Question and answer corpus recommendation method, device, computer equipment and storage medium

Abstract

The present application discloses a method, device, computer equipment and storage medium for recommending question-answer corpus, and belongs to the field of artificial intelligence technology. The present application maps and matches historical case data and professional symptom corpus to construct a professional symptom corpus, then obtains current case data, and calculates the similarity between the current case data and the historical case data to obtain case similarity, determines the case matching patient corresponding to the current patient based on the case feature similarity, obtains the target professional symptom corpus that matches the historical case data of the case matching patient, screens the target professional symptom corpus based on the collaborative filtering algorithm, obtains the symptom corpus to be pushed, and pushes the symptom corpus to be pushed to the current patient. In addition, the present application also relates to the field of blockchain technology, and case data can be stored on the nodes of the blockchain network. The present application promotes the efficiency of medical consultation by introducing collaborative filtering algorithms into the corpus recommendation of medical consultation scenarios.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a question-answer corpus recommendation method, apparatus, computer equipment and storage medium. Background Art

[0002] The intelligent question-and-answer system organizes the accumulated disordered corpus information in an orderly and scientific manner and establishes a knowledge-based classification model. These classification models can guide the newly added corpus consultation and service information, save human resources, improve the automation of information processing, and reduce website operating costs. It is based on the common questions and answers about the basic situation of the government and enterprises accumulated on the website over the years, and is organized into a standardized question-and-answer library to support intelligent question-and-answer of various forms of questions, which facilitates users, improves work efficiency, and enhances the corporate image.

[0003] However, most of the question-answering systems on the market are currently implemented based on keyword extraction. This method is only based on analyzing the user's current voice, extracting keywords, and then recommending question-answering corpora based on the extracted keywords. However, this method does not combine more user information of the user, resulting in poor corpus recommendation effects and affecting the user experience. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a question-and-answer corpus recommendation method, apparatus, computer equipment and storage medium to solve the technical problem that the existing question-and-answer corpus recommendation method does not combine more user information of the user, resulting in poor corpus recommendation effect and affecting the user experience.

[0005] In order to solve the above technical problems, the present application embodiment provides a question-answer corpus recommendation method, which adopts the following technical solution:

[0006] A question-answering corpus recommendation method, comprising:

[0007] Obtain historical case data from a preset case database, and obtain professional symptom corpus from a preset corpus;

[0008] Map and match historical case data and professional symptom corpus to build a professional symptom corpus;

[0009] Get the case data of the current patient and obtain the current case data;

[0010] Calculate the similarity between current case data and historical case data to obtain case similarity;

[0011] Determine the case matching patient corresponding to the current patient based on the similarity of case characteristics;

[0012] Obtaining target professional symptom corpus matching with historical case data of case-matched patients from a professional symptom corpus;

[0013] The target professional symptom corpus is screened based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed;

[0014] Push the symptom data to be pushed to the current patient.

[0015] Furthermore, the steps of mapping and matching the historical case data and the professional symptom corpus to construct a professional symptom corpus specifically include:

[0016] Extract symptom characteristics from historical case data to obtain historical symptom characteristics;

[0017] According to the historical symptom characteristics, the historical case data and professional symptom corpus are mapped and matched in the corpus to obtain the professional symptom corpus.

[0018] Furthermore, the steps of calculating the similarity between the current case data and the historical case data to obtain the case similarity specifically include:

[0019] Extract symptom features from current case data to obtain current symptom features;

[0020] Performing vector transformation on the current case feature to obtain the current case feature vector, and performing vector transformation on the historical case feature to obtain the historical case feature vector;

[0021] The cosine similarity between the current case feature vector and the historical case feature vector is calculated to obtain the case similarity.

[0022] Further, the steps of performing vector transformation on the current case feature to obtain the current case feature vector, and performing vector transformation on the historical case feature to obtain the historical case feature vector specifically include:

[0023] Assigning values ​​to the preset case feature table according to the current case features to obtain the current symptom feature table;

[0024] Parse the current symptom feature table to obtain the current case feature vector;

[0025] Assigning values ​​to the preset case characteristic table according to the historical case characteristics to obtain a historical symptom characteristic table;

[0026] Parse the historical symptom feature table to obtain the historical case feature vector.

[0027] Furthermore, the step of obtaining target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus specifically includes:

[0028] Obtain historical case data of patients matching the case, and obtain historical case data of the current patient;

[0029] Perform a data deduplication operation on the historical case data of the patient matching the case according to the historical case data of the current patient to obtain deduplicated case data;

[0030] Determine the professional symptom corpus corresponding to the deduplicated case data from the professional symptom corpus to obtain the target professional symptom corpus.

[0031] Furthermore, the target professional symptom corpus is screened based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed, which specifically includes:

[0032] Based on the collaborative filtering algorithm, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated to obtain the symptom similarity score;

[0033] Sort the symptom similarity scores, and determine the target symptoms to be pushed according to the similarity score sorting results;

[0034] The professional symptom corpus of the target symptom is determined from the target professional symptom corpus to obtain the symptom corpus to be pushed.

[0035] Furthermore, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated by the following formula to obtain the symptom similarity score:

[0036] Score(q)=∑cos(p i ,q)*Score(p i )

[0037] In the formula, Score(q) is the symptom similarity score, q is the symptom in the deduplicated case data, and p i is any symptom in the current case data, cos(p i ,q) is symptom q and symptom p i The similarity of Score(p i ) is the symptom p i Symptom scores in current case data.

[0038] In order to solve the above technical problems, the embodiment of the present application further provides a question-answer corpus recommendation device, which adopts the following technical solution:

[0039] A question-answer corpus recommendation device, comprising:

[0040] A historical data acquisition module is used to acquire historical case data from a preset case library and to acquire professional symptom corpus from a preset corpus;

[0041] The corpus construction module is used to map and match historical case data and professional symptom corpus to build a professional symptom corpus;

[0042] The current data acquisition module is used to acquire the case data of the current patient and obtain the current case data;

[0043] A case similarity calculation module is used to calculate the similarity between current case data and historical case data to obtain case similarity;

[0044] A patient matching module is used to determine the case matching patient corresponding to the current patient based on the similarity of case characteristics;

[0045] A corpus matching module is used to obtain target professional symptom corpus that matches the historical case data of case-matching patients from the professional symptom corpus;

[0046] The corpus screening module is used to screen the target professional symptom corpus based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed;

[0047] The corpus push module is used to push the symptom corpus to be pushed to the current patient.

[0048] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0049] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the question-answer corpus recommendation method as described above are implemented.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0051] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the question-and-answer corpus recommendation method as described above.

[0052] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0053] The present application discloses a method, device, computer equipment and storage medium for recommending question-answer corpus, and belongs to the field of artificial intelligence technology. The present application maps and matches historical case data and professional symptom corpus to construct a professional symptom corpus, then obtains current case data, and calculates the similarity between the current case data and the historical case data to obtain case similarity, determines the case matching patient corresponding to the current patient based on the case feature similarity, obtains the target professional symptom corpus that matches the historical case data of the case matching patient, and screens the target professional symptom corpus based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed, and pushes the symptom corpus to be pushed to the current patient. The present application introduces the collaborative filtering algorithm into the corpus recommendation of the consultation scenario, first calculates the matching patient with similar symptoms to the current patient through similarity, then obtains the professional symptom corpus corresponding to the historical case data of the matching patient, and pushes it to the current patient, accurately guides the patient to orally state the standard symptom information, effectively shortens the consultation time, and promotes the efficiency of the consultation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0056] Figure 2 A flowchart of an embodiment of a question-answer corpus recommendation method according to the present application is shown;

[0057] Figure 3 A schematic diagram showing the structure of an embodiment of a question-answer corpus recommendation device according to the present application is shown;

[0058] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0060] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0062] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0063] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0064] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0065] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0066] It should be noted that the question and answer corpus recommendation method provided in the embodiment of the present application is generally executed by a server, and accordingly, the question and answer corpus recommendation device is generally set in the server.

[0067] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0068] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for recommending question-answer corpus according to the present application. The method for recommending question-answer corpus includes the following steps:

[0069] S201, obtaining historical case data from a preset case library, and obtaining professional symptom corpus from a preset corpus.

[0070] S202, mapping and matching the historical case data and the professional symptom corpus to construct a professional symptom corpus.

[0071] Specifically, before the server recommends corpus, it needs to build a professional symptom corpus. First, the server obtains pre-collected historical case data from the preset case library. The historical case data can be crawled from the database of the authorized hospital. The historical case data records the symptoms and physical parameters of the historical patients. At the same time, the server obtains professional symptom corpus from the preset corpus, and maps and matches the historical case data and the professional symptom corpus to build a professional symptom corpus.

[0072] Furthermore, the steps of mapping and matching the historical case data and the professional symptom corpus to construct a professional symptom corpus specifically include:

[0073] Extract symptom characteristics from historical case data to obtain historical symptom characteristics;

[0074] According to the historical symptom characteristics, the historical case data and professional symptom corpus are mapped and matched in the corpus to obtain the professional symptom corpus.

[0075] Specifically, the server obtains professional symptom corpus from a preset corpus, and obtains historical symptom features by extracting symptom features from historical case data, and maps and matches historical case data and professional symptom corpus in the corpus based on the historical symptom features to obtain a professional symptom corpus.

[0076] In the above embodiment, the present application constructs a professional symptom corpus to facilitate subsequent patients to generate relevant professional symptom corpus when corpus recommendation is needed, so as to accurately guide patients to orally state standard symptom information, effectively shorten the consultation time, and promote the efficiency of the consultation.

[0077] S203, obtaining the case data of the current patient, and obtaining the current case data.

[0078] Specifically, after receiving the corpus recommendation instruction, the server obtains the case data of the current patient from the user client to obtain the current case data, wherein the current case data records the symptoms and physical parameters of the current patient.

[0079] In this embodiment, the question-answer corpus recommendation method is executed on an electronic device (eg Figure 1 The server shown in the figure) can receive the corpus recommendation instruction through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0080] S204, calculating the similarity between the current case data and the historical case data to obtain the case similarity.

[0081] Specifically, the server obtains the case data of the current patient, and obtains the case similarity by calculating the similarity between the current case data and the historical case data.

[0082] Furthermore, the steps of calculating the similarity between the current case data and the historical case data to obtain the case similarity specifically include:

[0083] Extract symptom features from current case data to obtain current symptom features;

[0084] Performing vector transformation on the current case feature to obtain the current case feature vector, and performing vector transformation on the historical case feature to obtain the historical case feature vector;

[0085] The cosine similarity between the current case feature vector and the historical case feature vector is calculated to obtain the case similarity.

[0086] Specifically, the server extracts historical symptom features from historical case data and current symptom features from current case data, and performs vector conversion on the historical symptom features and current case features to obtain historical case feature vectors and current case feature vectors. Finally, the server calculates the cosine similarity between the current case feature vector and the historical case feature vector to obtain the case similarity.

[0087] In a specific embodiment of the present application, the case similarity is obtained by calculating the cosine similarity between the current case feature vector and the historical case feature vector. The calculation formula of the cosine similarity is as follows:

[0088]

[0089] In the formula, x is the current feature vector, y is the historical feature vector, and x i is the i-th vector data in the current feature vector, y i is the i-th vector data in the historical feature vector, l (x，y) is the case similarity.

[0090] In the above embodiment, the present application performs feature extraction and feature vector conversion on the current case data and the historical case data, and calculates the case similarity between the current case feature vector and the historical case feature vector by cosine similarity, so as to determine the patient who matches the current patient.

[0091] Further, the steps of performing vector transformation on the current case feature to obtain the current case feature vector, and performing vector transformation on the historical case feature to obtain the historical case feature vector specifically include:

[0092] Assigning values ​​to the preset case feature table according to the current case features to obtain the current symptom feature table;

[0093] Parse the current symptom feature table to obtain the current case feature vector;

[0094] Assigning values ​​to the preset case characteristic table according to the historical case characteristics to obtain a historical symptom characteristic table;

[0095] Parse the historical symptom feature table to obtain the historical case feature vector.

[0096] Specifically, the present application realizes the conversion of case feature vectors through a preset case feature table. A specific case feature table is shown in the following table:

[0097] Table 1 Case characteristics

[0098] symptom cough Yellow nasal discharge Phlegm Itchy throat Fear of cold fever …… Assignment 1 1 0 1 0 1 ……

[0099] The number of symptoms can be selected according to different medical departments. For example, a case feature table counts a total of 8 symptoms. In a specific embodiment of the present application, the symptoms displayed in the case data of patient Zhang San include "cough", "yellow nasal discharge", "itchy throat" and "fever". Then, the symptoms are assigned in the preset case feature table, and the case feature vector is obtained by parsing the symptom feature table as (1, 1, 0, 1, 0, 1, 0, 0).

[0100] In the above embodiment, the case feature vector can be generated by performing symptom statistics through a preset case feature table.

[0101] S205, determining a case matching patient corresponding to the current patient based on the case feature similarity.

[0102] Specifically, the server determines the case-matching patient corresponding to the current patient based on the similarity of case features. The server uses the historical patient corresponding to the historical case data with the greatest similarity to the current case data as the case-matching patient, and pushes the professional symptom corpus used by the historical patient to the current patient, so as to accurately guide the patient to orally state the standard symptom information, effectively shorten the consultation time, and promote the efficiency of the consultation.

[0103] S206, obtaining target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus.

[0104] Specifically, after determining the case-matching patient, the server obtains target professional symptom corpus that matches the historical case data of the case-matching patient from the professional symptom corpus, wherein the target professional symptom corpus is the professional symptom corpus that the server has pushed to the case-matching patient.

[0105] Furthermore, the step of obtaining target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus specifically includes:

[0106] Obtain historical case data of patients matching the case, and obtain historical case data of the current patient;

[0107] Perform a data deduplication operation on the historical case data of the patient matching the case according to the historical case data of the current patient to obtain deduplicated case data;

[0108] Determine the professional symptom corpus corresponding to the deduplicated case data from the professional symptom corpus to obtain the target professional symptom corpus.

[0109] Specifically, before pushing the professional symptom corpus, the server will also perform a deduplication operation on the professional symptom corpus that has been pushed for the current patient, by obtaining the historical case data of the case-matching patient and the historical case data of the current patient, and performing a data deduplication operation on the historical case data of the case-matching patient based on the historical case data of the current patient to obtain the deduplicated case data, and determine the professional symptom corpus corresponding to the deduplicated case data from the professional symptom corpus to obtain the target professional symptom corpus, thereby reducing server overhead through data deduplication operations.

[0110] S207, screening the target professional symptom corpus based on a collaborative filtering algorithm to obtain the symptom corpus to be pushed.

[0111] Among them, collaborative filtering simply uses the preferences of a group of people with similar interests and common experiences to recommend information of interest to users. Individuals give a certain degree of response to the information (such as ratings, etc.) through a cooperative mechanism and record it to achieve the purpose of filtering and then help others filter information. Responses are not necessarily limited to those of particular interest. Records of information of particular disinterest are also very important. Collaborative filtering can be divided into rating or social filtering. Collaborative filtering is very popular in the global Internet field for its excellent speed and robustness.

[0112] Specifically, the present application introduces collaborative filtering algorithm into the corpus recommendation of medical consultation scenarios, screens the target professional symptom corpus through the collaborative filtering algorithm, obtains the symptom corpus to be pushed, and accurately guides patients to orally state standard symptom information, effectively shortens the consultation time, and promotes the efficiency of the consultation.

[0113] Furthermore, the target professional symptom corpus is screened based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed, which specifically includes:

[0114] Based on the collaborative filtering algorithm, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated to obtain the symptom similarity score;

[0115] Sort the symptom similarity scores, and determine the target symptoms to be pushed according to the similarity score sorting results;

[0116] The professional symptom corpus of the target symptom is determined from the target professional symptom corpus to obtain the symptom corpus to be pushed.

[0117] Specifically, the server calculates the similarity between each symptom in the current case data and each symptom in the matching historical case data to obtain a symptom similarity score, and then sorts the symptom similarity scores, and determines the top three symptoms in terms of similarity scores with the current symptoms as the target symptoms to be pushed, that is, the symptoms that the current patient is most likely to have, and determines the professional symptom corpus of the target symptom from the target professional symptom corpus to obtain the symptom corpus to be pushed.

[0118] Furthermore, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated by the following formula to obtain the symptom similarity score:

[0119] Score(q)=∑cos(p i ,q)*Score(p i )

[0120] In the formula, Score(q) is the symptom similarity score, q is the symptom in the deduplicated case data, and p iis any symptom in the current case data, cos(p i ,q) is symptom q and symptom p i The similarity of Score(p i ) is the symptom p i Symptom score in the current case data, Score(p i ) can also be calculated using the above formula, for example:

[0121] Score(p i )=∑cos(p i' ,p i )*Score(p i' )

[0122] In the formula, p i' For the previous case data, except for p i Any symptom other than

[0123] In the above embodiment, the present application screens the target professional symptom corpus through a collaborative filtering algorithm to obtain the symptom corpus to be pushed, so as to accurately guide the patient to orally state the standard symptom information, effectively shorten the consultation time, and promote the efficiency of the consultation.

[0124] S208, pushing the symptom corpus to be pushed to the current patient.

[0125] Specifically, after determining the symptom corpus to be pushed, the server sends the symptom corpus to be pushed to the user terminal of the current patient, and accurately guides the patient to orally state the standard symptom information.

[0126] In the above embodiment, the present application introduces a collaborative filtering algorithm into the corpus recommendation of the medical consultation scenario, firstly calculates the matching patients with similar symptoms to the current patient through similarity, then obtains the professional symptom corpus corresponding to the historical case data of the matching patients, and pushes it to the current patient, accurately guiding the patient to orally state the standard symptom information, effectively shortening the consultation time and promoting the efficiency of the consultation.

[0127] It should be emphasized that in order to further ensure the privacy and security of the above case data, the above case data can also be stored in a blockchain node.

[0128] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0130] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0131] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a question-answer corpus recommendation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0132] like Figure 3 As shown, the question-answer corpus recommendation device described in this embodiment includes:

[0133] The historical data acquisition module 301 is used to acquire historical case data from a preset case library and acquire professional symptom corpus from a preset corpus;

[0134] A corpus construction module 302 is used to map and match historical case data and professional symptom corpus to construct a professional symptom corpus;

[0135] The current data acquisition module 303 is used to acquire the case data of the current patient and obtain the current case data;

[0136] The case similarity calculation module 304 is used to calculate the similarity between the current case data and the historical case data to obtain the case similarity;

[0137] Patient matching module 305, for determining a case matching patient corresponding to the current patient based on case feature similarity;

[0138] A corpus matching module 306 is used to obtain target professional symptom corpus that matches the historical case data of the case matching patient from the professional symptom corpus;

[0139] The corpus screening module 307 is used to screen the target professional symptom corpus based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed;

[0140] The corpus pushing module 308 is used to push the symptom corpus to be pushed to the current patient.

[0141] Furthermore, the corpus construction module 302 specifically includes:

[0142] A first feature extraction unit is used to extract symptom features from historical case data to obtain historical symptom features;

[0143] The corpus construction unit is used to map and match historical case data and professional symptom corpus in the corpus according to historical symptom characteristics to obtain a professional symptom corpus.

[0144] Furthermore, the case similarity calculation module 304 specifically includes:

[0145] The second feature extraction unit is used to extract the symptom features in the current case data to obtain the current symptom features;

[0146] A vector conversion unit, used to perform vector conversion on the current case feature to obtain the current case feature vector, and to perform vector conversion on the historical case feature to obtain the historical case feature vector;

[0147] The case similarity calculation unit is used to calculate the cosine similarity between the current case feature vector and the historical case feature vector to obtain the case similarity.

[0148] Furthermore, the vector conversion unit specifically includes:

[0149] The first assignment subunit is used to assign values ​​to a preset case feature table according to the current case feature to obtain a current symptom feature table;

[0150] The first parsing subunit is used to parse the current symptom feature table to obtain the current case feature vector;

[0151] The second assignment subunit is used to assign values ​​to a preset case characteristic table according to the historical case characteristics to obtain a historical symptom characteristic table;

[0152] The second parsing subunit is used to parse the historical symptom feature table to obtain the historical case feature vector.

[0153] Furthermore, the corpus matching module 306 specifically includes:

[0154] A case acquisition unit, used to acquire historical case data of patients matching the case, and to acquire historical case data of the current patient;

[0155] A data deduplication unit, used to perform a data deduplication operation on the historical case data of the patient matching the case according to the historical case data of the current patient, to obtain deduplicated case data;

[0156] The corpus matching unit is used to determine the professional symptom corpus corresponding to the deduplicated case data from the professional symptom corpus to obtain the target professional symptom corpus.

[0157] Furthermore, the corpus screening module 307 specifically includes:

[0158] A similarity score calculation unit, used to calculate the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics based on a collaborative filtering algorithm to obtain a symptom similarity score;

[0159] A score sorting unit is used to sort the symptom similarity scores and determine the target symptoms to be pushed according to the similarity score sorting results;

[0160] The corpus screening unit is used to determine the professional symptom corpus of the target symptom from the target professional symptom corpus to obtain the symptom corpus to be pushed.

[0161] Furthermore, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated by the following formula to obtain the symptom similarity score:

[0162] Score(q)=∑cos(p i ,q)*Score(p i )

[0163] In the formula, Score(q) is the symptom similarity score, q is the symptom in the deduplicated case data, and p i is any symptom in the current case data, cos(p i ,q) is symptom q and symptom p i The similarity of Score(p i ) is the symptom p i Symptom scores in current case data.

[0164] In the above embodiment, the present application discloses a question-and-answer corpus recommendation device, which belongs to the field of artificial intelligence technology. The present application maps and matches historical case data and professional symptom corpus to construct a professional symptom corpus, then obtains current case data, and calculates the similarity between the current case data and the historical case data to obtain case similarity, determines the case matching patient corresponding to the current patient based on the case feature similarity, obtains the target professional symptom corpus that matches the historical case data of the case matching patient, and screens the target professional symptom corpus based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed, and pushes the symptom corpus to be pushed to the current patient. The present application introduces the collaborative filtering algorithm into the corpus recommendation of the consultation scenario, first calculates the matching patient with similar symptoms to the current patient through similarity, then obtains the professional symptom corpus corresponding to the historical case data of the matching patient, and pushes it to the current patient, accurately guides the patient to orally state the standard symptom information, effectively shortens the consultation time, and promotes the efficiency of the consultation.

[0165] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0166] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0167] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0168] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the question-answer corpus recommendation method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0169] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the question-answer corpus recommendation method.

[0170] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0171] The present application discloses a computer device, belonging to the field of artificial intelligence technology. The present application maps and matches historical case data and professional symptom corpus to construct a professional symptom corpus, then obtains current case data, and calculates the similarity between the current case data and the historical case data to obtain case similarity, determines the case matching patient corresponding to the current patient based on the case feature similarity, obtains the target professional symptom corpus that matches the historical case data of the case matching patient, screens the target professional symptom corpus based on the collaborative filtering algorithm, obtains the symptom corpus to be pushed, and pushes the symptom corpus to be pushed to the current patient. The present application introduces the collaborative filtering algorithm into the corpus recommendation of the consultation scenario, first calculates the matching patient with similar symptoms to the current patient through similarity, then obtains the professional symptom corpus corresponding to the historical case data of the matching patient, and pushes it to the current patient, accurately guides the patient to orally state the standard symptom information, effectively shortens the consultation time, and promotes the efficiency of the consultation.

[0172] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the question-and-answer corpus recommendation method as described above.

[0173] The present application discloses a storage medium, belonging to the field of artificial intelligence technology. The present application maps and matches historical case data and professional symptom corpus to construct a professional symptom corpus, then obtains current case data, and calculates the similarity between the current case data and the historical case data to obtain case similarity, determines the case matching patient corresponding to the current patient based on the case feature similarity, obtains the target professional symptom corpus that matches the historical case data of the case matching patient, screens the target professional symptom corpus based on the collaborative filtering algorithm, obtains the symptom corpus to be pushed, and pushes the symptom corpus to be pushed to the current patient. The present application introduces the collaborative filtering algorithm into the corpus recommendation of the consultation scenario, first calculates the matching patient with similar symptoms to the current patient through similarity, then obtains the professional symptom corpus corresponding to the historical case data of the matching patient, and pushes it to the current patient, accurately guides the patient to orally state the standard symptom information, effectively shortens the consultation time, and promotes the efficiency of the consultation.

[0174] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0175] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A question-answer corpus recommendation method, characterized in that: include: Obtain historical case data from a preset case database, and obtain professional symptom corpus from a preset corpus; Mapping and matching the historical case data and the professional symptom corpus to construct a professional symptom corpus; Get the case data of the current patient and obtain the current case data; Calculating the similarity between the current case data and the historical case data to obtain case similarity; Determine a case matching patient corresponding to the current patient based on the case similarity; Acquire target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus; The target professional symptom corpus is screened based on a collaborative filtering algorithm to obtain the symptom corpus to be pushed; Pushing the symptom corpus to be pushed to the current patient; The step of acquiring target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus includes: Acquire historical case data of patients matching the case, and acquire historical case data of the current patient; Performing a data deduplication operation on the historical case data of the patient matching the case according to the historical case data of the current patient to obtain deduplicated case data; Determine the professional symptom corpus corresponding to the deduplicated case data from the professional symptom corpus to obtain target professional symptom corpus; The target professional symptom corpus is screened based on the collaborative filtering algorithm to obtain the symptom corpus to be pushed, including: Based on the collaborative filtering algorithm, the similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated to obtain a symptom similarity score, wherein the current symptom characteristics are the symptom characteristics corresponding to the current case data; Sorting the symptom similarity scores, and determining the target symptom to be pushed according to the similarity score sorting result; Determining the professional symptom corpus of the target symptom from the target professional symptom corpus to obtain the symptom corpus to be pushed; The similarity between the symptom characteristics in the deduplicated case data and the current symptom characteristics is calculated by the following formula to obtain a symptom similarity score: Score(q)=Σcos(p i ,q)*Score(p i ) In the formula, Score(q) is the symptom similarity score, q is the symptom in the deduplicated case data, and p i is any symptom in the current case data, cos(p i ,q) is symptom q and symptom p i The similarity of Score(p i ) is the symptom p i Symptom scores in the current case data; Score(p i ) is calculated by the following formula: Score(p i )=Σcos(p i' ,p i )*Score(p i' ) In the formula, p i ' is the previous case data except p i Any symptom other than 2. The question-answer corpus recommendation method according to claim 1, wherein: The mapping and matching of the historical case data and the professional symptom corpus to construct a professional symptom corpus includes: Extracting symptom characteristics from the historical case data to obtain historical symptom characteristics; According to the historical symptom characteristics, the historical case data and the professional symptom corpus are mapped and matched in the corpus to obtain the professional symptom corpus.

3. The question-answer corpus recommendation method according to claim 2, characterized in that: The calculating the similarity between the current case data and the historical case data to obtain the case similarity comprises: Extracting symptom characteristics from the current case data to obtain current symptom characteristics; Performing vector transformation on the current symptom feature to obtain a current case feature vector, and performing vector transformation on the historical symptom feature to obtain a historical case feature vector; The cosine similarity between the current case feature vector and the historical case feature vector is calculated to obtain the case similarity.

4. The question-answer corpus recommendation method according to claim 3, characterized in that: The vector conversion of the current symptom feature to obtain the current case feature vector, and the vector conversion of the historical symptom feature to obtain the historical case feature vector include: Assigning values ​​to a preset case feature table according to the current symptom feature to obtain a current symptom feature table; Parsing the current symptom feature table to obtain the current case feature vector; Assigning values ​​to a preset case characteristic table according to the historical symptom characteristics to obtain a historical symptom characteristic table; The historical symptom feature table is parsed to obtain the historical case feature vector.

5. A question-answer corpus recommendation device, characterized in that: The question-answer corpus recommendation device performs the steps of the question-answer corpus recommendation method according to any one of claims 1 to 4, including: A historical data acquisition module is used to acquire historical case data from a preset case library and to acquire professional symptom corpus from a preset corpus; A corpus construction module, used for mapping and matching the historical case data and the professional symptom corpus to construct a professional symptom corpus; The current data acquisition module is used to acquire the case data of the current patient and obtain the current case data; A case similarity calculation module, used to calculate the similarity between the current case data and the historical case data to obtain the case similarity; A patient matching module, used for determining a case matching patient corresponding to the current patient based on the case similarity; A corpus matching module, used to obtain target professional symptom corpus matching the historical case data of the case-matching patient from the professional symptom corpus; A corpus screening module is used to screen the target professional symptom corpus based on a collaborative filtering algorithm to obtain the symptom corpus to be pushed; The corpus pushing module is used to push the symptom corpus to be pushed to the current patient.

6. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the question-answer corpus recommendation method according to any one of claims 1 to 4 when executing the computer-readable instructions.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the question-and-answer corpus recommendation method according to any one of claims 1 to 4 are implemented.

Images