Medical knowledge recommendation method based on pattern recognition, electronic equipment and medium

Abstract

The invention relates to the technical field of data processing, in particular to a medical knowledge recommendation method based on pattern recognition, electronic equipment and a medium, and the method comprises the steps: carrying out the clustering of sample treatment and nursing cases, and obtaining a plurality of sample clusters; determining an expression value of any sample cluster based on the plurality of sample clusters; based on the performance value, determining the correlation between the unclassified treatment and nursing cases and the any sample cluster; based on the correlation and the any sample cluster, determining a target category to which the unclassified treatment and nursing cases belong; and based on the target category, performing knowledge recommendation on input case query information. According to the method, the unclassified treatment and nursing cases are classified more accurately, so that more accurate medical knowledge recommendation can be performed when the input case query information is received.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a medical knowledge recommendation method, electronic equipment and medium based on pattern recognition in the field of data processing technology. Background Art

[0002] Palliative care refers to the practice centered on terminally ill patients and their families in a multidisciplinary collaborative model. The main contents include pain and other symptom control, comfort care, psychological, spiritual and social support, etc. Palliative care is a highly practical specialty with the characteristics of strong situational nature and rich content. The lack of corresponding cases and practices prevents nursing students from having a real end-of-life care experience and makes it difficult to achieve the course teaching objectives. With the continuous advancement of medical and educational collaboration, schools and hospitals actively cooperate to play their teaching functions, make full use of clinical case resources, and achieve an effective link between theory and practice. In order to facilitate the targeted learning of palliative care knowledge by nursing students, relevant cases of palliative care should be reasonably classified.

[0003] The existing technology classifies nursing cases mainly by clustering a large number of nursing cases, so that nursing cases with the same nursing situation are classified into one category. However, there are cases in which the nursing situation is not clearly defined or the nursing situation is relatively special and cannot be classified. When students query the nursing cases of the corresponding nursing situation, there will be omissions. In addition, there is a lack of systematic consideration of students' interests and abilities, which cannot highlight the advantages of personalized teaching. There is also a lack of interactivity in case teaching evaluation data collection and analysis of students' weak knowledge points. In this way, there are similar cases or relatively special cases between the nursing cases recorded for different nursing situations. When selecting recommended data, it is impossible to accurately classify the status of the case, and thus it is impossible to make accurate recommendations. Summary of the invention

[0004] In order to solve the technical problem in the prior art that there are similar cases or special cases between the medical care cases recorded for different nursing situations, and the status of the cases cannot be accurately classified when selecting recommended data, so that accurate recommendations cannot be made, the purpose of the present invention is to provide a medical knowledge recommendation method, electronic device and medium based on pattern recognition, and the technical solutions adopted are as follows: In a first aspect, an embodiment of the present invention provides a medical knowledge recommendation method based on pattern recognition, the method comprising: Clustering the sample treatment and nursing cases to obtain multiple sample clusters; Based on the multiple sample clusters, determine the performance value of any sample cluster; Determining the correlation between the unclassified care case and any one of the sample clusters based on the performance value; Based on the correlation and any one of the sample clusters, determining the target category to which the unclassified care case belongs; Based on the target category, knowledge recommendation is performed on the input case query information.

[0005] In a second aspect, a medical knowledge recommendation device based on pattern recognition is provided, the device comprising: A clustering module is used to cluster sample treatment and nursing cases to obtain multiple sample clusters; A first determination module, configured to determine a performance value of any sample cluster based on the multiple sample clusters; A second determination module is used to determine the correlation between the unclassified care case and any one of the sample clusters based on the performance value; A third determination module is used to determine the target category to which the unclassified treatment case belongs based on the correlation and any one of the sample clusters; The recommendation module is used to make knowledge recommendations for the input case query information based on the target category.

[0006] In a third aspect, an electronic device is provided, comprising: a memory for storing executable program code; and a processor for calling and running the executable program code from the memory, so that the electronic device executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0007] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0008] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect.

[0009] The present invention has the following beneficial effects: by clustering sample care cases, a plurality of sample clustering clusters are obtained; then, based on the plurality of sample clustering clusters, the performance value of any sample clustering cluster is determined; in this way, the performance value can intuitively reflect whether the nursing situation targeted by each sample clustering cluster is easy to occur. Then, based on the performance value, the correlation between the unclassified care case and any one of the sample clustering clusters is determined, and the target category to which the unclassified care case belongs is determined by combining the correlation with any one of the sample clustering clusters; in this way, by analyzing the correlation between the unclassified care case and any one of the sample clustering clusters obtained after clustering, the status of the unclassified care case can be judged, thereby accurately analyzing the target category of the unclassified care case. Finally, through the target category of the unclassified care case, a more accurate medical knowledge recommendation can be made for the input case query information. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0011] Figure 1 It is a schematic diagram of an implementation flow of a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention; Figure 2 This is another implementation flow diagram of a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention; Figure 3 This is another implementation flow diagram of a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention; Figure 4 It is another implementation flow diagram of a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention; Figure 5 It is a structural diagram of a medical knowledge recommendation device based on pattern recognition provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a medical knowledge recommendation method, electronic device and medium based on pattern recognition proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0013] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0014] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0015] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0016] The following specifically describes the application environment of a medical knowledge recommendation method based on pattern recognition provided by the present invention in conjunction with the accompanying drawings. Figure 1 , which shows a schematic diagram of the implementation process of a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention. The method can be implemented by the following steps: Step 101, clustering the sample treatment cases to obtain a plurality of sample clusters.

[0017] Here, by extracting keywords from the sample treatment cases, creating a sample space based on the similarity scores between the extracted sample keywords and the classification keywords, and then clustering the data in the sample space to obtain the sample cluster. In some possible implementations, the above step 101 can be implemented by the following steps 111 to 114 (not shown): Step 111, extract keywords from the sample treatment cases to obtain sample keywords.

[0018] Here, the sample treatment cases are stored in the database in text form, the sample treatment cases are extracted, and the sentences in the treatment cases are segmented using the maximum matching word segmentation algorithm. The word segmentation phrases in the treatment cases are extracted using the term frequency-inverse document frequency (TF-IDF) scoring algorithm to obtain sample keywords. The sample keywords may include nouns or verbs used in the sample treatment cases to describe the user's physical condition or psychological state.

[0019] Step 112: Determine the similarity between the sample keyword and the classification keyword.

[0020] Here, the classification keyword can be a set keyword, such as care, pain, psychology, spirit, etc. The sample keyword is compared and analyzed with multiple classification keywords such as care, pain, psychology, spirit, etc. through word embedding technology to obtain a similarity score between the sample keyword and the classification keyword, that is, the similarity between the sample keyword and the classification keyword.

[0021] Step 113: Create a sample space based on the similarity and the sample treatment cases.

[0022] Here, the similarity score between the sample treatment case and a classification keyword is used as a coordinate axis data to establish the sample space. If the sample treatment case contains only one keyword, the similarity score between this keyword and the classification keyword is used as the similarity score between the treatment case and the classification keyword and is placed in the sample space. If the sample treatment case contains multiple sample keywords, the average of the similarity scores between the multiple sample keywords and the classification keyword is used as the similarity score between the sample treatment case and the classification keyword and is placed in the sample space.

[0023] Step 114: cluster the sample space to obtain the multiple sample clusters.

[0024] Here, multiple data points in the sample space (where one data point represents the data after a sample treatment case is bound to a similarity score) are clustered using the density-based spatial clustering algorithm (DBSCAN), with the radius value set to 70 and the number of points in the neighborhood set to 20, to obtain multiple clusters. Among them, DBSCAN is a relatively representative density-based clustering algorithm. Unlike partitioning and hierarchical clustering methods, the DBSCAN algorithm defines a cluster as the largest set of density-connected points, which can divide areas with sufficiently high density into clusters and find clusters of any shape in a noisy spatial database. Compared with the K-means clustering method, the DBSCAN algorithm does not need to know the number of clusters to be formed in advance, and can find clusters of any shape. At the same time, the DBSCAN algorithm can identify noise points. The DBSCAN algorithm is insensitive to the order of samples in the database, that is, the input order of several patterns has little effect on the results. However, for samples at the boundary between clusters, their belonging may fluctuate depending on which cluster is detected first. In this way, by binding the similarity with the sample treatment cases, a sample space is created, and each data in the sample space is clustered, so that the obtained sample clusters can correspond to the similarity, which is convenient for the subsequent classification of unclassified treatment cases through the sample clusters.

[0025] Step 102: Determine the performance value of any sample cluster based on the multiple sample clusters.

[0026] Here, for each cluster in the multiple sample clusters, the performance value of the sample cluster is calculated. Different nursing situations contain different numbers of nursing cases, and the similarity between the nursing cases contained in a single nursing situation is also different. When the number of nursing cases contained in a single nursing situation is more, it proves that the current nursing situation is more likely to occur in daily life, and the nursing cases with similar relationships should be classified into this nursing situation. When the relationship between the nursing cases contained in a single nursing situation is closer, it proves that the characteristics of the single nursing situation are more obvious, and the nursing cases with such characteristics should be classified into this nursing situation. For example, the classification of a single nursing situation is mainly for the convalescent care of patients with mental illness, then the nursing cases related to psychology should be classified into this nursing situation. The above situation analyzes a single nursing situation in the sample space after clustering, mainly for different clusters in the sample space, and can evaluate a single cluster, that is, a single nursing situation, by the number of data points in the cluster, the distribution relationship between the distances between the data points, and the size of the space occupied by a single cluster.

[0027] In some possible implementations, the above step 102 can be performed by Figure 2 The steps shown achieve: Step 201: for any sample cluster, determine the distance between each data point and adjacent data points.

[0028] Here, taking any sample cluster as the jth cluster as an example, the distance between the ith data point in the jth cluster and its adjacent mth data point is calculated.

[0029] Step 202: Determine the performance value of any sample cluster based on the distance and any sample cluster.

[0030] Here, by combining the distance with the corresponding sample cluster, the performance value of the sample cluster is calculated, so as to evaluate the easy occurrence of the single nursing situation represented by the sample cluster through the performance value. In this way, by calculating the performance value for each sample cluster, it is possible to reflect whether the nursing category indicated by each sample cluster is easy to occur through the performance value.

[0031] In some possible implementations, the above step 202 can be performed by Figure 3 The steps shown achieve: Step 301: determine the spatial size of any sample cluster in the sample space.

[0032] Here, the space size is the size of the space occupied by any sample cluster in the sample space.

[0033] Step 302: Determine the ratio between the spatial size and the number of data points in any sample cluster.

[0034] Step 303: The ratio and the distance are merged to obtain a performance value of any sample cluster.

[0035] Here, by multiplying the ratio by the distance, we can get the performance value of any sample cluster.

[0036] In the above steps 301 to 303, taking any sample cluster as the jth cluster as an example, the performance value of the jth cluster is As shown in formula (1): (1); in, is the distance between the ith data point in the jth cluster and its adjacent mth data point (i.e., the distance between each data point and its adjacent data point). is the sum of the distances between all data points in the jth cluster and its adjacent data points. The smaller the sum of the distances, the closer the distances between different data points in the jth cluster, the closer the relationship between the nursing cases represented, and the greater the possibility that the data scatter points adjacent to the cluster belong to the jth cluster.

[0037] is the number of data points in the jth cluster (i.e., the number of data points in the sample cluster). The larger the number, the greater the possibility that the nursing situation classification represented by the current cluster appears in daily life, and the greater the possibility that the data scatter points adjacent to the cluster belong to the jth cluster. is the size of the space occupied by the jth cluster in the sample space (i.e., the spatial size of the sample cluster in the sample space). The smaller the value, the closer the distances between different data points in the jth cluster, the closer the relationship between the nursing cases represented, and the greater the possibility that the data scatter points adjacent to the cluster belong to the jth cluster. In this way, by combining the ratio between the spatial size of any sample cluster in the sample space and the number of data points in the sample cluster with the distance between each data point and the adjacent data point, the performance value of the sample cluster can be accurately calculated.

[0038] Step 103: Determine the correlation between the unclassified care cases and any of the sample clusters based on the performance value.

[0039] Here, the unclassified nursing cases are the nursing cases that have not been classified. Any sample cluster can be understood as a classified nursing situation, and the correlation between the unclassified nursing cases and any sample cluster is the correlation between the unclassified nursing cases and the classified nursing situations, which is used to characterize the distribution relationship between a single nursing case and the classified nursing situations in the sample space.

[0040] In some possible implementations, whether unclassified care cases should be classified into classified care situations (i.e., sample clusters) should be classified according to the degree of similarity between the unclassified care cases and the classified care situations. In the clustered sample space, it can be represented by the spatial distribution relationship between a single data point and the cluster. The smaller the distance between a single data point and the center point of the cluster range, the higher the degree of similarity between the care case represented by the single data point and the care situation represented by the cluster. And when the performance value of the cluster is larger, the possibility of the care situation represented by the cluster itself is greater, the degree of attraction to adjacent data scatter points is greater, and the possibility that the care case represented by a single data point should belong to the care situation represented by the cluster is greater. Therefore, screening can be performed based on the spatial distribution relationship between a single data point and the cluster and the performance value of the cluster. Among them, the above step 103 can be performed by Figure 4 The steps shown achieve: Step 401: in any sample cluster, determine the spatial distance between the unclassified treatment case and the center point of any sample cluster.

[0041] Here, taking any sample cluster as the jth cluster as an example, the spatial distance between the data point corresponding to the unclassified treatment case and the center point of any sample cluster (i.e., the cluster center) is calculated. In some possible implementations, the coordinates of the data point corresponding to the unclassified treatment case in space and the coordinates of the cluster center in space can be calculated by the centroid formula, and then the Euclidean distance is calculated by the two coordinate values ​​to obtain the spatial distance between the unclassified treatment case and the center point of any sample cluster.

[0042] Step 402: Determine the correlation between the unclassified care case and any one of the sample clusters based on the performance value and the spatial distance.

[0043] Here, by combining any sample cluster with the performance value, the correlation between the unclassified care case and any sample cluster can be calculated. In this way, by combining the spatial distance between the unclassified care case and the center point of any sample cluster (i.e., the classified care situation) and the performance value of the sample cluster, the correlation between the unclassified care case and any sample cluster can be accurately calculated.

[0044] In some possible implementations, the above step 402 may be implemented by the following steps 421 to 423 (not shown): Step 421: Determine the consistency between the unclassified care case and any one of the sample clusters based on the performance value and the spatial distance.

[0045] Here, we take the unclassified care case as the i-th unclassified care case and any sample cluster as the j-th cluster (i.e., the j-th classified care situation) as an example to illustrate the consistency between the i-th unclassified care case (i.e., the i-th unclassified data point) and the j-th classified care situation. , as shown in formula (2): (2); in, The performance value for classifying the jth nursing situation (jth cluster). The larger the value, the greater the possibility that the data points adjacent to the jth nursing situation (jth cluster) belong to this cluster. is the distance between the ith data point (i.e., the ith unclassified treatment case) and the center point of the jth cluster in the sample space (i.e., spatial distance), and Not 0. The smaller the value of is, the more similar the data features represented by the i-th data point and the j-th cluster are, and the more they should be classified into one category.

[0046] Step 422, based on the similarity between the unclassified medical cases and the classification keywords, and the similarity between any sample cluster and the classification keywords, determine the similarity difference.

[0047] Step 423: Determine the correlation between the unclassified care case and any one of the sample clusters based on the consistency and the similarity difference.

[0048] Here, the relationship between a single nursing case and the classified nursing situation (i.e., sample cluster) is also related to the similarity score between it and different classification keywords. When the data point position of a single nursing case in the sample space is close to the center point position of the classified nursing situation cluster, but the similarity score difference between the two positions in the sample space and a certain classification keyword is too large, it proves that the difference between the single nursing case and the classified nursing situation in a certain classification is too large, and it is not appropriate to be classified into the same classification nursing situation. The smaller the correlation between the single nursing case and the classified nursing situation.

[0049] Thus, we can obtain the correlation between the i-th unclassified nursing case and the j-th classified nursing situation (i.e., the j-th cluster) , as shown in formula (3): (3); in, is the consistency between the i-th unclassified care case and the j-th classified care situation (i.e., the j-th cluster). The larger the value, the more likely the i-th unclassified care case and the j-th classified care situation should be classified into one category. are the similarity scores between the keywords of the i-th unclassified nursing case and the j-th classified nursing situation and the m-th classified keyword, respectively. is the maximum value of the similarity score difference (i.e., similarity difference) between the center point position of the i-th unclassified nursing case and the j-th classified nursing situation and different classification keywords, and Not 0. The smaller the value, the smaller the difference between the i-th unclassified nursing case and the j-th classified nursing situation and different classification keywords, the more similar the classification emphasis is, and the more they should be classified into one category. In this way, by combining the similarity difference between the unclassified nursing case and any sample cluster with the classification keyword, and then combining the similarity difference with the consistency, the correlation between the unclassified nursing case and any sample cluster can be accurately analyzed.

[0050] Step 104: Determine the target category to which the unclassified care case belongs based on the correlation and any one of the sample clusters.

[0051] In some possible implementations, the above step 104 may be implemented by the following steps 141 and 142 (not shown): Step 141, based on the correlation, determine the similarity between the unclassified care cases and the classified care situations.

[0052] Here, when a new care case is added to the classified care situation, it will affect the similarity and other characteristics of the care cases in the classified care situation. When the care situation changes greatly before and after the addition of a new care case, it proves that the added care case is not similar to the current care situation classification content characteristics, and the possibility of belonging to the same category is small. When the change in the care situation before and after the addition of the new care case is smaller, the added care case is more similar to the current care situation classification content characteristics, and the possibility of belonging to the same category is greater. In the clustered sample space, the above characteristics can be reflected in the change in the performance value gap of a single data scatter point before and after the addition of the cluster. When the performance value gap before and after the addition of the new data point is smaller, the single data scatter point should belong to the cluster, and the care case represented by the single data scatter point should belong to the care situation represented by the cluster.

[0053] It can be obtained that the similarity between the i-th unclassified care case and the j-th classified care case (i.e., the j-th cluster) is , as shown in formula (4): (4); in, is the correlation between the ith unclassified care case and the jth classified care situation. The larger the value, the more likely the ith unclassified care case is to belong to the jth classified care situation. is the performance value of the jth classified nursing situation; is the performance value of the care situation (cluster) classification after adding the i-th unclassified care case. The difference between the performance values ​​of the previous nursing situation (cluster) classification after adding the i-th unclassified nursing case. The smaller the value, the more similar the focus of the i-th unclassified nursing case is to the j-th classified nursing situation, and the more likely they are to belong to the same classification. Use the activation function (Sigmoid function) for normalization and get , The value range of is [0, 1].

[0054] Step 142, based on the homogeneity, determine the target category of the unclassified care case.

[0055] Here, the unclassified care cases include care cases that are unclear in definition with multiple existing care situations after clustering, and care situations that are too special and should be classified as a separate care situation. If this care case is forcibly classified into the same category as other care situations, it will cause confusion in the content of care cases collected by keywords when students query later. A care case that should be classified as a separate care situation often has a larger gap than other care situations. In the sample space, it is manifested as a small R value between a single data scatter point and all other clusters, and it cannot be classified into any category. In some possible implementations, the degree of specialness of the unclassified care case is calculated by analyzing the similarity; and based on the degree of specialness and a preset degree of specialness threshold, the target category of the unclassified care case is determined. Among them, the degree of specialness of the i-th unclassified care case As shown in formula (5): (5); in, is the similarity between the i-th unclassified care case and the j-th classified care situation (i.e., the j-th cluster). The smaller the value, the less the current i-th unclassified care case belongs to the j-th classified care situation. is the number of clusters in the sample space. is the sum of the R values ​​of the ith unclassified nursing case and all the classified nursing situations in the sample space. The smaller the value, the less the ith unclassified case belongs to any classified nursing situation, the more special it is, and the more it should be classified by itself, and Not 0. Use Sigmoid function to normalize and get , its value range is [0, 1]. >0.5, it is determined that the i-th unclassified care case should form a nursing situation classification. For the remaining unclassified care cases that do not form a nursing situation classification, calculate their homology with all classified nursing situations, and take the category corresponding to the nursing situation (i.e., sample cluster) with the maximum homology as the target category of the unclassified care case. In this way, by analyzing the homology of the unclassified care case and the classified care situation, it is possible to determine whether the unclassified care case belongs to the same category as any sample cluster, and then accurately determine the target category of the unclassified care case.

[0056] Step 105: Based on the target category, knowledge recommendation is performed on the input case query information.

[0057] Here, all the nursing cases can be accurately classified according to the above analysis, so that nursing students can conduct learning inquiries. Then, the data classified by the processor is written into the memory through the data bus. The electronic device used in the embodiment of the present invention includes a memory, a processor, a display, and a data bus for connecting communications. When students enter key words (i.e., the input case query information) in the interface of the nursing case query system, the computer processor will call the nursing cases in the corresponding focus classification by determining the storage unit address, sending the address to the address bus, sending read and write signals, data transmission, etc., and display them on the computer display interface for students to select.

[0058] In an embodiment of the present invention, the performance value of any sample cluster is calculated through multiple sample clusters; in this way, the performance value can intuitively reflect whether the nursing situation targeted by each sample cluster is likely to occur. Afterwards, based on the performance value, the correlation between the unclassified nursing case and any sample cluster is determined, and the target category to which the unclassified nursing case belongs is determined by combining the correlation with any sample cluster; in this way, by analyzing the correlation between the unclassified nursing case and any sample cluster obtained after clustering, the status of the unclassified nursing case can be judged, thereby accurately analyzing the target category of the unclassified nursing case. Finally, through the target category of the unclassified nursing case, more accurate knowledge recommendation can be made for the input case query information.

[0059] An embodiment of the present invention provides a medical knowledge recommendation device based on pattern recognition, the device comprising: A clustering module is used to cluster sample treatment and nursing cases to obtain multiple sample clusters; A first determination module, configured to determine a performance value of any sample cluster based on the multiple sample clusters; A second determination module is used to determine the correlation between the unclassified care case and any one of the sample clusters based on the performance value; A third determination module is used to determine the target category to which the unclassified treatment case belongs based on the correlation and any one of the sample clusters; The recommendation module is used to make knowledge recommendations for the input case query information based on the target category.

[0060] In some possible implementations, the clustering module is further used to extract keywords from the sample care cases to obtain sample keywords; determine the similarity between the sample keywords and classification keywords; create a sample space based on the similarity and the sample care cases; and cluster the sample space to obtain the multiple sample clustering clusters.

[0061] In some possible implementations, determining the performance value of any sample clustering cluster based on the multiple sample clustering clusters includes: determining the distance between each data point and the adjacent data point for any sample clustering cluster; and determining the performance value of any sample clustering cluster based on the distance and any sample clustering cluster.

[0062] In some possible implementations, the first determination module is further used to determine the spatial size of any one of the sample clusters in the sample space; determine the ratio between the spatial size and the number of data points in any one of the sample clusters; and fuse the ratio with the distance to obtain a performance value of any one of the sample clusters.

[0063] In some possible implementations, the second determination module is further used to determine the spatial distance between the unclassified care case and the center point of any of the sample clusters in any of the sample clusters; and determine the correlation between the unclassified care case and any of the sample clusters based on the performance value and the spatial distance.

[0064] In some possible implementations, the second determination module is further used to determine the consistency between the unclassified care case and any one of the sample clusters based on the performance value and the spatial distance; determine the similarity difference based on the similarity between the unclassified care case and the classification keyword, and the similarity between any one of the sample clusters and the classification keyword; and determine the correlation between the unclassified care case and any one of the sample clusters based on the consistency and the similarity difference.

[0065] In some possible implementations, the third determination module is further used to determine the similarity between the unclassified care case and any one of the sample clusters based on the correlation; and determine the target category of the unclassified care case based on the similarity.

[0066] In some possible implementations, the third determination module is further used to determine the degree of particularity of the unclassified care case based on the similarity; and to determine the target category of the unclassified care case based on the degree of particularity and a preset degree of particularity threshold.

[0067] Optionally, the transmission medium can be a wired link (such as but not limited to coaxial cable, optical fiber and digital subscriber line (DSL)) or a wireless link (such as but not limited to wireless Fidelity (WIFI), Bluetooth and mobile device network).

[0068] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0069] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, the device 500 includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the device can execute any of the medical knowledge recommendation methods based on pattern recognition described above. In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute a medical knowledge recommendation method based on pattern recognition provided by an embodiment of the present invention.

[0070] This embodiment can divide the functional modules of the device according to the above method example. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation. In the case of dividing each module corresponding to each function, the device may also include a signal uploading module, a determination module, an adjustment module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0071] It should be understood that the device provided in this embodiment is used to execute the above-mentioned medical knowledge recommendation method based on pattern recognition, so the same effect as the above-mentioned implementation method can be achieved. In the case of an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic boxes, modules and circuits described in combination with the disclosure of the present invention. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module can be a memory.

[0072] In addition, the device provided in the embodiment of the present invention may be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a medical knowledge recommendation method based on pattern recognition provided in the above embodiment. This embodiment also provides a computer-readable storage medium, in which a computer program code is stored, and when the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a medical knowledge recommendation method based on pattern recognition provided in the above embodiment.

[0073] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement a medical knowledge recommendation method based on pattern recognition provided in the above embodiment. Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here. Through the description of the above implementation mode, the technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiment described above is only schematic. For example, the division of modules or 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 may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0074] It should be noted that the sequence of the above-mentioned embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A medical knowledge recommendation method based on pattern recognition, characterized in that: The method comprises: Clustering the sample treatment and nursing cases to obtain multiple sample clusters; Based on the multiple sample clusters, determine the performance value of any sample cluster; Determining the correlation between the unclassified care cases and any of the sample clusters based on the performance value; Based on the correlation and any one of the sample clusters, determining the target category to which the unclassified care case belongs; Based on the target category, knowledge recommendation is performed on the input case query information.

2. The medical knowledge recommendation method based on pattern recognition according to claim 1, characterized in that: The sample treatment cases are clustered to obtain multiple sample clusters, including: Extracting keywords from the sample treatment cases to obtain sample keywords; Determining the similarity between the sample keyword and the classification keyword; Creating a sample space based on the similarity and the sample treatment cases; The sample space is clustered to obtain the multiple sample clusters.

3. The medical knowledge recommendation method based on pattern recognition according to claim 2, characterized in that: The step of determining the performance value of any sample cluster based on the multiple sample clusters includes: For any of the sample clusters, determining the distance between each data point and an adjacent data point; Based on the distance and any one of the sample clusters, a performance value of the any one of the sample clusters is determined.

4. The medical knowledge recommendation method based on pattern recognition according to claim 3 is characterized in that: The determining, based on the distance and the any sample cluster, a performance value of the any sample cluster, comprises: Determine the spatial size of any sample cluster in the sample space; Determining a ratio between the spatial size and the number of data points in any one of the sample clusters; The ratio is combined with the distance to obtain a performance value of any sample cluster.

5. The medical knowledge recommendation method based on pattern recognition according to claim 1, characterized in that: Determining the correlation between the unclassified care case and any one of the sample clusters based on the performance value includes: In any of the sample clusters, determining the spatial distance between the unclassified treatment case and the center point of any of the sample clusters; Based on the performance value and the spatial distance, the correlation between the unclassified care case and any one of the sample clusters is determined.

6. The medical knowledge recommendation method based on pattern recognition according to claim 5, characterized in that: The step of determining the correlation between the unclassified care case and any one of the sample clusters based on the performance value and the spatial distance includes: Determining the consistency between the unclassified care case and any one of the sample clusters based on the performance value and the spatial distance; Determine a similarity difference based on the similarity between the unclassified treatment cases and the classification keywords, and the similarity between any sample cluster and the classification keywords; Based on the consistency and the similarity difference, the correlation between the unclassified care case and any one of the sample clusters is determined.

7. The medical knowledge recommendation method based on pattern recognition according to claim 1, characterized in that: The determining, based on the correlation and any one of the sample clusters, the target category to which the unclassified care case belongs includes: Based on the correlation, determining the similarity between the unclassified care case and any of the sample clusters; Based on the homogeneity, a target category for the unclassified care case is determined.

8. The medical knowledge recommendation method based on pattern recognition according to claim 7, characterized in that: Determining the target category of the unclassified care case based on the homogeneity includes: Based on the similarity, determining the uniqueness of the unclassified care case; Based on the degree of specificity and a preset degree of specificity threshold, a target category for the unclassified care case is determined.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the electronic device executes the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by a processor to implement the method according to any one of claims 1 to 8.

Images