CN111225115A - Information providing method and device - Google Patents
Information providing method and device Download PDFInfo
- Publication number
- CN111225115A CN111225115A CN201911165888.3A CN201911165888A CN111225115A CN 111225115 A CN111225115 A CN 111225115A CN 201911165888 A CN201911165888 A CN 201911165888A CN 111225115 A CN111225115 A CN 111225115A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- text
- voice
- seat terminal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- 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
-
- 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
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The invention provides an information providing method and device, wherein the method comprises the following steps: judging whether service information matched with voice data of a user exists or not, if not, sending text information corresponding to the voice data to the target seat terminal, executing a first step, continuing to interact with the user, and in the process of executing the first step, when receiving a service identifier corresponding to the text information and fed back by the target seat terminal, acquiring a response text matched with the service identifier in a preset response text list, synthesizing the response text into voice information, and providing the voice information for the user. Therefore, when the service information matched with the voice data of the user does not exist, the text information corresponding to the voice information is sent to the target seat terminal, so that a seat can conveniently select the corresponding service identifier according to the text information, the number of times of interaction with the user is reduced, meanwhile, the interaction with the user is continued, and the user experience is improved.
Description
Technical Field
The invention relates to the field of telephone banking, in particular to an information providing method and device.
Background
Telephone bank realizes that the user is closely connected with the bank through the telephone, so that the user does not need to go to the bank, and services such as inquiry, password modification, loss report and the like provided by the telephone bank can be obtained only by dialing the telephone number of the telephone bank.
At present, a telephone bank provides business services for a user by using a voice navigation system, wherein the voice navigation system identifies the user intention based on the voice of the user and broadcasts the business corresponding to the user intention to the user in a voice mode, and the same intention has a plurality of expression modes due to different expression habits of the user, so that the voice navigation system may have the situation that the user intention cannot be correctly identified, namely the situation that business information stored in the system in advance is not matched with the identified user intention. In the prior art, when the voice navigation system cannot correctly recognize the user intention, the system returns a fixed prompt voice to guide the user to continue interaction, so that the user repeatedly performs voice input, and the user experience is poor.
Disclosure of Invention
The invention provides an information providing method and device, and aims to solve the problem that when the user intention cannot be correctly recognized, a fixed prompt voice is returned to guide a user to continue interaction, so that the user repeatedly inputs voice, and the user experience is poor.
In order to achieve the purpose, the invention provides the following technical scheme:
an information providing method applied to a voice navigation system, the method comprising:
judging whether business information matched with voice data of a user exists or not;
if the service identifier does not exist, determining a target seat terminal, and sending text information corresponding to the voice data of the user to the target seat terminal so that an operator can select a corresponding service identifier according to the text information;
performing a first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
in the process of executing the first step, when a service identifier corresponding to the text message and fed back by the target agent terminal is received, acquiring a response text matched with the service identifier in a preset response text list;
and synthesizing the response text into voice information and providing the voice information to the user.
The above method, optionally, further includes:
if business information matched with the voice data of the user exists, acquiring a response text matched with a business identifier of the business information in a preset response text list;
and synthesizing the response text into voice information and providing the voice information to the user.
Optionally, the determining whether the service information matched with the voice data of the user exists includes:
acquiring voice data of a user;
recognizing the voice data to obtain text information corresponding to the voice data;
acquiring a user intention contained in the text information;
and judging whether business information matched with the user intention exists or not.
Optionally, the method for acquiring the user intention included in the text information includes:
and inputting the text information into a pre-constructed intention recognition model to obtain the user intention contained in the text information.
Optionally, the method for determining the target agent terminal includes:
acquiring running state information of each artificial seat terminal associated with the voice navigation system;
for each artificial seat terminal, judging whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state, if so, determining the artificial seat terminal as a first seat terminal;
and selecting one first seat terminal from all the first seat terminals as a target seat terminal according to a preset selection strategy.
An information providing apparatus applied to a voice navigation system, the apparatus comprising:
the judging unit is used for judging whether business information matched with the voice data of the user exists or not;
the sending unit is used for determining a target seat terminal if the service identifier does not exist, and sending the text information corresponding to the voice data of the user to the target seat terminal so that an operator can select a corresponding service identifier according to the text information;
an execution unit for executing the first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
a first obtaining unit, configured to, in the process of executing the first step, obtain a response text in a preset response text list, where the response text matches the service identifier, when the service identifier corresponding to the text information and fed back by the target agent terminal is received; and synthesizing the response text into voice information and providing the voice information to the user.
The above apparatus, optionally, further comprises:
the second acquisition unit is used for acquiring a response text matched with the service identifier of the service information in a preset response text list if the service information matched with the voice data of the user exists;
and the providing unit is used for synthesizing the response text into voice information and providing the voice information to the user.
The above apparatus, optionally, the determining unit includes:
the first acquisition subunit is used for acquiring voice data of a user;
the identification subunit is used for identifying the voice data and obtaining text information corresponding to the voice data;
a second acquiring subunit, configured to acquire a user intention included in the text information;
and the first judgment subunit is used for judging whether the service information matched with the user intention exists or not.
The above apparatus, optionally, the second obtaining subunit includes:
and the input subunit is used for inputting the text information into a pre-constructed intention recognition model to obtain the user intention contained in the text information.
The above apparatus, optionally, the sending unit includes:
the third acquisition subunit is used for acquiring the running state information of each artificial seat terminal associated with the voice navigation system;
the second judgment subunit is configured to judge, for each artificial seat terminal, whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state, and if so, determine the artificial seat terminal as the first seat terminal;
and the selecting subunit is used for selecting one first agent terminal from the first agent terminals as a target agent terminal according to a preset selecting strategy.
A storage medium comprising stored instructions, wherein the instructions, when executed, control a device on which the storage medium resides to perform the above-described information providing method.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the above-described information providing method.
Compared with the prior art, the invention has the following advantages:
the invention provides an information providing method and device, wherein the method comprises the following steps: judging whether service information matched with voice data of a user exists or not, if not, determining a target seat terminal, sending text information corresponding to the voice data of the user to the target seat terminal, and executing a first step. According to the technical scheme provided by the invention, when the service information matched with the voice data of the user does not exist, the text information corresponding to the voice information is sent to the target seat terminal, so that a seat worker can select the corresponding service identifier according to the text information, the interaction times with the user are reduced, meanwhile, the interaction with the user is continued according to the preset response text, and the user experience is improved.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method of providing information according to the present invention;
FIG. 2 is a flow chart of another method of an information providing method according to the present invention;
FIG. 3 is a flow chart of another method of an information providing method according to the present invention;
FIG. 4 is a flow chart illustrating interaction among modules of a voice navigation system according to the present invention;
FIG. 5 is a schematic structural diagram of an information providing apparatus according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
The embodiment of the invention provides an information providing method, which can be applied to various system platforms, wherein an execution main body of the information providing method can be a voice navigation system operated in a telephone bank, and a flow chart of the information providing method is shown in figure 1 and specifically comprises the following steps:
s101, judging whether business information matched with the voice data of the user exists or not.
In the method provided by the embodiment of the invention, when the voice data of the user is received, whether the service information matched with the voice data exists in the voice navigation system is judged.
Optionally, the voice navigation system pre-stores a corresponding relationship between the user intention and the service information, that is, the voice navigation system pre-stores a plurality of user intentions, determines whether there is service information matching the voice data, may be that the user intention is recognized based on the voice data of the user, the recognized user intention is matched with the pre-stored user intention based on the recognized user intention, if there is no pre-stored user intention matching the recognized user intention, it is determined that there is no service information matching the voice data of the user in the voice navigation system, step S102 is executed, and if there is a pre-stored user intention matching the recognized user intention, it is determined that there is service information matching the voice data of the user in the voice navigation system, step S103 is executed.
S102, determining a target agent terminal, sending text information corresponding to voice data of a user to the target agent terminal, and executing the first step.
In the method provided by the embodiment of the invention, each artificial seat terminal associated with the voice navigation system is determined, and a target seat terminal is determined from each artificial seat terminal. The method comprises the steps of sending text information corresponding to voice data of a user to a target agent terminal so that an agent of the target agent terminal can select a corresponding service identifier according to the text information, optionally displaying the text information corresponding to the voice data in the target agent terminal in a pop-up box mode, optionally presetting a service identifier selection list in each manual agent terminal, and directly selecting the service identifier corresponding to the text information in the service identifier selection list by the agent.
Optionally, when sending the text information corresponding to the voice data to the target agent terminal, a first step is performed, where the first step includes: inquiring the user according to a preset response text, judging whether service information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to a target seat terminal, returning and executing the step of inquiring the user according to the preset response text, namely, continuously interacting with the user while sending the text information corresponding to the voice data to the target seat terminal, avoiding long-time waiting of the user, interacting with the user based on the preset response text, judging whether the service information corresponding to the response information exists or not according to the response information fed back by the user in the interaction process, if not, sending the text information corresponding to the response information to the target seat terminal, and optionally, overlapping the text information corresponding to the response information of the user on the target seat terminal in the form of a pop-up box, so that the seat staff can accurately decide the corresponding service node based on the plurality of text messages.
Optionally, in the process of executing the first step, monitoring whether a service identifier fed back by the target agent terminal is received in real time, and when the service identifier fed back by the target agent terminal is received, determining whether the service identifier is overtime, where the condition that the service identifier is overtime includes that before the service identifier is received, service information corresponding to the response information is found based on response information of the user. If the service identifier is judged to be overtime, the task processing is not carried out, and if the service identifier is judged not to be overtime, the step S103 is executed.
S103, acquiring a response text matched with the service identifier in a preset response text list.
In the method provided by the embodiment of the invention, if the voice navigation system has the service information matched with the voice data of the user, the service identifier of the service information is determined, the response text matched with the service identifier of the service information is obtained from the preset response file list, and if the service identifier fed back by the target seat terminal is received in the process of executing the first step and the service identifier is not overtime, the response text matched with the service identifier fed back by the target seat terminal in the preset response text list is obtained.
Optionally, the voice navigation system prestores a corresponding relationship between the service identifier and the response text, and the response text matched with the service identifier can be found through the service identifier.
And S104, synthesizing the response text into voice information, and providing the voice information for the user.
In the method provided by the embodiment of the present invention, the response text is synthesized into the speech information, and optionally, the text-to-speech synthesis provided by the present invention is an existing speech synthesis technology, which is not described herein again; and providing the voice information to the user, optionally in a voice broadcast mode, and broadcasting the voice information to the user.
It should be noted that, in the process of executing the first step, that is, in the process of continuing the interaction with the user, if the service information matched with the response information of the user is identified based on the response information of the user before receiving the service identifier fed back by the target agent terminal, the response text matched with the service identifier of the service information is acquired, and the response text is synthesized into the voice information, so as to provide the voice information to the user.
The information providing method provided by the embodiment of the invention judges whether the service information matched with the voice data of the user exists or not, if not, the target seat terminal is determined, the text information corresponding to the voice data of the user is sent to the target seat terminal, and the first step is executed. By applying the information providing method provided by the embodiment of the invention, when the service information matched with the voice data of the user does not exist, the text information corresponding to the voice information is sent to the target seat terminal, so that a seat person can select the corresponding service identifier according to the text information, the interaction times with the user are reduced, meanwhile, the interaction with the user is continued according to the preset response text, and the user experience is improved.
In the embodiment of the present invention, the step S101 disclosed in fig. 1 determines whether there is service information matched with the voice data of the user, and the flowchart is shown in fig. 2, and specifically includes the following steps:
s201, voice data of a user are obtained.
In the method provided by the embodiment of the invention, the voice data of the user is acquired, and the voice data comprises the user intention.
S202, recognizing the voice data and obtaining text information corresponding to the voice data.
Optionally, in the method provided by the embodiment of the present invention, converting the voice data into the text information is prior art and is not described herein again.
S203, obtaining the user intention contained in the text information.
In the method provided by the embodiment of the present invention, the user intention included in the text information is obtained based on the text information, and optionally, the text information may be input into a pre-constructed intention recognition model to obtain the user intention included in the text information.
It should be noted that the present invention can also identify the user intention contained in the text information in other manners, which are not described herein.
And S204, judging whether business information matched with the user intention exists or not.
In the method provided by the embodiment of the invention, whether the service information matched with the user intention exists in the voice navigation system is judged based on the user intention, it should be noted that the voice navigation system stores the corresponding relation between the user intention and the service information in advance, the service information matched with the identified user intention exists is judged by comparing the identified user intention with the pre-stored user intention, if the identified user intention is consistent with the pre-stored user intention, the service information matched with the identified user intention exists, and if the identified user intention is inconsistent with the pre-stored user intention, the service information matched with the identified user intention does not exist.
In the information providing method provided by the embodiment of the invention, voice data is converted into text information, the user intention is identified based on the text information, and whether business information matched with the user intention exists or not is judged based on the user intention.
In the foregoing embodiment of the present invention, step S102 disclosed in fig. 1 relates to determining a target agent terminal, as shown in fig. 3, including the following steps:
s301, acquiring running state information of each artificial agent terminal associated with the voice navigation system.
In the method provided by the embodiment of the invention, the language navigation system is associated with a plurality of artificial seat terminals to obtain the running state information of each artificial seat terminal, wherein the running state information is used for representing the current state of the artificial seat terminal.
S302, judging whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state or not aiming at each artificial seat terminal, and if so, determining the artificial seat terminal as a first seat terminal.
In the method provided by the embodiment of the invention, whether the running state of each artificial seat terminal represents that the current running state of the artificial seat terminal is the working state is judged, optionally, if the artificial seat terminal is started and is in the ready state, the current running state of the artificial seat terminal is the working state, and if the artificial seat terminal is not started or is started but is not in the ready state, the current running state of the artificial seat terminal is the non-working state; and if the operating state of the artificial seat terminal is the working state, determining the artificial seat terminal as a first seat terminal.
And S303, selecting one first agent terminal from all the first agent terminals as a target agent terminal according to a preset selection strategy.
In the method provided by the embodiment of the invention, one first seat terminal is selected from all the first seat terminals as a target seat terminal according to a preset selection strategy.
Optionally, when the determined number of the first agent terminals is one, the first agent terminal is used as a target agent terminal. When a plurality of first seat terminals are determined, a polling mode can be adopted to select one first seat terminal as a target seat terminal, that is, if there are 4 first seat terminals, namely a first seat terminal a, a first seat terminal B, a first seat terminal C and a first seat terminal D, respectively, then a is currently used as the target seat terminal, and then the target seat terminal is determined from B, C and D next time; optionally, the priority of each human agent terminal may also be preset, and the target agent terminal is determined according to the sequence of the priority from high to low or from low to high.
It should be noted that the preset selection policy mentioned in the embodiment of the present invention is not limited to the manner of polling or setting priority provided above, and the implementation of the embodiment of the present invention is not affected by the difference of the selection policies.
The information providing method provided by the embodiment of the invention comprises the steps of obtaining the running state information of each artificial seat terminal, determining the artificial seat terminal with the running state information representing the working state as the first seat terminal, and determining the target seat terminal from each first seat terminal according to a preset selection strategy.
The embodiment of the present invention further provides a voice navigation system, which specifically includes: the system comprises a voice synthesis module, a voice navigation module, a voice recognition module, a semantic analysis module and an agent end module, wherein the interaction process in each module is shown in fig. 4, and specifically comprises the following steps:
and after receiving the voice data of the user, the voice navigation module sends the voice data to the voice recognition module.
The voice recognition module recognizes the voice data into text information by using the voice recognition engine and transmits the text information to the voice navigation module.
And after receiving the text information sent by the voice recognition module, the voice navigation module sends the text information to the semantic analysis module.
The semantic analysis module performs semantic recognition on the text information to obtain a semantic recognition result corresponding to the text information, namely, to obtain a user intention contained in the text information, and judges whether business information matched with the semantic recognition result exists or not, if so, the business identifier of the business information is sent to the voice navigation module, if not, a preset first identifier is sent to the voice navigation module, and optionally, the first identifier is used for indicating that no business information matched with the semantic recognition result exists.
When receiving the identification information sent by the semantic analysis module, the voice navigation system judges whether the identification information is a service identification, if so, a response text corresponding to the service identification is obtained and fed back to the voice synthesis module, and the voice synthesis module synthesizes the response text into voice to broadcast to a user; if not, the text information is sent to the seat end module, interaction with the user is continued, the seat end module feeds back a service identifier corresponding to the text information to the voice navigation module, the voice navigation module obtains a response text corresponding to the service identifier and feeds the response text back to the voice synthesis module when receiving the service identifier, and the voice synthesis module synthesizes the response text into voice and broadcasts the response text to the user.
Corresponding to the method described in fig. 1, an embodiment of the present invention further provides an information providing apparatus, which is used for implementing the method in fig. 1 specifically, and a schematic structural diagram of the information providing apparatus is shown in fig. 5, and specifically includes:
a judging unit 501, configured to judge whether there is service information matched with voice data of a user;
a sending unit 502, configured to determine a target agent terminal if the service identifier does not exist, and send text information corresponding to the voice data of the user to the target agent terminal, so that an agent selects a corresponding service identifier according to the text information;
an execution unit 503 for executing the first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
a first obtaining unit 504, configured to, in the process of executing the first step, obtain, when a service identifier corresponding to the text information and fed back by the target agent terminal is received, a response text in a preset response text list, where the response text matches the service identifier; and synthesizing the response text into voice information and providing the voice information to the user.
The information providing device provided by the embodiment of the invention judges whether the service information matched with the voice data of the user exists or not, if not, the target seat terminal is determined, the text information corresponding to the voice data of the user is sent to the target seat terminal, and the first step is executed. By applying the information providing device provided by the embodiment of the invention, when the service information matched with the voice data of the user does not exist, the text information corresponding to the voice information is sent to the target seat terminal, so that a seat person can select the corresponding service identifier according to the text information, the interaction times with the user are reduced, meanwhile, the interaction with the user is continued according to the preset response text, and the user experience is improved.
In an embodiment of the present invention, based on the foregoing solution, the method may further include:
the second acquisition unit is used for acquiring a response text matched with the service identifier of the service information in a preset response text list if the service information matched with the voice data of the user exists;
and the providing unit is used for synthesizing the response text into voice information and providing the voice information to the user.
In an embodiment of the present invention, based on the foregoing scheme, the determining unit 501 is configured to:
the first acquisition subunit is used for acquiring voice data of a user;
the identification subunit is used for identifying the voice data and obtaining text information corresponding to the voice data;
a second acquiring subunit, configured to acquire a user intention included in the text information;
and the first judgment subunit is used for judging whether the service information matched with the user intention exists or not. In an embodiment of the present invention, based on the foregoing solution, the second obtaining subunit is configured to:
and the input subunit is used for inputting the text information into a pre-constructed intention recognition model to obtain the user intention contained in the text information.
In an embodiment of the present invention, based on the foregoing scheme, the sending unit 502 is configured to:
the third acquisition subunit is used for acquiring the running state information of each artificial seat terminal associated with the voice navigation system;
the second judgment subunit is configured to judge, for each artificial seat terminal, whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state, and if so, determine the artificial seat terminal as the first seat terminal;
and the selecting subunit is used for selecting one first agent terminal from the first agent terminals as a target agent terminal according to a preset selecting strategy.
The embodiment of the invention also provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the device where the storage medium is located is controlled to execute the information providing method.
An electronic device is provided in an embodiment of the present invention, and the structural diagram of the electronic device is shown in fig. 6, which specifically includes a memory 601 and one or more instructions 602, where the one or more instructions 602 are stored in the memory 601 and configured to be executed by one or more processors 603 to perform the following operations on the one or more instructions 602:
judging whether business information matched with voice data of a user exists or not;
if the service identifier does not exist, determining a target seat terminal, and sending text information corresponding to the voice data of the user to the target seat terminal so that an operator can select a corresponding service identifier according to the text information;
performing a first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
in the process of executing the first step, when a service identifier corresponding to the text message and fed back by the target agent terminal is received, acquiring a response text matched with the service identifier in a preset response text list;
and synthesizing the response text into voice information and providing the voice information to the user.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in a plurality of software and/or hardware when implementing the invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The above detailed description is provided for an information providing method and apparatus, and the principle and the implementation of the present invention are explained by applying specific examples, and the description of the above examples is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An information providing method, applied to a voice navigation system, the method comprising:
judging whether business information matched with voice data of a user exists or not;
if the service identifier does not exist, determining a target seat terminal, and sending text information corresponding to the voice data of the user to the target seat terminal so that an operator can select a corresponding service identifier according to the text information;
performing a first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
in the process of executing the first step, when a service identifier corresponding to the text message and fed back by the target agent terminal is received, acquiring a response text matched with the service identifier in a preset response text list;
and synthesizing the response text into voice information and providing the voice information to the user.
2. The method of claim 1, further comprising:
if business information matched with the voice data of the user exists, acquiring a response text matched with a business identifier of the business information in a preset response text list;
and synthesizing the response text into voice information and providing the voice information to the user.
3. The method according to claim 1 or 2, wherein the determining whether the service information matching with the voice data of the user exists comprises:
acquiring voice data of a user;
recognizing the voice data to obtain text information corresponding to the voice data;
acquiring a user intention contained in the text information;
and judging whether business information matched with the user intention exists or not.
4. The method according to claim 3, wherein the obtaining of the user intention contained in the text information comprises:
and inputting the text information into a pre-constructed intention recognition model to obtain the user intention contained in the text information.
5. The method of claim 1, wherein the determining a target agent terminal comprises:
acquiring running state information of each artificial seat terminal associated with the voice navigation system;
for each artificial seat terminal, judging whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state, if so, determining the artificial seat terminal as a first seat terminal;
and selecting one first seat terminal from all the first seat terminals as a target seat terminal according to a preset selection strategy.
6. An information providing apparatus, applied to a voice navigation system, the apparatus comprising:
the judging unit is used for judging whether business information matched with the voice data of the user exists or not;
the sending unit is used for determining a target seat terminal if the service identifier does not exist, and sending the text information corresponding to the voice data of the user to the target seat terminal so that an operator can select a corresponding service identifier according to the text information;
an execution unit for executing the first step; the first step comprises: inquiring the user according to a preset response text, judging whether business information corresponding to the response information exists or not when receiving the response information of the user responding to the inquiry, if not, sending the text information corresponding to the response information to the target seat terminal, and returning to execute the step of inquiring the user according to the preset response text;
a first obtaining unit, configured to, in the process of executing the first step, obtain a response text in a preset response text list, where the response text matches the service identifier, when the service identifier corresponding to the text information and fed back by the target agent terminal is received; and synthesizing the response text into voice information and providing the voice information to the user.
7. The apparatus of claim 6, further comprising:
the second acquisition unit is used for acquiring a response text matched with the service identifier of the service information in a preset response text list if the service information matched with the voice data of the user exists;
and the providing unit is used for synthesizing the response text into voice information and providing the voice information to the user.
8. The apparatus according to claim 6 or 7, wherein the determining unit comprises:
the first acquisition subunit is used for acquiring voice data of a user;
the identification subunit is used for identifying the voice data and obtaining text information corresponding to the voice data;
a second acquiring subunit, configured to acquire a user intention included in the text information;
and the first judgment subunit is used for judging whether the service information matched with the user intention exists or not.
9. The apparatus of claim 8, wherein the second obtaining subunit comprises:
and the input subunit is used for inputting the text information into a pre-constructed intention recognition model to obtain the user intention contained in the text information.
10. The apparatus of claim 6, wherein the sending unit comprises:
the third acquisition subunit is used for acquiring the running state information of each artificial seat terminal associated with the voice navigation system;
the second judgment subunit is configured to judge, for each artificial seat terminal, whether the running state information of the artificial seat terminal represents that the current running state of the artificial seat terminal is a working state, and if so, determine the artificial seat terminal as the first seat terminal;
and the selecting subunit is used for selecting one first agent terminal from the first agent terminals as a target agent terminal according to a preset selecting strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911165888.3A CN111225115B (en) | 2019-11-25 | 2019-11-25 | Information providing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911165888.3A CN111225115B (en) | 2019-11-25 | 2019-11-25 | Information providing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111225115A true CN111225115A (en) | 2020-06-02 |
| CN111225115B CN111225115B (en) | 2021-06-25 |
Family
ID=70832102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911165888.3A Active CN111225115B (en) | 2019-11-25 | 2019-11-25 | Information providing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111225115B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111613226A (en) * | 2020-06-04 | 2020-09-01 | 中国银行股份有限公司 | Voice interaction method and device and test robot |
| CN114489557A (en) * | 2021-12-15 | 2022-05-13 | 青岛海尔科技有限公司 | Voice interaction method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004297595A (en) * | 2003-03-27 | 2004-10-21 | Nippon Telegr & Teleph Corp <Ntt> | Ivr device, telephone connection method, program for ivr device and storage medium in which program for ivr device is stored |
| KR20160029242A (en) * | 2014-09-04 | 2016-03-15 | 에스케이텔레콤 주식회사 | Method And Apparatus For Extracting Customer |
| CN105577529A (en) * | 2015-12-30 | 2016-05-11 | 上海智臻智能网络科技股份有限公司 | Robot customer service, and customer service method and intelligent customer service system thereof |
| CN109887525A (en) * | 2019-01-04 | 2019-06-14 | 平安科技（深圳）有限公司 | Intelligent customer service method, apparatus and computer readable storage medium |
| CN110162611A (en) * | 2019-04-23 | 2019-08-23 | 苏宁易购集团股份有限公司 | A kind of intelligent customer service answer method and system |
| CN110266899A (en) * | 2019-06-11 | 2019-09-20 | 平安科技（深圳）有限公司 | The recognition methods and customer service system that client is intended to |
| CN110300234A (en) * | 2018-03-21 | 2019-10-01 | 上海易谷网络科技股份有限公司 | IVR intelligent sound navigation silence seat technology |
-
2019
- 2019-11-25 CN CN201911165888.3A patent/CN111225115B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004297595A (en) * | 2003-03-27 | 2004-10-21 | Nippon Telegr & Teleph Corp <Ntt> | Ivr device, telephone connection method, program for ivr device and storage medium in which program for ivr device is stored |
| KR20160029242A (en) * | 2014-09-04 | 2016-03-15 | 에스케이텔레콤 주식회사 | Method And Apparatus For Extracting Customer |
| CN105577529A (en) * | 2015-12-30 | 2016-05-11 | 上海智臻智能网络科技股份有限公司 | Robot customer service, and customer service method and intelligent customer service system thereof |
| CN110300234A (en) * | 2018-03-21 | 2019-10-01 | 上海易谷网络科技股份有限公司 | IVR intelligent sound navigation silence seat technology |
| CN109887525A (en) * | 2019-01-04 | 2019-06-14 | 平安科技（深圳）有限公司 | Intelligent customer service method, apparatus and computer readable storage medium |
| CN110162611A (en) * | 2019-04-23 | 2019-08-23 | 苏宁易购集团股份有限公司 | A kind of intelligent customer service answer method and system |
| CN110266899A (en) * | 2019-06-11 | 2019-09-20 | 平安科技（深圳）有限公司 | The recognition methods and customer service system that client is intended to |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111613226A (en) * | 2020-06-04 | 2020-09-01 | 中国银行股份有限公司 | Voice interaction method and device and test robot |
| CN111613226B (en) * | 2020-06-04 | 2023-03-31 | 中国银行股份有限公司 | Voice interaction method and device and test robot |
| CN114489557A (en) * | 2021-12-15 | 2022-05-13 | 青岛海尔科技有限公司 | Voice interaction method, device, equipment and storage medium |
| CN114489557B (en) * | 2021-12-15 | 2024-03-22 | 青岛海尔科技有限公司 | Voice interaction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111225115B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10708423B2 (en) | Method and apparatus for processing voice information to determine emotion based on volume and pacing of the voice | |
| US7907705B1 (en) | Speech to text for assisted form completion | |
| CN107454657B (en) | Voice network distribution method | |
| CN110196927B (en) | Multi-round man-machine conversation method, device and equipment | |
| CN105206272A (en) | Voice transmission control method and system | |
| CN108933946B (en) | Voice-control-based live broadcasting attention method, storage medium, electronic equipment and system | |
| CN111225115B (en) | Information providing method and device | |
| CN111583931A (en) | Service data processing method and device | |
| CN106503046B (en) | Interaction method and system based on intelligent robot | |
| CN111885341A (en) | Voice acquisition method and device in video call process, computer equipment and medium | |
| CN111261151A (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN105338204A (en) | Interactive voice response method and device | |
| CN109902163B (en) | Intelligent response method, device, equipment and storage medium | |
| CN104010097A (en) | Multimedia communication system and method based on traditional PSTN call | |
| CN111510563A (en) | Intelligent outbound method and device, storage medium and electronic equipment | |
| CN111048091A (en) | Voice recognition method, voice recognition equipment and computer readable storage medium | |
| CN104732982A (en) | Method and device for recognizing voice in interactive voice response (IVR) service | |
| CN106371905B (en) | Application program operation method and device and server | |
| CN112908330B (en) | Voice wake-up method and device for terminal equipment and computer readable storage medium | |
| CN114067842B (en) | Customer satisfaction degree identification method and device, storage medium and electronic equipment | |
| CN109410926A (en) | Voice method for recognizing semantics and system | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN114202363A (en) | Artificial intelligence based call method, device, computer equipment and medium | |
| CN111292749A (en) | Session control method and device of intelligent voice platform | |
| CN111353771A (en) | Method, device, equipment and medium for remotely controlling payment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |