CN111627433A - Robot voice order processing method and device - Google Patents
Robot voice order processing method and device Download PDFInfo
- Publication number
- CN111627433A CN111627433A CN202010545182.6A CN202010545182A CN111627433A CN 111627433 A CN111627433 A CN 111627433A CN 202010545182 A CN202010545182 A CN 202010545182A CN 111627433 A CN111627433 A CN 111627433A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- merchant
- order
- conversation
- 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
-
- 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
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- 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
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
- Manipulator (AREA)
Abstract
The invention provides a method and a device for processing a robot voice order, wherein the method comprises the following steps: reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs; establishing a voice conversation according to the merchant information to which the first voice conversation information belongs; converting the first voice call to structured semantic intent data; updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in the merchant information; and generating order information by the updated voice conversation and the reply content. According to the invention, a set of merchant configuration table is established, and configuration information of multiple merchants is set on the same platform, so that multiple merchants can be used simultaneously, and the transverse expansion is unlimited; the voice analysis and the response are dynamically processed, so that the voice message of the response client supports the self-definition of a merchant, and the order information is uniformly managed in a voice conversation mode, so that the consistency and the integrity of the order are ensured.
Description
Technical Field
The invention relates to the field of voice recognition of telephone robots, in particular to a method and a device for processing a voice order of a robot.
Background
At present, similar telephone robot software systems exist in the industry, some systems are customized for a certain unit, and have insufficient expansibility, for example, the telephone robots of the current hotels (such as a Han family or a home and the like) can only answer the questions asked by the guests of the hotel, and the questions asked by the guests of the chain hotels in seven days by dialing the telephone can not be answered; some system voices are recorded in advance and cannot be changed, for example, when a guest replies about the room returning time for consultation, the guest replies to 12 pm in the next day in a unified way, and when special conditions are met, the room returning time is recorded in advance, so that flexible change cannot be realized.
Disclosure of Invention
The invention provides a method and a device for processing a robot voice order, aiming at solving the problems of insufficient expansibility and poor flexibility of a telephone robot software system in the prior art.
In a first aspect, the present invention provides a method for processing a robot voice order, including:
reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs;
establishing a voice conversation according to the merchant information to which the first voice conversation information belongs;
converting the first voice call to structured semantic intent data;
updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in the merchant information;
and generating order information by the updated voice conversation and the reply content.
Further, converting the first voice call to structured semantic intent data includes:
inputting voice information into a data analysis list through an SIP protocol;
the speech within the data analysis list is converted into structured semantic intent data.
Further, the merchant configuration information includes: a merchant telephone allocation information table, a merchant telephone configuration information table, an order information table and an order commodity list.
Further, updating the voice conversation according to the structured semantic intent data or configuring an information table according to the merchant conversation in the merchant information, and matching the reply content comprises:
if the structured semantic intention data is commodity demand information, completely supplementing the order information and the commodity information in the commodity demand information according to an order information table and an order commodity list in preset merchant configuration information, and updating the voice conversation by using the current supplement content;
and if the structured semantic intention data is non-commodity demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and matching reply contents.
Further, if the structured semantic intention data is non-commodity demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and after matching reply content, including:
performing voice synthesis on the reply content to generate an audio file, and sending the audio file to the client;
receiving second voice information sent by a client;
the second voice call is converted to structured semantic intent data.
Further, generating the order information from the updated voice session and the reply content comprises:
all voice sessions are deleted.
Further, the creating of the voice session according to the merchant information to which the first voice call information belongs includes:
establishing a voice conversation according to the merchant information to which the first voice conversation information belongs;
and storing the recognition result of the first voice call and/or the generated order commodity list in the voice call.
In a second aspect, the present invention provides a device for processing a robot voice order, comprising:
the voice call information acquisition module is used for reading preset merchant configuration information according to the acquired first voice call information and determining merchant information to which the first voice call information belongs;
the voice conversation establishing module is used for establishing voice conversation according to the merchant information to which the first voice conversation information belongs;
the conversion module is used for converting the first voice call into structured semantic intention data;
the data processing module according to semantic intention is used for updating the voice conversation according to the structured semantic intention data or configuring an information table according to merchant conversation in merchant information to match reply contents;
and the order information generating module is used for generating order information from the updated voice conversation and reply content.
In a third aspect, the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for robot voice order processing provided in the first aspect when executing the program.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of robotic voice order processing provided by the first aspect.
According to the method and the device for processing the robot voice order, a set of merchant configuration table is established, and configuration information of a plurality of merchants is set on the same platform, so that the merchants can use the voice order at the same time, and the transverse expansion is unlimited; the voice analysis and the response are dynamically processed, so that the voice message of the response client supports the self-definition of a merchant, and the order information is uniformly managed in a voice conversation mode, so that the consistency and the integrity of the order are ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for processing a robot voice order according to an embodiment of the present invention;
fig. 2 is a schematic overall flow chart of the robot voice order processing according to the embodiment of the present invention;
fig. 3 is a block diagram of a device for processing a robot voice order according to an embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
At present, similar telephone robot software systems exist in the industry, some systems are customized for a certain unit, the expansibility is insufficient, and some system voices are recorded in advance and cannot be changed, so that the flexibility is insufficient. In order to solve the above problem, an embodiment of the present invention provides a method for processing a robot voice order, as shown in fig. 1, where the method includes:
step S101, reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs;
step S102, establishing a voice conversation according to the business information to which the first voice communication information belongs;
step S103, converting the first voice call into structured semantic intention data;
step S104, updating the voice conversation according to the structured semantic intention data or configuring an information table according to the merchant conversation in the merchant information, and matching reply contents;
and step S105, generating order information by the updated voice conversation and the reply content.
Specifically, after the telephone robot connects the first voice call, the information of the merchant to which the first voice call information belongs is obtained from the merchant configuration table according to currently received and recognized information such as a merchant number, a merchant name, a room telephone number, a location identifier (room number) where the allocated telephone is located, and the like. Such as: the first voice information of the telephone robot is called from home, for example, and the system recognizes that the first voice is the telephone number of the room of the home 102, for example, and then directly acquires a series of configuration information of the home and the business, for example.
The merchant configuration information comprises: a merchant telephone allocation information table, a merchant telephone configuration information table, an order commodity list and the like. The merchant telephone allocation information table contains field information: a merchant number, a merchant name, a room telephone number, an identification of the location of the assigned telephone (room number), etc.; the merchant dialect configuration information table contains field information: a primary key unique number, a merchant number, a semantic intention identifier (scene identifier), a question, an answer, and the like; the order information table contains field information and the like: order number, merchant number, room telephone number, order time, order amount, etc.; the order commodity list contains field information: the main key is unique in number, order number, commodity name, commodity quantity, commodity unit price, commodity amount and the like. The unique primary key number mentioned in the embodiment of the present invention is used to uniquely identify a record or each row in the table, and the "primary key" meaning is the primary key word, which is the same as the meaning in the prior art and is not described again.
And then establishing a voice session based on the current first voice call information, namely, establishing a voice session for the current incoming call guest, wherein the voice session comprises the voice content of the current call, the result of semantic analysis of the call voice and an order commodity list (comprising attribute commodity numbers, commodity names, commodity quantity, commodity unit price and commodity amount), so that the final processing result of the first voice call information and all order commodity list information related to the first voice call information can be conveniently inquired.
And inputting voice information into the data analysis list through the SIP protocol, and converting the voice in the data analysis list into structured semantic intention data. And determining whether to update the voice conversation according to the content of the structured semantic intention data, adding order information meeting the requirements of the customer into the voice conversation and feeding back the order information to the customer, or inquiring and matching reply content most fitting the reality according to a merchant conversation configuration information table in merchant information.
And finally, generating order information by the updated voice conversation and reply content for storage.
According to the embodiment of the invention, a set of merchant configuration table is established, and configuration information of a plurality of merchants is set on the same platform, so that the merchants can be used simultaneously, and the transverse expansion is unlimited; the voice analysis and the response are dynamically processed, so that the voice message of the response client supports the self-definition of a merchant, and the order information is uniformly managed in a voice conversation mode, so that the consistency and the integrity of the order are ensured.
Based on the content of the above embodiments, as an alternative embodiment: updating the voice conversation according to the structured semantic intent data or configuring an information table according to merchant conversation in the merchant information, and matching reply content comprises:
if the structured semantic intention data is commodity demand information, completely supplementing the order information and the commodity information in the commodity demand information according to an order information table and an order commodity list in preset merchant configuration information, and updating the voice conversation by using the current supplement content;
and if the structured semantic intention data is non-commodity demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and matching reply contents.
Specifically, the voice input data of the user is parsed into structured semantic intention data. The semantic analysis can use a current third-party semantic analysis engine or a self-realized semantic analysis engine, if the structured semantic intention is the commodity requirement in the order, the order information and the commodity information in the commodity requirement information are completely supplemented according to an order information table and an order commodity detail table in preset merchant configuration information; and if the structured semantic intention data is non-commodity demand information, inquiring reply contents most fitting the reality in configuration according to the voice semantic analysis result of the user and by combining with the jargon configuration.
Based on the content of the above embodiments, as an alternative embodiment: if the structured semantic intention data is non-commodity demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and matching reply contents, wherein the step comprises the following steps:
performing voice synthesis on the reply content to generate an audio file, and sending the audio file to the client;
receiving second voice information sent by a client;
the second voice call is converted to structured semantic intent data.
Specifically, the reply content is subjected to speech synthesis to generate an audio file, the speech synthesis may use a speech synthesis engine of a current third party or a speech synthesis engine realized by the third party, and the synthesized audio file is returned to the client, played by a receiver, and waits for speech input of the client again.
Receiving second voice information sent by the customer, converting the second voice call into structured semantic intention data, circularly executing again to update the voice session according to the structured semantic intention data or configure an information table according to merchant speech in merchant information, and matching reply contents; and generating order information according to the updated voice conversation and the reply content.
Some systems in the prior art lack session management, each session generates an order record, and thus a large amount of invalid order record information is generated, for example, when a guest inquires about information about the price of a commodity, the current system stores the order record as an order record, and when the guest sends a message of "no purchase", the current system stores "no purchase" as an order record, so that all information about the price of the commodity is stored in the whole system, which results in excessive invalid record information and is inconvenient for later management, and in order to solve the problem, the present invention provides an optional embodiment: after the updated voice conversation and reply content are generated into order information, the method comprises the following steps:
all voice sessions are deleted.
Specifically, the voice session is destroyed, the voice session information is deleted, and the call is ended. That is, in the embodiment of the present invention, the voice conversation records of all the clients and the telephone robot are deleted, so that invalid order information can be cleared in time, the reduction of the invalid record information is ensured, and the memory space of the order system is saved. And because the purchase demand of the user is converted into the order information before the voice conversation is deleted, the information omission is not caused, and the consistency and the integrity of the order are ensured.
Based on the content of the above embodiments, as an alternative embodiment: the voice conversation establishment according to the business information to which the first voice call information belongs comprises:
establishing a voice conversation according to the merchant information to which the first voice conversation information belongs;
and storing the recognition result of the first voice call and/or the generated order commodity list in the voice call.
Specifically, the first voice call information is recorded in the form of a voice session, so as to store the current call recognition or processing result and/or the generated order commodity list.
Based on the content of the above embodiments, as an alternative embodiment: as shown in fig. 2, fig. 2 is a schematic overall flow chart of the robot voice order processing provided by the embodiment of the present invention, and the specific steps are as follows:
step 1: reading merchant configuration;
step 2: creating a voice session;
and step 3: acquiring user audio;
and 4, step 4: semantic parsing; if the identified semantic intention is a commodity requirement, executing a step 5, otherwise executing a step 7;
and 5: assembling the order;
step 6: updating the voice session;
and 7: analyzing the response message;
and 8: responding to the voice synthesis command, returning the synthesized audio file to the client, waiting for voice input, and executing the step 3;
and step 9: storing order information;
step 10: the voice session is destroyed.
According to another aspect of the present invention, an apparatus for processing a robot voice order is provided in an embodiment of the present invention, referring to fig. 3, fig. 3 is a block diagram of an apparatus for processing a robot voice order provided in an embodiment of the present invention. The device is used for completing the robot voice order processing provided by the embodiment of the invention in the embodiments. Therefore, the description and definition in the method for robot voice order processing provided by the embodiment of the present invention in the foregoing embodiments can be used for understanding the execution modules in the embodiments of the present invention.
The device includes:
the module 301 for acquiring merchant information to which the voice call belongs is used for reading preset merchant configuration information according to the acquired first voice call information and determining merchant information to which the first voice call information belongs;
a voice session creating module 302, configured to create a voice session according to the merchant information to which the first voice call information belongs;
a conversion module 303, configured to convert the first voice call into structured semantic intent data;
a according to semantic intent data processing module 304, configured to update the voice conversation according to the structured semantic intent data or configure an information table according to merchant speech technology in the merchant information, matching the reply content;
and an order information generating module 305, configured to generate order information from the updated voice session and the reply content.
Specifically, the specific process of each module in the apparatus of this embodiment to implement its function may refer to the related description in the corresponding method embodiment, and is not described herein again.
According to the embodiment of the invention, a set of merchant configuration table is established, and configuration information of a plurality of merchants is set on the same platform, so that the merchants can be used simultaneously, and the transverse expansion is unlimited; the voice analysis and the response are dynamically processed, so that the voice message of the response client supports the self-definition of a merchant, and the order information is uniformly managed in a voice conversation mode, so that the consistency and the integrity of the order are ensured.
Fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 4, the electronic device includes: a processor 401, a memory 402, and a bus 403;
the processor 401 and the memory 402 respectively complete communication with each other through the bus 403; the processor 401 is configured to call the program instructions in the memory 402 to execute the method for robot voice order processing provided by the foregoing embodiments, for example, including: reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs; establishing a voice conversation according to the merchant information to which the first voice conversation information belongs; converting the first voice call to structured semantic intent data; updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in the merchant information; and generating order information by the updated voice conversation and the reply content.
Embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of a method for robot voice order processing. Examples include: reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs; establishing a voice conversation according to the merchant information to which the first voice conversation information belongs; converting the first voice call to structured semantic intent data; updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in the merchant information; and generating order information by the updated voice conversation and the reply content.
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 the 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 can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable 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 methods of the various embodiments or some parts of the embodiments.
Finally, the principle and the implementation of the present invention are explained by applying the specific embodiments in the present invention, and the above description of the embodiments 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. A method for robotic voice order processing, the method comprising:
reading preset merchant configuration information according to the acquired first voice call information, and determining merchant information to which the first voice call information belongs;
establishing a voice conversation according to the merchant information to which the first voice conversation information belongs;
converting the first voice call to structured semantic intent data;
updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in merchant information;
and generating order information by the updated voice conversation and the reply content.
2. The method of claim 1, wherein converting the first voice call to structured semantic intent data comprises:
inputting the voice information into a data analysis list through an SIP protocol;
converting speech within the data analysis list into structured semantic intent data.
3. The method of claim 1, wherein the merchant configuration information comprises: a merchant telephone allocation information table, a merchant telephone configuration information table, an order information table and an order commodity list.
4. The method of claim 3, wherein the updating the voice session according to the structured semantic intent data or matching reply content according to a table of merchant conversational configuration information within merchant information comprises:
if the structured semantic intention data is commodity demand information, completely supplementing the order information and the commodity information in the commodity demand information according to the order information table and the order commodity detail table in preset merchant configuration information, and updating the voice conversation by using the current supplement content;
and if the structured semantic intention data is non-commodity demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and matching reply contents.
5. The method according to claim 4, wherein if the structured semantic intent data is non-commodity-demand information, searching a merchant speech configuration information table in merchant information to which the first voice call information belongs, and after matching reply content, including:
performing voice synthesis on the reply content to generate an audio file, and sending the audio file to a client;
receiving second voice information sent by a client;
converting the second voice call to structured semantic intent data.
6. The method of claim 1, wherein generating the order information from the updated voice session and the reply content comprises:
all voice sessions are deleted.
7. The method of claim 1, wherein creating the voice session based on the merchant information to which the first voice call information belongs comprises:
establishing a voice conversation according to the merchant information to which the first voice conversation information belongs;
and storing the recognition result of the first voice call and/or the generated order commodity list in the voice call.
8. An apparatus for robotic voice order processing, the apparatus comprising:
the voice call information acquisition module is used for reading preset merchant configuration information according to the acquired first voice call information and determining merchant information to which the first voice call information belongs;
the voice conversation establishing module is used for establishing voice conversation according to the merchant information to which the first voice conversation information belongs;
the conversion module is used for converting the first voice call into structured semantic intention data;
the data processing module according to semantic intention is used for updating the voice conversation according to the structured semantic intention data or matching reply contents according to a merchant conversation configuration information table in merchant information;
and the order information generating module is used for generating order information from the updated voice conversation and the reply content.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of robotic voice order processing according to any of claims 1 to 7 are implemented when the program is executed by the processor.
10. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of robotic speech order processing according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545182.6A CN111627433B (en) | 2020-06-16 | 2020-06-16 | Robot voice order processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010545182.6A CN111627433B (en) | 2020-06-16 | 2020-06-16 | Robot voice order processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111627433A true CN111627433A (en) | 2020-09-04 |
| CN111627433B CN111627433B (en) | 2023-11-28 |
Family
ID=72259584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010545182.6A Active CN111627433B (en) | 2020-06-16 | 2020-06-16 | Robot voice order processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111627433B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6658389B1 (en) * | 2000-03-24 | 2003-12-02 | Ahmet Alpdemir | System, method, and business model for speech-interactive information system having business self-promotion, audio coupon and rating features |
| CN102215301A (en) * | 2011-05-25 | 2011-10-12 | 张磊 | System and method for automatic call transferring and calling party information identification |
| CN103067619A (en) * | 2013-01-18 | 2013-04-24 | 张磊 | System device and method for automatic reservation |
| CN105243565A (en) * | 2015-10-22 | 2016-01-13 | 深圳创想未来机器人有限公司 | Robot and O2O trade realization method thereof |
| CN107451893A (en) * | 2017-08-02 | 2017-12-08 | 上海庆科信息技术有限公司 | A kind of method, high in the clouds information processor and the system of voice shopping |
| CN109065052A (en) * | 2018-11-05 | 2018-12-21 | 中通天鸿（北京）通信科技股份有限公司 | A kind of speech robot people |
| CN110019725A (en) * | 2017-12-22 | 2019-07-16 | 科沃斯商用机器人有限公司 | Man-machine interaction method, system and its electronic equipment |
| CN110060663A (en) * | 2019-04-28 | 2019-07-26 | 北京云迹科技有限公司 | A kind of method, apparatus and system of answer service |
| CN110290169A (en) * | 2019-05-09 | 2019-09-27 | 北京云迹科技有限公司 | A kind of Service Order response method and device |
| CN110740212A (en) * | 2019-09-26 | 2020-01-31 | 北京淇瑀信息科技有限公司 | Call answering method and device based on intelligent voice technology and electronic equipment |
| CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
| CN111242721A (en) * | 2019-12-30 | 2020-06-05 | 北京百度网讯科技有限公司 | Voice meal ordering method and device, electronic equipment and storage medium |
| CN111246031A (en) * | 2020-02-27 | 2020-06-05 | 大连即时智能科技有限公司 | Human-machine collaborative telephone customer service method and system |
-
2020
- 2020-06-16 CN CN202010545182.6A patent/CN111627433B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6658389B1 (en) * | 2000-03-24 | 2003-12-02 | Ahmet Alpdemir | System, method, and business model for speech-interactive information system having business self-promotion, audio coupon and rating features |
| CN102215301A (en) * | 2011-05-25 | 2011-10-12 | 张磊 | System and method for automatic call transferring and calling party information identification |
| CN103067619A (en) * | 2013-01-18 | 2013-04-24 | 张磊 | System device and method for automatic reservation |
| CN105243565A (en) * | 2015-10-22 | 2016-01-13 | 深圳创想未来机器人有限公司 | Robot and O2O trade realization method thereof |
| CN107451893A (en) * | 2017-08-02 | 2017-12-08 | 上海庆科信息技术有限公司 | A kind of method, high in the clouds information processor and the system of voice shopping |
| CN110019725A (en) * | 2017-12-22 | 2019-07-16 | 科沃斯商用机器人有限公司 | Man-machine interaction method, system and its electronic equipment |
| CN109065052A (en) * | 2018-11-05 | 2018-12-21 | 中通天鸿（北京）通信科技股份有限公司 | A kind of speech robot people |
| CN110060663A (en) * | 2019-04-28 | 2019-07-26 | 北京云迹科技有限公司 | A kind of method, apparatus and system of answer service |
| CN110290169A (en) * | 2019-05-09 | 2019-09-27 | 北京云迹科技有限公司 | A kind of Service Order response method and device |
| CN110740212A (en) * | 2019-09-26 | 2020-01-31 | 北京淇瑀信息科技有限公司 | Call answering method and device based on intelligent voice technology and electronic equipment |
| CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
| CN111242721A (en) * | 2019-12-30 | 2020-06-05 | 北京百度网讯科技有限公司 | Voice meal ordering method and device, electronic equipment and storage medium |
| CN111246031A (en) * | 2020-02-27 | 2020-06-05 | 大连即时智能科技有限公司 | Human-machine collaborative telephone customer service method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111627433B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932946B (en) | Voice interaction method and device for customer-on-demand service | |
| US10121475B2 (en) | Computer-implemented system and method for performing distributed speech recognition | |
| EP3331203B1 (en) | Instant communication with instant text data and voice data | |
| CA2490430C (en) | Method and apparatus for automatically building conversational systems | |
| CN103377652B (en) | A kind of method, device and equipment for carrying out speech recognition | |
| US9106724B1 (en) | Communication aggregation | |
| CN105206269A (en) | Voice processing method and device | |
| US11012573B2 (en) | Interactive voice response using a cloud-based service | |
| CN107800901B (en) | User call processing method, device, computer equipment and storage medium | |
| CN113724036B (en) | Method for providing problem consultation service and electronic equipment | |
| CN109189502A (en) | A kind of message treatment method and relevant device based on instant messaging public platform | |
| CN115982331A (en) | Information interaction method, device and equipment in conversation scene | |
| CN113472958A (en) | Method, system, electronic device and storage medium for receiving branch telephone in centralized mode | |
| WO2020129419A1 (en) | Voice inquiry system, voice inquiry processing method, smart speaker operation server device, and program | |
| CN114697281B (en) | Text message processing method and device, storage medium, electronic device | |
| CN112447179A (en) | Voice interaction method, device, equipment and computer readable storage medium | |
| CN111627433B (en) | Robot voice order processing method and device | |
| US8983040B2 (en) | Method and device for consulting a voice message | |
| CN113709314B (en) | Intelligent seat outbound method and device, electronic equipment and computer storage medium | |
| CN116996619A (en) | Voice service navigation method, device, equipment and storage medium | |
| US20200322293A1 (en) | Information processing system and method | |
| CN105553692A (en) | Interactive voice response system, telephone customer service system and data processing method thereof | |
| CN114697457B (en) | Voice message processing method and device, storage medium, and electronic device | |
| JP7730511B2 (en) | Telephone handling program, device and method | |
| KR101105567B1 (en) | Voice data providing system that provides voice data in call waiting time |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 702, 7th floor, NO.67, Beisihuan West Road, Haidian District, Beijing 100089 Applicant after: Beijing Yunji Technology Co.,Ltd. Address before: Room 702, 7th floor, NO.67, Beisihuan West Road, Haidian District, Beijing 100089 Applicant before: BEIJING YUNJI TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |