CN112598427A - After-sale service method and device, electronic equipment and storage medium - Google Patents
After-sale service method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112598427A CN112598427A CN202011471132.4A CN202011471132A CN112598427A CN 112598427 A CN112598427 A CN 112598427A CN 202011471132 A CN202011471132 A CN 202011471132A CN 112598427 A CN112598427 A CN 112598427A
- Authority
- CN
- China
- Prior art keywords
- evaluation information
- determining
- event
- emotion
- evaluation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000011156 evaluation Methods 0.000 claims abstract description 208
- 230000008451 emotion Effects 0.000 claims description 129
- 238000003062 neural network model Methods 0.000 claims description 26
- 230000002996 emotional effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005406 washing Methods 0.000 description 20
- 230000014509 gene expression Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 239000007788 liquid Substances 0.000 description 5
- 230000001364 causal effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- 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
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Abstract
The application provides an after-sale service method, an after-sale service device, an electronic device and a storage medium, wherein the after-sale service method comprises the following steps: acquiring evaluation information of the commodity; determining a first meta-event of the evaluation information in case that the evaluation information is determined to be a negative evaluation; determining a target reason for making the evaluation information on the commodity based on the first meta-event and a pre-stored event map, wherein the event map comprises the reason for the first meta-event; and outputting the target reason to enable the user to perform after-sales service based on the target reason.
Description
Technical Field
The present application relates to the field of electronic commerce technologies, and in particular, to an after-sales service method, an apparatus, an electronic device, and a storage medium.
Background
With the gradual pace of the e-commerce into the lives of people, online shopping has become a common mode of shopping, after people have finished online shopping, the goods are usually evaluated, and merchants can return visits to buyers who have negative evaluations on the goods after sale. However, the traditional sentiment analysis only can respectively show more obvious commodity comments, and the sentiment bias of the inverse mock, the inverse question and the metaphoric sentence is difficult to be analyzed. Negative comments on this part cannot be identified, resulting in missing data. In addition, after the evaluation of the seller is extracted, the relation between the evaluation and the entity is displayed in a knowledge graph mode so as to facilitate customer service, but the relation in the knowledge graph is relatively definite and static knowledge, and many comments are logical, for example, when the washing machine works, the sound is a little bit, when the knowledge graph is extracted, only the sound can be provided, when the washing machine works, the sound is big, but the sound of the washing machine works is big, the washing machine usually is caused by unbalance of balance liquid in the rolling process of the washing bucket, the information of the part cannot be seen in the knowledge graph, so that the customer service cannot understand the expression of the user, and the after-sale service efficiency is low.
Disclosure of Invention
In view of the foregoing problems, the present application provides an after-market service method, an apparatus, an electronic device, and a storage medium.
The application provides an after-sales service method, which comprises the following steps:
acquiring evaluation information of the commodity;
determining a first meta-event of the evaluation information in case that the evaluation information is determined to be a negative evaluation;
determining a target reason for making the evaluation information on the commodity based on the first meta-event and a pre-stored event map, wherein the event map comprises the reason for the first meta-event;
and outputting the target reason to enable the user to perform after-sales service based on the target reason.
In some embodiments, the method further comprises:
inputting the evaluation information into a first emotion analysis model, and determining a first probability that the evaluation information is negative evaluation, wherein the first emotion analysis model can identify the probability that the evaluation information with the explicit emotion is negative evaluation;
and determining whether the evaluation information is negative evaluation or not based on the first probability and a first preset probability threshold.
In some embodiments, the method further comprises:
determining that the evaluation information is suspected negative evaluation information under the condition that the evaluation information is determined not to be negative evaluation;
inputting the suspected negative evaluation information into a second emotion analysis model, and determining a second probability that the suspected negative evaluation is negative evaluation, wherein the second emotion analysis model can identify the probability that evaluation information with implicit emotion is negative evaluation;
and determining whether the suspected evaluation information is negative evaluation or not based on the second probability and a second preset probability threshold.
In some embodiments, the method further comprises:
acquiring a sample corpus, wherein the sample corpus is marked with implicit emotion words and context display emotion classification of the sample corpus;
determining the implicit emotional words, the context display emotion classification and a text vector of the sample corpus based on semantic relations based on the sample corpus;
determining a second emotion analysis model based on the implicit emotion words, the contextual display emotion classification, and the text vector;
and storing the second emotion analysis model.
In some embodiments, the determining a second emotion analysis model based on the implicit emotion word, the contextual display emotion classification, and the text vector comprises:
determining a first neural network model based on the implicit emotional words;
determining a second neural network model based on the contextual display sentiment classification;
determining a third neural network model based on the text vector;
and combining the first neural network model, the second neural network model and the third neural network model to obtain a second emotion analysis model.
In some embodiments, the method further comprises:
determining a second element event based on the target reason and the event graph;
and outputting the second element event to enable the user to perform after-sales service based on the target reason and the second element event.
In some embodiments, the determining a target reason for making the evaluation information for the commodity based on the first meta-event information and a pre-stored case map includes:
determining a target word of a first original event;
matching the target words with words in a pre-stored affair map to determine a matching result;
and determining a target reason for making the evaluation information for the commodity based on the matching result.
An embodiment of the present application provides an after-sales service apparatus, including:
the first acquisition module is used for acquiring the evaluation information of the commodity;
the first determination module is used for determining a first meta-event of the evaluation information under the condition that the evaluation information is determined to be negative evaluation;
the second determination module is used for determining a target reason for making the evaluation information on the commodity based on the first meta-event and a pre-stored affair map, wherein the affair map comprises the reason of the first meta-event;
and the first output module is used for outputting the target reason so as to enable the user to carry out after-sale service based on the target reason.
An embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the electronic device executes any one of the methods for after-sales service described above.
An embodiment of the present application provides a storage medium, where computer-executable instructions are stored in the storage medium, and the computer-executable instructions are configured to perform any one of the after-sales service methods described above.
According to the method, the device, the electronic equipment and the storage medium for after-sales service, under the condition that the evaluation information is determined to be negative evaluation, a first meta-event of the evaluation information is determined; determining a target reason for making the evaluation information for the commodity based on the first meta-event and a pre-stored case map; and outputting the target reason, so that the customer service can intuitively know the reason causing the first meta-event, understand that the user makes a real expression of the evaluation, and further improve the after-sales service efficiency.
Drawings
The present application will be described in more detail below on the basis of embodiments and with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart illustrating an implementation of a method for after-sales service according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an implementation process for establishing a second emotion analysis model according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating an implementation of a method for after-sales service according to an embodiment of the present application;
FIG. 4 is a schematic flowchart of a process for establishing an implicit emotion analysis model according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a case map of a washing machine according to an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of an after-sales service apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
In the drawings, like parts are designated with like reference numerals, and the drawings are not drawn to scale.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
The following description will be added if a similar description of "first \ second \ third" appears in the application file, and in the following description, the terms "first \ second \ third" merely distinguish similar objects and do not represent a specific ordering for the objects, and it should be understood that "first \ second \ third" may be interchanged under certain circumstances in a specific order or sequence, so that the embodiments of the application described herein can be implemented in an order other than that shown or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
The embodiment of the application provides an after-sales service method, which is applied to electronic equipment. The electronic device may be a mobile terminal, a computer, or the like, and the functions implemented by the method for after-sales service provided in the embodiments of the present application may be implemented by a processor of the electronic device calling a program code, where the program code may be stored in a computer storage medium. An embodiment of the present application provides an after-sales service method, and fig. 1 is a schematic flow chart illustrating an implementation of the after-sales service method provided in the embodiment of the present application, as shown in fig. 1, including:
step S101 acquires evaluation information of the product.
In this embodiment, the product may be a washing machine, a television, an air conditioner, a mobile terminal, a computer, or the like, the evaluation information is an evaluation of the product after the user purchases the product, the evaluation information may be an evaluation including an emotion display, and exemplarily, the product is a washing machine, and the evaluation showing the emotion is: this washing machine is really good. The evaluation of the displayed emotion is that the user directly expresses the user's emotion. In some embodiments, the rating information may be a rating of implicit emotion in which the sentence itself does not contain explicit emotional words, but expresses subjective emotion. The evaluation of the implicit emotion is generally divided into a factual implicit emotion and a modified implicit emotion. Metaphors, question reversers, and inverse mock. Illustratively, the evaluation of the implicit emotion may be that the washing machine is just like a small helper for housework, that the washing machine is somewhat fool, where is the intelligence?
And step S102, under the condition that the evaluation information is determined to be negative evaluation, determining a first meta-event of the evaluation information.
In the embodiment of the application, before step S102, it is further required to determine whether the evaluation information is a positive evaluation or a negative evaluation, and a first probability that the evaluation information is a negative evaluation may be determined by a first emotion analysis model, where the first emotion analysis model can identify that the evaluation information with an explicit emotion is a probability of a negative evaluation; and determining whether the evaluation information is negative evaluation or not based on the first probability and a first preset probability threshold. In the embodiment of the application, when the first probability is greater than a first preset probability threshold, the evaluation information is determined to be negative evaluation, and when the first probability is less than the first preset probability threshold, the evaluation information is determined to be suspected negative evaluation information; inputting the suspected negative evaluation information into a second emotion analysis model, and determining a second probability that the suspected negative evaluation is negative evaluation, wherein the second emotion analysis model can identify the probability that evaluation information with implicit emotion is negative evaluation; and determining whether the suspected evaluation information is negative evaluation or not based on the second probability and a second preset probability threshold. In this embodiment of the application, when the second probability is greater than a second probability threshold, it is determined that the suspected negative evaluation information is a negative evaluation, and when the second probability is less than the second probability threshold, it is determined that the suspected negative evaluation information is not a negative evaluation.
In this embodiment of the present application, meta-event extraction may be performed on evaluation information to obtain a first meta-event of the evaluation information. For example, if the evaluation information indicates that the washing machine is sounding when operating, the first meta-event is: the washing machine has loud working sound.
Step S103, determining a target reason for making the evaluation information for the commodity based on the first meta-event and a pre-stored event map.
In the embodiment of the application, a matter graph is pre-stored, and the matter graph comprises the reason of the first meta-event. Determining a target word of a first original event when a target reason for making the evaluation information on the commodity is realized based on the first meta-event and a pre-stored affair map; matching the target words with words in a pre-stored affair map to determine a matching result; and determining a target reason for making the evaluation information for the commodity based on the matching result. In summary, the cause and effect events with loud washing machine sound can be determined through the event map, and the cause and effect events can be many, for example, the transmitter sound is loud due to unbalance of the balance liquid, or the sound is loud due to loosening of the screw, and in the embodiment of the present application, the target reasons may be: unbalance of balance liquid, loosening of screws and the like.
And step S104, outputting the target reason to enable the user to perform after-sales service based on the target reason.
In the embodiment of the application, after the target reason is determined, the target reason can be output, the customer service can perform after-sales service based on the target reason, the after-sales service can be that multiple users return visits to locate specific problems and then can feed back to an after-sales maintenance department to search corresponding maintenance personnel for home-on maintenance. In the embodiment of the application, after the target reason is output, the client can quickly understand the problems of the user and the mechanical faults, and the problem that the user experience is poor due to the fact that the customer service part is familiar with and is not smoothly communicated with the user is avoided.
According to the method for after-sales service, under the condition that the evaluation information is determined to be negative evaluation, a first meta-event of the evaluation information is determined; determining a target reason for making the evaluation information for the commodity based on the first meta-event and a pre-stored case map; and outputting the target reason, so that the customer service can intuitively know the reason causing the first meta-event, understand that the user makes a real expression of the evaluation, and further improve the after-sales service efficiency.
In some embodiments, before determining the first meta-event of the evaluation information in the case that the evaluation information is determined to be a negative evaluation in step S102, "the method further comprises:
step S1, inputting the evaluation information into a first emotion analysis model, and determining a first probability that the evaluation information is a negative evaluation, where the first emotion analysis model can recognize that the evaluation information with an explicit emotion is a probability of a negative evaluation.
In the embodiment of the application, the first emotion analysis model is trained in advance, and the first emotion analysis model is obtained by training through a neural network model. In the embodiment of the application, the sample marked with the probability of displaying the emotion and the evaluation type is input into the neural network model for training, so that the evaluation type of the evaluation information capable of identifying the emotion is obtained.
Step S2, determining whether the evaluation information is a negative evaluation based on the first probability and a first preset probability threshold.
The first probability may be compared with a first preset probability threshold, and for example, when the first probability is greater than the first threshold probability threshold, the evaluation information may be determined as a negative evaluation, and when the first probability is less than the first preset probability threshold, the evaluation information may be determined as a positive evaluation. In the examples of the present application, the negative evaluation was a poor evaluation, and the positive evaluation was a good evaluation.
In some embodiments, after the step S2 "determining whether the evaluation information is a negative evaluation based on the first probability and a first preset probability threshold", the method further includes:
step S3, when it is determined that the evaluation information is not a negative evaluation, determines that the evaluation information is suspected negative evaluation information.
In the embodiment of the application, the first emotion analysis model can identify the evaluation of the displayed emotion, but cannot identify the evaluation of the implicit emotion, so that when the first emotion analysis model determines that the evaluation is not a negative evaluation, the negative evaluation of the implicit emotion used by the user may be possible. Therefore, the evaluation information is determined here as the suspected negative evaluation information.
Step S4, inputting the suspected negative evaluation information into a second emotion analysis model, and determining a second probability that the suspected negative evaluation is a negative evaluation.
In the embodiment of the application, the second emotion analysis model can identify the probability that the evaluation information with the implicit emotion is negative evaluation. In the embodiment of the application, the implicit emotion does not contain explicit emotion words, but expresses subjective emotion. The implicit emotion sentences are usually divided into actual implicit emotions and modified implicit emotions. Metaphors, question reversers, and inverse mock.
In the embodiment of the application, the second emotion analysis model is pre-established and can be obtained by obtaining a sample corpus, wherein the sample corpus is marked with implicit emotion words and context display emotion classification of the sample corpus; determining the implicit emotional words, the context display emotion classification and a text vector of the sample corpus based on semantic relations based on the sample corpus; determining a second emotion analysis model based on the implicit emotion words, the contextual display emotion classification, and the text vector; thereby storing the second emotion analysis model.
Step S5, determining whether the suspected evaluation information is a negative evaluation based on the second probability and a second preset probability threshold.
In this embodiment of the application, when the second probability is greater than a second preset probability threshold, it is determined that the suspected negative evaluation information is a negative evaluation. When the second probability is less than the second threshold probability threshold, the suspected negative evaluation information is not a negative evaluation, and when not a negative evaluation, the evaluation information may be a neutral evaluation and a positive evaluation.
Before step S4 "inputting the suspected negative evaluation information into a second emotion analysis model and determining a second probability that the suspected negative evaluation is a negative evaluation", the method further includes establishing the second emotion analysis model, and fig. 2 is a schematic flow chart of an implementation of establishing the second emotion analysis model according to an embodiment of the present application, as shown in fig. 2, including:
and step S11, obtaining sample corpora.
In the embodiment of the application, the sample corpus is marked with implicit emotion words and the context of the sample corpus shows emotion classification.
Step S12, determining the implicit emotional words, the context display emotion classification and the text vector of the sample corpus based on the semantic relation based on the sample corpus;
step S13, determining a second emotion analysis model based on the implicit emotion words, the context display emotion classification and the text vector.
In the embodiment of the application, a first neural network model can be determined based on the implicit emotional words; determining a second neural network model based on the contextual display sentiment classification; determining a third neural network model based on the text vector; and combining the first neural network model, the second neural network model and the third neural network model to obtain a second emotion analysis model.
And step S14, storing the second emotion analysis model.
In some embodiments, after obtaining the target reason, the following steps may be further included:
and step S105, determining a second element event based on the target reason and the event map.
In the embodiment of the application, the second element event is different from the first element event, the second element event has a causal relationship with the target reason, and illustratively, the problem of the washing machine balancing liquid may have other expressions, and the other expressions are stored in a case map, so that the second element event is determined.
And S106, outputting the second element event to enable the user to perform after-sales service based on the target reason and the second element event.
In the embodiment of the application, the customer service can better perform after-sales service through the target reason and the second element event.
In some embodiments, the step S103 "determining the target reason for making the evaluation information on the commodity based on the first meta-event information and a pre-stored case map" may be implemented by:
step S1031, determining a target word of the first original event;
step S1032, matching the target words with words in a pre-stored affair map, and determining a matching result;
step S1033, based on the matching result, determines a target reason for making the evaluation information for the commodity.
In an embodiment of the present application, an after-sales service method is provided, and fig. 3 is a schematic flow chart illustrating an implementation of the after-sales service method provided in the embodiment of the present application, as shown in fig. 3, including:
in step S21, a comment on the product (the same evaluation information as in the above-described embodiment) is acquired.
And step S22, emotion analysis.
According to the embodiment of the application, emotion analysis is performed through the first emotion analysis model.
Step S23, determine whether the comment is a negative evaluation.
In the embodiment of the application, the first probability is obtained after emotion analysis, and whether the comment is a negative evaluation or not can be determined based on the first probability and a first preset probability threshold.
In the embodiment of the present application, when the review is a negative evaluation, step S24 is executed, and when the review is not a negative evaluation, step S25 is executed.
And step S24, storing the affair map.
In the embodiment of the application, the cause and effect relationship between the first meta-event and the reason is stored in the event map.
And step S25, implicit emotion analysis.
In the embodiment of the application, implicit emotion analysis is performed through the second emotion analysis model. In the implicit emotional sentence, the sentence does not contain explicit emotional words, but expresses subjective emotion. The implicit emotion sentences are usually divided into actual implicit emotions and modified implicit emotions. The term "semantic expression" is used to refer to a semantic expression that is a semantic expression of a semantic expression, a metaphor expression, a question return, and a reverse mock expression. The following are examples of explicit and implicit emotions:
step S26, determining whether the comment is a negative evaluation.
In the embodiment of the present application, when the comment is a negative evaluation, step S24 is executed. When the comment is not a negative evaluation, the flow ends.
And step S27, storing the affair map.
And step S28, extracting the causal events in the comments.
In step S29, the plurality of information streams are subjected to comment analysis.
In step S30, the comment analysis result (the same as the target reason in the above-described embodiment) is output.
And step S31, pushing the analysis result to make the customer service return visit after sale.
In this embodiment of the application, before step S25, the method further includes: an implicit emotion analysis model (the same as the second emotion analysis model in the above embodiment) is established, the establishment process may be implemented through the following steps, and fig. 4 is a schematic flowchart of a process for establishing an implicit emotion analysis model provided in the embodiment of the present application, and as shown in fig. 4, the process includes:
in step S41, the corpus labeled with emotional tendencies (the same as the sample corpus in the above embodiment) is obtained.
Step S42, determining the implicit emotion words, the context display emotion classification and the multilayer convolution neural network text vector based on the syntactic semantic relationship of the corpus.
And step S43, carrying out multi-dimensional combination.
In step S44, a model (the same as the second emotion analysis model in the above embodiment) is constructed.
In step S45, the model is output.
Thus, the implicit emotion analysis model is established, and the process of establishing the model is finished.
In the embodiment of the present application, in step S24, the method may be implemented by:
and step S51, extracting meta-events from the comments to obtain a plurality of original events. For example, the washing machine is loud when it is operating. Then, the event is extracted, namely the washing machine is high in work sound.
And step S52, matching based on a preset event map and meta-events, wherein the event map comprises events connected according to a causal relationship or an event time sequence relationship.
And step S53, obtaining the causal relationship of the meta-event through matching with the preset event map.
Fig. 5 is a schematic structural diagram of a case map of a washing machine according to an embodiment of the present application, and as shown in fig. 5, it is determined that the reason why the operation sound of the washing machine is loud is the engine problem or the balance liquid problem when the operation business of the washing machine is loud through the case map of fig. 5.
According to the after-sale service method provided by the embodiment of the application, the inverse mock, the inverse question and the metaphoric commodity evaluation which cannot be identified by the traditional emotion analysis are analyzed through the implicit emotion analysis, the commodity evaluations of more buyers are collected, and suggestions beneficial to the product progress optimization direction or commodity insufficiency are analyzed. The fact map is a logic society, and research objects are the predicate events and internal and external relations thereof. The comments of the users are sorted according to the logic, the user expression is understood in time, the real expression of the users is sorted for the customer service, and the after-sale service efficiency of the customer service is improved.
Based on the foregoing embodiments, the embodiments of the present application provide an after-sales service apparatus, where the apparatus includes modules and units included in the modules, and the modules and the units may be implemented by a processor in a computer device; of course, the implementation can also be realized through a specific logic circuit; in the implementation process, the processor may be a Central Processing Unit (CPU), a Microprocessor Unit (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.
An after-sales service apparatus according to an embodiment of the present application is provided, and fig. 6 is a schematic structural diagram of the after-sales service apparatus according to the embodiment of the present application, where the after-sales service apparatus 600 includes:
a first obtaining module 601, configured to obtain evaluation information of a commodity;
a first determining module 602, configured to determine a first meta-event of the evaluation information if it is determined that the evaluation information is a negative evaluation;
a second determining module 603, configured to determine a target reason for making the evaluation information for the commodity based on the first meta-event and a pre-stored case diagram, where the case diagram includes a reason for the first meta-event;
a first output module 604, configured to output the target reason, so that the user performs after-sales service based on the target reason.
In some embodiments, the after-market apparatus 600 further comprises:
the third determining module is used for inputting the evaluation information into a first emotion analysis model and determining a first probability that the evaluation information is negative evaluation, wherein the first emotion analysis model can identify that the evaluation information with the explicit emotion is the probability of negative evaluation;
and the fourth determining module is used for determining whether the evaluation information is negative evaluation or not based on the first probability and a first preset probability threshold.
In some embodiments, the after-market apparatus 600 further comprises:
a fifth determining module, configured to determine that the evaluation information is suspected negative evaluation information when it is determined that the evaluation information is not negative evaluation;
a sixth determining module, configured to input the suspected negative evaluation information into a second emotion analysis model, and determine a second probability that the suspected negative evaluation is a negative evaluation, where the second emotion analysis model is capable of identifying that evaluation information with an implicit emotion is a probability of a negative evaluation;
and determining whether the suspected negative evaluation information is a negative evaluation or not based on the second probability and a second preset probability threshold.
In some embodiments, the after-market apparatus 600 further comprises:
the second acquisition module is used for acquiring a sample corpus, wherein the sample corpus is marked with implicit emotion words and context display emotion classification of the sample corpus;
a seventh determining module, configured to determine, based on the sample corpus, the implicit emotion words, the context display emotion classification, and a text vector of the sample corpus based on a semantic relationship;
an eighth determining module, configured to determine a second emotion analysis model based on the implicit emotion words, the contextual display emotion classification, and the text vector;
and storing the second emotion analysis model.
In some embodiments, the seventh determining module comprises:
a first determining unit, configured to determine a first neural network model based on the implicit emotional words;
a second determining unit for determining a second neural network model based on the contextual display emotion classification;
a third determination unit configured to determine a third neural network model based on the text vector;
and the merging unit is used for merging the first neural network model, the second neural network model and the third neural network model to obtain a second emotion analysis model.
In some embodiments, the after-market apparatus 600 further comprises:
a ninth determining module for determining a second element event based on the objective reason and the event graph;
and the second output module is used for outputting the second element event so as to enable the user to carry out after-sales service based on the target reason and the second element event.
In some embodiments, the second determining module 603 includes:
the fourth determining unit is used for determining a target word of the first original event;
the fifth determining unit is used for matching the target words with words in a pre-stored affair map and determining a matching result;
a sixth determining unit configured to determine a target reason for making the evaluation information for the commodity based on a matching result.
In the embodiment of the present application, if the method of after-sales service is implemented in the form of a software functional module and sold or used as a standalone product, the method may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
Accordingly, an embodiment of the present application provides a storage medium having a computer program stored thereon, wherein the computer program is configured to implement, when executed by a processor, the steps in the method for providing after-sales service provided in the above embodiment.
The embodiment of the application provides an electronic device; fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 7, the electronic device 700 includes: a processor 701, at least one communication bus 702, a user interface 703, at least one external communication interface 704, a memory 705. Wherein the communication bus 702 is configured to enable connective communication between these components. The user interface 703 may include a display screen, and the external communication interface 704 may include standard wired and wireless interfaces, among others. The processor 701 is configured to execute the program of the after-sales service method stored in the memory to implement the steps in the after-sales service method provided in the above-described embodiment.
The above description of the display device and storage medium embodiments is similar to the description of the method embodiments above, with similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the computer device and the storage medium of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, 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 like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a controller to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of after-market servicing, comprising:
acquiring evaluation information of the commodity;
determining a first meta-event of the evaluation information in case that the evaluation information is determined to be a negative evaluation;
determining a target reason for making the evaluation information on the commodity based on the first meta-event and a pre-stored event map, wherein the event map comprises the reason for the first meta-event;
and outputting the target reason to enable the user to perform after-sales service based on the target reason.
2. The method of claim 1, further comprising:
inputting the evaluation information into a first emotion analysis model, and determining a first probability that the evaluation information is negative evaluation, wherein the first emotion analysis model can identify the probability that the evaluation information with the explicit emotion is negative evaluation;
and determining whether the evaluation information is negative evaluation or not based on the first probability and a first preset probability threshold.
3. The method of claim 2, further comprising:
determining that the evaluation information is suspected negative evaluation information under the condition that the evaluation information is determined not to be negative evaluation;
inputting the suspected negative evaluation information into a second emotion analysis model, and determining a second probability that the suspected negative evaluation information is negative evaluation, wherein the second emotion analysis model can identify that evaluation information with implicit emotion is the probability of negative evaluation;
and determining whether the suspected negative evaluation information is a negative evaluation or not based on the second probability and a second preset probability threshold.
4. The method of claim 3, further comprising:
acquiring a sample corpus, wherein the sample corpus is marked with implicit emotion words and context display emotion classification of the sample corpus;
determining the implicit emotional words, the context display emotion classification and a text vector of the sample corpus based on semantic relations based on the sample corpus;
determining a second emotion analysis model based on the implicit emotion words, the contextual display emotion classification, and the text vector;
and storing the second emotion analysis model.
5. The method of claim 4, wherein determining a second emotion analysis model based on the implicit emotion words, the contextual display emotion classification, and the text vector comprises:
determining a first neural network model based on the implicit emotional words;
determining a second neural network model based on the contextual display sentiment classification;
determining a third neural network model based on the text vector;
and combining the first neural network model, the second neural network model and the third neural network model to obtain a second emotion analysis model.
6. The method of claim 1, further comprising:
determining a second element event based on the target reason and the event graph;
and outputting the second element event to enable the user to perform after-sales service based on the target reason and the second element event.
7. The method of claim 1, wherein determining the target reason for making the evaluation information for the commodity based on the first meta-event information and a pre-stored event map comprises:
determining a target word of a first original event;
matching the target words with words in a pre-stored affair map to determine a matching result;
and determining a target reason for making the evaluation information for the commodity based on the matching result.
8. An after-market service device, comprising:
the first acquisition module is used for acquiring the evaluation information of the commodity;
the first determination module is used for determining a first meta-event of the evaluation information under the condition that the evaluation information is determined to be negative evaluation;
the second determination module is used for determining a target reason for making the evaluation information on the commodity based on the first meta-event and a pre-stored affair map, wherein the affair map comprises the reason of the first meta-event;
and the first output module is used for outputting the target reason so as to enable the user to carry out after-sale service based on the target reason.
9. An electronic device, comprising a memory and a processor, the memory having stored thereon a computer program which, when executed by the processor, performs the method of after-market serving of any one of claims 1 to 7.
10. A storage medium having stored thereon computer-executable instructions for performing the method of after-market servicing of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011471132.4A CN112598427A (en) | 2020-12-14 | 2020-12-14 | After-sale service method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011471132.4A CN112598427A (en) | 2020-12-14 | 2020-12-14 | After-sale service method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112598427A true CN112598427A (en) | 2021-04-02 |
Family
ID=75195208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011471132.4A Pending CN112598427A (en) | 2020-12-14 | 2020-12-14 | After-sale service method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112598427A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446813A (en) * | 2017-12-19 | 2018-08-24 | 清华大学 | A kind of method of electric business service quality overall merit |
| CN109388748A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | A kind of answering method of comment information, storage medium and server |
| CN109582764A (en) * | 2018-11-09 | 2019-04-05 | 华南师范大学 | Interaction attention sentiment analysis method based on interdependent syntax |
| CN111523914A (en) * | 2019-01-17 | 2020-08-11 | 阿里巴巴集团控股有限公司 | User satisfaction evaluation method, device and system and data display platform |
| CN111523923A (en) * | 2020-04-06 | 2020-08-11 | 北京三快在线科技有限公司 | Merchant comment management system, method, server and storage medium |
| CN111538816A (en) * | 2020-07-09 | 2020-08-14 | 平安国际智慧城市科技股份有限公司 | Question-answering method, device, electronic equipment and medium based on AI identification |
-
2020
- 2020-12-14 CN CN202011471132.4A patent/CN112598427A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446813A (en) * | 2017-12-19 | 2018-08-24 | 清华大学 | A kind of method of electric business service quality overall merit |
| CN109388748A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | A kind of answering method of comment information, storage medium and server |
| CN109582764A (en) * | 2018-11-09 | 2019-04-05 | 华南师范大学 | Interaction attention sentiment analysis method based on interdependent syntax |
| CN111523914A (en) * | 2019-01-17 | 2020-08-11 | 阿里巴巴集团控股有限公司 | User satisfaction evaluation method, device and system and data display platform |
| CN111523923A (en) * | 2020-04-06 | 2020-08-11 | 北京三快在线科技有限公司 | Merchant comment management system, method, server and storage medium |
| CN111538816A (en) * | 2020-07-09 | 2020-08-14 | 平安国际智慧城市科技股份有限公司 | Question-answering method, device, electronic equipment and medium based on AI identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017000513A1 (en) | Information pushing method and apparatus based on user search behavior, storage medium, and device | |
| KR102472572B1 (en) | Method for profiling user's intention and apparatus therefor | |
| US20150186790A1 (en) | Systems and Methods for Automatic Understanding of Consumer Evaluations of Product Attributes from Consumer-Generated Reviews | |
| US8533198B2 (en) | Mapping descriptions | |
| CN104933081A (en) | Search suggestion providing method and apparatus | |
| JP2003330948A (en) | Device and method for evaluating web page | |
| KR20140026932A (en) | System and method providing a suited shopping information by analyzing the propensity of an user | |
| US11276099B2 (en) | Multi-perceptual similarity detection and resolution | |
| US10901992B2 (en) | System and method for efficiently handling queries | |
| US20190065455A1 (en) | Intelligent form creation | |
| WO2023049635A1 (en) | Real-time product environmental impact scoring | |
| US20220382794A1 (en) | System and method for programmatic generation of attribute descriptors | |
| US10719561B2 (en) | System and method for analyzing popularity of one or more user defined topics among the big data | |
| US11373041B2 (en) | Text classification using models with complementary granularity and accuracy | |
| CN111737607B (en) | Data processing method, device, electronic equipment and storage medium | |
| US11966698B2 (en) | System and method for automatically tagging customer messages using artificial intelligence models | |
| JP2020067864A (en) | Knowledge search device, method for searching for knowledge, and knowledge search program | |
| CN112598427A (en) | After-sale service method and device, electronic equipment and storage medium | |
| JP2019128925A (en) | Event presentation system and event presentation device | |
| CN113689233A (en) | Advertisement putting and selecting method and corresponding device, equipment and medium thereof | |
| CN113379432A (en) | Sales system customer matching method based on machine learning | |
| CN113344674A (en) | Product recommendation method, device, equipment and storage medium based on user purchasing power | |
| CN113139115A (en) | Information recommendation method, search method, device, client, medium and equipment | |
| CN112148939A (en) | Data processing method and device and electronic equipment | |
| Joung et al. | An LDA-based Approach for Product Attribute Identification from Online Customer Reviews |
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 |