CN115512705A - Voice interaction method, server and computer readable storage medium - Google Patents

Voice interaction method, server and computer readable storage medium Download PDF

Info

Publication number
CN115512705A
CN115512705A CN202211465546.5A CN202211465546A CN115512705A CN 115512705 A CN115512705 A CN 115512705A CN 202211465546 A CN202211465546 A CN 202211465546A CN 115512705 A CN115512705 A CN 115512705A
Authority
CN
China
Prior art keywords
node
applet
vehicle
target
round
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
Application number
CN202211465546.5A
Other languages
Chinese (zh)
Inventor
樊骏锋
宁洪珂
赵群
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Xiaopeng Motors Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Motors Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiaopeng Motors Technology Co Ltd filed Critical Guangzhou Xiaopeng Motors Technology Co Ltd
Priority to CN202211465546.5A priority Critical patent/CN115512705A/en
Publication of CN115512705A publication Critical patent/CN115512705A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/3332—Query translation
    • G06F16/3334—Selection or weighting of terms from queries, including natural language queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3343—Query execution using phonetics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/353—Clustering; Classification into predefined classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation
    • 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
    • G10L15/26—Speech to text systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W2040/089—Driver voice
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/21—Voice
    • 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 discloses a voice interaction method, which comprises the following steps: receiving a vehicle-forwarded voice request comprising an associated first-round conversation and second-round conversation; processing a first round of conversation, and determining a target vehicle-mounted system applet and an applet flow truncation node which respond to a voice request; determining a target function page for realizing voice interaction in a target vehicle-mounted system applet according to the applet flow cut-off node; and supplementing information of the small program flow truncation node according to the second wheel call so as to complete voice interaction through the vehicle display target function page. In the application, after the server processes the received voice request, the applet and the applet flow truncation node of the target vehicle-mounted system can be determined, and the target function page is determined and displayed through the vehicle according to the supplementary information in the second round of conversation. The voice interaction method can identify the function requirements of the voice requests in multiple rounds of conversation of the user, namely, the user can directly reach the page of the target function of the applet, so that the voice interaction process is more convenient.

Description

Voice interaction method, server and computer readable storage medium
Technical Field
The present application relates to the field of vehicle-mounted voice technologies, and in particular, to a voice interaction method, a server, and a computer-readable storage medium.
Background
Currently, in-vehicle voice technology may support user interaction within a vehicle cabin via voice, such as controlling vehicle components or interacting with components in an in-vehicle system user interface. In a scene that a user performs voice interaction with a vehicle-mounted system applet, only a single-round voice control applet is supported to be opened or closed, and if the user needs to realize a specific function in the applet, manual operation is often required for many times, so that the fluency and convenience of voice interaction are influenced, and the user experience is poor.
Disclosure of Invention
The application provides a voice interaction method, a server and a computer readable storage medium.
The voice interaction method comprises the following steps:
receiving a voice request forwarded by a vehicle, the voice request including associated first and second round conversations;
processing the first round of conversation, and determining a target vehicle-mounted system applet and an applet flow truncation node responding to the voice request;
determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node;
and supplementing the information of the applet process truncation node according to the second wheel dialog so as to display the target function page through the vehicle to complete the voice interaction.
Therefore, in the application, when a user needs to realize a specific function in the applet, the first round of interaction is carried out through voice and a vehicle, after the server processes a received voice request, a target vehicle-mounted system applet and an applet flow cut-off node capable of realizing a function requirement can be determined, a target function page with a realization function in the applet is determined according to information of the applet flow cut-off node supplemented in the second round of conversation, and the voice interaction process can be completed through the vehicle display target function page. The voice interaction method can identify the functional requirements of the voice requests in multiple rounds of conversations of the user, the user can operate the corresponding vehicle-mounted system applet and directly reach the page of the target function without sending the voice request with complete information in one round of conversations, so that the expression of the user is closer to the expression habit of natural voice, meanwhile, the functional requirements can be realized without multiple times of manual operation of the user, the convenience of voice interaction and the use efficiency of the vehicle-mounted system applet are improved, and the user experience is improved.
The processing the first round of dialogue to determine a target vehicle-mounted system applet and applet flow cutoff node responding to the voice request includes:
and determining the small program of the target vehicle-mounted system and the small program flow truncation node according to the matching relation between the first slot position information obtained by processing the first wheel dialogue and the small program flow node.
Therefore, the target vehicle-mounted system applet and the applet flow truncation node in the flow can be determined according to the matching relation between the first slot position information and the applet flow node processed in the first round of dialogue, the first slot position information is inherited to the second round of dialogue, the user does not need to repeat in the second round of dialogue, the target function page subsequent determination process is facilitated, and convenience and efficiency of voice interaction in the vehicle are improved.
The determining the target vehicle-mounted system applet and the applet flow truncation node according to the matching relationship between the first slot position information obtained by processing the first wheel dialogue and the applet flow node comprises the following steps:
determining the target vehicle-mounted system applet according to the first slot position information;
matching the first slot position information according to the small program flow node matching relation of the small program of the target vehicle-mounted system to obtain a plurality of corresponding flow nodes, wherein each corresponding flow node corresponds to the positioning identifier of one functional page;
and determining the small program flow truncation node according to the matching processing result, wherein the small program flow truncation node is a flow node next to a corresponding flow node before the first non-incremental value in the matching processing result.
Therefore, the target vehicle-mounted system small program and the small program flow truncation node in the flow can be determined according to the matching relation between the first slot position information processed in the first round of conversation and the small program flow node. The corresponding process node is matched with the positioning identifier of the function page, so that the target function page and the vehicle-mounted system display small program page can be conveniently determined. The convenience and the efficiency of voice interaction in the vehicle are improved.
The determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node comprises the following steps:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and the small program of the target vehicle-mounted system small program;
under the condition that the interval time between the first round of conversation and the second round of conversation is less than preset time, performing series combination on a plurality of corresponding process nodes and the small program process truncation node to determine a target process node;
and determining the target function page according to the positioning identifier corresponding to the target process node.
Therefore, the small program flow node corresponding to the second slot position information obtained by processing in the second round of conversation can be determined as the small program flow truncation node in the small program flow of the target vehicle-mounted system, so that the slot position information in the second round of conversation can be supplemented into the missing node information in the first round of conversation, and the target flow node and the target function page can be finally confirmed. The corresponding process node is matched with the positioning identifier of the function page, so that the target function page and the vehicle-mounted system display small program page can be conveniently determined. The convenience and the efficiency of voice interaction in the vehicle are improved.
The supplementing the information of the applet process truncation node according to the second wheel conversation so as to complete the voice interaction by displaying the target function page through the vehicle comprises:
assigning corresponding slot position information to each corresponding process node according to the first slot position information;
supplementing the slot position information of the small program flow truncation node according to the second slot position information, and determining the slot position information of the target flow node according to the slot position information of each corresponding flow node and the slot position information of the small program flow truncation node so as to display the target function page through the vehicle to complete the voice interaction.
Therefore, according to the first slot position information and the second slot position information, slot position information is given to the process nodes and the process truncation nodes of multiple rounds of conversations in the voice request sent by the user, and the slot position information of the target process node can be obtained, so that the vehicle can complete the display of the target function page and complete voice interaction.
The determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node comprises the following steps:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and the small program of the target vehicle-mounted system small program;
acquiring the jump relation of the applet truncation node under the condition that the interval time of the first round of dialogue and the second round of dialogue is greater than or equal to the preset time;
determining the target process node according to the jump relation;
and determining the target function page according to the positioning identifier of the target process node.
Therefore, the second slot position information can be obtained by processing the second wheel conversation, and the process node corresponding to the second slot position information is determined according to the matching relation between the target vehicle-mounted small program and the small program process node. When the interval time between the first round of conversation and the second round of conversation is greater than or equal to the preset time, the fact that the user has the requirement for browsing the page corresponding to the applet intercepting node in the preset time is indicated, the jump relation of the applet intercepting node is obtained to determine the target process node, the target function page is determined according to the jump relation, the target function page is conveniently displayed by a subsequent vehicle, and voice interaction is completed.
The supplementing the information of the applet process truncation node according to the second wheel conversation so as to complete the voice interaction by displaying the target function page through the vehicle comprises:
determining an information supplement function page corresponding to the small program flow cut-off node according to the first wheel conversation, so that a user can select to supplement the information of the small program flow cut-off node by displaying the information supplement function page through the vehicle;
and determining slot position information of the target process node according to the first slot position information and second slot position information obtained by processing the second wheel dialogue aiming at the information supplement function page, so as to display the target function page through the vehicle and finish the voice interaction.
Therefore, the information of the applet truncation node can be supplemented by the second wheel dialog according to the information supplementing function page corresponding to the applet truncation node, the second slot position information obtained by the second wheel dialog is filled into the process nodes in the series connection relation to determine the slot position information of the target process node, and finally the target page is displayed through the vehicle to finish voice interaction.
The receiving of the voice request forwarded by the vehicle comprises:
after receiving the first round of dialogue forwarded by the vehicle, identifying the sound zone information of the first round of dialogue in a vehicle cabin;
and if the sound zone information is a main driving sound zone and the vehicle is in a driving state, feeding back to a user that the target vehicle-mounted system applet function is unavailable.
Therefore, the sound zone information of the first round of conversation can be identified, the use of the target vehicle-mounted system applet function by the main driving user is limited in the driving state, and the driving safety is guaranteed.
The method further comprises the following steps:
and if the sound zone information is the main driving sound zone and the vehicle gear information is in the P gear state, receiving the second round conversation forwarded by the vehicle.
Therefore, the voice zone information can be identified, if the first round of conversation is sent by the main driving user, and the vehicle is in the P-gear state, the second round of conversation initiated by the main driving can be received, the requirement of the user for using the vehicle-mounted system applet function is met under the condition that the driving safety is guaranteed, and the user use experience is improved.
The method further comprises the following steps:
and if the sound zone information is a non-main driving sound zone, receiving the second round of conversation forwarded by the vehicle, and feeding back a driving safety prompt to a user.
Therefore, the voice zone information can be identified, if the first round of conversation is sent by a non-main driving user, the second round of conversation initiated by the main driving can be received, and the safety prompt is fed back to the user, so that the requirement of the user for using the vehicle-mounted system applet function is met under the condition of ensuring the driving safety, and the use experience of the user is improved.
The server of the application comprises a processor and a memory, wherein the memory stores a computer program, and the computer program realizes the method when being executed by the processor.
The computer-readable storage medium of the present application stores a computer program that, when executed by one or more processors, implements the method described above.
Additional aspects and advantages of embodiments of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of embodiments of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a voice interaction method according to the present application;
FIG. 2 is a second schematic flow chart of the voice interaction method of the present application;
fig. 3 is a third flowchart of the voice interaction method of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the embodiments of the present application.
Referring to fig. 1 and fig. 2, the present application provides a voice interaction method, including:
01: receiving a voice request forwarded by a vehicle, the voice request including associated first-turn conversations and second-turn conversations;
02: processing a first round of conversation, and determining a target vehicle-mounted system applet and an applet flow truncation node which respond to a voice request;
03: determining a target function page for realizing voice interaction in a target vehicle-mounted system applet according to the applet process cut-off node;
04: and supplementing information of the small program flow truncation node according to the second wheel call so as to complete voice interaction through the vehicle display target function page.
The application also provides a server comprising a memory and a processor. The voice processing method can be realized by the server. Specifically, the memory stores a computer program, and the processor is configured to receive a voice request forwarded by a vehicle, including a first round of dialog and a second round of dialog associated with each other, process the first round of dialog, determine a target vehicle-mounted system applet and an applet flow truncation node that respond to the voice request, determine a target function page for implementing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node, and supplement information of the applet flow truncation node according to the second round of dialog, so as to complete voice interaction by displaying the target function page by the vehicle.
With the development and popularization of vehicle electronic technology, a display device of a vehicle, such as a central control display screen, is greatly enriched in interactive functions, and more services are accessed to a vehicle terminal in a small program form. The introduction of the small program platform meets the diverse experiences of the driving process of the driver and the passengers. However, voice operation only provides that a user opens an applet through voice, and the operation after entering the applet can still only be completed manually by the user, so that the convenience is poor and the user experience is poor. In the related technology, in order to facilitate user operation, the elements of the applet are directly reached through voice interaction, that is, the process nodes are set, and the process nodes are connected in series according to the process sequence, so that the applet page containing the elements required by the user voice request is finally obtained. Referring to table 1, taking an applet catering applet a related to a certain shopping as an example, a commodity purchasing process can be divided into the following process nodes:
TABLE 1
Figure 479438DEST_PATH_IMAGE001
In the related art, a default user sends a single-round voice request with clear requirements, and the situation that the user may need to pass through multiple rounds of voice requests to completely provide information of the slot positions of the nodes of the small program flow is ignored. For example, in the example above, the user makes a voice request "I want to click on restaurant applet A to the company". The user decides to order food by using the catering applet A, but does not explicitly select commodities, and still wants to select specific commodities by combining the commodity pictures. At this time, the flow nodes connected in series according to the flow sequence stop at the node three, and return to the previous node of the node three, namely the node two, corresponding to the index bar search page, and the user needs to manually input or send a voice request to add the commodity a into the shopping cart so as to add the commodity information. And the subsequent process node information also needs to be manually input by the user or make a voice request again. However, the receiving address information is provided in the voice request sent by the user at first, but the flow is interrupted at the node three and cannot be filled in the node six, so that the voice interaction process cannot be smoothly performed, and the user experience is poor.
The method and the device can support direct shopping applet elements according to multiple rounds of voice request contents. As shown in fig. 2, in one example of the present application, multiple rounds of dialog involve multiple rounds of voice requests made by a user. For example, the first turn of the dialog is "I want to click on restaurant applet A to company" and the user can be directed to the search page of restaurant applet A. The second round of the conversation is "click on article a Bar", which can be the user until the user has clicked on article a and set the address as the final settlement page for the company. The scheme can realize the direct reaching of all elements in multiple rounds of conversations, and a user does not need to provide information of all nodes in one round of conversations or repeat voice of the same node information in the multiple rounds of conversations.
The vehicle-mounted system applet related in the application is an applet which is oriented to a user and runs on a vehicle according to personal needs, and the vehicle does not need to be installed and adapted in advance. The target vehicle-mounted system applet is a vehicle-mounted system applet capable of responding to a voice request of a user and fulfilling a voice request function requirement. The small program flow truncation node is a node for changing the sequential jumping relation of the flow nodes and can connect the nodes included in the two-round voice requests. The target function page is a page which has the capability of realizing the function requirement of the voice request in the target vehicle-mounted system applet.
After receiving the voice request of shopping, the server can determine a target vehicle-mounted system applet and an applet flow truncation node corresponding to the voice request according to the matched flow node, and accordingly determines a target function page for realizing the voice request. Furthermore, the information of the cut-off node of the small program flow can be supplemented according to the second round of conversation, and finally, a target function page can be displayed through a vehicle to finish the voice interaction process. The voice interaction method can enable a user to realize specific functions of the vehicle-mounted system applet without carrying out excessive manual operation.
In summary, in the present application, when a user needs to implement a specific function in an applet, through a first round of interaction between voice and a vehicle, after a server processes a received voice request, a target vehicle-mounted system applet and an applet flow cutoff node that can implement a function requirement can be determined, and a target function page having an implementation function in the applet can be determined according to information of the applet flow cutoff node supplemented in a second round of conversation, that is, a voice interaction process can be completed through a vehicle display target function page. The voice interaction method can identify the functional requirements of the voice requests in multiple rounds of conversations of the user, the user is not required to send out the voice request with complete information in one round of conversation, the corresponding vehicle-mounted system applet can be operated and the page with the target function can be directly reached, the expression of the user is enabled to be closer to the expression habit of natural voice, meanwhile, the functional requirements can be achieved without multiple times of manual operation of the user, the convenience of voice interaction and the use efficiency of the vehicle-mounted system applet are improved, and the user experience is improved.
Step 02 includes:
and determining the applet and the applet flow cut-off node of the target vehicle-mounted system according to the matching relation between the first slot position information obtained by processing the first wheel call and the applet flow node.
The processor is used for determining the target vehicle-mounted system small program and small program flow truncation nodes according to the matching relation between the first slot position information obtained by processing the first wheel conversation and the small program flow nodes.
Specifically, referring to fig. 2, the voice request received by the server for the first time may be regarded as a first round of conversation, and the processed slot position information is the first slot position information. Furthermore, first slot position information extracted from a first round of conversation of a user voice request is matched with the small program flow node, when the user sends the voice request to initiate the first round of conversation, a target vehicle-mounted system small program with the capacity of realizing the voice request function requirement can be determined according to the extracted first slot position information, and the small program flow cut-off node is determined according to the small program flow node information.
As shown in table 1, all functions of the applets accessed to the vehicle-mounted system can be combed, the service field where the user voice request intention information is located is analyzed, and all possible applet process node hopping relationships are sorted out to determine the applet process nodes. For example, in the above example, when the first round of the dialog is "i want to click on the restaurant applet a to the company" in the voice request from the user, in the first slot information, "restaurant applet a" may be matched to node two. When the small program flow is carried out to the third node, the first slot position information of 'selected product and specification' which can be matched with the third node cannot be extracted, but the first slot position information 'company' of 'adding a receiving address' which is matched with the sixth node exists. The small program flow truncation node can be determined according to the jump relation between the node three and the node six.
Therefore, the target vehicle-mounted system applet and the applet in the process can be determined according to the matching relation between the first slot position information and the applet process node obtained by processing in the first round of dialogue, the first slot position information is inherited to the second round of dialogue, the user does not need to repeat in the second round of dialogue, the subsequent process of determining the target function page is facilitated, and the convenience and the efficiency of voice interaction in the vehicle are improved.
The step of determining the target vehicle-mounted system applet and applet flow truncation node according to the matching relationship between the first slot position information obtained by processing the first wheel dialogue and the applet flow node comprises the following steps:
determining a target vehicle-mounted system applet according to the first slot position information;
matching the first slot position information according to the small program flow node matching relation of the small program of the target vehicle-mounted system to obtain a plurality of corresponding flow nodes;
and determining the small program flow truncation node according to the matching processing result.
The processor is used for determining a target vehicle-mounted system applet according to the first slot position information, performing matching processing on the first slot position information according to the applet process node matching relation of the target vehicle-mounted system applet to obtain a plurality of corresponding process nodes, and determining an applet process cut-off node according to a matching processing result.
Specifically, referring to fig. 2, taking the catering applet a as an example, as shown in table 1, each flow node has a corresponding positioning identifier, and the positioning identifier may be a uniform resource locator, and the type of the positioning identifier is not limited herein. When a user sends a voice request that the user wants to click on a catering applet A to a company, the first slot position information is processed to be the catering applet A and the company, and the target vehicle-mounted system applet is judged to be the catering applet A. As shown in table 1, the flow node matching relationship of the target applet "diet applet a" is as follows, that is, node one corresponds to "Open", node two corresponds to "Search", node three corresponds to "specificities Number", node four corresponds to "Add to cart", node five corresponds to "Order", node six corresponds to "Add address", node seven corresponds to "Confirm page", node eight corresponds to "Pay", and node nine corresponds to "Close". According to the matching relation, the first slot position information can be matched to obtain a plurality of corresponding process nodes, namely a first node corresponding to the catering applet A, a second node corresponding to a direct Search page, a sixth node corresponding to the company, each corresponding process node corresponds to a positioning identifier, namely the positioning identifiers corresponding to the process nodes corresponding to the first slot position information comprise an Open corresponding to the first node, a Search corresponding to the second node and an address corresponding to the sixth node.
In the above example, the user sends a voice request "i want to click on a catering applet a to a company" and "catering applet a" can be matched with a node two. When the small program flow is carried out to the third node, the first slot position information of 'product selection and specification' which can be matched with the third node cannot be extracted, but the first slot position information 'company' of 'adding a receiving address' which is matched with the sixth node exists, and the sixth node is the first non-incremental flow node in the matching processing result.
Further, the applet flow truncation node is a flow node next to a previous corresponding flow node of the first non-incremental value corresponding flow node in the matching processing result. And determining a next flow node in the small program flow, namely a node three, as a small program flow truncation node if the first non-incremental value flow node is a node six and the previous corresponding flow node is a node two as the matching processing result of the first slot position information in the voice request.
Therefore, the target vehicle-mounted system small program and the small program flow truncation node in the flow can be determined according to the matching relation between the first slot position information processed in the first round of conversation and the small program flow node. The corresponding process node is matched with the positioning identifier of the function page, so that the target function page and the vehicle-mounted system display small program page can be conveniently determined. The convenience and the efficiency of voice interaction in the vehicle are improved.
Step 03 comprises:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and the small program of the target vehicle-mounted system small program;
under the condition that the interval time between the first round of conversation and the second round of conversation is less than the preset time, performing series combination on a plurality of corresponding process nodes and the small program process cut-off nodes to determine a target process node;
and determining a target function page according to the positioning identifier corresponding to the target process node.
The processor is used for determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and a target vehicle-mounted system small program, and performing series combination on a plurality of corresponding process nodes and the small program process cut-off node under the condition that the interval time between the first round of conversation and the second round of conversation is less than preset time, determining a target process node, and determining a target function page according to a positioning identifier corresponding to the target process node.
Specifically, referring to fig. 2, after the first wheel session is ended in the above example, the voice request sent again by the user is regarded as a second wheel session, and when the voice request is "click to a commodity a bar", the second slot information obtained by processing is "commodity a" and "commodity" where "commodity a" and "commodity a" are default to 1, and the number slot value is "1". And matching the obtained second slot position information to obtain a plurality of corresponding process nodes, namely a node three, namely a commodity a, and a node four, namely 1. And determining the flow node corresponding to the second slot position information as the small program flow cut-off node in order to enable the flow node corresponding to the voice request in the second round of conversation to be successfully connected in series with the small program flow cut-off node obtained after the first round of conversation is processed. If the interval time between the first round of conversation and the second round of conversation is less than the preset time with a certain duration, the fact that the user does not have the requirement for browsing the page corresponding to the applet intercepting node within the preset time is shown. The corresponding small program flow nodes obtained in the two-round conversation processing and the small program flow interception nodes can be combined in series according to the node sequence, and the target flow node is determined. The preset duration may be set to 10 seconds, or may be changed according to the length of the workflow of the target applet, which is not limited herein.
After the target process node to be finally executed is determined, as shown in table 1, each process node for purchasing a commodity by using the catering applet a has a corresponding positioning identifier. The target function page needing to be displayed by the vehicle can be determined to be a payment information confirming page according to the target process node, namely the positioning identifier 'Confirm payment' corresponding to the node seven.
Therefore, the small program flow node corresponding to the second slot position information obtained by processing in the second round of conversation can be determined as the small program flow truncation node in the small program flow of the target vehicle-mounted system, so that the slot position information in the second round of conversation can be supplemented into the missing node information in the first round of conversation, and the target flow node and the target function page can be finally confirmed. The corresponding process node is matched with the positioning identifier of the function page, so that the target function page and the vehicle-mounted system display small program page can be conveniently determined. The convenience and the efficiency of voice interaction in the vehicle are improved.
Step 04 comprises:
assigning corresponding slot position information to each corresponding process node according to the first slot position information;
and supplementing the slot position information of the small program flow truncation node according to the second slot position information, and determining the slot position information of the target flow node according to the slot position information of each corresponding flow node and the slot position information of the small program flow truncation node so as to complete voice interaction by displaying the target function page through the vehicle.
The processor is used for assigning corresponding slot position information to each corresponding process node according to the first slot position information, supplementing slot position information of the small program process cut-off node according to the second slot position information, and determining slot position information of the target process node according to the slot position information of each corresponding process node and the slot position information of the small program process cut-off node so as to complete voice interaction through the vehicle display target function page.
Specifically, referring to fig. 2, first slot information in the first round of session may be extracted, and after the matching of the first slot information and the corresponding relationship of the process node is completed, slot information is given to each node. In the above example, for the voice request "i want to click on a restaurant applet a to a company" in the first round of conversation, the slot position information is given to each node, and it can be obtained that the node one is "restaurant applet a", the node two is "search", and the node six is "company".
Similarly, the second slot information in the second round of conversation may be extracted to supplement the slot information of the applet flow truncated node. In the above example, for the voice request in the second round of conversation, "click to purchase article a bar", the three-article slot information of the node is "article a" and the number slot information is "1" by semantic default.
Further, the slot position information of the target process node is determined according to the slot position information of the corresponding process node and the applet process truncation node, namely the slot position information of the node seven is 'payment confirmation information'. After the slot position information of the target process node is obtained, the target function page can be displayed through the vehicle, and voice interaction is completed.
Therefore, the slot position information can be given to the flow nodes and the flow truncation nodes of the multi-turn conversation in the voice request sent by the user according to the first slot position information and the second slot position information, and the slot position information of the target flow node can be obtained, so that the vehicle can complete the display of the target function page and complete the voice interaction.
Step 03 further comprises:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to the matching relation between the second slot position information obtained by processing the second wheel dialogue and the small program process node of the target vehicle-mounted system small program;
acquiring the jump relation of the small program cut-off node under the condition that the interval time between the first round of conversation and the second round of conversation is greater than or equal to the preset time;
determining a target process node according to the jump relation;
and determining a target function page according to the positioning identifier of the target process node.
The processor is used for determining a process node corresponding to the second slot position information as a small program process truncation node according to a matching relation between the second slot position information obtained by processing the second wheel conversation and a small program process node of a target vehicle-mounted system small program, acquiring a skip relation of the small program truncation node under the condition that the interval time between the first round of conversation and the second round of conversation is greater than or equal to preset time, determining the target process node according to the skip relation, and finally determining a target function page according to a positioning identifier of the target process node.
Specifically, referring to fig. 2, the second wheel session may be processed to obtain second slot position information. In the above example, the user sends a second round of conversation "click a good a bar", and according to the applet process node matching relationship of the target onboard system applet, as shown in table 1, the process node corresponding to the second slot position information may be determined as a process cut-off node, that is, node three.
In the voice request sent by the user, if the interval time between the first round of conversation and the second round of conversation is greater than or equal to the preset time, the requirement that the user browses the page corresponding to the applet intercepting node exists in the preset time is indicated. The preset duration may be set to 10 seconds, or may be changed according to the length of the workflow of the target applet, which is not limited herein. In the above example, the first turn of the dialog of the user is "i want to order the restaurant applet a to the company", and the cut-off node of the applet has a jump relationship from the node three to the node six, which indicates that the user has determined the ordering address although the ordering content is not clear. And according to the jumping relation, confirming that the node behind the node six is the target process node, namely the node seven. And finally, obtaining a page with a target function of 'payment information confirmation' according to the positioning identifier 'Confirm payment' of the node seven.
Therefore, the second slot position information can be obtained by processing the second wheel conversation, and the process node corresponding to the second slot position information is determined according to the matching relation between the target vehicle-mounted small program and the small program process node. When the interval time of the first round of conversation and the second round of conversation is greater than or equal to the preset time, and the fact that the user has the requirement for browsing the page corresponding to the applet intercepting node in the preset time is indicated, the skip relation of the applet intercepting node is obtained to determine a target process node, and therefore a target function page is determined, so that a subsequent vehicle can display the target function page, and voice interaction is completed.
Step 04 further comprises:
determining an information supplement function page corresponding to the small program flow cut-off node according to the first wheel call, and displaying the information supplement function page through a vehicle to enable a user to select information for supplementing the small program flow cut-off node;
and determining the slot position information of the target process node according to the first slot position information and second slot position information obtained by processing a second wheel conversation aiming at the information supplement function page so as to finish voice interaction by displaying the target function page through the vehicle.
The processor is used for determining a process node corresponding to the second slot position information as a small program process cut-off node according to a matching relation between the second slot position information obtained by processing the second wheel conversation and a small program process node of a target vehicle-mounted system small program, acquiring a skip relation of the small program cut-off node under the condition that the interval time between the first round of conversation and the second round of conversation is greater than or equal to preset time, determining the target process node according to the skip relation, and determining a target function page according to a positioning identifier of the target process node
Specifically, referring to fig. 2, for the two-round conversations of the above example, the first round of conversation is "i want to click on the catering applet a to the company", the second round of conversation is "click on the commodity a bar", and the cut-off node of the applet process is node three. And if the interval time between the first round of conversation and the second round of conversation is greater than or equal to the preset time, indicating that the user has the requirement of browsing the page corresponding to the applet intercepting node. The user can cut off the information of the node before the node, namely the node two, corresponding to the information supplement function page displayed by the vehicle, and initiate a second round of conversation after the preset time so as to supplement the information of the small program flow cut-off node, namely the node three.
Further, the state that the first node to the sixth node are all filled with the slot information can be obtained according to the first slot information in the first round of conversation and the second slot information in the second round of conversation in the complementary flow node. And the slot position information of the target process node, namely the node seven, can be determined, and finally the voice interaction is completed by displaying a target function page through the vehicle.
Therefore, the information of the applet intercepting node can be supplemented by the second wheel telephone according to the information supplementing function page corresponding to the applet intercepting node, the second slot position information obtained by the second wheel telephone is filled into the process node with information loss in the series relation, so that the slot position information of the target process node is determined, and finally the target page is displayed through the vehicle to finish voice interaction.
Referring to fig. 3, receiving a voice request forwarded by a vehicle includes:
05: after receiving a first round of dialogue forwarded by a vehicle, identifying the sound zone information of the first round of dialogue in a vehicle cabin;
06: and if the sound zone information is the main driving sound zone and the vehicle is in a driving state, feeding back the unavailable function of the target vehicle-mounted system applet to the user.
The processor is used for identifying the sound zone information of the first round of dialogue in the vehicle cabin after receiving the first round of dialogue forwarded by the vehicle, and if the sound zone information is the main driving sound zone and the vehicle is in a driving state, the processor feeds back the target vehicle-mounted system applet function unavailable to the user.
Specifically, the server treats the first receipt of a vehicle-forwarded voice request as a first turn of a conversation. After the first dialogue is received, the sound zone information of the first round of dialogue in the vehicle cabin is identified, and the position of the user initiating the first round of dialogue in the vehicle is judged, namely the user is identified to be a main driving mode, a secondary driving mode or a rear row mode.
When the recognized sound zone information is displayed as the main driving sound zone, the driving state of the vehicle is judged. When the vehicle is in a driving state, in order to ensure driving safety, the main driving user cannot use the function of the target vehicle-mounted system applet. The user may be fed back that the target in-vehicle system applet function is not available.
Therefore, the sound zone information of the first round of conversation can be identified, the use of the target vehicle-mounted system applet function by the main driving user is limited in the driving state, and the driving safety is guaranteed.
Referring to fig. 3, the method further includes:
07: and if the sound zone information is the main driving sound zone and the vehicle gear information is in the P gear state, receiving a second round of dialogue forwarded by the vehicle.
The processor is used for receiving a second round of dialogue forwarded by the vehicle if the sound zone information is the main driving sound zone and the vehicle gear information is in a P gear state.
Specifically, after the first dialogue is received, the sound zone information of the first round of dialogue in the vehicle cabin is identified, and when the identified sound zone information is displayed as a main driving sound zone, the driving state of the vehicle is judged. When the vehicle gear information is in the P gear, i.e., the vehicle is in a stopped state, the primary driver will not be restricted from using the target on-board system applet function. Thus, the primary user again makes a voice request that is forwarded by the vehicle to the server as a second turn of the conversation.
Therefore, the voice zone information can be identified, if the first round of conversation is sent by the main driving user, and the vehicle is in the P-gear state, the second round of conversation initiated by the main driving can be received, the requirement of the user for using the vehicle-mounted system applet function is met under the condition that the driving safety is guaranteed, and the user use experience is improved.
Referring to fig. 3, the method further includes:
08: and if the sound zone information is the non-main driving sound zone, receiving a second round of dialogue forwarded by the vehicle, and feeding back a driving safety prompt to the user.
And the processor is used for receiving a second round of dialogue forwarded by the vehicle and feeding back a driving safety prompt to the user if the sound zone information is a non-main driving sound zone.
Specifically, after receiving the first dialogue, recognizing the sound zone information of the first round of dialogue in the vehicle cabin, and when the recognized sound zone information is displayed as a non-main driving sound zone, receiving the second round of dialogue initiated by the user in the sound zone for ensuring driving safety, and feeding back driving safety prompts to the user, wherein the similar voice prompt of 'not influencing normal driving of the driver in the operation process' is included.
Therefore, the information of the sound zone can be identified, if the first round of conversation is sent by a non-main driving user, the second round of conversation initiated by the main driving can be received, and the safety prompt is fed back to the user, so that the requirement of the user for using the vehicle-mounted system applet function is met under the condition of ensuring the driving safety, and the use experience of the user is improved.
The computer-readable storage medium of the present application stores a computer program that, when executed by one or more processors, implements the method described above.
In the description herein, references to the description of the terms "above," "specifically," "similarly," "further," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (12)

1. A method of voice interaction, comprising:
receiving a voice request forwarded by a vehicle, the voice request including associated first and second round conversations;
processing the first round of conversation, and determining a target vehicle-mounted system applet and an applet flow cut-off node responding to the voice request;
determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node;
and supplementing the information of the applet process truncation node according to the second wheel conversation so as to display the target function page through the vehicle to complete the voice interaction.
2. The method of claim 1, wherein the processing the first round of dialog to determine a target on-board applet and applet flow truncation node to respond to the voice request comprises:
and determining the small program of the target vehicle-mounted system and the small program flow truncation node according to the matching relation between the first slot position information obtained by processing the first wheel dialogue and the small program flow node.
3. The voice interaction method according to claim 2, wherein the determining the target vehicle-mounted system applet and the applet flow truncation node according to a first slot information and applet flow node matching relationship obtained by processing the first wheel session comprises:
determining the target vehicle-mounted system applet according to the first slot position information;
matching the first slot position information according to the small program flow node matching relation of the small program of the target vehicle-mounted system to obtain a plurality of corresponding flow nodes, wherein each corresponding flow node corresponds to the positioning identifier of one functional page;
and determining the small program flow truncation node according to the matching processing result, wherein the small program flow truncation node is a flow node next to a corresponding flow node before the first non-incremental value in the matching processing result.
4. The voice interaction method according to claim 3, wherein the determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node comprises:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and the small program of the target vehicle-mounted system small program;
under the condition that the interval time between the first round of conversation and the second round of conversation is less than preset time, performing series combination on a plurality of corresponding process nodes and the small program process truncation node to determine a target process node;
and determining the target function page according to the positioning identifier corresponding to the target process node.
5. The voice interaction method according to claim 4, wherein the supplementing the information of the applet process truncation node according to the second wheel conversation to complete the voice interaction by the vehicle displaying the target function page comprises:
assigning corresponding slot position information to each corresponding process node according to the first slot position information;
supplementing the slot position information of the small program flow truncation node according to the second slot position information, and determining the slot position information of the target flow node according to the slot position information of each corresponding flow node and the slot position information of the small program flow truncation node so as to display the target function page through the vehicle to complete the voice interaction.
6. The voice interaction method according to claim 3, wherein determining a target function page for realizing voice interaction in the target vehicle-mounted system applet according to the applet flow truncation node comprises:
determining a process node corresponding to the second slot position information as a small program process cut-off node according to a small program process node matching relation between the second slot position information obtained by processing the second wheel conversation and the small program of the target vehicle-mounted system small program;
acquiring the jump relation of the applet truncation node under the condition that the interval time of the first round of dialogue and the second round of dialogue is greater than or equal to the preset time;
determining the target process node according to the jump relation;
and determining the target function page according to the positioning identifier of the target process node.
7. The voice interaction method according to claim 6, wherein the supplementing the information of the applet process truncation node according to the second wheel conversation to complete the voice interaction by the vehicle displaying the target function page comprises:
determining an information supplement function page corresponding to a process node before the small program process cut-off node according to the first wheel conversation, so that a user can select to supplement the information of the small program process cut-off node by displaying the information supplement function page through the vehicle;
and determining slot position information of the target process node according to the first slot position information and second slot position information obtained by processing the second wheel dialogue aiming at the information supplement function page, so as to display the target function page through the vehicle and finish the voice interaction.
8. The method of claim 1, wherein receiving the vehicle-forwarded voice request comprises:
after receiving the first round of dialogue forwarded by the vehicle, identifying the sound zone information of the first round of dialogue in a vehicle cabin;
and if the sound zone information is a main driving sound zone and the vehicle is in a driving state, feeding back to a user that the target vehicle-mounted system applet function is unavailable.
9. The method of voice interaction according to claim 8, further comprising:
and if the sound zone information is the main driving sound zone and the vehicle gear information is in the P gear state, receiving the second round conversation forwarded by the vehicle.
10. The method of voice interaction according to claim 8, further comprising:
and if the sound zone information is a non-main driving sound zone, receiving the second round of conversation forwarded by the vehicle, and feeding back a driving safety prompt to a user.
11. A server, characterized in that the server comprises a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, carries out the method of any one of claims 1-10.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by one or more processors, implements the method of any one of claims 1-10.
CN202211465546.5A 2022-11-22 2022-11-22 Voice interaction method, server and computer readable storage medium Pending CN115512705A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211465546.5A CN115512705A (en) 2022-11-22 2022-11-22 Voice interaction method, server and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211465546.5A CN115512705A (en) 2022-11-22 2022-11-22 Voice interaction method, server and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN115512705A true CN115512705A (en) 2022-12-23

Family

ID=84514452

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211465546.5A Pending CN115512705A (en) 2022-11-22 2022-11-22 Voice interaction method, server and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN115512705A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992948A (en) * 2019-11-18 2020-04-10 上海博泰悦臻电子设备制造有限公司 Restaurant reservation method and terminal based on multiple rounds of voice interaction
CN112131885A (en) * 2019-06-24 2020-12-25 北京猎户星空科技有限公司 Semantic recognition method and device, electronic equipment and storage medium
CN112164401A (en) * 2020-09-18 2021-01-01 广州小鹏汽车科技有限公司 Voice interaction method, server and computer-readable storage medium
CN112634898A (en) * 2021-01-10 2021-04-09 上海极豆科技有限公司 Novel multi-round interaction method for vehicle-mounted voice service food purchasing function
CN113126765A (en) * 2021-04-22 2021-07-16 北京云迹科技有限公司 Multi-modal input interaction method and device, robot and storage medium
CN113646742A (en) * 2019-05-06 2021-11-12 谷歌有限责任公司 Generating and updating speech-based software applications using application templates
CN114299959A (en) * 2021-12-14 2022-04-08 北京捷通华声科技股份有限公司 Method and device for generating visual multi-turn conversations through voice commands
CN114898748A (en) * 2022-05-27 2022-08-12 广州小鹏汽车科技有限公司 Voice interaction method, vehicle and storage medium
CN114969299A (en) * 2022-06-21 2022-08-30 鼎富新动力(北京)智能科技有限公司 Conversation management method and device, computer equipment and storage medium
CN114999486A (en) * 2022-06-17 2022-09-02 广州小鹏汽车科技有限公司 Voice interaction method, vehicle and storage medium

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113646742A (en) * 2019-05-06 2021-11-12 谷歌有限责任公司 Generating and updating speech-based software applications using application templates
CN112131885A (en) * 2019-06-24 2020-12-25 北京猎户星空科技有限公司 Semantic recognition method and device, electronic equipment and storage medium
CN110992948A (en) * 2019-11-18 2020-04-10 上海博泰悦臻电子设备制造有限公司 Restaurant reservation method and terminal based on multiple rounds of voice interaction
CN112164401A (en) * 2020-09-18 2021-01-01 广州小鹏汽车科技有限公司 Voice interaction method, server and computer-readable storage medium
CN112634898A (en) * 2021-01-10 2021-04-09 上海极豆科技有限公司 Novel multi-round interaction method for vehicle-mounted voice service food purchasing function
CN113126765A (en) * 2021-04-22 2021-07-16 北京云迹科技有限公司 Multi-modal input interaction method and device, robot and storage medium
CN114299959A (en) * 2021-12-14 2022-04-08 北京捷通华声科技股份有限公司 Method and device for generating visual multi-turn conversations through voice commands
CN114898748A (en) * 2022-05-27 2022-08-12 广州小鹏汽车科技有限公司 Voice interaction method, vehicle and storage medium
CN114999486A (en) * 2022-06-17 2022-09-02 广州小鹏汽车科技有限公司 Voice interaction method, vehicle and storage medium
CN114969299A (en) * 2022-06-21 2022-08-30 鼎富新动力(北京)智能科技有限公司 Conversation management method and device, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
KR101747527B1 (en) Mirroring deeplinks
CN105306281A (en) Information processing method and client
CN111163326A (en) Virtual gift presenting method, virtual gift presenting device, medium, and electronic apparatus
JP7176218B2 (en) Information retrieval server, information retrieval system and information retrieval method
US10951553B2 (en) Updatable message channels/topics for customer service interaction
CN112612559A (en) Message processing method and device, electronic equipment and storage medium
CN110633815A (en) Car pooling method and device, electronic equipment and storage medium
CN109978522A (en) A kind of method, apparatus and equipment of order payment
KR20130062799A (en) Method for managing keyword information server
US20140114801A1 (en) User terminal for providing in-app service and in-app service server
CN115052169A (en) Interaction method, device, electronic equipment and computer readable medium
CN108122124B (en) Information pushing method, platform and system
CN111913769A (en) Application display method, device and equipment
CN114898748A (en) Voice interaction method, vehicle and storage medium
CN110505287B (en) Service-based business line recommendation method, device and storage medium
CN115512705A (en) Voice interaction method, server and computer readable storage medium
CN113342298A (en) Screen projection method, terminal, vehicle-mounted equipment and computer storage medium
WO2024045837A1 (en) Service providing method and apparatus, and terminal, storage medium and program product
US20190160942A1 (en) Powertrain optimization mobile application
CN115527537A (en) Voice interaction method, server and computer readable storage medium
CN114299947A (en) Generation method, vehicle control method, terminal device, and storage medium
CN115588433A (en) Voice interaction method, server and computer readable storage medium
CN114827704A (en) Vehicle-mounted system interaction method with vehicle, storage medium and mobile terminal
CN112308262A (en) Service management method and device
US20230123698A1 (en) Method and Apparatus for Providing Metaverse Environment

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