CN112163083A - Intelligent question and answer method and device, electronic equipment and storage medium - Google Patents
Intelligent question and answer method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112163083A CN112163083A CN202011121798.7A CN202011121798A CN112163083A CN 112163083 A CN112163083 A CN 112163083A CN 202011121798 A CN202011121798 A CN 202011121798A CN 112163083 A CN112163083 A CN 112163083A
- Authority
- CN
- China
- Prior art keywords
- vector
- question
- similarity
- information
- elements
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003058 natural language processing Methods 0.000 claims abstract description 18
- 238000012986 modification Methods 0.000 claims description 20
- 230000004048 modification Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000003607 modifier Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000392928 Parachromis friedrichsthalii Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an intelligent question answering method, an intelligent question answering device, electronic equipment and a storage medium, which belong to the technical field of information, and the method comprises the following steps: firstly, receiving problem information sent by a consumer through a client, and generating a first problem vector corresponding to the problem information through natural language processing; then, carrying out similarity judgment on the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judgment result; if the similarity judgment result is that the similarity of the first question vector and the second question vector is larger than a preset threshold value, returning example answers of the first similar question set; and finally, receiving a selection instruction of the shopping guide at the display terminal, and sending a final answer determined based on the example answer and the selection instruction to the client. According to the embodiment, the consumer is replied by intelligently returning the example answers and combining with manual intervention of shopping guide, so that the communication cost between the consumer and the shopping guide customer service can be saved, and the question of the consumer can be answered quickly and accurately.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to an intelligent question answering method, an intelligent question answering device, electronic equipment and a storage medium.
Background
With the development of the internet, big data, rapid application of new retail and a value idea taking customer requirements as a core, the method has a dominant position. The demands of consumers continuously present the characteristics of individuation and diversification, so that the user image analysis and further the accurate marketing become important measures for sales upgrading of various merchants. Particularly, in a household appliance sale scene, when various large merchants communicate with customers on line, either a real person customer service reply mode or a robot reply mode is adopted. When the real person customer service is adopted for replying, the real person customer service needs to answer a large number of repeated questions, and a large amount of time is wasted; the robot replies, which has the problem that the loss of the client is easily caused because the reply answer is not accurate.
Disclosure of Invention
In order to overcome the problems in the related technology at least to a certain extent, the application provides the intelligent question-answering method, the intelligent question-answering device, the electronic equipment and the storage medium, so that when the shopping guide customer service and the consumer chat online, the communication cost between the consumer and the shopping guide customer service is saved, and the question of the consumer is answered quickly and accurately, so that the purchasing desire of the consumer is guided effectively.
In order to achieve the purpose, the following technical scheme is adopted in the application:
in a first aspect, the present application provides an intelligent question answering method, including: receiving problem information sent by a client, and generating a first problem vector corresponding to the problem information through natural language processing; carrying out similarity judgment on the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judgment result; if the similarity judgment result indicates that the similarity of the first question vector and the second question vector is greater than a preset threshold, returning example answers of a first similar question set; wherein the first similar question set is a similar question set to which the example question belongs; and receiving a selection instruction of the shopping guide at the display terminal, and sending a final answer determined based on the example answer and the selection instruction to the client.
Further, the step of generating a first question vector corresponding to the question information through natural language processing includes: extracting a character string of the question information through natural language processing; extracting entity information and entity modification information by performing Chinese word segmentation on the character string; and generating the first problem vector by taking the entity information and the entity modification information as elements.
Further, the step of performing similarity judgment on the first question vector and a second question vector corresponding to the example question to obtain a similarity judgment result includes: determining elements of the second problem vector; generating a similarity vector between the first problem vector and the second problem vector based on elements of the second problem vector; and calculating the length of the similarity vector, and determining the comparison result of the length of the similarity vector and a preset threshold value as a similarity judgment result.
Further, the generating of the similarity vector between the first question vector and the second question vector based on the elements of the second question vector includes: comparing the entity information with the reference entity information to obtain a first similarity value; comparing the entity modification information with the entity reference modification information to obtain a second similarity value; and generating a similarity vector between the first question vector and the second question vector by taking the first similarity value and the second similarity value as elements.
Further, the method further comprises: respectively counting the number of elements of the first problem vector and the number of elements of the second problem vector; calculating a ratio of the number of elements of the first problem vector to the number of elements of the second problem vector; and if the ratio is larger than the preset ratio, recalculating the ratio based on a preset calculation formula.
Further, the method further comprises: if the similarity judgment result indicates that the similarity of the first problem vector and the second problem vector is not greater than a preset threshold, prompting the shopping guide to carry out external input at a display terminal; and receiving a final answer input by the shopping guide at the display terminal.
Further, the method further comprises: when the similarity judgment result shows that the similarity of the first question vector and the second question vector is not larger than a preset threshold value, a second similar question set is newly established; example answers corresponding to the second set of similar questions are received and issued.
In a second aspect, the present application provides an intelligent question answering device, comprising: the system comprises a receiving and generating unit, a processing unit and a processing unit, wherein the receiving and generating unit is used for receiving question information sent by a client and generating a first question vector corresponding to the question information through natural language processing; the similarity judging unit is used for judging the similarity of the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judging result; a returning unit, configured to return an example answer of a first similar question set if the similarity determination result indicates that the similarity between the first question vector and the second question vector is greater than a preset threshold; wherein the first similar question set is a similar question set to which the example question belongs; and the receiving and sending unit is used for receiving a selection instruction of the shopping guide on the display terminal and sending a final answer determined based on the example answer and the selection instruction to the client.
In a third aspect, the present application provides an electronic device, comprising: a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the first aspects.
In a fourth aspect, the present application provides a storage medium having stored thereon a computer program for performing the steps of the method of any of the first aspect described above when the computer program is executed by a processor.
According to the intelligent question-answering method, the intelligent question-answering device, the electronic equipment and the storage medium, the question information sent by a consumer through a client is received, and a first question vector corresponding to the question information is generated through natural language processing; then, carrying out similarity judgment on the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judgment result; if the similarity judgment result is that the similarity of the first question vector and the second question vector is larger than a preset threshold value, returning example answers of the first similar question set; wherein, the first similar question set is a similar question set to which the example question belongs; and finally, receiving a selection instruction of the shopping guide at the display terminal, and sending a final answer determined based on the example answer and the selection instruction to the client. When the shopping guide customer service and the consumer chat online, the consumer is replied by intelligently returning example answers and combining with manual intervention of shopping guide, so that the communication cost between the consumer and the shopping guide customer service can be saved, the question of the consumer can be answered quickly and accurately, and the purchasing desire of the consumer can be guided effectively.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow diagram illustrating a method for intelligent question answering in accordance with an exemplary embodiment;
FIG. 2 is a flow diagram illustrating another intelligent question and answer method in accordance with an exemplary embodiment;
FIG. 3 is a flow diagram illustrating yet another intelligent question and answer method in accordance with an exemplary embodiment;
fig. 4 is a block diagram illustrating the structure of an intelligent question answering apparatus according to an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail below. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without making any creative effort, shall fall within the protection scope of the present application.
With the development of the internet, big data, rapid application of new retail and a value idea taking customer requirements as a core, the method has a dominant position. The demands of consumers continuously present the characteristics of individuation and diversification, so that the user image analysis and further the accurate marketing become important measures for sales upgrading of various merchants. In addition, based on the development of NLP (Natural Language Processing) and machine learning technology, the application of intelligent question and answer technology has been put into use in the customer service field, and emotion tendency analysis can be performed primarily according to semantics. And enterprise WeChat provides perfect plug-in development capability, and enterprises can develop plug-ins according to self requirements. Because the intelligent question-answering technology is usually used for corpus training in a certain specific field, the final training result can be used for solving the problem in the field. Therefore, the present embodiment solves some problems in online consumption chat scenes in the white electricity field by using an intelligent question and answer technology, and the specific technical problems are as follows: (1) the time is wasted because a large number of repetitive questions need to be answered when the traditional shopping guide is communicated with the consumer; (2) when a consumer communicates with the shopping guide robot, the problem that the consumer runs off is easily caused because the shopping guide robot answers the problem of the consumer inaccurately. Based on this, the application provides an intelligent question-answering method, an intelligent question-answering device, electronic equipment and a storage medium, which can save the communication cost between a consumer and a shopping guide customer service through a mode that the shopping guide customer service and the consumer are answered by intelligently returning example answers and combining with shopping guide manual intervention when the shopping guide customer service and the consumer are online chatted, answer the question of the consumer quickly and accurately, and further effectively guide the purchasing desire of the consumer. For ease of understanding, the present application is described in detail below.
Referring first to a flowchart of an intelligent question answering method shown in fig. 1, the method mainly includes the following steps S102 to S108:
step S102, receiving the question information sent by the client, and generating a first question vector corresponding to the question information through natural language processing. The natural language is convenient to process, and the first problem vector can be obtained quickly.
And step S104, carrying out similarity judgment on the first question vector and a second question vector corresponding to the example question to obtain a similarity judgment result. The example questions are contained in a similar set of questions to which the example questions belong, and all of the similar set of questions are in a full-scale library of questions. Example questions in different similar question sets are dissimilar, while any two similar questions in the same similar question bank are similar.
Step S106, if the similarity determination result indicates that the similarity between the first question vector and the second question vector is greater than the preset threshold, returning an example answer of the first similar question set. Wherein the first similar question set is a similar question set to which the example question belongs. In this embodiment, when the answer is greater than the preset threshold, all the example answers of the first similar question set may be selected as the final answers to be determined.
And step S108, receiving a selection instruction of the shopping guide at the display terminal, and sending a final answer determined based on the example answer and the selection instruction to the client.
Since the number of the provided example answers of the first similar question set is large, the final answer needs to be determined, so that a selection instruction of shopping guide at the display terminal can be received for manual intervention, and the final answer has higher accuracy.
According to the intelligent question-answering method, the consumer can be replied by intelligently returning example answers and combining shopping guide manual intervention, the communication cost between the consumer and the shopping guide customer service can be saved, the question of the consumer can be answered quickly and accurately, and the purchasing desire of the consumer can be guided effectively.
In one embodiment, the step of generating a first question vector corresponding to the question information by natural language processing in step S102 includes:
step S201, extracting a character string of question information through natural language processing;
step S202, extracting entity information and entity modification information by performing Chinese word segmentation on the character string;
step S203 generates a first problem vector using the entity information and the entity modification information as elements.
In the embodiment of the present invention, a problem text (i.e., the problem information) of a consumer may be preprocessed by using a ready-made chinese word library based on a string matching method to extract a problem entity (i.e., the entity information) and a problem entity modifier (i.e., the entity modification information), where the problem entity mainly refers to a noun (i.e., a product name), and the problem entity modifier refers to one or more of an adjective, an adverb, a verb, and a preposition other than the noun. The first problem vector generated is Q ═ t, v1,v2...vn) Where t represents a problem entity, v1,v2...vnAll represent problem entity modifiers; finally, the similarity vector A (p) is formedt,p1...pnP), calculating the length value of the similarity vector a, and comparing the length value with a preset threshold, wherein the threshold can be set by referring to different service conditions.
In one embodiment, the step S104 of performing similarity determination on the first question vector and the second question vector corresponding to the example question to obtain a similarity determination result includes:
step S301, determining elements of a second problem vector;
step S302, generating a similarity vector between the first question vector and the second question vector based on elements of the second question vector;
step S303, calculating the length of the similarity vector, and determining the comparison result between the length of the similarity vector and a preset threshold as the similarity determination result.
In one embodiment, the elements of the second question vector include reference entity information and entity reference modification information, and the step S302 of generating a similarity vector between the first question vector and the second question vector based on the elements of the second question vector includes:
step S401, comparing the entity information with reference entity information to obtain a first similarity value;
step S402, comparing the entity modification information with the entity reference modification information to obtain a second similarity value;
step S403 generates a similarity vector between the first question vector and the second question vector using the first similarity value and the second similarity value as elements.
In an embodiment of the invention, the first question vector is associated with a second question vector W of an example question in a full-scale question banknAnd (4) carrying out comparison calculation, wherein the similarity judgment rule is as follows: firstly, the problem entities are compared, if the problem entities are the same, the comparison result p is obtainedt1, in contrast to pt0; then, the problem entity modifiers are compared, and v is searched from Q in a character string matching mode1,v2...vnIf the problem entity modifier v is foundiExemplary, alignment result pvi1, otherwise pvi＝0。
The question information is Q: is this yellow jacket discounted for october? Second problem vector W corresponding to example problem1: how can the coat be discounted? Another example problem corresponds to a second problem vector W2: how can the holiday of the outer slipover? The first problem vector is: v. ofQNot in yellow ═ this pieceCover, october, discount }, i.e., the problem entity is yellow cover, vW1V ═ jacket, discount }, vW2Number (v) of jacket, holiday, discount }, numberW1)＝2，pt1＝0，Pw1＝(2-2)/2＝0，number(vW2)＝3，pt2＝0，Pw2＝(4/3-1)/1＝0.3，AW1＝{0，0,，0，1}，|AW1|＝1；AW2＝{0，0,，0，1}，|AW2|＝1。
In one embodiment, the method further comprises:
step S501, respectively counting the element number of the first problem vector and the element number of the second problem vector;
step S502, calculating the ratio of the number of elements of the first problem vector to the number of elements of the second problem vector;
in step S503, if the ratio is greater than the preset ratio, the ratio is recalculated based on the preset calculation formula.
In the present embodiment, P ═ number (v) is calculatedQ)/number(vW) If P is>1, then P ═ P- [ P ═ P])/[P]Wherein]Indicating rounding.
In one embodiment, as shown in fig. 2, the method further comprises:
step S107, if the similarity judgment result shows that the similarity of the first problem vector and the second problem vector is not greater than a preset threshold value, prompting the shopping guide to carry out external input on a display terminal;
and step S109, receiving the final answer input by the shopping guide at the display terminal.
In one embodiment, as shown in fig. 2, the method further comprises:
step S110, when the similarity judgment result shows that the similarity of the first question vector and the second question vector is not larger than a preset threshold value, a second similar question set is newly established;
in step S112, an example answer corresponding to the second similar question set is received and issued.
Illustratively, as shown in fig. 3, the present embodiment can also be described in the following steps:
step S11, Chinese word segmentation and key entity extraction; step S12, semantic analysis is carried out, and semantic similarity expression calculation is carried out on the questions in the full-scale question bank; in step S13, it is determined whether the similarity is greater than a set threshold. If the finally calculated vector length of A is larger than the set similarity threshold, judging that the problem exists in a full quantity problem set, and bringing the problem into a same-quality problem set; step S14, the question is included in the same nature question set. Because the example answers of the same-nature question set are edited in advance, the answers of the same-nature question set can be directly returned to the shopping guide, and the shopping guide carries out a reference step; s15, returning example answers of the question set; and if the shopping guide finds that the example answer of the question is consistent with the current consumer, directly selecting the answer to send. In step S16, the shopping guide selection answers directly answer the consumer. S13, if the vector length of A obtained by final calculation is smaller than the set similarity threshold, judging that the problem is a new problem, and establishing a new homogeneity problem set, and S17, establishing a new homogeneity problem set; step S18, prompting the shopping guide, typing and answering the consumer question; step S19, organizing the professional monthly to write the answers of the new isotropic question set examples. That is, the user is prompted to purchase the question without any answer to the relevant example, and the purchase guide needs to type on his/her own to communicate with the consumer.
According to the embodiment, repeated questions of the consumer can be accumulated in a household appliance sales scene by utilizing an NLP (non line of sight) correlation technology and adopting a chat function plug-in of enterprise WeChat, the repeated questions are edited in advance, and the consumer can quickly, accurately and effectively answer the repeated questions when asking the questions again.
Corresponding to the foregoing intelligent question-answering method, the present application further provides an intelligent question-answering device, see a structural block diagram of the intelligent question-answering device shown in fig. 4, which mainly includes the following modules:
a receiving and generating unit 402, configured to receive the question information sent by the client, and generate a first question vector corresponding to the question information through natural language processing;
a similarity determination unit 404, configured to perform similarity determination on the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity determination result;
a returning unit 406, configured to return an example answer of the first similar question set if the similarity determination result indicates that the similarity between the first question vector and the second question vector is greater than a preset threshold; wherein, the first similar question set is a similar question set to which the example question belongs;
and a receiving and sending unit 408, configured to receive a selection instruction of the shopping guide at the display terminal, and send a final answer determined based on the example answer and the selection instruction to the client.
The intelligent question answering device provided by the embodiment can save the communication cost between the consumer and the shopping guide customer service through the mode of replying the consumer by intelligently returning example answers and combining with the manual intervention of shopping guide, quickly and accurately answer the question of the consumer, and further effectively guide the purchasing desire of the consumer.
In a specific embodiment, the receiving and generating unit 402 is further configured to: extracting a character string of the question information through natural language processing; extracting entity information and entity modification information by performing Chinese word segmentation on the character string; and generating a first problem vector by taking the entity information and the entity modification information as elements.
In a specific embodiment, the similarity determination unit 404 is further configured to: determining elements of a second problem vector; generating a similarity vector between the first problem vector and the second problem vector based on elements of the second problem vector; and calculating the length of the similarity vector, and determining the comparison result of the length of the similarity vector and a preset threshold value as a similarity judgment result.
In a specific embodiment, the elements of the second problem vector include reference entity information and entity reference modification information, and the similarity determination unit 404 is further configured to: comparing the entity information with reference entity information to obtain a first similarity value; comparing the entity modification information with the entity reference modification information to obtain a second similarity value; and generating a similarity vector between the first question vector and the second question vector by taking the first similarity value and the second similarity value as elements.
In a specific embodiment, the apparatus further includes a statistics unit, a first calculation unit, and a second calculation unit, wherein:
a counting unit, configured to count the number of elements of the first problem vector and the number of elements of the second problem vector, respectively;
a first calculation unit for calculating a ratio of the number of elements of the first problem vector to the number of elements of the second problem vector,
and the second calculating unit is used for recalculating the ratio based on a preset calculating formula if the ratio is greater than the preset ratio.
In a specific embodiment, the apparatus further includes a prompting unit and a receiving unit, wherein:
the prompting unit is used for prompting the shopping guide to carry out external input on the display terminal if the similarity judgment result shows that the similarity of the first question vector and the second question vector is not greater than a preset threshold value;
and the receiving unit is used for receiving the final answer input by the shopping guide at the display terminal.
In a specific embodiment, the apparatus further comprises:
the new establishing unit is used for establishing a second similar problem set when the similarity judgment result shows that the similarity of the first problem vector and the second problem vector is not larger than a preset threshold value;
and the receiving and issuing unit is used for receiving and issuing example answers corresponding to the second similar question set.
Further, the present embodiment also provides an electronic device, including: a processor and a storage device; the storage device stores a computer program, and the computer program executes the intelligent question answering method when being executed by the processor.
Further, the present embodiment also provides a storage medium, where a computer program is stored on the storage medium, and the computer program is executed by the processor to execute the above intelligent question-answering method.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, the meaning of "plurality" means at least two unless otherwise specified.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or intervening elements may also be present; when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present, and further, as used herein, connected may include wirelessly connected; the term "and/or" is used to include any and all combinations of one or more of the associated listed items.
Any process or method descriptions in flow charts or otherwise described herein may be understood as: represents modules, segments or portions of code which include one or more executable instructions for implementing specific logical functions or steps of a process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. An intelligent question answering method is characterized by comprising the following steps:
receiving problem information sent by a client, and generating a first problem vector corresponding to the problem information through natural language processing;
carrying out similarity judgment on the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judgment result;
if the similarity judgment result indicates that the similarity of the first question vector and the second question vector is greater than a preset threshold, returning example answers of a first similar question set; wherein the first similar question set is a similar question set to which the example question belongs;
and receiving a selection instruction of the shopping guide at the display terminal, and sending a final answer determined based on the example answer and the selection instruction to the client.
2. The method of claim 1, wherein the step of generating a first question vector corresponding to question information through natural language processing comprises:
extracting a character string of the question information through natural language processing;
extracting entity information and entity modification information by performing Chinese word segmentation on the character string;
and generating the first problem vector by taking the entity information and the entity modification information as elements.
3. The method according to claim 2, wherein the step of performing similarity determination on the first question vector and a second question vector corresponding to the example question to obtain a similarity determination result comprises:
determining elements of the second problem vector;
generating a similarity vector between the first problem vector and the second problem vector based on elements of the second problem vector;
and calculating the length of the similarity vector, and determining the comparison result of the length of the similarity vector and a preset threshold value as a similarity judgment result.
4. The method of claim 3, wherein the elements of the second problem vector include reference entity information and entity reference modifier information, and wherein the step of generating the similarity vector between the first problem vector and the second problem vector based on the elements of the second problem vector comprises:
comparing the entity information with the reference entity information to obtain a first similarity value;
comparing the entity modification information with the entity reference modification information to obtain a second similarity value;
and generating a similarity vector between the first question vector and the second question vector by taking the first similarity value and the second similarity value as elements.
5. The method of claim 3, further comprising:
respectively counting the number of elements of the first problem vector and the number of elements of the second problem vector;
calculating a ratio of the number of elements of the first problem vector to the number of elements of the second problem vector;
and if the ratio is larger than the preset ratio, recalculating the ratio based on a preset calculation formula.
6. The method of claim 1, further comprising:
if the similarity judgment result indicates that the similarity of the first problem vector and the second problem vector is not greater than a preset threshold, prompting the shopping guide to carry out external input at a display terminal;
and receiving a final answer input by the shopping guide at the display terminal.
7. The method of claim 6, further comprising:
when the similarity judgment result shows that the similarity of the first question vector and the second question vector is not larger than a preset threshold value, a second similar question set is newly established;
example answers corresponding to the second set of similar questions are received and issued.
8. An intelligent question answering device, comprising:
the system comprises a receiving and generating unit, a processing unit and a processing unit, wherein the receiving and generating unit is used for receiving question information sent by a client and generating a first question vector corresponding to the question information through natural language processing;
the similarity judging unit is used for judging the similarity of the first problem vector and a second problem vector corresponding to the example problem to obtain a similarity judging result;
a returning unit, configured to return an example answer of a first similar question set if the similarity determination result indicates that the similarity between the first question vector and the second question vector is greater than a preset threshold; wherein the first similar question set is a similar question set to which the example question belongs;
and the receiving and sending unit is used for receiving a selection instruction of the shopping guide on the display terminal and sending a final answer determined based on the example answer and the selection instruction to the client.
9. An electronic device, comprising: a processor and a storage device;
the storage device has stored thereon a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A storage medium having a computer program stored thereon, wherein the computer program is adapted to perform the steps of the method according to any of the claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011121798.7A CN112163083B (en) | 2020-10-20 | 2020-10-20 | Intelligent question-answering method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011121798.7A CN112163083B (en) | 2020-10-20 | 2020-10-20 | Intelligent question-answering method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112163083A true CN112163083A (en) | 2021-01-01 |
| CN112163083B CN112163083B (en) | 2023-11-03 |
Family
ID=73867506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011121798.7A Active CN112163083B (en) | 2020-10-20 | 2020-10-20 | Intelligent question-answering method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163083B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115334362A (en) * | 2022-07-16 | 2022-11-11 | 珠海格力电器股份有限公司 | Bullet screen problem processing method and device, storage medium, service equipment and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049433A (en) * | 2012-12-11 | 2013-04-17 | 微梦创科网络科技（中国）有限公司 | Automatic question answering method, automatic question answering system and method for constructing question answering case base |
| US20170351677A1 (en) * | 2016-06-03 | 2017-12-07 | International Business Machines Corporation | Generating Answer Variants Based on Tables of a Corpus |
| CN109740077A (en) * | 2018-12-29 | 2019-05-10 | 北京百度网讯科技有限公司 | Answer searching method, device and its relevant device based on semantic indexing |
| CN110263144A (en) * | 2019-06-27 | 2019-09-20 | 深圳前海微众银行股份有限公司 | A kind of answer acquisition methods and device |
| CN110674272A (en) * | 2019-09-05 | 2020-01-10 | 科大讯飞股份有限公司 | Question answer determining method and related device |
| CN111221954A (en) * | 2020-01-09 | 2020-06-02 | 珠海格力电器股份有限公司 | Method, device, storage medium and terminal for constructing household appliance maintenance question-answer library |
| CN111639502A (en) * | 2020-05-26 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Text semantic matching method and device, computer equipment and storage medium |
| US20200311145A1 (en) * | 2019-03-28 | 2020-10-01 | Beijing Jingdong Shangke Information Technology Co., Ltd. | System and method for generating an answer based on clustering and sentence similarity |
-
2020
- 2020-10-20 CN CN202011121798.7A patent/CN112163083B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049433A (en) * | 2012-12-11 | 2013-04-17 | 微梦创科网络科技（中国）有限公司 | Automatic question answering method, automatic question answering system and method for constructing question answering case base |
| US20170351677A1 (en) * | 2016-06-03 | 2017-12-07 | International Business Machines Corporation | Generating Answer Variants Based on Tables of a Corpus |
| CN109740077A (en) * | 2018-12-29 | 2019-05-10 | 北京百度网讯科技有限公司 | Answer searching method, device and its relevant device based on semantic indexing |
| US20200311145A1 (en) * | 2019-03-28 | 2020-10-01 | Beijing Jingdong Shangke Information Technology Co., Ltd. | System and method for generating an answer based on clustering and sentence similarity |
| CN110263144A (en) * | 2019-06-27 | 2019-09-20 | 深圳前海微众银行股份有限公司 | A kind of answer acquisition methods and device |
| CN110674272A (en) * | 2019-09-05 | 2020-01-10 | 科大讯飞股份有限公司 | Question answer determining method and related device |
| CN111221954A (en) * | 2020-01-09 | 2020-06-02 | 珠海格力电器股份有限公司 | Method, device, storage medium and terminal for constructing household appliance maintenance question-answer library |
| CN111639502A (en) * | 2020-05-26 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Text semantic matching method and device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115334362A (en) * | 2022-07-16 | 2022-11-11 | 珠海格力电器股份有限公司 | Bullet screen problem processing method and device, storage medium, service equipment and system |
| CN115334362B (en) * | 2022-07-16 | 2023-09-26 | 珠海格力电器股份有限公司 | Barrage problem processing method, barrage problem processing device, barrage problem storage medium, barrage problem service equipment and barrage problem service system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112163083B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fang et al. | Factors affecting consumer stickiness to continue using mobile applications | |
| CN103377262B (en) | The method and apparatus being grouped to user | |
| US20180053234A1 (en) | Description information generation and presentation systems, methods, and devices | |
| US20210311751A1 (en) | Machine-learning models applied to interaction data for determining interaction goals and facilitating experience-based modifications to interface elements in online environments | |
| CN109493113A (en) | A kind of providing method and device of favor information | |
| Zanubiya et al. | Increasing Consumers with Satisfaction Application based Digital Marketing Strategies | |
| CN109087162A (en) | Data processing method, system, medium and calculating equipment | |
| CN110910179B (en) | Grouping marketing method and device | |
| CN109003113A (en) | Evaluate the method and device of data processing and displaying, electronic equipment and storage equipment | |
| CN110782259A (en) | Member level management method and device | |
| CN116894711A (en) | Commodity recommendation reason generation method and device and electronic equipment | |
| CN109711917A (en) | Information-pushing method and device | |
| KR20220050078A (en) | Method, Apparatus and System for Generating Online Shopping Mall | |
| CN114862516A (en) | Document recommendation method, storage medium, and program product | |
| WO2001084394A1 (en) | Interactive control system | |
| CN110399473B (en) | Method and device for determining answers to user questions | |
| CN112115710B (en) | Industry information identification method and device | |
| CN112163083A (en) | Intelligent question and answer method and device, electronic equipment and storage medium | |
| CN111309882B (en) | Method and device for realizing intelligent customer service question and answer | |
| CN110555747A (en) | method and device for determining target user | |
| CN108510302A (en) | A kind of marketing decision-making method and trading server | |
| CN116484880A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110781399A (en) | Cross-platform information pushing method and device | |
| CN112015970A (en) | Product recommendation method, related equipment and computer storage medium | |
| CN110738521B (en) | Client selling method and device for multi-merchant brand |
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 |