CN112925898B - Question-answering method and device based on artificial intelligence, server and storage medium - Google Patents
Question-answering method and device based on artificial intelligence, server and storage medium Download PDFInfo
- Publication number
- CN112925898B CN112925898B CN202110395698.1A CN202110395698A CN112925898B CN 112925898 B CN112925898 B CN 112925898B CN 202110395698 A CN202110395698 A CN 202110395698A CN 112925898 B CN112925898 B CN 112925898B
- Authority
- CN
- China
- Prior art keywords
- target
- question
- answer
- terminal
- page
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the application provides a question-answering method, a question-answering device, a question-answering server and a question-answering storage medium based on artificial intelligence, wherein the method is applied to the field of the artificial intelligence and comprises the following steps: acquiring a question-answer request submitted by a first terminal, wherein the question-answer request carries user information and problem description information of a target user; acquiring a service information set of a target user according to user information; identifying the questioning intention of the target user by utilizing the question description information to obtain an intention identification result; converting the intention recognition result into a target question-answering instruction; matching a target reply template for a target user according to the service information set and the target question-answer instruction; and obtaining reply contents aiming at the target user according to the target reply template, and outputting the reply contents through the first terminal. By adopting the method and the device, the question and answer service quality can be improved. The present application relates to blockchain technology, such as user information, question description information, and answer content may be written into the blockchain.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an artificial intelligence based question answering method, device, server and storage medium.
Background
Today, electronic commerce, electronic government and enterprise informatization are widely developed, and various websites or platforms face the demands of massive client consultation, client service, client notification and the like. The traditional manual service mode can not meet the requirement far, and intelligent customer service robots and the like are introduced in the industry in recent years to relieve manpower and improve efficiency.
The traditional intelligent customer service robot carries out question-sentence type retrieval after semantic understanding by introducing word segmentation processing and part-of-speech labeling and collocating a continuously rich semantic knowledge base, and answers are retrieved from a question-answer retrieval library for replying. More intelligent, if the accurate answer can not be retrieved, matching processing is carried out on the client question, and a relatively accurate answer is selected from a plurality of candidate results according to similarity calculation to answer.
In the face of a scene with rapid service development and change, and when different services are required to be classified or the reply content is required to be personalized, the robot cannot rapidly and accurately deal with, and the question and answer service quality is poor.
Disclosure of Invention
The embodiment of the application provides a question and answer method, a question and answer device, a server and a storage medium based on artificial intelligence, which can improve the question and answer service quality.
In a first aspect, an embodiment of the present application provides an artificial intelligence based question-answering method, including:
acquiring a question-answer request submitted by a first terminal, wherein the question-answer request carries user information and question description information of a target user;
acquiring a service information set of the target user according to the user information;
identifying the question intention of the target user by utilizing the question description information to obtain an intention identification result;
converting the intention recognition result into a target question-answering instruction;
matching a target reply template for the target user according to the service information set and the target question-answer instruction;
and obtaining reply content aiming at the target user according to the target reply template, and outputting the reply content through the first terminal.
Optionally, the user information includes user identification information and service system indication information, and the acquiring the service information set of the target user according to the user information includes:
and acquiring a service information set of the target user from a target service system according to the user identification information, wherein the target service system is a service system indicated by the service system indication information.
Optionally, the acquiring, according to the user identification information, the service information set of the target user from the target service system includes:
inquiring a link address for accessing the target service system according to the service system indication information;
performing splicing processing on the user identification information and the link address to obtain a spliced link address;
and acquiring the service information set of the target user from the target service system according to the spliced link address.
Optionally, the method further comprises:
searching a first plug-in module, wherein the first plug-in module comprises a page code of a link address configuration page;
transmitting the first plug-in module to the target service system so that the target service system configures a link address for accessing the target service system based on the first plug-in module;
and receiving a link address returned by the target service system and used for accessing the target service system, and storing the link address used for accessing the target service system.
Optionally, the matching, according to the service information set and the target question-answer instruction, a target answer template for the target user includes:
Acquiring a conditional expression corresponding to the target question-answering instruction;
substituting each service information in the service information set into the conditional expression to operate so as to obtain an operation result;
and determining a reply template corresponding to the operation result, and determining the reply template corresponding to the operation result as a target reply template.
Optionally, the method further comprises:
outputting a first page through a second terminal, wherein the first page comprises a plurality of question-answering instructions, and the plurality of question-answering instructions comprise the target question-answering instructions;
after detecting a selection instruction of the target question-answer instruction sent by the second terminal, outputting a second page through the second terminal, so that the second terminal configures a conditional expression and a response template corresponding to the target question-answer instruction based on the second page;
and acquiring a conditional expression and a reply template corresponding to the target question-answer instruction, and storing the conditional expression and the reply template configured by the second terminal for the target question-answer instruction.
Optionally, the outputting, by the second terminal, the second page includes:
searching a second plug-in template, wherein the second plug-in template comprises a page code of the second page;
And sending the second plug-in module to the second terminal so that the second terminal generates the second page according to the second plug-in module and outputs the second page.
In a second aspect, the present application provides an artificial intelligence based question answering apparatus, comprising:
the acquisition module is used for acquiring a question-answer request submitted by the first terminal, wherein the question-answer request carries user information and question description information of a target user;
the acquisition module is further used for acquiring a service information set of the target user according to the user information;
the recognition module is used for recognizing the questioning intention of the target user by utilizing the question description information to obtain an intention recognition result;
the conversion module is used for converting the intention recognition result into a target question-answer instruction;
the matching module is used for matching a target answer template for the target user according to the service information set and the target question-answer instruction;
the obtaining module is further used for obtaining reply content aiming at the target user according to the target reply template;
and the communication module is used for outputting the reply content through the first terminal.
In a third aspect, embodiments of the present application provide a server comprising a processor and a memory, the processor and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program for execution by a processor to implement the method of the first aspect.
In summary, the server may obtain a question-answer request submitted by the first terminal, where the question-answer request carries user information and problem description information of the target user; the server can acquire a service information set of the target user according to the user information, and acquire an intention recognition result about the target user by utilizing the problem description information; the server can convert the intention recognition result into a target question-answer instruction, and match a target answer template for a target user according to the service information set and the target question-answer instruction, so that answer content aiming at the target user is obtained according to the target answer template, answer content is output through the first terminal, when a scene with quicker service development change is faced, and different services are required to be classified or the answer content is required to be personalized, the application can acquire the service information set in real time, and match the template by combining the target question-answer instruction obtained through technologies such as intention recognition and the like, so that answer content is generated, the question-answer flow is quicker, the answer content is more accurate, and the question-answer service quality is effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an artificial intelligence based question-answering method provided in an embodiment of the present application;
FIG. 2a is a schematic diagram of a relationship between a question and answer instruction and an answer template according to an embodiment of the present application;
FIG. 2b is a schematic diagram of a target page according to an embodiment of the present application;
FIG. 2c is a schematic diagram of another target page provided in an embodiment of the present application;
FIG. 2d is a schematic diagram of another target page provided in an embodiment of the present application;
FIG. 2e is a schematic diagram of another target page provided in an embodiment of the present application;
FIG. 2f is a schematic diagram of a question-answering process provided in an embodiment of the present application;
FIG. 3 is a flow chart of another method for providing an artificial intelligence based question-answering according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an artificial intelligence-based question answering device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, a schematic flow chart of an artificial intelligence-based question-answering method is provided in an embodiment of the present application. The method can be applied to a server. The server may be a server or a cluster of servers. Specifically, the method may comprise the steps of:
s101, acquiring a question-answer request submitted by a first terminal, wherein the question-answer request carries user information and question description information of a target user.
The first terminal can be a smart phone, a tablet personal computer, a notebook computer, a self-service terminal, a robot, such as an intelligent question-answering robot arranged in a market. The target user may be a user corresponding to the first terminal.
Wherein the user information may include user identification information. The user identification information is information for uniquely identifying the target user, including but not limited to any of the following: a user nickname, a user account number, a user cell phone number,
Wherein the question description information includes a question description statement. In one embodiment, the question description information may include question description statements and question context information, which may include the ID of the question-answer request (to uniquely identify one question-answer request) and the question-answer round (e.g., round 1, round 2).
In one embodiment, the question-answer request submitted by the first terminal may be forwarded to the server by the first terminal through another server, or may also be sent to the server by the first terminal.
In one application scenario, the question-answering request may be generated according to a question description sentence input by the target user obtained by the first terminal after detecting a click operation of the send button by the target user. Or, the question-answer request may be generated according to the target answer content after the first terminal detects the click operation of the sending button by the target user and obtains the target answer content selected by the target user from the existing answer content, where the target answer content may be a piece of answer content already displayed on the chat interface.
S102, acquiring a service information set of the target user according to the user information.
In this embodiment of the present application, the server may query the service information set of the target user according to the user information, for example, the server may query the service information set of the target user from the specified database or the target service system according to the user information. Wherein the link address for accessing the target business system may be configured based on the first plug-in template. The acquired service information sets are different according to different services used or consulted by the user. For example, for a loan service, the set of service information may include service information such as a payoff amount, a payoff time, a payoff period number, a payoff amount, and the like; for customer service, the service information set may include service date, user appeal, user attitude, and the like.
S103, identifying the questioning intention of the target user by utilizing the question description information to obtain an intention identification result.
S104, converting the intention recognition result into a target question-answering instruction.
Wherein the intention recognition result may include at least one keyword indicating a question intention of the target user. The target question-answering instruction refers to a question-answering instruction obtained through conversion according to the intention recognition result. The target question-answering instruction may be a string of characters. In one embodiment, the target question-answering instruction may be a character string indicating a business field to which the question description information corresponds, the character string being composed of numbers and/or letters.
In this embodiment of the present application, the method for identifying the question intent of the target user by using the question description information by the server to obtain the intent identification result may be: and the server calls an intention recognition model to recognize the question intention of the target user according to the question description information, so as to obtain an intention recognition result.
In one embodiment, the manner in which the server converts the intent recognition result into the target question-answer instruction may be: and the server determines a target question-answering instruction corresponding to the intention recognition result according to the corresponding relation between the keywords and the question-answering instruction.
In one embodiment, the server may further send the problem description information to a designated device (such as a designated robot), trigger the designated device to identify a question intention of the target user by using the problem description information, obtain an intention identification result, convert the intention identification result into a target question-answer instruction, and receive the target question-answer instruction returned by the designated device.
S105, matching a target reply template for the target user according to the service information set and the target question-answer instruction.
Wherein the target reply template refers to a reply template matched by the target user
In one embodiment, the server may determine, as the target reply template, a reply template corresponding to the target question-answer instruction according to the correspondence between the question-answer instruction and the reply template.
In one embodiment, the server may determine a use condition corresponding to the target question-answer instruction, and when the use condition is satisfied, acquire the target answer template. The use condition may be used to determine whether a target reply template may be used or may also be used to determine which reply template is specifically used as the target reply template.
In one embodiment, when the use condition is a use condition set based on a conditional expression, the server may acquire the conditional expression corresponding to the target question-answer instruction, and acquire the target answer template according to the service information set and the conditional expression.
In one embodiment, the server may obtain a conditional expression corresponding to the target question-answer instruction, and substitute each service information in the service information set into the conditional expression to perform operation, so as to obtain an operation result; the server determines a reply template corresponding to the operation result and determines the reply template corresponding to the operation result as a target reply template. Different operation results correspond to different reply templates, for example, referring to fig. 2a, one operation instruction may correspond to 4 reply templates. The reply template corresponding to the obtained operation result may be determined as the target reply template. The symbol in the drawings of the embodiments of the present application conceals the corresponding character (e.g., numeral or letter), and the symbol is displayed in the position of the corresponding character (e.g., numeral or letter) during the actual application process.
In one embodiment, the server may output a target page through the second terminal, where the target page is a page capable of configuring a question-answer instruction, a use condition, and a answer template. The second terminal may configure the target question-answer instruction, and the use condition and the answer template corresponding to the target question-answer instruction based on the target page. After the second terminal configures the target question-answer instruction and the use condition and the reply template corresponding to the target question-answer instruction, the server can acquire the target question-answer instruction and the use condition and the reply template corresponding to the target question-answer instruction, and store the target question-answer instruction and the use condition and the reply template corresponding to the target question-answer instruction. In one embodiment, the second terminal may be a terminal corresponding to a developer who can use the server, or may also be a terminal corresponding to a manager corresponding to the target service system, or the like. The second terminal may be a desktop computer, a notebook computer, a laptop computer, or the like.
In one embodiment, the target page may be a page as shown in fig. 2 b-2 c, the second terminal may display the page, the user corresponding to the second terminal may configure the target question-answer instruction and the use condition and the answer template corresponding to the target question-answer instruction based on the page, the user corresponding to the second terminal may click a determination button on the page after the configuration is completed to send the target question-answer instruction and the use condition and the answer template corresponding to the target question-answer instruction to the server, and the server may receive the target question-answer instruction and the use condition and the answer template corresponding to the target question-answer instruction and store the target question-answer instruction and the use condition and the answer template corresponding to the target question-answer instruction. The target page includes a question and answer instruction input area, a use condition input area, and a answer template input area. The question and answer instruction input area is used for inputting question and answer instructions, such as target question and answer instructions. The condition input area is used for inputting a conditional expression. The reply template input area is used for inputting a reply template. In one embodiment, the use of a conditional input area, when used to set a conditional expression, may be used to input an operator and a comparison value across the operator. In one embodiment, the target page may further include a status selection option including a status valid option and a status invalid option to determine whether the usage condition is satisfied later when the set is determined to be a valid status.
In one embodiment, the server may output a first page through the second terminal, the first page including a plurality of question-answer instructions, the plurality of question-answer instructions including a target question-answer instruction. After detecting a selection instruction of the target question-answer instruction sent by the second terminal, the server outputs a second page through the second terminal, so that the second terminal configures a conditional expression and a reply template corresponding to the target question-answer instruction based on the second page. The server acquires the conditional expression and the reply template corresponding to the target question-answer instruction, and stores the conditional expression and the reply template corresponding to the target question-answer instruction. The second page includes a question and answer instruction display area, a conditional expression input area, and a answer template input area. The second page here, the question and answer instruction display area of which displays the target question and answer instruction. In one embodiment, the question-answer instruction display area may not respond to the question-answer instruction input operation, i.e., the user corresponding to the second terminal will not be able to perform the question-answer instruction input operation based on the question-answer instruction display area. In one embodiment, the use of a conditional input area, when used to set a conditional expression, may be used to input an operator and a comparison value across the operator. In one embodiment, the second page may further include a status selection option including a status valid option and a status invalid option to determine whether the usage condition is satisfied later when the set is determined to be a valid status. Examples of the second page can be seen in fig. 2 b-2 c, among others. The second page may be identical to the target page in style, but has a difference in functions of the question-answer instruction display area and the question-answer instruction input area.
In one embodiment, the manner in which the server outputs the second page through the second terminal is specifically that the server searches for a second plugin template, where the second plugin template includes a page code of the second page. And the server sends the second plug-in module to the second terminal so that the second terminal generates the second page according to the second plug-in module and outputs the second page. Here, the second plug-in module can be embedded in the second terminal in the form of a page plug-in.
In one embodiment, when the use condition is a use condition set based on a preset value, such as a general answer, the server may acquire an answer template corresponding to the target question-answer instruction as the target answer template. The judgment of the condition is not required to be performed based on the use condition set by the preset value, compared with the use condition set based on the conditional expression. For example, the target page or the second page may also be referred to as the pages shown in fig. 2 d-2 e, where the target page differs from the second page as described above. The use condition is a general reply as can be seen from the pages shown in fig. 2 d-2 e.
S106, obtaining reply content aiming at the target user according to the target reply template, and outputting the reply content through the first terminal.
In one embodiment, the server may determine a target reply template as reply content to the target user.
In one embodiment, the server may identify the type of target reply template, and when the target reply template is a generic template, determine the target reply template as reply content to the target user.
In one embodiment, when the target reply template is a replacement template, the server replaces the corresponding service variable of the service information in the target reply template with each service information in the service information set to obtain a replaced reply template, and determines the replaced reply template as reply content to the target user.
In one embodiment, when the target reply template is a cyclic template, the server may replace service variables corresponding to the service information in the target reply template with each service information in the service information set multiple times, to obtain multiple replaced reply templates, combine the multiple replaced reply templates to obtain a combined reply template, and determine the combined reply template as reply content to the target user.
For example, referring to FIG. 2f, assume that the target user has 8 loan data, and the answer templates correspondingly configured are: application time: [ application time ], product: [ product name ] loan amount: [ loan amount ]. When the target answer template is a circulation template, the server can circularly process each (8 in this example) loan data of the target user, replace the business variable in the answer template by each loan data to obtain 8 filled answer templates (the N-th loan data corresponds to the serial number N), and finally the 8 filled answer templates are combined into a complete answer template to serve as answer contents for the target user.
It can be seen that, in the embodiment of fig. 1, the server may obtain a question-answer request submitted by the first terminal, where the question-answer request carries user information and problem description information of the target user; the server can acquire a service information set of the target user according to the user information, and acquire an intention recognition result about the target user by utilizing the problem description information; the server can convert the intention recognition result into a target question-answer instruction, and match a target answer template for a target user according to the service information set and the target question-answer instruction, so that answer content aiming at the target user is obtained according to the target answer template, and the answer content is output through the first terminal, and the process can effectively improve the question-answer service quality.
Referring to fig. 3, a flowchart of another question-answering method based on artificial intelligence according to an embodiment of the present application is shown. The method can be applied to a server. The server may be a server or a cluster of servers.
Specifically, the method may comprise the steps of:
s301, acquiring a question and answer request submitted by a first terminal, wherein the question and answer request carries user information and question description information of a target user, and the user information comprises user identification information and service system indication information.
Wherein the user identification information is information for uniquely identifying the target user, including but not limited to any of the following: the service system indication information is indication information which can be used for determining a target service system, for example, the service system indication information can be identification information of the target service system or an application account registered by a service provider (such as an enterprise). The identification information of the target service system is information for a unique target service system, for example, the identification information of the target service system may be an xx service system or an xx service. The application account registered by the service provider is not identification information of the service system, for example, the application account registered by the service provider may be a public number registered by the service provider on a public number platform.
S302, acquiring a service information set of the target user from a target service system according to the user identification information, wherein the target service system is a service system indicated by the service system indication information.
In one embodiment, the server obtains the service information set of the target user from the target service system according to the user identification information, and can query the link address for accessing the target service system according to the service system indication information, and splice the user identification information and the link address to obtain the spliced link address, so as to obtain the service information set of the target user from the target service system according to the spliced link address. In one embodiment, the link address may be a link address for a set of service information for each user accessing the target service system.
In one embodiment, the server may look up a first plugin template that includes a page code linking an address configuration page. The first plug-in template may be embedded in the target business system in the form of a page plug-in. The server sends the first plug-in template to a target business system so that the target business system configures a link address for accessing the target business system based on the first plug-in template. And the server receives the link address returned by the target service system and used for accessing the target service system, and stores the link address used for accessing the target service system. In one application scenario, the server may find the first plugin template, then send the first plugin template to the target service system, an administrator of the target service system may access the target service system and view a link address configuration page generated based on the first plugin template, then configure a link address of the target service system based on the link address configuration page, specifically may configure a link address for accessing a service information set of each user of the target service system, then return the configured link address to the target service system, and the target service system may forward the link address to the server.
S303, identifying the questioning intention of the target user by utilizing the question description information to obtain an intention identification result.
S304, converting the intention recognition result into a target question-answering instruction.
S305, matching a target reply template for the target user according to the service information set and the target question-answer instruction.
S306, obtaining reply content aiming at the target user according to the target reply template, and outputting the reply content through the first terminal.
Step S303 to step S306 can refer to step S103 to step S106, which are not described herein.
In one embodiment, if the aforementioned problem description information does not include problem context information, the server may initialize one problem context information and transmit the problem context information to the first terminal. If the question description information contains the question context information, the stored question context information is updated, and the answer content and the updated question context information (including the ID of the new question-answer request and the updated question-answer round) are sent to the first terminal, so that the user terminal submits the new question-answer request according to the updated question context information.
It can be seen that, in the embodiment shown in fig. 3, the server may obtain a question-answer request submitted by the first terminal, where the question-answer request carries user information and question description information of the target user, and the user information includes user identification information and service system indication information; the server acquires a service information set of a target user from a target service system according to the user identification information, wherein the target service system is a service system indicated by service system indication information; the server utilizes the question description information to identify the questioning intention of the target user, an intention identification result is obtained, and the intention identification result is converted into a target questioning and answering instruction, so that a target answering template is matched for the target user according to the service information set and the target questioning and answering instruction, answer content aiming at the target user is obtained according to the target answering template, and the answer content is output through the first terminal.
The present application relates to blockchain technology, and as the question-answer request may be sent by the first terminal to the server through the blockchain network, corresponding answer content may also be sent to the first terminal through the blockchain network. Alternatively, the server may write the user information, the question description information, and the answer content into the blockchain. The data written to the blockchain may be used for subsequent quality of questioning and answering service determinations, or subsequent troubleshooting.
Referring to fig. 4, a schematic diagram of a question answering device based on artificial intelligence according to an embodiment of the present application is shown. The question answering apparatus may be applied to a server. Specifically, the question answering apparatus may include:
the acquiring module 401 is configured to acquire a question-answer request submitted by the first terminal, where the question-answer request carries user information and question description information of the target user.
The obtaining module 401 is further configured to obtain a service information set of the target user according to the user information.
And the recognition module 402 is configured to recognize the question intention of the target user by using the question description information, so as to obtain an intention recognition result.
A conversion module 403, configured to convert the intention recognition result into a target question-answer instruction.
And the matching module 404 is configured to match a target answer template for the target user according to the service information set and the target question-answer instruction.
The obtaining module 401 is further configured to obtain reply content for the target user according to the target reply template.
And the communication module 405 is configured to output the reply content through the first terminal.
In an alternative embodiment, the user information includes user identification information and service system indication information, and the obtaining module 401 obtains, according to the user information, a service information set of the target user, specifically obtains, according to the user identification information, the service information set of the target user from a target service system, where the target service system is the service system indicated by the service system indication information.
In an optional implementation manner, the obtaining module 401 obtains, from a target service system, a service information set of the target user according to the user identification information, specifically, queries a link address for accessing the target service system according to the service system indication information; performing splicing processing on the user identification information and the link address to obtain a spliced link address; and acquiring the service information set of the target user from the target service system according to the spliced link address.
In an alternative embodiment, the question answering apparatus further comprises a search module 406 and a storage module 407.
In an alternative embodiment, the lookup module 406 is configured to lookup a first plugin template that includes a page code linking an address configuration page.
In an alternative embodiment, the communication module 405 is further configured to send the first add-in template to the target service system, so that the target service system configures a link address for accessing the target service system based on the first add-in template.
In an alternative embodiment, the communication module 405 is further configured to receive a link address returned by the target service system for accessing the target service system;
in an alternative embodiment, the storage module 407 is configured to store the link address for accessing the target service system.
In an alternative embodiment, the matching module 404 matches a target answer template for the target user according to the service information set and the target question-answer instruction, specifically, obtains a conditional expression corresponding to the target question-answer instruction; substituting each service information in the service information set into the conditional expression to operate so as to obtain an operation result; and determining a reply template corresponding to the operation result, and determining the reply template corresponding to the operation result as a target reply template.
In an optional implementation manner, the communication module 405 is further configured to output, through a second terminal, a first page, where the first page includes a plurality of question-answer instructions, where the plurality of question-answer instructions include the target question-answer instruction, and after detecting a selection instruction sent by the second terminal for the target question-answer instruction, output, through the second terminal, a second page, so that the second terminal configures a conditional expression and a response template corresponding to the target question-answer instruction based on the second page;
in an alternative embodiment, the obtaining module 401 is further configured to obtain a conditional expression and a reply template corresponding to the target question-and-answer instruction.
In an alternative embodiment, the storage module 407 is further configured to store a conditional expression and a reply template configured by the second terminal for the target question-answer instruction.
In an alternative embodiment, the communication module 405 outputs a second page through the second terminal, including: searching a second plug-in template through a searching module 406, wherein the second plug-in template comprises page codes of the second page; and sending the second plug-in module to the second terminal so that the second terminal generates the second page according to the second plug-in module and outputs the second page.
It can be seen that, in the embodiment shown in fig. 4, the question-answering device may acquire a question-answering request submitted by the first terminal, where the question-answering request carries user information and question description information of the target user; the question answering device can acquire a service information set of the target user according to the user information, and acquire an intention recognition result about the target user by utilizing the question description information; the question-answering device can convert the intention recognition result into a target question-answering instruction, and a target answer template is matched for the target user according to the service information set and the target question-answering instruction, so that answer content aiming at the target user is obtained according to the target answer template, and the answer content is output through the first terminal, and the process can effectively improve the question-answering service quality.
Fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application. The server described in the present embodiment may include: one or more processors 1000 and a memory 2000. The processor 1000 and the memory 2000 may be connected by a bus or the like.
The processor 1000 may be a central processing module (Central Processing Unit, CPU) which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 2000 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as a disk memory. The memory 2000 is used to store a set of program codes, and the processor 1000 may call the program codes stored in the memory 2000. Specifically:
a processor 1000, configured to obtain a question-answer request submitted by a first terminal, where the question-answer request carries user information and question description information of a target user;
acquiring a service information set of the target user according to the user information;
identifying the question intention of the target user by utilizing the question description information to obtain an intention identification result;
converting the intention recognition result into a target question-answering instruction;
matching a target reply template for the target user according to the service information set and the target question-answer instruction;
and obtaining reply content aiming at the target user according to the target reply template, and outputting the reply content through the first terminal.
In one embodiment, the servers described in this application may also include a communication interface (not shown in fig. 5). The communication interface may be a standard wired or wireless communication interface.
In one embodiment, the processor 1000 may transmit reply content to the first terminal through the communication interface so that the first terminal displays the reply content.
In one embodiment, the user information includes user identification information and service system indication information, and the processor 1000 obtains the service information set of the target user according to the user information, specifically obtains the service information set of the target user from a target service system according to the user identification information, where the target service system is the service system indicated by the service system indication information.
In one embodiment, the processor 1000 obtains a service information set of the target user from a target service system according to the user identification information, specifically, queries out a link address for accessing the target service system according to the service system indication information; performing splicing processing on the user identification information and the link address to obtain a spliced link address; and acquiring the service information set of the target user from the target service system according to the spliced link address.
In one embodiment, the processor 1000 is further configured to find a first plugin template, where the first plugin template includes a page code linking an address configuration page; transmitting the first plug-in module to the target service system so that the target service system configures a link address for accessing the target service system based on the first plug-in module; and receiving a link address returned by the target service system and used for accessing the target service system, and storing the link address used for accessing the target service system. In one embodiment, the processor 1000 may send the first plug-in module to the target service system through a communication interface, and may also receive, through the communication interface, a link address returned by the target service system for accessing the target service system. In one embodiment, the processor 1000 may store the link address for accessing the target business system through the memory 2000.
In one embodiment, the processor 1000 matches a target answer template for the target user according to the service information set and the target question-answer instruction, specifically, obtains a conditional expression corresponding to the target question-answer instruction; substituting each service information in the service information set into the conditional expression to operate so as to obtain an operation result; and determining a reply template corresponding to the operation result, and determining the reply template corresponding to the operation result as a target reply template.
In one embodiment, the processor 1000 is further configured to output, by the second terminal, a first page, the first page including a plurality of question-answering instructions, the plurality of question-answering instructions including the target question-answering instruction; after detecting a selection instruction of the target question-answer instruction sent by the second terminal, outputting a second page through the second terminal, so that the second terminal configures a conditional expression and a response template corresponding to the target question-answer instruction based on the second page; and acquiring a conditional expression and a reply template corresponding to the target question-answer instruction, and storing the conditional expression and the reply template configured by the second terminal for the target question-answer instruction. In one embodiment, the processor 1000 may transmit a first page to the second terminal through the communication interface so that the second terminal displays the first page, and may also transmit a second page to the second terminal through the communication interface so that the second terminal displays the second page. In one embodiment, processor 1000 may maintain a conditional expression of the target question-answer quality configuration and an answer template through memory 2000.
In one embodiment, the processor 1000 outputs a second page through the second terminal, specifically searches for a second plug-in template, where the second plug-in template includes a page code of the second page; and sending the second plug-in module to the second terminal so that the second terminal generates the second page according to the second plug-in module and outputs the second page.
In specific implementation, the processor 1000 described in the embodiments of the present application may perform the implementation described in the embodiments of fig. 1 and fig. 3, or may perform the implementation described in the embodiments of the present application, which is not described herein again.
The functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in the form of sampling hardware or in the form of sampling software functional modules.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Wherein the computer readable storage medium may be volatile or nonvolatile. For example, the computer storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like. The computer readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
The foregoing disclosure is only a preferred embodiment of the present application, and it is not intended to limit the scope of the claims, and one of ordinary skill in the art will understand that all or part of the processes for implementing the embodiments described above may be performed with equivalent changes in the claims of the present application and still fall within the scope of the present application.
Claims (7)
1. An artificial intelligence based question-answering method, comprising:
acquiring a question-answer request submitted by a first terminal, wherein the question-answer request carries user information and question description information of a target user;
acquiring a service information set of the target user according to the user information;
Identifying the question intention of the target user by utilizing the question description information to obtain an intention identification result;
converting the intention recognition result into a target question-answering instruction;
matching a target reply template for the target user according to the service information set and the target question-answer instruction, wherein the matching comprises the following steps: acquiring a conditional expression corresponding to the target question-answer instruction, substituting each service information in the service information set into the conditional expression to perform operation to obtain an operation result, determining a answer template corresponding to the operation result, and determining the answer template corresponding to the operation result as a target answer template;
obtaining reply content for the target user according to the target reply template, outputting the reply content through the first terminal,
the method further comprises the steps of:
outputting a first page through a second terminal, wherein the first page comprises a plurality of question-answering instructions, and the plurality of question-answering instructions comprise the target question-answering instructions;
after detecting a selection instruction of the target question-answer instruction sent by the second terminal, outputting a second page through the second terminal, so that the second terminal configures a conditional expression and a response template corresponding to the target question-answer instruction based on the second page, wherein the outputting the second page through the second terminal comprises: searching a second plug-in template, wherein the second plug-in template comprises a page code of the second page, and the second plug-in template is sent to the second terminal so that the second terminal can generate the second page according to the second plug-in template and output the second page;
And acquiring a conditional expression and a reply template corresponding to the target question-answer instruction, and storing the conditional expression and the reply template configured by the second terminal for the target question-answer instruction.
2. The method according to claim 1, wherein the user information includes user identification information and service system indication information, and the acquiring the service information set of the target user according to the user information includes:
and acquiring a service information set of the target user from a target service system according to the user identification information, wherein the target service system is a service system indicated by the service system indication information.
3. The method according to claim 2, wherein said obtaining the service information set of the target user from the target service system according to the user identification information comprises:
inquiring a link address for accessing the target service system according to the service system indication information;
performing splicing processing on the user identification information and the link address to obtain a spliced link address;
and acquiring the service information set of the target user from the target service system according to the spliced link address.
4. A method according to claim 3, characterized in that the method further comprises:
searching a first plug-in module, wherein the first plug-in module comprises a page code of a link address configuration page;
transmitting the first plug-in module to the target service system so that the target service system configures a link address for accessing the target service system based on the first plug-in module;
and receiving a link address returned by the target service system and used for accessing the target service system, and storing the link address used for accessing the target service system.
5. An artificial intelligence based question answering apparatus, comprising:
the acquisition module is used for acquiring a question-answer request submitted by the first terminal, wherein the question-answer request carries user information and question description information of a target user;
the acquisition module is further used for acquiring a service information set of the target user according to the user information;
the recognition module is used for recognizing the questioning intention of the target user by utilizing the question description information to obtain an intention recognition result;
the conversion module is used for converting the intention recognition result into a target question-answer instruction;
The matching module is used for matching a target reply template for the target user according to the service information set and the target question-answer instruction, and is also used for acquiring a conditional expression corresponding to the target question-answer instruction, substituting each service information in the service information set into the conditional expression to perform operation, obtaining an operation result, determining a reply template corresponding to the operation result, and determining the reply template corresponding to the operation result as a target reply template;
the obtaining module is further used for obtaining reply content aiming at the target user according to the target reply template;
the communication module is used for outputting the reply content through the first terminal;
the communication module is also used for outputting a first page through a second terminal, the first page comprises a plurality of question-answer instructions, the plurality of question-answer instructions comprise the target question-answer instructions, after detecting a selection instruction of the target question-answer instructions sent by the second terminal, the second terminal outputs a second page, so that the second terminal configures a conditional expression and a reply template corresponding to the target question-answer instructions based on the second page,
The communication module is further used for searching a second plug-in module, the second plug-in module comprises a page code of the second page, the second plug-in module is sent to the second terminal, so that the second terminal generates the second page according to the second plug-in module, and the second page is output;
the acquisition module is also used for acquiring a conditional expression and a reply template corresponding to the target question-answer instruction;
and the storage module is used for storing a conditional expression and a reply template configured by the second terminal for the target question-answer instruction.
6. A server comprising a processor and a memory, the processor and the memory being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-4.
7. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement the method of any of claims 1-4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110395698.1A CN112925898B (en) | 2021-04-13 | 2021-04-13 | Question-answering method and device based on artificial intelligence, server and storage medium |
| PCT/CN2021/097022 WO2022217708A1 (en) | 2021-04-13 | 2021-05-29 | Artificial intelligence-based question and answer method and apparatus, server, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110395698.1A CN112925898B (en) | 2021-04-13 | 2021-04-13 | Question-answering method and device based on artificial intelligence, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112925898A CN112925898A (en) | 2021-06-08 |
| CN112925898B true CN112925898B (en) | 2023-07-18 |
Family
ID=76174320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110395698.1A Active CN112925898B (en) | 2021-04-13 | 2021-04-13 | Question-answering method and device based on artificial intelligence, server and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112925898B (en) |
| WO (1) | WO2022217708A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114489557B (en) * | 2021-12-15 | 2024-03-22 | 青岛海尔科技有限公司 | Voice interaction method, device, equipment and storage medium |
| CN116307663B (en) * | 2023-02-16 | 2023-09-08 | 广州力麒智能科技有限公司 | Intelligent self-service government affair service system, government affair service general method and terminal |
| CN116932911B (en) * | 2023-07-24 | 2023-12-15 | 山东翰林科技有限公司 | Electric power knowledge question-answering assistant construction method based on ChatGPT |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664599A (en) * | 2018-05-09 | 2018-10-16 | 腾讯科技（深圳）有限公司 | Intelligent answer method, apparatus, intelligent answer server and storage medium |
| CN110298906A (en) * | 2019-06-28 | 2019-10-01 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN111104495A (en) * | 2019-11-19 | 2020-05-05 | 深圳追一科技有限公司 | Information interaction method, device, equipment and storage medium based on intention recognition |
| CN112182185A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Intelligent client auxiliary processing method and system for power supply field |
| CN112202978A (en) * | 2020-08-24 | 2021-01-08 | 维知科技张家口有限责任公司 | Intelligent outbound call system, method, computer system and storage medium |
| CN112328871A (en) * | 2020-10-27 | 2021-02-05 | 深圳集智数字科技有限公司 | Reply generation method, device, equipment and storage medium based on RPA module |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019836A (en) * | 2017-08-23 | 2019-07-16 | 中兴通讯股份有限公司 | A kind of intelligent answer method and device |
| CN107885874B (en) * | 2017-11-28 | 2020-09-29 | 上海智臻智能网络科技股份有限公司 | Data query method and device, computer equipment and computer readable storage medium |
| CN108595494B (en) * | 2018-03-15 | 2022-05-20 | 腾讯科技（深圳）有限公司 | Method and device for acquiring reply information |
| JP7054413B2 (en) * | 2018-03-27 | 2022-04-13 | 株式会社日立製作所 | Customer support system and customer support method |
| CN110968663B (en) * | 2018-09-30 | 2023-05-23 | 北京国双科技有限公司 | Answer display method and device of question-answering system |
-
2021
- 2021-04-13 CN CN202110395698.1A patent/CN112925898B/en active Active
- 2021-05-29 WO PCT/CN2021/097022 patent/WO2022217708A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664599A (en) * | 2018-05-09 | 2018-10-16 | 腾讯科技（深圳）有限公司 | Intelligent answer method, apparatus, intelligent answer server and storage medium |
| CN110298906A (en) * | 2019-06-28 | 2019-10-01 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN111104495A (en) * | 2019-11-19 | 2020-05-05 | 深圳追一科技有限公司 | Information interaction method, device, equipment and storage medium based on intention recognition |
| CN112202978A (en) * | 2020-08-24 | 2021-01-08 | 维知科技张家口有限责任公司 | Intelligent outbound call system, method, computer system and storage medium |
| CN112182185A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Intelligent client auxiliary processing method and system for power supply field |
| CN112328871A (en) * | 2020-10-27 | 2021-02-05 | 深圳集智数字科技有限公司 | Reply generation method, device, equipment and storage medium based on RPA module |
Non-Patent Citations (1)
| Title |
|---|
| 政务服务中的智能问答机器人：现状、机理和关键支撑;王友奎 等;《电子政务 E-GOVERNMENT》(第02期);34-45 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022217708A1 (en) | 2022-10-20 |
| CN112925898A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021082953A1 (en) | Machine reading understanding method and apparatus, storage medium, and device | |
| WO2022088672A1 (en) | Machine reading comprehension method and apparatus based on bert, and device and storage medium | |
| CN112925898B (en) | Question-answering method and device based on artificial intelligence, server and storage medium | |
| CN110929125B (en) | Search recall method, device, equipment and storage medium thereof | |
| CN111552799B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN108959559B (en) | Question and answer pair generation method and device | |
| CN111026858B (en) | Project information processing method and device based on project recommendation model | |
| CN112650854B (en) | Intelligent reply method and device based on multiple knowledge graphs and computer equipment | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN112287069B (en) | Information retrieval method and device based on voice semantics and computer equipment | |
| US20190236155A1 (en) | Feedback for a conversational agent | |
| US11646984B2 (en) | Emoji recommendation system and method | |
| CN113656547B (en) | Text matching method, device, equipment and storage medium | |
| CN115687647A (en) | Notarization document generation method and device, electronic equipment and storage medium | |
| CN111930891B (en) | Knowledge graph-based search text expansion method and related device | |
| CN113177407A (en) | Data dictionary construction method and device, computer equipment and storage medium | |
| CN112527967A (en) | Text matching method, device, terminal and storage medium | |
| CN112069304A (en) | Question answering method, device, server and storage medium for insurance business | |
| CN111428230A (en) | Information verification method, device, server and storage medium | |
| CN111783425A (en) | Intention identification method based on syntactic analysis model and related device | |
| US20180293508A1 (en) | Training question dataset generation from query data | |
| CN111695031A (en) | Label-based searching method, device, server and storage medium | |
| CN111552890A (en) | Name information processing method and device based on name prediction model and electronic equipment | |
| KR102605941B1 (en) | Trademark application service providing system and integrated server | |
| CN115827834A (en) | Answer generation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |