WO2020048333A1

WO2020048333A1 - Knowledge base update method and apparatus, and computer device and storage medium

Info

Publication number: WO2020048333A1
Application number: PCT/CN2019/102528
Authority: WO
Inventors: 刘丹; 胡雪莹; 刘坤
Original assignee: 平安医疗健康管理股份有限公司
Priority date: 2018-09-03
Filing date: 2019-08-26
Publication date: 2020-03-12
Also published as: CN109408644A

Abstract

A knowledge base update method, comprising: obtaining first update data corresponding to a medical knowledge base; extracting a first medical word from the first update data; obtaining a first application word corresponding to the first medical word according to a medical knowledge graph; querying second update data corresponding to the first application word; and updating an application knowledge base according to the second update data.

Description

Method, device, computer equipment and storage medium for updating knowledge base

Cross-reference to related applications

This application claims the priority of a Chinese patent application filed on September 3, 2018 with the Chinese Patent Office under the application number of 2018110209948 and entitled "Knowledge Base Update Method, Device, Computer Equipment, and Storage Medium", the entire contents of which are incorporated by reference Incorporated in this application.

Technical field

The present application relates to a method, an apparatus, a computer device, and a storage medium for updating a knowledge base.

Background technique

The conventional medical quality management knowledge system includes a medical knowledge base and an application-based knowledge base. The construction method is mainly to manually or semi-automatically structure the data, and to analyze and analyze the medical authority data such as drug specifications, pharmacopoeia, and prescription sets. Construct a "medical knowledge base", and then reprocess the "medical knowledge base" to generate an "application-based knowledge base" for each product to call.

However, the inventors realized that because medical-related authority data is updated frequently, when the medical knowledge base is updated, the corresponding content in the application-based knowledge base needs to be manually updated, which requires a lot of manpower each time, and the data update efficiency is low.

Summary of the Invention

According to various embodiments disclosed in the present application, a method, an apparatus, a computer device, and a storage medium for updating a knowledge base are provided.

A method for updating a knowledge base, including:

Acquiring first updated data corresponding to a medical knowledge base, the first medical word segmentation is a medical-level keyword represented by the first updated data;

Extracting a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Obtaining a first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas, where the first application segmentation is a keyword used to characterize an application level of the first medical segmentation;

Querying the second update data corresponding to the first application word segmentation; and

Updating the application-type knowledge base according to the second update data.

A knowledge base updating device includes:

A first update module, configured to obtain first update data corresponding to a medical knowledge base, where the first medical word segmentation is a medical-level keyword represented by the first update data;

An extraction module, configured to extract a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Atlas analysis module, configured to obtain a first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas, where the first application segmentation is a keyword used to characterize an application level of the first medical segmentation;

A query module, configured to query the second update data corresponding to the first application segmentation; and

The second update module is configured to update the application-type knowledge base according to the second update data.

A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the one or more processors are executed. The following steps:

One or more non-volatile storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

Acquiring first updated data corresponding to a medical knowledge base, where the first medical word segmentation is a medical-level keyword represented by the first updated data;

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features and advantages of the application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions in the embodiments of the present application more clearly, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can obtain other drawings according to the drawings without paying creative labor.

FIG. 1 is an application scenario diagram of a method for updating a knowledge base according to one or more embodiments.

FIG. 2 is a schematic flowchart of a method for updating a knowledge base according to one or more embodiments.

FIG. 3 is a schematic flowchart of a medical knowledge atlas generation method according to one or more embodiments.

FIG. 4 is a schematic flowchart of a request return method according to one or more embodiments.

FIG. 5 is a block diagram of a knowledge base updating apparatus according to one or more embodiments.

FIG. 6 is a block diagram of a computer device according to one or more embodiments.

detailed description

In order to make the scheme and advantages of the present application more clear and clear, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

The knowledge base update method provided in this application can be applied to the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through a network. The terminal sends the first update data to the server. After the server obtains the first update data, it first updates the medical knowledge base according to the first update data, and then obtains the first update data in the application database according to the medical knowledge map obtained through training. The corresponding second update data updates the application database; the medical knowledge map can extract the first medical word segmentation in the first update data and match the first application word segmentation corresponding to the first medical word segmentation according to the trained rules. Thereby, the second update data for updating the application knowledge base is obtained, and the application knowledge base is updated following the medical knowledge base. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.

In some embodiments, as shown in FIG. 2, a method for updating a knowledge base is provided. The method is applied to the server in FIG. 1 as an example, and includes the following steps:

S202. Acquire first update data corresponding to the medical knowledge base.

Medical knowledge base Medical related theoretically expressed data; such as manual or semi-automatic structured data, medical authority data such as drug specifications, pharmacopoeia, and prescription sets are split and analyzed to build a "medical knowledge base".

The first update data is used to update the medical knowledge base, such as medicines or prescriptions that do not exist in the original medical knowledge base; for example, the first updated data may be a new medicine in the medical knowledge base and related to this medicine Text description, this description can be a description of its efficacy, medicinal properties or appearance.

Specifically, when there is data to be updated in the medical knowledge base, the terminal may send the first update data to be updated to the server, and after the server obtains the first update data, it starts to perform subsequent step S204.

S204. Extract a first medical word segmentation from the first update data.

The first medical word segmentation is data corresponding to the first update data in the medical knowledge atlas that has an index function; such as a drug name or a keyword of a drug property.

The medical knowledge atlas is a visual data model that is trained based on historical diagnostic information, medical diagnosis and treatment experience, and can connect the medical knowledge base with the application-based knowledge base. The medical knowledge atlas is based on the first medical word segmentation and the first applied word segmentation. The mapping relationship between the medical knowledge base and the application-based knowledge base established by the mapping relationship between them. For example, the mapping relationship between the medicine name of the first medical word segmentation and the indication of the first application word segmentation can be reflected through this knowledge map.

Specifically, the medical knowledge atlas is a mapping relationship between a medical knowledge base and an application-based knowledge base established through a mapping relationship between a first medical word segmentation and a first application word segmentation. If the server needs to implement the application-based knowledge base to synchronize the medical knowledge base through the medical knowledge map, it must first extract the first medical word segmentation from the first update data.

S206. Obtain a first application segmentation corresponding to the first medical segmentation according to the medical knowledge atlas.

The first application word segmentation is data with an index function used to obtain the second updated data, such as keywords used to reflect the indication of a certain drug and its use in the clinic.

Specifically, the server obtains the first application participle corresponding to the first medical participle according to the trained mapping relationship; that is, the server can obtain an application-based knowledge base of the drug in clinical use according to a keyword such as a drug name to be updated Related keywords in.

S208: Query the second update data corresponding to the first application segmentation.

The second update data is used to update the application-based knowledge base. For example, when the first update data is a new drug and a description of the drug in the medical knowledge base, the second update data may be an application-based knowledge base. The knowledge base supplements the usage, dosage and precautions of this medicine in a certain type of disease or clinical treatment.

Specifically, the server inquires the second update data for updating the application-type knowledge base in the medical knowledge map according to the first application word segmentation.

S210: Update the application-type knowledge base according to the second update data.

The application-based knowledge base is a database that is established based on the first application word segmentation and reflects the actual use of the data in the medical knowledge base; for example, medicines corresponding to outpatient symptoms and the usage and consumption of medicines.

Specifically, after the server obtains the second update data, it starts an update step of the application database, and supplements the obtained second update data to a position corresponding to the first application word segmentation in the application database.

In the above embodiment, the server first updates the medical knowledge base according to the first update data, and then obtains the second update data corresponding to the first update data in the application database according to the medical knowledge map obtained by the training, and performs the application database update. Update; the medical knowledge map can extract the first medical word segmentation in the first update data, and match the first medical word segmentation corresponding to the first medical word segmentation according to the trained rules, so as to obtain the second used to update the application knowledge base Update the data and implement the application-based knowledge base to follow the medical knowledge base. There is no need to update two knowledge bases each time, which improves the efficiency of data update.

In some embodiments, referring to FIG. 3, before obtaining the first application segmentation corresponding to the first medical segmentation according to the medical knowledge at step S206 in the method for updating the knowledge base, the method for generating the medical knowledge atlas may further include: It includes the following steps:

S302. Extract a second medical word segmentation from a medical knowledge base.

The second medical word segmentation is to extract data such as keywords in the medical knowledge base to construct the index data of the medical knowledge base in the medical knowledge atlas; such as the names of medicines or keywords in the medical knowledge base.

Specifically, the server extracts keywords from the medical knowledge base used to construct an index of the medical knowledge base in the medical knowledge atlas. Optionally, the server may establish a keyword database to identify the keywords existing in the keyword database from the medical knowledge base as the second medical word segmentation; it may also recognize the second medical word segmentation from the medical knowledge base through semantic recognition rules ; Semantic recognition rules can use NLP (Natural Language Processing) natural language processing (NLP) technology to identify the meaning of the medical knowledge base, and extract or reorganize the second medical word segmentation.

S304. Extract a second application segmentation corresponding to the second medical segmentation from the application-based knowledge base.

The second application of word segmentation is also to extract data such as keywords in the application-based knowledge base to construct data from the index of the application-based knowledge base in the medical knowledge atlas; for example, to reflect the indications of a drug and its use in outpatient clinics. Keywords such as usage, etc.

Specifically, the server extracts keywords from the application-based knowledge base for constructing an index of the application-based knowledge base in the medical knowledge atlas. Optionally, the server may establish a keyword database, and identify keywords existing in the keyword database from the medical knowledge database as a second application word segmentation.

S306. Establish a correspondence between the second medical segmentation and the second application segmentation.

Specifically, since the application-based knowledge base is established based on the medical knowledge base, the application-based knowledge base may include part of the second medical word segmentation in the medical knowledge base, and the server may find each of the medical knowledge bases based on this relationship. A second medical word segmentation corresponding to the second medical word segmentation, thereby establishing a mapping relationship between the two. In addition, the server may also supplement the mapping relationship between the second medical segmentation and the second application segmentation according to the information supplemented by the technician.

S308. Generate a medical knowledge map according to the corresponding relationship.

Specifically, the server imports the second medical word segmentation and the second application word segmentation into the initial graph model, and expresses the mapping relationship between the second medical word segmentation and the second application word segmentation in a visual table or image form to form medical knowledge. Atlas.

In the above embodiment, according to the existing data of the medical knowledge base and the application-based knowledge base, the keywords of the two are extracted to establish a connection between the medical knowledge base and the application-based knowledge base, and a medical knowledge map is established for The information between the medical knowledge base and the application knowledge base is linked to prepare for the simultaneous update of the two libraries.

In some embodiments, step S302 in the above method for updating a knowledge base extracts a second medical word segmentation from a medical knowledge base, which may include: identifying medical keywords from the medical knowledge base according to a preset keyword database; obtaining semantic recognition rules, The supplementary word segmentation corresponding to the medical keywords is extracted from the medical knowledge base according to the semantic recognition rules; the medical keyword and the supplementary word segmentation are combined to obtain a second medical word segmentation.

The preset keyword database is a database containing a number of medical keywords established by technicians based on actual application requirements; such as a database containing commonly used drug names; medical keywords are keywords that reflect information in the medical knowledge base, such as drugs Keywords such as name, medicine, indication, etc. The supplementary word segmentation is used to supplement medical keywords, and is extracted by the server from the medical knowledge base according to semantic recognition rules.

Specifically, when the server obtains the second medical word segmentation, the server may first identify the second application word segmentation from the medical knowledge base through the semantic recognition rule through the preset keyword library constructed, and extract or reorganize the second medical word segmentation Apply word segmentation. Because the preset keywords may not include all the second medical word segmentation in the medical knowledge base that needs to be extracted to construct the medical knowledge base, the supplementary word segmentation may be extracted from the medical knowledge base to supplement the medical keywords through semantic recognition rules; Semantic recognition rules can use NLP (Natural Language Processing) technology to identify the meaning of the medical knowledge base and extract supplementary word segmentation for supplementing medical keywords.

In the above embodiment, by constructing a preset keyword database, it is ensured that the server can extract all medical keywords in the preset keyword database; and then the missing part of the preset keyword database is extracted through semantic recognition rules, thereby ensuring the server The second medical word segmentation can be accurately and comprehensively obtained from the medical knowledge base.

In some embodiments, referring to FIG. 4, the above method for updating a knowledge base may further include a request return method, which includes:

S402. Receive a medical knowledge request sent by a terminal. The medical knowledge request carries medical knowledge data and request data.

The medical knowledge request is a data request sent by the terminal to the server, and is used to obtain response data corresponding to the medical knowledge request from the server; for example, a data request sent by the terminal to the server to obtain an instance of a drug in clinical application. The medical knowledge data is the data part of the medical knowledge request for querying the medical knowledge base, such as the name of the medicine. The request data is related information of the medical knowledge data that needs to be obtained, that is, it can be an example of clinical application in the above example.

Specifically, when the terminal needs to obtain a data request that needs to be queried by using the medical knowledge map, the medical knowledge data is combined with the request data to generate a medical knowledge request, and the request is sent to the server. After the server receives the medical knowledge request, Perform the following steps based on the medical knowledge data and request data sections.

S404. Extract the requested medical word segmentation from the medical knowledge data.

The requested medical word segmentation is data corresponding to the medical knowledge data in the medical knowledge atlas that has an index function and is included in the second medical word segmentation; such as a drug name or a keyword of a medicinal property.

Specifically, in order to perform data query using the medical knowledge map, the server needs to extract the requested medical word segmentation in the medical knowledge data first.

S406. Obtain a request application segmentation corresponding to the requested medical segmentation according to the medical knowledge map.

Requested application segmentation is the data corresponding to the requested medical segmentation in the medical knowledge atlas. It is an indexed segmentation used to obtain response data. It is included in the second application segmentation, such as to reflect the indication of a drug and in the clinic. Keywords in usage, etc.

Specifically, the server obtains the requested application segmentation corresponding to the requested medical segmentation according to the trained mapping relationship; that is, the server can obtain the relevant key of the drug in the clinical application-based knowledge base based on keywords such as a drug name word.

S408: Obtain response data corresponding to the request data from the application-type knowledge base according to the requested application word segmentation.

Specifically, the server uses the requested application word segmentation as an index, searches the application-type knowledge base for content related to the requested application word segmentation, and then selects content corresponding to the requested data from the queried content according to the requested data as response data.

Optionally, when there are several application-type knowledge bases, the corresponding application-type knowledge bases may be first selected according to the request, and the content corresponding to the requested application word-forms is returned from the application-based word segment according to the request as response data.

S410. Send the reply data to the terminal.

Specifically, after the server obtains the response data from the application-based knowledge base, it returns the corresponding data to the terminal that sends the medical knowledge request to complete the data request process.

For example, a terminal initiates a medical knowledge request for a server to obtain an instance of a drug in clinical application. The medical knowledge data in the medical knowledge request is a description of the drug, and the request data is an instance of clinical application. After the server obtains the medical knowledge request, it extracts the description request medical segmentation from the content describing the medicine, such as the name, appearance, and medicinal properties of the medicine, and then locates the medicine from the medical knowledge map, and then from the medical knowledge map Get the relevant request application segmentation of this drug in the commonly used field of the drug. According to the name and common field of the drug, query the clinical case of this drug from the application-based knowledge base of the corresponding field as the response data and return to The terminal that initiated this medical knowledge request.

In the above embodiment, the mapping relationship between the medical knowledge base trained in the medical knowledge map and the content of the application-based knowledge base can be used to intelligently and conveniently output corresponding professional content to each product according to the medical knowledge request.

In some embodiments, after the step S210 in the above method for updating a knowledge base updates the application-type knowledge base according to the second update data, the method may further include: obtaining verification data corresponding to the second update data; comparing the second update data with Whether the verification data are the same, if different, correct the medical knowledge map based on the verification data.

The verification data is data for verifying whether the second update data is correct, and the server may obtain data when the application database is manually updated separately as verification data.

Specifically, after the server obtains the second update data according to the above-mentioned knowledge base update method, the server may obtain data when the application database is manually updated separately as verification data, and compare the second update data with the verification data, if they are not the same , The medical knowledge map may have a mismatch between the first medical word segmentation and the first application word segmentation, or there may be no content related to the first update data in the medical knowledge map. At this time, the medical knowledge map is corrected according to the verification data, such as correcting the matching relationship between the first medical word segmentation and the first application word segmentation, or supplementing the relevant content of the first medical word segmentation corresponding to the first updated data in the medical knowledge map and establishing Its relationship with the application-based knowledge base.

In the foregoing embodiment, when the mapping relationship between the medical knowledge base and the content of the application-based knowledge base established according to the medical knowledge map is used to update the application-based knowledge base, the second update data obtained by the medical knowledge map may not appear. Accurate conditions, so that the medical knowledge atlas can be corrected regularly to ensure the accuracy of the medical knowledge atlas in application.

It should be understood that although the steps in the flowcharts of FIGS. 2 to 4 are sequentially displayed in accordance with the directions of the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless explicitly stated in this document, the execution of these steps is not strictly limited, and these steps can be performed in other orders. Moreover, at least a part of the steps in FIGS. 2 to 4 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. These sub-steps or The execution order of the phases is not necessarily performed sequentially, but may be performed in turn or alternately with other steps or at least a part of the sub-steps or phases of other steps.

As shown in FIG. 5, a device for updating a knowledge base is provided, including: a first update module 100, an extraction module 200, a map analysis module 300, a query module 400, and a second update module 500:

The first update module 100 is configured to obtain first update data corresponding to the medical knowledge base.

The extraction module 200 is configured to extract a first medical word segmentation from the first update data.

Atlas analysis module 300 is configured to obtain a first application segmentation corresponding to the first medical segmentation according to the medical knowledge atlas.

The query module 400 is configured to query the second update data corresponding to the first application segmentation.

The second update module 500 is configured to update the application-type knowledge base according to the second update data.

In some embodiments, the above knowledge base updating device may further include:

The first extraction module is configured to extract a second medical word segmentation from a medical knowledge base.

The second extraction module is configured to extract a second application segmentation corresponding to the second medical segmentation from the application-based knowledge base.

A relationship establishing module is configured to establish a correspondence between a second medical word segmentation and a second application word segmentation.

A model training module is used to generate a medical knowledge map according to the corresponding relationship.

In some embodiments, the first extraction module in the above knowledge base updating device may include:

A keyword extraction unit is configured to identify medical keywords from a medical knowledge base according to a preset keyword database.

A supplementary word segmentation extraction unit is configured to extract a supplementary word segmentation corresponding to a medical keyword from a medical knowledge base according to a semantic recognition rule.

The medical word segmentation obtaining unit is configured to combine a medical keyword and a supplementary word segmentation to obtain a second medical word segmentation.

The request receiving module is configured to receive a medical knowledge request sent by a terminal, and the medical knowledge request carries medical knowledge data and request data.

The requested medical word segmentation extraction module is used for extracting the requested medical word segmentation from the medical knowledge data.

The request application segmentation acquisition module is configured to obtain a request application segmentation corresponding to the requested medical segmentation according to the medical knowledge map.

The response data obtaining module is configured to obtain the response data corresponding to the request data from the application-type knowledge base according to the request application word segmentation.

The reply data sending module is used to send the reply data to the terminal.

The verification data obtaining module is configured to obtain verification data corresponding to the second update data.

A map correction module is used to compare whether the second updated data is the same as the verification data, and if different, correct the medical knowledge map based on the verification data.

For the specific limitation of the knowledge base updating device, refer to the foregoing limitation on the method of updating the knowledge base, and details are not described herein again. Each module in the above-mentioned knowledge base updating device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware form or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor calls and performs the operations corresponding to the above modules.

In some embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 6. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for operating the operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store knowledge base data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement a method for updating a knowledge base.

Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer equipment to which the scheme of the present application is applied. The specific computer equipment may be Include more or fewer parts than shown in the figure, or combine certain parts, or have a different arrangement of parts.

A computer device includes a memory and one or more processors. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the one or more processors execute the following steps:

Obtaining first updated data corresponding to the medical knowledge base;

Extracting a first medical word segmentation from the first update data;

Acquiring a first application segmentation corresponding to the first medical segmentation according to a medical knowledge atlas;

In some embodiments, before acquiring the first application segmentation corresponding to the first medical segmentation according to the medical knowledge atlas realized by the processor executing the computer-readable instructions, the method further includes:

Extracting a second medical word segmentation from the medical knowledge base;

Extracting a second application word segment corresponding to the second medical word segmentation from the application knowledge base;

Establishing a correspondence between the second medical participle and the second applied participle; and

Generating a medical knowledge map according to the corresponding relationship.

In some embodiments, extracting the second medical word segmentation from the medical knowledge base implemented by the processor when executing the computer-readable instructions may include:

Identifying medical keywords from the medical knowledge base according to a preset keyword library;

Acquiring a semantic recognition rule, and extracting a supplementary word segmentation corresponding to the medical keyword from the medical knowledge base according to the semantic recognition rule; and

Combining the medical keywords and the supplementary word segmentation to obtain a second medical word segmentation.

In some embodiments, when the processor executes the computer-readable instructions, the following steps are also implemented:

Receiving a medical knowledge request sent by a terminal, where the medical knowledge request carries medical knowledge data and request data;

Extracting requested medical word segmentation from the medical knowledge data;

Obtaining a requested application segmentation corresponding to the requested medical segmentation according to the medical knowledge atlas;

Obtaining response data corresponding to the request data from the application-based knowledge base according to the request application word segmentation; and

Sending the reply data to the terminal.

In some embodiments, after updating the application-type knowledge base according to the second update data implemented when the processor executes the computer-readable instructions, the method further includes:

Acquiring verification data corresponding to the second update data; and

Compare whether the second update data is the same as the verification data, and if different, correct the medical knowledge map according to the verification data.

One or more non-volatile computer-readable instruction storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

Obtaining first updated data corresponding to the medical knowledge base;

Extracting a first medical word segmentation from the first update data;

In some embodiments, before the computer-readable instructions implemented by the processor to obtain the first application segmentation corresponding to the first medical segmentation according to the medical knowledge map, the method further includes:

Extracting a second medical word segmentation from the medical knowledge base;

Generating a medical knowledge map according to the corresponding relationship.

In some embodiments, extracting the second medical word segmentation from the medical knowledge base when computer-readable instructions are executed by a processor includes:

In some embodiments, the computer-readable instructions, when executed by a processor, further implement the following steps:

Extracting requested medical word segmentation from the medical knowledge data;

Sending the reply data to the terminal.

In some embodiments, after the computer-readable instructions are executed by the processor and the application-type knowledge base is updated according to the second update data, the method may further include:

Acquiring verification data corresponding to the second update data; and

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in a non-volatile computer. In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined. In order to make the description concise, all possible combinations of the technical features in the above embodiments have not been described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be the range described in this specification.

The above embodiments only express several implementation manners of the present application, and the description thereof is more specific and detailed, but it cannot be understood as a limitation on the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of this application patent shall be subject to the appended claims.

Claims

A method for updating a knowledge base, including:

When an update of the medical knowledge base is detected, obtaining first update data from the medical knowledge base, the first medical word segmentation is a medical-level keyword represented by the first update data;

Extracting a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Acquiring the established mapping relationship between the first medical segmentation and the first application segmentation, and acquiring the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas according to the mapping relationship, the first application Word segmentation is a keyword used to characterize the first medical word segmentation at the application level;

Querying the second update data corresponding to the first application word segmentation; and

Updating the application-type knowledge base according to the second update data.
The method according to claim 1, before the acquiring the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas, further comprising:

Extracting a second medical word segmentation for training the connection between the medical knowledge base and the application knowledge base from the medical knowledge base;

Extracting a second application word segment corresponding to the second medical word segmentation from the application knowledge base;

Establishing a correspondence between the second medical participle and the second applied participle; and

Generating a medical knowledge map according to the corresponding relationship.
The method according to claim 2, wherein the extracting a second medical word segmentation for training a connection between the medical knowledge base and an application knowledge base from the medical knowledge base comprises:

Identifying medical keywords from the medical knowledge base according to a preset keyword library;

Acquiring a semantic recognition rule, and extracting a supplementary word segmentation corresponding to the medical keyword from the medical knowledge base according to the semantic recognition rule; and

Combining the medical keywords and the supplementary word segmentation to obtain a second medical word segmentation.
The method according to claim 1, further comprising:

Receiving a medical knowledge request sent by a terminal, where the medical knowledge request carries medical knowledge data and request data;

Extracting requested medical word segmentation from the medical knowledge data;

Obtaining a requested application segmentation corresponding to the requested medical segmentation according to the medical knowledge atlas;

Obtaining response data corresponding to the request data from the application-based knowledge base according to the request application word segmentation; and

Sending the reply data to the terminal.
The method according to claim 1, wherein after the updating the application-type knowledge base according to the second update data, further comprising:

Acquiring verification data corresponding to the second update data; and

Compare whether the second update data is the same as the verification data, and if different, correct the medical knowledge map according to the verification data.
A knowledge base updating device, characterized in that the device includes:

A first update module, configured to obtain first update data from the medical knowledge base when an update occurs in the medical knowledge base, where the first medical word segmentation is a medical-level keyword represented by the first update data;

An extraction module, configured to extract a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Atlas analysis module, configured to obtain the established mapping relationship between the first medical segmentation and the first application segmentation, and obtain the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas according to the mapping relationship The first applied word segmentation is a keyword used to characterize the first medical word segmentation at an application level;

A query module, configured to query the second update data corresponding to the first application segmentation; and

The second update module is configured to update the application-type knowledge base according to the second update data.
The apparatus according to claim 6, further comprising:

A first extraction module, configured to extract a second medical word segmentation from the medical knowledge base for training a connection between the medical knowledge base and an application knowledge base;

A second extraction module, configured to extract a second application segmentation corresponding to the second medical segmentation from the application-based knowledge base;

A relationship establishing module for establishing a correspondence between the second medical word segmentation and the second application word segmentation; and

A model training module is configured to generate a medical knowledge map according to the corresponding relationship.
The apparatus according to claim 7, wherein the first extraction module comprises:

A keyword extraction unit, configured to identify medical keywords from the medical knowledge base according to a preset keyword database;

A supplementary word segmentation extraction unit for extracting a supplementary word segmentation corresponding to the medical keyword from the medical knowledge base according to the semantic recognition rule; and

A medical word segmentation obtaining unit, configured to combine the medical keyword and the supplementary word segmentation to obtain a second medical word segmentation.
The apparatus according to claim 6, further comprising:

A request receiving module, configured to receive a medical knowledge request sent by a terminal, where the medical knowledge request carries medical knowledge data and request data;

Request medical word segmentation extraction module, for extracting requested medical word segmentation from the medical knowledge data;

A request application segmentation acquisition module, configured to obtain a request application segmentation corresponding to the requested medical segmentation according to the medical knowledge atlas;

A reply data acquisition module, configured to obtain reply data corresponding to the request data from the application-based knowledge base according to the request application word segmentation; and

The reply data sending module is configured to send the reply data to the terminal.
The apparatus according to claim 6, further comprising:

The verification data obtaining module is configured to obtain verification data corresponding to the second update data. and

A map correction module is used to compare whether the second updated data is the same as the verification data, and if different, correct the medical knowledge map based on the verification data.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more processors are caused. Each processor performs the following steps:

When an update of the medical knowledge base is detected, obtaining first update data from the medical knowledge base, the first medical word segmentation is a medical-level keyword represented by the first update data;

Extracting a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Acquiring the established mapping relationship between the first medical segmentation and the first application segmentation, and acquiring the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas according to the mapping relationship, the first application Word segmentation is a keyword used to characterize the first medical word segmentation at the application level;

Querying the second update data corresponding to the first application word segmentation; and

Updating the application-type knowledge base according to the second update data.
The computer device according to claim 11, wherein before the obtaining the first application segmentation corresponding to the first medical segmentation according to the medical knowledge atlas, which is executed when the processor executes the computer-readable instructions, further include:

Extracting a second medical word segmentation for training the connection between the medical knowledge base and the application knowledge base from the medical knowledge base;

Extracting a second application word segment corresponding to the second medical word segmentation from the application knowledge base;

Establishing a correspondence between the second medical participle and the second applied participle; and

Generating a medical knowledge map according to the corresponding relationship.
The computer device according to claim 12, characterized in that said extracting from said medical knowledge base and executed to train said medical knowledge base and application knowledge base executed by said processor when executing said computer-readable instructions The second medical participle, including:

Identifying medical keywords from the medical knowledge base according to a preset keyword library;

Acquiring a semantic recognition rule, and extracting a supplementary word segmentation corresponding to the medical keyword from the medical knowledge base according to the semantic recognition rule; and

Combining the medical keywords and the supplementary word segmentation to obtain a second medical word segmentation.
The computer device according to claim 11, wherein the processor further executes the following steps when executing the computer-readable instructions:

Receiving a medical knowledge request sent by a terminal, where the medical knowledge request carries medical knowledge data and request data;

Extracting requested medical word segmentation from the medical knowledge data;

Obtaining a requested application segmentation corresponding to the requested medical segmentation according to the medical knowledge atlas;

Obtaining response data corresponding to the request data from the application-based knowledge base according to the request application word segmentation; and

Sending the reply data to the terminal.
The computer device according to claim 11, wherein after the processor executes the computer-readable instructions, after the updating the application-type knowledge base according to the second update data, further comprising:

Acquiring verification data corresponding to the second update data; and

Compare whether the second update data is the same as the verification data, and if different, correct the medical knowledge map according to the verification data.
One or more non-transitory computer-readable instruction storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps :

When an update of the medical knowledge base is detected, obtaining first update data from the medical knowledge base, the first medical word segmentation is a medical-level keyword represented by the first update data;

Extracting a first medical word segmentation for retrieving a medical knowledge map from the first update data;

Acquiring the established mapping relationship between the first medical segmentation and the first application segmentation, and acquiring the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas according to the mapping relationship, the first application Word segmentation is a keyword used to characterize the first medical word segmentation at the application level;

Querying the second update data corresponding to the first application word segmentation; and

Updating the application-type knowledge base according to the second update data.
The storage medium according to claim 16, wherein the computer-readable instructions, which are implemented when the processor executes, obtain the first application segmentation corresponding to the first medical segmentation from the medical knowledge atlas. Before, it also included:

Extracting a second medical word segmentation for training the connection between the medical knowledge base and the application knowledge base from the medical knowledge base;

Extracting a second application word segment corresponding to the second medical word segmentation from the application knowledge base;

Establishing a correspondence between the second medical participle and the second applied participle; and

Generating a medical knowledge map according to the corresponding relationship.
The storage medium according to claim 17, wherein the computer-readable instructions, which are implemented when the processor executes, are extracted from the medical knowledge base for training the medical knowledge base and application knowledge base. Intermedical second participle, including:

Identifying medical keywords from the medical knowledge base according to a preset keyword library;

Acquiring a semantic recognition rule, and extracting a supplementary word segmentation corresponding to the medical keyword from the medical knowledge base according to the semantic recognition rule; and

Combining the medical keywords and the supplementary word segmentation to obtain a second medical word segmentation.
The storage medium according to claim 16, wherein the computer-readable instructions further implement the following steps when executed by the processor: receiving a medical knowledge request sent by a terminal, wherein the medical knowledge request carries medical knowledge Data and request data;

Extracting requested medical word segmentation from the medical knowledge data;

Obtaining a requested application segmentation corresponding to the requested medical segmentation according to the medical knowledge atlas;

Obtaining response data corresponding to the request data from the application-based knowledge base according to the request application word segmentation; and

Sending the reply data to the terminal.
The storage medium according to claim 16, wherein after the computer-readable instructions are executed by the processor to update an application-based knowledge base according to the second update data, further comprising:

Acquiring verification data corresponding to the second update data; and

Compare whether the second update data is the same as the verification data, and if different, correct the medical knowledge map according to the verification data.