[0047] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned method for grouping and clustering traditional Chinese medicine information.

[0048] This invention extracts features from historical information of a generated Traditional Chinese Medicine (TCM) medical system to obtain medical item tags. This avoids excessive noise data in the historical information, which can lead to poor generalization ability. Retaining appropriate noise data helps prevent overfitting. The medical item tags are then clustered at a first level according to a preset grouping clustering model to determine the grouped items of the TCM medical system. By flexibly selecting an outlier function to represent the different degrees of loss caused by outliers, the parameters in the preset grouping clustering model can be better described by the outliers. A patient matrix for each grouped item is generated, and the clustering index of the patient matrix is ​​calculated. The preset grouping clustering model is then optimized using the clustering index to obtain an optimized grouping clustering model. This optimized model considers the distribution characteristics of the quantity, amount, and number of people in each grouped item reflected in a large amount of historical information from the TCM medical system, fully exploring the correlation between each grouped item. Therefore, this invention proposes a method, device, electronic device, and computer-readable storage medium for TCM information grouping clustering, which can solve the problem of low efficiency in TCM information grouping clustering. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating a method for grouping and clustering traditional Chinese medicine information according to an embodiment of the present invention.

[0050] Figure 2 This is a schematic diagram of the process for generating first-level group labels according to an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the process for calculating clustering metrics according to an embodiment of the present invention;

[0052] Figure 4 This is a functional block diagram of a TCM information grouping and clustering device provided in an embodiment of the present invention;

[0053] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the traditional Chinese medicine information grouping and clustering method according to an embodiment of the present invention.

[0054] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0055] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0056] This application provides a method for grouping and clustering traditional Chinese medicine (TCM) information. The executing entity of this TCM information grouping and clustering method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the TCM information grouping and clustering method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0057] Reference Figure 1 The diagram shown is a flowchart illustrating a method for grouping and clustering traditional Chinese medicine information according to an embodiment of the present invention. In this embodiment, the method includes:

[0058] S1. Generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system.

[0059] In this embodiment of the invention, the historical information of the TCM medical system includes, but is not limited to, patient information, the medical system classification of the TCM medical system, patient consumption information, patient payment information, patient account balance, payment data, and management data. The patient information mainly consists of the patient's basic personal information, such as age, employment information, income information, and family information. The payment data includes various information about the patient's access to medical services, which can record the patient's medical behavior relatively completely and is a relatively important and unique data link in the medical insurance information system. The management data is some data that can support medical insurance decision-making and management based on existing patient data and payment data, including information on fund income and expenditure, expenses, and disease types at various levels.

[0060] In detail, the services include external application of traditional Chinese medicine, enemas, fumigation and washing, acupuncture, massage, local medication, auricular acupuncture, scraping, acupoint application, cupping, ultrasound introduction of traditional Chinese medicine, sound therapy, fumigation, acupoint injection, Bian stone therapy, hook therapy, balance acupuncture, fire needle therapy, abdominal acupuncture, heat-sensitive moxibustion, thunder-fire moxibustion, etc.; patient information such as age, employment information, income information, and family information; and department labels such as traditional Chinese medicine clinics, acupuncture rooms, massage rooms, physiotherapy rooms, rehabilitation rooms, and health care rooms. The service items, department labels, and patient information all belong to the medical project labels.

[0061] In this embodiment of the invention, the step of extracting features from the historical information to obtain medical item tags for the traditional Chinese medicine medical system includes:

[0062] The historical information is cleaned to obtain standard information; the standard information is segmented to obtain information segments; the information segments are vectorized to obtain segmented vectors; the segmented vectors are concatenated to obtain medical item tags for the TCM medical system.

[0063] In detail, the data cleaning includes: missing value processing, format and content processing, and removal of duplicate and noisy data. Specifically, the missing value processing involves removing fields, filling in missing values, and re-retrieving data from the historical information based on the missing rate and importance. The format and content processing...

[0064] In this embodiment of the invention, the step of segmenting the standard information to obtain information segmentation of the standard information includes: using a preset text annotation tool to annotate the standard information with states to obtain a set of state values; obtaining the initial probability of each state in the set of state values ​​according to a preset initial state probability distribution, and generating an initial matrix of the set of state values ​​using the initial probabilities; calculating the initial matrix using a preset state transition probability formula to obtain a state transition probability distribution matrix; calculating the state transition probability distribution matrix using a preset emission probability formula to obtain an observation state probability matrix; and segmenting the standard information according to the observation state probability matrix to obtain information segmentation of the standard information.

[0065] In detail, the preset text annotation tool can utilize BasicFinderSaas, Doccano, Brat, etc.; the state annotation refers to the position of the word sequence in the sentence, for example: B represents the beginning character of the word, M represents the middle character of the word, E represents the end character of the word, and S represents a single character forming a word. When the input is "Xiaoming graduated with a master's degree from the Institute of Computing Technology, Chinese Academy of Sciences", the output state sequence is "BEBEBMEBEBMEBES". Based on this state sequence, we can perform word segmentation: "BE / BE / BME / BE / BME / BE / S". Therefore, the standard information is segmented into the following words: "Xiaoming / Master / Graduated from / China / Academy / Computing / Institute".

[0066] In detail, the word2vec algorithm and the glove algorithm can be used to vectorize the information after word segmentation.

[0067] In detail, feature extraction of the historical information is performed to prevent excessive noise data from leading to poor generalization ability, and appropriate noise data helps to prevent overfitting.

[0068] S2. Perform first-level clustering on the medical item tags according to the preset grouping clustering model to obtain the first-level grouping tags of the medical item tags.

[0069] In this embodiment of the invention, multiple clustering operations are performed on the medical item tags according to a preset grouping clustering model, so that the clustering of the medical item tags meets expectations. The first-level clustering is the first clustering operation performed on the medical item tags to obtain the first-level grouping tags of the medical item tags.

[0070] In this embodiment of the invention, the reference Figure 2 As shown, the step of performing first-level clustering of the medical item tags according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags includes:

[0071] S21. Number the medical item label to obtain the item number of the medical item label;

[0072] S22. Determine the objective function, decision variables, and constraints for grouping and clustering the project numbers according to the preset grouping and clustering model;

[0073] S23. Based on the objective function, the decision variables, and the constraints, the project numbers are grouped and clustered to obtain the initial group numbers of the project numbers, and the medical project labels corresponding to the initial group numbers are determined as first-level group labels.

[0074] In detail, numbering the medical item tags involves representing them in matrix form. For example, when a medical item tag describes the consumption amount in the traditional Chinese medicine medical system, the consumption data of each patient under each medical item tag can be represented by a matrix. Assuming the traditional Chinese medicine medical system has *a* patients and *b* medical item tags, the consumption data of each patient is arranged column-wise, forming the total consumption data denoted as A. A is an m×n matrix, where the k-th column represents the consumption data of the k-th patient under each medical item tag. jk This represents the amount spent by the k-th patient on the j-th medical item tag.

[0075] Specifically, the decision variable represents the group to which each medical item label belongs, and the value range of the decision variable is 0 or 1, w ij This indicates the subordinate relationship between the j-th label and the i-th group.

[0076] Specifically, the constraint condition is that the decision variable can only take the values ​​0 or 1, and satisfies the following conditions: This further ensures that each medical item label can only be assigned to one group.

[0077] In detail, the grouping and clustering of the project numbers according to the objective function, the decision variables, and the constraints is performed using the preset grouping and clustering model. The medical project tags are input into the preset grouping and clustering model, and the first-level grouping tags of the medical project tags are obtained through a certain step of the preset grouping and clustering model. After that, the parameters of the preset grouping and clustering model are further optimized to achieve the best grouping and clustering.

[0078] In detail, the objective function is as follows:

[0079]

[0080] Where, min L is the minimum difference in information among patients in the same primary group label, c represents the total number of groups for the primary group label, i is the identifier of the primary group label, n represents the total number of patients, and k is the identifier of the patient. It is an outlier function, and... It depends on the value. Indicates selection The larger of the two, and 0. This represents the total information value of each patient under the first-level group label of the i-th group, m represents the total number of medical item labels, j is the identifier of the medical item label, and ub i It is an indicator that measures the degree of clustering of the total information values ​​of each patient under the primary group label of the i-th group, w ij X represents the affiliation between the j-th medical item label and the i-th group. jk This represents the information value of the medical item label for the k-th patient in the j-th case.

[0081] In detail, outliers represent the degree of negative impact on the aggregation process, and the outliers are represented using the outlier function. When the outlier function is... When each outlier is considered equally important, and when the outlier function is f(x) = x, it means that the larger the outlier value, the greater its impact on the degree of clustering.

[0082] Furthermore, outlier functions can be flexibly selected to account for different degrees of loss caused by outliers.

[0083] In detail, the objective function represents the desire to minimize the differences in information among patients in the same group of primary group labels, thereby ensuring that the information in the same group of primary group labels is as clustered as possible.

[0084] S3. Determine the grouping items of the TCM medical system based on the first-level grouping labels, and select one of the grouping items as the target item.

[0085] In this embodiment of the invention, the grouping items can be hierarchically classified from the primary grouping labels. First, the primary grouping labels are divided according to departments, such as traditional Chinese medicine clinics, acupuncture rooms, massage rooms, physiotherapy rooms, rehabilitation rooms, and health preservation rooms. Then, the services provided by the departments are divided. For example, the services of the health preservation room include scraping, acupoint application, cupping, ultrasound introduction of traditional Chinese medicine, sound therapy, fumigation, and acupoint injection. The services of the traditional Chinese medicine clinic include external application of traditional Chinese medicine, enemas, fumigation, acupuncture, massage, and local medication.

[0086] Generally, category labels for the departments are generated, and the grouping items of the traditional Chinese medicine medical system are determined based on the category labels.

[0087] S4. Generate a patient matrix for the target project based on the preset patient identity identifier and the first-level group label, calculate the clustering index of the patient matrix, and optimize the preset group clustering model using the clustering index to obtain the optimized group clustering model.

[0088] In this embodiment of the invention, the preset patient identification can be the patient's ID card number or the patient's medical insurance account; the clustering index is an indicator that measures the degree of information aggregation of the patient under the target item.

[0089] In detail, the patient matrix is ​​generated based on the preset patient identity identifier and the primary grouping label. Because the patient's medical insurance information can reveal when, in which department, and what services the patient received. For example, on August 31, 2022, Zhang San received acupuncture and cupping at the physiotherapy department of the Traditional Chinese Medicine outpatient clinic of Hospital A, and also received a foot massage in the massage room, spending a total of 1,000 yuan. Therefore, the online system databases of the physiotherapy department and the massage room both contain some information about Zhang San.

[0090] In this embodiment of the invention, the reference Figure 3 As shown, the calculation of the clustering index of the patient matrix includes:

[0091] S31. Sort the information values ​​of the medical item tags of the patients according to the patient matrix to obtain a sequence list of the information values;

[0092] S32. The information value is marked with quartiles according to the sequence list to obtain multiple quartile groups of the information value;

[0093] S33. Calculate the clustering index of the patient matrix based on the quartile group where the information value is located and the preset quartile distance algorithm.

[0094] In detail, the information values ​​of the patient's medical item tags can be sorted according to the amount of consumption of the patient under the medical item tags; the box plot is used to display the distribution characteristics of the data, and the plotting elements of the box plot include the upper edge, the upper quartile Q3, the median, the lower quartile Q1, the lower edge, outliers, and the interquartile range IQR, which is IQR = Q3 - Q1.

[0095] Furthermore, assuming that all patients have a total of l data points in the medical item labels of the i-th group, arranging these l numbers in ascending order yields a sequence list of information values, denoted as x. i If i = 1, 2, ..., k, then the i-th Number Let Q1 be the lower quantile. Number Let Q3 be the lower quantile, and from this we can also obtain IQR = Q3 - Q1.

[0096] In detail, if If it's not an integer, you can remember it as... for The result of rounding up. for The result of rounding down is Q1, which is calculated as follows:

[0097]

[0098] In detail, when When it's not an integer, you might as well remember it as... for The result of rounding up. for The result of rounding down is Q3, which is calculated as follows:

[0099]

[0100] In detail, when hour, Then Q1 = (2.25-2)*x2+3-2.25*x3. When 3(l+1)4 = 6.75, 3(l+1)4+ = 7, 3(l+1)4- = 6. So Q3 = (6.75-6)*x6+(7-6.75)*x7.

[0101] In this embodiment of the invention, calculating the clustering index of the patient matrix includes:

[0102] The clustering index of the patient matrix is ​​calculated using the following quartile distance algorithm:

[0103]

[0104] Where i is the identifier of the target project, ub i It is the clustering index of the patient matrix, x i This is the patient matrix for each patient under the target item in the i-th group. This represents the matrix mean of all the patients mentioned under the target item. Let l represent the matrix variance of all patients under the target item, where l is the total number of target items.

[0105] In this embodiment of the invention, optimizing the preset grouping clustering model using the clustering index to obtain an optimized grouping clustering model includes:

[0106] S11. Determine the first-level outliers when performing first-level clustering using the preset grouping clustering model based on the clustering index, and perform iterative clustering on the first-level grouping labels based on the first-level outliers;

[0107] S12. When the first-level outlier is greater than or equal to the preset threshold, repeat step S11. When the first-level outlier is less than the preset threshold, stop the iterative clustering of the first-level group labels.

[0108] S13. Generate anomaly functions based on outliers at each level during iterative clustering according to the first-level grouping labels;

[0109] S14. The constraint conditions are used as a penalty term for the objective function to modify the objective function, thereby obtaining the modified objective function;

[0110] S15. Optimize the preset grouping clustering model according to the modified objective function and the abnormal function to obtain the optimized grouping clustering model.

[0111] In detail, determining the first-level outliers when performing first-level clustering using the preset grouping clustering model based on the clustering index involves obtaining the objective function value using the clustering index, subtracting the objective function value from the preset expected value to obtain the difference between the objective function value and the preset expected value, and comparing the difference with the preset threshold. The preset expected value is determined based on the optimization objective of the preset grouping clustering model.

[0112] Furthermore, the iterative clustering is to obtain the global optimal value of the objective function. By continuously iterating the first-level group labels, an optimal clustering state of the first-level group labels is obtained.

[0113] In detail, the generation of outlier functions based on the first-level grouping labels during iterative clustering can be achieved by using tools such as Origin and Matlab to perform curve fitting on the outliers at each level, thereby obtaining the outlier functions for each level of outliers.

[0114] Furthermore, the reason for using the constraint condition as a penalty term in the objective function is that the constrained optimization problem of discrete decision variables with values ​​of 0 or 1 is difficult to solve. Therefore, the optimization problem is transformed into an unconstrained optimization problem of continuous decision variables with values ​​in the real number domain, making the optimization problem easier to solve.

[0115] Specifically, the modified objective function is:

[0116]

[0117] The parameters in the modified objective function have been explained above and will not be repeated here.

[0118] S5. Obtain the target information in the TCM medical system, and use the optimized grouping clustering model to group and cluster the target information to obtain the grouped and clustered target information.

[0119] In this embodiment of the invention, the target information includes, but is not limited to, patient information, the medical system classification of the TCM medical system, patient consumption information, patient payment information, patient account balance, payment data, and management data. The target information and the historical information are obtained using the same method, both generated from the medical insurance system of the TCM medical system. That is, the information of the medical insurance system of the TCM medical system can be divided into two parts: one part is the historical information, and the other part is the target information. The historical information is used to optimize the grouping clustering model, and the optimized grouping clustering model is used to group and cluster the target information. Specifically, using the optimized grouping clustering model to group and cluster the target information means that only the maximum number of groups needs to be determined, and the algorithm can automatically determine a suitable number of groups within that range. The target information is input into the optimized grouping clustering model, and the optimized model parameters and model functions in the optimized grouping clustering model are used to group and cluster the target information to obtain the grouped and clustered target information.

[0120] This invention extracts features from historical information of a generated Traditional Chinese Medicine (TCM) medical system to obtain medical item tags. This avoids excessive noise data in the historical information, which can lead to poor generalization ability. Retaining appropriate noise data helps prevent overfitting. The medical item tags are then clustered at a first level according to a preset grouping clustering model to determine the grouping items of the TCM medical system. An outlier function is flexibly selected to represent the different degrees of loss caused by outliers. Based on the fact that outliers better describe the parameters in the preset grouping clustering model, a patient matrix for each grouping item is generated. The clustering index of the patient matrix is ​​calculated, and the preset grouping clustering model is optimized using the clustering index to obtain an optimized grouping clustering model. This optimized model considers the distribution characteristics of the quantity, amount, and number of people in each grouping item reflected in a large amount of historical information from the TCM medical system, fully exploring the correlation between each grouping item. Therefore, this invention proposes a TCM information grouping clustering method that can solve the problem of low efficiency in TCM information grouping clustering.

[0121] like Figure 4 The diagram shown is a functional block diagram of a traditional Chinese medicine information grouping and clustering device provided in an embodiment of the present invention.

[0122] The TCM information grouping and clustering device 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the TCM information grouping and clustering device 100 may include a feature extraction module 101, a first-level clustering module 102, a grouping item module 103, a model optimization module 104, and a grouping and clustering module 105. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0123] In this embodiment, the functions of each module / unit are as follows:

[0124] The feature extraction module 101 is used to generate historical information of the traditional Chinese medicine medical system, extract features from the historical information, and obtain medical item tags of the traditional Chinese medicine medical system.

[0125] The first-level clustering module 102 is used to perform first-level clustering on the medical item tags according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags.

[0126] The grouping item module 103 is used to determine the grouping items of the TCM medical system according to the first-level grouping label, and select one of the grouping items as the target item;

[0127] The model optimization module 104 is used to generate a patient matrix of the target item based on the preset patient identity identifier and the first-level group label, calculate the clustering index of the patient matrix, and optimize the preset group clustering model using the clustering index to obtain the optimized group clustering model.

[0128] The grouping and clustering module 105 is used to obtain target information in the traditional Chinese medicine medical system, and to perform grouping and clustering on the target information using the optimized grouping and clustering model to obtain the grouped and clustered target information.

[0129] like Figure 5 The diagram shown is a schematic representation of an electronic device for implementing a method for grouping and clustering traditional Chinese medicine information, according to an embodiment of the present invention.

[0130] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a traditional Chinese medicine information grouping and clustering program.

[0131] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a TCM information grouping and clustering program) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0132] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a TCM information grouping and clustering program, but also to temporarily store data that has been output or will be output.

[0133] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0134] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0135] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0136] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0137] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0138] The TCM information grouping and clustering program stored in the memory 11 of the electronic device is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0139] Generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system;

[0140] The medical item tags are clustered in a first-level manner according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags;

[0141] The grouping items of the TCM medical system are determined based on the primary grouping labels, and one of the items in the grouping items is selected as the target item.

[0142] A patient matrix for the target project is generated based on the preset patient identity identifier and the first-level group label. The clustering index of the patient matrix is ​​calculated, and the preset grouping clustering model is optimized using the clustering index to obtain the optimized grouping clustering model.

[0143] The target information in the TCM medical system is obtained, and the optimized grouping clustering model is used to group and cluster the target information to obtain the grouped and clustered target information.

[0144] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0145] Furthermore, if the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0146] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0147] Generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system;

[0148] The medical item tags are clustered in a first-level manner according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags;

[0149] The grouping items of the TCM medical system are determined based on the primary grouping labels, and one of the items in the grouping items is selected as the target item.

[0150] A patient matrix for the target project is generated based on the preset patient identity identifier and the first-level group label. The clustering index of the patient matrix is ​​calculated, and the preset grouping clustering model is optimized using the clustering index to obtain the optimized grouping clustering model.

[0151] The target information in the TCM medical system is obtained, and the optimized grouping clustering model is used to group and cluster the target information to obtain the grouped and clustered target information.

[0152] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0153] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0155] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0156] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0157] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0158] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0159] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for grouping and clustering information in Traditional Chinese Medicine, characterized in that, The method includes: Generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system; The medical item tags are clustered in a first-level manner according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags; The grouping items of the TCM medical system are determined based on the primary grouping labels, and one of the items in the grouping items is selected as the target item. A patient matrix for the target item is generated based on the preset patient identity identifier and the first-level grouping label. The information values ​​of the medical item labels of the patients are sorted to obtain a sequence list of the information values. The information values ​​are then labeled with quartiles based on the sequence list to obtain multiple quartile groups of the information values. The clustering index of the patient matrix is ​​calculated based on the quartile group to which the information values ​​belong. The preset grouping clustering model is optimized using the clustering index to obtain an optimized grouping clustering model. The target information in the TCM medical system is obtained, and the optimized grouping clustering model is used to group and cluster the target information to obtain the grouped and clustered target information.

2. The TCM information grouping and clustering method as described in claim 1, characterized in that, The step of extracting features from the historical information to obtain medical item tags for the traditional Chinese medicine medical system includes: The historical information is cleaned to obtain standard information of the historical information; The standard information is segmented into words to obtain the information words of the standard information; The information is segmented into words and then vectorized to obtain the word segmentation vectors. The word segmentation vectors are concatenated to obtain the medical item tags of the traditional Chinese medicine medical system.

3. The TCM information grouping and clustering method as described in claim 1, characterized in that, The step of performing first-level clustering of the medical item tags according to a preset grouping clustering model to obtain first-level grouping tags for the medical item tags includes: The medical item labels are assigned numbers to obtain the item numbers of the medical item labels; The objective function, decision variables, and constraints for grouping and clustering the project numbers are determined according to the preset grouping and clustering model. The project numbers are grouped and clustered according to the objective function, the decision variables, and the constraints to obtain the initial group numbers of the project numbers, and the medical project labels corresponding to the initial group numbers are determined as the first-level group labels.

4. The TCM information grouping and clustering method as described in claim 3, characterized in that, The objective function is as follows: in, It is the minimum difference in information among patients in the same primary grouping label. This indicates the total number of groups for the first-level grouping label. It is the identifier of the first-level group label. This represents the total number of patients. It is the identifier of the patient. It is an outlier function, and... It depends on the value. Indicates selection and The larger one, It is the first The total information value of each patient under the first-level group label described in the group. This indicates the total number of labels for the stated medical items. It is the identifier of the medical item label. It is to measure the patient's condition at the time. The index representing the degree of clustering of the total information value of each patient under the first-level group label described in the group. Indicates the first The medical item label mentioned above is related to the first Subordination relationships between groups Indicates the first The patient in The information value of the medical item label.

5. The TCM information grouping and clustering method as described in claim 1, characterized in that, The calculation of the clustering index of the patient matrix includes: The clustering index of the patient matrix is ​​calculated using the following formula: in, The first one is the one mentioned Group target project, It is the clustering index of the patient matrix. It is the quartile of the above The patient matrix for each patient under the target project described in the group. This represents the matrix mean of all the patients mentioned under the target item. This represents the matrix variance of all the patients under the target item. This represents the total number of target projects.

6. The method for grouping and clustering TCM information as described in any one of claims 1 to 5, characterized in that, The step of optimizing the preset grouping clustering model using the clustering index to obtain the optimized grouping clustering model includes: S11. Determine the first-level outliers when performing first-level clustering using the preset grouping clustering model based on the clustering index, and perform iterative clustering on the first-level grouping labels based on the first-level outliers; S12. When the first-level outlier is greater than or equal to the preset threshold, repeat step S11. When the first-level outlier is less than the preset threshold, stop the iterative clustering of the first-level group labels. S13. Generate anomaly functions based on outliers at each level during iterative clustering according to the first-level grouping labels; S14. The constraint conditions are used as a penalty term for the objective function to modify the objective function, thereby obtaining the modified objective function; S15. Optimize the preset grouping clustering model according to the modified objective function and the abnormal function to obtain the optimized grouping clustering model.

7. A traditional Chinese medicine information grouping and clustering device, characterized in that, The device includes: The feature extraction module is used to generate historical information of the TCM medical system, extract features from the historical information, and obtain medical item tags of the TCM medical system. The first-level clustering module is used to perform first-level clustering on the medical item tags according to a preset grouping clustering model to obtain the first-level grouping tags of the medical item tags; The grouping item module is used to determine the grouping items of the TCM medical system based on the first-level grouping labels, and select one of the grouping items as the target item; The model optimization module is used to generate a patient matrix of the target items based on the preset patient identity identifier and the first-level grouping label, sort the information values ​​of the medical item label of the patient to obtain a sequence list of the information values, perform quartile labeling on the information values ​​according to the sequence list to obtain multiple quartile groups of the information values, calculate the clustering index of the patient matrix according to the quartile group of the information value, and optimize the preset grouping clustering model using the clustering index to obtain the optimized grouping clustering model; The grouping and clustering module is used to obtain target information from the TCM medical system, and to group and cluster the target information using the optimized grouping and clustering model to obtain the grouped and clustered target information.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the TCM information grouping and clustering method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the TCM information grouping and clustering method as described in any one of claims 1 to 6.

Images