CN112820285A

CN112820285A - Interaction method and earphone equipment

Info

Publication number: CN112820285A
Application number: CN202011608665.2A
Authority: CN
Inventors: 谢冰茹; 刘婷; 宋瑞强; 应蕾; 李林旭; 张奇
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2020-12-29
Filing date: 2020-12-29
Publication date: 2021-05-18

Abstract

The embodiment of the invention provides an interaction method and earphone equipment, wherein the method comprises the following steps: recognizing the nutritional health inquiry intention according to the voice data of the user; obtaining nutritional health information matched with the nutritional health query intent; and outputting the matched nutritional health information. Under the condition that the user is inconvenient to operate by hands, the requirement of the user for inquiring the nutritional and health information can be met.

Description

Interaction method and earphone equipment

Technical Field

The present invention relates to the field of electronic devices, and in particular, to an interaction method and an earphone device.

Background

With the improvement of health consciousness of people, people pay more and more attention to the nutritional information of food, people with nutritional query requirements are more and more, and software and websites for querying the nutritional information on the market are more and more based on the requirements.

At present, a user generally uses software or a website to inquire the nutritional information on the electronic equipment, and the user generally needs to manually input keywords when the user inquires the nutritional information by using the software or the website. However, in some scenarios, there are still some limitations on the operation of the electronic device, which are not favorable for the user to operate the electronic device. For example, in driving a car, riding, running, etc., it is inconvenient for a user to operate a handheld electronic device.

Disclosure of Invention

In view of the above, embodiments of the present invention are proposed to provide an interaction method and a corresponding headset device that overcome or at least partially solve the above-mentioned problems.

In order to solve the above problem, an embodiment of the present invention discloses an interaction method, which is applied to an earphone device, and the method includes:

recognizing the nutritional health inquiry intention according to the voice data of the user;

obtaining nutritional health information matched with the nutritional health query intent;

and outputting the matched nutritional health information.

Optionally, the method further comprises:

obtaining question-asking guide information according to the voice data of the user;

and outputting the question guiding information.

Optionally, the headset device comprises a headset and/or a headset receiving means; the recognizing the nutritional health query intention according to the voice data of the user comprises the following steps:

the headset or the headset receiving device identifies a nutritional health query intent from voice data of a user.

Optionally, the obtaining the nutritional health information for which the nutritional health query is intended to match includes:

the headset or the headset storage device obtains the nutritional health information matched with the nutritional health inquiry intention.

Optionally, the earphone storage device has a display screen, and the outputting the matched nutritional and health information includes:

the earphone or the earphone containing device plays the matched nutritional and health information in a voice mode;

and/or the earphone containing device displays the matched nutritional health information on the display screen.

Optionally, the obtaining of the question guidance information according to the voice data of the user includes:

and the earphone or the earphone containing device acquires question-asking guide information according to the voice data of the user.

Optionally, the earphone storage device has a display screen, and the outputting the question guidance information includes:

the earphone or the earphone containing device carries out voice playing on the question-asking guide information;

and/or the earphone accommodating device displays the question guiding information on the display screen.

Optionally, the headset device is in communication with a server; the recognizing the nutritional health query intention according to the voice data of the user comprises the following steps:

and sending voice data of the user to the server so that the server can identify the nutritional health inquiry intention according to the voice data.

Optionally, the obtaining nutritional health information that matches the nutritional health query intent comprises:

and receiving the nutritional health information which is sent by the server and matched with the nutritional health inquiry intention.

and receiving question guiding information sent by the server, wherein the question guiding information is determined by the server according to the voice data of the user.

Optionally, the identifying the nutritional health query intent from the user's voice data comprises:

performing text recognition on the voice data to obtain a recognition text;

and performing semantic analysis on the recognition text to obtain a nutritional health inquiry intention.

Optionally, the recognition text comprises at least one sentence; the obtaining nutritional health information that matches the nutritional health query intent, comprising:

identifying, from the at least one statement, a statement corresponding to the nutritional health query intent;

and acquiring the matched nutritional health information according to the statement corresponding to the nutritional health inquiry intention.

Optionally, the obtaining the matched nutritional health information according to the statement corresponding to the nutritional health query intention includes:

and calling a nutritional health service interface API to acquire nutritional health information matched with the statement corresponding to the nutritional health inquiry intention.

identifying a slot of the statement corresponding to the nutritional health query intent;

determining key information of the slot position matching from the statement corresponding to the nutritional health inquiry intention;

and acquiring matched nutritional health information according to the nutritional health inquiry intention, the slot position and the matched key information.

determining slot positions missing key information;

and generating question guide information according to the slot position lacking the key information and playing the question guide information in a voice mode.

Optionally, the headset has a voice assistant to which the interactive method is applied.

The embodiment of the invention also discloses earphone equipment, which is used for identifying the nutritional health inquiry intention according to the voice data of the user; obtaining nutritional health information matched with the nutritional health query intent; and outputting the matched nutritional health information.

Optionally, the earphone device is further configured to obtain question guidance information according to the voice data of the user; and outputting the question guiding information.

the earphone or the earphone containing device is used for recognizing the nutritional health inquiry intention according to the voice data of the user.

Optionally, the headset or the headset storage device is used for acquiring the nutritional health information matched with the nutritional health inquiry intention.

Optionally, the headset or the headset storage device is used for playing the matched nutritional and health information in a voice manner;

and/or the earphone accommodating device is used for displaying the matched nutritional health information on the display screen.

Optionally, the earphone or the earphone storage device is configured to obtain question guidance information according to the voice data of the user.

Optionally, the earphone or the earphone storage device is configured to perform voice playing on the question guidance information;

and/or the earphone accommodating device is used for displaying the question guiding information on the display screen.

Optionally, the headset device is configured to send voice data of the user to the server, so that the server recognizes the nutritional and health query intention according to the voice data.

Optionally, the headset device is configured to receive the nutritional health information sent by the server and matching with the nutritional health query intention.

Optionally, the earphone device is configured to receive question guidance information sent by the server, where the question guidance information is determined by the server according to the voice data of the user.

Optionally, the headset device is configured to perform text recognition on the voice data to obtain a recognition text; and performing semantic analysis on the recognition text to obtain a nutritional health inquiry intention.

Optionally, the headset device is configured to identify a statement corresponding to the nutritional health query intent from the at least one statement; and acquiring the matched nutritional health information according to the statement corresponding to the nutritional health inquiry intention.

Optionally, the headset device is configured to call a nutritional health service interface API to obtain nutritional health information matched with the statement corresponding to the nutritional health query intention.

Optionally, the headset device to identify a slot of the statement corresponding to a nutritional health query intent; determining key information of the slot position matching from the statement corresponding to the nutritional health inquiry intention; and acquiring matched nutritional health information according to the nutritional health inquiry intention, the slot position and the matched key information.

Optionally, the earphone device is configured to determine a slot where the key information is missing; and generating question guide information according to the slot position lacking the key information and playing the question guide information in a voice mode.

Optionally, the headset has a voice assistant by which the above-described functionality is implemented.

An embodiment of the present invention also discloses a headset device, the headset device is in communication with a terminal device, the headset device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:

and outputting the matched nutritional health information.

Optionally, the method further comprises:

and outputting the question guiding information.

performing text recognition on the voice data to obtain a recognition text;

determining slot positions missing key information;

Optionally, the headset has a voice assistant, and instructions for performing the above operations are performed by the voice assistant.

The embodiment of the invention also discloses a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program realizes the steps of the interaction method when being executed by a processor.

The embodiment of the invention has the following advantages:

in the embodiment of the invention, the earphone device can identify the nutritional health inquiry intention of the user according to the voice data of the user, acquire the nutritional health information matched with the nutritional health inquiry intention and play the nutritional health information in voice. Under the condition that the user is inconvenient to operate by hands, the requirement of the user for inquiring the nutritional and health information can be met. For example, the user can speak the content to be queried at any time during riding, and the earphone device can acquire corresponding nutritional and health information and play the information in voice during riding.

Drawings

FIG. 1 is a flow chart of the steps of an interaction method of an embodiment of the present invention;

FIG. 2 is a flow chart of steps of another interaction method of an embodiment of the present invention;

FIG. 3 is a flow chart of steps of another interaction method of an embodiment of the present invention;

FIG. 4 is a flow chart of steps of another interaction method of an embodiment of the present invention;

fig. 5 is a block diagram of a configuration of an earphone device according to an embodiment of the present invention;

fig. 6 is a block diagram of an alternative embodiment of an earphone device of the present invention;

FIG. 7 is a block diagram illustrating a structure of a headset device for interaction in accordance with an exemplary embodiment;

fig. 8 is a schematic structural diagram of an electronic device for interaction according to another exemplary embodiment of the present invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Referring to fig. 1, a flowchart illustrating steps of an interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset device, and the method specifically includes the following steps:

step 101, recognizing the nutritional health inquiry intention according to the voice data of the user.

The headset device may collect voice data of the user and identify a nutritional and health query intent based on the voice data of the user.

In one embodiment, a headset device may include a headset and a headset receiving apparatus. The earphone storage device is a device matched with an earphone, the earphone storage device is generally used for storing the earphone and charging a wireless earphone, and the earphone storage device further has the capabilities of data processing, transmission, storage and the like. The headset may communicate wirelessly with the headset receiving device to transmit data. The earphone or the earphone containing device can collect voice data of a user and identify the nutrition and health inquiry intention according to the voice data of the user.

In one embodiment, the headset device may communicate with a server. The headset device may send the user's voice data to the server to cause the server to identify the nutritional health query intent from the voice data.

And step 102, acquiring nutritional health information matched with the nutritional health inquiry intention.

The headset device may obtain nutritional health information that matches the nutritional health query intent.

In one embodiment, the headset device may generate matching nutritional health information from the nutritional health query intent. In particular, the headset or headset receiving device may generate the matched nutritional health information according to the nutritional health query intent. The earphone containing device can generate matched nutritional health information according to the nutritional health inquiry intention, and the earphone can receive the matched nutritional health information sent by the earphone containing device.

In one embodiment, the server may identify the nutritional health query intent from the user's voice data sent by the headset device and then generate nutritional health information that matches the nutritional health query intent, and the headset device may receive the nutritional health information that matches the nutritional health query intent sent by the server. Specifically, the headset or the headset containing device can receive nutritional health information which is sent by the server and matched with the nutritional health inquiry intention.

And 103, outputting the matched nutritional health information.

The earphone device can output the matched nutritional health information. Specifically, the earphone or the earphone containing device can play the matched nutritional and health information in a voice mode. Earphone storage device can have the display screen, and earphone storage device can show the nutrition health information that matches at the display screen.

In the embodiment of the present invention, the nutritional and health information may include a text, and the headset device may generate and play a voice corresponding To the text by using a text-To-speech tts (text To speech) technology. When the user wants to inquire the nutrition and health information, the user can speak the contents needing to be inquired. For example, the user speaks: "what should the fracture patient eat more? ", this phrase may indicate that the user has a nutritional and health query intent. The headset device may obtain nutritional health information that the nutritional health query intent matches, for example, the nutritional health information may be: if people keep leisure indoors after fracture, the people can not shine sun and are easy to lack vitamin D. Therefore, after fracture, people need to eat more vitamin D-rich food (such as fish, liver, egg yolk and the like) and get sunned as much as possible.

Referring to fig. 2, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset device, and the method may specifically include the following steps:

step 201, recognizing the nutrition and health inquiry intention according to the voice data of the user.

In one embodiment, the step 201 may include the following sub-steps:

and a substep S11 of performing text recognition on the voice data to obtain a recognized text.

The headphone apparatus may have a Speech recognition asr (automatic Speech recognition) function. For example, the headphone device may be provided with a voice recognition chip, or a voice recognition program may be provided in the headphone device chip. The voice recognition function of the earphone equipment can be used for carrying out voice recognition on the voice data of the user locally on the earphone equipment to obtain the recognized text.

And a substep S12, performing semantic analysis on the recognition text to obtain the nutritional health inquiry intention.

Specifically, sentence detection can be performed on the recognition text to obtain at least one sentence; identifying a user intent corresponding to the at least one statement. The sentence or sentences included in the recognition text can be determined by sentence detection. The sentence corresponding to the nutritional health query intention may be determined from the sentences included in the recognition text. In embodiments of the invention the headset device may support instructions that, in turn, may determine a plurality of statements corresponding to the nutritional health query intent.

The recognition text obtained by performing voice recognition on the voice data of the user can be a plain text, and sentence detection can be performed on the recognition text to obtain at least one sentence while the recognition text obtained by performing voice recognition on the voice data is obtained. For example, the user speaks: the grapes in the supermarket are special in price, fresh and fresh, and can be eaten. The recognition text obtained by carrying out voice recognition on the words spoken by the user is 'the supermarket is that the grapes are special, fresh and I can eat the grapes'.

If the recognition text has more contents, the analysis result obtained by directly performing semantic analysis processing on the recognition text cannot accurately reflect the meaning which the user actually wants to express, and the recognition text needs to be subjected to sentence detection to obtain a sentence, and then semantic analysis is performed according to the sentence. Sentence detection includes sentence break detection and symbol addition. Sentence break detection is the detection of where in the recognized text a sentence break is needed. For example, sentence break detection is performed on the recognition text 'can eat grapes at the special price of grapes in the supermarket', it can be determined that sentence breaks are needed after the special price of grapes in the supermarket ', and it can be determined that sentence breaks are needed after the special price of grapes in the supermarket'. The symbol adding is to add punctuation marks, such as commas, periods, question marks and the like, at the positions of the punctuation. For example, a comma is added at "supermarket grape specials" and a comma is added after "arm-fresh". After sentence detection, three sentences are obtained, namely 'special price of grapes in a supermarket', 'very fresh' and 'how I can eat grapes'.

For example, the user speaks: how to lose weight, the newly bought trousers cannot be worn, the earphone device can recognize that the two sentences are 'how to lose weight' respectively according to the voice data of the user, and the newly bought trousers cannot be worn. The earphone device can determine that the user has the nutrition and health inquiry intention according to the 'how to lose weight', and determine that the 'how to lose weight' corresponds to the nutrition and health inquiry intention. It was determined that "newly purchased pants were not worn" did not correspond to a nutritional health query intent.

In the embodiment of the present invention, the headphone device may perform semantic analysis on the sentence by using a natural Language understanding (nlu) technology, so as to obtain the user intention. For example, the sentence is semantically analyzed using a semantic analysis model trained in advance.

In one embodiment, a headset device may include a headset and a headset receiving apparatus. The earphone storage device is a device matched with an earphone, the earphone storage device is generally used for storing the earphone and charging a wireless earphone, and the earphone storage device further has the capabilities of data processing, transmission, storage and the like. The headset may communicate wirelessly with the headset receiving device to transmit data.

The earphone or the earphone containing device can collect voice data of a user and identify the nutrition and health inquiry intention according to the voice data of the user.

Step 202, acquiring nutritional health information matched with the nutritional health inquiry intention.

In one embodiment, the headset device may generate matching nutritional health information from the nutritional health query intent. The step 202 may comprise the sub-steps of:

sub-step S21, identifying a sentence corresponding to the nutritional health query intention from the at least one sentence comprised in the identification text.

And a substep S22 of obtaining the matched nutritional health information according to the statement corresponding to the nutritional health inquiry intention.

In one example, the sub-step S22 may include: and calling a nutritional health service interface API to acquire nutritional health information matched with the statement corresponding to the nutritional health inquiry intention.

Specifically, the headset device may call an Application Programming Interface (API) to use the nutritional health service. The nutritional health service may generate matching nutritional health information for the user's statements using a preset knowledge base and a knowledge graph. The knowledge base can be a knowledge base which is provided with guidance by professional and authoritative organizations and covers 18 subdivided groups of people, 1800 food materials and 2000 diseases. The knowledge map can be the most comprehensive and authoritative nutrition and health knowledge map in the domestic food and nutrition field. The nutritional and health service can provide authoritative, professional and comprehensive services for users.

In an embodiment of the present invention, the sub-step S22 may further include the following sub-steps:

substep S221, identifying a slot for the statement corresponding to the nutritional health query intent.

In the field of natural language processing, a slot can be understood as a well-defined attribute of an entity, and an entity refers to an object having a specific meaning in a corpus. Slot filling is the value that determines the slot position, i.e., the value that extracts the well-defined property of a given entity from the corpus.

Substep S222, determining key information of the slot matching from the statement corresponding to the nutritional health query intention.

The key information may be a slot value of the slot. For example, the statement: "can I eat grape", the corresponding intention of the statement is the nutrition and health inquiry intention, the statement has a slot position of a nutrition and health inquiry object, and key information corresponding to the slot position is identified as the grape from the statement.

And a substep S223 of obtaining the matched nutritional health information according to the nutritional health inquiry intention, the slot position and the matched key information.

According to the nutritional health inquiry intention, the slot position of the nutritional health inquiry object and the key information 'grape' corresponding to the slot position, the matched nutritional health information can be obtained. For example, "grape is a low-protein, low-sodium food material, which is beneficial for people suffering from pancreatitis, gastritis, diarrhea, etc. In the embodiment of the present invention, when a user wants to inquire nutritional and health information, the user may say that the user may not accurately express the meaning of inquiring the nutritional and health information, and such a scenario may be referred to as a scenario in which a problem lacks key information. In the scene of missing key information, the corresponding mode can be a mode of using a question back so that the user can speak the correct questioning content or ignore the question. The question of the key information can be well solved in the mode of question return, but the user can not be answered immediately.

In the embodiment of the invention, when a scene that a question lacks key information occurs, the nutritional and health information can be obtained according to the existing key information, so that the knowledge requirements of users are met, the effect of asking one answer is achieved, and the situation that the users cannot answer is avoided.

In one example, the headset or headset receiving device may generate matching nutritional health information according to the nutritional health query intent. The earphone containing device can generate matched nutritional health information according to the nutritional health inquiry intention, and the earphone can receive the matched nutritional health information sent by the earphone containing device.

And 203, outputting the matched nutritional health information.

And step 204, obtaining question guidance information according to the voice data of the user.

In the scene of missing key information in the problem, in the voice interaction, the interaction difficulty is increased and the interaction success rate is reduced due to the fact that the interaction flow is lengthened. In contrast, in the embodiment of the present invention, the earphone device may play the question guidance information in voice after playing the health answer information in voice, so as to prompt the user of a correct question making manner. The interactive characteristics of the original question and answer are maintained, extra interactive rounds are not needed to be added, and the interactive success rate is ensured. For example, the user says "can I eat grape", and the corresponding question guidance information may be: "want to know more accurate information, you can ask me as follows: can grapes be eaten for losing weight? ". After hearing the question guide information, the user can more clearly ask the question, and the question quality is improved.

In an embodiment of the present invention, the step 204 may include the following sub-steps:

and a substep S31 of determining the slot which lacks key information in the slots corresponding to the sentences intended by the nutritional health inquiry.

And a substep S32, generating question guide information according to the slot position lacking the key information and playing the question guide information in a voice mode.

For example, the user speaks: the earphone device can identify that the user has the nutrition and health inquiry intention after eating the chafing dish, the sentence can have a slot position of a disease and a slot position of a processing mode, key information matched with the slot position of the disease can be the oral ulcer, and the slot position of the processing mode lacks key information. The questioning guide information can be generated according to the slot position of the processing mode, that is, you can ask me the following steps: how the canker sores are treated ".

In one embodiment, the earphone device can acquire the question guidance information according to the voice data of the user. Specifically, the earphone or the earphone storage device can acquire question guidance information according to voice data of a user.

In one embodiment, the headset device may generate the questioning guidance information according to voice data of the user. Specifically, the earphone or the earphone storage device may generate question guidance information according to voice data of the user.

In one embodiment, the earphone device can receive the questioning guide information sent by the server, wherein the questioning guide information is determined by the server according to the voice data of the user. Specifically, the headset or the headset storage device may receive the question guidance information sent by the server.

And step 205, outputting the question guiding information.

The earphone device can output the questioning guidance information. The questioning guidance information may include text, and the earphone device may generate and play a voice corresponding to the text by using TTS technology.

Specifically, the earphone or the earphone storage device can play the question guidance information in voice. The earphone storage device can be provided with a display screen, and the question guide information can be displayed on the display screen by the earphone storage device.

In the embodiment of the invention, the earphone equipment can acquire the voice data of the user, identify the nutrition and health inquiry intention of the user according to the voice data, acquire the nutrition and health information matched with the nutrition and health inquiry intention and play the nutrition and health information in a voice mode; and acquiring question guide information according to the voice data of the user and playing the question guide information in a voice mode. The embodiment of the invention can meet the requirement of the user for inquiring the nutritional and health information under the condition that the user is inconvenient to operate by hands. When a scene that a question lacks key information occurs, the nutritional and health information can be acquired according to the existing key information, so that the knowledge requirements of users are met, and the effect of asking one answer is achieved. And the user can be prompted to have a correct question mode by playing question guide information through voice.

Referring to fig. 3, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset device, and the headset device is provided with a voice assistant, and the method may specifically include the following steps:

in step 301, the voice assistant identifies the nutritional and health query intent according to the voice data of the user.

In one embodiment, a headset device may include a headset and a headset receiving apparatus. The earphone storage device is a device matched with an earphone, the earphone storage device is generally used for storing the earphone and charging a wireless earphone, and the earphone storage device further has the capabilities of data processing, transmission, storage and the like. The headset may communicate wirelessly with the headset receiving device to transmit data. The voice assistant of the earphone or the earphone containing device can collect voice data of the user and recognize the nutritional and health inquiry intention according to the voice data of the user.

In one embodiment, the headset device may communicate with a server. The voice assistant of the headset device may send the user's voice data to the server to cause the server to recognize the nutritional health query intent from the voice data.

Step 302, the voice assistant acquires nutritional health information matching the nutritional health query intent.

The voice assistant of the headset device may obtain the nutritional health information that matches the nutritional health query intent.

In one embodiment, the voice assistant of the headset device may generate matching nutritional health information from the nutritional health query intent. In particular, the headset or a voice assistant of the headset receiving device may generate the matched nutritional and health information according to the nutritional and health query intention. The voice assistant of the earphone receiving device can generate the matched nutritional health information according to the nutritional health inquiry intention, and the voice assistant of the earphone can receive the matched nutritional health information sent by the earphone receiving device.

In one embodiment, the server may identify the nutritional health query intent from the user's voice data sent by the headset device and then generate nutritional health information that matches the nutritional health query intent, and the voice assistant of the headset device may receive the nutritional health information that matches the nutritional health query intent sent by the server. Specifically, the voice assistant of the headset or the headset containing device can receive the nutritional health information which is sent by the server and matched with the nutritional health inquiry intention.

And step 303, the voice assistant outputs the matched nutritional health information.

The voice assistant of the headset device may output the matched nutritional and health information. Specifically, the voice assistant of the headset or the headset storage device can play the matched nutritional and health information in a voice mode. The earphone containing device can be provided with a display screen, and the voice assistant of the earphone containing device can display the matched nutritional and health information on the display screen. In the embodiment of the present invention, the nutritional and health information may include a text, and the voice assistant of the headset device may generate and play a voice corresponding To the text by using a text-To-voice tts (text To speech) technology.

In the embodiment of the invention, the voice assistant of the earphone device can recognize the nutritional health inquiry intention of the user according to the voice data of the user, acquire the nutritional health information matched with the nutritional health inquiry intention and play the nutritional health information in voice. Under the condition that the user is inconvenient to operate by hands, the requirement of the user for inquiring the nutritional and health information can be met.

Referring to fig. 4, a flowchart illustrating steps of another interaction method according to an embodiment of the present invention is shown, where the method is applied to a headset device, and the method may specifically include the following steps:

in step 401, the voice assistant identifies the nutritional health query intent based on the user's voice data.

The voice assistant of the headset device may collect voice data of the user and identify a nutritional and health query intent based on the voice data of the user.

In one embodiment, the step 401 may include the following sub-steps:

and a substep S41, the voice assistant performs text recognition on the voice data to obtain a recognized text.

And in the substep S42, the voice assistant performs semantic analysis on the recognized text to obtain the nutritional and health inquiry intention.

Specifically, sentence detection can be performed on the recognition text to obtain at least one sentence; identifying a user intent corresponding to the at least one statement.

The sentence or sentences included in the recognition text can be determined by sentence detection. The sentence corresponding to the nutritional health query intention may be determined from the sentences included in the recognition text. In embodiments of the invention the headset device may support instructions that, in turn, may determine a plurality of statements corresponding to the nutritional health query intent.

The recognition text obtained by performing voice recognition on the voice data of the user can be a plain text, and sentence detection can be performed on the recognition text to obtain at least one sentence while the recognition text obtained by performing voice recognition on the voice data is obtained. If the recognition text has more contents, the analysis result obtained by directly performing semantic analysis processing on the recognition text cannot accurately reflect the meaning which the user actually wants to express, and the recognition text needs to be subjected to sentence detection to obtain a sentence, and then semantic analysis is performed according to the sentence. Sentence detection includes sentence break detection and symbol addition. Sentence break detection is the detection of where in the recognized text a sentence break is needed.

In the embodiment of the present invention, the voice assistant of the headset device may perform semantic analysis on the sentence by using a natural Language understanding (nlu) technology, so as to obtain the user intention. For example, the sentence is semantically analyzed using a semantic analysis model trained in advance.

The voice assistant of the earphone or the earphone containing device can collect voice data of the user and recognize the nutritional and health inquiry intention according to the voice data of the user.

At step 402, the voice assistant obtains nutritional health information that matches the nutritional health query intent.

In one embodiment, the voice assistant of the headset device may generate matching nutritional health information from the nutritional health query intent. The step 402 may comprise the sub-steps of:

in sub-step S51, the voice assistant identifies a sentence corresponding to the nutritional health query intent from the at least one sentence included in the recognition text.

And a substep S52 of obtaining the matched nutritional health information according to the statement corresponding to the nutritional health inquiry intention.

In one example, the sub-step S52 may include: and calling a nutritional health service interface API to acquire nutritional health information matched with the statement corresponding to the nutritional health inquiry intention.

Specifically, the voice assistant of the headset device may call an Application Programming Interface (API) to use the nutritional health service. The nutritional health service may generate matching nutritional health information for the user's statements using a preset knowledge base and a knowledge graph. The knowledge base can be a knowledge base which is provided with guidance by professional and authoritative organizations and covers 18 subdivided groups of people, 1800 food materials and 2000 diseases. The knowledge map can be the most comprehensive and authoritative nutrition and health knowledge map in the domestic food and nutrition field. The nutritional and health service can provide authoritative, professional and comprehensive services for users.

In an embodiment of the present invention, the sub-step S52 may further include the following sub-steps:

in sub-step S521, the voice assistant identifies the slot of the sentence corresponding to the nutritional health query intent.

In substep S522, the voice assistant determines the key information of the slot matching from the sentence corresponding to the nutritional health query intention.

The key information may be a slot value of the slot.

And in the substep S523, the voice assistant acquires the matched nutritional health information according to the nutritional health inquiry intention, the slot position and the matched key information.

In one example, a voice assistant of the headset or headset receptacle may generate matching nutritional health information according to the nutritional health query intent. The voice assistant of the earphone receiving device can generate the matched nutritional health information according to the nutritional health inquiry intention, and the voice assistant of the earphone can receive the matched nutritional health information sent by the earphone receiving device.

And step 403, the voice assistant outputs the matched nutritional health information.

The voice assistant of the headset device may output the matched nutritional and health information. Specifically, the voice assistant of the headset or the headset storage device can play the matched nutritional and health information in a voice mode. The earphone containing device can be provided with a display screen, and the voice assistant of the earphone containing device can display the matched nutritional and health information on the display screen.

And step 404, the voice assistant acquires question guidance information according to the voice data of the user.

In the scene of missing key information in the problem, in the voice interaction, the interaction difficulty is increased and the interaction success rate is reduced due to the fact that the interaction flow is lengthened. In this regard, in the embodiment of the present invention, the voice assistant of the headset device may play the question guidance information in voice after playing the health answer information in voice, so as to prompt the user of a correct question-asking manner. The interactive characteristics of the original question and answer are maintained, extra interactive rounds are not needed to be added, and the interactive success rate is ensured.

In an embodiment of the present invention, the step 404 may include the following sub-steps:

in sub-step S61, the voice assistant determines the slot lacking the key information among the slots corresponding to the sentences intended by the nutritional health query.

And in the substep S62, the voice assistant generates question guiding information according to the slot position lacking the key information and plays the question guiding information in a voice mode.

In one embodiment, the voice assistant of the headset device may obtain the questioning guidance information according to the voice data of the user. Specifically, the voice assistant of the headset or the headset storage device can acquire the question-asking guidance information according to the voice data of the user.

In one embodiment, the voice assistant of the headset device may generate the questioning guidance information according to the voice data of the user. Specifically, the voice assistant of the headset or the headset storage device can generate question guidance information according to the voice data of the user.

In one embodiment, the voice assistant of the headset device may receive the questioning guidance information sent by the server, wherein the questioning guidance information is determined by the server based on the voice data of the user. Specifically, the voice assistant of the headset or the headset storage device can receive the question guidance information sent by the server.

Step 405, the voice assistant outputs the question guidance information.

The voice assistant of the headset device may output the quiz guidance information. The questioning guidance information may include text, and the earphone device may generate and play a voice corresponding to the text by using TTS technology.

Specifically, the voice assistant of the headset or the headset storage device can play the questioning guidance information in voice. The earphone receiving device can be provided with a display screen, and the voice assistant of the earphone receiving device can display the question-asking guide information on the display screen.

In the embodiment of the invention, the voice assistant of the earphone equipment can acquire the voice data of the user, recognize the nutritional health inquiry intention of the user according to the voice data, acquire the nutritional health information matched with the nutritional health inquiry intention and play the nutritional health information in a voice mode; and acquiring question guide information according to the voice data of the user and playing the question guide information in a voice mode. The embodiment of the invention can meet the requirement of the user for inquiring the nutritional and health information under the condition that the user is inconvenient to operate by hands. When a scene that a question lacks key information occurs, the nutritional and health information can be acquired according to the existing key information, so that the knowledge requirements of users are met, and the effect of asking one answer is achieved. And the user can be prompted to have a correct question mode by playing question guide information through voice.

It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

Referring to fig. 5, there is shown a block diagram of a headset device 500 for recognizing a nutritional health query intent from voice data of a user in accordance with an embodiment of the present invention; obtaining nutritional health information matched with the nutritional health query intent; and outputting the matched nutritional health information.

Referring to fig. 6, a block diagram of an alternative embodiment of the earphone device of the present invention is shown, where the earphone device 500 is further configured to obtain question guidance information according to the voice data of the user; and outputting the question guiding information.

In an alternative embodiment of the present invention, the earphone device 500 comprises an earphone 502 and/or an earphone receiving device 504; the recognizing the nutritional health query intention according to the voice data of the user comprises the following steps:

the headset 502 or the headset receiving device 504 is used for recognizing the nutritional health query intention according to the voice data of the user.

In an optional embodiment of the present invention, the headset 502 or the headset receiving device 504 is configured to obtain the nutritional health information matched with the nutritional health query intention.

In an optional embodiment of the present invention, the headset 502 or the headset storage device 504 is configured to perform voice playing on the matched nutritional and health information;

and/or the earphone receiving device 504 is used for displaying the matched nutritional health information on the display screen.

In an optional embodiment of the present invention, the earphone 502 or the earphone receiving device 504 is configured to obtain question guidance information according to voice data of the user.

In an optional embodiment of the present invention, the earphone 502 or the earphone storage 504 is configured to perform voice playing on the question guidance information;

and/or the earphone storage 504 is used for displaying the question guidance information on the display screen.

In an optional embodiment of the invention, the headset device 500 is configured to send voice data of the user to the server, so that the server recognizes the nutritional health query intention according to the voice data.

In an optional embodiment of the present invention, the headset device 500 is configured to receive the nutritional health information sent by the server and matching with the nutritional health query intention.

In an optional embodiment of the present invention, the headset device 500 is configured to receive question guidance information sent by the server, where the question guidance information is determined by the server according to voice data of the user.

In an optional embodiment of the present invention, the headset device 500 is configured to perform text recognition on the voice data to obtain a recognition text; and performing semantic analysis on the recognition text to obtain a nutritional health inquiry intention.

In an alternative embodiment of the present invention, the headset device 500 is configured to identify a phrase corresponding to the nutritional health query intent from among the at least one phrase; and acquiring the matched nutritional health information according to the statement corresponding to the nutritional health inquiry intention.

In an optional embodiment of the present invention, the headset device 500 is configured to call a nutritional health service interface API to obtain nutritional health information matching the statement corresponding to the nutritional health query intention.

In an alternative embodiment of the present invention, the earphone device 500 is configured to identify a slot of the sentence corresponding to the nutritional health query intention; determining key information of the slot position matching from the statement corresponding to the nutritional health inquiry intention; and acquiring matched nutritional health information according to the nutritional health inquiry intention, the slot position and the matched key information.

In an optional embodiment of the present invention, the earphone device 500 is configured to determine a slot where key information is missing; and generating question guide information according to the slot position lacking the key information and playing the question guide information in a voice mode.

In an alternative embodiment of the invention, the headset is provided with a voice assistant by means of which the above-mentioned functions are implemented.

Fig. 7 is a block diagram illustrating a structure of an earphone device 700 for interaction according to an exemplary embodiment.

Referring to fig. 7, the headset device 700 may include one or more of the following components: a processing component 702, a memory 704, a power component 706, a multimedia component 708, an audio component 710, an input/output (I/O) interface 712, a sensor component 714, and a communication component 716.

The processing component 702 generally controls the overall operation of the headset device 700, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 702 may include one or more processors 720 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 702 may include one or more modules that facilitate interaction between the processing component 702 and other components. For example, the processing component 702 can include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

The memory 704 is configured to store various types of data to support operations at the headset device 700. Examples of such data include instructions for any application or method operating on the headset device 700, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 704 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power component 706 provides power to the various components of the headset device 700. The power components 706 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the headset device 700.

The multimedia component 708 comprises a screen providing an output interface between the earphone device 700 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front facing camera and/or a rear facing camera. When the headset device 700 is in an operation mode, such as a photographing mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 710 is configured to output and/or input audio signals. For example, the audio component 710 includes a Microphone (MIC) configured to receive external audio signals when the headset device 700 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 704 or transmitted via the communication component 716. In some embodiments, audio component 710 also includes a speaker for outputting audio signals.

The I/O interface 712 provides an interface between the processing component 702 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 714 includes one or more sensors for providing various aspects of state assessment for the headset device 700. For example, the sensor component 714 may detect an open/closed state of the headphone device 700, the relative positioning of the components, such as a display and keypad of the headphone device 700, the sensor component 714 may also detect a change in position of the headphone device 700 or a component of the headphone device 700, the presence or absence of user contact with the headphone device 700, the orientation or acceleration/deceleration of the headphone device 700, and a change in temperature of the headphone device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 716 is configured to facilitate wired or wireless communication between the headset device 700 and other devices. The headset device 700 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 714 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 714 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the ear speaker device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as the memory 704 comprising instructions, executable by the processor 720 of the headset device 700 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A non-transitory computer readable storage medium in which instructions, when executed by a processor of a headset device, enable the headset device to perform a method of interaction, the method comprising:

and outputting the matched nutritional health information.

Optionally, the method further comprises:

and outputting the question guiding information.

performing text recognition on the voice data to obtain a recognition text;

determining slot positions missing key information;

Fig. 8 is a schematic structural diagram of an electronic device 800 for interaction according to another exemplary embodiment of the present invention. The electronic device 800 may be a server, which may vary widely due to configuration or performance, and may include one or more Central Processing Units (CPUs) 822 (e.g., one or more processors) and memory 832, one or more storage media 830 (e.g., one or more mass storage devices) storing applications 842 or data 844. Memory 832 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 822 may be configured to communicate with the storage medium 830 to execute a series of instruction operations in the storage medium 830 on the server.

The server may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input-output interfaces 858, one or more keyboards 856, and/or one or more operating systems 841, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

In an exemplary embodiment, the server is configured to execute one or more programs by the one or more central processors 822 including instructions for:

and receiving voice data of the user sent by the earphone equipment, and identifying the nutritional health inquiry intention according to the voice data.

Optionally, the method further comprises: and generating nutritional health information matched with the nutritional health inquiry intention, and sending the nutritional health information matched with the nutritional health inquiry intention to the earphone equipment.

Optionally, the method further comprises: and generating question guide information according to the voice data of the user, and sending the question guide information to the earphone equipment.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The interaction method and the earphone device provided by the invention are described in detail, and the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An interaction method applied to a headset device, the method comprising:

and outputting the matched nutritional health information.

2. The method of claim 1, further comprising:

and outputting the question guiding information.

3. The method of claim 2, wherein the headset device comprises a headset and/or a headset receiving device; the recognizing the nutritional health query intention according to the voice data of the user comprises the following steps:

4. The method of claim 3, wherein obtaining the nutritional health information for which the nutritional health query is intended to match comprises:

5. The method of claim 3, wherein the headset receiving device has a display screen, and the outputting the matched nutritional and health information comprises:

6. The method according to claim 3, wherein the obtaining of the question guidance information according to the voice data of the user comprises:

7. The method of claim 6, wherein the headset receiving device has a display screen, and the outputting the question guidance information comprises:

8. An earphone device, characterized in that,

the earphone device is used for identifying the nutritional health inquiry intention according to the voice data of the user; obtaining nutritional health information matched with the nutritional health query intent; and outputting the matched nutritional health information.

9. An earphone device, wherein the earphone device is in communication with a terminal device, wherein the earphone device comprises a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein execution of the one or more programs by one or more processors comprises instructions for:

and outputting the matched nutritional health information.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the interaction method according to any one of claims 1 to 7.