A medical knowledge recommendation method, device, electronic device and storage medium
Through the weight generation network and preprocessing of the medical knowledge base, combined with the weight matching of input vocabulary and medical vocabulary, the resource waste and information overload problems of existing medical knowledge recommendation methods are solved, and more accurate recommendation results and higher user satisfaction are achieved.
Patent Information
- Application Number
- CN202210350188.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-02
- Publication Date
- 2025-09-05
- Estimated Expiration
- 2042-04-02
AI Technical Summary
The existing medical knowledge recommendation methods have problems such as high time complexity, waste of resources, low user usage, and overload of recommendation results and expected deviations.
By obtaining the weight matching of the vocabulary vector of the user input statement and the medical knowledge base, the weight generation network is used to learn input vocabulary weights, and combined with the medical vocabulary weights, the correlation is calculated to obtain recommended results, including preprocessing and maximum correlation threshold filtering.
Save human resources, improve recommendation accuracy, reduce information overload, reduce user expectations deviations, and enhance user sense of use.
Smart Images
Figure CN114691994B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information recommendation technology, and in particular to a method, device, electronic device and computer-readable storage medium for recommending medical knowledge. Background Art
[0002] With the development of the Internet and big data, rich medical knowledge faces the contradiction between supply and demand of massive management and precise delivery. Therefore, a medical knowledge recommendation method is needed to provide data with high matching degree for user query, subscription and other needs.
[0003] Existing medical knowledge recommendation methods use recommendation algorithms with too high time complexity, or use traditional machine learning methods that require manual feature extraction, which not only wastes resources but also has low user usage. In addition, when providing medical knowledge data to users, the user's basic information, logs, and historical records are usually taken into consideration, resulting in information overload in the recommendation results, and the recommendation results deviate from the user's actual expected results. Summary of the Invention
[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device and computer-readable storage medium for recommending medical knowledge, which saves human resources, does not cause information overload in the recommendation results, improves the accuracy of medical knowledge recommendations, reduces user expectation deviations, and improves user experience.
[0005] In a first aspect, embodiments of the present application provide a method for recommending medical knowledge, the method comprising:
[0006] Obtaining a medical knowledge base and a user's input statement;
[0007] Performing word segmentation on the input sentence to obtain input word vectors corresponding to input words in the input sentence;
[0008] Extracting an input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector;
[0009] Performing weight matching on the input words in the input sentence and the medical knowledge base according to the input word weights to obtain a relevance;
[0010] A recommendation result is obtained according to the relevance.
[0011] In the above implementation process, by matching the input vocabulary weights with the medical knowledge base, more appropriate and practical recommendation results can be obtained, which saves human resources, does not cause information overload in the recommendation results, improves the accuracy of medical knowledge recommendations, reduces user expectation deviations, and improves user experience.
[0012] Furthermore, the step of extracting the input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector includes:
[0013] Obtaining a sentence vector corresponding to the input sentence;
[0014] Obtaining encoding information corresponding to the input vocabulary vector in the input sentence;
[0015] Normalization is performed based on the sentence vector, the input vocabulary vector, and the encoding information to obtain an input vocabulary weight corresponding to the input vocabulary.
[0016] In the above implementation process, incorporating encoding information into the process of extracting input word weights can more accurately extract the features of the input words, improve the accuracy of subsequent recommendations, and reduce user expectation deviations.
[0017] Furthermore, before the step of obtaining the input statement and the medical knowledge base, the method further includes: preprocessing the medical knowledge base.
[0018] In the above implementation process, by preprocessing the medical knowledge base, the data in the medical knowledge base can be made closer to reality and input sentences, ensuring that the conformity of the medical knowledge base is closer to the user and improving the accuracy of subsequent recommendations.
[0019] Furthermore, the step of preprocessing the medical knowledge base includes:
[0020] Performing word segmentation processing on the medical knowledge base to obtain medical vocabulary;
[0021] A medical term weight of the medical term is obtained.
[0022] In the above implementation process, obtaining the medical vocabulary and medical vocabulary weights of the medical knowledge base can facilitate the extraction of medical vocabulary features, reduce the time for searching the medical knowledge base, and save occupied memory space.
[0023] Furthermore, the step of weight-matching the input vocabulary in the input sentence with the medical knowledge base according to the input vocabulary weight to obtain the relevance includes:
[0024] Matching the input vocabulary weight with the medical vocabulary weight of the medical vocabulary to obtain candidate medical vocabulary;
[0025] Obtaining a candidate medical vocabulary weight corresponding to the candidate medical vocabulary;
[0026] The relevance of the candidate medical vocabulary is obtained according to the input vocabulary weight and the candidate medical vocabulary weight.
[0027] In the above implementation process, obtaining candidate medical terms first can narrow the calculation range of relevance, make subsequent recommendations more accurate, reduce memory space usage, and reduce redundancy.
[0028] Furthermore, the step of obtaining a recommendation result according to the relevance includes:
[0029] Get the maximum correlation threshold;
[0030] Determining whether the correlation with the largest value among the correlations of the candidate medical terms is greater than the maximum correlation threshold;
[0031] If so, the candidate medical vocabulary corresponding to the largest correlation among the candidate medical vocabulary correlations is selected as the recommendation result.
[0032] In the above implementation process, the recommendation results are selected according to the maximum relevance threshold to avoid recommendation results that do not meet user expectations, which can further improve the user experience and make the recommendation results more relevant and more in line with user needs.
[0033] In a second aspect, an embodiment of the present application further provides a device for recommending medical knowledge, the device comprising:
[0034] An acquisition module is used to acquire the medical knowledge base and the user's input statement;
[0035] A word segmentation processing module, configured to perform word segmentation processing on the input sentence to obtain an input word vector corresponding to the input word in the input sentence;
[0036] An extraction module, configured to extract an input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector;
[0037] a matching module, configured to perform weight matching on the input vocabulary in the input sentence and the medical knowledge base according to the input vocabulary weight to obtain a relevance;
[0038] The recommendation module is used to obtain recommendation results according to the relevance.
[0039] In the above implementation process, by matching the input vocabulary weights with the medical knowledge base, more appropriate and practical recommendation results can be obtained, which saves human resources, does not cause information overload in the recommendation results, improves the accuracy of medical knowledge recommendations, reduces user expectation deviations, and improves user experience.
[0040] Furthermore, the device also includes a preprocessing module: used for preprocessing the medical knowledge base.
[0041] In the above implementation process, by preprocessing the medical knowledge base, the data in the medical knowledge base can be made closer to reality and input sentences, ensuring that the conformity of the medical knowledge base is closer to the user and improving the accuracy of subsequent recommendations.
[0042] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.
[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the first aspects.
[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.
[0045] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by practicing the above-mentioned technology of the present disclosure.
[0046] It can be implemented according to the contents of the specification. The following is a detailed description of the preferred embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.
[0048] Figure 1 A flowchart of a method for recommending medical knowledge provided in an embodiment of the present application;
[0049] Figure 2 A schematic diagram of the structure of a device for recommending medical knowledge provided in an embodiment of the present application;
[0050] Figure 3 A schematic diagram of the structural composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0051] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0052] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.
[0053] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0054] Example 1
[0055] Figure 1 This is a flow chart of the medical knowledge recommendation method provided in the embodiment of the present application. Figure 1 As shown, the method includes:
[0056] S1, obtains the medical knowledge base and the user's input statement;
[0057] S2, perform word segmentation on the input sentence to obtain the input vocabulary vector corresponding to the input vocabulary in the input sentence;
[0058] S3, extracting the input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector;
[0059] S4, weight matching the input words in the input sentence with the medical knowledge base according to the input word weights to obtain relevance;
[0060] S5, obtain recommendation results based on relevance.
[0061] In the above implementation process, by matching the input vocabulary weights with the medical knowledge base, more appropriate and practical recommendation results can be obtained, which saves human resources, does not cause information overload in the recommendation results, improves the accuracy of medical knowledge recommendations, reduces user expectation deviations, and improves user experience.
[0062] The embodiment of the present application extracts the input vocabulary weight of the input vocabulary, matches it with the medical vocabulary weight in the medical knowledge base to obtain relevance, and obtains recommendation results based on the relevance. The input vocabulary weight and the medical vocabulary weight can be obtained by constructing a weight generation network.
[0063] In one possible implementation, S3 includes:
[0064] Get the sentence vector corresponding to the input sentence;
[0065] Get the corresponding encoding information of the input vocabulary vector in the input sentence;
[0066] Normalization is performed based on the sentence vector, input vocabulary vector, and encoding information to obtain the input vocabulary weight corresponding to the input vocabulary.
[0067] In the above implementation process, incorporating encoding information into the process of extracting input word weights can more accurately extract the features of the input words, improve the accuracy of subsequent recommendations, and reduce user expectation deviations.
[0068] The embodiment of the present application can use a weight generation network to learn the weight information of the input vocabulary in the input sentence, and obtain the input vocabulary weight corresponding to the input vocabulary. The weight generation network contains a generation subnetwork for learning sentence vectors, that is, the input is the input sentence, and the output is the sentence vector. Bi-LSTM can be used as the generation subnetwork of the sentence vector. The weight generation network uses a multi-head attention mechanism (Multi-Head Attention) to learn the correlation between the input vocabulary vector and the sentence vector to obtain the input vocabulary weight, and adds encoding information (position encoding PE) to encode its position information at the time of input. After the output of the multi-head attention network is summed and normalized, it is the input vocabulary weight corresponding to each input vocabulary in the input sentence.
[0069] Furthermore, before the step of obtaining the input sentence and the medical knowledge base, the method further includes: preprocessing the medical knowledge base.
[0070] In the above implementation process, by preprocessing the medical knowledge base, the data in the medical knowledge base can be made closer to reality and input sentences, ensuring that the conformity of the medical knowledge base is closer to the user and improving the accuracy of subsequent recommendations.
[0071] Furthermore, the step of preprocessing the medical knowledge base includes:
[0072] Perform word segmentation on the medical knowledge base to obtain medical vocabulary;
[0073] Get the medical word weight of the medical word.
[0074] In the above implementation process, obtaining the medical vocabulary and medical vocabulary weights of the medical knowledge base can facilitate the extraction of medical vocabulary features, reduce the time for searching the medical knowledge base, and save occupied memory space.
[0075] For example, for example, a sentence in the medical knowledge base is "If you have a cold or fever, you should take a certain cold medicine", after word segmentation, it is " <bos> / cold / fever / should / take / some / cold / medicine / <eos>Taking this embodiment as an example, the word segmentation tool SentensePiece can be used for word segmentation.
[0076] In one possible implementation, S4 includes:
[0077] Matching the input word weights with the medical word weights of the medical words to obtain candidate medical words;
[0078] Obtain candidate medical vocabulary weights corresponding to candidate medical vocabulary;
[0079] The relevance of the candidate medical vocabulary is obtained according to the input vocabulary weight and the candidate medical vocabulary weight.
[0080] In the above implementation process, obtaining candidate medical terms first can narrow the calculation range of relevance, make subsequent recommendations more accurate, reduce memory space usage, and reduce redundancy.
[0081] Exemplarily, the embodiment of the present application needs to match each input word with the medical knowledge base, because the weight of each input word in the input sentence is different. For example: in input sentence A: "You should take certain medicine when you have a cold" and sentence B in the medical knowledge base: "New coronary pneumonia has symptoms similar to a cold", the input word "cold" in input sentence A has a different input word weight in input sentence A than the medical word "cold" in the medical knowledge base. The medical word weight in sentence B in the medical knowledge base is different. Therefore, in order to ensure the most semantically consistent match, it is necessary to select candidate medical words from the medical vocabulary to narrow the matching range, which can also make the matching results more accurate.
[0082] The total weight is obtained by multiplying the input vocabulary weight corresponding to the input vocabulary and the candidate medical vocabulary weight corresponding to the candidate medical vocabulary. The relevance of each candidate medical vocabulary in the medical knowledge base is calculated to obtain the relevance of all candidate medical vocabulary.
[0083] In one possible implementation, S5 includes:
[0084] Get the maximum correlation threshold;
[0085] Determine whether the relevance with the largest value among the relevances of the candidate medical terms is greater than a maximum relevance threshold;
[0086] If so, the candidate medical vocabulary corresponding to the largest correlation value among the candidate medical vocabulary is selected as the recommendation result.
[0087] In the above implementation process, the recommendation results are selected according to the maximum relevance threshold to avoid recommendation results that do not meet user expectations, which can further improve the user experience and make the recommendation results more relevant and more in line with user needs.
[0088] The candidate medical term corresponding to the highest correlation value among the correlations is selected as the recommendation result. Optionally, this embodiment of the application sets a maximum correlation threshold. If the maximum correlation value is greater than the highest correlation value among the correlations of the candidate medical terms, it indicates that there are no recommendation results that match the input sentence, and the recommendation result cannot be entered at this time.
[0089] Example 2
[0090] In order to execute the method corresponding to the above embodiment 1 and achieve the corresponding functions and technical effects, a medical knowledge recommendation device is provided below, such as Figure 2 As shown, the device includes:
[0091] Acquisition module 1, used to acquire the medical knowledge base and the user's input statement;
[0092] The word segmentation processing module 2 is used to perform word segmentation processing on the input sentence to obtain the input word vector corresponding to the input word in the input sentence;
[0093] Extraction module 3, used for extracting input vocabulary weights corresponding to input vocabulary according to the input vocabulary vector;
[0094] Matching module 4, for weight matching the input words in the input sentence with the medical knowledge base according to the input word weights to obtain relevance;
[0095] The recommendation module 5 is used to obtain recommendation results based on relevance.
[0096] In the above implementation process, by matching the input vocabulary weights with the medical knowledge base, more appropriate and practical recommendation results can be obtained, which saves human resources, does not cause information overload in the recommendation results, improves the accuracy of medical knowledge recommendations, reduces user expectation deviations, and improves user experience.
[0097] Furthermore, the device also includes a preprocessing module: used for preprocessing the medical knowledge base.
[0098] Furthermore, the preprocessing module is also used to:
[0099] Perform word segmentation on the medical knowledge base to obtain medical vocabulary;
[0100] Get the medical word weight of the medical word.
[0101] Furthermore, the extraction module 3 is further configured to:
[0102] Get the sentence vector corresponding to the input sentence;
[0103] Get the corresponding encoding information of the input vocabulary vector in the input sentence;
[0104] Normalization is performed based on the sentence vector, input vocabulary vector, and encoding information to obtain the input vocabulary weight corresponding to the input vocabulary.
[0105] Furthermore, the matching module 4 is further configured to:
[0106] Matching the input word weights with the medical word weights of the medical words to obtain candidate medical words;
[0107] Obtain candidate medical vocabulary weights corresponding to candidate medical vocabulary;
[0108] The relevance of the candidate medical vocabulary is obtained according to the input vocabulary weight and the candidate medical vocabulary weight.
[0109] Furthermore, the recommendation module 5 is also used to:
[0110] Get the maximum correlation threshold;
[0111] Determine whether the relevance with the largest value among the relevances of the candidate medical terms is greater than a maximum relevance threshold;
[0112] If so, the candidate medical vocabulary corresponding to the largest correlation value among the candidate medical vocabulary is selected as the recommendation result.
[0113] The medical knowledge recommendation device can implement the method of the above embodiment 1. The options in the above embodiment 1 are also applicable to this embodiment and will not be described in detail here.
[0114] The rest of the contents of the embodiments of this application can refer to the contents of the above-mentioned embodiment 1, and will not be repeated in this embodiment.
[0115] Example 3
[0116] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the medical knowledge recommendation method of embodiment one.
[0117] Optionally, the above-mentioned electronic device may be a server.
[0118] See Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 31, a communication interface 32, a memory 33, and at least one communication bus 34. The communication bus 34 is used to enable direct communication between these components. The communication interface 32 of the device in this embodiment of the present application is used to communicate signaling or data with other node devices. The processor 31 may be an integrated circuit chip with signal processing capabilities.
[0119] The processor 31 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor can be a microprocessor, or the processor 31 can also be any conventional processor.
[0120] The memory 33 may be, but is not limited to, a random access memory (RAM), 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), etc. The memory 33 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 31, the device can perform the above-mentioned operations. Figure 1 The various steps involved in the method embodiment.
[0121] Optionally, the electronic device may further include a storage controller and an input / output unit. The memory 33, storage controller, processor 31, peripheral interfaces, and input / output units are electrically connected to each other, directly or indirectly, to enable data transmission or interaction. For example, these components may be electrically connected to each other via one or more communication buses 34. The processor 31 is configured to execute executable modules stored in the memory 33, such as software function modules or computer programs included in the device.
[0122] The input and output unit is used to provide users with the ability to create tasks and to create optional start time periods or preset execution times for the tasks to enable interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and keyboard.
[0123] I understand. Figure 3 The structure shown is only for illustration, and the electronic device may also include Figure 3 More or fewer components than shown, or with Figure 3 Different configurations shown. Figure 3 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0124] In addition, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the medical knowledge recommendation method of embodiment one.
[0125] An embodiment of the present application further provides a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.
[0126] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.
[0127] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0128] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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 and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
[0129] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.
[0130] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.
[0131] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise," "include," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.< / eos> < / bos>
Claims
1. A method for recommending medical knowledge, characterized in that: The method comprises: Preprocess the medical knowledge base; Obtaining a medical knowledge base and a user's input statement; Performing word segmentation on the input sentence to obtain input word vectors corresponding to input words in the input sentence; Extracting an input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector; Performing weight matching on the input words in the input sentence and the medical knowledge base according to the input word weights to obtain a relevance; Obtaining recommendation results based on the relevance; The step of preprocessing the medical knowledge base includes: Performing word segmentation processing on the medical knowledge base to obtain medical vocabulary; obtaining a medical vocabulary weight of the medical vocabulary; The step of performing weight matching on the input vocabulary in the input sentence and the medical knowledge base according to the input vocabulary weight to obtain the relevance includes: Matching the input vocabulary weight with the medical vocabulary weight of the medical vocabulary to obtain candidate medical vocabulary; Obtaining a candidate medical vocabulary weight corresponding to the candidate medical vocabulary; The relevance of the candidate medical vocabulary is obtained according to the input vocabulary weight and the candidate medical vocabulary weight.
2. The method for recommending medical knowledge according to claim 1, characterized in that: The step of extracting the input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector includes: Obtaining a sentence vector corresponding to the input sentence; Obtaining encoding information corresponding to the input vocabulary vector in the input sentence; Normalization is performed based on the sentence vector, the input vocabulary vector, and the encoding information to obtain an input vocabulary weight corresponding to the input vocabulary.
3. The method for recommending medical knowledge according to claim 1, characterized in that: The step of obtaining a recommendation result according to the relevance includes: Get the maximum correlation threshold; Determining whether the correlation with the largest value among the correlations of the candidate medical terms is greater than the maximum correlation threshold; If so, the candidate medical vocabulary corresponding to the largest correlation among the candidate medical vocabulary correlations is selected as the recommendation result.
4. A device for recommending medical knowledge, characterized in that: The device comprises: An acquisition module is used to acquire the medical knowledge base and the user's input statement; A word segmentation processing module, configured to perform word segmentation processing on the input sentence to obtain an input word vector corresponding to the input word in the input sentence; An extraction module, configured to extract an input vocabulary weight corresponding to the input vocabulary according to the input vocabulary vector; a matching module, configured to perform weight matching on the input vocabulary in the input sentence and the medical knowledge base according to the input vocabulary weight to obtain a relevance; A recommendation module, configured to obtain a recommendation result based on the relevance; The device also includes a pre-processing module for: Preprocess the medical knowledge base; Performing word segmentation processing on the medical knowledge base to obtain medical vocabulary; obtaining a medical vocabulary weight of the medical vocabulary; Matching the input vocabulary weight with the medical vocabulary weight of the medical vocabulary to obtain candidate medical vocabulary; Obtaining a candidate medical vocabulary weight corresponding to the candidate medical vocabulary; The relevance of the candidate medical vocabulary is obtained according to the input vocabulary weight and the candidate medical vocabulary weight.
5. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the medical knowledge recommendation method according to any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that The device stores a computer program, which, when executed by a processor, implements the medical knowledge recommendation method according to any one of claims 1 to 3.