CN115442480A - Outbound method, device, medium, server and intelligent robot - Google Patents
Outbound method, device, medium, server and intelligent robot Download PDFInfo
- Publication number
- CN115442480A CN115442480A CN202211139410.5A CN202211139410A CN115442480A CN 115442480 A CN115442480 A CN 115442480A CN 202211139410 A CN202211139410 A CN 202211139410A CN 115442480 A CN115442480 A CN 115442480A
- Authority
- CN
- China
- Prior art keywords
- outbound
- identifier
- communication
- list
- intelligent robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000004891 communication Methods 0.000 claims abstract description 193
- 230000000977 initiatory effect Effects 0.000 claims abstract description 27
- 238000012163 sequencing technique Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000001228 spectrum Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/027—Concept to speech synthesisers; Generation of natural phrases from machine-based concepts
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The disclosure provides an outbound method, an outbound device, a media, a server and an intelligent robot, wherein the method comprises the following steps: when the current working scene is an outbound scene, sequencing data to be outbound corresponding to the first identification to obtain an outbound list, wherein the data to be outbound comprises a second identification; generating an outbound command and sending the outbound command to the intelligent robot; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the calling-out instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the calling-out list; and initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy. The method is used for solving a series of defects generated when the intelligent robot is used for assisting manual operation in the prior art, and realizing the purpose of actively controlling the intelligent robot to carry out outbound operation matched with manual outbound.
Description
Technical Field
The disclosure relates to the technical field of human-computer interaction, and in particular relates to an outbound method, an outbound device, an outbound medium, a server and an intelligent robot.
Background
In the industry of carrying out operation by mainly depending on the artificial telephone, in order to reduce the burden of the artificial operation, an intelligent robot is introduced to assist the artificial operation. In the practical application process of the intelligent robot, a customer service worker is required to distribute tasks to the intelligent robot, and the intelligent robot performs outbound operation according to the distributed tasks.
In the prior art, tasks need to be manually allocated to the intelligent robot to trigger the outbound operation of the intelligent robot, and the intelligent robot cannot be automatically controlled to perform the outbound operation. In addition, the experience of the existing intelligent robot for calling out is inconsistent with the experience of the manual calling out operation for the client.
Disclosure of Invention
The present disclosure provides an outbound method, an outbound device, a medium, a server and an intelligent robot, which are used to solve a series of defects generated when an intelligent robot is used to assist manual work in the prior art, and realize active control of the intelligent robot to perform outbound operation matched with manual outbound.
The present disclosure provides an outbound method, applied to a server, the method including:
when the current working scene is an outbound scene, sequencing data to be outbound corresponding to a first identifier to obtain an outbound list, wherein the data to be outbound comprises a second identifier, and the first identifier and the second identifier indicate different user roles;
generating an outbound command and sending the outbound command to the intelligent robot;
wherein, the outbound command comprises: the tone type of the first identifier and the outbound list;
the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
According to the outbound method provided by the present disclosure, the sorting the data to be outbound corresponding to the first identifier to obtain an outbound list includes:
acquiring a historical communication record corresponding to the second identifier in the data to be called out;
determining the outbound success rate of each second identifier based on the historical communication records;
and sequencing the second identification in the data to be called out based on the calling out success rate to obtain the calling out list.
According to the outbound method provided by the present disclosure, before the outbound command is generated, the method further comprises:
acquiring audio data corresponding to the first identifier;
inputting the audio data into a voice generation model to obtain target audio data output by the voice generation model and a tone type corresponding to the target audio data;
the target audio data is voice corresponding to the tone of the first identification;
wherein the speech generation model is obtained by training an audio data sample, a target audio data sample and a tone type sample.
According to the outbound method provided by the present disclosure, the inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a tone type corresponding to the target audio data includes:
inputting the audio data into a feature extraction layer of the voice generation model to obtain tone features output by the feature extraction layer;
and inputting the tone features into a voice generation layer of the voice generation model to obtain the target audio data output by the voice generation layer and the tone type corresponding to the target audio data.
According to the outbound method provided by the present disclosure, before the generating the outbound command, the method further includes:
acquiring a historical communication record corresponding to the second identifier in the data to be called out;
determining behavior characteristics corresponding to the second identification based on the historical communication records;
and generating a communication strategy corresponding to the behavior characteristics, and sending the communication strategy to the intelligent robot.
The present disclosure provides an outbound method applied to an intelligent robot, the method including:
receiving an outbound command sent by a server, wherein the outbound command comprises: the tone type and the outbound list of the first identifier;
acquiring a communication strategy corresponding to a second identifier in the outbound list, wherein the first identifier and the second identifier indicate different user roles;
and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
According to the outbound method provided by the present disclosure, before the obtaining of the communication policy corresponding to the second identifier in the outbound list, the method further includes:
receiving a communication strategy sent by the server;
storing the communication strategy in a node of a multi-branch tree based on a second identifier corresponding to the communication strategy;
the obtaining of the communication policy corresponding to the second identifier in the outbound list includes:
and determining a target node from the multi-branch tree based on a second identifier in the outbound list, and acquiring the communication strategy from the target node.
According to the outbound method provided by the present disclosure, the determining a target node from the multi-way tree based on a second identifier in the outbound list, and acquiring the communication policy from the target node, includes:
determining an initial target node based on a second identifier in the outbound list, and acquiring an initial communication strategy from the initial target node;
the initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy comprises:
initiating an outbound operation on the second identifier based on the tone type and the initial communication strategy;
after initiating an outbound operation for the second identifier based on the tone type and the initial communication policy, the method further includes:
acquiring a current communication record corresponding to the second identifier;
and determining a current target node from the multi-branch tree based on the current communication record, acquiring the current communication strategy from the current target node, and playing the acquired current communication strategy.
According to the outbound method provided by the present disclosure, the method further comprises:
under the condition that the current working scene is a manual operation scene, acquiring a current communication record corresponding to the second identifier;
and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and recommending the current communication strategy to the first identifier.
The present disclosure also provides an outbound device, comprising:
the sequencing module is used for sequencing the data to be outbound corresponding to the first identifier to obtain an outbound list under the condition that the current working scene is an outbound scene, wherein the data to be outbound comprises a second identifier, and the first identifier and the second identifier indicate different user roles;
the sending module is used for generating an outbound command and sending the outbound command to the intelligent robot;
wherein, the outbound command comprises: the tone type of the first identifier and the outbound list;
the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
The present disclosure also provides an outbound device, comprising:
a receiving module, configured to receive an outbound command sent by a server, where the outbound command includes: the tone type and the outbound list of the first identifier;
an obtaining module, configured to obtain a communication policy corresponding to a second identifier in the outbound list, where the first identifier and the second identifier indicate different user roles;
and the outbound module is used for initiating outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy.
The present disclosure also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the outbound method applied to a server as any one of the above.
The present disclosure also provides a server for implementing the outbound method applied to the server as described in any one of the above.
The present disclosure also provides an intelligent robot, including: the intelligent robot calling-out method comprises a robot body and a controller, wherein the controller is used for realizing the calling-out method applied to the intelligent robot.
According to the outbound method, the outbound device, the media, the server and the intelligent robot, the data to be outbound corresponding to the first identification are sequenced to obtain an outbound list under the condition that the current working scene is an outbound scene, the data to be outbound comprises the second identification, so that the method monitors the working scene in real time, generates the outbound list under the outbound scene, and provides effective data for actively controlling the intelligent robot to initiate outbound operation; further, an outbound command is generated and sent to the intelligent robot, and the intelligent robot is actively controlled to initiate an outbound operation; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the calling-out instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the calling-out list; based on the tone type and the communication strategy, the second identification in the outbound list initiates an outbound operation, and therefore when the intelligent robot performs the outbound operation, the tone consistent with the first identification and the communication strategy matched with the second identification are adopted, and the customer experience is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the present disclosure or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart diagram of an outbound method applied to a server provided by the present disclosure;
fig. 2 is a schematic flow chart diagram of an outbound method applied to an intelligent robot provided by the present disclosure;
FIG. 3 is a schematic structural diagram of an outbound system provided by the present disclosure;
figure 4 is a outbound implementation signaling diagram of an outbound system provided by the present disclosure;
FIG. 5 is a schematic structural diagram of an outbound device provided by the present disclosure;
FIG. 6 is a schematic structural diagram of an outbound device provided by the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device provided by the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present disclosure, belong to the protection scope of the embodiments of the present disclosure.
The outbound method of the embodiments of the present disclosure is described below in conjunction with fig. 1-4.
To clearly illustrate the outbound method disclosed in this document, the following further details the application context:
although the intelligent robot is used for replacing manual operation is a great trend of industry development, a long way is still needed, and how to improve the manual efficiency by using the intelligent robot at the present stage is a big pain point in the industry. Because the intelligent robot outbound service belongs to the intelligent voice service, the intelligent robot outbound service is generally directly distributed to the intelligent robot for processing by a preset model or a responsible person of an organization uniformly controls the initiation of the intelligent robot outbound task.
However, for working scenes such as payment reminding and the like which need to follow up the communication condition of the client for a long time, the two schemes cannot well improve the efficiency and solve the problem. For example, in a repayment reminding scene, a front-line worker has more and more appeal and wants to improve the work efficiency by calling some cases under the name of the intelligent robot, and improve the achievement on the premise of guaranteeing the experience of the client.
In the following, the repayment reminding field is taken as an example for explanation:
under a repayment reminding scene, generally, a case which is just overdue firstly initiates an outbound operation of the intelligent robot through a preset model, and after a period of time, the case which is still overdue is delivered to manual customer service for processing. And the intelligent robot is not driven to exhale any more by the model in the period.
In addition, after the task is allocated to the customer service, the outbound operation of the intelligent robot needs to be initiated manually, the process depends too much on manual experience, and the outbound resource waste can be caused because some new employees cannot be screened effectively. When the intelligent robot initiates an outbound operation, the tone of the intelligent robot is different from the artificial tone, which causes the problem of inconsistent customer experience, and the user experience is not good.
In order to effectively solve the above problem, an embodiment of the present disclosure provides an outbound method applied to a server, as shown in fig. 1, where the method includes:
and 101, sequencing the data to be outbound corresponding to the first identifier to obtain an outbound list under the condition that the current working scene is an outbound scene.
Wherein the data to be called out comprises a second identifier.
The first identifier and the second identifier indicate different user roles, and the first identifier is a customer service identifier, namely an identifier capable of representing a customer service identity role; the second identity is a client identity, i.e. an identity capable of representing the client identity role.
Wherein, the work scene includes: manual work scenarios and outbound scenarios.
Wherein, the outbound scenario includes: the method comprises the following steps of serving a preset scene where a timing task needing an intelligent robot to call out is located, and serving a scene when the client is not located in a manual operation scene on time.
The scene when the customer service is not in the manual operation scene on time is as follows: the customer service manual operation is required in the preset time period, but the customer service is not operated in the time period.
Specifically, whether the current working scene is an outbound scene is judged, and under the condition that the current working scene is judged to be the outbound scene, the data to be outbound corresponding to the first identifier are sequenced to obtain an outbound list; and under the condition that the current working scene is judged to be a manual working scene, receiving a user request input based on the first identifier, and executing operation corresponding to the user request.
In a specific embodiment, a specific implementation manner of obtaining the outbound list is as follows:
acquiring a historical communication record corresponding to a second identifier in the data to be called out; determining the outbound success rate of each second identifier based on the historical communication records; and sequencing the second identifiers in the data to be outbound call based on the outbound call success rate to obtain an outbound call list.
Wherein, historical communication record includes: historical communication records of the customer service and the customer and historical communication records of the intelligent robot and the customer.
Wherein, historical communication record includes: communication time, successful connection, communication duration, communication content and the like.
For the repayment reminding scene, the outbound success rate is used for indicating the repayment probability of the second identifier; for a product promotion scene, the outbound success rate is used for indicating the purchase probability of the second identifier; and the like.
Wherein the second identifier is data capable of uniquely representing the customer information.
Specifically, based on the historical communication records, the call completing rate, the optimal broadcasting time and the optimal broadcasting times corresponding to each second identifier are determined; determining the outbound success rate based on the call completing rate, the optimal broadcasting time and the optimal broadcasting times; and sequencing the second identifiers according to the sequence of big and small based on the successful power of the outbound call to obtain an outbound list.
The outbound list at least comprises a mobile phone number identifier so that the intelligent robot can make outbound based on the mobile phone number identifier.
According to the method and the device, the outbound success rate of each second identifier is determined through the historical communication records so as to sort the second identifiers in the outbound data, and the purpose is to enable the intelligent robot to outbound according to the outbound list, guarantee the effectiveness of outbound operation and improve the overall operation efficiency.
In one embodiment, in order to guarantee user experience, the tone of the intelligent robot during outbound call is consistent with that of customer service. Acquiring audio data corresponding to the first identifier; inputting the audio data into a voice generation model to obtain target audio data output by the voice generation model and a tone type corresponding to the target audio data; the target audio data are voices corresponding to the timbre of the first identification; the voice generation model is obtained through training of the audio data sample, the target audio data sample and the tone type sample.
Wherein each customer service person pre-records audio data.
In a specific embodiment, audio data is input into a feature extraction layer of a speech generation model to obtain tone features output by the feature extraction layer; and inputting the tone characteristics into a voice generation layer of the voice generation model to obtain target audio data output by the voice generation layer and a tone type corresponding to the target audio data.
Among them, the speech generating model of the present disclosure is constituted by a neural network (tacontron 2) and a neural network (waveglow).
In which Tacotron2 is a speech synthesis framework that includes a sonographic prediction network (feature extraction layer) and a vocoder (speech generation layer).
The system comprises a sound spectrum prediction network and a voice recognition network, wherein the sound spectrum prediction network is used for predicting input audio data into a frame sequence of a Mel frequency spectrum, the audio data is represented in a character sequence mode, and the frame sequence of the Mel frequency spectrum is a tone characteristic.
The vocoder is used for generating a time domain waveform from the frame sequence of the predicted Mel frequency spectrum to obtain target audio data.
The speech generation model of the present disclosure is capable of further determining a timbre type corresponding thereto based on the timbre features.
The target audio data generated by the method is very similar to a real person in listening, the user conversation perception value (MOS value) is high in score, for example, 4.5 scores, so that the intelligent robot can send out a tone consistent with customer service when calling out, and the user experience is improved.
In one embodiment, in order to ensure the effectiveness of communication between the intelligent robot and the client, the communication strategy corresponding to the client is configured for the intelligent robot. The method comprises the steps of obtaining a historical communication record corresponding to a second identifier in data to be called out; determining behavior characteristics corresponding to the second identification based on the historical communication records; and generating a communication strategy corresponding to the behavior characteristics, and sending the communication strategy to the intelligent robot.
Wherein, the communication strategy includes: specific communication with the corresponding client, communication types and the like, wherein the communication types comprise: pressure application type and soothing type, etc.
And finally, the intelligent robot carries out outbound calling by adopting tone and ditch conversation corresponding to customer service and tone corresponding to the customer.
Wherein, historical communication record still includes: communication attitude score, communication tone score and communication speech quality score of the client.
And determining the behavior characteristics corresponding to the second identification based on the communication attitude score, the communication tone score and the speaking quality score of the client.
For example, when the behavior characteristics indicate that the second identifier is strong and hard, a communication strategy of an application type corresponding to the second identifier is generated; for another example, when the behavior characteristics indicate that the second identifier shows anxiety, a communication strategy of a placating type corresponding to the second identifier is generated; and the like.
According to the method and the system, the communication strategy corresponding to the behavior characteristics of the client is generated, so that the intelligent robot can communicate with the client through the generated communication strategy, and the communication efficiency is improved.
And 102, generating an outbound command and sending the outbound command to the intelligent robot.
Wherein, the outbound command comprises: the tone type and the outbound list of the first identifier.
The outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation to a second identifier in the outbound list based on the tone type and the communication strategy.
When the customer service does not arrive at post on time, the intelligent robot under the name of the customer service automatically initiates the outbound of the data to be outbound; if the customer service and the client agree on the communication time, automatically initiating an outbound call of the intelligent robot according to the communication time; the method comprises the steps of automatically reserving the active calling-out operation of the intelligent robot, and actively controlling the intelligent robot or automatically initiating the calling-out operation by the intelligent robot when the reservation date is reached.
The outbound method applied to the server, provided by the disclosure, is characterized in that data to be outbound corresponding to a first identifier are sequenced to obtain an outbound list under the condition that a current working scene is an outbound scene, the data to be outbound comprises a second identifier, so that the method can be seen; further, an outbound command is generated and sent to the intelligent robot, so that the intelligent robot is actively controlled to initiate an outbound operation; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the calling-out instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the calling-out list; based on the tone type and the communication strategy, the second identification in the outbound list initiates an outbound operation, and therefore, when the outbound operation is performed by the intelligent robot, the tone consistent with the first identification and the communication strategy matched with the second identification are adopted, and the customer experience is effectively improved.
The embodiment of the present disclosure further provides an outbound method applied to an intelligent robot, as shown in fig. 2, the method includes:
Wherein, the outbound command comprises: the tone type and the outbound list of the first identifier.
Different customer service servers can correspond to one intelligent robot, and one customer service server can also correspond to one intelligent robot.
In a specific embodiment, before an outbound command sent by a server is received, a communication strategy sent by the server is received; storing the communication strategy in the nodes of the multi-branch tree based on the second identification corresponding to the communication strategy; and further, after the outbound command sent by the server is received, determining a target node from the multi-branch tree based on the second identifier in the outbound list, and acquiring a communication strategy from the target node.
The intelligent robot comprises a plurality of intelligent robots, a plurality of multi-branch trees, a second identification, a plurality of nodes and a strategy mark, wherein the multi-branch trees correspond to the second identification, the multi-branch trees comprise the plurality of nodes, and each node comprises a section of communication strategy and the strategy mark corresponding to the communication strategy.
By using the multi-branch tree storage and communication strategy, the layer height of the tree is reduced, the number of traversed nodes is reduced during searching, the data searching speed is increased, and the data searching time is shortened.
In a specific embodiment, a specific implementation manner of obtaining the communication policy is as follows: determining an initial target node based on a second identifier in the outbound list, and acquiring an initial communication strategy from the initial target node; initiating an outbound operation to the second identifier based on the tone type and the initial communication strategy; based on the tone type and the initial communication strategy, after an outbound operation is initiated on the second identifier, a current communication record corresponding to the second identifier is obtained; and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and playing the acquired current communication strategy.
Specifically, when an outbound command is received, an initial communication strategy is obtained from the multi-branch tree based on the second identification; and initiating an outbound operation to the second identifier according to the tone type and the initial communication strategy. And after the call-out is confirmed to be connected, acquiring a current communication record corresponding to the second identifier, analyzing the current communication record to obtain a strategy mark, finding a current target node from the multi-branch tree based on the strategy mark, and further acquiring and playing a current communication strategy from the current target node until the call is finished.
The intelligent robot disclosed by the invention communicates with the client based on the pre-configured communication strategy, so that the client experience is ensured, and the outbound call success rate is improved.
And step 203, initiating an outbound operation to a second identifier in the outbound list based on the tone type and the communication strategy.
In a specific embodiment, under the condition that the current working scene is a manual working scene, the current communication record corresponding to the second identifier is obtained; and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and recommending the current communication strategy to the first identifier.
The intelligent robot monitors the communication content between the customer service staff and the customer in real time, analyzes the current communication record of the customer to obtain the strategy mark, finds the current target node from the multi-branch tree based on the strategy mark, further obtains the current communication strategy from the current target node, and sends the communication strategy to a computer or a mobile phone to provide communication assistance for the customer service.
The method and the system monitor the manual operation scene, avoid the problem of inaccurate word use in manual communication, ensure the communication quality and improve the user experience.
The outbound method applied to the intelligent robot provided by the disclosure comprises the steps of receiving an outbound command sent by a server; a communication strategy corresponding to the second identifier in the outbound list is obtained, so that the effectiveness of communication is ensured; based on the tone type and the communication strategy, the second identification in the outbound list initiates an outbound operation, and therefore when the intelligent robot performs the outbound operation, the tone consistent with the first identification and the communication strategy matched with the second identification are adopted, and the customer experience is effectively improved.
The embodiment of the present disclosure further provides an outbound system, where the outbound system described below and the outbound method described above may be referred to correspondingly, and repeated parts are not repeated, as shown in fig. 3, the system includes a server 301 and an intelligent robot 302.
The following describes a specific implementation of the system with reference to fig. 4:
s401, the server obtains a tone type corresponding to the audio data through a voice generation model;
s402, the server obtains a communication strategy through a historical communication record;
s403, the server sends the communication strategy to the intelligent robot;
s404, the server sorts the data to be called out corresponding to the first identification based on the historical communication record under the condition that the working scene is determined to be the calling out scene, and a calling out list is obtained;
s405, the server generates an outbound command;
s406, the server sends the outbound command to the intelligent robot;
s407, the intelligent robot receives an outbound command;
s408, the intelligent robot acquires a communication strategy corresponding to the second identifier in the outbound list;
and S409, the intelligent robot initiates an outbound operation on the second identifier according to the tone type and the communication strategy.
According to the intelligent robot outbound control method and system, the active control of the outbound operation of the intelligent robot is achieved through the outbound system, part of manual work is standardized, and the resource utilization rate is greatly improved.
The outbound device provided in the embodiment of the present disclosure is described below, and the outbound device described below and the outbound method described above may be referred to correspondingly, and repeated parts are not described again, as shown in fig. 5, the device includes:
the sequencing module 501 is configured to sequence the data to be outbound corresponding to the first identifier to obtain an outbound list when the current working scenario is an outbound scenario, where the data to be outbound includes a second identifier, and the first identifier and the second identifier indicate different user roles;
a sending module 502, configured to generate an outbound command and send the outbound command to the intelligent robot;
wherein, the outbound command comprises: the tone type and the outbound list of the first identifier;
the calling-out instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the calling-out list; and initiating an outbound operation to a second identifier in the outbound list based on the tone type and the communication strategy.
In a specific embodiment, the sorting module 501 is specifically configured to obtain a historical communication record corresponding to the second identifier in the data to be called out; determining the outbound success rate of each second identifier based on the historical communication records; and sequencing the second identifiers in the data to be outbound call based on the outbound call success rate to obtain an outbound call list.
In a specific embodiment, the apparatus further includes a first generating module, configured to obtain audio data corresponding to the first identifier; inputting the audio data into a voice generation model to obtain target audio data output by the voice generation model and a tone type corresponding to the target audio data; the target audio data is voice corresponding to the tone of the first identification; the voice generation model is obtained through training of the audio data sample, the target audio data sample and the tone type sample.
In a specific embodiment, the first generating module is specifically configured to input audio data into a feature extraction layer of a speech generation model, so as to obtain a tone feature output by the feature extraction layer; and inputting the tone characteristics into a voice generation layer of the voice generation model to obtain target audio data output by the voice generation layer and a tone type corresponding to the target audio data.
In a specific embodiment, the apparatus further includes a second generating module, configured to obtain a historical communication record corresponding to a second identifier in the data to be called out; determining behavior characteristics corresponding to the second identification based on the historical communication records; and generating a communication strategy corresponding to the behavior characteristics, and sending the communication strategy to the intelligent robot.
The outbound device provided by the embodiment of the present disclosure is described below, where the outbound device described below and the outbound method described above may be referred to correspondingly, and repeated parts are not described again, as shown in fig. 6, the device includes:
a receiving module 601, configured to receive an outbound command sent by a server, where the outbound command includes: the tone type and the outbound list of the first identifier;
an obtaining module 602, configured to obtain a communication policy corresponding to a second identifier in the outbound list, where the first identifier and the second identifier indicate different user roles;
the outbound module 603 is configured to initiate an outbound operation on the second identifier in the outbound list based on the tone type and the communication policy.
In a specific embodiment, the obtaining module 602 is further configured to receive a communication policy sent by the server; storing the communication strategy in the nodes of the multi-branch tree based on the second identification corresponding to the communication strategy; the obtaining module 602 is specifically configured to determine a target node from the multi-way tree based on the second identifier in the outbound list, and obtain the communication policy from the target node.
In a specific embodiment, the obtaining module 602 is specifically configured to determine an initial target node based on a second identifier in the outbound list, and obtain an initial communication policy from the initial target node; the outbound module 603 is specifically configured to initiate an outbound operation on the second identifier based on the tone type and the initial communication policy; the outbound module 603 is further configured to obtain a current communication record corresponding to the second identifier; and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and playing the acquired current communication strategy.
In a specific embodiment, the device further includes a recommendation module, configured to, in a case that the current working scene is a manual operation scene, obtain a current communication record corresponding to the second identifier; and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and recommending the current communication strategy to the first identifier.
The embodiment of the present disclosure further provides a server, where the server is configured to implement the outbound method applied to the server as described in any of the above embodiments.
The embodiment of the disclosure further provides an intelligent robot, which includes a robot body and a controller, wherein the controller is used for implementing the outbound method applied to the intelligent robot as explained in any one of the above embodiments.
Fig. 7 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 7: a processor (processor) 701, a communication Interface (Communications Interface) 702, a memory (memory) 703 and a communication bus 704, wherein the processor 701, the communication Interface 702 and the memory 703 complete communication with each other through the communication bus 704. Processor 701 may invoke logic instructions in memory 703 to perform an outbound method applied to the server, the method comprising: when the current working scene is an outbound scene, sequencing data to be outbound corresponding to the first identification to obtain an outbound list, wherein the data to be outbound comprises a second identification, and the first identification and the second identification indicate different user roles; generating an outbound command and sending the outbound command to the intelligent robot; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; based on the tone type and the communication strategy, initiating an outbound operation to a second identifier in an outbound list, or executing an outbound method applied to the intelligent robot, wherein the method comprises the following steps: receiving an outbound command sent by a server, wherein the outbound command comprises: the tone type and the outbound list of the first identifier; acquiring a communication strategy corresponding to a second identifier in the outbound list, wherein the first identifier and the second identifier indicate different user roles; and initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy.
In addition, the logic instructions in the memory 703 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present disclosure also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform the outbound method applied to a server provided by the above methods, the method comprising: when the current working scene is an outbound scene, sequencing data to be outbound corresponding to the first identification to obtain an outbound list, wherein the data to be outbound comprises a second identification, and the first identification and the second identification indicate different user roles; generating an outbound command and sending the outbound command to the intelligent robot; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy.
In yet another aspect, the present disclosure also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the various provided outbound methods applied to a server, the method comprising: when the current working scene is an outbound scene, sequencing data to be outbound corresponding to the first identification to obtain an outbound list, wherein the data to be outbound comprises a second identification, and the first identification and the second identification indicate different user roles; generating an outbound command and sending the outbound command to the intelligent robot; wherein, the outbound command comprises: the tone type and the outbound list of the first identifier; the calling-out instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the calling-out list; and initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy.
The above-described embodiments of the apparatus are merely illustrative, and 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several 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 various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solutions of the present disclosure, not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.
Claims (14)
1. An outbound method, applied to a server, the method comprising:
when the current working scene is an outbound scene, sequencing data to be outbound corresponding to a first identifier to obtain an outbound list, wherein the data to be outbound comprises a second identifier, and the first identifier and the second identifier indicate different user roles;
generating an outbound command and sending the outbound command to the intelligent robot;
wherein, the outbound command comprises: the tone type of the first identifier and the outbound list;
the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
2. The outbound method according to claim 1, wherein said sorting the data to be outbound corresponding to the first identifier to obtain an outbound list comprises:
acquiring a historical communication record corresponding to the second identifier in the data to be called out;
determining the outbound success rate of each second identifier based on the historical communication records;
and sequencing the second identification in the data to be called out based on the calling out success rate to obtain the calling out list.
3. The outbound method of claim 1, wherein prior to said generating an outbound command, further comprising:
acquiring audio data corresponding to the first identifier;
inputting the audio data into a voice generation model to obtain target audio data output by the voice generation model and a tone type corresponding to the target audio data;
the target audio data are voices corresponding to the timbres of the first marks;
wherein the speech generation model is obtained by training audio data samples, target audio data samples and tone type samples.
4. The outbound method according to claim 3, wherein said inputting the audio data into a speech generation model to obtain target audio data output by the speech generation model and a tone type corresponding to the target audio data comprises:
inputting the audio data into a feature extraction layer of the voice generation model to obtain tone features output by the feature extraction layer;
and inputting the tone features into a voice generation layer of the voice generation model to obtain the target audio data output by the voice generation layer and the tone type corresponding to the target audio data.
5. The outbound method of any one of claims 1-4, wherein prior to generating the outbound command, further comprising:
acquiring a historical communication record corresponding to the second identifier in the data to be called out;
determining behavior characteristics corresponding to the second identification based on the historical communication records;
and generating a communication strategy corresponding to the behavior characteristics, and sending the communication strategy to the intelligent robot.
6. An outbound method, applied to an intelligent robot, the method comprising:
receiving an outbound command sent by a server, wherein the outbound command comprises: the tone type and the outbound list of the first identifier;
acquiring a communication strategy corresponding to a second identifier in the outbound list, wherein the first identifier and the second identifier indicate different user roles;
and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
7. The outbound method according to claim 6, wherein before the obtaining the communication policy corresponding to the second identifier in the outbound list, the method further comprises:
receiving a communication strategy sent by the server;
storing the communication strategy in a node of a multi-branch tree based on a second identifier corresponding to the communication strategy;
the obtaining of the communication policy corresponding to the second identifier in the outbound list includes:
and determining a target node from the multi-branch tree based on a second identifier in the outbound list, and acquiring the communication strategy from the target node.
8. The outbound method of claim 7, wherein said determining a target node from said multi-way tree based on a second identifier in said outbound list, and obtaining said communication policy from said target node comprises:
determining an initial target node based on a second identifier in the outbound list, and acquiring an initial communication strategy from the initial target node;
the initiating an outbound operation to the second identifier in the outbound list based on the tone type and the communication strategy comprises:
initiating an outbound operation on the second identifier based on the tone type and the initial communication strategy;
after initiating an outbound operation for the second identifier based on the tone type and the initial communication policy, the method further includes:
acquiring a current communication record corresponding to the second identifier;
and determining a current target node from the multi-branch tree based on the current communication record, acquiring the current communication strategy from the current target node, and playing the acquired current communication strategy.
9. The outbound method according to any one of claims 6-8, wherein said method further comprises:
under the condition that the current working scene is a manual operation scene, acquiring a current communication record corresponding to the second identifier;
and determining a current target node from the multi-branch tree based on the current communication record, acquiring a current communication strategy from the current target node, and recommending the current communication strategy to the first identifier.
10. An outbound device, comprising:
the sequencing module is used for sequencing the data to be outbound corresponding to the first identifier to obtain an outbound list under the condition that the current working scene is an outbound scene, wherein the data to be outbound comprises a second identifier, and the first identifier and the second identifier indicate different user roles;
the sending module is used for generating an outbound command and sending the outbound command to the intelligent robot;
wherein, the outbound command comprises: the tone type of the first identifier and the outbound list;
the outbound instruction is used for instructing the intelligent robot to acquire a communication strategy corresponding to the second identifier in the outbound list; and initiating an outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
11. An outbound device, comprising:
a receiving module, configured to receive an outbound command sent by a server, where the outbound command includes: the tone type and the outbound list of the first identifier;
an obtaining module, configured to obtain a communication policy corresponding to a second identifier in the outbound list, where the first identifier and the second identifier indicate different user roles;
and the outbound module is used for initiating outbound operation on the second identifier in the outbound list based on the tone type and the communication strategy.
12. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the outbound method of any of claims 1 to 5.
13. A server arranged to implement the outbound method of any one of claims 1 to 5.
14. An intelligent robot, characterized by comprising a robot body and a controller for implementing the outbound method according to any one of claims 6 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139410.5A CN115442480A (en) | 2022-09-19 | 2022-09-19 | Outbound method, device, medium, server and intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139410.5A CN115442480A (en) | 2022-09-19 | 2022-09-19 | Outbound method, device, medium, server and intelligent robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115442480A true CN115442480A (en) | 2022-12-06 |
Family
ID=84249766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211139410.5A Pending CN115442480A (en) | 2022-09-19 | 2022-09-19 | Outbound method, device, medium, server and intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115442480A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116246643A (en) * | 2022-12-26 | 2023-06-09 | 深度好奇(杭州)科技有限公司 | Speech robot and artificial seat tone normalization method, system and equipment |
-
2022
- 2022-09-19 CN CN202211139410.5A patent/CN115442480A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116246643A (en) * | 2022-12-26 | 2023-06-09 | 深度好奇(杭州)科技有限公司 | Speech robot and artificial seat tone normalization method, system and equipment |
| CN116246643B (en) * | 2022-12-26 | 2023-07-28 | 深度好奇(杭州)科技有限公司 | Speech robot and artificial seat tone normalization method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109873909B (en) | Voice calling method, device and equipment and computer storage medium | |
| KR102348904B1 (en) | Method for providing chatting service with chatbot assisted by human counselor | |
| CN111105782B (en) | Session interaction processing method and device, computer equipment and storage medium | |
| CN110035187A (en) | A method of realizing AI and operator attendance seamless switching in the phone | |
| CN108073600A (en) | A kind of intelligent answer exchange method, device and electronic equipment | |
| CN111683175B (en) | Method, device, equipment and storage medium for automatically answering incoming call | |
| CN111583931A (en) | Service data processing method and device | |
| CN109859032A (en) | Funds on account collection method, apparatus, equipment and storage medium based on intelligent sound | |
| CN115442480A (en) | Outbound method, device, medium, server and intelligent robot | |
| CN112201222A (en) | Voice interaction method, device, equipment and storage medium based on voice call | |
| CN109545203A (en) | Audio recognition method, device, equipment and storage medium | |
| CN110489519B (en) | Session method based on session prediction model and related products | |
| CN113840040B (en) | Man-machine cooperation outbound method, device, equipment and storage medium | |
| CN111339282A (en) | Intelligent online response method and intelligent customer service system | |
| KR20090076318A (en) | Realtime conversational service system and method thereof | |
| CN112102807A (en) | Speech synthesis method, apparatus, computer device and storage medium | |
| CN108182942B (en) | Method and device for supporting interaction of different virtual roles | |
| CN111858874A (en) | Conversation service processing method, device, equipment and computer readable storage medium | |
| CN111225115A (en) | Information providing method and device | |
| CN110795551A (en) | Intelligent conversation method, device and related equipment | |
| CN114222029A (en) | Intelligent customer service call method and device, computer equipment and storage medium | |
| CN111353771A (en) | Method, device, equipment and medium for remotely controlling payment | |
| CN111611407A (en) | Customer service interaction method, customer service interaction device, storage medium and equipment | |
| US20040006482A1 (en) | Method and system for the processing and storing of voice information | |
| CN115879583B (en) | Method and device for processing work order data and computer readable storage medium |
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 |