CN113378554A

CN113378554A - Medical information intelligent interaction method and system

Info

Publication number: CN113378554A
Application number: CN202110638142.0A
Authority: CN
Inventors: 黄葵; 李井锐; 王先知
Original assignee: Hunan Trasen Technology Co ltd
Current assignee: Hunan Trasen Technology Co ltd
Priority date: 2021-06-08
Filing date: 2021-06-08
Publication date: 2021-09-10
Anticipated expiration: 2041-06-08
Also published as: CN113378554B

Abstract

According to the method and the system for the intelligent interaction of the medical information, the description content correlation between the description content of the sample medical information and the description content of the medical information of the key content to be selected is obtained, the key content to be selected is extracted from the key content to be selected, the first key content to be selected is obtained, the difference degree of the interaction content between the sample medical information and the first key content to be selected is determined aiming at each target medical information content, the difference degree of the interaction content extracted from the first key content to be selected is larger than the preset difference parameter of the interaction content, the second key content to be selected is obtained, and the target interaction key content is determined according to the second key content to be selected. The method and the device have the advantages that a large number of samples are not needed to be used for carrying out large-scale verification, labor cost can be saved, the matching degree of the target interaction scheme to new data is high, the integrity of target interaction is improved, and the determination of the key content to be selected and the interaction of the first key content to be selected and the second key content to be selected are faster.

Description

Medical information intelligent interaction method and system

Technical Field

The application relates to the technical field of information interaction, in particular to a method and a system for intelligently interacting medical information.

Background

With the continuous development of artificial intelligence, which is a very broad science composed of different fields, a main goal of research through artificial intelligence is to make machines competent for some complex tasks that usually require human intelligence to complete. But the understanding of this "complex work" is different for different times and for different people.

In the interaction technology of medical information, the interaction efficiency can be greatly improved by using artificial intelligence, so that the time cost can be effectively saved, but some defects exist in the related intelligent interaction technology.

Disclosure of Invention

In view of this, the present application provides a method and a system for intelligent interaction of medical information.

In a first aspect, a method for intelligent interaction of medical information is provided, which includes:

carrying out medical information interaction on sample medical information of target medical information content to be processed and medical information to be processed based on at least two medical information interaction modes, and determining key content to be selected of the target medical information content in the medical information to be processed, wherein the category of the target medical information content is at least one;

for each target medical information content, respectively identifying medical information description contents of the corresponding sample medical information and the key content to be selected to obtain the description contents of the sample medical information and the medical information description contents of the key content to be selected;

obtaining the description content correlation between the description content of the sample medical information corresponding to the same target medical information content and the medical information description content of the key content to be selected, and extracting the key content to be selected with the description content correlation meeting preset correlation parameters from the key content to be selected of the target medical information content to obtain the first key content to be selected of each target medical information content;

determining the interactive content difference degree of the corresponding sample medical information and the medical information of the first to-be-selected key content according to each target medical information content;

extracting the key content to be selected, of which the difference degree of the interactive content of the medical information is greater than the preset interactive content difference parameter, from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content;

and determining target interactive key content of each target medical information content according to the second key content to be selected of each target medical information content.

Further, the step of performing medical information interaction between the sample medical information of the target medical information content to be processed and the medical information to be processed based on at least two medical information interaction modes to determine key content to be selected of the target medical information content in the medical information to be processed includes:

carrying out substantial interaction on sample medical information of target medical information content to be processed and the medical information to be processed, and determining medical information key content of each target medical information content in the medical information to be processed, wherein the medical information key content is successfully subjected to substantial interaction and serves as the key content to be selected of each target medical information content;

sample medical information of the target medical information content to be processed is subjected to sample interaction with the medical information to be processed, and medical information key content of each target medical information content in the medical information to be processed, which is successfully sample-interacted, is determined and serves as key content to be selected of each target medical information content;

and performing description content point interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed, and determining medical information key content of each target medical information content in the medical information to be processed, wherein the description content point interaction of each target medical information content is successful and the medical information key content is used as the key content to be selected of each target medical information content.

Further, the step of performing substantial interaction between the sample medical information of the target medical information content to be processed and the medical information to be processed to determine medical information key content of each target medical information content in the medical information to be processed, which is successful in substantial interaction, before being used as the key content to be selected of each target medical information content, further includes:

acquiring a medical information content main label of sample medical information aiming at the sample medical information of the target medical information content to be processed;

and if the main label of the medical information content is a preset non-substantial content label, aiming at the sample medical information of the target medical information content, not loading the sample medical information of the target medical information content to be processed, and performing substantial interaction with the medical information to be processed.

Further, the performing sample interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed to determine medical information key content of each target medical information content in the medical information to be processed, which is successfully sample-interacted, as the key content to be selected of each target medical information content, includes:

respectively carrying out medical information classification on the sample medical information of the target medical information content to be processed and the medical information to be processed;

and carrying out sample interaction on the divided sample medical information and the divided medical information to be processed, and determining key contents to be selected of target medical information contents in the medical information to be processed according to an interaction result.

Further, the identifying, for each target medical information content, medical information description content of the corresponding sample medical information and key content to be selected, respectively, to obtain description content of the sample medical information and key content to be selected medical information description content, includes:

aiming at each target medical information content, carrying out identification operation on corresponding sample medical information to obtain identification description content of the sample medical information as description content of the sample medical information;

and aiming at each target medical information content, identifying the corresponding key content to be selected to obtain the identification description content of the key content to be selected as the medical information description content of the key content to be selected.

Further, the determining, for each target medical information content, the interactive content difference degree between the corresponding sample medical information and the medical information of the first to-be-selected key content includes:

determining a first interactive content average word number of the corresponding sample medical information and a second interactive content average word number of the medical information in the corresponding first to-be-selected key content aiming at each target medical information content;

and calculating the difference value of the average word number of the first interactive content and the average word number of the second interactive content to obtain the interactive content difference degree of the sample medical information of the target medical information content and the medical information of the first to-be-selected key content.

Further, the determining, for each target medical information content, a first interactive content average word number of the corresponding sample medical information and a second interactive content average word number of the medical information in the corresponding to-be-selected key content includes:

if the word number of the sample medical information of the target medical information content or the corresponding first to-be-selected key content is smaller than the preset word number, dividing the sample medical information and the first to-be-selected key content into medical information blocks with the same category according to the same dividing mode to obtain sample sub-medical information of the sample medical information and the first to-be-selected sub-key content of the first to-be-selected key content;

calculating the average word number of first interactive contents of each sample sub-medical information and the average word number of second interactive contents of each first sub-key content to be selected;

the calculating a difference value between the average word number of the first interactive content and the average word number of the second interactive content to obtain the interactive content difference degree between the sample medical information of the target medical information content and the medical information of the first to-be-selected key content includes: calculating the difference value of the average word number of the interactive contents between the sample sub-medical information of the corresponding interactive object in the sample medical information and the key contents to be selected and the first key contents to be selected based on the average word number of the first interactive contents and the average word number of the second interactive contents;

the step of extracting the key content to be selected, of which the difference degree of the interactive content of the medical information is greater than the preset interactive content difference parameter, from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content includes: and extracting at least one kind of key content to be selected with the interactive content average word number difference value larger than a preset difference parameter from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content.

Further, the determining target interactive key content of each target medical information content according to the second key content to be selected of the target medical information content includes:

if the second key content to be selected is not repeated with other second key content to be selected, determining the second key content to be selected as the target interactive key content of the corresponding target medical information content;

if the second key content to be selected is repeated with other second key content to be selected, determining the minimum unit key content containing the repeated second key content to be selected from the medical information to be processed, and determining the sample medical information of the target medical information content corresponding to the minimum unit key content;

interacting the minimum unit key content with sample medical information of target medical information content corresponding to the minimum unit key content;

and according to an interaction result, determining a target medical information content finally corresponding to the minimum unit key content and a target interaction key content of the target medical information content in the minimum unit key content.

Further, the interacting the minimum unit key content with the sample medical information of the target medical information content corresponding to the minimum unit key content includes:

if the types of the target medical information content corresponding to the minimum unit key content are at least two, respectively carrying out sample interaction on the minimum unit key content and the sample medical information of each corresponding target medical information content to obtain sample interaction key content interacted with each sample medical information in the minimum unit key content and a first sample interaction evaluation of the sample medical information and the sample interaction key content, wherein the first sample interaction evaluation is used for representing the interaction mode of the sample medical information and the sample interaction key content;

the determining, according to the interaction result, a target medical information content finally corresponding to the minimum unit key content and a target interaction key content of the target medical information content in the minimum unit key content includes: and according to the first sample interactive evaluation, determining sample medical information and sample interactive key content with the highest interactive mode, wherein the sample medical information and the sample interactive key content are respectively used as a target medical information content finally corresponding to the minimum unit key content and a target interactive key content of the target medical information content in the minimum unit key content.

In a second aspect, a system for intelligent interaction of medical information is provided, which comprises a processor and a memory, which are communicated with each other, wherein the processor is used for reading the computer program from the memory and executing the computer program, so as to realize the method.

According to the method and the system for intelligently interacting the medical information, the sample medical information of the target medical information content to be processed and the medical information to be processed are subjected to medical information interaction based on at least two medical information interaction modes, the key content to be selected of the target medical information content in the medical information to be processed is determined, wherein the type of the target medical information content is at least one, medical information description content identification is respectively carried out on the corresponding sample medical information and the key content to be selected aiming at each target medical information content, the description content of the sample medical information and the medical information description content of the key content to be selected are obtained, the description content of the sample medical information corresponding to the same target medical information content and the description content relevance between the description content of the medical information of the key content to be selected are obtained, the description content relevance is extracted from the key content to be selected of the target medical information content, and meets the preset relevance The method comprises the steps of obtaining first to-be-selected key content of each target medical information content through key content to be selected of parameters, determining the difference degree of the interaction content of the corresponding sample medical information and the medical information of the first to-be-selected key content aiming at each target medical information content, extracting the to-be-selected key content with the difference degree of the interaction content of the medical information larger than the preset interaction content difference parameter from the first to-be-selected key content of each target medical information content, obtaining second to-be-selected key content of each target medical information content, and determining the target interaction key content of the target medical information content according to the second to-be-selected key content of each target medical information content. Therefore, a large number of samples are not needed to be used for carrying out verification, labor cost can be saved, the target interaction scheme has high matching degree on new data, the integrity of target interaction is improved, and the determination of the key content to be selected and the interaction of the first key content to be selected and the second key content to be selected are quicker.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a flowchart of a method for intelligently interacting medical information according to an embodiment of the present application.

Fig. 2 is a block diagram of an apparatus for intelligently interacting medical information according to an embodiment of the present application.

Fig. 3 is an architecture diagram of a system for intelligently interacting medical information according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions of the present application, the following detailed descriptions of the technical solutions of the present application are provided with the accompanying drawings and the specific embodiments, and it should be understood that the detailed descriptions of the embodiments and the embodiments of the present application are detailed descriptions of the technical solutions of the present application, and are not limiting of the technical solutions of the present application, and the technical descriptions of the embodiments and the embodiments of the present application may be combined with each other without conflict.

Referring to fig. 1, a method for intelligent interaction of medical information is shown, which may include the following steps 100-600.

Step 100, performing medical information interaction on sample medical information of target medical information content to be processed and medical information to be processed based on at least two medical information interaction modes, and determining key content to be selected of the target medical information content in the medical information to be processed.

For example, the category of the target medical information content is at least one.

Step 200, for each target medical information content, respectively identifying medical information description content of the corresponding sample medical information and key content to be selected, so as to obtain description content of the sample medical information and medical information description content of the key content to be selected.

For example, the target medical information content represents a historical illness condition of the patient.

Step 300, obtaining the description content correlation between the description content of the sample medical information corresponding to the same target medical information content and the medical information description content of the key content to be selected, and extracting the key content to be selected, of which the description content correlation meets the preset correlation parameter, from the key content to be selected of the target medical information content to obtain the first key content to be selected of each target medical information content.

For example, the first candidate key content represents medical interaction information that satisfies the interaction requirement.

Step 400, for each target medical information content, determining the interactive content difference degree between the corresponding sample medical information and the medical information of the first to-be-selected key content.

Step 500, extracting the key content to be selected, of which the difference degree of the interactive content of the medical information is greater than the preset interactive content difference parameter, from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content.

For example, the second candidate key content represents key medical interaction content extracted from the first candidate key content.

Step 600, determining target interactive key content of each target medical information content according to second key content to be selected of the target medical information content.

For example, the target interactive key content represents the feature of intelligent interaction of medical information.

It can be understood that, when the technical solutions described in steps 100 to 600 are executed, the sample medical information of the target medical information content to be processed and the medical information to be processed are subjected to medical information interaction based on at least two medical information interaction modes, the key content to be selected of the target medical information content in the medical information to be processed is determined, wherein the category of the target medical information content is at least one, for each target medical information content, medical information description content identification is respectively performed on the corresponding sample medical information and the key content to be selected, so as to obtain the description content of the sample medical information and the key content medical information description content to be selected, obtain the description content correlation between the description content of the sample medical information corresponding to the same target medical information content and the key content medical information description content to be selected, and extract the description content correlation from the key content to be selected of the target medical information content, which satisfies the preset correlation The method comprises the steps of obtaining first to-be-selected key content of each target medical information content according to the to-be-selected key content of the relevance parameter, determining the difference degree of the interaction content of the corresponding sample medical information and the medical information of the first to-be-selected key content according to each target medical information content, extracting the to-be-selected key content of which the difference degree of the interaction content of the medical information is larger than the preset interaction content difference parameter from the first to-be-selected key content of each target medical information content, obtaining second to-be-selected key content of each target medical information content, and determining the target interaction key content of each target medical information content according to the second to-be-selected key content of each target medical information content. Therefore, a large number of samples are not needed to be used for carrying out verification, labor cost can be saved, the target interaction scheme has high matching degree on new data, the integrity of target interaction is improved, and the determination of the key content to be selected and the interaction of the first key content to be selected and the second key content to be selected are quicker.

In an alternative embodiment, the inventors have discovered that sample medical information of the target medical information content to be processed, when the medical information interaction is carried out on the basis of at least two medical information interaction modes with the medical information to be processed, the problem that the sample medical information of the target medical information content is inaccurate exists, so that it is difficult to accurately determine the key content to be selected of the target medical information content in the medical information to be processed, in order to improve the above technical problem, the sample medical information of the target medical information content to be processed described in step 100, the step of performing medical information interaction with the medical information to be processed based on at least two medical information interaction modes and determining the key content to be selected of the target medical information content in the medical information to be processed may specifically include the technical scheme described in the following step q 1-step q 3.

And q1, performing substantial interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed, and determining medical information key content of each target medical information content in the medical information to be processed, wherein the medical information key content is successfully subjected to substantial interaction and serves as the key content to be selected of each target medical information content.

And q2, performing sample interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed, and determining the medical information key content of each target medical information content in the medical information to be processed, which is successfully interacted with the sample, as the key content to be selected of each target medical information content.

And q3, performing description content point interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed, and determining the medical information key content of each target medical information content in the medical information to be processed, which is successfully interacted with the description content point, as the key content to be selected of each target medical information content.

It can be understood that, when the technical solutions described in the above steps q 1-q 3 are executed, when the sample medical information of the target medical information content to be processed and the medical information to be processed are subjected to medical information interaction based on at least two medical information interaction modes, the problem that the sample medical information of the target medical information content is inaccurate is avoided, so that the key content to be selected of the target medical information content in the medical information to be processed can be accurately determined.

Based on the above basis, the sample medical information of the target medical information content to be processed and the medical information to be processed perform substantial interaction, and before determining the medical information key content of each target medical information content in the medical information to be processed, which is successful in substantial interaction, as the to-be-selected key content of each target medical information content, the following technical solutions described in step w1 and step w2 may also be included.

And step w1, acquiring the medical information content main label of the sample medical information aiming at the sample medical information of the target medical information content to be processed.

Step w2, if the main label of the medical information content is a preset non-substantial content label, for the sample medical information of the target medical information content, not loading the sample medical information of the target medical information content to be processed, and performing substantial interaction with the medical information to be processed.

It can be understood that when the technical solutions described in the above steps w1 and w2 are executed, the accuracy of the step of performing substantial interaction on the medical information to be processed is improved by accurately obtaining the main label of the medical information content.

In an alternative embodiment, the inventors found that, when sample medical information of the target medical information content to be processed is sample-interacted with the medical information to be processed, there is a problem that classification of medical information is inaccurate, so that it is difficult to accurately determine medical information key content of each sample of the target medical information content in the medical information to be processed, as the candidate key content of each target medical information content, in order to improve the above technical problem, the step of sample-interacting the sample medical information of the target medical information content to be processed, described in step q2, with the medical information to be processed, determining medical information key content of each sample of the target medical information content in the medical information to be processed, as the candidate key content of each target medical information content, the method specifically comprises the technical scheme described in the following steps q2a1 and q2a 2.

And q2a1, classifying the sample medical information of the target medical information content to be processed and the medical information to be processed into medical information categories respectively.

And q2a2, performing sample interaction on the divided sample medical information and the divided medical information to be processed, and determining key contents to be selected of each target medical information content in the medical information to be processed according to an interaction result.

It can be understood that, when the technical solutions described in the above steps q2a1 and q2a2 are executed, when sample medical information of the target medical information content to be processed is sample-interacted with the medical information to be processed, the problem of inaccurate classification of medical information is avoided, so that the medical information key content of each target medical information content in the medical information to be processed, which is successfully sample-interacted, can be accurately determined as the candidate key content of each target medical information content.

In an alternative embodiment, the inventor finds that, when medical information description content identification is performed on corresponding sample medical information and candidate key content respectively for each target medical information content, there is a problem that description content of the sample medical information is not accurate, so that it is difficult to accurately obtain description content of the sample medical information and candidate key content medical information description content, and in order to improve the above technical problem, the step of performing medical information description content identification on corresponding sample medical information and candidate key content respectively for each target medical information content described in step 200 to obtain description content of the sample medical information and candidate key content medical information description content may specifically include the technical solutions described in the following steps e1 and e 2.

And e1, identifying the corresponding sample medical information according to the target medical information content, and obtaining the identification description content of the sample medical information as the description content of the sample medical information.

And e2, aiming at each target medical information content, identifying the corresponding key content to be selected to obtain the identification description content of the key content to be selected as the medical information description content of the key content to be selected.

It can be understood that, when the technical solutions described in the above steps e1 and e2 are executed, and medical information description content identification is respectively performed on corresponding sample medical information and candidate key content for each target medical information content, the problem that the description content of the sample medical information is not accurate is avoided, so that the description content of the sample medical information and the description content of the candidate key content medical information can be accurately obtained.

In an alternative embodiment, the inventor finds that, for each target medical information content, the average word number of the first interactive content and the average word number of the second interactive content are not accurate, so that it is difficult to accurately determine the interactive content difference degree of the corresponding sample medical information and the medical information of the first to-be-selected key content, and in order to improve the above technical problem, the step of determining the interactive content difference degree of the corresponding sample medical information and the medical information of the first to-be-selected key content for each target medical information content described in step 400 may specifically include the technical solutions described in the following step r1 and step r 2.

And r1, determining the first interactive content average word number of the corresponding sample medical information and the second interactive content average word number of the medical information in the corresponding first to-be-selected key content for each target medical information content.

And r2, calculating the difference between the average word number of the first interactive content and the average word number of the second interactive content to obtain the interactive content difference between the sample medical information of the target medical information content and the medical information of the first to-be-selected key content.

It can be understood that, when the technical solutions described in the above steps r1 and r2 are executed, the problem that the average word count of the first interactive contents and the average word count of the second interactive contents are not accurate is avoided for each target medical information content, so that the interactive content difference degree of the corresponding sample medical information and the medical information of the first to-be-selected key content can be accurately determined.

In an alternative embodiment, the inventor finds that, for each target medical information content, there is a problem that the first sub-key content to be selected is inaccurate, so that it is difficult to accurately determine the first interactive content average word number of the corresponding sample medical information and the second interactive content average word number of the medical information in the corresponding key content to be selected, and in order to improve the above technical problem, the step of determining the first interactive content average word number of the corresponding sample medical information and the second interactive content average word number of the medical information in the corresponding key content to be selected, which is described in step r1, for each target medical information content, may specifically include the technical solutions described in the following steps r1a 1-r 1a 4.

And r1a1, if the word number of the sample medical information or the corresponding first to-be-selected key content of the target medical information content is less than the preset word number, dividing the sample medical information and the first to-be-selected key content into medical information blocks with equal categories according to the same dividing mode to obtain sample sub-medical information of the sample medical information and the first to-be-selected sub-key content of the first to-be-selected key content.

And r1a2, calculating the average word number of the first interactive contents of each sample sub-medical information and the average word number of the second interactive contents of each first candidate sub-key content.

Step r1a3, where the calculating the difference between the first interactive content average word count and the second interactive content average word count to obtain the interactive content difference between the sample medical information of the target medical information content and the medical information of the first to-be-selected key content includes: and calculating the difference value of the average word number of the interactive contents of the sample sub-medical information and the first to-be-selected sub-key contents of the corresponding interactive objects in the sample medical information and the to-be-selected key contents based on the average word number of the first interactive contents and the average word number of the second interactive contents.

Step r1a4, the step of extracting the key content to be selected, of which the difference degree of the interactive content of the medical information is greater than the preset interactive content difference parameter, from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content includes: and extracting at least one kind of key content to be selected with the interactive content average word number difference value larger than a preset difference parameter from the first key content to be selected of each target medical information content to obtain the second key content to be selected of each target medical information content.

It can be understood that, when the technical solutions described in the above steps r1a 1-r 1a4 are executed, the problem that the first candidate sub-keyword is inaccurate is avoided for each target medical information content, so that the first interactive content average word number of the corresponding sample medical information and the second interactive content average word number of the medical information in the corresponding candidate keyword can be accurately determined.

In an alternative embodiment, the inventor finds that, when the second candidate key content of each target medical information content is selected, the target interactive key content is inaccurate, so that it is difficult to accurately determine the target interactive key content of the target medical information content, and in order to improve the above technical problem, the step of determining the target interactive key content of the target medical information content according to the second candidate key content of each target medical information content described in step 600 may specifically include the technical solutions described in the following steps y 1-y 4.

Step y1, if there is no repetition between the second key content to be selected and other second key content to be selected, determining that the second key content to be selected is the target interactive key content of the corresponding target medical information content.

Step y2, if the second candidate key content is repeated with other second candidate key content, determining the minimum unit key content containing the repeated second candidate key content from the to-be-processed medical information, and determining the sample medical information of the target medical information content corresponding to the minimum unit key content.

And y3, interacting the minimum unit key content with the sample medical information of the target medical information content corresponding to the minimum unit key content.

Step y4, according to the interaction result, determining a target medical information content finally corresponding to the minimum unit key content and a target interaction key content of the target medical information content in the minimum unit key content.

It can be understood that, when the technical solutions described in the above steps y 1-y 4 are performed, the problem of inaccurate target interactive key content is avoided according to the second candidate key content of each target medical information content, so that the target interactive key content of the target medical information content can be accurately determined.

In an alternative embodiment, the inventor finds that, when the minimum unit key content is interacted with the sample medical information of the target medical information content corresponding to the minimum unit key content, there is a problem that the minimum unit key content is inaccurate, so that it is difficult to accurately interact with the sample medical information of the target medical information content, and in order to improve the above technical problem, the step of interacting the minimum unit key content with the sample medical information of the target medical information content corresponding to the minimum unit key content described in step y3 may specifically include the technical solutions described in the following steps y3a1 and y3a 2.

Step y3a1, if the categories of the target medical information content corresponding to the minimum unit key content are at least two, respectively performing sample interaction on the minimum unit key content and the sample medical information of each corresponding target medical information content to obtain sample interaction key content interacting with each sample medical information in the minimum unit key content and a first sample interaction evaluation of the sample medical information and the sample interaction key content, wherein the first sample interaction evaluation is used for representing the interaction mode of the sample medical information and the sample interaction key content.

Step y3a2, the determining a target medical information content finally corresponding to the minimum unit key content and a target interactive key content of the target medical information content in the minimum unit key content according to the interaction result includes: and according to the first sample interactive evaluation, determining sample medical information and sample interactive key content with the highest interactive mode, wherein the sample medical information and the sample interactive key content are respectively used as a target medical information content finally corresponding to the minimum unit key content and a target interactive key content of the target medical information content in the minimum unit key content.

It can be understood that, when the technical solutions described in the above steps y3a1 and y3a2 are performed, when the minimum unit key content interacts with the sample medical information of the target medical information content corresponding to the minimum unit key content, the problem that the minimum unit key content is inaccurate is avoided, so that the sample medical information of the target medical information content can be accurately interacted.

Based on the above basis, before determining the target interactive key content of each target medical information content according to the second candidate key content of the target medical information content, the following technical solutions described in step a1 and step a2 may also be included.

Step a1, performing sample interaction on the corresponding sample medical information and second candidate key content aiming at each target medical information content, and determining a second sample interaction evaluation of each second candidate key content, wherein the second sample interaction evaluation is used for representing the interaction mode of the sample medical information and the second candidate key content.

Step a2, extracting the second sample interaction evaluation candidate key content meeting the preset sample interaction score parameter from the second candidate key content to obtain the updated second candidate key content.

It can be understood that, when the technical solutions described in the above steps a1 and a2 are executed, the second sample interactive evaluation of each second candidate key content is accurately determined, so as to improve the accuracy of the updated second candidate key content.

On the basis, please refer to fig. 2 in combination, a medical information intelligent interaction apparatus 200 is provided, which is applied to a data processing terminal, and includes:

the content determining module 210 is configured to perform medical information interaction on sample medical information of target medical information content to be processed and medical information to be processed based on at least two medical information interaction modes, and determine key content to be selected of the target medical information content in the medical information to be processed, where the category of the target medical information content is at least one;

the content obtaining module 220 is configured to perform medical information description content identification on the corresponding sample medical information and the to-be-selected key content respectively according to each target medical information content, so as to obtain a description content of the sample medical information and a medical information description content of the to-be-selected key content;

the first content obtaining module 230 is configured to obtain description content correlation between description content of sample medical information corresponding to the same target medical information content and medical information description content of key content to be selected, extract key content to be selected, of which the description content correlation meets preset correlation parameters, from the key content to be selected of the target medical information content, and obtain first key content to be selected of each target medical information content;

a difference determining module 240, configured to determine, for each target medical information content, an interactive content difference degree between the corresponding sample medical information and the medical information of the first to-be-selected key content;

a second content obtaining module 250, configured to extract, from the first to-be-selected key content of each target medical information content, to-be-selected key content of which the interactive content difference degree of the medical information is greater than a preset interactive content difference parameter, and obtain a second to-be-selected key content of each target medical information content;

and the target content determining module 260 is configured to determine target interactive key content of each target medical information content according to the second key content to be selected of the target medical information content.

On the basis of the above, please refer to fig. 3, which shows a system 300 for intelligent interaction of medical information, comprising a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program to implement the above method.

On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.

In summary, based on the above-mentioned scheme, sample medical information of target medical information content to be processed and medical information to be processed may be subjected to medical information interaction based on at least two medical information interaction modes, and candidate key content of the target medical information content in the medical information to be processed is determined, wherein the category of the target medical information content is at least one, for each target medical information content, medical information description content identification is respectively performed on the corresponding sample medical information and candidate key content, so as to obtain description content of the sample medical information and medical information description content of the candidate key content, obtain description content association between the description content of the sample medical information corresponding to the same target medical information content and the medical information description content of the candidate key content, extract the candidate key content whose description content association satisfies preset association parameters from the candidate key content of the target medical information content, the method comprises the steps of obtaining first to-be-selected key content of each target medical information content, determining the difference degree of the interaction content of the corresponding sample medical information and the medical information of the first to-be-selected key content aiming at each target medical information content, extracting the to-be-selected key content with the difference degree of the interaction content of the medical information being larger than the preset interaction content difference parameter from the first to-be-selected key content of each target medical information content, obtaining second to-be-selected key content of each target medical information content, and determining the target interaction key content of the target medical information content according to the second to-be-selected key content of each target medical information content. Therefore, a large number of samples are not needed to be used for carrying out verification, labor cost can be saved, the target interaction scheme has high matching degree on new data, the integrity of target interaction is improved, and the determination of the key content to be selected and the interaction of the first key content to be selected and the second key content to be selected are quicker.

It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for intelligent interaction of medical information is characterized by comprising the following steps:

2. The method for intelligently interacting medical information according to claim 1, wherein the step of performing medical information interaction between the sample medical information of the target medical information content to be processed and the medical information to be processed based on at least two medical information interaction modes to determine the key content to be selected of the target medical information content in the medical information to be processed comprises the steps of:

3. The method for intelligently interacting medical information according to claim 2, wherein the step of performing substantial interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed to determine the medical information key content of each target medical information content in the medical information to be processed, which is successful in substantial interaction, before being used as the key content to be selected of each target medical information content, further comprises the step of:

4. The method for intelligently interacting medical information according to claim 2, wherein the performing sample interaction on the sample medical information of the target medical information content to be processed and the medical information to be processed to determine medical information key content of each target medical information content in the medical information to be processed, which is successfully sample-interacted, as the candidate key content of each target medical information content comprises:

5. The method for intelligently interacting medical information according to claim 1, wherein the step of respectively performing medical information description content identification on the corresponding sample medical information and the key content to be selected for each target medical information content to obtain the description content of the sample medical information and the medical information description content of the key content to be selected comprises the steps of:

6. The method for intelligently interacting medical information according to claim 1, wherein the determining, for each target medical information content, the degree of difference between the interaction content of the corresponding sample medical information and the medical information of the first to-be-selected key content includes:

7. The method for intelligently interacting medical information according to claim 6, wherein the determining, for each target medical information content, a first interactive content average word count of the corresponding sample medical information and a second interactive content average word count of the medical information in the corresponding candidate key content comprises:

8. The method for intelligently interacting medical information according to any one of claims 1 to 7, wherein the determining the target interactive key content of each target medical information content according to the second candidate key content of the target medical information content comprises:

9. The method for intelligently interacting medical information according to claim 8, wherein the interacting the minimum unit key content with the sample medical information of the target medical information content corresponding to the minimum unit key content comprises:

10. A system for intelligent interaction of medical information, comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method of any one of claims 1 to 9.