CN112199474A - Voice customer service method and system - Google Patents
Voice customer service method and system Download PDFInfo
- Publication number
- CN112199474A CN112199474A CN202011118512.XA CN202011118512A CN112199474A CN 112199474 A CN112199474 A CN 112199474A CN 202011118512 A CN202011118512 A CN 202011118512A CN 112199474 A CN112199474 A CN 112199474A
- Authority
- CN
- China
- Prior art keywords
- customer
- key information
- information
- voice
- target
- 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 48
- 238000000605 extraction Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 25
- 239000013589 supplement Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000005406 washing 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
- G06F16/3343—Query execution using phonetics
-
- 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
Abstract
The invention discloses a voice customer service method and a system, wherein the voice customer service method comprises the following steps: acquiring target voice information and converting the target voice information into target text information; analyzing the target text information and determining a target problem corresponding to the target text information; determining a solution corresponding to the target voice information according to the target problem; and outputting the solution. The invention aims to automatically improve the user experience of the voice intelligent customer service through the weight of the customer service key information and the customer complaint key information extraction training and the training of the customer complaint list, quickly provide a satisfactory problem solution corresponding to the customer complaint request for the user, and greatly improve the service quality and the service efficiency, thereby avoiding the loss of the reputation and reducing the loss risk of the user, and being convenient for the user.
Description
Technical Field
The invention relates to the technical field of voice recognition, in particular to a voice customer service method and a voice customer service system.
Background
With the progress of voice recognition technology, the experience requirements of customers on call center customer service seats are higher and higher, the traditional button selection type customer service system menu no longer meets the customer requirements, and the customer service industry gradually starts to deploy voice robots to replace the traditional call center seats. Generally, a voice service seat changes a traditional service telephone menu into a voice service menu corresponding to voice, when a user dials a service telephone, the service item required by the user can be identified in a service server through voice speaking, and the user jumps to a specified function to execute operation through identifying the voice service item.
However, currently, voice customer service cannot deal with customer service demands which are not in a menu or service demands, and cannot give an accurate solution in time through manual customer service, and the execution performance of the customer service demands is unclear, so that the processing efficiency is low, the telephone charge cost and the time cost are increased, and great influence is brought to a user.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Therefore, a voice customer service method and a voice customer service system are needed to be provided for solving the technical problem that the efficiency is low because the customer service requirements cannot be determined quickly and the solutions cannot be provided technically in the prior art.
A voice customer service method comprises the following steps:
acquiring target voice information and converting the target voice information into target text information;
analyzing the target text information and determining a target problem corresponding to the target text information;
determining a solution corresponding to the target voice information according to the target problem;
and outputting the solution.
The voice customer service method, wherein the analyzing the target text information and determining the target question corresponding to the target text information specifically includes:
extracting the customer appeal key information corresponding to the preset customer appeal key information category in the target text information according to the preset customer appeal key information category;
determining a customer appeal information item corresponding to the target text information according to preset customer appeal key information category weight and customer appeal key information dimension;
associating the customer complaint information items with corresponding customer complaint key information to form a customer complaint list key information table;
and determining a target problem matched with the customer complaint information entry in the customer complaint list key information table according to the incidence relation between the preset customer complaint key information and the problem, so as to serve as the target problem corresponding to the target text information.
The voice customer service method, wherein the extracting, according to a preset customer complaint key information category, customer complaint key information corresponding to the preset customer complaint key information category from the target text information specifically includes:
acquiring a trained key information extraction model, wherein the key information extraction model is configured with a preset customer appeal key information category;
and inputting the target text information into the key information extraction model, and outputting the customer appeal key information corresponding to the target text information through the key information extraction model.
The voice customer service method, wherein the training step of the key information extraction model comprises the following steps:
acquiring a training set, wherein the training set comprises a plurality of text messages;
inputting a plurality of text messages into a preset general model, training through the preset general model, and outputting first customer complaint key information corresponding to each text message;
comparing the first customer complaint key information corresponding to each text information with the target customer complaint information corresponding to each text information;
continuously adjusting the parameters of the preset general model according to the comparison result until the comparison result meets the preset condition, and stopping the training of the general model;
and taking the corresponding general model as the key information extraction model when the comparison result meets the preset condition.
The voice customer service method further includes, after extracting, according to a preset customer complaint key information category, customer complaint key information corresponding to the preset customer complaint key information category from the target text information:
if the target text information has customer complaint key information loss corresponding to a plurality of preset customer complaint key information types, prompting a user to fill in the customer complaint key information corresponding to the plurality of missing customer complaint key information types;
and acquiring the supplemented customer complaint key information, and updating the customer complaint list key information table according to the supplemented customer complaint key information.
The voice customer service method, wherein the step of obtaining the supplemented customer complaint key information and updating the customer complaint list key information table according to the supplemented customer complaint key information further comprises the steps of:
determining the service type of the information in the updated customer complaint list key information table;
if the service type of the information in the updated customer complaint list key information table is the customer service complaint type, determining whether the information in the new customer complaint list key information table meets preset customer complaint complaints conditions;
if the customer complaint requirement condition is not met, analyzing the to-be-supplemented key information in the updated customer complaint list key information table, and prompting a user to supplement the corresponding to-be-supplemented key information;
and acquiring a customer complaint list key information table after the customer is mended.
The voice customer service method, wherein the determining a solution corresponding to the target voice information according to the target problem specifically includes:
obtaining customer complaint key information corresponding to the target problem;
and determining a solution matched with the target problem according to the customer appeal key information.
The voice customer service method, wherein when there are a plurality of solutions, the outputting the solution specifically includes:
obtaining a plurality of solutions;
calculating the weights of the solutions, and sequencing the solutions according to the calculation result;
and outputting the sorted solution.
The voice customer service method, wherein the voice customer service method further comprises:
obtaining a customer complaint work order, wherein the customer complaint work order comprises customer complaint parameter information corresponding to the solution;
and outputting a solution list to be optimized according to the customer complaint parameter information corresponding to the solution.
The application also provides a voice customer service system, which comprises an intelligent terminal and a server, wherein the intelligent terminal is connected with the server, and the voice customer service system is used for realizing the steps in the voice customer service method.
Has the advantages that:
compared with the prior art, the invention provides a voice customer service method and a system, wherein the voice customer service method comprises the following steps: acquiring target voice information and converting the target voice information into target text information; analyzing the target text information and determining a target problem corresponding to the target text information; determining a solution corresponding to the target voice information according to the target problem; and outputting the solution. The invention aims to automatically improve the user experience of the voice intelligent customer service through the weight of the customer service key information and the customer complaint key information extraction training and the training of the customer complaint list, quickly provide a satisfactory problem solution corresponding to the customer complaint request for the user, and greatly improve the service quality and the service efficiency, thereby avoiding the loss of the reputation and reducing the loss risk of the user, and being convenient for the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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 invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
fig. 1 is a flowchart of a voice customer service method provided by the present invention.
Fig. 2 is a functional block diagram of a voice customer service system according to the present invention.
Fig. 3 is a block diagram of an intelligent terminal in the voice customer service system according to the present invention.
Detailed Description
The present invention provides a voice customer service method and system, and in order to make the purpose, technical scheme and effect of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The inventor researches and discovers that the voice customer service seat changes a traditional customer service telephone menu into a voice customer service menu corresponding to voice, when a user dials a customer service telephone, the user can only passively select a specified problem, a satisfactory solution can not be provided for the user often, the user appeal is not in the customer service appeal of the menu or the service appeal can not be processed under most conditions, only a manual service mode can be switched, the problem is often solved easily, the problem is solved easily, the telephone cost and the time cost are increased easily, and the inconvenience is caused.
Based on the problems, the application provides a voice customer service method and a voice customer service system, which are used for extracting training and training a customer complaint list according to the weight of the customer service key information and the customer complaint key information, automatically perfecting the user experience of voice intelligent customer service, quickly providing a satisfactory problem solution corresponding to the customer complaint request for a user, and greatly improving the service quality and the service efficiency, so that the loss of the reputation and the loss risk of the user are avoided, and convenience is brought to the user.
The invention will be further explained by the description of the embodiments with reference to the drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a voice customer service method provided in this embodiment, where the voice customer service method is applied to a voice customer service system, and the voice customer service system is shown in fig. 2, and includes an intelligent terminal 100 and a server 200, where the intelligent terminal 100 is connected to the server 200. The terminal 100 may be a mobile terminal, such as a mobile phone, or a fixed terminal, such as a smart television, and the smart terminal is not limited as long as the smart terminal has a voice recognition function.
As shown in fig. 1, the voice customer service method includes:
and S10, acquiring target voice information and converting the target voice information into target text information.
In the embodiment of the present invention, the target voice information refers to voice information for indicating a target problem, and the target voice information can be acquired by the intelligent terminal by triggering a voice button on the intelligent terminal by a user, or the target voice information sent by the user can be automatically acquired by detecting a human voice by the intelligent terminal. For example: when the user dials 10086, the speech: the voice collection device on the intelligent terminal is started to collect voice of the 'inquiry telephone charge' after detecting the voice, and the voice is used as target voice information. The voice collecting device can be a microphone, a loudspeaker or other voice sensors for collecting human voice.
And the intelligent terminal acquires the target voice information and then sends the target voice information to a server connected with the intelligent terminal, namely the target voice information is synchronized to a voice customer service system. Since the collected target voice information is diversified, such as dialect, in order to increase the recognition speed and improve the recognition accuracy, the customer service system can convert the target voice information into the target voice information in a standard voice format, such as mandarin. That is, without limiting the user group, even if the collected target voice information is non-standard voice information such as dialect voice, the non-standard voice information can be converted into target voice information corresponding to a standard voice format through the embodiment of the invention.
Further, the target voice information is converted into target text information. In the conversion process, the target text information is automatically deduplicated so that the target text information conforms to semantic logic. The target text information comprises effective content and invalid content, and in order to improve the accuracy of target problem matching and reduce errors, invalid parts in the target text information need to be removed. Therefore, semantic analysis including but not limited to chinese word segmentation, part of speech tagging, dependency analysis and entity recognition processing is performed on the target text information, so as to determine effective contents in the target text content, and finally form effective target text information.
Furthermore, the original target voice information and the converted target text information are both stored in the customer complaint voice-to-text record in the customer complaint work order database. The customer complaint work order database comprises customer complaint work orders. The customer complaint work order is created by a voice customer service system, and one conversation corresponds to one customer complaint work order. Each customer complaint work order corresponds to a unique customer complaint work order identifier, and the customer complaint work order can be quickly searched through the customer complaint work order identifier. The customer complaint work order records original target voice information, target text information, customer complaint key information, customer complaint list key information records and dynamic solution records of a user. The dynamic solution record refers to all records generated in the process of problem evaluation or session termination given by a solution issued by a user through a voice customer service system.
And S20, analyzing the target text information and determining a target problem corresponding to the target text information.
In the embodiment of the present invention, in order to provide a solution timely and accurately, a target problem corresponding to the target text information needs to be determined.
For example, the analyzing the target text information and determining the target question corresponding to the target text information specifically includes:
and S21, extracting the customer appeal key information corresponding to the preset customer appeal key information type in the target text information according to the preset customer appeal key information type.
Specifically, the target text information is different due to different user requirements. Different target text information covers different contents and even multiple sources, so that feature information extraction needs to be performed on the target text information. In this embodiment, the feature information extraction is to extract keyword information from the target text information. Therefore, customer appeal key information categories need to be preset, and different customer appeal key information categories are also called key attributes. And the customer appeal key information category is used for indicating the content in the extraction target text information. And the customer complaint key information category is set according to different user requirements. In this embodiment, the customer appeal key information category includes a service object, an equipment model, a fault type, and the like. The service object is equipment needing problem solving, such as a washing machine, a mobile phone, a set-top box and the like or service. The fault types include dead halt, voice unavailable, and the like. The fault type is determined by a fault description.
For example: the intelligent terminal takes a television as an example, the service object in the customer complaint key information category is the television, the equipment model is led55A1, and the fault type is crash.
In specific implementation, the extracting, according to a preset customer appeal key information category, customer appeal key information corresponding to the preset customer appeal key information category from the target text information specifically includes:
s211, acquiring a trained key information extraction model, wherein the key information extraction model is configured with preset customer appeal key information categories;
s212, inputting the target text information into the key information extraction model, and outputting the customer appeal key information corresponding to the target text information through the key information extraction model.
The training step of the key information extraction model comprises the following steps:
m1, acquiring a training set, wherein the training set comprises a plurality of text messages;
m2, inputting a plurality of text messages into a preset general model, training through the preset general model, and outputting first customer complaint key information corresponding to each text message;
m3, comparing the first customer appeal key information corresponding to each text information with the target customer appeal information corresponding to each text information;
m4, continuously adjusting the parameters of the preset general model according to the comparison result until the comparison result meets the preset conditions and stopping the training of the general model;
and M5, taking the corresponding general model as the key information extraction model when the comparison result meets the preset condition.
Specifically, the target customer appeal information refers to information conforming to semantics, and is obtained by extracting and combining information corresponding to the customer appeal key information category from text information. The preset condition refers to that the first customer appeal key information is the same as or similar to the target customer appeal information, that is, the output first customer appeal key information is not changed any more, and the universal model training is stopped when the difference between the output first customer appeal key information and the target customer appeal information is within a range.
Furthermore, the target text information is input into the trained key information extraction model, and the customer complaint key information is output through the key information extraction model, so that the customer complaint key information in the target text information can be known through AI learning training, the invalid key information is removed, the labor cost is saved, the identification efficiency and the extraction efficiency are accelerated, and a foundation is laid for quickly determining the subsequent solution.
And S22, determining the customer appeal information item corresponding to the target text information according to the preset customer appeal key information category weight and the customer appeal key information dimension.
Specifically, the weight corresponding to each customer complaint key information category is preset. And dividing the target text information according to the set weight and the customer appeal key information dimension to form independent customer appeal information items. The customer complaint information entry is similar to a program electronic menu.
And S23, associating the customer appeal information items with the corresponding customer appeal key information to form a customer appeal list key information table.
Specifically, the relationship between the customer appeal information entry and the corresponding customer appeal key information is established, so that the customer appeal information entry is found through the customer appeal key information. The customer appeal list key information table comprises customer appeal information entries and customer appeal key information.
In some other embodiments, if customer appeal key information corresponding to a plurality of preset customer appeal key information categories is missing in the target text information, prompting a user to supplement the customer appeal key information corresponding to the missing customer appeal key information categories; and acquiring the supplemented customer complaint key information, and updating the customer complaint list key information table according to the supplemented customer complaint key information. For example: if 7 customer appeal key information categories are preset. In the process of extracting the target text information, the customer appeal key information corresponding to 2 customer appeal key information categories is null, such as service objects and fault types. At this time, the voice customer service system will send the missing customer appeal key information category to the intelligent terminal, and display the category in the session box, so as to prompt the user to add the customer appeal key information corresponding to the customer appeal key information category. And after the user mends the corresponding customer complaint key information, logically combining the mended customer complaint key information with the original customer complaint key information to form a customer complaint list key information table.
Further, in another embodiment, after the obtaining the supplemented customer complaint key information and updating the customer complaint list key information table according to the supplemented customer complaint key information, the method further includes:
h1, determining the service type of the information in the updated customer complaint list key information table;
h2, if the service type of the information in the updated customer complaint list key information table is the customer complaint type, determining whether the information in the new customer complaint list key information table meets the preset customer complaint condition;
h3, if the preset customer complaint requirement condition is not met, analyzing the to-be-supplemented key information in the updated customer complaint list key information table, and prompting the user to supplement the corresponding to-be-supplemented key information;
h4, obtaining the customer complaint list key information table after the customer is mended.
That is to say, when a missing occurs in the target text information extraction process, the customer complaint demand analysis needs to be performed on the target text information to determine the service type corresponding to the target text information, so as to determine the reason for the missing. The service types include a customer demand type and a non-customer demand type. And if the service type corresponding to the target text information is a non-customer service appeal type, not performing operation and prompting the user. And if the service type corresponding to the target text information is a customer service appeal type, judging whether the originally extracted customer appeal key information meets the lowest customer appeal request or not, wherein the lowest customer appeal request is preset. And once the originally extracted customer complaint key information does not accord with the lowest customer complaint request, analyzing the to-be-supplemented key information required to be supplemented in the original customer complaint list key information table, and sending the to-be-supplemented key information to the intelligent terminal to prompt the user to supplement. And when the key information after the completion is received, the key information is logically combined with the original customer complaint key information to form a new customer complaint list key information table.
In another embodiment, in order to save analysis time, improve efficiency, and improve accuracy of the solution, the user may also first mend the missing key information when the target text information is missing, then perform service type judgment according to the mended customer appeal key information, and analyze whether the mended customer appeal key information can meet the minimum requirement of the customer appeal once the service type is determined to be the customer appeal type.
And S24, determining a target problem matched with the customer complaint information entry in the customer complaint list key information table according to the preset incidence relation between the customer complaint key information and the problem, and taking the target problem as a target problem corresponding to the target text information.
Specifically, by means of the customer complaint key information, namely, the key word, the target question matched with the key word is searched in the database of the voice customer service system.
And S30, determining a solution corresponding to the target voice information according to the target problem.
In this embodiment, the determining, according to the target problem, a solution corresponding to the target voice information specifically includes:
s31, obtaining the customer appeal key information corresponding to the target problem;
and S32, determining a solution matched with the target problem according to the customer appeal key information.
That is to say, the voice customer service system stores the problems and the solutions corresponding to each problem in advance, and each problem corresponds to a keyword, so once a target problem is determined, customer complaint key information corresponding to the target problem can be known, the customer complaint key information is the keyword, the target problem matched with the customer complaint key information in the book library is searched through the customer complaint key information, and thus the solution corresponding to the target problem can be determined according to the association relationship between the preset problem and the solution, and further the solution corresponding to the target voice information is determined. In the searching and matching process, multidimensional searching can be carried out through a plurality of keywords, so that the solution corresponding to the target problem can be quickly positioned.
And S40, outputting the solution.
In this embodiment, the voice service system outputs one or more solutions corresponding to the obtained target problem to send to the intelligent terminal or the voice prompt user.
Illustratively, when the solution is multiple, the outputting the solution specifically includes:
s41, acquiring a plurality of solutions;
s42, calculating the weights of the solutions, and sorting the solutions according to the calculation result;
and S43, outputting the sorted solution.
It can be understood that the first output solution is not necessarily capable of solving the problem of the user, and therefore, if there are multiple solutions, it is necessary to calculate the weights of the multiple solutions according to the weights of the customer complaint request list, and then rank the multiple solutions according to the calculation result, in this embodiment, rank the multiple solutions in a manner that the weights are from high to low, for example: the solution with the highest weight is ranked first, and the solution with the lowest weight is ranked last. And then displaying the sorting result on the intelligent terminal. In this embodiment, the solution displayed on the intelligent terminal may be a link or a two-dimensional code.
Further, the plurality of solutions can also inform the user in a voice manner to be suitable for the group which does not operate.
It should be noted that, after the solution is output, the voice customer service system collects the evaluation, satisfaction and the like of the user on the solution and stores the evaluation, satisfaction and the like in the customer complaint work order for reference, and meanwhile, the back-end personnel can conveniently improve and optimize the customer complaint work order, so that the user experience is improved.
Meanwhile, the voice customer service system outputs a solution list to be optimized according to the customer complaint parameter information corresponding to the solution in the customer complaint work order. The solution list to be optimized comprises a list corresponding to the target problem which is not solved. The customer appeal parameter information comprises polling times of the solutions, customer appeal list keyword satisfaction degrees corresponding to the solutions, invalid customer appeal rates, non-statistical customer appeal rates and the like. The database is perfected by solving the solution list to be optimized, the solution efficiency of similar customer complaints is optimized, and invalid session polling is reduced.
Therefore, based on the steps S10-S40, the method extracts training and training of the customer complaint list according to the weight of the customer service key information and the customer complaint key information, automatically improves the user experience of the voice intelligent customer service, quickly provides a satisfactory problem solution corresponding to the customer complaint request for the user, and greatly improves the service quality and the service efficiency, thereby avoiding the loss of the reputation and reducing the risk of the user loss, and facilitating the user.
Based on the voice customer service method, the present invention further provides a voice customer service system, as shown in fig. 2, the voice customer service system 1 includes an intelligent terminal 100 and a server 200, the intelligent terminal 100 is connected with the server 200, the intelligent terminal 100 includes at least one processor (processor)20 as shown in fig. 3; a display screen 21; and a memory (memory)22, and may further include a communication Interface (Communications Interface)23 and a bus 24. The processor 20, the display 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a user guidance interface preset in the initial setting mode. The communication interface 23 may transmit information. The processor 20 may call logic instructions in the memory 22 to perform the methods in the embodiments described above.
Furthermore, the logic instructions in the memory 22 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product.
The memory 22, which is a computer-readable storage medium, may be configured to store a software program, a computer-executable program, such as program instructions or modules corresponding to the methods in the embodiments of the present invention. The processor 30 executes the functional application and data processing, i.e. implements the method in the above-described embodiments, by executing the software program, instructions or modules stored in the memory 22.
The memory 22 may include a storage program area and a storage data area, wherein the storage program area may store an application program required for operating the voice customer service system, at least one function; the storage data area may store data created according to the use of the terminal device, and the like. Further, the memory 22 may include a high speed random access memory and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, may also be transient storage media.
In addition, the specific processes loaded and executed by the storage medium and the instruction processors in the terminal device are described in detail in the method, and are not stated herein.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A voice customer service method comprises the following steps:
acquiring target voice information and converting the target voice information into target text information;
analyzing the target text information and determining a target problem corresponding to the target text information;
determining a solution corresponding to the target voice information according to the target problem;
and outputting the solution.
2. The voice customer service method according to claim 1, wherein the analyzing the target text information and determining the target question corresponding to the target text information specifically comprises:
extracting the customer appeal key information corresponding to the preset customer appeal key information category in the target text information according to the preset customer appeal key information category;
determining a customer appeal information item corresponding to the target text information according to preset customer appeal key information category weight and customer appeal key information dimension;
associating the customer complaint information items with corresponding customer complaint key information to form a customer complaint list key information table;
and determining a target problem matched with the customer complaint information entry in the customer complaint list key information table according to the incidence relation between the preset customer complaint key information and the problem, so as to serve as the target problem corresponding to the target text information.
3. The voice customer service method according to claim 2, wherein the extracting, according to a preset customer complaint key information category, customer complaint key information corresponding to the preset customer complaint key information category in the target text information specifically includes:
acquiring a trained key information extraction model, wherein the key information extraction model is configured with a preset customer appeal key information category;
and inputting the target text information into the key information extraction model, and outputting the customer appeal key information corresponding to the target text information through the key information extraction model.
4. The voice customer service method according to claim 3, wherein the training step of the key information extraction model comprises:
acquiring a training set, wherein the training set comprises a plurality of text messages;
inputting a plurality of text messages into a preset general model, training through the preset general model, and outputting first customer complaint key information corresponding to each text message;
comparing the first customer complaint key information corresponding to each text information with the target customer complaint information corresponding to each text information;
continuously adjusting the parameters of the preset general model according to the comparison result until the comparison result meets the preset condition, and stopping the training of the general model;
and taking the corresponding general model as the key information extraction model when the comparison result meets the preset condition.
5. The voice customer service method according to claim 2, wherein after extracting the customer appeal key information corresponding to the customer appeal key information category in the target text information according to the customer appeal key information category, the method further comprises:
if the target text information has customer complaint key information loss corresponding to a plurality of preset customer complaint key information types, prompting a user to fill in the customer complaint key information corresponding to the plurality of missing customer complaint key information types;
and acquiring the supplemented customer complaint key information, and updating the customer complaint list key information table according to the supplemented customer complaint key information.
6. The voice customer service method according to claim 5, wherein the step of obtaining the supplemented customer complaint key information and updating the customer complaint list key information table according to the supplemented customer complaint key information further comprises:
determining the service type of the information in the updated customer complaint list key information table;
if the service type of the information in the updated customer complaint list key information table is the customer service complaint type, determining whether the information in the new customer complaint list key information table meets preset customer complaint complaints conditions;
if the customer complaint requirement condition is not met, analyzing the to-be-supplemented key information in the updated customer complaint list key information table, and prompting a user to supplement the corresponding to-be-supplemented key information;
and acquiring a customer complaint list key information table after the customer is mended.
7. The voice customer service method according to claim 1, wherein the determining a solution corresponding to the target voice message according to the target problem specifically comprises:
obtaining customer complaint key information corresponding to the target problem;
and determining a solution matched with the target problem according to the customer appeal key information.
8. The voice customer service method according to claim 1, wherein when there are a plurality of solutions, the outputting the solution specifically comprises:
obtaining a plurality of solutions;
calculating the weights of the solutions, and sequencing the solutions according to the calculation result;
and outputting the sorted solution.
9. The voice customer service method according to claim 1, further comprising:
obtaining a customer complaint work order, wherein the customer complaint work order comprises customer complaint parameter information corresponding to the solution;
and outputting a solution list to be optimized according to the customer complaint parameter information corresponding to the solution.
10. A voice customer service system, characterized in that the voice customer service system comprises an intelligent terminal and a server, the intelligent terminal is connected with the server, and the voice customer service system is used for implementing the steps in the voice customer service method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011118512.XA CN112199474A (en) | 2020-10-19 | 2020-10-19 | Voice customer service method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011118512.XA CN112199474A (en) | 2020-10-19 | 2020-10-19 | Voice customer service method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112199474A true CN112199474A (en) | 2021-01-08 |
Family
ID=74008818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011118512.XA Pending CN112199474A (en) | 2020-10-19 | 2020-10-19 | Voice customer service method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112199474A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766749A (en) * | 2021-01-22 | 2021-05-07 | 北京高途云集教育科技有限公司 | Feedback information processing method, system and storage medium |
| CN112966116A (en) * | 2021-05-19 | 2021-06-15 | 南京视察者智能科技有限公司 | Method and device for intelligently generating reception record and terminal equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447285B1 (en) * | 2007-03-26 | 2013-05-21 | Callwave Communications, Llc | Methods and systems for managing telecommunications and for translating voice messages to text messages |
| CN106340308A (en) * | 2016-08-25 | 2017-01-18 | 北京云知声信息技术有限公司 | Speech reply method and device |
| CN107153965A (en) * | 2017-04-05 | 2017-09-12 | 芜湖恒天易开软件科技股份有限公司 | A kind of intelligent customer service solution of multiple terminals |
| CN109241252A (en) * | 2018-07-27 | 2019-01-18 | 北京小米移动软件有限公司 | Consulting replies method, apparatus, electronic equipment and storage medium |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| CN110335595A (en) * | 2019-06-06 | 2019-10-15 | 平安科技（深圳）有限公司 | Slotting based on speech recognition asks dialogue method, device and storage medium |
| CN110830665A (en) * | 2019-11-12 | 2020-02-21 | 德邦物流股份有限公司 | Voice interaction method and device and express service system |
| CN111192060A (en) * | 2019-12-23 | 2020-05-22 | 广州供电局有限公司 | Electric power IT service-based full-channel self-service response implementation method |
| CN111586244A (en) * | 2020-05-20 | 2020-08-25 | 深圳康佳电子科技有限公司 | Voice customer service method and system |
-
2020
- 2020-10-19 CN CN202011118512.XA patent/CN112199474A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8447285B1 (en) * | 2007-03-26 | 2013-05-21 | Callwave Communications, Llc | Methods and systems for managing telecommunications and for translating voice messages to text messages |
| CN106340308A (en) * | 2016-08-25 | 2017-01-18 | 北京云知声信息技术有限公司 | Speech reply method and device |
| CN107153965A (en) * | 2017-04-05 | 2017-09-12 | 芜湖恒天易开软件科技股份有限公司 | A kind of intelligent customer service solution of multiple terminals |
| CN109241252A (en) * | 2018-07-27 | 2019-01-18 | 北京小米移动软件有限公司 | Consulting replies method, apparatus, electronic equipment and storage medium |
| CN109981910A (en) * | 2019-02-22 | 2019-07-05 | 中国联合网络通信集团有限公司 | Business recommended method and apparatus |
| CN110335595A (en) * | 2019-06-06 | 2019-10-15 | 平安科技（深圳）有限公司 | Slotting based on speech recognition asks dialogue method, device and storage medium |
| CN110830665A (en) * | 2019-11-12 | 2020-02-21 | 德邦物流股份有限公司 | Voice interaction method and device and express service system |
| CN111192060A (en) * | 2019-12-23 | 2020-05-22 | 广州供电局有限公司 | Electric power IT service-based full-channel self-service response implementation method |
| CN111586244A (en) * | 2020-05-20 | 2020-08-25 | 深圳康佳电子科技有限公司 | Voice customer service method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766749A (en) * | 2021-01-22 | 2021-05-07 | 北京高途云集教育科技有限公司 | Feedback information processing method, system and storage medium |
| CN112966116A (en) * | 2021-05-19 | 2021-06-15 | 南京视察者智能科技有限公司 | Method and device for intelligently generating reception record and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109344237B (en) | Information processing method and device for man-machine interaction | |
| CN107784033B (en) | Method and device for recommending based on session | |
| CN110110038B (en) | Telephone traffic prediction method, device, server and storage medium | |
| US20120330662A1 (en) | Input supporting system, method and program | |
| CN111368043A (en) | Event question-answering method, device, equipment and storage medium based on artificial intelligence | |
| CN104462600A (en) | Method and device for achieving automatic classification of calling reasons | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN107092602B (en) | Automatic response method and system | |
| CN113051362A (en) | Data query method and device and server | |
| CN112199474A (en) | Voice customer service method and system | |
| CN111897528B (en) | Low-code platform for enterprise online education | |
| CN111159334A (en) | Method and system for house source follow-up information processing | |
| CN107871055B (en) | Data analysis method and device | |
| KR20110048675A (en) | Call center counsel method and counsel system using voice recognition and tagging | |
| CN114722199A (en) | Risk identification method and device based on call recording, computer equipment and medium | |
| CN111831286B (en) | User complaint processing method and device | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| CN111460114A (en) | Retrieval method, device, equipment and computer readable storage medium | |
| CN110311943A (en) | The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform | |
| CN110895538A (en) | Data retrieval method, device, storage medium and processor | |
| CN111723580B (en) | Power dispatching station information graph validation method based on voice recognition and image recognition | |
| CN115186063A (en) | Service data processing method, device, equipment and storage medium | |
| CN111291042B (en) | Power data processing system and method for power supply service | |
| CN112115157B (en) | Response device, response method, and storage medium | |
| CN111062729A (en) | Information acquisition method, device and equipment |
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 |