Prescription traditional efficacy prediction method and device based on enrichment analysis

Abstract

The invention provides a prescription traditional efficacy prediction method and device based on enrichment analysis, and relates to the technical field of traditional Chinese medicine informatization and traditional Chinese medicine prescription analysis. The method comprises the following steps: acquiring traditional Chinese medicine composition and dosage information of a prescription to be predicted; inputting the composition and dosage information of the traditional Chinese medicines into a constructed prescription traditional efficacy prediction model based on enrichment analysis; and obtaining a traditional efficacy prediction result of the prescription according to the traditional Chinese medicine composition, the dosage information and the prescription traditional efficacy prediction model based on enrichment analysis. According to the method, prescription analysis is carried out from the perspective of informatics, a prescription traditional efficacy prediction model based on enrichment analysis is constructed, and the most possible efficacy of the prescription is predicted after prescription traditional Chinese medicine composition information is input into the model.

Description

Technical Field

[0001] The present invention relates to the field of information technology of traditional Chinese medicine and traditional Chinese medicine prescription analysis technology, and in particular to a method and device for predicting the traditional efficacy of prescriptions based on enrichment analysis. Background Art

[0002] Prescriptions are the main means of using Chinese medicine to prevent and treat diseases, one of the main tools for syndrome differentiation and treatment, and the central link of Chinese medicine theory and clinical research. Prescriptions are composed of selected drugs and combinations based on syndrome differentiation and legislation. Each Chinese herbal medicine has its own unique efficacy. The efficacy of prescriptions is the result of the collection and synergy of these Chinese herbal medicines. Accurately grasping the efficacy of prescriptions after the prescriptions are composed plays a key role in clinical efficacy. The research of traditional Chinese medicine and modern medicine is different. Different from modern pharmacological effects such as anti-inflammatory and anti-coagulation, traditional Chinese medicine has unique perspectives and terms for the efficacy of Chinese medicine, such as invigorating qi and calming the nerves. In traditional Chinese medicine diagnosis and treatment, the efficacy of prescriptions is accumulated through continuous diagnosis and treatment experience, and the prediction of prescription efficacy mainly depends on the personal experience and ability of doctors; in modern research, some researchers use modern information technology to predict the traditional efficacy of prescriptions, providing a reference of certain value for subsequent clinical practice.

[0003] The existing methods for analyzing the efficacy of prescriptions based on information technology of traditional Chinese medicine are mainly to predict prescriptions by constructing information models. At present, modern research on the prediction of prescription efficacy in informatics mostly improves the performance of information prediction models by expanding more relevant information and more algorithms. For example, some researchers have incorporated a large amount of modern Chinese medicine pharmacology information (such as target information), and some researchers have continuously tried various algorithms to predict the efficacy of prescriptions, including some complex algorithms such as graph convolutional networks and semi-supervised learning genetic algorithms. Although researchers have made efforts from the perspective of data and algorithms, the data and algorithms used in this type of method still have shortcomings in reflecting the idea of ​​TCM syndrome differentiation and treatment, and have certain limitations, resulting in low accuracy in the prediction of traditional prescription efficacy.

[0004] The modern use of information technology to predict the efficacy of prescriptions is usually achieved by the following three methods:

[0005] Method 1: Prediction method based on topic model. It uses topic model to mine the potential relationship between efficacy labels and Chinese medicine, proposes a new supervised topic model for prescription efficacy prediction, and incorporates the results of prescription compatibility law mining into the learning process. The advantage of this method is that it can mine potential topics from a large amount of prescription data, reveal the correlation and commonality between Chinese medicines, and provide strong support for the prediction of prescription efficacy. The disadvantage is that the topic model, as a typical bag-of-words model, has great limitations for short text data such as Chinese medicine prescriptions, and it is difficult to gain insight into the complex correlation between Chinese medicine combinations and prescription efficacy.

[0006] Method 2: Prediction method based on deep learning model. It is to establish multiple binary classifiers to predict the efficacy of prescriptions through improved deep learning models, such as models composed of bidirectional long short-term memory neural networks and convolutional neural networks. The advantage of this method is that it can automatically learn the characteristics of the data without manually designing and selecting features. In addition, the deep learning model has good processing capabilities for complex nonlinear relationships and can more accurately predict the efficacy of prescriptions. The disadvantage is that although the deep learning model has achieved certain success in predicting the efficacy of prescriptions, it also has some limitations. The deep learning model requires a large amount of high-quality data for training to learn the complex relationship between drug prescriptions and efficacy. If there is noise, missing values ​​or outliers in the data, and the data distribution is uneven, it will affect the prediction effect of the model. In addition, the deep learning model has poor interpretability. When predicting the efficacy of prescriptions, it cannot provide which Chinese medicines and compatibility relationships have an important impact on the prediction results, making the prediction results difficult to understand.

[0007] Method 3: Prediction method based on GCN (Graph Convolution Network). It is a neural network model that specializes in processing graph structure data. In the prediction of prescription efficacy, GCN can regard Chinese medicine as nodes in the graph and the compatibility relationship between Chinese medicine as edges, thereby constructing a graph structure. The advantage of this method is that it can make full use of the compatibility relationship between Chinese medicines, effectively apply the concept of deep learning to unstructured data, capture the interaction and synergy of Chinese medicines in prescriptions, and thus more accurately predict the efficacy of prescriptions. The disadvantage is that although GCN has a strong ability to process unstructured data, it also has certain defects when applied to the prediction of prescription efficacy. First, constructing the graph structure of the prescription requires appropriate nodes and edges. If the accurate association information between nodes cannot be constructed, the prediction effect will be greatly reduced. In addition, GCN also has poor interpretability like deep learning models. Summary of the invention

[0008] In order to solve the technical problem of low accuracy in the prediction of traditional efficacy of prescriptions in the prior art, the embodiment of the present invention provides a method and device for predicting traditional efficacy of prescriptions based on enrichment analysis. The technical solution is as follows:

[0009] On the one hand, a method for predicting the traditional efficacy of prescriptions based on enrichment analysis is provided, the method being implemented by a device for predicting the traditional efficacy of prescriptions, the method comprising:

[0010] S1. Obtain the Chinese medicine composition and dosage information of the prescription to be predicted.

[0011] S2. Input the composition and dosage information of traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis.

[0012] S3. According to the composition and dosage information of traditional Chinese medicine and the traditional efficacy prediction model of prescriptions based on enrichment analysis, the traditional efficacy prediction results of the prescriptions are obtained.

[0013] Among them, the construction process of the traditional efficacy prediction model of prescriptions based on enrichment analysis includes:

[0014] S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions.

[0015] S22. Based on the basic corpus of traditional Chinese medicine, assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis.

[0016] S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained. The accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy, and the prediction conformity rate of the prescription traditional efficacy prediction model is obtained.

[0017] Optionally, the construction of a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions in S21 includes:

[0018] S211. Collect the names and effects of traditional Chinese medicines to build an initial basic corpus of traditional Chinese medicines.

[0019] S212, collecting prescription names, names of Chinese medicines in prescription components, dosages of Chinese medicines in prescription components, and prescription efficacy, to construct an initial prescription basic corpus.

[0020] S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

[0021] Optionally, the initial Chinese medicine basic corpus and the initial prescription basic corpus are structured and normalized in S213 to obtain a Chinese medicine basic corpus and a prescription basic corpus, including:

[0022] The names of traditional Chinese medicines in the initial basic corpus of prescriptions are replaced with synonyms, and the replaced names are consistent with those in the basic corpus of traditional Chinese medicines.

[0023] The prescription efficacy in the initial prescription basic corpus is replaced with synonyms and structured.

[0024] Optionally, in S22, according to the basic corpus of traditional Chinese medicine, assigning values ​​to variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis includes:

[0025] Construct a disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph, and assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis based on the basic corpus of traditional Chinese medicine and the disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph.

[0026] Optionally, the formula for calculating the hypergeometric distribution of the prescription efficacy enrichment analysis in S22 is shown in the following formula (1):

[0027] (1)

[0028] In the formula, Indicates the degree of enrichment, represents the symbol of the combinatorial function, Indicates the number of Chinese medicines with a certain efficacy among all Chinese medicines. Indicates the number of Chinese medicines with a certain efficacy in the prescription to be predicted, Indicates the number of all Chinese medicines in the field of traditional Chinese medicine, Indicates the number of Chinese medicines contained in the prescription to be predicted.

[0029] Optionally, in S23, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated according to the hypergeometric distribution calculation formula after the assignment, and then the traditional effect prediction result of the prescription is obtained, and the accuracy of the traditional effect prediction result of the prescription is calculated with the actual recorded effect to obtain the prediction conformity rate of the traditional effect prediction model of the prescription, including:

[0030] According to the assigned hypergeometric distribution calculation formula, the enrichment degree of multiple effects of each prescription in the basic corpus of prescriptions is calculated, and the enrichment degrees of multiple effects are sorted in order from low to high. The effects with an enrichment degree less than or equal to 0.05 are obtained as the traditional efficacy prediction results of the prescriptions. The accuracy of the traditional efficacy prediction results of the prescriptions is then calculated with the actual recorded efficacy of each prescription in the basic corpus of prescriptions to obtain the efficacy prediction conformity rate of the traditional efficacy prediction model of prescriptions.

[0031] On the other hand, a device for predicting the traditional efficacy of prescriptions based on enrichment analysis is provided, and the device is applied to a method for predicting the traditional efficacy of prescriptions based on enrichment analysis, and the device comprises:

[0032] The acquisition module is used to obtain the Chinese medicine composition and dosage information of the prescription to be predicted.

[0033] The input module is used to input the composition and dosage information of traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis.

[0034] The output module is used to obtain the traditional efficacy prediction results of the prescription based on the composition and dosage information of traditional Chinese medicine and the traditional efficacy prediction model of the prescription based on enrichment analysis.

[0035] Among them, the construction process of the traditional efficacy prediction model of prescriptions based on enrichment analysis includes:

[0036] S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions.

[0037] S22. Based on the basic corpus of traditional Chinese medicine, assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis.

[0038] S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained. The accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy, and the prediction conformity rate of the prescription traditional efficacy prediction model is obtained.

[0039] Optionally, the input module is further configured to:

[0040] S211. Collect the names and effects of traditional Chinese medicines to build an initial basic corpus of traditional Chinese medicines.

[0041] S212, collecting prescription names, names of Chinese medicines in prescription components, dosages of Chinese medicines in prescription components, and prescription efficacy, to construct an initial prescription basic corpus.

[0042] S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

[0043] Optionally, the input module is further configured to:

[0044] The names of traditional Chinese medicines in the initial basic corpus of prescriptions are replaced with synonyms, and the replaced names are consistent with those in the basic corpus of traditional Chinese medicines.

[0045] The prescription efficacy in the initial prescription basic corpus is replaced with synonyms and structured.

[0046] Optionally, the input module is further configured to:

[0047] Construct a disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph, and assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis based on the basic corpus of traditional Chinese medicine and the disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph.

[0048] Optionally, the formula for calculating the hypergeometric distribution of prescription efficacy enrichment analysis is shown in the following formula (1):

[0049] (1)

[0050] In the formula, Indicates the degree of enrichment, represents the symbol of the combinatorial function, Indicates the number of Chinese medicines with a certain efficacy among all Chinese medicines. Indicates the number of Chinese medicines with a certain efficacy in the prescription to be predicted, Indicates the number of all Chinese medicines in the field of traditional Chinese medicine, Indicates the number of Chinese medicines contained in the prescription to be predicted.

[0051] Optionally, the input module is further configured to:

[0052] According to the assigned hypergeometric distribution calculation formula, the enrichment degree of multiple effects of each prescription in the basic corpus of prescriptions is calculated, and the enrichment degrees of multiple effects are sorted in order from low to high. The effects with an enrichment degree less than or equal to 0.05 are obtained as the traditional efficacy prediction results of the prescriptions. The accuracy of the traditional efficacy prediction results of the prescriptions is then calculated with the actual recorded efficacy of each prescription in the basic corpus of prescriptions to obtain the efficacy prediction conformity rate of the traditional efficacy prediction model of prescriptions.

[0053] On the other hand, a device for predicting the traditional efficacy of prescriptions is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned methods for predicting the traditional efficacy of prescriptions based on enrichment analysis is implemented.

[0054] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for predicting the traditional efficacy of prescriptions based on enrichment analysis.

[0055] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0056] In the present invention, by establishing a basic corpus of traditional Chinese medicine and prescriptions, not only a large amount of information such as traditional Chinese medicine ingredients, efficacy and prescription composition is collected, providing a solid data basis for predicting the efficacy of prescriptions, but also the traditional Chinese medicine and prescription information is standardized and normalized, and the data in the corpus is uniformly processed and labeled to ensure the accuracy and consistency of the data, providing a reliable basis for the efficacy prediction and analysis of prescriptions.

[0057] The present invention utilizes the operation of gene enrichment analysis and hypergeometric distribution calculation and applies it to the prediction of prescription efficacy, which can reflect how multiple Chinese medicines are comprehensively fitted to form the rules of the whole prescription efficacy. It not only has good adaptability, explainability and operability, but also takes into account the interactions and associations between Chinese medicines, making the prediction results more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0059] Figure 1 It is a flow chart of a method for predicting traditional efficacy of prescriptions based on enrichment analysis provided by an embodiment of the present invention;

[0060] Figure 2 It is a block diagram of a device for predicting traditional efficacy of prescriptions based on enrichment analysis provided by an embodiment of the present invention;

[0061] Figure 3 It is a structural schematic diagram of a prescription traditional efficacy prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0063] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0064] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0065] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0066] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0067] The embodiment of the present invention provides a method for predicting the traditional efficacy of prescriptions based on enrichment analysis. The method can be implemented by a device for predicting the traditional efficacy of prescriptions, which can be a terminal or a server. Figure 1 The flowchart of the method for predicting the traditional efficacy of prescriptions based on enrichment analysis is shown in FIG. The processing flow of the method may include the following steps:

[0068] S1. Obtain the Chinese medicine composition and dosage information of the prescription to be predicted.

[0069] S2. Input the composition and dosage information of traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis.

[0070] The process of constructing a traditional prescription efficacy prediction model based on enrichment analysis may include the following steps S21-S23:

[0071] S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions.

[0072] Optionally, the above step S21 may include the following steps S211-S213:

[0073] S211. Collect the names and effects of traditional Chinese medicines to build an initial basic corpus of traditional Chinese medicines.

[0074] S212, collecting prescription names, names of Chinese medicines in prescription components, dosages of Chinese medicines in prescription components, and prescription efficacy, to construct an initial prescription basic corpus.

[0075] S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

[0076] Optionally, the above step S213 may include:

[0077] S2131. Replace the names of Chinese medicines in the initial basic corpus of prescriptions with their synonyms, so that the names of the replaced Chinese medicines are consistent with the names of the Chinese medicines in the basic corpus of Chinese medicines.

[0078] S2132. Replace synonyms and perform structural processing on the efficacy of prescriptions in the initial prescription basic corpus.

[0079] In a feasible implementation, this step S21 mainly collects and organizes data related to the prediction of the efficacy of traditional Chinese medicine prescriptions, including the name of the prescription, the composition of the prescription, the name of the Chinese medicine, the efficacy of the Chinese medicine, etc., to build a relatively complete and authoritative basic corpus of Chinese medicine and prescriptions. At the same time, collect and organize data related to the basic theory of traditional Chinese medicine, connect the efficacy of Chinese medicine and related knowledge of traditional Chinese medicine symptoms and syndromes, and jointly organize them to form a knowledge graph.

[0080] Specifically, we first collect data related to the prediction of prescription efficacy and perform normalization on it to build a relatively complete and authoritative basic corpus of traditional Chinese medicine and prescriptions.

[0081] The basic corpus of traditional Chinese medicine includes the name and efficacy of traditional Chinese medicine, and collects 474 commonly used traditional Chinese medicines (source: Ling Yikui. Chinese Materia Medica [M]. Shanghai: Shanghai Science and Technology Press, 2001; National Pharmacopoeia Committee. Pharmacopoeia of the People's Republic of China: Volume 1 [M]. Beijing: China Medical Science and Technology Press, 2020.).

[0082] The basic corpus information of prescriptions includes the name of the prescription, the name of the Chinese medicine in the prescription, the dosage of the Chinese medicine in the prescription and the efficacy of the prescription. 174 classic prescriptions were collected as the training set (source: Deng Zhongjia. Prescription Science [M]. Beijing: China Traditional Chinese Medicine Press, 2019).

[0083] Furthermore, the collected relevant data are structured and standardized: the names of Chinese medicines in the basic corpus of prescriptions are replaced with synonyms to keep them consistent with the names of Chinese medicines in the basic corpus of traditional Chinese medicines, and all are standardized with reference to the pharmacopoeia; the efficacy of prescriptions in the basic corpus of prescriptions are replaced with synonyms and structured to keep them consistent with the efficacy of Chinese medicines in the basic corpus of traditional Chinese medicines.

[0084] At the same time, in order to solve the problem of inconsistent and incomplete description of the efficacy of traditional Chinese medicine in traditional records, the present invention uses the unique logical system of TCM cognition of diseases, syndromes and symptoms to construct a related knowledge network, and efficacy is a term formed for the treatment of diseases, syndromes and symptoms. In this way, the efficacy of traditional Chinese medicine and related TCM disease syndrome knowledge are connected in series to form a knowledge graph. The main theoretical sources of the knowledge graph are "Basic Theory of Traditional Chinese Medicine", "Diagnosis of Traditional Chinese Medicine" and "Chinese Materia Medica" (Yin Huihe. Basic Theory of Traditional Chinese Medicine [M]. Shanghai: Shanghai Science and Technology Press, 2017; Deng Tietao. Diagnosis of Traditional Chinese Medicine [M]. Shanghai: Shanghai Science and Technology Press, 2017; Ling Yikui. Chinese Materia Medica [M]. Shanghai: Shanghai Science and Technology Press, 2001; National Pharmacopoeia Committee. Pharmacopoeia of the People's Republic of China: Volume 1 [M]. Beijing: China Medical Science and Technology Press, 2020.). After the knowledge graph is constructed, the variable values ​​required for hypergeometric calculation can be completed through node statistics.

[0085] S22. Based on the basic corpus of traditional Chinese medicine, assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis.

[0086] Specifically, a disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph is constructed, and the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis are assigned values ​​according to the basic corpus of traditional Chinese medicine and the disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph.

[0087] In a feasible implementation, this step S22 is to apply the gene enrichment analysis hypergeometric distribution to the prescription efficacy analysis, perform a differential comparison calculation between the efficacy of the predicted prescription Chinese medicine set and the efficacy of all Chinese medicine sets, calculate the probability of the efficacy, and assign values ​​to the variables in the hypergeometric distribution formula.

[0088] Specifically, the relevant variables of the prescription efficacy enrichment analysis calculation are assigned values ​​according to the basic corpus of traditional Chinese medicine in step S21. Specifically, the variables in the hypergeometric distribution formula of the prescription efficacy enrichment analysis are assigned values. The formula of the hypergeometric distribution calculation of the prescription efficacy enrichment analysis is shown in the following formula (1):

[0089] (1)

[0090] In the formula, Indicates the degree of enrichment, represents the symbol of the combinatorial function, Indicates the number of Chinese medicines with a certain efficacy among all Chinese medicines. Indicates the number of Chinese medicines with a certain efficacy in the prescription to be predicted, represents the number of all Chinese medicines in the field of traditional Chinese medicine, and in this invention, represents the number of all Chinese medicines in the basic corpus of Chinese medicines, Indicates the number of Chinese medicines contained in the prescription to be predicted.

[0091] Furthermore, the specific definition of variable assignment in the formula is:

[0092] variable :Number of Chinese medicines in prescriptions: To predict the number of Chinese medicines in a prescription. Generally, a prescription consists of 4 to 10 Chinese medicines. For example, Siwu Decoction contains four herbs: Chuanxiong, Angelica, Rehmannia and White Peony. .

[0093] variable : Number of Chinese medicines in the field: that is, the number of all Chinese medicines in the basic Chinese medicine corpus. There are 474 Chinese medicines in the basic Chinese medicine corpus of the present invention, so ,After the corpus construction is stable, this value remains basically unchanged.

[0094] variable :Number of Chinese medicines with a certain efficacy in a prescription: refers to the number of all Chinese medicines with a certain efficacy in the prescription to be predicted. For example: There are 2 Chinese medicines involved in the prescription for the efficacy of clearing heat, then , other effects such as replenishing qi are counted in the same way.

[0095] variable :Number of Chinese medicines with a certain efficacy in a field: refers to the number of all Chinese medicines with a certain efficacy in the basic corpus of Chinese medicines. This statistic is not limited to the Chinese medicines for the intended prescription prediction, but the number of all Chinese medicines. Usually, the number of Chinese medicines involved in a certain efficacy ranges from a few to dozens. After the corpus is stabilized, this value remains basically unchanged. For example, if 20 Chinese medicines have the efficacy of clearing heat, then .

[0096] The following is an example of Baohe Pills to demonstrate the variable assignment in the hypergeometric distribution formula of the prescription efficacy:

[0097] variable : That is, the number of Chinese medicines in Baohe Pills. Baohe Pills are composed of seven herbs: hawthorn, Shenqu, pinellia, tuckahoe, tangerine peel, forsythia and radish seeds. .

[0098] variable : That is, the number of all Chinese medicines in the basic Chinese medicine corpus. There are 474 Chinese medicines in the basic Chinese medicine corpus of the present invention, so .

[0099] variable : That is, the number of Chinese medicines with a certain effect in Baohe Pills. For example, there are three Chinese medicines (hawthorn, Shenqu, and radish seeds) involved in the effect of digestion in Baohe Pills. .

[0100] variable : That is, the number of all Chinese medicines with a certain effect in the basic corpus of Chinese medicine. For example, there are 8 Chinese medicines with the effect of digestion in the basic corpus of Chinese medicine. .

[0101] S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained. The accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy, and the prediction conformity rate of the prescription traditional efficacy prediction model is obtained.

[0102] Specifically, according to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and the enrichment degree of multiple effects is sorted from low to high, and the effects with enrichment degree less than or equal to 0.05 are obtained as the traditional effect prediction results of the prescription. The prediction results are then compared with the actual recorded effects of each prescription in the prescription basic corpus for accuracy calculation to obtain the efficacy prediction compliance rate of the model.

[0103] In a feasible implementation, the P values ​​(enrichment levels) of multiple effects of Chinese medicine in the 174 prescriptions in the prescription basic corpus in step S21 are calculated respectively by using the hypergeometric distribution calculation formula and the assigned related variables in step S22. By calculating the above formula, a P value can be calculated for each possible effect of the prescription. These P values ​​are sorted from low to high. The lower the P value, the more likely the effect is the full effect of the prescription. The present invention uses the effect with a P value less than or equal to 0.05 as the predicted effect of the prescription.

[0104] The present invention takes Baohe Pills as an example, obtains variable assignments in the hypergeometric calculation formula through steps S21 and S22, substitutes them into the hypergeometric distribution calculation formula for calculation, and obtains the P value (enrichment degree) of the possible efficacy of Baohe Pills as shown in Table 1 (schematic table of enrichment degree P value sorting line), wherein after substituting into the formula, the P value of the efficacy of "digestion" is calculated to be 0.000012566, ranking first:

[0105] Table 1

[0106]

[0107] In the calculation of hypergeometric distribution in other fields, the significance is usually expressed by a P value less than 0.05, which is based on the 95% critical value in the normal distribution commonly used in medical statistics, that is, a P value equal to 0.05 is a commonly used significance threshold. If the P value is less than or equal to 0.05, it is generally considered that the result is statistically significant, that is, the present invention has sufficient evidence to reject the null hypothesis and believes that the observed enrichment is not a random event. Therefore, the present invention also uses the efficacy with a P value less than or equal to 0.05 as the predicted efficacy of the prescription. Taking Baohe Pills as an example, the efficacy with a P value less than or equal to 0.05 is used, and the eight efficacies of "digestion, accumulation, treatment of food accumulation (spleen and stomach qi stagnation), treatment of food accumulation in children, digestion and accumulation, digestion and stomach, treatment of meat accumulation and descending qi and phlegm" are used as the test efficacy. After the accuracy calculation is performed with the actual recorded efficacy of the whole prescription of Baohe Pills as "digestion, stomach", the predicted compliance rate is 71.42%.

[0108] The above steps S21-S23 are to extract the efficacy of the whole prescription to be predicted from the efficacy of all Chinese medicines through enrichment analysis, and calculate the enrichment degree (P value) of the efficacy of Chinese medicines using hypergeometric distribution. The P value above the significance threshold of 0.05 is the efficacy of the prescription to be predicted, and finally a model for predicting the efficacy of prescriptions is formed.

[0109] S3. According to the composition and dosage information of traditional Chinese medicine and the traditional efficacy prediction model of prescriptions based on enrichment analysis, the traditional efficacy prediction results of the prescriptions are obtained.

[0110] The present invention analyzes the efficacy of prescriptions from an informatics perspective and constructs a traditional prescription efficacy prediction model based on enrichment analysis. After inputting the Chinese medicine composition and dosage information of the prescription, the model predicts the most likely efficacy of the prescription.

[0111] The present invention also provides a series of solutions to the deficiencies in the prior art. In summary, the technical problems solved by the present invention include the following points:

[0112] (1) The present invention conducts a predictive study on the efficacy of prescriptions based on the characteristics of traditional Chinese medicine. Combining the relevant theories of traditional Chinese medicine, the present invention not only considers the efficacy of a single Chinese medicine, but also the relationship between prescriptions and Chinese medicines, as well as the interaction and association between multiple Chinese medicines, thereby realizing the analysis of the overall efficacy of the prescription.

[0113] (2) The present invention uses the characteristics of enrichment analysis to carry out research on the prediction of prescription efficacy. The advantage of enrichment analysis is that it can extract biologically meaningful information from massive data to form a core algorithm for the prediction of prescription efficacy. Compared with the existing technology, it can systematically integrate the importance and correlation information of the efficacy of traditional Chinese medicine, making the prescription prediction results more accurate and reliable.

[0114] (3) The present invention is based on known knowledge of traditional Chinese medicine and Chinese pharmacology, and has a high degree of interpretability. When predicting the efficacy of a prescription, it can provide which Chinese medicines and compatibility relationships have an important impact on the prediction results, making the prediction results easy to understand and accept.

[0115] In the embodiment of the present invention, by establishing a basic corpus of traditional Chinese medicine and prescriptions, not only a large amount of information such as traditional Chinese medicine ingredients, efficacy and prescription composition is collected, providing a solid data basis for predicting the efficacy of prescriptions, but also the traditional Chinese medicine and prescription information is standardized and normalized, and the data in the corpus is uniformly processed and labeled to ensure the accuracy and consistency of the data, providing a reliable basis for the efficacy prediction and analysis of prescriptions.

[0116] The present invention utilizes the operation of gene enrichment analysis and hypergeometric distribution calculation and applies it to the prediction of prescription efficacy, which can reflect how multiple Chinese medicines are comprehensively fitted to form the rules of the whole prescription efficacy. It not only has good adaptability, explainability and operability, but also takes into account the interactions and associations between Chinese medicines, making the prediction results more accurate.

[0117] Figure 2 The block diagram of a device for predicting the traditional efficacy of prescriptions based on enrichment analysis according to an exemplary embodiment is shown. The device is used in a method for predicting the traditional efficacy of prescriptions based on enrichment analysis. Figure 2 The device includes an acquisition module 310, an input module 320 and an output module 330. Among them:

[0118] The acquisition module 310 is used to obtain the Chinese medicine composition and dosage information of the prescription to be predicted.

[0119] The input module 320 is used to input the composition and dosage information of traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis.

[0120] The output module 330 is used to obtain the traditional efficacy prediction result of the prescription according to the composition and dosage information of the traditional Chinese medicine and the traditional efficacy prediction model of the prescription based on the enrichment analysis.

[0121] Among them, the construction process of the traditional efficacy prediction model of prescriptions based on enrichment analysis includes:

[0122] S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions.

[0123] S22. Based on the basic corpus of traditional Chinese medicine, assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis.

[0124] S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained. The accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy, and the prediction conformity rate of the prescription traditional efficacy prediction model is obtained.

[0125] Optionally, the input module 320 is further configured to:

[0126] S211. Collect the names and effects of traditional Chinese medicines to build an initial basic corpus of traditional Chinese medicines.

[0127] S212, collecting prescription names, names of Chinese medicines in prescription components, dosages of Chinese medicines in prescription components, and prescription efficacy, to construct an initial prescription basic corpus.

[0128] S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

[0129] Optionally, the input module 320 is further configured to:

[0130] The names of traditional Chinese medicines in the initial basic corpus of prescriptions are replaced with synonyms, and the replaced names are consistent with those in the basic corpus of traditional Chinese medicines.

[0131] The prescription efficacy in the initial prescription basic corpus is replaced with synonyms and structured.

[0132] Optionally, the input module 320 is further configured to:

[0133] Construct a disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph, and assign values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis based on the basic corpus of traditional Chinese medicine and the disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph.

[0134] Optionally, the formula for calculating the hypergeometric distribution of prescription efficacy enrichment analysis is shown in the following formula (1):

[0135] (1)

[0136] In the formula, Indicates the degree of enrichment, represents the symbol of the combinatorial function, Indicates the number of Chinese medicines with a certain efficacy among all Chinese medicines. Indicates the number of Chinese medicines with a certain efficacy in the prescription to be predicted, Indicates the number of all Chinese medicines in the field of traditional Chinese medicine, Indicates the number of Chinese medicines contained in the prescription to be predicted.

[0137] Optionally, the input module 320 is further configured to:

[0138] According to the assigned hypergeometric distribution calculation formula, the enrichment degree of multiple effects of each prescription in the basic corpus of prescriptions is calculated, and the enrichment degrees of multiple effects are sorted in order from low to high. The effects with an enrichment degree less than or equal to 0.05 are obtained as the traditional efficacy prediction results of the prescriptions. The accuracy of the traditional efficacy prediction results of the prescriptions is then calculated with the actual recorded efficacy of each prescription in the basic corpus of prescriptions to obtain the efficacy prediction conformity rate of the traditional efficacy prediction model of prescriptions.

[0139] In the embodiment of the present invention, by establishing a basic corpus of traditional Chinese medicine and prescriptions, not only a large amount of information such as traditional Chinese medicine ingredients, efficacy and prescription composition is collected, providing a solid data basis for predicting the efficacy of prescriptions, but also the traditional Chinese medicine and prescription information is standardized and normalized, and the data in the corpus is uniformly processed and labeled to ensure the accuracy and consistency of the data, providing a reliable basis for the efficacy prediction and analysis of prescriptions.

[0140] The present invention utilizes the operation of gene enrichment analysis and hypergeometric distribution calculation and applies it to the prediction of prescription efficacy, which can reflect how multiple Chinese medicines are comprehensively fitted to form the rules of the whole prescription efficacy. It not only has good adaptability, explainability and operability, but also takes into account the interactions and associations between Chinese medicines, making the prediction results more accurate.

[0141] Figure 3 is a schematic diagram of the structure of a device for predicting the traditional efficacy of a prescription provided by an embodiment of the present invention, such as Figure 3 As shown, the prescription traditional efficacy prediction device may include the above Figure 2The device for predicting the traditional efficacy of prescriptions based on enrichment analysis is shown. Optionally, the device for predicting the traditional efficacy of prescriptions 410 may include a first processor 2001 .

[0142] Optionally, the prescription traditional efficacy prediction device 410 may further include a memory 2002 and a transceiver 2003 .

[0143] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0144] Combine the following Figure 3 The components of the prescription traditional efficacy prediction device 410 are specifically introduced as follows:

[0145] The first processor 2001 is the control center of the prescription traditional efficacy prediction device 410, which can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0146] Optionally, the first processor 2001 can execute various functions of the prescription traditional efficacy prediction device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0147] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 are shown in FIG.

[0148] In a specific implementation, as an embodiment, the prescription traditional efficacy prediction device 410 may also include multiple processors, such as Figure 3 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0149] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0150] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and access the first processor 2001 through the interface circuit ( Figure 3 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0151] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0152] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 3 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0153] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and may be connected to the first processor 2001 through the interface circuit ( Figure 3 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0154] It should be noted that Figure 3 The structure of the prescription traditional efficacy prediction device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0155] In addition, the technical effects of the prescription traditional efficacy prediction device 410 can refer to the technical effects of the prescription traditional efficacy prediction method based on enrichment analysis described in the above method embodiment, which will not be repeated here.

[0156] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0157] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0158] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0159] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0160] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0161] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0162] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0164] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0165] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0167] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0168] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for predicting the traditional efficacy of prescriptions based on enrichment analysis, characterized in that: The method comprises: S1. Obtaining the composition and dosage information of the Chinese medicine of the prescription to be predicted; S2, inputting the composition and dosage information of the traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis; S3, obtaining a prediction result of the traditional efficacy of the prescription according to the composition and dosage information of the traditional Chinese medicine and the traditional efficacy prediction model of the prescription based on enrichment analysis; The process of constructing the traditional efficacy prediction model of prescriptions based on enrichment analysis includes: S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions; S22. According to the basic corpus of traditional Chinese medicine, assigning values ​​to variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis; S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained, and the accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy to obtain the prediction conformity rate of the prescription traditional efficacy prediction model.

2. The method for predicting the traditional efficacy of prescriptions based on enrichment analysis according to claim 1, characterized in that: The construction of the basic corpus of traditional Chinese medicine and the basic corpus of prescriptions in S21 includes: S211, collect the names and effects of traditional Chinese medicines and build an initial basic corpus of traditional Chinese medicines; S212, collecting prescription names, names of Chinese medicines in prescriptions, dosages of Chinese medicines in prescriptions, and prescription effects, to construct an initial prescription basic corpus; S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

3. The method for predicting the traditional efficacy of prescriptions based on enrichment analysis according to claim 2, characterized in that: The step S213 of structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus includes: Replacing the names of Chinese medicines in the initial basic corpus of prescriptions with synonyms, so that the names of the Chinese medicines after replacement are consistent with the names of the Chinese medicines in the basic corpus of Chinese medicines; The prescription effects in the initial prescription basic corpus are replaced with synonyms and structured.

4. The method for predicting the traditional efficacy of prescriptions based on enrichment analysis according to claim 1, characterized in that: The step S22 assigns values ​​to the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis according to the basic corpus of traditional Chinese medicine, including: A disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph is constructed, and according to the basic Chinese medicine corpus and the disease-syndrome-symptom-efficacy-traditional Chinese medicine knowledge graph, the variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis are assigned values.

5. The method for predicting the traditional efficacy of prescriptions based on enrichment analysis according to claim 1, characterized in that: The formula for calculating the hypergeometric distribution of the prescription efficacy enrichment analysis in S22 is shown in the following formula (1): （1） In the formula, Indicates the degree of enrichment, represents the symbol of the combinatorial function, Indicates the number of Chinese medicines with a certain efficacy among all Chinese medicines. Indicates the number of Chinese medicines with a certain efficacy in the prescription to be predicted, Indicates the number of all Chinese medicines in the field of traditional Chinese medicine, Indicates the number of Chinese medicines contained in the prescription to be predicted.

6. The method for predicting the traditional efficacy of prescriptions based on enrichment analysis according to claim 1, characterized in that: The step S23 calculates the enrichment degree of multiple effects of each prescription in the prescription basic corpus according to the hypergeometric distribution calculation formula after the assignment, and then obtains the traditional effect prediction result of the prescription, and calculates the accuracy of the traditional effect prediction result of the prescription and the actual recorded effect to obtain the prediction conformity rate of the prescription traditional effect prediction model, including: According to the assigned hypergeometric distribution calculation formula, the enrichment levels of multiple effects of each prescription in the basic corpus of prescriptions are calculated, and the enrichment levels of the multiple effects are sorted in order from low to high, and the effects with an enrichment level less than or equal to 0.05 are obtained as the traditional efficacy prediction results of the prescriptions, and then the accuracy of the traditional efficacy prediction results of the prescriptions and the actually recorded effects of each prescription in the basic corpus of prescriptions are calculated to obtain the efficacy prediction conformity rate of the traditional efficacy prediction model of the prescriptions.

7. A device for predicting the traditional efficacy of prescriptions based on enrichment analysis, wherein the device for predicting the traditional efficacy of prescriptions based on enrichment analysis is used to implement the method for predicting the traditional efficacy of prescriptions based on enrichment analysis as claimed in any one of claims 1 to 6, characterized in that: The device comprises: An acquisition module is used to obtain the composition and dosage information of the Chinese medicine of the prescription to be predicted; An input module, used to input the composition and dosage information of the traditional Chinese medicine into the constructed traditional efficacy prediction model of prescriptions based on enrichment analysis; An output module, used to obtain a traditional efficacy prediction result of the prescription according to the composition and dosage information of the traditional Chinese medicine and the traditional efficacy prediction model of the prescription based on enrichment analysis; The process of constructing the traditional efficacy prediction model of prescriptions based on enrichment analysis includes: S21. Construct a basic corpus of traditional Chinese medicine and a basic corpus of prescriptions; S22. According to the basic corpus of traditional Chinese medicine, assigning values ​​to variables of the hypergeometric distribution calculation formula for prescription efficacy enrichment analysis; S23. According to the hypergeometric distribution calculation formula after assignment, the enrichment degree of multiple effects of each prescription in the prescription basic corpus is calculated, and then the traditional efficacy prediction result of the prescription is obtained, and the accuracy of the traditional efficacy prediction result of the prescription is calculated with the actual recorded efficacy to obtain the prediction conformity rate of the prescription traditional efficacy prediction model.

8. The device for predicting traditional efficacy of prescriptions based on enrichment analysis according to claim 7, characterized in that: The construction of the basic corpus of traditional Chinese medicine and the basic corpus of prescriptions includes: S211, collect the names and effects of traditional Chinese medicines and build an initial basic corpus of traditional Chinese medicines; S212, collecting prescription names, names of Chinese medicines in prescriptions, dosages of Chinese medicines in prescriptions, and prescription effects, to construct an initial prescription basic corpus; S213, structuring and normalizing the initial Chinese medicine basic corpus and the initial prescription basic corpus to obtain a Chinese medicine basic corpus and a prescription basic corpus.

9. A device for predicting the traditional efficacy of prescriptions, characterized in that: The prescription traditional efficacy prediction device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images