CN111008720A - Restaurant reservation method and terminal based on multiple rounds of voice interaction - Google Patents
Restaurant reservation method and terminal based on multiple rounds of voice interaction Download PDFInfo
- Publication number
- CN111008720A CN111008720A CN201911253601.2A CN201911253601A CN111008720A CN 111008720 A CN111008720 A CN 111008720A CN 201911253601 A CN201911253601 A CN 201911253601A CN 111008720 A CN111008720 A CN 111008720A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- restaurant
- travel
- voice interaction
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000006870 function Effects 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 15
- 235000012054 meals Nutrition 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 description 4
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 235000019640 taste Nutrition 0.000 description 2
- 230000004308 accommodation Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
- G06Q10/025—Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The application relates to a restaurant reservation method based on multiple rounds of voice interaction, which is applied to a terminal and comprises the following steps: receiving a voice instruction for reserving a restaurant; performing multiple voice interactions with a user to provide restaurant information matching the travel information when the travel information is shared by the co-diners; after receiving the voice command for confirming the restaurant reservation, the restaurant reservation operation is executed. In this way, the user can quickly book to the restaurant according with the travel arrangement of the common diners through voice, and the user experience is improved.
Description
Technical Field
The application relates to the technical field of voice interaction, in particular to a restaurant reservation method and terminal based on multiple rounds of voice interaction.
Background
In the prior art, a user can not directly book a restaurant by voice, the user still needs to manually screen information in the process of reserving the restaurant by voice, the operation is complicated, the man-machine interaction mode is unnatural, meanwhile, when the user needs to have a meal with friends, the user can not fast book the restaurant meeting the travel arrangement of the friends, the booking efficiency is low, and the user experience is poor.
Disclosure of Invention
The present application aims to provide a restaurant reservation method and a terminal based on multiple rounds of voice interaction, which can solve the above technical problems and can quickly reserve to a restaurant conforming to the schedule of the common diners through voice.
In order to solve the above technical problem, the present application provides a restaurant reservation method based on multiple rounds of voice interaction, which is applied to a terminal and includes:
receiving a voice instruction for reserving a restaurant;
performing multiple rounds of voice interaction with a user to provide restaurant information matching the travel information when the travel information is shared by common diners;
after receiving the voice command for confirming the restaurant reservation, the restaurant reservation operation is executed.
Wherein the receiving of the voice instruction to reserve the restaurant comprises:
receiving voice information;
judging whether the content of the voice information contains keywords for reserving a restaurant;
if yes, the voice message is confirmed to be a voice instruction for reserving the restaurant.
Before the determining whether the content of the voice message contains a keyword for reserving a restaurant, the method further includes:
judging whether the voice information contains a keyword for awakening the voice interaction function;
if so, identifying the user identity according to the voiceprint characteristics of the voice information;
if the identification is successful, starting a voice interaction function, and entering the step of judging whether the content of the voice information contains the keywords for reserving the restaurant.
Wherein the performing multiple rounds of voice interactions with the user to provide restaurant information matching the travel information when the travel information is shared by the common diner comprises:
outputting first voice information for inquiring the common diner;
receiving second voice information;
obtaining the information of the common diner according to the voice content of the second voice information and judging whether the travel information of the common diner needs to be inquired or not;
if the travel information of the common diner is required to be inquired, acquiring the travel information shared by the corresponding common diner according to the common diner information;
if the travel information is acquired, restaurant information is matched according to the travel information;
and outputting third voice information containing the matched restaurant information.
Wherein, if the travel information is acquired, matching restaurant information according to the travel information includes:
if the travel information is acquired, judging whether the travel information contains dining preferences or not;
if the travel information contains the dining preference, the restaurant information is matched according to the travel arrangement and the dining preference contained in the travel information;
and if the meal preference is not contained, matching the restaurant information according to the travel arrangement contained in the travel information.
Wherein the performing multiple rounds of voice interactions with a user to provide restaurant information matching the travel information when sharing the travel information with a common diner further comprises:
when a voice command for confirming restaurant information is received, judging whether the dining information is complete;
and if the information is not complete, outputting fourth voice information for prompting the supplementary meal information.
Wherein, the method further comprises:
when voice interaction is carried out, semantic analysis is carried out on the currently received voice information;
judging whether the currently received voice information is related to the context information according to the semantic analysis result;
if so, using the currently received voice information;
and if not, filtering the currently received voice information.
Wherein, the method further comprises:
when voice interaction is carried out, the duration of not receiving voice information after each voice output is accumulated;
when the time length reaches a preset time length, judging whether the restaurant reservation is finished;
if the restaurant reservation is not finished, recording the current reservation process and closing the voice interaction function;
when the voice interaction function is awakened again, the recorded subscription procedure is entered.
Wherein, the method further comprises:
if the restaurant reservation fails or the restaurant reservation is not completed, recording the restaurant information currently provided;
when a voice instruction to reserve a restaurant is received again, voice information for prompting the recorded restaurant information is output.
The application also provides a terminal, which comprises a memory and a processor, wherein the memory stores at least one program instruction, and the processor is used for realizing the restaurant reservation method based on multiple rounds of voice interaction by loading and executing the at least one program instruction.
According to the restaurant reservation method and the terminal based on the multiple rounds of voice interaction, after the terminal receives the voice command for reserving restaurants, the terminal performs multiple rounds of voice interaction with the user so as to provide restaurant information matched with the travel information when the common diners share the travel information, and after the voice command for confirming the restaurant reservation is received, restaurant reservation operation is executed. In this way, the user can quickly book to the restaurant according with the travel arrangement of the common diners through voice, and the user experience is improved.
The foregoing description is only an overview of the technical solutions of the present application, and in order to make the technical means of the present application more clearly understood, the present application may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present application more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart illustrating a restaurant reservation method based on multiple voice interactions according to a first embodiment.
Fig. 2 is a schematic structural diagram of a terminal according to a second embodiment.
Detailed Description
To further illustrate the technical means and effects of the present application for achieving the purpose of subscribing applications, the following detailed description is provided with reference to the accompanying drawings and preferred embodiments for specific implementation manners, methods, steps, structures, features and effects of the positioning method of the mobile terminal, the vehicle-mounted terminal and the mobile terminal according to the present application.
The foregoing and other technical matters, features and effects of the present application will be apparent from the following detailed description of preferred embodiments, which is to be read in connection with the accompanying drawings. While the present application is susceptible to particular embodiments and features, it is to be understood that various changes, modifications and substitutions may be made therein without departing from the spirit and scope of the present application.
Fig. 1 is a flowchart illustrating a restaurant reservation method based on multiple voice interactions according to a first embodiment. Referring to fig. 1, the restaurant reservation method based on multiple rounds of voice interaction of the present embodiment is applied to a terminal, and includes:
The voice command is a command input by a user in a voice mode, and the user can wake up a voice interaction function (or called as a voice assistant), identify and reserve a restaurant and the like through voice. In this embodiment, the process of receiving a voice command to reserve a restaurant includes:
receiving voice information;
judging whether the content of the voice information contains keywords for reserving a restaurant;
if yes, the voice message is confirmed to be the voice instruction for reserving the restaurant.
After receiving the voice information, the terminal identifies the content of the voice information to judge the type of the instruction input by the user, and when the content of the voice information contains a keyword for reserving a restaurant, the terminal determines that the voice instruction for reserving the restaurant is input by the user. For example, when the user utters "order a restaurant", the keyword "restaurant" including the predetermined restaurant may be obtained by content recognition, and the keyword of the predetermined restaurant may also be a word such as "dinner", "lunch", "meal", "gourmet", or the like, which may express a dining intention, but is not limited thereto.
In actual implementation, before determining whether the content of the voice message contains a keyword for reserving a restaurant, the method may further include the following steps:
judging whether the voice information contains a keyword for awakening the voice interaction function;
if so, identifying the user identity according to the voiceprint characteristics of the voice information;
if the identification is successful, starting a voice interaction function, and judging whether the content of the voice information contains a keyword for reserving the restaurant.
The user can simultaneously complete the operations of awakening voice interaction function, identity recognition and restaurant reservation instruction input through one-time voice input. The terminal firstly judges whether the voice information contains a keyword for awakening the voice interaction function, such as a name 'small E' of a voice assistant and a calling word 'hello', and after the keyword containing the voice interaction function is confirmed, the identity of a user is identified according to the voiceprint feature of the voice information, if the voiceprint feature of the voice information is consistent with the voiceprint feature of a preset user, the identity identification is successful, at the moment, the voice interaction function is started, the step of judging whether the content of the voice information contains the keyword for reserving a restaurant is automatically carried out, and if the content of the voice information contains the keyword for reserving the restaurant is confirmed, the voice information is a voice command for reserving the restaurant. By the mode, a user for example speaks ' small E ' to order a restaurant ', the operations of awakening the voice interaction function, identity recognition and restaurant reservation instruction input can be completed simultaneously, the voice interaction function does not need to be awakened for multiple times, and interaction efficiency is improved.
Multiple voice interactions with the user are performed to provide restaurant information matching the travel information when the travel information is shared by the co-diners, step 120.
The voice interaction means that the user interacts with the terminal through voice, so that the terminal performs a manner similar to manual reminding, and the operation of reserving the restaurant can be completed according to set steps without any characters or manual input.
In this embodiment, multiple rounds of voice interaction with a user to provide restaurant information matching the travel information when the travel information is shared by the people having a common meal include:
outputting first voice information for inquiring the common diner;
receiving second voice information;
obtaining the information of the common diner according to the voice content of the second voice information and judging whether the travel information of the common diner needs to be inquired or not;
if the travel information of the common diner is required to be inquired, acquiring the travel information shared by the corresponding common diner according to the information of the common diner;
if the travel information is acquired, restaurant information is matched according to the travel information;
and outputting third voice information containing the matched restaurant information.
In this embodiment, if the travel information is acquired, matching restaurant information according to the travel information includes:
if the travel information is acquired, judging whether the travel information contains dining preferences;
if the travel information contains the dining preference, the restaurant information is matched according to the travel arrangement and the dining preference contained in the travel information;
and if the meal preference is not contained, matching the restaurant information according to the travel arrangement contained in the travel information.
After the terminal judges that a voice command for reserving a restaurant is received, first voice information for inquiring the common diner, such as 'you want to eat food together with him', is output, after the user replies, content recognition is carried out on the received voice information, information of the common diner, such as name, unit, contact information and the like, is extracted, and meanwhile whether the travel information of the common diner needs to be inquired or not is judged according to the received voice information and the recognition result comprising the first voice information and the second voice information, for example, when the voice content of the received voice information comprises keywords such as 'business trip' and 'meeting', the travel information of the common diner needs to be inquired.
Then, the travel information shared by the corresponding common diners is obtained according to the common diner information, the travel information is shared by the common diners in advance, for example, the travel information is shared through social software or navigation application, the travel information comprises travel arrangements such as business trip plans and schedules, and therefore the travel information can show when the common diners are free and can be invited conveniently, and besides the information is shared, other information is kept secret strictly to protect privacy.
And after the travel information of the common diners is obtained, restaurant information is matched according to the travel information. Specifically, the user can include dining preferences such as preferred restaurant types and tastes, etc., in addition to the schedule when sharing the schedule information, so that the dining satisfaction can be improved. And if the travel information contains the dining preference, matching the restaurant information according to the travel arrangement and the dining preference contained in the travel information, and if the travel information does not contain the dining preference, matching the restaurant information according to the travel arrangement contained in the travel information. The terminal matches the restaurant through the independent query interface provided by the third-party restaurant reservation server, so that restaurant information such as name, place, taste, per-capita consumption and the like is obtained, then voice information is generated according to the restaurant information and output to inform a user, and if the user feels satisfied, the voice information for confirming the restaurant information can be replied.
In one embodiment, the process of performing multiple voice interactions with a user to provide restaurant information matching the travel information when the travel information is shared by the common diner may further comprise:
when a voice command for confirming restaurant information is received, judging whether the dining information is complete;
and if the information is not complete, outputting fourth voice information for prompting the supplementary meal information.
In the voice interaction process, a user can add dining information such as the number of people, time, city and the like when replying any voice information, the terminal judges whether the user inputs the dining information or not at the same time when performing voice recognition each time, judges whether the dining information is complete or not when receiving a voice instruction for confirming restaurant information, and outputs fourth voice information for prompting the supplement of the dining information if the dining information is incomplete, for example, the number of people not provided by the user, and outputs' people have a total of several people to have a dinner? If the meal information is complete, the restaurant reservation operation is executed.
In order to realize multiple interactions of voice, in an embodiment, when performing voice interaction, the method further includes the following steps:
performing semantic analysis on the currently received voice information;
judging whether the currently received voice information is related to the context information according to the semantic analysis result;
if so, using the currently received voice information;
and if not, filtering the currently received voice information.
When semantic analysis is carried out, context information in the interactive process is used for judging the relevance of voice information, so that the method has a filtering effect on other noises, can shield irrelevant voice input, namely filter the voice input irrelevant to the context information, avoids the interference of irrelevant voice noise and realizes the continuity of voice interaction.
To improve the booking efficiency, in one embodiment, when performing voice interaction, the method further includes the following steps:
accumulating the time length of not receiving the voice information after each voice output;
when the time length reaches the preset time length, judging whether the restaurant reservation is finished;
if the restaurant reservation is not finished, recording the current reservation process and closing the voice interaction function;
when the voice interaction function is awakened again, the recorded subscription procedure is entered.
The time length for accumulating the speech information which is not received after each speech output is 15-30 seconds, namely the terminal is still in the speech recognition state in the time length, thereby giving more time for thinking and feedback input to the user. If the preset duration lasts and the user does not input relevant voice, the voice interaction function is closed, whether restaurant reservation is finished or not is judged before, if the restaurant reservation is finished, the voice interaction function is directly closed, if the restaurant reservation is not finished, the current reservation progress is recorded and the voice interaction function is closed, so that the progress of reserving the restaurant can be recorded, and the recorded data can be stored in the cloud server. When the user wakes up the voice interaction function again, the reservation stage is directly entered, such as interruption of the reservation process by the telephone, and the business of people nearby, etc., and the voice interaction function may need to be woken up again to make a restaurant reservation. By the method, the user can enter the original reservation process quickly if interrupted in the process of reserving the restaurant, other information does not need to be input, and the reservation efficiency is improved.
After the terminal outputs the third voice message containing the restaurant information, the user can reply contents such as 'confirm reservation' by voice so as to input a voice command for confirming the reservation of the restaurant, at the moment, if the dining information is complete, the restaurant reservation operation is directly executed, and if the dining information is incomplete, in the process of executing the restaurant reservation operation, the user can be prompted to reply the corresponding dining information by outputting the voice message to finish the restaurant reservation operation through multiple rounds of voice interaction. The restaurant reservation operation is completed through a separate query interface provided by the third party restaurant reservation server.
In order to improve the subscription efficiency, the method of this embodiment further includes:
if the restaurant reservation fails or the restaurant reservation is not completed, recording the restaurant information currently provided;
when a voice instruction to reserve a restaurant is received again, voice information for prompting the recorded restaurant information is output.
After restaurant information is provided, if feedback of a user is not received or the user feedback is not reserved temporarily, the currently provided restaurant information is recorded, and when the user inputs a voice instruction for reserving the restaurant again, the voice information for prompting the recorded restaurant information is automatically output, so that the user is actively reminded whether the similar restaurant is reserved, other information does not need to be input again, and the time selected by the user is greatly saved.
By the mode, context memory of voice interaction can be realized, closed loop of user reservation is continuously realized, voice is given in the whole process, no character is needed, the travel time and accommodation arrangement of common diners are quickly known, a user can quickly find and reserve a restaurant according with the travel arrangement of friends, and user experience is good.
In practice, the restaurant reservation process may be as follows by the above method.
User voice: "Xiao E, Zhou Wu I school to ask for guests. "
The voice assistant: "do you want to get into the food with whom? When? Several bits? "
User voice: "my classmate leaf X came from Xian. "
The voice assistant: ' me ' knows that your schoolmates have shared the journey cheer, can live in Shanghai for two days, in Pudong Shangri La, this saturday night 9 o ' clock to 11 o ' clock, I propose booking luxuriant 88 building drink coffee, or 12 o ' clock in the noon of sunday. "
User voice: "then help me reserve a cafeteria bar at 12 pm on weekdays. "
According to the restaurant reservation method based on the multiple rounds of voice interaction, after the voice command for reserving restaurants is received, the terminal conducts multiple rounds of voice interaction with the user so as to provide restaurant information matched with the travel information when the common diners share the travel information, and after the voice command for confirming that the restaurants are reserved is received, restaurant reservation operation is executed. In this way, the user can quickly book to the restaurant according with the travel arrangement of the common diners through voice, and the user experience is improved.
Fig. 2 is a schematic structural diagram of a terminal according to a second embodiment. Referring to fig. 2, the terminal of the present embodiment includes a memory 210 and a processor 220, the memory 210 stores at least one computer program, and the processor 220 implements a restaurant reservation method based on multiple rounds of voice interactions by loading and executing the at least one computer program, including the following steps:
receiving a voice instruction for reserving a restaurant;
performing multiple voice interactions with a user to provide restaurant information matching the travel information when the travel information is shared by the co-diners;
after receiving the voice command for confirming the restaurant reservation, the restaurant reservation operation is executed.
Wherein the processor 220 performs the step of receiving voice instructions to reserve a restaurant, comprising:
receiving voice information;
judging whether the content of the voice information contains keywords for reserving a restaurant;
if yes, the voice message is confirmed to be the voice instruction for reserving the restaurant.
Before the step of determining whether the content of the voice message contains a keyword for reserving a restaurant is executed by the processor 220, the method further includes:
judging whether the voice information contains a keyword for awakening the voice interaction function;
if so, identifying the user identity according to the voiceprint characteristics of the voice information;
if the identification is successful, starting a voice interaction function, and judging whether the content of the voice information contains a keyword for reserving the restaurant.
Wherein processor 220 performs multiple voice interactions with the user to provide restaurant information matching the travel information when the travel information is shared by the co-diners, including:
outputting first voice information for inquiring the common diner;
receiving second voice information;
obtaining the information of the common diner according to the voice content of the second voice information and judging whether the travel information of the common diner needs to be inquired or not;
if the travel information of the common diner is required to be inquired, acquiring the travel information shared by the corresponding common diner according to the information of the common diner;
if the travel information is acquired, restaurant information is matched according to the travel information;
and outputting third voice information containing the matched restaurant information.
The step of, if the travel information is acquired, matching the restaurant information according to the travel information by the processor 220 includes:
if the travel information is acquired, judging whether the travel information contains dining preferences;
if the travel information contains the dining preference, the restaurant information is matched according to the travel arrangement and the dining preference contained in the travel information;
and if the meal preference is not contained, matching the restaurant information according to the travel arrangement contained in the travel information.
Wherein the processor 220 performs multiple voice interactions with the user to provide restaurant information matching the travel information when the travel information is shared by the common diner, further comprising:
when a voice command for confirming restaurant information is received, judging whether the dining information is complete;
and if the information is not complete, outputting fourth voice information for prompting the supplementary meal information.
Wherein, the processor 220 is further configured to perform the following steps:
when voice interaction is carried out, semantic analysis is carried out on the currently received voice information;
judging whether the currently received voice information is related to the context information according to the semantic analysis result;
if so, using the currently received voice information;
and if not, filtering the currently received voice information.
Wherein, the processor 220 is further configured to perform the following steps:
when voice interaction is carried out, the duration of not receiving voice information after each voice output is accumulated;
when the time length reaches the preset time length, judging whether the restaurant reservation is finished;
if the restaurant reservation is not finished, recording the current reservation process and closing the voice interaction function;
when the voice interaction function is awakened again, the recorded subscription procedure is entered.
Wherein, the processor 220 is further configured to perform the following steps:
if the restaurant reservation fails or the restaurant reservation is not completed, recording the restaurant information currently provided;
when a voice instruction to reserve a restaurant is received again, voice information for prompting the recorded restaurant information is output.
In one embodiment, the terminal is a navigation terminal.
Please refer to the specific contents described in the embodiment shown in fig. 1, and details thereof are not repeated herein.
The terminal receives the voice command for reserving the restaurant, performs multiple rounds of voice interaction with the user to provide restaurant information matched with the travel information when the common diner shares the travel information, and executes restaurant reservation operation after receiving the voice command for confirming the restaurant reservation. In this way, the user can quickly book to the restaurant according with the travel arrangement of the common diners through voice, and the user experience is improved.
Although the present application has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application, and all changes, substitutions and alterations that fall within the spirit and scope of the application are to be understood as being included within the following description of the preferred embodiment.
Claims (10)
1. A restaurant reservation method based on multiple rounds of voice interaction is applied to a terminal and is characterized by comprising the following steps:
receiving a voice instruction for reserving a restaurant;
performing multiple rounds of voice interaction with a user to provide restaurant information matching the travel information when the travel information is shared by common diners;
after receiving the voice command for confirming the restaurant reservation, the restaurant reservation operation is executed.
2. The restaurant reservation method based on multiple rounds of voice interaction of claim 1, wherein the receiving voice instructions to reserve a restaurant comprises:
receiving voice information;
judging whether the content of the voice information contains keywords for reserving a restaurant;
if yes, the voice message is confirmed to be a voice instruction for reserving the restaurant.
3. The restaurant reservation method based on multiple rounds of voice interaction as claimed in claim 2, wherein before the determining whether the content of the voice message contains a keyword for reserving a restaurant, further comprising:
judging whether the voice information contains a keyword for awakening the voice interaction function;
if so, identifying the user identity according to the voiceprint characteristics of the voice information;
if the identification is successful, starting a voice interaction function, and entering the step of judging whether the content of the voice information contains the keywords for reserving the restaurant.
4. The restaurant reservation method based on multiple rounds of voice interaction according to claim 1, wherein the multiple rounds of voice interaction with the user to provide restaurant information matching the travel information when the travel information is shared by the common diners comprises:
outputting first voice information for inquiring the common diner;
receiving second voice information;
obtaining the information of the common diner according to the voice content of the second voice information and judging whether the travel information of the common diner needs to be inquired or not;
if the travel information of the common diner is required to be inquired, acquiring the travel information shared by the corresponding common diner according to the common diner information;
if the travel information is acquired, restaurant information is matched according to the travel information;
and outputting third voice information containing the matched restaurant information.
5. The restaurant reservation method based on multiple rounds of voice interaction as claimed in claim 4, wherein the matching restaurant information according to the travel information if the travel information is obtained comprises:
if the travel information is acquired, judging whether the travel information contains dining preferences or not;
if the travel information contains the dining preference, the restaurant information is matched according to the travel arrangement and the dining preference contained in the travel information;
and if the meal preference is not contained, matching the restaurant information according to the travel arrangement contained in the travel information.
6. The method of claim 4, wherein the multiple rounds of voice interaction with the user to provide restaurant information matching the travel information when the travel information is shared by the co-diners, further comprises:
when a voice command for confirming restaurant information is received, judging whether the dining information is complete;
and if the information is not complete, outputting fourth voice information for prompting the supplementary meal information.
7. The method of restaurant reservation based on multiple rounds of voice interaction of claim 1, further comprising:
when voice interaction is carried out, semantic analysis is carried out on the currently received voice information;
judging whether the currently received voice information is related to the context information according to the semantic analysis result;
if so, using the currently received voice information;
and if not, filtering the currently received voice information.
8. The method of restaurant reservation based on multiple rounds of voice interaction of claim 1, further comprising:
when voice interaction is carried out, the duration of not receiving voice information after each voice output is accumulated;
when the time length reaches a preset time length, judging whether the restaurant reservation is finished;
if the restaurant reservation is not finished, recording the current reservation process and closing the voice interaction function;
when the voice interaction function is awakened again, the recorded subscription procedure is entered.
9. The method of restaurant reservation based on multiple rounds of voice interaction of claim 1, further comprising:
if the restaurant reservation fails or the restaurant reservation is not completed, recording the restaurant information currently provided;
when a voice instruction to reserve a restaurant is received again, voice information for prompting the recorded restaurant information is output.
10. A terminal comprising a memory storing at least one program instruction and a processor implementing the method of restaurant reservation based on multiple rounds of voice interaction of any of claims 1-9 by loading and executing the at least one program instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911253601.2A CN111008720A (en) | 2019-12-09 | 2019-12-09 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911253601.2A CN111008720A (en) | 2019-12-09 | 2019-12-09 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111008720A true CN111008720A (en) | 2020-04-14 |
Family
ID=70115211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911253601.2A Pending CN111008720A (en) | 2019-12-09 | 2019-12-09 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008720A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782780A (en) * | 2020-05-28 | 2020-10-16 | 博泰车联网(南京)有限公司 | Booking method and terminal based on multi-round voice interaction |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293029A1 (en) * | 2009-05-13 | 2010-11-18 | Hugh Olliphant | System and Method for Automatically Scheduling Appointments |
| CN102156800A (en) * | 2011-02-17 | 2011-08-17 | 华南理工大学 | Service industry information processing method and system based on voice conversation technology |
| US20140278673A1 (en) * | 2013-03-14 | 2014-09-18 | Sap Ag | Meeting scheduling application |
| CN108510355A (en) * | 2018-03-12 | 2018-09-07 | 拉扎斯网络科技（上海）有限公司 | The implementation method and relevant apparatus that interactive voice is made a reservation |
| CN109323707A (en) * | 2018-09-12 | 2019-02-12 | 上海博泰悦臻电子设备制造有限公司 | Stroke reminding method and navigation terminal |
| CN109359754A (en) * | 2018-09-25 | 2019-02-19 | 斑马网络技术有限公司 | Dining room booking method, device, system and storage medium |
| CN109545212A (en) * | 2018-12-11 | 2019-03-29 | 百度在线网络技术（北京）有限公司 | Exchange method, smart machine and storage medium |
| CN109558539A (en) * | 2018-11-23 | 2019-04-02 | 咪咕数字传媒有限公司 | A kind of information recommendation method, device and computer readable storage medium |
| CN109658173A (en) * | 2018-05-04 | 2019-04-19 | 美味不用等（上海）信息科技股份有限公司 | A kind of food and beverage sevice customization method and system |
-
2019
- 2019-12-09 CN CN201911253601.2A patent/CN111008720A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293029A1 (en) * | 2009-05-13 | 2010-11-18 | Hugh Olliphant | System and Method for Automatically Scheduling Appointments |
| CN102156800A (en) * | 2011-02-17 | 2011-08-17 | 华南理工大学 | Service industry information processing method and system based on voice conversation technology |
| US20140278673A1 (en) * | 2013-03-14 | 2014-09-18 | Sap Ag | Meeting scheduling application |
| CN108510355A (en) * | 2018-03-12 | 2018-09-07 | 拉扎斯网络科技（上海）有限公司 | The implementation method and relevant apparatus that interactive voice is made a reservation |
| CN109658173A (en) * | 2018-05-04 | 2019-04-19 | 美味不用等（上海）信息科技股份有限公司 | A kind of food and beverage sevice customization method and system |
| CN109323707A (en) * | 2018-09-12 | 2019-02-12 | 上海博泰悦臻电子设备制造有限公司 | Stroke reminding method and navigation terminal |
| CN109359754A (en) * | 2018-09-25 | 2019-02-19 | 斑马网络技术有限公司 | Dining room booking method, device, system and storage medium |
| CN109558539A (en) * | 2018-11-23 | 2019-04-02 | 咪咕数字传媒有限公司 | A kind of information recommendation method, device and computer readable storage medium |
| CN109545212A (en) * | 2018-12-11 | 2019-03-29 | 百度在线网络技术（北京）有限公司 | Exchange method, smart machine and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782780A (en) * | 2020-05-28 | 2020-10-16 | 博泰车联网(南京)有限公司 | Booking method and terminal based on multi-round voice interaction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110992948B (en) | Restaurant reservation method and terminal based on multi-round voice interaction | |
| US10853582B2 (en) | Conversational agent | |
| US11544675B2 (en) | Contextually aware schedule services | |
| EP3400699B1 (en) | Cross device companion application for phone | |
| CN112262381B (en) | Compiling and evaluating automatic assistant responses to privacy questions | |
| US9106757B2 (en) | Terminal, server, and method for actively providing information based on communication contents | |
| KR102029278B1 (en) | Conditional publishing of person-controlled content in group context | |
| US11436417B2 (en) | Providing access to user-controlled resources by automated assistants | |
| US10572476B2 (en) | Refining a search based on schedule items | |
| JP6163266B2 (en) | Automatic activation of smart responses based on activation from remote devices | |
| US20200110915A1 (en) | Systems and methods for conducting multi-task oriented dialogues | |
| WO2008123757A1 (en) | Method for inferring personal relationship by using readable data, and method and system for attaching tag to digital data by using the readable data | |
| WO2015109249A1 (en) | Methods and systems for contact management | |
| EP3506129A1 (en) | Information processing apparatus, information processing method, and program | |
| EP3885937A1 (en) | Response generation device, response generation method, and response generation program | |
| US20210404830A1 (en) | Navigation device, vehicle, navigation method, and non-transitory storage medium | |
| US11144887B2 (en) | Dynamic event naming | |
| CN109558539A (en) | A kind of information recommendation method, device and computer readable storage medium | |
| CN111008720A (en) | Restaurant reservation method and terminal based on multiple rounds of voice interaction | |
| US10666595B2 (en) | Method and system for integration of shared calendars with messaging applications | |
| CN111782780A (en) | Booking method and terminal based on multi-round voice interaction | |
| US20140365249A1 (en) | System and method for providing location based social dining matching | |
| US20180181920A1 (en) | Method, system and non-transitory computer-readable recording medium for assisting schedule management | |
| US11983676B2 (en) | Dynamic event naming | |
| CN111784012A (en) | Ticket booking method and terminal based on multi-round language interaction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ying Zhenkai Inventor before: Ying Yilun |
|
| CB03 | Change of inventor or designer information | ||
| 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 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant after: Botai vehicle networking technology (Shanghai) Co.,Ltd. Address before: Room 208, building 4, 1411 Yecheng Road, Jiading District, Shanghai, 201821 Applicant before: SHANGHAI PATEO ELECTRONIC EQUIPMENT MANUFACTURING Co.,Ltd. |
|
| CB02 | Change of applicant information |