Intelligent registration method and device for simulating inquiry and storage medium

Abstract

The invention discloses an intelligent registration method and device for simulating interrogation, equipment and a storage medium. The method comprises the following steps: knowing disease information of a user through a simulation interrogation mode; screening related case samples in a database according to the disease information to obtain case sample information; a decision tree is formed by adopting a model trained through an ID3 algorithm according to the case sample information, and clinical doctor inquiry is simulated according to node information of the decision tree; and evaluating the illness condition of the user according to the inquiry result information and giving a registration suggestion. According to the invention, the disease of the patient can be known in detail through the simulated inquiry thinking, the department to be registered of the patient is judged through the decision tree algorithm, and more scientific and accurate registration suggestions are provided. And meanwhile, cases diagnosed by the patient become a sample set of a decision tree algorithm after data processing, so that the timeliness of the sample set is ensured, that is, the sample set dynamically changes along with pathogenic factors and diagnosis departments, and more accurate intelligent registration information is ensured.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to applications in the field of intelligent assisted registration in hospitals, and more particularly to an intelligent registration method, device and storage medium for simulated medical consultation. Background Art

[0002] The symptom information corresponding to the existing intelligent registration system database is mostly fixed data obtained from medical books or other methods. With the development and mutation of pathogenic factors such as viruses and bacteria, the symptoms of the disease are changing dynamically, and the diagnosis department and treatment method are also changing dynamically. That is to say, the same disease has different symptoms for the same patient at different historical stages, and the department and treatment method may also be different. At present, there is a lack of data sample sets that change dynamically with pathogenic factors and treatment methods to more accurately decide which department a certain disease should be registered in. Different people have symptoms in the same part, and the corresponding registration departments may not be the same. For example, if they all have headaches, it may be a cold virus headache or a neurasthenia headache. In this case, the registration system based on the human body model may be inaccurate. The same patient with the same symptom may have very different causes at different time stages. At the same time, due to insufficient knowledge of the patient's current physical information, it is easy to deviate if the historical case data is directly used to recommend the registration department.

[0003] Therefore, proposing a system that can intelligently assess a patient's condition and give accurate registration recommendations is a technical problem that needs to be solved urgently. Summary of the invention

[0004] To this end, the present invention provides an intelligent registration method, device and storage medium for simulated medical consultation to solve at least one of the technical problems mentioned above.

[0005] To achieve the above objectives, in a first aspect, the present invention provides an intelligent registration method for simulated consultation, comprising:

[0006] Understand the user's disease information through simulated consultation;

[0007] According to the symptom information, relevant case samples in the database are screened to obtain first case sample information;

[0008] Read the first case sample information, use the model trained by the ID3 algorithm to form a decision tree, and then simulate the clinical doctor's consultation according to the node information of the decision tree;

[0009] The user's medical condition is assessed based on the consultation result information and registration recommendations are given.

[0010] Furthermore, after evaluating the user's medical condition based on the medical consultation result information and providing a registration suggestion, it also includes: after the user is diagnosed according to the registration suggestion, collecting second case sample information after the user's diagnosis, and dynamically updating the database.

[0011] Furthermore, forming a decision tree by using a model trained by an ID3 algorithm includes:

[0012] The first case sample information is disassembled by natural language, and valuable symptom information is obtained from the disassembled first case sample information by logic processing service. According to the valuable symptom information, the corresponding branch attribute A and sample set S are searched from the database, and the formula is quoted:

[0013]

[0014] Among them, E(S) represents the entropy value of the sample set S, n represents the number of sample sets S, and there are n different values ​​in total. i Represents different categories of sample sets;

[0015]

[0016] Among them, E A (S) represents the sample entropy value of the branch attribute, S j represents the j-th subset of S divided according to the branch attribute A, and m represents the category corresponding to the branch attribute A in the database;

[0017] Gain(S,A)=E(S)-E A (S) (3)

[0018] Where Gain(S,A) represents the information gain of branch attribute A relative to sample set S;

[0019] Substitute the sample set S into formula (1) to calculate the first information entropy of the data set; substitute the branch attribute A into formula (2) to calculate the second information entropy; substitute the first information entropy and the second information entropy into formula (3) to calculate the information gain; select the feature with the largest information gain as the current decision tree node according to the information gain result, and update the data set and feature set according to the feature.

[0020] Furthermore, the disassembling the first case sample information by natural language includes:

[0021] Obtaining outpatient case data as training sample source data, cleaning the training sample source data, removing invalid cases such as those that cannot be diagnosed and those with missing symptom information, and semantically annotating the cleaned cases;

[0022] A term set of medical terms is obtained, and semantic annotation is performed on the original medical record content according to the term set; a sequence annotation model is trained based on the semantic annotation, and the sequence annotation model is used to identify different entities and relationships in the case text, divide the character strings in the medical record content into phrases, and extract the medical record structured information to obtain initial structured symptom information data.

[0023] Furthermore, the method of understanding the user's disease information through simulated medical consultation includes: the user inputs basic information such as age, gender, physical symptoms, etc. through a mobile smart terminal device, and the mobile smart terminal device performs word segmentation processing on the user's description of the symptoms through natural language processing.

[0024] Further, after selecting the feature with the largest information gain as the current decision tree node according to the information gain result, the method further includes:

[0025] Dividing the current decision tree node into two sample sets, calculating entropy values ​​before splitting for the two sample sets respectively, and calculating information gains of other branch attributes;

[0026] If the classification attribute of the newly generated node is not unique, the newly generated node will continue to be classified, and the process will be repeated until all samples belong to the same class.

[0027] Furthermore, based on the decision tree nodes and the user's answers, the decision tree is traversed until there are no child nodes; based on the final child node, the registration department to which the user belongs is determined and suggestions are given; after obtaining the symptom information input by the user, specific details about the symptom information are provided to the user through message push; when the user's affirmative answer is obtained, the decision tree traversal is terminated, the corresponding conclusion is given to the user, and the user is prompted with corresponding precautions; when the user's negative answer is obtained, the questioning continues through message push until the user gives an affirmative answer, and the corresponding conclusion is given to the user through message push, and the user is prompted with corresponding precautions; when the user answers no, the decision tree traversal and the question and answer process are repeated.

[0028] In a second aspect, the present invention also provides an intelligent registration device for simulating medical consultation, comprising: an information acquisition unit, an information search unit, a central control unit, and an output unit;

[0029] Information acquisition unit: used to understand the user's disease information through simulated consultation;

[0030] An information search unit is used to filter relevant case samples in the database according to the symptom information to obtain first case sample information;

[0031] The central control unit reads the sample information of the first case, uses the model trained by the ID3 algorithm to form a decision tree, and then simulates the clinical doctor's consultation according to the node information of the decision tree;

[0032] Output unit: used to evaluate the user's medical condition based on the consultation result information and give registration suggestions.

[0033] In a third aspect, the present invention provides a computing device, comprising:

[0034] A memory for storing program instructions;

[0035] The processor is used to call the program instructions stored in the memory and execute the above-mentioned intelligent registration method for simulated medical consultation according to the obtained program instructions.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium, including computer-readable instructions. When a computer reads and executes the computer-readable instructions, the above-mentioned intelligent registration method for simulated medical consultation is implemented. The readable medium may be multiple, and the multiple readable media can operate independently of each other.

[0037] Compared with the prior art, this solution understands the user's symptom information through simulated consultation; screens relevant case samples in the database according to the symptom information to obtain case sample information; forms a decision tree based on the case sample information using a model trained by the ID3 algorithm, and then simulates the clinical doctor's consultation based on the node information of the decision tree; evaluates the user's illness based on the consultation result information and gives registration suggestions. The simulated consultation thinking of the present invention can understand the patient's symptoms in detail, and use the decision tree algorithm to determine the department that the patient needs to register, providing more scientific and accurate registration suggestions. At the same time, after the patient's diagnosed case is processed by data, it becomes a sample set of the decision tree algorithm, which ensures the timeliness of the sample set, that is, the sample set changes dynamically with the pathogenic factors and diagnostic departments, thereby ensuring that the intelligent registration information is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 A schematic diagram of a flow chart of an embodiment of an intelligent registration method for simulated medical consultation provided by the present invention;

[0040] Figure 2 A structural diagram of an embodiment of the intelligent registration method for simulated medical consultation provided by the present invention;

[0041] Figure 3A structural diagram of an embodiment of the intelligent registration method for simulated medical consultation provided by the present invention;

[0042] Figure 4 A timing diagram of an embodiment of the intelligent registration method for simulated medical consultation provided by the present invention;

[0043] Figure 5 A flow chart of an embodiment of the intelligent registration method for simulated medical consultation provided by the present invention;

[0044] Figure 6 A structural block diagram of an embodiment of the intelligent registration device for simulated medical consultation provided by the present invention;

[0045] Figure 7 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0046] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0047] It will be understood by those skilled in the art that, unless otherwise stated, the singular forms "a", "an" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0048] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0049] The ID3 algorithm involved in the present invention is a decision tree learning algorithm. It is based on the concepts of entropy and information gain, and constructs a decision tree by dividing a data set into smaller subsets. The core idea of ​​this algorithm is to divide the data by selecting the attributes that can best reduce the uncertainty of the data until all the data belong to the same category. In the ID3 algorithm, information refers to the uncertainty of the data. In order to measure the uncertainty of information, the concept of information entropy is used. Information entropy is an indicator that measures the uncertainty in a data set. The larger its value, the higher the uncertainty of the data set. Feature selection is measured by calculating the information gain of each attribute, and the feature with the largest information gain is selected for splitting. This algorithm is widely used in medical diagnosis, financial risk assessment and other problems.

[0050] In order to make the objectives, technical solutions and advantages of the present application more clear, the specific implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0051] The core of the present invention is to provide an intelligent registration method for simulating medical consultation. Figure 1 The figure is a flow chart of the intelligent registration method for simulated consultation provided in this embodiment. In order to better understand the method, Figure 1 The technical solution of this embodiment is described in detail:

[0052] Step S1: understanding the user's symptom information through simulated consultation;

[0053] Step S2: screening relevant case samples in the database according to the symptom information to obtain first case sample information;

[0054] Step S3: reading the first case sample information, using the model trained by the ID3 algorithm to form a decision tree, and then simulating the clinical doctor's consultation according to the node information of the decision tree;

[0055] Step S4: Evaluate the user's medical condition based on the consultation result information and give registration suggestions.

[0056] In a preferred embodiment, after evaluating the user's medical condition based on the consultation result information and giving a registration suggestion, it also includes: after the user is diagnosed according to the registration suggestion, collecting second case sample information after the user's diagnosis, and dynamically updating the database.

[0057] In a preferred embodiment, forming a decision tree by using a model trained by the ID3 algorithm comprises:

[0058] The first case sample information is disassembled by natural language, and valuable symptom information is obtained from the disassembled first case sample information by logic processing service. According to the valuable symptom information, the corresponding branch attribute A and sample set S are searched from the database, and the formula is quoted:

[0059]

[0060] Among them, E(S) represents the entropy value of the sample set S, n represents the number of sample sets S, and there are n different values ​​in total. i Represents different categories of sample sets;

[0061]

[0062] Among them, E A (S) represents the sample entropy value of the branch attribute, S jrepresents the j-th subset of S divided according to the branch attribute A, and m represents the category corresponding to the branch attribute A in the database;

[0063] Gain(S,A)=E(S)-EA(S) (3)

[0064] Where Gain(S,A) represents the information gain of branch attribute A relative to sample set S;

[0065] Substitute the sample set S into formula (1) to calculate the first information entropy of the data set; substitute the branch attribute A into formula (2) to calculate the second information entropy; substitute the first information entropy and the second information entropy into formula (3) to calculate the information gain; select the feature with the largest information gain as the current decision tree node according to the information gain result, and update the data set and feature set according to the feature.

[0066] In a preferred embodiment, the disassembling of the first case sample information by natural language includes:

[0067] Obtaining outpatient case data as training sample source data, cleaning the training sample source data, removing invalid cases such as those that cannot be diagnosed and those with missing symptom information, and semantically annotating the cleaned cases;

[0068] A term set of medical terms is obtained, and semantic annotation is performed on the original medical record content according to the term set; a sequence annotation model is trained based on the semantic annotation, and the sequence annotation model is used to identify different entities and relationships in the case text, divide the character strings in the medical record content into phrases, and extract the medical record structured information to obtain initial structured symptom information data.

[0069] In a preferred embodiment, the method of understanding the user's disease information through simulated medical consultation includes: the user inputs basic information such as age, gender, physical symptoms, etc. through a mobile smart terminal device, and the mobile smart terminal device performs word segmentation processing on the user's description of the symptoms through natural language processing.

[0070] In a preferred embodiment, after selecting the feature with the largest information gain as the current decision tree node according to the information gain result, the method further includes:

[0071] Dividing the current decision tree node into two sample sets, calculating entropy values ​​before splitting for the two sample sets respectively, and calculating information gains of other branch attributes;

[0072] If the classification attribute of the newly generated node is not unique, the newly generated node will continue to be classified, and the process will be repeated until all samples belong to the same class.

[0073] In a preferred embodiment, the decision tree is traversed according to the decision tree nodes and the user's answers until there are no child nodes; the registration department to which the user belongs is determined according to the final child node, and suggestions are given; after obtaining the symptom information input by the user, the specific details of the symptom information are provided to the user through message push; when the user's affirmative answer is obtained, the decision tree traversal is terminated, the corresponding conclusion is given to the user, and the user is prompted with corresponding precautions; when the user's negative answer is obtained, the questioning continues through message push until the user gives an affirmative answer, and the corresponding conclusion is given to the user through message push, and the user is prompted with corresponding precautions; when the user answers no, the decision tree traversal and the question and answer process are repeated.

[0074] In the scheme of this embodiment, the user's symptom information is understood through a simulated consultation method; the relevant case samples in the database are screened according to the symptom information to obtain the case sample information; a decision tree is formed according to the case sample information using a model trained by the ID3 algorithm, and then the clinical doctor's consultation is simulated according to the node information of the decision tree; the user's illness is evaluated according to the consultation result information and registration suggestions are given. The simulated consultation thinking of the present invention can understand the patient's symptoms in detail, and use the decision tree algorithm to determine the department that the patient needs to register, and provide more scientific and accurate registration suggestions. At the same time, after the patient's diagnosed case is processed by data, it becomes a sample set of the decision tree algorithm, which ensures the timeliness of the sample set, that is, the sample set changes dynamically with the pathogenic factors and diagnostic departments, thereby ensuring that the intelligent registration information is more accurate.

[0075] For ease of understanding, a specific example is provided below to further explain the present application.

[0076] Embodiment 1:

[0077] See also Figure 4 The timing diagram of the solution provided in this embodiment is shown in FIG. Figure 5 ,pass Figure 4 and Figure 5 It can be seen that patients can input basic information such as age, gender, and physical symptoms through mobile smart devices, and then segment the patient's description of symptoms through natural language processing. For example, the symptom description information "I have a fever today" is segmented into "I", "today", and "fever", and their unique correct segmentation form is recorded in a table. The logical processing service obtains valuable patient symptom information from the segmentation information, and then filters out relevant data sets based on the information. For example, the valuable patient symptom information obtained from the segmentation information just now is "fever". The sample set related to fever that can be found in the database is detailed in Table 1 (for the convenience of calculation, 14 samples sorted in reverse order by date are retained here):

[0078]

[0079] Table 1

[0080] From the sample data in Table 1, we can see that this sample has "body temperature over 39 degrees Celsius", "cough", "runny nose", "throat pain", and "chest tightness" as branch attributes, and the registration department as the sample classification attribute has 4 categories: "respiratory department", "cardiology department", "internal medicine department", and "emergency department". There are 14 samples in total, including 6 "respiratory department", 2 "cardiology department", 1 "internal medicine department", and 5 "emergency department". Let this sample set be S. According to the entropy calculation formula Entropy(S), the entropy value before classification is:

[0081]

[0082] Assuming that "body temperature exceeds 39 degrees Celsius" is used as the branch attribute, the split data is divided into two branches, see Figure 2 shown.

[0083] The information entropy of the branch sample set with body temperature exceeding 39 degrees Celsius is:

[0084]

[0085] The information entropy of the branch sample set with body temperature not higher than 39 degrees Celsius is:

[0086]

[0087] According to the information gain calculation formula Let the attribute "whether the body temperature is higher than 39 degrees Celsius" be X. From this, we can calculate that the information gain after splitting as a branch attribute is:

[0088]

[0089] Similarly, the information gain of other attributes as branch attributes can be calculated. The information gain of "runny nose", "cough" and "chest tightness" as branch attributes are 0.1999, 0.3599 and 0.4636 respectively. It can be seen that "body temperature over 39 degrees Celsius" can obtain the maximum information gain when used as a branch attribute, that is, it has the strongest ability to distinguish samples, so here we choose to use "body temperature over 39 degrees Celsius" as the root node of the branch attribute for division. After this split, two sample sets appear. The sample set with body temperature over 39 degrees Celsius is shown in Table 2 below:

[0090]

[0091] Table 2

[0092] The sample set with body temperature below 39 degrees Celsius is as follows in Table 3:

[0093]

[0094]

[0095] Table 3

[0096] Then, the entropy value before splitting is calculated for the two sample sets respectively, and the information gain with "runny nose", "cough" and "chest tightness" as branch attributes is calculated respectively. If the classification attribute of the newly generated node is not unique, the newly generated node will continue to be split, and this step will be repeated until all samples belong to the same category. (In order to ensure calculation efficiency, restrictions such as the maximum depth of the decision tree can be preset).

[0097] In the process of building a decision tree, after all attributes are used for branching, samples of different categories still exist in the same leaf node. The branching conditions in the sample data cannot distinguish samples from more than two departments. In addition, when the restriction condition is reached and the construction is forced to stop, there will be a situation where there are multiple classifications in the sample set of the node. In this case, the department with the majority of samples in this node is taken as the classification of the node (it can also give multiple registration department suggestions for patients based on the proportion of the number of departments).

[0098] The decision tree finally formed by the sample set is shown in Figure 3 shown.

[0099] The AI ​​robot simulates the clinical doctor's consultation thinking, and traverses the decision tree according to the decision tree nodes and the patient's answers until there are no child nodes. According to the final leaf node, the patient's registration department is determined and suggestions are given. After obtaining the patient's input symptom information of fever, the robot asks the patient "Is the body temperature over 39 degrees Celsius?" through message push. The patient answers yes or no. For patients who answer yes, the decision tree traversal ends, and the robot gives the conclusion that the patient should go to the "emergency room" and reminds the patient to "avoid strenuous exercise." For patients who answer no, the robot continues to ask "Do you have a cough?" through message push. When the patient answers yes, the decision tree leaf node "Respiratory Department" is the last layer of the branch. At this time, through message push, the robot gives the conclusion that the patient should go to the "Respiratory Department" and reminds the patient to "avoid spicy and greasy food on the day of the consultation." When the patient answers no, the decision tree traversal and question-and-answer process continue to be repeated.

[0100] After the patient completes the consultation in the hospital, the system collects the patient's case and diagnosis-related information, and forms structured sample information in the sample set according to the data processing method described in the second paragraph. The sample will affect the generation of new decision trees in the intelligent registration system and affect the decision of the registration department. That is, the intelligent registration system will give the latest registration conclusion as the pathogenic factors mutate and the symptoms change.

[0101] In one embodiment, the present invention provides an intelligent registration device for simulating medical consultation, see Figure 6 The structure block diagram of a smart registration device for simulating medical consultation provided in this embodiment is shown, and the device includes: an information acquisition unit 10, an information search unit 20, a central control unit 30, and an output unit 40;

[0102] Information acquisition unit: used to understand the user's disease information through simulated consultation;

[0103] An information search unit is used to filter relevant case samples in the database according to the symptom information to obtain first case sample information;

[0104] The central control unit reads the sample information of the first case, uses the model trained by the ID3 algorithm to form a decision tree, and then simulates the clinical doctor's consultation according to the node information of the decision tree;

[0105] Output unit: used to evaluate the user's medical condition based on the consultation result information and give registration suggestions.

[0106] In the scheme of this embodiment, the user's symptom information is understood through a simulated consultation method; the relevant case samples in the database are screened according to the symptom information to obtain the case sample information; a decision tree is formed according to the case sample information using a model trained by the ID3 algorithm, and then the clinical doctor's consultation is simulated according to the node information of the decision tree; the user's illness is evaluated according to the consultation result information and registration suggestions are given. The simulated consultation thinking of the present invention can understand the patient's symptoms in detail, and use the decision tree algorithm to determine the department that the patient needs to register, and provide more scientific and accurate registration suggestions. At the same time, after the patient's diagnosed case is processed by data, it becomes a sample set of the decision tree algorithm, which ensures the timeliness of the sample set, that is, the sample set changes dynamically with the pathogenic factors and diagnostic departments, thereby ensuring that the intelligent registration information is more accurate.

[0107] The intelligent registration device for simulated medical consultation in this embodiment is used to implement the aforementioned intelligent registration method for simulated medical consultation. Therefore, the specific implementation method of the intelligent registration device for simulated medical consultation can be found in the specific implementation method of the intelligent registration method for simulated medical consultation in the previous text. For example, the information acquisition unit 10 is used to implement step S1 in the above-mentioned intelligent registration method for simulated medical consultation, and the information search unit 20 is used to implement step S2 in the above-mentioned intelligent registration method for simulated medical consultation, etc. Therefore, its specific implementation method can refer to the description of the corresponding various parts of the embodiments. The device provided by the present invention is attached to the method provided by the present invention, and its specific effects can refer to the above-mentioned method, which will not be repeated here.

[0108] In one embodiment, a computing device is provided, comprising:

[0109] A memory for storing program instructions;

[0110] A processor is used to implement the steps of any of the above-mentioned intelligent registration methods for simulated medical consultation when executing the computer program.

[0111] As an example, Figure 7 A schematic diagram of the structure of an electronic device applicable to the embodiment of the present application is shown. Figure 7 As shown, the electronic device 2000 includes: a processor 2001 and a memory 2003. The processor 2001 and the memory 2003 are connected, such as through a bus 2002. Optionally, the electronic device 2000 may also include a transceiver 2004. It should be noted that in actual applications, the transceiver 2004 is not limited to one, and the structure of the electronic device 2000 does not constitute a limitation on the embodiments of the present application.

[0112] The processor 2001 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 2004 may include a receiver and a transmitter. The transceiver 2004 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0113] Processor 2001 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 2001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0114] The bus 2002 may include a path to transmit information between the above components. The bus 2002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 2002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0115] The memory 2003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, 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 to these.

[0116] Optionally, the memory 2003 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 2001. The processor 2001 is used to execute the application code stored in the memory 2003 to implement the investment and financing project recommendation method provided in any embodiment of the present application.

[0117] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method and will not be described in detail here.

[0118] The intelligent registration method of simulated consultation provided by the present invention has obvious advantages and beneficial effects compared with the prior art. The user's symptom information is understood through simulated consultation; the relevant case samples in the database are screened according to the symptom information to obtain case sample information; a decision tree is formed according to the case sample information using a model trained by the ID3 algorithm, and then the clinical doctor's consultation is simulated according to the node information of the decision tree; the user's illness is evaluated according to the consultation result information and registration suggestions are given. The simulated consultation thinking of the present invention can understand the patient's symptoms in detail, and determine the department that the patient needs to register through the decision tree algorithm, providing more scientific and accurate registration suggestions. At the same time, after the patient's diagnosed case is processed by data processing, it becomes a sample set of the decision tree algorithm, which ensures the timeliness of the sample set, that is, the sample set changes dynamically with the pathogenic factors and the diagnosis department, thereby ensuring that the intelligent registration information is more accurate.

[0119] In one embodiment, a computer-readable storage medium is provided, including computer-readable instructions. When a computer reads and executes the computer-readable instructions, the steps of the above-mentioned intelligent registration method for simulated consultation are implemented. The intelligent registration method for simulated consultation provided by the present invention has obvious advantages and beneficial effects compared with the prior art. The user's symptom information is understood by simulating consultation; the relevant case samples in the database are screened according to the symptom information to obtain case sample information; a decision tree is formed according to the case sample information using a model trained by the ID3 algorithm, and then the clinical doctor's consultation is simulated according to the node information of the decision tree; the user's illness is evaluated according to the consultation result information and registration suggestions are given. The simulated consultation thinking of the present invention can understand the patient's symptoms in detail, and judge the department that the patient needs to register through the decision tree algorithm, and provide more scientific and accurate registration suggestions. At the same time, after the patient's diagnosed case is processed by data processing, it becomes a sample set of the decision tree algorithm, which ensures the timeliness of the sample set, that is, the sample set changes dynamically with the pathogenic factors and the diagnosis department, thereby ensuring that the intelligent registration information is more accurate.

[0120] Through the description of the above implementation methods, technical personnel 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 actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the specific device can be divided into different functional modules to complete all or part of the functions described above.

[0121] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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 this application.

[0122] In several embodiments covered by the present application, it should be understood that the disclosed devices, equipment and methods can be implemented in other ways. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, or it can be an electrical, mechanical or other form of connection.

[0123] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0124] In addition, each functional module in each embodiment of the present application can be implemented in the form of hardware or in the form of software functional modules. If these functional modules are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application is essentially or part of the prior art that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a computer program product, which includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application 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 devices. The computer program product is stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, a computer instruction can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks (SSDs)).

[0125] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent registration method for simulated medical consultation, characterized in that: Understand the user's disease information through simulated consultation; According to the symptom information, relevant case samples in the database are screened to obtain first case sample information; Read the first case sample information, use the model trained by the ID3 algorithm to form a decision tree, and then simulate the clinical doctor's consultation according to the node information of the decision tree; The user's medical condition is assessed based on the consultation result information and registration recommendations are given.

2. The intelligent registration method for simulated medical consultation according to claim 1, characterized in that: After evaluating the user's medical condition based on the medical inquiry result information and providing a registration suggestion, the method also includes: after the user is diagnosed according to the registration suggestion, collecting second case sample information after the user's diagnosis, and dynamically updating the database.

3. The intelligent registration method for simulated medical consultation according to claim 1, characterized in that: The forming of a decision tree by adopting a model trained by the ID3 algorithm comprises: The first case sample information is disassembled by natural language, and valuable symptom information is obtained from the disassembled first case sample information by logic processing service. According to the valuable symptom information, the corresponding branch attribute A and sample set S are searched from the database, and the formula is quoted: Among them, E(S) represents the entropy value of the sample set S, n represents the number of sample sets S, and there are n different values ​​in total. i Represents different categories of sample sets; Among them, E A (S) represents the sample entropy value of the branch attribute, S j represents the j-th subset of S divided according to the branch attribute A, and m represents the category corresponding to the branch attribute A in the database; Gain(S,A)=E(S)-E A (S) (3) Where Gain(S,A) represents the information gain of branch attribute A relative to sample set S; Substitute the sample set S into formula (1) to calculate the first information entropy of the data set; substitute the branch attribute A into formula (2) to calculate the second information entropy; substitute the first information entropy and the second information entropy into formula (3) to calculate the information gain; select the feature with the largest information gain as the current decision tree node according to the information gain result, and update the data set and feature set according to the feature.

4. The intelligent registration method for simulated medical consultation according to claim 3, characterized in that: The disassembling of the first case sample information by natural language includes: Obtaining outpatient case data as training sample source data, cleaning the training sample source data, removing invalid cases such as those that cannot be diagnosed and those with missing symptom information, and semantically annotating the cleaned cases; A term set of medical terms is obtained, and semantic annotation is performed on the original medical record content according to the term set; a sequence annotation model is trained based on the semantic annotation, and the sequence annotation model is used to identify different entities and relationships in the case text, divide the character strings in the medical record content into phrases, and extract the medical record structured information to obtain initial structured symptom information data.

5. The intelligent registration method for simulated medical consultation according to any one of claims 1 to 4, characterized in that: The method of understanding the user's symptom information through simulated medical consultation includes: the user inputs basic information such as age, gender, and physical symptoms through a mobile smart terminal device, and the mobile smart terminal device performs word segmentation processing on the user's description of the symptoms through natural language processing.

6. The intelligent registration method for simulated consultation according to claim 3, characterized in that: After selecting the feature with the largest information gain as the current decision tree node according to the information gain result, the method further includes: Dividing the current decision tree node into two sample sets, calculating entropy values ​​before splitting for the two sample sets respectively, and calculating information gains of other branch attributes; If the classification attribute of the newly generated node is not unique, the newly generated node will continue to be classified, and the process will be repeated until all samples belong to the same class.

7. The intelligent registration method for simulated medical consultation according to claim 6, characterized in that: According to the decision tree nodes and the user's answer, the decision tree is traversed until there are no child nodes; according to the final child node, the registration department to which the user belongs is determined and suggestions are given; after obtaining the symptom information input by the user, the specific details of the symptom information are provided to the user through message push; when the user's affirmative answer is obtained, the decision tree traversal is completed, the corresponding conclusion is given to the user, and the user is prompted to pay attention to the corresponding matters; when the user's negative answer is obtained, the questioning continues through message push until the user gives an affirmative answer, and the corresponding conclusion is given to the user through message push, and the user is prompted to pay attention to the corresponding matters; when the user answers no, the decision tree traversal and question-and-answer process continue to be repeated.

8. An intelligent registration device for simulating medical consultation, characterized in that: include: Information acquisition unit, information search unit, central control unit, output unit; Information acquisition unit: used to understand the user's disease information through simulated consultation; An information search unit is used to filter relevant case samples in the database according to the symptom information to obtain first case sample information; The central control unit reads the sample information of the first case, uses the model trained by the ID3 algorithm to form a decision tree, and then simulates the clinical doctor's consultation according to the node information of the decision tree; Output unit: used to evaluate the user's medical condition based on the consultation result information and give registration suggestions.

9. A computing device, characterized in that include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the method according to any one of claims 1 to 7 according to the obtained program instructions.

10. A computer-readable storage medium, characterized in that: It includes computer-readable instructions. When a computer reads and executes the computer-readable instructions, it implements the method as claimed in any one of claims 1 to 7. There can be multiple readable media, and the multiple readable media can operate independently of each other.

Images