CN113849612A

CN113849612A - Method, device, terminal and storage medium for acquiring epidemic prevention information

Info

Publication number: CN113849612A
Application number: CN202111062440.6A
Authority: CN
Inventors: 周圣凯; 陈孝良; 李智勇
Original assignee: Beijing SoundAI Technology Co Ltd
Current assignee: Beijing SoundAI Technology Co Ltd
Priority date: 2021-09-10
Filing date: 2021-09-10
Publication date: 2021-12-28

Abstract

The application discloses a method, a device, a terminal and a storage medium for acquiring epidemic prevention information, which relate to the technical field of artificial intelligence, wherein the method for acquiring epidemic prevention information comprises the following steps: determining a plurality of matching results corresponding to epidemic prevention consultation information based on a plurality of question and answer matching modes, wherein the matching results comprise answer information and matching parameters, and the matching parameters are used for expressing the matching degree between the epidemic prevention consultation information and reference consultation information corresponding to the answer information; determining a first semantic feature corresponding to the epidemic prevention consultation information; determining a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results; and outputting answer information included in the target matching result. According to the embodiment of the application, a plurality of question-answer matching modes are adopted, the semantic features of the epidemic prevention consultation are combined, answer information corresponding to the epidemic prevention consultation information is searched, and the accuracy of the epidemic prevention consultation is improved.

Description

Method, device, terminal and storage medium for acquiring epidemic prevention information

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for acquiring epidemic prevention information.

Background

When a large-scale medical and health event is met, such as a virus infection event, virus detection is carried out on users in a risk area to determine whether the users are infected with viruses; in addition, epidemic prevention measures such as vaccination and the like are also carried out on users in risk areas so as to effectively block the spread of viruses. At this time, the user may need to know epidemic prevention information such as information related to virus detection or information related to vaccination.

Disclosure of Invention

The embodiment of the application provides a method, a device, a terminal and a storage medium for acquiring epidemic prevention information. The technical scheme is as follows:

according to an aspect of the embodiments of the present application, there is provided a method for acquiring epidemic prevention information, the method including:

determining a plurality of matching results corresponding to epidemic prevention consultation information based on a plurality of question and answer matching modes, wherein the matching results comprise answer information and matching parameters, and the matching parameters are used for expressing the matching degree between the epidemic prevention consultation information and reference consultation information corresponding to the answer information;

determining a first semantic feature corresponding to the epidemic prevention consultation information;

determining a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results;

and outputting answer information included in the target matching result.

In a possible implementation manner, the determining a first semantic feature corresponding to the epidemic prevention advisory information includes:

determining at least one second semantic feature corresponding to the epidemic prevention consultation information based on at least one piece of epidemic prevention related information;

determining the first semantic feature based on the at least one second semantic feature.

In another possible implementation manner, the determining, based on at least one epidemic prevention related information, at least one second semantic feature corresponding to the epidemic prevention consultation information includes at least one of the following implementation manners:

if the epidemic prevention related information is the number of epidemic prevention keywords contained in the epidemic prevention consultation information, determining the number of the epidemic prevention keywords contained in the epidemic prevention consultation information to obtain a second semantic feature;

if the epidemic prevention related information is the length of the epidemic prevention consultation information, determining the length of the epidemic prevention consultation information to obtain a second semantic feature;

if the epidemic prevention related information is the number of participles contained in the epidemic prevention consultation information, performing participle on the epidemic prevention consultation information to obtain a plurality of participles, and determining the number of the participles to obtain the second semantic features;

if the epidemic prevention related information is that whether the epidemic prevention consultation information contains time information, determining a time detection result corresponding to the epidemic prevention information, wherein the time detection result is used for indicating whether the epidemic prevention consultation information contains the time information or not, and determining a second semantic feature corresponding to the time detection result;

and if the epidemic prevention related information is that whether the epidemic prevention consultation information contains the site information, determining a site detection result corresponding to the epidemic prevention information, wherein the site detection result is used for indicating whether the epidemic prevention consultation information contains the site information, and determining a second semantic feature corresponding to the site detection result.

In another possible implementation manner, the determining a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results includes:

determining the target matching result from the plurality of matching results based on the first semantic feature and matching parameters included in the plurality of matching results; alternatively, the first and second electrodes may be,

determining the target matching result from the plurality of matching results based on the first semantic feature, answer information included in the plurality of matching results, and a matching parameter.

In another possible implementation manner, the determining the target matching result from the plurality of matching results based on the first semantic feature and the matching parameters included in the plurality of matching results includes:

splicing the first semantic features and the matching parameters included by the matching results in sequence to obtain first target matching features;

and inputting the first target matching feature into a first classification model to obtain the target matching result, wherein the first classification model is used for determining the matching result based on the matching feature.

In another possible implementation manner, the sequentially splicing the first semantic features and the matching parameters included in the multiple matching results to obtain a first target matching feature includes:

weighting the matching parameters included in the matching results based on the priority corresponding to each matching result;

and sequentially splicing the first semantic features and the weighted multiple matching parameters to obtain the first target matching features.

In another possible implementation manner, the determining the target matching result from the multiple matching results based on the first semantic feature, answer information included in the multiple matching results, and a matching parameter includes:

splicing the first semantic features, answer information and matching parameters included by the multiple matching results in sequence to obtain second target matching features;

and inputting the second target matching feature into a second classification model to obtain the target matching result, wherein the second classification model is used for determining the matching result based on the matching feature.

In another possible implementation manner, the sequentially splicing the first semantic features, the answer information included in the multiple matching results, and the matching parameters to obtain second target matching features includes:

and sequentially splicing the first semantic features, the plurality of answer information and the weighted plurality of matching parameters to obtain the second target matching features.

In another possible implementation manner, for each question-answer matching manner, the process of determining the matching result corresponding to the epidemic prevention advisory information based on the question-answer matching manner includes:

if the question-answer matching mode is a similarity matching mode, determining matching parameters between the epidemic prevention consultation information and a plurality of pieces of reference consultation information;

selecting reference consultation information with the maximum matching parameter from the plurality of reference consultation information;

and determining answer information corresponding to the reference consulting information and the maximum matching parameter.

In another possible implementation manner, the determining answer information corresponding to the reference consulting information includes:

determining a region to which the epidemic prevention consultation information belongs, and determining answer information matched with the region from a plurality of answer information corresponding to the reference consultation information; alternatively, the first and second electrodes may be,

determining a current login account, and determining answer information matched with the user portrait from a plurality of answer information corresponding to the reference consultation information based on the user portrait corresponding to the current login account; alternatively, the first and second electrodes may be,

determining the consultation type of the epidemic prevention consultation information, and determining answer information matched with the consultation type from a plurality of answer information corresponding to the reference consultation information; alternatively, the first and second electrodes may be,

determining context information of the epidemic prevention consultation information, and determining intention information corresponding to the epidemic prevention consultation information based on the context information; and determining answer information matched with the intention information from a plurality of answer information corresponding to the reference consultation information.

if the question-answer matching mode is a sentence pattern matching mode, determining the sentence pattern of the epidemic prevention consultation information;

determining matching parameters between the sentence pattern and a plurality of reference sentence patterns;

selecting a reference sentence pattern with the maximum matching parameter from the plurality of reference sentence patterns;

and determining answer information corresponding to the reference sentence pattern and the maximum matching parameter.

and the question-answer matching mode is that question-answer matching is carried out based on a third classification model, the epidemic prevention consultation information is input into the third classification model to obtain the answer information and the matching parameters, and the third classification model is used for determining the answer information and the matching parameters based on epidemic prevention information.

In another possible implementation manner, the inputting the epidemic prevention advisory information into the third classification model to obtain the answer information and the matching parameters includes:

inputting the epidemic prevention consultation information into a third classification model, wherein the third classification model is used for searching answer information matched with the epidemic prevention consultation information from N pieces of answer information based on matching parameters between the epidemic prevention consultation information and a plurality of pieces of benchmark consultation information; under the condition that matched answer information is found, outputting the answer information and the corresponding matching parameters; and under the condition that the matched answer information is not found, outputting preset answer information and the corresponding matching parameters, wherein N is an integer greater than 1.

In another possible implementation manner, before determining a plurality of matching results corresponding to the epidemic prevention advisory information based on a plurality of question-answer matching manners, the method further includes:

acquiring input text information, and determining the epidemic prevention consultation information corresponding to the text information; alternatively, the first and second electrodes may be,

and acquiring the input voice signal, and determining the epidemic prevention consultation information corresponding to the voice signal.

According to another aspect of the embodiments of the present application, there is provided an apparatus for acquiring epidemic prevention information, the apparatus including:

the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining a plurality of matching results corresponding to epidemic prevention consultation information based on a plurality of question-answer matching modes, the matching results comprise answer information and matching parameters, and the matching parameters are used for representing the matching degree between the epidemic prevention consultation information and reference consultation information corresponding to the answer information;

the second determination module is used for determining a first semantic feature corresponding to the epidemic prevention consultation information;

a third determining module for determining a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results;

and the output module is used for outputting answer information included in the target matching result.

In one possible implementation manner, the second determining module includes:

the first determination unit is used for determining at least one second semantic feature corresponding to the epidemic prevention consultation information based on at least one piece of epidemic prevention related information;

a second determining unit for determining the first semantic feature based on the at least one second semantic feature.

In another possible implementation manner, the epidemic prevention related information is the number of epidemic prevention keywords contained in the epidemic prevention consultation information, and the first determining unit is configured to determine the number of epidemic prevention keywords contained in the epidemic prevention consultation information to obtain a second semantic feature; alternatively, the first and second electrodes may be,

the epidemic prevention related information is the length of the epidemic prevention consultation information, and the first determining unit is used for determining the length of the epidemic prevention consultation information to obtain a second semantic feature; alternatively, the first and second electrodes may be,

the epidemic prevention related information is the number of participles contained in the epidemic prevention consultation information, and the first determining unit is used for performing participle on the epidemic prevention consultation information to obtain a plurality of participles, determining the number of the participles and obtaining the second semantic features; alternatively, the first and second electrodes may be,

the epidemic prevention related information is whether the epidemic prevention consultation information contains time information, the first determining unit is used for determining a time detection result corresponding to the epidemic prevention information, the time detection result is used for indicating whether the epidemic prevention consultation information contains the time information, and a second semantic feature corresponding to the time detection result is determined; alternatively, the first and second electrodes may be,

the epidemic prevention related information is whether the epidemic prevention consultation information contains site information, the first determining unit is used for determining a site detection result corresponding to the epidemic prevention information, the site detection result is used for indicating whether the epidemic prevention consultation information contains the site information, and a second semantic feature corresponding to the site detection result is determined.

In another possible implementation manner, the third determining module includes:

a third determining unit, configured to determine the target matching result from the plurality of matching results based on the first semantic feature and the matching parameters included in the plurality of matching results;

a fourth determining unit, configured to determine the target matching result from the multiple matching results based on the first semantic feature, answer information included in the multiple matching results, and a matching parameter.

In another possible implementation manner, the third determining unit includes:

the first splicing subunit is used for sequentially splicing the first semantic features and the matching parameters included in the matching results to obtain first target matching features;

and the first classification subunit is used for inputting the first target matching feature into a first classification model to obtain the target matching result, and the first classification model is used for determining the matching result based on the matching feature.

In another possible implementation manner, the first splicing subunit is configured to weight matching parameters included in the multiple matching results based on a priority corresponding to each matching result; and sequentially splicing the first semantic features and the weighted multiple matching parameters to obtain the first target matching features.

In another possible implementation manner, the fourth determining unit includes:

the second splicing subunit is used for sequentially splicing the first semantic features, the answer information and the matching parameters included in the multiple matching results to obtain second target matching features;

and the second classification subunit is used for inputting the second target matching feature into a second classification model to obtain the target matching result, and the second classification model is used for determining the matching result based on the matching feature.

In another possible implementation manner, the second splicing subunit is configured to weight matching parameters included in the multiple matching results based on a priority corresponding to each matching result; and sequentially splicing the first semantic features, the plurality of answer information and the weighted plurality of matching parameters to obtain the second target matching features.

In another possible implementation manner, the first determining module includes:

a fifth determining unit, configured to determine matching parameters between the epidemic prevention advisory information and the plurality of pieces of reference advisory information if the question-answer matching manner is a similarity matching manner;

a first selecting unit configured to select reference consultation information having a largest matching parameter from the plurality of reference consultation information;

a sixth determining unit, configured to determine answer information corresponding to the reference consulting information and the largest matching parameter.

In another possible implementation manner, the sixth determining unit is configured to determine an area to which the epidemic prevention advisory information belongs, and determine answer information matched with the area from a plurality of answer information corresponding to the reference advisory information; alternatively, the first and second electrodes may be,

the sixth determining unit is configured to determine a current login account, and determine answer information matched with the user portrait from a plurality of answer information corresponding to the reference consultation information based on the user portrait corresponding to the current login account; alternatively, the first and second electrodes may be,

the sixth determining unit is configured to determine a consultation type of the epidemic prevention consultation information, and determine answer information matched with the consultation type from a plurality of answer information corresponding to the reference consultation information; alternatively, the first and second electrodes may be,

the sixth determining unit is configured to determine context information of the epidemic prevention advisory information, and determine intention information corresponding to the epidemic prevention advisory information based on the context information; and determining answer information matched with the intention information from a plurality of answer information corresponding to the reference consultation information.

In another possible implementation manner, the first determining module further includes:

a seventh determining unit, configured to determine a sentence pattern of the epidemic prevention advisory information if the question-answer matching manner is a sentence pattern matching manner;

an eighth determining unit configured to determine a matching parameter between the sentence pattern and a plurality of reference sentence patterns;

a second selection unit configured to select a reference sentence pattern having a largest matching parameter from the plurality of reference sentence patterns;

and the ninth determining unit is used for determining answer information corresponding to the reference sentence pattern and the maximum matching parameter.

and the classification unit is used for inputting the epidemic prevention consultation information into the third classification model to obtain the answer information and the matching parameters if the question-answer matching mode is the question-answer matching based on the third classification model, and the third classification model is used for determining the answer information and the matching parameters based on the epidemic prevention information.

In another possible implementation manner, the classification unit is configured to input the epidemic prevention advisory information into the third classification model, and the third classification model is configured to search answer information matched with the epidemic prevention advisory information from N answer information based on matching parameters between the epidemic prevention advisory information and a plurality of pieces of benchmark advisory information; under the condition that matched answer information is found, outputting the answer information and the corresponding matching parameters; and under the condition that the matched answer information is not found, outputting preset answer information and the corresponding matching parameters, wherein N is an integer greater than 1.

In another possible implementation manner, the apparatus further includes:

the first acquisition module is used for acquiring the input text information and determining the epidemic prevention consultation information corresponding to the text information; alternatively, the first and second electrodes may be,

and the second acquisition module is used for acquiring the input voice signal and determining the epidemic prevention consultation information corresponding to the voice signal.

According to another aspect of the embodiments of the present application, there is provided a terminal including one or more processors and one or more memories, where at least one program code is stored in the one or more memories, and the at least one program code is loaded by the one or more processors and executed to implement the operations performed by the method for obtaining epidemic prevention information according to any one of the above possible implementation manners.

According to another aspect of the embodiments of the present application, there is provided a storage medium having at least one program code stored therein, where the at least one program code is loaded by a processor and executed to implement the operations performed by the method for acquiring epidemic prevention information according to any one of the above possible implementation manners.

According to another aspect of embodiments of the present application, there is provided a computer program or a computer program product comprising: computer program code which, when executed by a computer, causes the computer to carry out the operations performed by the method of obtaining epidemic prevention information as described in any one of the possible implementations above.

In the embodiment of the application, a plurality of matching results corresponding to the epidemic prevention consultation information can be obtained based on a plurality of question-answer matching modes; the first semantic features corresponding to the epidemic prevention consultation information can represent the meaning of the questions the user wants to consult, so that the answer information included in the target matching result is determined from the multiple matching results based on the first semantic features, the accuracy of the determined answer information can be improved, and the accuracy of epidemic prevention consultation is improved.

Drawings

FIG. 1 is a schematic illustration of an implementation environment provided by an exemplary embodiment of the present application;

FIG. 2 is a flowchart of a method for obtaining epidemic prevention information, according to an example embodiment of the present application;

FIG. 3 is a flowchart of a method for obtaining epidemic prevention information, according to an example embodiment of the present application;

FIG. 4 is a schematic diagram of obtaining epidemic prevention information, provided by an exemplary embodiment of the present application;

FIG. 5 is a flowchart of a method for obtaining epidemic prevention information, according to an example embodiment of the present application;

FIG. 6 is a schematic diagram of a voice control apparatus according to an exemplary embodiment of the present application;

fig. 7 is a schematic structural diagram of a terminal according to an exemplary embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It will be understood that the terms "first," "second," and the like as used herein may be used herein to describe various concepts, which are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another.

As used herein, the terms "at least one," "a plurality," "each," and "any," at least one of which includes one, two, or more than two, and a plurality of which includes two or more than two, each of which refers to each of the corresponding plurality, and any of which refers to any of the plurality. For example, the plurality of matching results includes 3 matching results, each of the 3 matching results refers to each of the 3 matching results, and any one of the 3 matching results refers to any one of the 3 matching results, which may be the first one, the second one, or the third one.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application, and as shown in fig. 1, the implementation environment includes a terminal 101 and a server 102. The terminal 101 and the server 102 are connected by a wireless or wired network.

Optionally, the terminal 101 is any type of terminal such as a smartphone, a tablet computer, or a desktop computer. The server 102 is a server, or a server cluster composed of a plurality of servers, or a cloud computing service center.

The terminal 101 has installed thereon an application served by the server 102, through which the terminal 101 can implement functions such as data transmission, message interaction, and the like. Optionally, the application is a stand-alone application, an applet integrated in a host application, or a public number integrated in a host application, etc. For example, the application is a stand-alone epidemic prevention consultation application, an epidemic prevention consultation applet integrated in a social application, or an epidemic prevention consultation public number integrated in a social application, and the like, and the application has a matching function, and of course, the consultation assistant can also have other functions, such as a voice recognition function, a positioning function, and the like.

In some embodiments, the user inputs epidemic prevention consultation information on a consultation interface provided by the application of the terminal 101, the terminal 101 sends the epidemic prevention consultation information to the server 102, the server 102 determines answer information corresponding to the epidemic prevention consultation information, sends the answer information to the terminal 101, and the terminal 101 displays the answer information on the consultation interface to feed back to the user. In other embodiments, the terminal may also locally obtain answer information corresponding to the epidemic prevention consultation information.

Wherein, the epidemic prevention consultation information can be any question related to epidemic prevention of consultation; for example, the epidemic prevention counseling information is information such as "a few injection is needed for vaccine", "how to reserve for vaccination", and the like.

Fig. 2 is a flowchart of a method for acquiring epidemic prevention information according to an embodiment of the present application. The embodiment of the application is executed by the terminal, and the method comprises the following steps:

step 201: and the terminal determines a plurality of matching results corresponding to the epidemic prevention consultation information based on a plurality of question-answer matching modes.

Step 202: the terminal determines a first semantic feature corresponding to the epidemic prevention consultation information.

Step 203: the terminal determines a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results.

Step 204: and the terminal outputs answer information included in the target matching result.

Fig. 3 is a flowchart of a method for acquiring epidemic prevention information according to an embodiment of the present application. The embodiment of the application is executed by the terminal, and the method comprises the following steps:

step 301: and the terminal acquires the epidemic prevention consultation information.

When a user wants to consult epidemic prevention information, the user trigger terminal displays an epidemic prevention consultation interface, the epidemic prevention consultation interface at least comprises an input control, and the user can trigger the input control to input the epidemic prevention consultation information; correspondingly, the terminal detects that the input control is triggered to acquire the input epidemic prevention consultation information; the epidemic prevention consultation information is related to any epidemic prevention of the user consultation, such as the problems of how to reserve vaccination and how to make a few injection for vaccination.

In a possible implementation manner, the input control is an input box, and a user can directly input epidemic prevention consultation information in the input box; correspondingly, the step of the terminal acquiring the inputted epidemic prevention consultation information comprises the following steps: and the terminal acquires the inputted text information and determines epidemic prevention consultation information corresponding to the text information. In the embodiment of the application, the user inputs the epidemic prevention consultation information to the terminal in a text information input mode, so that the user is not influenced by the environment when consulting the epidemic prevention information.

In another possible implementation, the input control is a voice input button, and the user can press the voice input button for a long time and speak the epidemic prevention advisory information. Correspondingly, the step of the terminal acquiring the inputted epidemic prevention consultation information comprises the following steps: the terminal acquires the input voice signal and determines epidemic prevention consultation information corresponding to the voice signal. In the embodiment of the application, the user inputs the epidemic prevention consultation information to the terminal in a mode of inputting the voice signal, so that the input efficiency is improved.

The epidemic prevention consultation interface can be a home page or a secondary interface of an application for consulting epidemic prevention information. Under the condition that the epidemic prevention consultation interface is the secondary interface of the application, the process that the terminal displays the epidemic prevention consultation interface comprises the following steps: and the terminal displays a home page of the application, the home page at least comprises an epidemic prevention consultation control, and when the terminal detects that the epidemic prevention consultation control is triggered, the terminal jumps from the home page to an epidemic prevention consultation interface.

The epidemic prevention consultation interface at least comprises an input control, and also comprises at least one news information link, an artificial customer service control, a plurality of reference consultation information and the like. The news information link is used for triggering the terminal to display news information content corresponding to the news information link, the artificial customer service control is used for triggering the terminal to display an artificial service interface, and the reference consultation information is used for triggering the terminal to display answer information corresponding to the reference consultation information. The system comprises an epidemic prevention consultation interface, an input control, an artificial customer service control and an artificial customer service control, wherein at least one news consultation link is displayed at the uppermost end of the epidemic prevention consultation interface, a plurality of pieces of reference consultation information are displayed in the middle of the epidemic prevention consultation interface, the input control is displayed at the bottom of the epidemic prevention consultation interface, and the artificial customer service control is displayed on the right side of the epidemic prevention consultation interface.

It should be noted that, in the case that the plurality of pieces of reference consultation information include epidemic prevention consultation information that the user wants to consult, the user can directly click the reference consultation information to trigger the terminal to display answer information corresponding to the reference consultation information, so that the step of subsequently inputting epidemic prevention consultation information is omitted, and the efficiency of acquiring epidemic prevention information is improved. And under the condition that the plurality of pieces of benchmark consultation information do not comprise epidemic prevention consultation information which the user wants to consult, the user can click the input control to manually input the epidemic prevention consultation information which the user wants to consult into the terminal. Or, under the condition that the plurality of pieces of reference consultation information do not include epidemic prevention consultation information which the user wants to consult, the user can click the manual customer service control to acquire the epidemic prevention information in a manual customer service mode.

In the embodiment of the application, at least one news information link is displayed in the epidemic prevention consultation interface, so that a user can browse news consultation in the epidemic prevention consultation interface, and the function of the epidemic prevention consultation interface is enriched.

In a possible implementation manner, the plurality of pieces of reference consultation information displayed in the epidemic prevention consultation interface are common, that is, the plurality of pieces of reference consultation information displayed in the epidemic prevention consultation interface of each user are the same. In another possible implementation manner, the plurality of pieces of benchmark consultation information displayed in the epidemic prevention consultation interface are exclusive, that is, the plurality of pieces of benchmark consultation information displayed in the epidemic prevention consultation interface of each user are different. Correspondingly, the process that the terminal determines the plurality of reference consultation information displayed in the epidemic prevention consultation interface comprises the following steps: the terminal acquires at least one item of identity information, region information and historical epidemic prevention consultation information of the user, and determines a plurality of matched reference consultation information based on the at least one item of the identity information, the region information and the historical epidemic prevention consultation information.

In the embodiment of the application, the terminal can recommend the personalized reference consultation information for the user according to the relevant information of the user, the recommended reference consultation information can be more consistent with the intention of the user, and the reference consultation information consistent with the intention of the user is displayed on the epidemic prevention consultation interface, so that the user can obtain the corresponding answer information only by clicking once, the operation is simple, and the efficiency of obtaining the epidemic prevention information by the user is improved.

Step 302: and the terminal determines a plurality of matching results corresponding to the epidemic prevention consultation information based on a plurality of question-answer matching modes.

The question-answer matching mode is a mode of obtaining corresponding answers based on questions and is used for obtaining corresponding matching results based on the epidemic prevention consultation information. The matching result comprises answer information and matching parameters, wherein the answer information is a solution corresponding to the epidemic prevention consultation information, the matching parameters are used for representing the matching degree between the epidemic prevention consultation information and reference consultation information corresponding to the answer information, and the reference consultation information is related epidemic prevention problems stored in the terminal in advance, such as epidemic prevention related problems including vaccine making needles, vaccine reservation and the like.

In the embodiment of the present application, the question-answer matching manners include a similarity matching manner, a sentence matching manner, and a matching manner based on the third classification model.

The first way, the question-answer matching way is a similarity matching way, and step 302 can be implemented by the following three steps, including:

(3021) and the terminal determines matching parameters between the epidemic prevention consultation information and the plurality of reference consultation information based on a question-answer matching mode.

Wherein the matching parameter is the similarity between the epidemic prevention consultation information and the benchmark consultation information. In a possible implementation manner, the terminal extracts a first keyword in the epidemic prevention consultation information, determines the similarity between the first keyword and a second keyword in each piece of reference consultation information, and determines the matching parameters between the epidemic prevention consultation information and the plurality of pieces of reference consultation information based on the similarity between the first keyword and the second keyword in each piece of epidemic prevention consultation information. In the embodiment of the application, the process of determining the matching parameters is simpler based on the similarity of the keywords between the epidemic prevention consultation information and the reference consultation information, so that the efficiency of determining the matching parameters can be improved.

In another possible implementation manner, the terminal acquires first intention information of the epidemic prevention advisory information, determines a similarity between the first intention information and second intention information of each piece of reference advisory information, and determines a matching parameter between the epidemic prevention advisory information and a plurality of pieces of reference advisory information based on the similarity between the first intention information and the second intention information of each piece of reference advisory information. In the embodiment of the application, because the intention information can reflect the real meaning of the user, the determined matching parameters are more accurate based on the similarity of the intention information between the epidemic prevention consultation information and the reference consultation information, and therefore the accuracy of determining the matching parameters can be improved.

(3022) The terminal selects reference consultation information with the maximum matching parameter from the plurality of reference consultation information.

The terminal selects the maximum matching parameter from the plurality of matching parameters and determines the reference consultation information corresponding to the maximum matching parameter. In the embodiment of the application, the terminal selects the reference consultation information with the highest similarity, so that the intention of the user is better met, and the accuracy of epidemic prevention consultation is improved.

In a possible implementation manner, after the terminal selects the maximum matching parameter, the terminal may directly execute the step of reference consultation information corresponding to the maximum matching parameter; in another possible implementation manner, after the terminal selects the maximum matching parameter, it is determined whether the maximum matching parameter is greater than a first parameter threshold; and if the maximum matching parameter is larger than the first parameter threshold, determining the reference consultation information corresponding to the maximum matching parameter. Under the condition that the maximum matching parameter is not greater than the first parameter threshold value, the terminal outputs first prompt information, wherein the first prompt information is used for indicating that an answer corresponding to the epidemic prevention consultation information is not inquired; or the first prompt message comprises preset first answer information. The preset first answer information is answer information of the bottom pocket.

The first parameter threshold may be set and changed as needed, and in the embodiment of the present application, the first parameter threshold is not specifically limited. In the embodiment of the application, the terminal sets the first parameter threshold value for the matching parameter, and only when the maximum matching parameter exceeds the first parameter threshold value, the reference consultation information corresponding to the maximum matching parameter can be determined, so that the condition that wrong reference consultation information is matched when the matching parameters are all low, and wrong answer information is output is avoided.

(3023) And the terminal determines answer information corresponding to the reference consultation information and the maximum matching parameter.

The terminal stores a plurality of pieces of reference consultation information and associated answer information in advance. In this step, the step in which the terminal determines answer information corresponding to the reference consultation information includes: and the terminal acquires answer information corresponding to the reference consultation information from the association relation between the reference consultation information and the answer information based on the reference consultation information.

One piece of reference consultation information is associated with a plurality of pieces of answer information, and in a possible implementation mode, the terminal can feed back corresponding answer information for the user based on the area where the user is located; correspondingly, the step of the terminal determining answer information corresponding to the reference consultation information includes: the terminal acquires the positioning information of the terminal, determines the area to which the epidemic prevention consultation information belongs based on the positioning information, and determines answer information matched with the area from a plurality of answer information corresponding to the reference consultation information. For example, the terminal acquires the positioning information of the terminal as "beijing", determines that the type of the beijing vaccination is "first vaccine", and outputs corresponding answer information "first vaccine needs to be vaccinated with 2 injections".

In the embodiment of the application, the terminal can acquire epidemic prevention information based on the positioning information, and can specially solve epidemic prevention related problems in different regions.

One piece of reference consultation information is associated with a plurality of pieces of answer information, and in another possible implementation mode, the terminal can feed back corresponding answer information for the user based on the portrait of the user; correspondingly, the step of the terminal determining answer information corresponding to the reference consultation information includes: the terminal determines a current login account, and determines answer information matched with the user portrait from a plurality of answer information corresponding to the reference consultation information based on the user portrait corresponding to the current login account. The user portrait is identity information of a current login account and comprises information such as a name, an identity card number and a mobile phone number. For example, the terminal acquires the current login account of the terminal, acquires the identification card information of the user image from the login account, and can know that the age of the user is 1 year and is not suitable for inoculation of the first vaccine according to the identification card information, but can determine that the matched answer information is that the second vaccine needs to be inoculated by 3 injections at the moment.

In the embodiment of the application, the terminal can acquire epidemic prevention information based on the user portrait and can perform special answer aiming at different users.

In another possible implementation manner, the terminal may feed back corresponding answer information to the user based on the consultation type; correspondingly, the step of the terminal determining answer information corresponding to the reference consultation information includes: the terminal determines the consultation type of the epidemic prevention consultation information and determines answer information matched with the consultation type from a plurality of answer information corresponding to the reference consultation information. For example, the epidemic prevention consultation information received by the terminal is "first vaccine requires a few needles for inoculation", and the consultation type of the epidemic prevention consultation information is determined to be about "first vaccine", so that answer information matched with the consultation type is output as "first vaccine requires 2 injections for inoculation".

In the embodiment of the application, the terminal can acquire the epidemic prevention information based on the consultation type of the epidemic prevention consultation information, and can solve various types of problems.

In another possible implementation mode, the terminal can feed back corresponding answer information for the user by different contexts of the epidemic prevention consultation information; correspondingly, the step of the terminal determining answer information corresponding to the reference consultation information includes: the terminal determines context information of the epidemic prevention consultation information and determines intention information corresponding to the epidemic prevention consultation information based on the context information, wherein the context information can be time information, place information, epidemic prevention related information and the like in the epidemic prevention consultation information. The terminal can acquire intention information of the user from the information and then determine answer information matched with the intention information from a plurality of answer information corresponding to the reference consultation information. For example, the epidemic prevention consultation information received by the terminal is "9 month beijing area has vaccine", and the context information is "9 month", "beijing" and ". prime", so as to judge that the user intends to inoculate ". prime vaccine" on beijing during 9 month, and further obtain corresponding answer information of the benchmark consultation question ". prime vaccine how to make an appointment".

In the embodiment of the application, the terminal can acquire the epidemic prevention information based on the context information of the epidemic prevention consultation information, so that the intention of the user can be better met, and the accuracy of the epidemic prevention consultation is improved.

It should be noted that the above methods may be combined, that is, the terminal obtains the epidemic prevention information by adopting a similarity matching method, selects the reference consultation information with the highest similarity to the epidemic prevention consultation information, and determines the matching result corresponding to the epidemic prevention consultation information by combining various epidemic prevention related information such as regional information, current login account information, consultation types, context information, and the like.

In the embodiment of the application, the epidemic prevention information is acquired by combining various methods, so that the intention of a user can be better met, and the accuracy of epidemic prevention consultation is improved.

The second way, question-answer matching way is sentence pattern matching way. Step 302 may be implemented by four steps including:

(3024) the terminal determines the sentence pattern of the epidemic prevention consultation information.

The sentence pattern is a format of the epidemic prevention consultation information, for example, a sentence pattern such as a word mark vaccine for a few needles and a sentence pattern such as how the word mark vaccine reserves.

(3025) The terminal determines matching parameters between the sentence pattern and a plurality of reference sentence patterns.

The basic sentence pattern is a sentence pattern related to the prestored epidemic prevention consultation information, and each basic sentence pattern corresponds to answer information related to epidemic prevention. The matching parameter is the ratio of the same word number in the epidemic prevention consultation information and the reference sentence pattern to the total word number of the epidemic prevention consultation information.

(3026) The terminal selects the reference sentence pattern with the maximum matching parameter from the plurality of reference sentence patterns.

The terminal selects the maximum matching parameter from the multiple matching parameters and determines the reference sentence pattern corresponding to the maximum matching parameter. In the embodiment of the application, the terminal selects the reference sentence pattern with the highest matching parameter degree, so that the user intention is better met, and the accuracy of epidemic prevention consultation is improved.

In a possible implementation manner, after the terminal selects the maximum matching parameter, the step of determining the reference sentence pattern corresponding to the maximum matching parameter may be directly performed; in another possible implementation, after the maximum matching parameter is selected, it is determined whether the maximum matching parameter is greater than a second parameter threshold; and executing the step of determining the reference sentence pattern corresponding to the maximum matching parameter when the maximum matching parameter is larger than the second parameter threshold. Under the condition that the maximum matching parameter is not greater than a second parameter threshold value, the terminal outputs second prompt information, wherein the second prompt information is used for indicating that an answer corresponding to the epidemic prevention consultation information is not inquired; or the second prompt message comprises preset second answer information. And the preset second answer information is the answer information of the bottom pocket.

The second parameter threshold may be set and changed as needed, and in the embodiment of the present application, the second parameter threshold is not specifically limited. In the embodiment of the application, the terminal sets the second parameter threshold for the matching parameters, and only when the maximum matching parameter exceeds the second parameter threshold, the reference sentence pattern corresponding to the maximum matching parameter can be determined, so that the situation that an error reference sentence pattern is matched when the matching parameters are all low, and therefore wrong answer information is output is avoided.

(3027) And the terminal determines answer information corresponding to the reference sentence pattern and the maximum matching parameter.

In one possible implementation manner, the terminal stores a plurality of reference periods and a plurality of answer information associated therewith in advance. In this step, the step of the terminal determining answer information corresponding to the reference sentence pattern includes: and the terminal acquires answer information corresponding to the reference sentence pattern from the corresponding relation between the reference sentence pattern and the answer information based on the reference sentence pattern. For example, the epidemic prevention advisory information received by the terminal is ". the" vaccine needs to be injected for several times ", the sentence pattern for obtaining the epidemic prevention advisory information". the "vaccine is injected for several times", the matching parameters between the sentence pattern of the epidemic prevention advisory information and the sentence pattern of each reference advisory information are calculated, based on the maximum matching parameters, the prestored reference advisory information is determined to be ". the" vaccine is injected for several times ", and the corresponding answer information" the first vaccine needs to be injected for 2 injections, and the second vaccine needs to be injected for 3 injections "is obtained.

In the embodiment of the application, epidemic prevention information is obtained by adopting a sentence pattern matching mode, answer information corresponding to the reference sentence pattern with the largest matching parameter is output, and the answer information of the epidemic prevention consultation problem can be accurately found in the epidemic prevention question and answer consultation scene, so that the accuracy of the epidemic prevention consultation is improved.

And in the third mode, the question-answer matching mode is a matching mode based on a third classification model. Step 302 includes: and inputting the epidemic prevention consultation information into the third classification model by the terminal to obtain answer information and matching parameters. The third classification model is used for determining answer information and a matching parameter based on the epidemic prevention information, and the matching parameter is the probability of classifying the epidemic prevention consultation information into one of a plurality of pieces of benchmark consultation information.

The point to be described is that the reference consultation information and the corresponding answer information are manually labeled in advance, the labeling classifies the reference consultation information according to the answer information, the answer information corresponding to the reference consultation information has N types, and then all the answer information has N +1 types, wherein the extra 1 type is preset third answer information used for representing the condition that the matched answer information is not found and outputting the answer information of the bottom of pocket. And the terminal inputs the marked answer information and the reference consultation information into the classification model for training to obtain a trained third classification model. In the embodiment of the present application, the third classification model is not particularly limited, and for example, the third classification model is a bayesian model, a CNN model, or a DAN model.

The method comprises the following steps that the terminal inputs epidemic prevention consultation information into a third classification model to obtain answer information and matching parameters, and comprises the following steps: the terminal matches the epidemic prevention consultation information with the plurality of pieces of benchmark consultation information to obtain corresponding matching parameters, the third classification model is used for searching answer information matched with the epidemic prevention consultation information from the N pieces of answer information based on the matching parameters between the epidemic prevention consultation information and the plurality of pieces of benchmark consultation information, and the answer information and the corresponding matching parameters are output under the condition that the matched answer information is found; and under the condition that the matched answer information is not found, outputting preset third answer information and corresponding matching parameters, wherein N is an integer larger than 1.

For example, the epidemic prevention consultation information received by the terminal is that the vaccines need to be injected for several times, the epidemic prevention consultation information is input into a third classification model, the epidemic prevention consultation information is classified into a class with a reference consultation question of vaccines for several times, and corresponding answer information, namely that the first vaccine needs to be inoculated with 2 injections and the second vaccine needs to be inoculated with 3 injections, is obtained according to classification results.

In the embodiment of the application, the epidemic prevention consultation information is classified by adopting a method for acquiring the epidemic prevention information based on the third classification model, corresponding answer information is output according to the classification result, and the answer information of the epidemic prevention consultation problem can be quickly found in the scene of the epidemic prevention question and answer consultation, so that the efficiency of the epidemic prevention consultation is improved.

It should be noted that, after the terminal determines the three matching results based on the above three question-answer matching manners, step 303 may be directly executed; or, the terminal determines the target matching result where the maximum matching parameter is based on the matching parameters included in each matching result, and directly outputs the matching parameters included in the target matching result. Or, the terminal determines whether the matching parameters included in the obtained matching result are greater than a third parameter threshold value by adopting a first question-answer matching mode, and directly outputs answer information included in the matching result under the condition that the matching parameters are greater than the third parameter threshold value. The first question-answer matching mode is any one of a similarity matching mode, a sentence matching mode and a matching mode based on a third classification model.

In the embodiment of the application, when the maximum matching parameter obtained based on a question-answer matching mode is large enough, the matching degree of the epidemic prevention consultation information and the reference consultation information is high, other modes are not needed for matching, and the operation consumption is reduced.

In another possible implementation method, the terminal determines 3 matching results corresponding to the epidemic prevention consultation information by using the 3 question-answer matching modes, wherein the 3 matching results comprise 3 matching parameters and 3 answer information, namely each matching mode corresponds to one matching parameter and one answer information. The terminal selects one matching result from the 3 matching results and outputs answer information of the matching result.

In the embodiment of the application, a plurality of question-answer matching modes are adopted to search the answer information corresponding to the epidemic prevention consultation information, so that the answer information of the epidemic prevention consultation information can be accurately found in the epidemic prevention question-answer consultation scene, and the accuracy rate of epidemic prevention consultation is improved.

And the terminal determines the process of the matching result corresponding to the epidemic prevention consultation information for each question and answer matching mode based on the question and answer matching mode, and the process of the corresponding matching result is different in different question and answer matching modes.

Step 303: and the terminal determines at least one second semantic feature corresponding to the epidemic prevention consultation information based on the at least one epidemic prevention related information.

The epidemic prevention related information is at least one of the number of epidemic prevention keywords contained in the epidemic prevention consultation information, the length of the epidemic prevention consultation information, the number of words of scores contained in the epidemic prevention consultation information and whether the place information is contained in the epidemic prevention consultation information.

In one possible implementation method, the epidemic prevention related information is the number of epidemic prevention keywords contained in the epidemic prevention consultation information, wherein the epidemic prevention keywords are words or phrases related to epidemic situations, such as first stitches, vaccines, nucleic acids and the like. Correspondingly, the step of determining the second semantic feature corresponding to the epidemic prevention consultation information by the terminal based on the epidemic prevention related information comprises the following steps: the terminal determines the number of epidemic prevention keywords contained in the epidemic prevention consultation information based on the epidemic prevention consultation information, and determines a second semantic feature corresponding to the epidemic prevention consultation information based on the number of the epidemic prevention keywords.

For example, the epidemic prevention consultation information received by the terminal is 'how the first needle is reserved by the vaccine', the keywords for obtaining the epidemic prevention consultation information are 'the first needle' and 'the vaccine', and the number of the keywords is 2, so that the keywords are used as a second semantic feature corresponding to the epidemic prevention consultation information. In the embodiment of the application, the epidemic prevention information is obtained through the number of the keywords of the epidemic prevention consultation information, and the epidemic prevention consultation information containing part of the same keywords but with different intentions can be distinguished, so that the intention of a user can be better met, and the accuracy of the epidemic prevention consultation is further improved.

In another possible implementation method, the epidemic prevention related information is the length of the epidemic prevention consultation information. Correspondingly, the step of determining the second semantic feature corresponding to the epidemic prevention consultation information by the terminal based on the epidemic prevention related information comprises the following steps: the terminal determines the length of the epidemic prevention consultation information based on the epidemic prevention consultation information, and determines a second semantic feature corresponding to the epidemic prevention consultation information based on the length of the epidemic prevention consultation information.

For example, the epidemic prevention consultation information received by the terminal is 'how the first vaccine makes an appointment', the length of the epidemic prevention consultation information is obtained, the length of the epidemic prevention consultation information is 11, and the epidemic prevention consultation information is used as a second semantic feature corresponding to the epidemic prevention consultation information. For example, the epidemic prevention consultation information received by the terminal is the vaccination, the length of the obtained epidemic prevention consultation information is 8, and the obtained epidemic prevention consultation information is used as a second semantic feature corresponding to the epidemic prevention consultation information. In the embodiment of the application, aiming at epidemic prevention consultation information with the same keywords but different intentions, wrong epidemic prevention information can be removed by acquiring the length of the epidemic prevention consultation information, so that the accuracy of epidemic prevention consultation is improved.

In another possible implementation method, the epidemic prevention related information is the number of words of the epidemic prevention consultation information. Correspondingly, the step of determining the second semantic feature corresponding to the epidemic prevention consultation information by the terminal based on the epidemic prevention related information comprises the following steps: the terminal carries out word segmentation processing on the epidemic prevention consultation information to obtain a plurality of words, the number of the words is determined, and a second semantic feature corresponding to the epidemic prevention consultation information is determined based on the number of the words.

For example, the epidemic prevention consultation information received by the terminal is 'how the first vaccine makes an appointment', the epidemic prevention consultation information is subjected to word segmentation, the word segmentation result is 'first needle', 'vaccine', 'how' and 'appointment', the number of the obtained word segments is 4, and the word segments are used as a second semantic feature corresponding to the epidemic prevention consultation information. In the embodiment of the application, the epidemic prevention information is obtained through the word segmentation number of the epidemic prevention consultation information, the epidemic prevention consultation information containing the same word segmentation but different intentions can be distinguished, and the corresponding answer information can be accurately found, so that the accuracy of the epidemic prevention consultation is improved.

In another possible implementation method, the epidemic prevention related information is whether the epidemic prevention consultation information contains time information. Correspondingly, the step of determining the second semantic feature corresponding to the epidemic prevention consultation information by the terminal based on the epidemic prevention related information comprises the following steps: the terminal carries out time detection on the received epidemic prevention consultation information, determines a time detection result corresponding to the epidemic prevention information, wherein the time detection result is used for representing a plurality of question-answer matching modes in the epidemic prevention consultation information, and determines a second semantic feature corresponding to the epidemic prevention consultation information according to the time detection result by combining whether the semantic features of the epidemic prevention consultation contain the time information.

For example, the epidemic prevention consultation information received by the terminal is 'vaccine is in Beijing area in 9 months', and the time information '9 months' in the epidemic prevention consultation information is obtained and is used as a second semantic feature corresponding to the epidemic prevention consultation information. The terminal can output corresponding answer information for the 9 month vaccine case. In the embodiment of the application, the epidemic prevention information is obtained by detecting whether the epidemic prevention consultation information contains time information or not, so that the epidemic prevention consultation information with the same key words but different time can be distinguished, different answer information is output aiming at different time, and the accuracy of the epidemic prevention consultation can be improved.

In another possible implementation method, the epidemic prevention related information is whether the place information is included in the epidemic prevention consultation information. Correspondingly, the step of determining the second semantic feature corresponding to the epidemic prevention consultation information by the terminal based on the epidemic prevention related information comprises the following steps: the terminal carries out location detection on the received epidemic prevention consultation information, determines a location detection result corresponding to the epidemic prevention information, wherein the location detection result is used for indicating whether the epidemic prevention consultation information contains location information, and determines a second semantic feature corresponding to the epidemic prevention consultation information according to the location detection result.

For example, the epidemic prevention consultation information received by the terminal is 'vaccine is in Beijing area in 9 months', and the place information 'Beijing' in the epidemic prevention consultation information is obtained and is used as a second semantic feature corresponding to the epidemic prevention consultation information. The terminal can output corresponding answer information aiming at the situation of the vaccine of Beijing. In the embodiment of the application, the epidemic prevention information is obtained by detecting whether the place information is contained in the epidemic prevention consultation information, so that the epidemic prevention consultation information with the same key words and different places can be distinguished, different answer information is output aiming at different regions, and special answers can be carried out on users in different regions, thereby improving the accuracy of the epidemic prevention consultation.

Step 304: the terminal determines the first semantic features based on the at least one second semantic feature.

In a possible implementation manner, the terminal directly splices at least one second semantic feature to obtain a first semantic feature, wherein the first semantic feature is used for representing features of epidemic prevention related information in epidemic prevention consultation information. In the embodiment of the application, the terminal splices all the second semantic features to obtain the semantic features, so that the first semantic features can contain all epidemic prevention related information in the epidemic prevention consultation information and information is not lost.

In another possible implementation manner, the terminal determines the weight of each second semantic feature, and concatenates at least one second semantic feature based on the weight of each second semantic feature to obtain the first semantic feature. In the embodiment of the application, the terminal presets the weight for each second semantic feature, so that the output answer information has the emphasis, and a user can obtain the key information from the answer information.

The weights of the second semantic features are common, that is, the weights of the second semantic features of each user are the same. Or, the weight of the second semantic features is user-specific, that is, the weight of the second semantic features of each user is different; correspondingly, the process that the terminal determines the weight of each second semantic feature comprises the following steps: the terminal obtains historical epidemic prevention consultation information input by the user, determines intention information of the user based on the historical epidemic prevention consultation information, and determines the weight of each second semantic feature based on the intention information of the user.

In the embodiment of the application, the terminal determines the weight of each second semantic feature based on the historical epidemic prevention consultation information of the user, so that the determined weight of each second voice feature is more in line with the idea of the user, and the accuracy is improved.

In another possible implementation manner, the terminal may also splice part of the second semantic features, instead of splicing all the determined second semantic features; correspondingly, the step of the terminal determining the semantic features based on the at least one second semantic feature comprises: the terminal obtains at least one item of identity information and positioning information of a user, selects a target semantic feature from at least one second semantic feature based on the at least one item of identity information and positioning information, and splices the target semantic feature to obtain a first semantic feature. The selected target semantic features are matched with at least one of the identity information and the positioning information of the user, namely different users or users in different regions, and the selected target semantic features are different.

In the embodiment of the application, the terminal only selects the important second semantic features related to the user for splicing, and special answer information can be output for different users.

Step 305: the terminal determines a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results.

In the embodiment of the application, the terminal determines the target matching result from the multiple matching results, and two modes exist.

In a first way, the terminal determines a target matching result from the plurality of matching results based on the first semantic feature and the matching parameters included in the plurality of matching results. Step 305 may be implemented by two steps, including:

(3051) and the terminal sequentially splices the first semantic features and the matching parameters included by the matching results to obtain first target matching features.

In a possible implementation manner, the terminal directly and sequentially splices the first semantic feature and the matching parameters included in the multiple matching results to obtain a first target matching feature. The first target matching characteristics are used for matching answer information corresponding to the epidemic prevention consultation information.

In the embodiment of the application, the mode that the matching parameters included in the matching results are combined with the semantic features of the epidemic prevention consultation information is adopted, so that the obtained first target matching features are more consistent with the epidemic prevention consultation information of the user, and the accuracy of the epidemic prevention consultation is improved.

In another possible implementation manner, the terminal sequentially splices the semantic features and the matching parameters included in the multiple matching results based on the priority to obtain the first target matching feature. Correspondingly, the step that the terminal sequentially splices the first semantic feature and the matching parameters included by the matching results to obtain the first target matching feature comprises the following steps: determining the weight of the matching parameters corresponding to each question-answer mode based on the priority of each question-answer matching mode, weighting the matching parameters included in each matching result based on the weight of the matching parameters corresponding to each question-answer mode, and sequentially splicing the first semantic features and the weighted matching parameters to obtain first target matching features.

The priorities corresponding to the multiple matching question-answering manners may be preset, for example, the priority ranking is as follows: and the priority of the matching result of the similarity matching mode is higher than that of the matching result of the sentence matching mode and higher than that of the matching result based on the third classification model. Moreover, the size of the priority is positively correlated with the weight of the matching parameter; that is, the higher the priority of the matching question-answering mode is, the greater the weight of the matching parameters included in the corresponding matching result is.

In the embodiment of the application, the terminal weights each matching parameter based on the priority, so that the obtained first target matching characteristic ignores irrelevant information in the epidemic prevention consultation information, and the accuracy of the epidemic prevention consultation is improved.

(3052) The terminal inputs the first target matching feature into a first classification model to obtain a target matching result, and the first classification model is used for determining the matching result based on the matching feature.

In this embodiment, the first classification model is not specifically limited, and for example, the first classification model is a bayesian model, a CNN model, or a DAN model.

The terminal classifies the matching results into 3 classes through the matching characteristics, namely the matching results of the similarity matching mode, the matching results of the sentence matching mode and the matching results based on the third classification model matching mode. The terminal determines a target matching result from the 3 types of matching results based on the first target matching feature.

For example, referring to fig. 4, a user inputs epidemic prevention consultation information, the terminal determines three matching results through three question-answer matching modes of similarity recall, sentence matching and a third classification model, each matching result includes corresponding answer information and matching parameters, a first semantic feature corresponding to the epidemic prevention consultation information and the matching parameters included in the multiple matching results are spliced to obtain a first target matching feature, and the first target matching feature is input into the first classification model to obtain a target matching result.

In the embodiment of the application, the terminal inputs the first target matching characteristic into the first classification model to obtain a target matching result, so that answer information of the epidemic prevention consultation problem can be quickly found in an epidemic prevention question and answer consultation scene, and the efficiency of epidemic prevention consultation is improved.

In the second mode, the terminal determines a target matching result from the multiple matching results based on the first semantic feature, answer information and matching parameters included in the multiple matching results. Step 305 may be implemented by two steps, including:

(3053) and the terminal sequentially splices the first semantic features, answer information and matching parameters included by the multiple matching results to obtain second target matching features.

In a possible implementation manner, the terminal directly and sequentially splices the first semantic features, answer information included in the multiple matching results and matching parameters to obtain second target matching features. In one case, the terminal firstly splices the first semantic features with matching parameters included in a plurality of matching results, and then splices the first semantic features with answer information included in the plurality of matching results to obtain second target matching features. In another case, the terminal firstly splices the first semantic features with answer information included in a plurality of matching results, and then splices the first semantic features with matching parameters included in a plurality of matching results to obtain second target matching features. And the second target matching characteristic is used for matching answer information corresponding to the epidemic prevention consultation information.

In the embodiment of the application, the answer information and the matching parameters included in the multiple matching results are combined with the semantic features of the epidemic prevention consultation information, so that the obtained second target matching features are more consistent with the epidemic prevention consultation information of the user, and the accuracy of the epidemic prevention consultation is improved.

In another possible implementation manner, the terminal sequentially splices the semantic features and answer information and matching parameters included in the multiple matching results based on the priority to obtain second target matching features. Correspondingly, the terminal sequentially splices the answer information and the matching parameters included by the first semantic feature and the multiple matching results to obtain a second target matching feature, and the method comprises the following steps: weighting the matching parameters included in the matching results based on the priority corresponding to each matching result; and sequentially splicing the first semantic features, the plurality of answer information and the weighted plurality of matching parameters to obtain second target matching features.

In the embodiment of the application, the terminal weights each matching parameter based on the priority, and then combines the answer information in a plurality of matching results, so that the obtained second target matching characteristic ignores irrelevant information in the epidemic prevention consultation information, and is closer to intention information in the epidemic prevention consultation information, thereby improving the accuracy of the epidemic prevention consultation.

(3054) And the terminal inputs the second target matching characteristic into a second classification model to obtain a target matching result, and the second classification model is used for determining the matching result based on the matching characteristic.

In this embodiment, the second classification model is not specifically limited, and for example, the second classification model is a bayesian model, a CNN model, or a DAN model.

The terminal classifies the matching results into 3 classes through the matching characteristics, namely the matching results of the similarity matching mode, the matching results of the sentence matching mode and the matching results based on the third classification model matching mode. And the terminal determines a target matching result from the 3 types of matching results based on the second target matching characteristic.

In the embodiment of the application, the terminal inputs the second target matching characteristic into the second classification model to obtain the target matching result, so that answer information of the epidemic prevention consultation problem can be quickly found in the scene of the epidemic prevention consultation and answer consultation, and the efficiency of the epidemic prevention consultation is improved.

Step 306: and the terminal outputs answer information included in the target matching result.

In a possible implementation manner, the answer information is text information, the terminal directly displays the answer information on the consultation interface, and the answer information is fed back to the user. In the embodiment of the application, the terminal outputs the answer information in a text form, so that the user can acquire the answer information more intuitively, and the efficiency of acquiring the answer information is improved.

In another possible implementation manner, the answer information is voice information, the terminal displays a voice signal on the consultation interface, and when the voice signal is detected to be triggered by the user, the voice signal is played and the answer information is fed back to the user. In the embodiment of the application, the terminal outputs the answer information in a voice mode, and the answer information can be transmitted to the user under the condition that the user is inconvenient to see the consultation interface.

For example, referring to fig. 4, answer information included in the target matching result is output.

Fig. 5 is a flowchart of a method for acquiring epidemic prevention information according to an embodiment of the present application. In the embodiment of the application, the server matches answer information corresponding to the epidemic prevention consultation information for explanation, and the method comprises the following steps:

step 501: and the terminal acquires the epidemic prevention consultation information.

This step is the same as step 301, and is not described herein again.

Step 502: and the terminal sends the epidemic prevention consultation information to the server.

Step 503: the server receives the epidemic prevention consultation information, and determines a plurality of matching results corresponding to the epidemic prevention consultation information based on a plurality of question-answer matching modes.

Step 504: the server determines at least one second semantic feature corresponding to the epidemic prevention consultation information based on the at least one epidemic prevention related information.

Step 505: the server determines the first semantic features based on the at least one second semantic feature.

Step 506: the server determines a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results.

Steps 503 and 506 are the same as steps 302 and 305, respectively, and are not described herein again.

Step 507: and the server sends answer information included in the target matching result to the terminal.

Step 508: the terminal receives the answer information and outputs the answer information.

The process of outputting the answer information by the terminal in step 508 is the same as that in step 306, and is not described herein again.

In the embodiment of the application, the terminal requests the server to match the answer information corresponding to the epidemic prevention consultation information, so that the terminal does not need to operate a classification model, the memory of the terminal can be saved, and the operation efficiency is improved.

Fig. 6 is a schematic structural diagram of an apparatus for acquiring epidemic prevention information according to an embodiment of the present application, and referring to fig. 6, the apparatus includes:

a first determining module 601, configured to determine, based on multiple question-answer matching manners, multiple matching results corresponding to epidemic prevention advisory information, where the matching results include answer information and matching parameters, and the matching parameters are used to indicate a matching degree between the epidemic prevention advisory information and reference advisory information corresponding to the answer information;

a second determining module 602, configured to determine a first semantic feature corresponding to the epidemic prevention advisory information;

a third determining module 603 configured to determine a target matching result from the plurality of matching results based on the first semantic feature and the plurality of matching results;

the output module 604 is configured to output answer information included in the target matching result.

In a possible implementation manner, the second determining module 602 includes:

In another possible implementation manner, the epidemic prevention related information is the number of epidemic prevention keywords contained in the epidemic prevention consultation information; the first determining unit is used for determining the number of the epidemic prevention keywords contained in the epidemic prevention consultation information to obtain a second semantic feature; alternatively, the first and second electrodes may be,

the epidemic prevention related information is the number of participles contained in the epidemic prevention consultation information, and the first determining unit is used for performing participle on the epidemic prevention consultation information to obtain a plurality of participles, determining the number of the participles and obtaining the second semantic feature; alternatively, the first and second electrodes may be,

the first determining unit is configured to determine a location detection result corresponding to the epidemic prevention information, where the location detection result is used to indicate whether the epidemic prevention consultation information includes the location information, and determine a second semantic feature corresponding to the location detection result.

In another possible implementation manner, the third determining module 603 includes:

a third determining unit configured to determine a target matching result from the plurality of matching results based on the first semantic feature and a matching parameter included in the plurality of matching results;

and the fourth determining unit is used for determining a target matching result from the multiple matching results based on the first semantic features, the answer information included in the multiple matching results and the matching parameters.

In another possible implementation manner, the third determining unit includes:

the first splicing subunit is used for sequentially splicing the first semantic feature and the matching parameters included in the matching results to obtain a first target matching feature;

In another possible implementation manner, the first splicing subunit is configured to weight matching parameters included in the multiple matching results based on a priority corresponding to each matching result; and sequentially splicing the first semantic feature and the weighted multiple matching parameters to obtain the first target matching feature.

the second splicing subunit is used for sequentially splicing the first semantic features, answer information included by the multiple matching results and the matching parameters to obtain second target matching features;

and the second classification subunit is used for inputting the second target matching characteristic into a second classification model to obtain a target matching result, and the second classification model is used for determining the matching result based on the matching characteristic.

In another possible implementation manner, the second splicing subunit is configured to weight matching parameters included in the multiple matching results based on a priority corresponding to each matching result; and sequentially splicing the first semantic features, the plurality of answer information and the weighted plurality of matching parameters to obtain second target matching features.

In another possible implementation manner, the first determining module 601 includes:

a first selecting unit for selecting reference consultation information with the maximum matching parameter from the plurality of reference consultation information;

the sixth determining unit is configured to determine context information of the epidemic prevention advisory information, and determine intention information corresponding to the epidemic prevention advisory information based on the context information; answer information matching the intention information is determined from a plurality of answer information corresponding to the reference consultation information.

In another possible implementation manner, the first determining module 601 further includes:

In another possible implementation manner, the second classification unit is configured to input the epidemic prevention advisory information into the third classification model, and the third classification model is configured to search answer information matched with the epidemic prevention advisory information from N answer information based on matching parameters between the epidemic prevention advisory information and a plurality of reference advisory information; under the condition that the matched answer information is found, outputting the answer information and the corresponding matching parameters; and under the condition that the matched answer information is not found, outputting preset answer information and the corresponding matching parameter, wherein N is an integer larger than 1.

In another possible implementation manner, the apparatus further includes:

Fig. 7 shows a block diagram of a terminal 700 according to an exemplary embodiment of the present disclosure. The terminal 700 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. The terminal 800 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

In general, terminal 700 includes: a processor 701 and a memory 702.

The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 701 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 701 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 702 may include one or more computer-readable storage media, which may be non-transitory. Memory 702 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 702 is used to store at least one instruction for execution by processor 701 to implement the XXXX methods provided by method embodiments in the present disclosure.

In some embodiments, the terminal 700 may further optionally include: a peripheral interface 703 and at least one peripheral. The processor 701, the memory 702, and the peripheral interface 703 may be connected by buses or signal lines. Various peripheral devices may be connected to peripheral interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 704, touch screen display 705, camera 706, camera assembly 706, audio circuitry 707, positioning assembly 708, and power source 709.

The peripheral interface 703 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 701 and the memory 702. In some embodiments, processor 701, memory 702, and peripheral interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral interface 703 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 704 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 704 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 704 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 704 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 704 may also include NFC (Near Field Communication) related circuits, which are not limited by this disclosure.

The display screen 705 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to capture touch signals on or over the surface of the display screen 705. The touch signal may be input to the processor 701 as a control signal for processing. At this point, the display 705 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 705 may be one, providing the front panel of the terminal 700; in other embodiments, the display 705 can be at least two, respectively disposed on different surfaces of the terminal 700 or in a folded design; in still other embodiments, the display 705 may be a flexible display disposed on a curved surface or on a folded surface of the terminal 700. Even more, the display 705 may be arranged in a non-rectangular irregular pattern, i.e. a shaped screen. The Display 705 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or the like.

The camera assembly 706 is used to capture images or video. Optionally, camera assembly 706 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 706 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuitry 707 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 701 for processing or inputting the electric signals to the radio frequency circuit 704 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 700. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 701 or the radio frequency circuit 704 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 707 may also include a headphone jack.

The positioning component 708 is used to locate the current geographic Location of the terminal 700 for navigation or LBS (Location Based Service). The Positioning component 708 can be a Positioning component based on the GPS (Global Positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the russian eu.

Power supply 709 is provided to supply power to various components of terminal 700. The power source 709 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When power source 709 includes a rechargeable battery, the rechargeable battery may be a support wired or wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 700 also includes one or more sensors 710. The one or more sensors 710 include, but are not limited to: acceleration sensor 711, gyro sensor 712, pressure sensor 713, fingerprint sensor 714, optical sensor 715, and proximity sensor 716.

The acceleration sensor 711 can detect the magnitude of acceleration in three coordinate axes of a coordinate system established with the terminal 700. For example, the acceleration sensor 711 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 701 may control the touch screen 705 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 711. The acceleration sensor 711 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 712 may detect a body direction and a rotation angle of the terminal 700, and the gyro sensor 712 may cooperate with the acceleration sensor 711 to acquire a 3D motion of the terminal 700 by the user. From the data collected by the gyro sensor 712, the processor 701 may implement the following functions: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

Pressure sensors 713 may be disposed on a side bezel of terminal 700 and/or an underlying layer of touch display 705. When the pressure sensor 713 is disposed on a side frame of the terminal 700, a user's grip signal on the terminal 700 may be detected, and the processor 701 performs right-left hand recognition or shortcut operation according to the grip signal collected by the pressure sensor 713. When the pressure sensor 713 is disposed at a lower layer of the touch display 705, the processor 701 controls the operability control on the UI interface according to the pressure operation of the user on the touch display 705. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 714 is used for collecting a fingerprint of a user, and the processor 701 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 714, or the fingerprint sensor 714 identifies the identity of the user according to the collected fingerprint. When the user identity is identified as a trusted identity, the processor 701 authorizes the user to perform relevant sensitive operations, including unlocking a screen, viewing encrypted information, downloading software, paying, changing settings, and the like. The fingerprint sensor 714 may be disposed on the front, back, or side of the terminal 700. When a physical button or a vendor Logo is provided on the terminal 700, the fingerprint sensor 714 may be integrated with the physical button or the vendor Logo.

The optical sensor 715 is used to collect the ambient light intensity. In one embodiment, the processor 701 may control the display brightness of the touch display 705 based on the ambient light intensity collected by the optical sensor 715. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 705 is increased; when the ambient light intensity is low, the display brightness of the touch display 705 is turned down. In another embodiment, processor 701 may also dynamically adjust the shooting parameters of camera assembly 706 based on the ambient light intensity collected by optical sensor 715.

A proximity sensor 716, also referred to as a distance sensor, is typically disposed on a front panel of the terminal 700. The proximity sensor 716 is used to collect the distance between the user and the front surface of the terminal 700. In one embodiment, when the proximity sensor 716 detects that the distance between the user and the front surface of the terminal 700 gradually decreases, the processor 701 controls the touch display 705 to switch from the bright screen state to the dark screen state; when the proximity sensor 716 detects that the distance between the user and the front surface of the terminal 700 gradually becomes larger, the processor 701 controls the touch display 705 to switch from the breath screen state to the bright screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 7 is not intended to be limiting of terminal 700 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

In an exemplary embodiment, a computer-readable storage medium is further provided, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is loaded and executed by a terminal, so as to implement the method for acquiring epidemic prevention information in the foregoing embodiments. The computer readable storage medium may be a memory. For example, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program or a computer program product is also provided, which includes computer program code, when executed by a computer, causes the computer to implement the method for acquiring epidemic prevention information in the above-mentioned embodiments.

In an exemplary embodiment, a computer program according to an embodiment of the present application may be deployed to be executed on one computer device or on multiple computer devices located at one site, or may be executed on multiple computer devices distributed at multiple sites and interconnected by a communication network, and the multiple computer devices distributed at the multiple sites and interconnected by the communication network may constitute a block chain system.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for obtaining epidemic prevention information, the method comprising:

and outputting answer information included in the target matching result.

2. The method of claim 1, wherein the determining the first semantic feature corresponding to the epidemic prevention advisory information comprises:

3. The method of claim 2, wherein the determining at least one second semantic feature corresponding to the epidemic prevention advisory information based on at least one epidemic prevention related information comprises at least one of the following implementation manners:

4. The method of claim 1, wherein determining a target match result from the plurality of match results based on the first semantic feature and the plurality of match results comprises:

5. The method of claim 4, wherein determining the target matching result from the plurality of matching results based on the first semantic feature and the matching parameters included in the plurality of matching results comprises:

6. The method according to claim 5, wherein the sequentially splicing the first semantic feature and the matching parameters included in the matching results to obtain a first target matching feature comprises:

7. The method according to claim 4, wherein the determining the target matching result from the plurality of matching results based on the first semantic feature, answer information included in the plurality of matching results, and matching parameters comprises:

8. The method according to claim 7, wherein the sequentially concatenating the first semantic features, the answer information included in the plurality of matching results, and the matching parameters to obtain second target matching features comprises:

9. The method according to claim 1, wherein the process of determining the matching result corresponding to the epidemic prevention advisory information based on the question-answer matching manner for each question-answer matching manner comprises:

10. The method as claimed in claim 9, wherein the process of determining answer information corresponding to the reference consultation information comprises:

11. The method according to claim 1, wherein the process of determining the matching result corresponding to the epidemic prevention advisory information based on the question-answer matching manner for each question-answer matching manner comprises:

12. The method according to any one of claims 1 to 11, wherein the process of determining the matching result corresponding to the epidemic prevention advisory information based on the question-answer matching manner comprises, for each question-answer matching manner:

13. The method of claim 12, wherein said inputting said epidemic prevention advisory information into said third classification model to obtain said answer information and said matching parameters comprises:

inputting the epidemic prevention consultation information into the three classification models, wherein the third classification model is used for searching answer information matched with the epidemic prevention consultation information from N answer information based on matching parameters between the epidemic prevention consultation information and a plurality of pieces of reference consultation information; under the condition that matched answer information is found, outputting the answer information and the corresponding matching parameters; and under the condition that the matched answer information is not found, outputting preset answer information and the corresponding matching parameters, wherein N is an integer greater than 1.

14. The method of claim 1, wherein before determining the matching results corresponding to the epidemic prevention advisory information based on the question-answer matching manners, the method further comprises:

15. An apparatus for obtaining epidemic prevention information, the apparatus comprising:

16. A terminal, comprising one or more processors and one or more memories having stored therein at least one program code, the at least one program code being loaded into and executed by the one or more processors to implement the operations of the method of obtaining epidemic information according to any one of claims 1 through 14.

17. A computer-readable storage medium, wherein at least one program code is stored in the storage medium, and the at least one program code is loaded and executed by a processor to implement the operations performed by the method for acquiring epidemic prevention information according to any one of claims 1 to 14.