CN111061849A - Answer information feedback method and device - Google Patents
Answer information feedback method and device Download PDFInfo
- Publication number
- CN111061849A CN111061849A CN201911218330.7A CN201911218330A CN111061849A CN 111061849 A CN111061849 A CN 111061849A CN 201911218330 A CN201911218330 A CN 201911218330A CN 111061849 A CN111061849 A CN 111061849A
- Authority
- CN
- China
- Prior art keywords
- preset
- information
- keyword
- question
- keywords
- 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.)
- Pending
Links
Images
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
Abstract
The application provides an answer information feedback method and device, and relates to the technical field of intelligent question answering. Firstly, problem information sent by a client is obtained, and then the problem information is preprocessed to obtain a key phrase corresponding to the problem information; the method comprises the steps that a keyword group comprises at least one keyword, the keyword group is matched with a plurality of preset problem information from a preset knowledge base, each preset problem information corresponds to a relevant keyword, and the keywords in each preset problem information are subjected to part-of-speech scoring; the method comprises the steps of obtaining part-of-speech scores of keywords in each preset question message, determining target preset question messages according to comparison of the part-of-speech scores of the keywords in the preset question messages, and finally sending answer messages corresponding to the target preset question messages to a client. The answer information feedback method and device have the advantages of being high in speed and high in accuracy.
Description
Technical Field
The application relates to the technical field of intelligent question answering, in particular to an answer information feedback method and device.
Background
At present, in order to serve users well, more and more internet enterprises use an intelligent question-answering system to perform user maintenance. Namely, when the user asks questions online, the preset answer information can be matched through the system and fed back to the user.
However, the currently provided intelligent question-answering system generally has poor answer matching accuracy, so that the user experience is poor.
Disclosure of Invention
The application aims to provide an answer information feedback method and device to solve the problem that in the prior art, the accuracy of answers matched by an intelligent question-answering system is poor.
In order to achieve the above purpose, the embodiments of the present application employ the following technical solutions:
in one aspect, an embodiment of the present application provides an answer information feedback method, where the method is applied to a server in an intelligent question-answering system, where the intelligent question-answering system further includes at least one client, and the server is in communication connection with the client, and the method includes:
acquiring problem information sent by the client;
preprocessing the question information to obtain a key phrase corresponding to the question information; wherein, the keyword group comprises at least one keyword;
matching a plurality of preset problem information from a preset knowledge base by using the keyword group, wherein each preset problem information corresponds to the keyword;
performing part-of-speech scoring on the keywords in each piece of preset problem information; acquiring the part-of-speech score of the keyword in each preset question message;
determining target preset problem information according to comparison of parts of speech scores of keywords in the preset problem information;
and sending answer information corresponding to the target preset question information to the client.
On the other hand, the present application further provides an answer information feedback device, where the device is applied to a server in an intelligent question-answering system, the intelligent question-answering system further includes at least one client, the server is in communication connection with the client, and the device includes:
the data acquisition unit is used for acquiring the problem information sent by the client;
the data processing unit is used for preprocessing the question information to acquire a key phrase corresponding to the question information; wherein, the keyword group comprises at least one keyword;
the data processing unit is further configured to match a plurality of preset question information from a preset knowledge base by using the keyword group, wherein each preset question information corresponds to the keyword;
the data processing unit is also used for performing part-of-speech scoring on the keywords in each preset question message; acquiring the part-of-speech score of the keyword in each preset question message;
the data processing unit is also used for determining target preset problem information according to comparison of the parts of speech scores of the keywords in the preset problem information;
and the data sending unit is used for sending answer information corresponding to the target preset question information to the client.
Compared with the prior art, the method has the following beneficial effects:
the embodiment of the application provides an answer information feedback method and device, which are applied to a server in an intelligent question-answering system, wherein the intelligent question-answering system also comprises at least one client, the server is in communication connection with the client, firstly, question information sent by the client is obtained, and then the question information is preprocessed to obtain a key phrase corresponding to the question information; the method comprises the steps that a keyword group comprises at least one keyword, the keyword group is matched with a plurality of preset problem information from a preset knowledge base, each preset problem information corresponds to a relevant keyword, and the keywords in each preset problem information are subjected to part-of-speech scoring; the method comprises the steps of obtaining part-of-speech scores of keywords in each preset question message, determining target preset question messages according to comparison of the part-of-speech scores of the keywords in the preset question messages, and finally sending answer messages corresponding to the target preset question messages to a client. According to the method and the device, the preset question information can be determined in the preset knowledge base according to the keywords, the best matched preset question information is determined according to the part-of-speech score of the preset question information, and then the answer information corresponding to the preset question information is fed back to the user, so that the fed-back answer information is higher in precision, and the experience of the user is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and it will be apparent to those skilled in the art that other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is an interaction diagram of an intelligent question answering system according to an embodiment of the present application.
Fig. 2 is a schematic block diagram of a server provided in an embodiment of the present application.
Fig. 3 is a schematic flowchart of an answer information determination method according to an embodiment of the present application.
Fig. 4 is a schematic flowchart of the sub-step of S104 in fig. 3 provided in an embodiment of the present application.
Fig. 5 is a schematic flowchart of the sub-step of S106 in fig. 3 according to an embodiment of the present disclosure.
Fig. 6 is another schematic flowchart of the sub-step of S106 in fig. 3 according to an embodiment of the present disclosure.
Fig. 7 is a schematic flowchart of the sub-step of S108 in fig. 3 according to an embodiment of the present application.
Fig. 8 is a schematic flowchart of the sub-step of S110 in fig. 3 according to an embodiment of the present application.
Fig. 9 is a block diagram of an answer information determination apparatus according to an embodiment of the present application.
In the figure: 100-a server; 101-a memory; 102-a processor; 103-a communication interface; 200-answer information determination means; 210-a data acquisition unit; 220-a data processing unit; 300-intelligent question-answering system; 310-client.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally found in use of products of the application, and are used only for convenience in describing the present application and for simplification of description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application.
In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
First embodiment
As described in the background art, the smart question-answering system is a system that can determine a corresponding answer from preset contents according to a question input by a user and transmit the answer to the user, thereby enabling the user to ask a question at any time. However, the currently provided intelligent question-answering system generally has a problem of poor answer matching accuracy, so that the user experience is poor. Such as the familiar "answer questions," i.e., the user's question is associated with little or no relevance to the answers obtained from the intelligent question-answering system.
In view of this, the present application provides an answer information feedback method, so as to achieve an effect of improving the matching accuracy of the intelligent question and answer system by using a part-of-speech scoring manner.
It should be noted that, the answer information determining method provided by the present application is applied to a server in an intelligent question-answering system, please refer to fig. 1, the intelligent question-answering system 300 further includes at least one client 310, and the server 100 is in communication connection with the client 310. It is understood that the client 310 may be an electronic device used by the user, such as a mobile phone, a computer, a wearable device or other device capable of interacting with the background. Moreover, there are many users per internet merchant, that is, in the intelligent question-answering system 300, the number of the clients 310 may be many.
The answer information determination method provided by the present application is exemplarily described below with a server as an execution subject.
Referring to fig. 2, the server includes a memory 101, a processor 102 and a communication interface 103, wherein the memory 101, the processor 102 and the communication interface 103 are electrically connected to each other directly or indirectly to implement data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, such as program instructions/modules corresponding to the answer information determination device 200 provided in the embodiments of the present application, and the processor 102 executes the software programs and modules stored in the memory 101, so as to execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 102 may be an integrated circuit chip having signal processing capabilities. The processor 102 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
It will be appreciated that the configuration shown in fig. 2 is merely illustrative and that server 100 may include more or fewer components than shown in fig. 2 or have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
Referring to fig. 3, the answer information feedback method provided in the present application includes:
s102, problem information sent by the client is obtained.
S104, preprocessing the question information to obtain a key phrase corresponding to the question information; wherein, the keyword group comprises at least one keyword.
And S106, matching a plurality of preset question information from a preset knowledge base by using the keyword group, wherein each preset question information corresponds to a related keyword.
S108, performing part-of-speech scoring on the keywords in each preset question message; so as to obtain the part-of-speech score of the keyword in each preset question message.
S110, determining target preset problem information according to comparison of the parts of speech scores of the keywords in the preset problem information.
And S112, sending answer information corresponding to the target preset question information to the client.
That is, in the present application, when a user needs to ask a question to a customer of an internet merchant, corresponding question information may be input, so that the server 100 can acquire the corresponding question information. For example, the user inputs the question "do it rains today" question.
In one possible implementation, the user input as question information may be in the form of a question sentence, such as the question sentence information described above as "do you rain today". In another possible implementation manner, the user may also send question information, such as "i want to rent a car in guangzhou" or the like, to the server 100 in a statement form through the client 310, and the server 100 may default whether the question posed by the user has a corresponding car in guangzhou for renting, a specific fee for renting a car, or the like. This is not a limitation of the present application.
After receiving the question information, the server 100 preprocesses the question information, and can further obtain a corresponding keyword group in the question information, where the keyword group includes at least one keyword.
In addition, the server 100 is further provided with a preset knowledge base, a plurality of preset question information are stored in the knowledge base, and each preset question information is correspondingly provided with one standard answer. The server 100 can determine a plurality of preset problem information matched and associated with the keyword group from a preset knowledge base, and then perform part-of-speech scoring on the keywords in each preset problem information, thereby obtaining part-of-speech scores of the keywords in each preset problem information. Finally, the server 100 can determine the target preset question information according to the comparison of the parts of speech scores of the keywords in the preset question information, and send answer information corresponding to the target preset question information to the client 310.
By the answer information determining method provided by the application, the server 100 can match answers with higher precision after a user asks a question, so that the user experience is better.
As a possible implementation manner, referring to fig. 4, S104 includes:
s1041, performing word segmentation processing on the question information to obtain at least one candidate keyword.
S1042, performing word-stop-removing processing on at least one candidate keyword to obtain a target keyword.
It can be understood that, in order to effectively extract the keywords in the user question, the question information provided by the user needs to be participled. For example, a jieba word segmentation algorithm is adopted to perform word segmentation processing on the problem information of the user, so as to obtain at least one candidate keyword. The jieba word segmentation algorithm uses a prefix dictionary to realize efficient word graph scanning, generates a Directed Acyclic Graph (DAG) formed by all possible word generation conditions of Chinese characters in a sentence, then adopts dynamic programming to search a maximum probability path, finds out a maximum segmentation combination based on word frequency, adopts an HMM model based on the word forming capability of the Chinese characters for unknown words, and uses a Viterbi algorithm.
For example, when the user inputs that the question information is "how to charge for car rental in guangzhou", the server 100 performs word segmentation processing on the question information, and the information after word segmentation is "guangzhou/car rental/yes/how to charge/woollen", so that the server 100 can acquire six candidate keywords of "guangzhou", "car rental", "yes", "how", "charge" and "woollen".
Since the candidate keywords include some words that do not contribute to the problem, in the present application, the server 100 performs the word-stopping process on the candidate keywords, so as to obtain the target keywords.
The term removing process refers to removing stop words in the candidate keywords, such as words like o, mo, ba, etc. Of course, there may be words, which the present application does not limit in any way. Meanwhile, the stop word can also remove other words which do not play a role in the question, such as yes, how, etc.
It can be understood that, after the six candidate keywords of "guangzhou", "car rental", "yes", "how", "charge" and "wool" are processed by the stop-word removing process, the target keywords are the three keywords of "guangzhou", "car rental" and "charge".
As a possible implementation manner, after the step of S1042, S104 further includes:
and S1043, performing synonym conversion on the keywords obtained after the stop word removing processing to obtain target keywords.
It is understood that the intelligent question answering system 300 further comprises a database, which is in communication with the server 100, wherein the staff member can store synonyms into the database, for example, synonyms including but not limited to invoicing and invoicing, mei-rou coupons and mei-rou coupons, car renting and car borrowing, etc., and when the server 100 determines a candidate keyword, it can determine whether the keyword has a synonym from the database, and if so, the synonym is used as the target keyword. By the method, the intelligent question-answering system 300 can automatically identify different synonyms, determine whether the associated synonyms exist in the use process, and facilitate the problem information of different keywords input by a user to determine the corresponding keyword groups.
For example, the server 100 communicates with a database, and after the server 100 receives the question information of the user and obtains the keyword, the server 100 obtains the synonym from the database by using the keyword, thereby implementing the synonym conversion.
Of course, if the server 100 cannot find the corresponding keyword from the database using the keyword, the synonym conversion is not required.
As a possible implementation manner, in the present application, referring to fig. 5, S106 includes:
s1061, determining preset problem information containing all keywords from a preset knowledge base.
And S1062, when the number of the determined preset problem information is smaller than the threshold value, removing one keyword, and re-determining the preset problem information by using the remaining keywords until the number of the determined preset problem information is larger than or equal to the threshold value.
When the keyword group is determined, the server 100 matches preset problem information from the database by using the keyword group. It is to be understood that the knowledge base described herein is also essentially a database that is communicatively coupled to the server 100. And a plurality of preset problem information is stored in the knowledge base, the preset problem information is a problem which can be provided by a user in the using process, and operation and maintenance personnel can update the preset problem information in the database in real time according to actual using requirements. Meanwhile, the database and the synonym database may be the same database, and may also be the same database, which is not limited in this application.
After determining the keyword group, the server 100 determines the preset problem information from the knowledge base by using the keyword group, for example, if the keyword group includes three keywords, the server 100 matches all the preset problem information including the three keywords from the database.
Taking the keyword group as "guangzhou, car rental, and toll collection" as an example for explanation, after the server 100 determines the keyword group, the preset problem information that the server 100 can determine from the knowledge base includes two preset problems, that is, what the charging condition of the car rental in guangzhou is, "and" the charging of the car rental in guangzhou changes ".
In order to further improve the accuracy of determining the user problem, in the present application, it is required to meet that the number of the determined preset problem information reaches a threshold, for example, the threshold is set to 5, the number of the preset problem information determined by using the keyword group is required to be greater than 5, and then the most accurate preset problem information is determined from the 5 preset problem information.
In view of this, when the number of the preset problem information is smaller than the threshold, for example, the number of the preset problem information determined according to "guangzhou, car rental, and fee collection" is 2, and the number of the preset information is smaller than the threshold, the server 100 will extract one keyword, and re-determine the preset problem information by using the remaining keywords. For example, the server 100 may eliminate the guangzhou, so that two keywords "rent car and charge" remain in the keyword group, and then match the preset problem information in the knowledge base with the two keywords.
If the number of the matched preset problem information reaches 5, for example, 6 preset problem information are matched, stopping the matching process; and if the matched preset problem information is still smaller than the threshold value, rejecting a keyword again, and continuously re-determining the preset problem information by using the rest keywords.
Through the implementation mode of the application, the preset problem information with enough quantity can be matched from the database by using the key phrases, so that the finally determined preset problem information and the problem information provided by the user are more accurate.
As a possible implementation manner, S104 further includes:
and S104-4, performing part-of-speech scoring on each keyword in the keyword group corresponding to the question information.
On the basis, referring to fig. 6, the step S1062 includes:
and S1062-a, when the number of the determined preset problem information is smaller than a threshold value, eliminating the keyword with the lowest score after the part of speech is scored, and re-determining the preset problem information by using the remaining keywords.
That is, after the server 100 processes the question information of the client 310 and obtains the keyword group, the server 100 also performs part-of-speech scoring on each keyword.
Further, S104-4 includes:
and S104-4a, determining the parts of speech of the keywords, wherein the parts of speech comprise nouns, verbs, adjectives, adverbs and prepositions.
And S104-4b, determining the part-of-speech score of the keyword according to the part-of-speech of the keyword.
That is, after determining the keywords, the parts of speech of the keywords in the question information of the user, such as nouns, verbs, adjectives, adverbs, and prepositions, are first determined. Because the corresponding key degrees of the part of speech are different in a sentence, a scoring mechanism can be preset, and the part of speech score of the keyword is determined according to the scoring machine intelligence.
For example, if a keyword is a noun, the score is 1 in the part of speech, if the keyword is an adjective, the score is 0.5, if the keyword is a verb, the score is 0.8, and so on.
Taking the user question "how to charge for car rental in Guangzhou" as an example, after determining the keyword group of "Guangzhou, car rental, charge", the server 100 scores each keyword, where Guangzhou is a preposition whose part-of-speech score is 0.5, car rental is also a preposition whose score is 0.5, charge is a verb, and whose score is 0.8.
That is, when the number of the determined preset problem information is smaller than the threshold value, the server 100 may remove the keyword "guangzhou" or "rent car", and then re-match the preset problem information. Until the number of the matched preset problem information is larger than or equal to the threshold value.
Referring to fig. 7 as a possible implementation manner of the present application, the step S108 includes:
s1081, determining parts of speech of the keywords, wherein the parts of speech include nouns, verbs, adjectives, adverbs and prepositions.
S1082, determining a part-of-speech score of the keyword according to the part-of-speech of the keyword.
It should be noted that even if the same keyword is in different contexts, the parts of speech thereof are different, for example, "rent car" is a preposition in the question information sent by the client 310, and is a verb in the matched preset question information, and the parts of speech thereof are not consistent.
Also, as a possible implementation manner, referring to fig. 8, S110 includes:
s1101, summing the parts-of-speech scores of all the keywords in each preset question information to obtain a total part-of-speech score.
And S1102, selecting preset problem information with the highest part-of-speech total score as target preset problem information.
Namely, the determination of the target preset problem in the application is determined by the sum of the parts of speech scores of the keywords in the preset problem information. For example, in the preset question information determined by the server 100, the keywords of the first preset question information are a1 and B, C, where a1 is a preposition, the part-of-speech score of the preposition is 0.5, and the part-of-speech score of B, C is also 0.5, so that the total part-of-speech score of the preset question information is 1.5. The keywords of the second preset question information are also a2 and B, C, where a2 is a noun with a part-of-speech score of 1 and a part-of-speech score of B, C is also 0.5, and then the total part-of-speech score of the preset question information is 2. Therefore, the server 100 determines the second question information as the target preset question information.
It should be noted that, in the knowledge base, each piece of preset question information corresponds to one piece of answer information, for example, the preset question information "what the charging condition of the car rental in Guangzhou" is "corresponds to answer information of" 150 yuan/day ", and" does the charging of the car rental in Guangzhou "corresponds to answer information of" 1 month and 1 day later, the corresponding answer information is affected by fluctuation of the oil price information, and the car rental fee may be adjusted up ".
When the server 100 determines the target preset question information, it may determine answer information corresponding to the target preset question information from the knowledge base and send the answer information to the client 310.
It can be understood that the answer information determination method provided by the application can be used for providing service for the user in 24 hours, and is more convenient. In addition, by the answer information determining method provided by the application, the problem of the user can be determined more accurately, and the answer corresponding to the problem provided by the user is further determined.
Second embodiment
Referring to fig. 9, a functional unit of an answer information determination apparatus 200 according to a preferred embodiment of the present invention is shown. It should be noted that the basic principle and the generated technical effect of the answer information determination apparatus 200 provided in the present embodiment are the same as those of the above embodiments, and for the sake of brief description, no part of the embodiments of the present invention is mentioned, and reference may be made to the corresponding contents in the above embodiments. The answer information determination device 200 includes:
a data obtaining unit 210, configured to obtain the question information sent by the client 310.
It is understood that S102 may be performed by the data acquisition unit 210.
The data processing unit 220 is configured to pre-process the question information to obtain a keyword group corresponding to the question information; wherein, the keyword group comprises at least one keyword.
The data processing unit 220 is configured to perform word segmentation on the question information to obtain at least one candidate keyword.
The data processing unit 220 is configured to perform word segmentation on the question information to obtain at least one candidate keyword, and perform word segmentation removal processing on the at least one candidate keyword to obtain a target keyword.
It is understood that S104 may be performed by the data processing unit 220.
The data processing unit 220 is further configured to match a plurality of preset question information from a preset knowledge base by using the keyword group, where each preset question information corresponds to a related keyword.
The data processing unit 220 is further configured to, when the determined number of preset question information is smaller than the threshold, reject one of the keywords, and re-determine the preset question information by using the remaining keywords until the determined number of preset question information is greater than or equal to the threshold.
It is understood that S106 may be performed by the data processing unit 220.
The data processing unit 220 is further configured to score parts of speech of the keywords in each preset question information; so as to obtain the part-of-speech score of the keyword in each preset question message.
It is understood that S108 may be performed by the data processing unit 220.
The data processing unit 220 is further configured to determine target preset question information according to comparison of the parts of speech scores of the keywords in the preset question information.
It is understood that S110 may be performed by the data processing unit 220.
And a data sending unit, configured to send answer information corresponding to the target preset question information to the client 310.
It is understood that S112 may be performed by the data processing unit 220.
To sum up, the embodiment of the present application provides an answer information feedback method and device, which are applied to a server in an intelligent question-and-answer system, where the intelligent question-and-answer system further includes at least one client, and the server is in communication connection with the client, and first obtains question information sent by the client, and then preprocesses the question information to obtain a keyword group corresponding to the question information; the method comprises the steps that a keyword group comprises at least one keyword, the keyword group is matched with a plurality of preset problem information from a preset knowledge base, each preset problem information corresponds to a relevant keyword, and the keywords in each preset problem information are subjected to part-of-speech scoring; the method comprises the steps of obtaining part-of-speech scores of keywords in each preset question message, determining target preset question messages according to comparison of the part-of-speech scores of the keywords in the preset question messages, and finally sending answer messages corresponding to the target preset question messages to a client. According to the method and the device, the preset question information can be determined in the preset knowledge base according to the keywords, the best matched preset question information is determined according to the part-of-speech score of the preset question information, and then the answer information corresponding to the preset question information is fed back to the user, so that the fed-back answer information is higher in precision, and the experience of the user is improved.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. An answer information feedback method, wherein the method is applied to a server in an intelligent question-answering system, the intelligent question-answering system further comprises at least one client, and the server is in communication connection with the client, and the method comprises the following steps:
acquiring problem information sent by the client;
preprocessing the question information to obtain a key phrase corresponding to the question information; wherein, the keyword group comprises at least one keyword;
matching a plurality of preset problem information from a preset knowledge base by using the keyword group, wherein each preset problem information corresponds to the keyword;
performing part-of-speech scoring on the keywords in each piece of preset problem information; acquiring the part-of-speech score of the keyword in each preset question message;
determining target preset problem information according to comparison of parts of speech scores of keywords in the preset problem information;
and sending answer information corresponding to the target preset question information to the client.
2. The answer information feedback method of claim 1, wherein the step of preprocessing the question information to obtain the keyword group corresponding to the question information comprises:
performing word segmentation processing on the question information to obtain at least one candidate keyword;
and performing word stopping processing on the at least one candidate keyword to obtain a target keyword.
3. The answer information feedback method of claim 2, wherein after the step of performing a stop-word process on the at least one candidate keyword, the method further comprises:
and carrying out synonym conversion on the keywords obtained after the stop word removing processing so as to obtain the target keywords.
4. The answer information feedback method of claim 1, wherein the step of matching a plurality of preset question information from a preset knowledge base using the keyword group comprises:
determining preset problem information containing all keywords from the preset knowledge base;
and when the determined number of the preset problem information is smaller than the threshold value, one keyword is removed, and the remaining keywords are used for re-determining the preset problem information until the determined number of the preset problem information is larger than or equal to the threshold value.
5. The answer information feedback method of claim 4, wherein before the step of removing one of the keywords and re-determining the preset question information using the remaining keywords when the determined number of the preset question information is less than the threshold value, the method further comprises:
performing part-of-speech scoring on each keyword in the keyword group corresponding to the question information;
the step of removing one keyword when the number of the determined preset problem information is smaller than a threshold value and re-determining the preset problem information by using the remaining keywords comprises the following steps:
and when the number of the determined preset problem information is smaller than a threshold value, eliminating the keyword with the lowest score after the part of speech is scored, and re-determining the preset problem information by using the remaining keywords.
6. The answer information feedback method of claim 1, wherein the step of determining the target preset question information according to the comparison of the parts of speech scores of the keywords in the preset question information comprises:
adding the parts of speech scores of all keywords in each piece of preset question information to obtain a total part of speech score;
and selecting preset problem information with the highest part-of-speech total score as target preset problem information.
7. The answer information feedback method of claim 1, wherein the step of performing part-of-speech scoring on the keywords in each piece of the preset question information comprises:
determining parts of speech of the keywords, wherein the parts of speech comprise nouns, verbs, adjectives, adverbs and prepositions;
and determining the part-of-speech score of the keyword according to the part-of-speech of the keyword.
8. An answer information feedback device, wherein the device is applied to a server in an intelligent question-answering system, the intelligent question-answering system further comprises at least one client, the server is in communication connection with the client, and the device comprises:
the data acquisition unit is used for acquiring the problem information sent by the client;
the data processing unit is used for preprocessing the question information to acquire a key phrase corresponding to the question information; wherein, the keyword group comprises at least one keyword;
the data processing unit is further configured to match a plurality of preset question information from a preset knowledge base by using the keyword group, wherein each preset question information corresponds to the keyword;
the data processing unit is also used for performing part-of-speech scoring on the keywords in each preset question message; acquiring the part-of-speech score of the keyword in each preset question message;
the data processing unit is also used for determining target preset problem information according to comparison of the parts of speech scores of the keywords in the preset problem information;
and the data sending unit is used for sending answer information corresponding to the target preset question information to the client.
9. The answer information feedback device of claim 8, wherein the data processing unit is configured to perform word segmentation processing on the question information to obtain at least one candidate keyword;
the data processing unit is further used for performing word stopping processing on the at least one candidate keyword to obtain a target keyword.
10. The answer information feedback device of claim 8, wherein the data processing unit is further configured to determine preset question information including all keywords from the preset knowledge base;
the data processing unit is further used for removing one keyword when the number of the determined preset problem information is smaller than a threshold value, and re-determining the preset problem information by using the remaining keywords until the number of the determined preset problem information is larger than or equal to the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218330.7A CN111061849A (en) | 2019-12-03 | 2019-12-03 | Answer information feedback method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911218330.7A CN111061849A (en) | 2019-12-03 | 2019-12-03 | Answer information feedback method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111061849A true CN111061849A (en) | 2020-04-24 |
Family
ID=70299543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911218330.7A Pending CN111061849A (en) | 2019-12-03 | 2019-12-03 | Answer information feedback method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111061849A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287088A (en) * | 2020-11-20 | 2021-01-29 | 四川长虹电器股份有限公司 | Intelligent man-machine interaction query method, system, computer equipment and storage medium |
| CN116304277A (en) * | 2023-03-01 | 2023-06-23 | 深圳一资源网络平台有限公司 | Intelligent matching method, system and storage medium based on AI |
-
2019
- 2019-12-03 CN CN201911218330.7A patent/CN111061849A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287088A (en) * | 2020-11-20 | 2021-01-29 | 四川长虹电器股份有限公司 | Intelligent man-machine interaction query method, system, computer equipment and storage medium |
| CN116304277A (en) * | 2023-03-01 | 2023-06-23 | 深圳一资源网络平台有限公司 | Intelligent matching method, system and storage medium based on AI |
| CN116304277B (en) * | 2023-03-01 | 2023-12-15 | 张素愿 | Intelligent matching method, system and storage medium based on AI |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5936698B2 (en) | Word semantic relation extraction device | |
| WO2020042925A1 (en) | Man-machine conversation method and apparatus, electronic device, and computer readable medium | |
| CN109299280B (en) | Short text clustering analysis method and device and terminal equipment | |
| US9785684B2 (en) | Determining temporal categories for a domain of content for natural language processing | |
| WO2020140373A1 (en) | Intention recognition method, recognition device and computer-readable storage medium | |
| US20100138402A1 (en) | Method and system for improving utilization of human searchers | |
| US20150178390A1 (en) | Natural language search engine using lexical functions and meaning-text criteria | |
| US10586174B2 (en) | Methods and systems for finding and ranking entities in a domain specific system | |
| CN107357777B (en) | Method and device for extracting label information | |
| Rani et al. | Automatic construction of generic stop words list for hindi text | |
| CN112100396A (en) | Data processing method and device | |
| Lommatzsch et al. | An Information Retrieval-based Approach for Building Intuitive Chatbots for Large Knowledge Bases. | |
| CN111061849A (en) | Answer information feedback method and device | |
| CN110348003A (en) | The abstracting method and device of text effective information | |
| CN111737420A (en) | Class case retrieval method, system, device and medium based on dispute focus | |
| WO2019005360A1 (en) | Categorizing electronic content | |
| CN113157887A (en) | Knowledge question-answering intention identification method and device and computer equipment | |
| Tohidi et al. | Optimizing the performance of Persian multi-objective question answering system | |
| CN111737607A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
| CN111476026A (en) | Statement vector determination method and device, electronic equipment and storage medium | |
| CN111914533A (en) | Method and system for analyzing English long sentence | |
| Wijaya et al. | Knowledge based chatbot with context recognition | |
| Kaur et al. | Effective question answering techniques and their evaluation metrics | |
| WO2010060117A1 (en) | Method and system for improving utilization of human searchers | |
| Čeh et al. | Developing a question answering system for the Slovene language |
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 |