CN111914073A - Customer service response method, device, equipment and storage medium - Google Patents
Customer service response method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111914073A CN111914073A CN202010678454.XA CN202010678454A CN111914073A CN 111914073 A CN111914073 A CN 111914073A CN 202010678454 A CN202010678454 A CN 202010678454A CN 111914073 A CN111914073 A CN 111914073A
- Authority
- CN
- China
- Prior art keywords
- user
- keywords
- customer service
- slot
- intention
- 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
- 230000004044 response Effects 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000012790 confirmation Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 abstract description 19
- 230000003993 interaction Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000005429 filling process Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Library & Information Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a customer service response method, a customer service response device, customer service response equipment and a storage medium. The method comprises the steps of receiving question content input by a user, wherein the question content comprises at least two keywords; acquiring all keywords in the question content; determining a target instruction of a user according to the labels of all the keywords; performing slot filling processing on the target instruction according to the keywords to determine the intention of the user; and obtaining an answer corresponding to the target instruction according to the intention. The method reduces the interaction process with the user in the customer service and user response process, and improves the key information acquisition efficiency.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method, an apparatus, a device, and a storage medium for customer service response.
Background
The gradual development of telecommunication services enables more and more users to know about service solution problems through a customer service system, and in order to improve efficiency and reduce waste of human resources, man-machine conversation services in the telecommunication customer service system are continuously improved.
In the existing full-language portal of a customer service system, configuration is mostly realized through a self-service customer service module, the self-service customer service module is provided with question and answer nodes of different levels, the self-service customer service module acquires key information filling nodes of a user in each level in a question and answer mode, and the acquired information is combined to give the user answers. For example, a user inputs a statement "wants to query consumption records of a certain number within one month" in the process of conversation with the customer service module, the self-service customer service module identifies one key information "consumption record" at the first level, and then sends a query to the user to acquire the second key information in the user answers until all key information is acquired, for example, the statement contains three key information "consumption records", "a certain number" and "within one month", so that the self-service customer service module is required to converse with the user at least three times, and the key information is combined to give the corresponding answer of the user.
However, in the prior art, the efficiency of acquiring the key information is low.
Disclosure of Invention
The application provides a customer service response method, a customer service response device, customer service response equipment and a storage medium, and solves the problem that the efficiency of obtaining key information is low in the prior art.
In a first aspect, the present application provides a customer service response method, including: receiving question content input by a user, wherein the question content comprises at least two keywords; acquiring all keywords in the question content; determining a target instruction of a user according to the labels of all the keywords; performing slot filling processing on the target instruction according to the keywords to determine the intention of the user; according to the intention, the answer corresponding to the target instruction is obtained, wherein when the keyword of the user is obtained, all keywords in the problem content of the user are obtained at one time, the obtained keywords can be directly filled in the groove when the intention of the user is determined subsequently, the user does not need to be asked for the problem for many times to obtain the keywords, so that the interaction process with the user is reduced, and the obtaining efficiency of the key information is improved under the condition that the user speaks the least number of words.
Optionally, determining the target instruction of the user according to the tags of all the keywords includes: randomly combining the labels corresponding to all the keywords; matching each combination with a preset instruction set, wherein the instruction set comprises at least one instruction; and determining the instruction with the highest matching degree as a target instruction of the user, randomly combining the labels of all the keywords, and matching the labels with a preset instruction set to obtain the target instruction closest to the user problem, thereby further improving the customer service response accuracy.
Optionally, all keywords in the question content are obtained, including: the method comprises the steps of obtaining keywords corresponding to labels in problem contents according to the labels corresponding to the grooves in a groove pool, wherein the groove pool comprises at least two grooves, obtaining the keywords according to the labels of the groove pool, and obtaining the keywords capable of being processed by filling the grooves more efficiently, so that the process of obtaining a large number of redundant keywords and matching the keywords is saved, and the obtaining efficiency of key information is further improved.
Optionally, before obtaining the keyword corresponding to the tag in the question content according to the tag corresponding to each slot in the slot pool, the method further includes: and extracting the label corresponding to the slot according to the historical problem content, updating the slot pool, and updating the slot pool according to the historical problem content of the user, so that the label in the slot pool is more suitable for the interactive response of the user and the customer service, and the key information acquisition efficiency is further improved.
Optionally, before obtaining the answer corresponding to the target instruction according to the intention, the method further includes: outputting confirmation information to the user, wherein the confirmation information is used for confirming whether the intention of the user is correct; the response information of the user is received, the response information is used for indicating that the intention is correct, the confirmation information of the target instruction is input to the user before the target instruction is obtained, whether the intention corresponding to the target instruction is correct or not can be determined for the user, the answer which the user wants to obtain is given, and the accuracy of customer service response is further improved.
In a second aspect, the present application provides a customer service response device, comprising: the system comprises a first receiving module, a first obtaining module, a determining module, a processing module and a second obtaining module, wherein the first receiving module is used for receiving question contents input by a user, and the question contents comprise at least two keywords; the first acquisition module is used for acquiring all keywords in the question content; the determining module is used for determining a target instruction of the user according to the labels of all the keywords; the processing module is used for performing slot filling processing on the target instruction according to the keywords and determining the intention of the user; the second obtaining module is used for obtaining the answer corresponding to the target instruction according to the intention.
Optionally, the determining module is specifically configured to: randomly combining the labels corresponding to all the keywords; matching each combination with a preset instruction set, wherein the instruction set comprises at least one instruction; and determining the instruction with the highest matching degree as a target instruction of the user.
Optionally, the first obtaining module is specifically configured to: and acquiring the keywords corresponding to the labels in the question content according to the labels corresponding to the grooves in the groove pool, wherein the groove pool comprises at least two grooves.
Optionally, the method further includes: and the updating module is used for extracting the label corresponding to the slot according to the historical problem content and updating the slot pool.
Optionally, the method further includes: the output module is used for outputting confirmation information to the user, and the confirmation information is used for confirming whether the intention of the user is correct or not; the second receiving module is used for receiving response information of the user, and the response information is used for indicating that the intention is correct.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the customer service response method according to the first aspect or the optional manner of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer program product, which includes computer executable instructions, and when the computer executable instructions are executed by a processor, the computer program product is configured to implement the customer service response method according to the first aspect or the alternatives of the first aspect.
The application provides a customer service response method, a customer service response device, customer service response equipment and a storage medium, wherein the customer service response method comprises the following steps: receiving question content input by a user, wherein the question content comprises at least two keywords; acquiring all keywords in the question content; determining a target instruction of a user according to the labels of all the keywords; performing slot filling processing on the target instruction according to the keywords to determine the intention of the user; according to the intention, the answer corresponding to the target instruction is obtained, wherein when the keyword of the user is obtained, all keywords in the problem content of the user are obtained at one time, the obtained keywords can be directly filled in the groove when the intention of the user is determined subsequently, the user does not need to be asked for the problem for many times to obtain the keywords, so that the interaction process with the user is reduced, and the obtaining efficiency of the key information is improved under the condition that the user speaks the least number of words.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a schematic process diagram of a customer service response method provided by the prior art;
fig. 2 is a schematic flowchart of a customer service response method according to an embodiment of the present application;
FIG. 3 is a user interface diagram of a customer service response device according to an embodiment of the present application;
fig. 4 is a schematic process diagram of a customer service response method according to an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating another customer service response method according to an embodiment of the present application;
fig. 6 is a schematic flowchart of a further customer service response method according to an embodiment of the present application;
FIG. 7 is a schematic flow chart illustrating another customer service response method according to an embodiment of the present application;
FIG. 8 is a user interface diagram of another customer service response device provided in an embodiment of the present application;
fig. 9 is a schematic structural diagram of a customer service answering device according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a customer service answering device according to an embodiment of the present application.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the preferred embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar components or components having the same or similar functions throughout. The described embodiments are only some, but not all embodiments of the invention. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The terms referred to in this application are explained first:
groove: the attributes that an entity has well-defined, such as the attributes in the departure location slot, destination slot, and departure time slot in a taxi are "departure location", "destination", and "departure time", respectively.
Filling a groove: the process of converting a user's target instruction into the user's intent to complete the information, extracts the values of well-defined attributes of a given entity from a large corpus.
And (4) slot position: the groove is composed of groove positions, and one groove position is a groove filling mode.
In the customer service conversation process, a plurality of slot positions are provided, the customer service system needs to extract key node information in user questions and fill the key node information into the corresponding slot positions so as to obtain a user instruction, the target instruction of the user is converted into the intention of the user through the slot filling process, and finally the user answer is given.
Exemplarily, fig. 1 is a process schematic diagram of a customer service response method provided by the prior art, as shown in fig. 1, a customer service system is provided with question and answer nodes of different levels, the nodes include slots to be filled, the customer service system acquires key information of a user in each level in a question and answer mode, the key information is filled in the slots, the acquired information is combined to give a user answer, a process of interaction between the customer service system and the user is shown in fig. 1, the user inputs a question "i wants to query a consumption record of a local number for 1 month" into the customer service system, the customer service system acquires the key information "consumption record" and invokes an utterance "you want to acquire the consumption record of which telephone number", the user inputs "local number", the customer service system acquires the key information "local number" and invokes the utterance "you want to acquire the consumption record of the local number for several months", the user inputs 'month 1', the customer service system acquires key information 'month 1' and integrates the key information to give a user answer, and the consumption record of january of the own phone number is sent to a mobile phone, so that the conventional customer service system needs to perform question and answer interaction with the user once to acquire each piece of key information, the query and answer interaction with the user needs to be performed for multiple times in the process of one customer service query, only one piece of key information can be acquired when the user inputs a statement once, and the efficiency of acquiring the key information is low.
In order to solve the above problems, embodiments of the present application provide a customer service response method, apparatus, device, and storage medium, where when a keyword of a user question content is obtained, all keywords in the question content are obtained, and when a slot filling process is performed, a pre-obtained keyword is filled in a corresponding slot, and there is no need to send an inquiry to a user many times to obtain key information.
The technical scheme of the application is explained in detail as follows:
fig. 2 is a schematic flow chart of a customer service response method according to an embodiment of the present application. The method is performed by part or all of the customer service answering device, and the part of the customer service answering device can be a processor in the customer service answering device. The following describes a customer service response method using the customer service response device as an execution subject. As shown in fig. 2, the method comprises the steps of:
s201: the customer service response device receives the question content input by the user.
Wherein, the question content comprises at least two keywords.
The user inquires the question from the customer service response device in the process of interacting with the customer service response device, the customer service response device needs to obtain the intention of the user through a sentence of the question inquired by the user, therefore, the inquiry sentence comprises at least two keywords, and the sentence of the user can be converted into an instruction by combining the keywords.
Optionally, the interaction between the user and the customer service response device may be in a form of voice, such as telephone customer service, or in a form of text, such as a form of text input through a query interface, or in a form of a combination of voice and text, which is not limited in this application.
Optionally, when the user interacts with the customer service response device in a voice manner, the customer service response device may convert the received voice of the user into a text and then process the text.
If the user interacts with the customer service response device in a text manner, wherein an optional manner is to perform a conversation through a user interface, exemplarily, fig. 3 is a user interface diagram of the customer service response device provided in an embodiment of the present application, as shown in fig. 3, the user may input a question to interact with the customer service response device, and the user interface of the response device displays an answer to the question on the user interface.
S202: the customer service response equipment acquires all keywords in the question content.
Alternatively, the customer service response device may obtain all words or nouns in the question content of the user, and use the words as all keywords in the question content, for example, if the question content of the user is "please help me to inquire about the call records of the local machine in 12 months", then the customer service response device obtains all the nouns "local machine", "12 months" and "call records" as all keywords of the question content of the user.
In an optional mode two, the customer service response device may obtain the keyword corresponding to the tag in the question content according to the tag corresponding to each slot in the slot pool, where the slot pool includes at least two slots. The purpose of the customer service response device for obtaining the keywords is to fill the slot positions to determine that the user intention is converted into a user specific instruction, so that the obtained keywords can be obtained according to the labels corresponding to the slots in the slot pool, for example, the labels of two slots in the slot pool are 'name' and 'month', the keywords 'zhangsan' and '4 month' can be obtained from the problem content 'i want to inquire about the call in zhangsan 4 month', the keywords can be obtained according to the labels, the keywords capable of being processed by slot filling can be obtained more efficiently, the process of obtaining a large number of redundant keywords and matching the keywords is saved, the obtaining efficiency of the key information is further improved, and the user experience is improved.
S203: and the customer service response equipment determines the target instruction of the user according to the labels of all the keywords.
S204: and the customer service response equipment performs slot filling processing on the target instruction according to the keyword to determine the intention of the user.
S205: and the customer service response equipment acquires the answer corresponding to the target instruction according to the intention.
The keywords have corresponding labels, for example, the label corresponding to "zhang san" is "name", and the label corresponding to "woman" is "gender", the labels corresponding to the keywords are combined to obtain a target instruction, and then slot filling processing is performed according to the keywords to obtain the intention of the user, so that the answer corresponding to the user is fed back.
A schematic diagram of performing slot filling processing according to a keyword to obtain a user intention is shown in fig. 4, where fig. 4 is a schematic process diagram of a customer service response method provided in an embodiment of the present application, in a session process between a user and a customer service response device, key information of a slot 1 and a slot 2 is expressed in a question content of the user at the same time, the slot 1 and the slot 2 are subjected to slot filling processing, a target instruction 1 and a target instruction 2 can be obtained according to the key information of the slot 1 and the slot 2, and an answer of a target instruction of the user is given.
Optionally, when the obtained keywords are few or a clear instruction of the user cannot be obtained by performing slot filling processing according to the existing keywords, the corresponding dialogues of the slot positions may be called to obtain more keywords for the user.
The method comprises the steps that customer service response equipment receives question content input by a user, wherein the question content comprises at least two keywords; acquiring all keywords in the question content; determining a target instruction of a user according to the labels of all the keywords; performing slot filling processing on the target instruction according to the keywords to determine the intention of the user; according to the intention, the answer corresponding to the target instruction is obtained, wherein when the keyword of the user is obtained, all keywords in the problem content of the user are obtained at one time, the obtained keywords can be directly filled in the groove when the intention of the user is determined subsequently, the user does not need to be asked for the problem for many times to obtain the keywords, so that the interaction process with the user is reduced, and the obtaining efficiency of the key information is improved under the condition that the user speaks the least number of words.
Fig. 5 is a schematic flowchart of another customer service response method according to an embodiment of the present application, as shown in fig. 5, where fig. 5 is based on the embodiment of fig. 2, and S203 includes:
s401: and the customer service response equipment randomly combines the labels corresponding to all the keywords.
S402: the customer service answering device matches each combination with a preset instruction set.
Wherein, the instruction set comprises at least one instruction.
The problem content of one sentence of the user comprises a plurality of keywords, the keywords are combined randomly, the combination comprises the combination of the number and the type of the keywords, the combinations are matched with an instruction set preset in customer service response equipment, the instruction with the highest matching degree is determined to be the instruction of the user, and the user instruction with the highest accuracy can be obtained.
Optionally, the preset instruction set may be an instruction set preset by the customer service response device according to a specific scene, or an instruction set determined according to a historical query problem, which is not specifically limited in this application.
S403: and the customer service response equipment determines the instruction with the highest matching degree as the target instruction of the user.
Optionally, the matching degree between each combination of matching degrees and the instructions in the instruction set may be determined according to semantic similarity, or may be determined according to the number of words that contain the same word, and the like, which is not specifically limited in this application.
According to the method and the device, the customer service response equipment can obtain various combined instructions by randomly combining the labels of all the keywords, and can be matched with the preset instruction set to obtain the target instruction closest to the user problem, so that the customer service response quality is further improved, and the user experience is improved.
Fig. 6 is a schematic flowchart of another customer service response method according to an embodiment of the present application, and fig. 6 is based on fig. 5, and further, S202 specifically includes:
s502: and the customer service response equipment acquires the keywords corresponding to the labels in the question content according to the labels corresponding to the slots in the slot pool.
Wherein, the tank pool comprises at least two tanks.
For example, a plurality of keywords are acquired at one time, and tags corresponding to a plurality of slots need to be acquired, so that a slot pool at least includes two slots, and the purpose of acquiring the keywords by the customer service response device is to fill the slot position to determine that the user intention is converted into a user-defined instruction, so that the acquired keywords can be acquired according to tags corresponding to each slot in the slot pool, for example, tags of two slots in the slot pool are "name" and "month", respectively, and then the keywords "zhang" and "4 month" can be acquired from the question content "i want to inquire about the call of zhang 4 month" of the user ".
Optionally, at least two slots and tags corresponding to the slots are stored in the slot pool, and the slot pool may be extracted according to the content of the historical problem or guessed in advance according to the application scenario.
Before S502, the method further includes:
s501: and the customer service response equipment extracts the label corresponding to the slot according to the historical problem content and updates the slot pool.
Optionally, the customer service response device stores the content of the historical problem, the slot corresponding to the label which is not included in the slot pool extracted from the content of the historical problem can be updated to the slot pool, so that more labels and slots corresponding to the content of the user problem can be collected, various user problems can be solved, the slot corresponding to the label of which the occurrence frequency is greater than a preset threshold value can be added to the slot pool, and the updating of the slot pool is realized on the basis of saving the storage space.
The customer service response equipment updates the slot pool according to the historical problem content of the user, so that the labels in the slot pool are more suitable for interactive response of the user and the customer service, the key information acquisition efficiency is further improved, and the user experience is improved.
Fig. 7 is a schematic flowchart of another customer service response method according to an embodiment of the present application, where fig. 7 is based on fig. 6, and further before S205, the method further includes:
s601: the customer service response equipment outputs confirmation information to the user, wherein the confirmation information is used for confirming whether the intention of the user is correct or not.
Optionally, the manner of outputting the confirmation information to the user by the customer service response device may be voice or text, which is not specifically limited in the present application.
For example, as shown in fig. 8, fig. 8 is a user interface diagram of another customer service response device provided in an embodiment of the present application, where the customer service response device interacts with a user in a text form, before the customer service response device obtains an answer corresponding to a target instruction according to an intention, the customer service response device outputs confirmation information to the user to confirm whether the intention is correct or not, for example, the customer service response device obtains, according to the above steps, a monthly total consumption amount of the user, which is the number 150 × 5552 to be inquired, and outputs the answer after the user confirms that the intention is correct. It is to be understood that fig. 8 shows only one form of the user interface for convenience of example, and the display form of the user interface is not particularly limited by the present invention.
S602: the customer service response device receives response information of the user, wherein the response information is used for indicating that the intention is correct.
Optionally, if the user indicates that the intention determined by the customer service response device is not the intention intended by the user, that is, the user gives a negative option, then the customer service response device may output other intentions determined by the keyword combination to confirm to the user whether the other intentions are correct, may select the intentions according to the order of matching degree with the preset instruction to confirm, and may also output the question to confirm according to the number of times of inquiry of the intentions in the historical question.
Optionally, if the user selects incorrectly for multiple times, the filled slot interface configuration may be called to obtain more keywords from the user for slot filling.
According to the method and the device, whether the intention corresponding to the target instruction is correct can be determined for the user by the customer service response device, the target instruction determined by the customer service response device can be confirmed for the user before the answer to the question is output, the problem answer which the user does not want to inquire can be avoided being given, the answer which the user wants to obtain is obtained, the accuracy of customer service response is further improved, and the user experience is improved.
Fig. 9 is a schematic structural diagram of a customer service answering device according to an embodiment of the present application, and as shown in fig. 9, the device according to the present embodiment includes:
a first receiving module 901, configured to receive question content input by a user.
Wherein, the question content comprises at least two keywords.
A first obtaining module 902, configured to obtain all keywords in the question content.
A determining module 903, configured to determine a target instruction of the user according to the tags of all the keywords.
And the processing module 904 is configured to perform slot filling processing on the target instruction according to the keyword, and determine the intention of the user.
The second obtaining module 905 is configured to obtain an answer corresponding to the target instruction according to the intention.
Optionally, the determining module 903 is specifically configured to:
randomly combining the labels corresponding to all the keywords; each combination is matched against a preset instruction set.
Wherein, the instruction set comprises at least one instruction; and determining the instruction with the highest matching degree as a target instruction of the user.
Optionally, the first obtaining module 902 is specifically configured to: and acquiring the keywords corresponding to the labels in the question content according to the labels corresponding to the grooves in the groove pool, wherein the groove pool comprises at least two grooves.
Optionally, the method further includes:
and the updating module 906 is configured to extract the label corresponding to the slot according to the content of the historical problem, and update the slot pool.
Optionally, the method further includes:
an output module 907, configured to output confirmation information to the user, where the confirmation information is used for the user to confirm whether the intention is correct.
A second receiving module 908, configured to receive response information of the user, where the response information is used to indicate that the intention is correct.
Fig. 10 is a schematic structural diagram of a customer service answering device according to an embodiment of the present application. As shown in fig. 10, the customer service response apparatus includes: a processor 101 and a memory 102.
The memory 102 stores computer-executable instructions.
The processor 101 executes computer-executable instructions stored by the memory 102 to cause the processor 102 to perform the customer service response method described above.
Optionally, the debugging device of the test vector of the chip further includes: and a transceiver 103 for enabling communication with other network devices or terminal devices.
The customer service response device of the embodiment of the present application may be configured to execute the technical solutions in the method embodiments of the present application, and the implementation principle and the technical effect are similar, which are not described herein again.
An embodiment of the present application further provides a computer-readable storage medium, where a computer executing instruction is stored in the computer-readable storage medium, and the computer executing instruction is used for implementing any one of the above customer service response methods when executed by a processor.
The embodiment of the present application further provides a computer program product, where the program product includes computer executable instructions, and the computer executable instructions are executed by a processor to implement any one of the above-mentioned customer service response methods.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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, may be located in one place, or may be 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, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (12)
1. A customer service response method, comprising:
receiving question content input by a user, wherein the question content comprises at least two keywords;
acquiring all keywords in the question content;
determining a target instruction of a user according to the labels of all the keywords;
performing slot filling processing on the target instruction according to the keywords to determine the intention of the user;
and obtaining an answer corresponding to the target instruction according to the intention.
2. The method of claim 1, wherein determining the target instruction of the user according to the labels of all the keywords comprises:
randomly combining the labels corresponding to all the keywords;
matching each combination with a preset instruction set, wherein the instruction set comprises at least one instruction;
and determining the instruction with the highest matching degree as a target instruction of the user.
3. The method of claim 2, wherein the obtaining all keywords in the question content comprises:
and acquiring the keywords corresponding to the labels in the question content according to the labels corresponding to the slots in a slot pool, wherein the slot pool comprises at least two slots.
4. The method according to claim 3, wherein before obtaining the keyword corresponding to the tag in the question content according to the tag corresponding to each slot in the slot pool, the method further comprises:
and extracting the label corresponding to the slot according to the historical problem content, and updating the slot pool.
5. The method according to claim 4, wherein before obtaining the answer corresponding to the target instruction according to the intention, further comprising:
outputting confirmation information to the user, wherein the confirmation information is used for confirming whether the intention is correct or not by the user;
and receiving response information of the user, wherein the response information is used for indicating that the intention is correct.
6. A customer service response apparatus, comprising:
the system comprises a first receiving module, a second receiving module and a display module, wherein the first receiving module is used for receiving question contents input by a user, and the question contents comprise at least two keywords;
the first acquisition module is used for acquiring all keywords in the question content;
the determining module is used for determining a target instruction of the user according to the labels of all the keywords;
the processing module is used for performing slot filling processing on the target instruction according to the keyword to determine the intention of the user;
and the second acquisition module is used for acquiring the answer corresponding to the target instruction according to the intention.
7. The apparatus of claim 6, wherein the determining module is specifically configured to:
randomly combining the labels corresponding to all the keywords;
matching each combination with a preset instruction set, wherein the instruction set comprises at least one instruction;
and determining the instruction with the highest matching degree as a target instruction of the user.
8. The apparatus of claim 7, wherein the first obtaining module is specifically configured to:
and acquiring the keywords corresponding to the labels in the question content according to the labels corresponding to the slots in a slot pool, wherein the slot pool comprises at least two slots.
9. The apparatus of claim 8, further comprising:
and the updating module is used for extracting the label corresponding to the slot according to the historical problem content and updating the slot pool.
10. The apparatus of claim 9, further comprising:
the output module is used for outputting confirmation information to the user, and the confirmation information is used for confirming whether the intention is correct or not by the user;
and the second receiving module is used for receiving response information of the user, and the response information is used for indicating that the intention is correct.
11. A customer service answering device comprising: a memory and a processor;
the memory is to store computer instructions; the processor is configured to execute the computer instructions stored by the memory to implement the customer service response method of any one of claims 1 to 5.
12. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the customer service response method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678454.XA CN111914073A (en) | 2020-07-15 | 2020-07-15 | Customer service response method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010678454.XA CN111914073A (en) | 2020-07-15 | 2020-07-15 | Customer service response method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914073A true CN111914073A (en) | 2020-11-10 |
Family
ID=73281569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010678454.XA Pending CN111914073A (en) | 2020-07-15 | 2020-07-15 | Customer service response method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914073A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925975A (en) * | 2021-01-27 | 2021-06-08 | 长沙市到家悠享网络科技有限公司 | Household service recommendation method, equipment and storage medium |
| CN117828064B (en) * | 2024-03-05 | 2024-05-28 | 之江实验室 | Question-answering system and construction method thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808695A (en) * | 2016-03-03 | 2016-07-27 | 陈包容 | Method and device for obtaining chat reply contents |
| CN106126516A (en) * | 2016-05-31 | 2016-11-16 | 刘华英 | Man-machine interaction method and system |
| CN106649405A (en) * | 2015-11-04 | 2017-05-10 | 陈包容 | Method and device for acquiring reply prompt content of chat initiating sentence |
| CN107220912A (en) * | 2017-06-12 | 2017-09-29 | 上海市高级人民法院 | Litigation services intelligence system and robot |
| CN108170792A (en) * | 2017-12-27 | 2018-06-15 | 北京百度网讯科技有限公司 | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence |
| CN109033305A (en) * | 2018-07-16 | 2018-12-18 | 深圳前海微众银行股份有限公司 | Question answering method, equipment and computer readable storage medium |
| CN109815326A (en) * | 2019-01-24 | 2019-05-28 | 网易（杭州）网络有限公司 | Dialog control method and device |
| CN111241260A (en) * | 2020-01-08 | 2020-06-05 | 平安科技（深圳）有限公司 | Data processing method, device and equipment based on human-computer interaction and storage medium |
-
2020
- 2020-07-15 CN CN202010678454.XA patent/CN111914073A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649405A (en) * | 2015-11-04 | 2017-05-10 | 陈包容 | Method and device for acquiring reply prompt content of chat initiating sentence |
| CN105808695A (en) * | 2016-03-03 | 2016-07-27 | 陈包容 | Method and device for obtaining chat reply contents |
| CN106126516A (en) * | 2016-05-31 | 2016-11-16 | 刘华英 | Man-machine interaction method and system |
| CN107220912A (en) * | 2017-06-12 | 2017-09-29 | 上海市高级人民法院 | Litigation services intelligence system and robot |
| CN108170792A (en) * | 2017-12-27 | 2018-06-15 | 北京百度网讯科技有限公司 | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence |
| CN109033305A (en) * | 2018-07-16 | 2018-12-18 | 深圳前海微众银行股份有限公司 | Question answering method, equipment and computer readable storage medium |
| CN109815326A (en) * | 2019-01-24 | 2019-05-28 | 网易（杭州）网络有限公司 | Dialog control method and device |
| CN111241260A (en) * | 2020-01-08 | 2020-06-05 | 平安科技（深圳）有限公司 | Data processing method, device and equipment based on human-computer interaction and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 声智科技: "《智能语音开发》", 北京航空航天大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925975A (en) * | 2021-01-27 | 2021-06-08 | 长沙市到家悠享网络科技有限公司 | Household service recommendation method, equipment and storage medium |
| CN117828064B (en) * | 2024-03-05 | 2024-05-28 | 之江实验室 | Question-answering system and construction method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11934394B2 (en) | Data query method supporting natural language, open platform, and user terminal | |
| AU2012238229B2 (en) | Multi-modal customer care system | |
| US11379183B2 (en) | System and method for providing a response to a user query using a visual assistant | |
| US20130094633A1 (en) | Method and apparatus for enhancing an interactive voice response (ivr) system | |
| CN103377652A (en) | Method, device and equipment for carrying out voice recognition | |
| CN110941708B (en) | Intelligent question and answer library establishing method, intelligent question and answer method and device and computer equipment | |
| CN110096655A (en) | Sort method, device, equipment and the storage medium of search result | |
| CN109582760A (en) | A kind of response flow engine system applied in Intelligent dialogue system | |
| US10068007B1 (en) | Interface between a virtual personal assisitant and an interactive voice response system | |
| CN111914073A (en) | Customer service response method, device, equipment and storage medium | |
| CN106709018A (en) | Method and device for hitting preset problems | |
| CN110717012A (en) | Method, device, equipment and storage medium for recommending grammar | |
| CN108595141A (en) | Pronunciation inputting method and device, computer installation and computer readable storage medium | |
| US11729315B2 (en) | Interactive voice response (IVR) for text-based virtual assistance | |
| US11100928B2 (en) | Configuration for simulating an interactive voice response system for language interpretation | |
| US20200322293A1 (en) | Information processing system and method | |
| CN109299240B (en) | Chat robot knowledge display method and device | |
| CN109446311B (en) | Chat enhancement method, device, storage medium and terminal | |
| CN114500481A (en) | Service request processing method, system and device | |
| EP3244333A1 (en) | Method and device for concealing personal information on calling interface | |
| CN112071313A (en) | Voice broadcasting method and device, electronic equipment and medium | |
| EP4092996A1 (en) | System and method for personalizing the language associated with outbound calls | |
| CN115529387A (en) | Service index generation method, device, server and storage medium | |
| CN113076413A (en) | Parameter association service method, system, device and storage medium | |
| US20200366790A1 (en) | Configuration for transitioning a communication from an automated system to a simulated live customer agent |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201110 |