CN112965590A - Artificial intelligence interaction method, system, computer equipment and storage medium - Google Patents
Artificial intelligence interaction method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112965590A CN112965590A CN202110152305.4A CN202110152305A CN112965590A CN 112965590 A CN112965590 A CN 112965590A CN 202110152305 A CN202110152305 A CN 202110152305A CN 112965590 A CN112965590 A CN 112965590A
- Authority
- CN
- China
- Prior art keywords
- person
- awakening
- artificial intelligence
- response
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an artificial intelligence interaction method, an artificial intelligence interaction system, computer equipment and a storage medium, relates to the field of artificial intelligence, solves the problem of low intelligent degree of an artificial intelligence system in the prior art, and has the technical key points that: the artificial intelligence interaction method comprises the following steps: acquiring a wake-up action; determining a awakening person through an awakening action, and acquiring biological information of the awakening person, wherein the biological information at least comprises face information, action information and audio information of the awakening person; matching and outputting an exclusive response strategy of the awakening person according to the acquired biological information, wherein the exclusive response strategy is to preset a plurality of groups of different response actions according to the biological information of the awakening person; the embodiment provided by the invention matches different response strategies for different awakeners and makes different response actions according to the moods of the awakeners, so that the artificial intelligence realizes the improvement of individuation and intellectualization when making the response actions.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an artificial intelligence interaction method, an artificial intelligence interaction system, computer equipment and a storage medium.
Background
With the development of computer technology, artificial intelligence has gone into thousands of households from the laboratory stage, such as millet love classmates, Alibara Tianmaoling and the like, and the artificial intelligence effectively improves the convenience of life.
However, the artificial intelligence in the prior art still has limitations, for example, most of the artificial intelligence in the prior art recognizes the user intention by means of keyword recognition, the recognition method enables the artificial intelligence to have a low intelligence degree in the process of recognizing the user intention, and the artificial intelligence can be applied to some command-type working scenes, but in the field of human-artificial intelligence conversation, the interaction method is very easy to have a question of answering during the conversation process, and greatly reduces the experience of the artificial intelligence, so that an artificial intelligence interaction method, a system, computer equipment and a storage medium are provided.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an artificial intelligence interaction method, system, computer device and storage medium to solve the problem of low intelligence degree of the artificial intelligence system in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme when being applied to the intelligent terminal:
acquiring a wake-up action, wherein the wake-up action comprises a wake-up gesture, a wake-up word and a wake-up instruction;
determining a awakening person through an awakening action, and acquiring biological information of the awakening person, wherein the biological information at least comprises face information, action information and audio information of the awakening person;
and matching and outputting an exclusive response strategy of the awakening person according to the acquired biological information, wherein the exclusive response strategy is to preset a plurality of groups of different response actions according to the biological information of the awakening person.
Further, the specific guarantee of acquiring the wake-up action includes at least one of:
acquiring a video, comparing the video with a preset video clip, and switching from a standby state to a working state when the matching degree of the acquired video and the video clip reaches a preset value;
acquiring an audio frequency, comparing the audio frequency with a preset audio frequency fragment, and switching from a standby state to a working state when the matching degree of the acquired audio frequency and the audio frequency fragment reaches a preset value;
and switching the standby state into the working state when the wake-up instruction of the upstream control end is acquired.
Still further, the specific step of determining to wake up the person through the wake-up action includes at least one of:
the method comprises the steps that a person who makes a wakeup gesture in a video clip containing the wakeup gesture acquired by a video acquisition device is determined as a wakeup person, and biological information of the wakeup person is acquired through the video acquisition device and an audio acquisition device;
the method comprises the steps that a person who speaks the awakening word in an audio clip containing the awakening word acquired by an audio acquisition device serves as an awakening person, meanwhile, the video acquisition device and the audio acquisition device are matched to capture the person who speaks the awakening word and determine the person as the awakening person, and biological information of the awakening person is acquired through the video acquisition device and the audio acquisition device;
the method comprises the steps of obtaining a person operating a control end through a video acquisition device, determining the person as a awakening person, and acquiring biological information of the awakening person through the video acquisition device and an audio acquisition device.
As a preferred aspect of the present invention, the step of determining to wake up the person includes:
the position of the sound source containing the awakening words is obtained through the audio acquisition device, and people at the position of the sound source are obtained through the video acquisition device and serve as awakening personnel.
Further, the step of matching the exclusive response strategy of the awakened person comprises:
and taking the acquired biological information as search information to search a built-in response database, and calling a special response strategy stored in the response database.
Still further, the step of matching the proprietary reply policy further comprises:
analyzing the emotion of the awakened person according to the acquired biological information;
acquiring interactive information sent by awakening personnel, and retrieving an exclusive response strategy corresponding to the awakening personnel at the moment based on the interactive information;
invoking a response action corresponding to the emotion of the awakening person in the exclusive response strategy;
and outputting the response action.
Further, the method further comprises;
and when the exclusive response strategy of the awakening personnel is not matched, calling the response strategy stored in the general response database and outputting the response strategy.
An artificial intelligence interaction system, comprising:
the acquisition module is used for acquiring the awakening action, the biological information of the awakened person and the interactive information sent by the awakened person;
the information processing module is used for analyzing information containing awakening actions, biological information of awakened persons and interactive information sent by the awakened persons;
the storage module is used for storing a response strategy;
and the response module finishes response action by calling the response strategy pinched by the storage module.
A computer device, characterized in that it comprises a processor for implementing the steps of the method as described above when executing a computer program stored in a memory.
A storage medium having stored thereon a computer program (instructions), characterized in that the computer program (instructions), when executed by a processor, implements the steps of the method as described above.
In conclusion, compared with the prior art, the invention has the following beneficial effects:
1. the embodiment provided by the invention matches different response strategies for different awakening persons, and makes different response actions according to different moods or scenes of the awakening persons, so that the artificial intelligence realizes personalized and intelligent improvement when making the response actions.
2. The invention can improve the experience of the user on the artificial intelligent equipment and is convenient for the use of the intelligent equipment.
3. The interactive mode of the invention is diversified, and is suitable for normal people and disabled people.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a schematic diagram of the structure of the inventor's intelligence.
FIG. 3 is a schematic diagram of the structure of the semantic database and the response database in the present invention.
FIG. 4 is a schematic diagram of the structure of the dedicated response database in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
The artificial intelligence interaction method provided by the invention in figure 1 is applied to an intelligent terminal and comprises the following steps:
s100, acquiring a wake-up action, wherein the wake-up action comprises a wake-up gesture, a wake-up word and a wake-up instruction;
s200, determining a awakening person through an awakening action, and acquiring biological information of the awakening person, wherein the biological information at least comprises face information, action information and audio information of the awakening person;
s300, matching and outputting an exclusive response strategy of the awakening person according to the acquired biological information, wherein the exclusive response strategy is to preset a plurality of groups of different response actions according to the biological information of the awakening person;
as shown in fig. 2, as a preferred mode of the present invention, the artificial intelligence includes a video analysis module 100 and an audio analysis module 200, the video analysis module 100 is connected to an image capture device on the intelligent terminal for obtaining video, and the audio analysis module 200 is connected to an audio capture device on the intelligent terminal for obtaining audio;
the awakening gesture is a specific video segment preset in the intelligent terminal, the awakening action is acquired by a video acquisition device and is compared with the preset video segment, and when the matching degree of the acquired video and the video segment reaches the preset value, the standby state is switched to the working state;
in some examples, the wake-up gesture may be a fist making, palm opening, or a specific trajectory drawn in space, and the artificial intelligence switches from a standby state to a working state by recognizing a specific wake-up action, and then by recognizing and determining a person who made the wake-up action as a wake-up person;
when a person awakens the artificial intelligence through an awakening gesture, the artificial intelligence acquires a video through an image acquisition device on the intelligent terminal, compares the acquired video with a video fragment stored in the intelligent terminal frame by frame, and judges that the person awakens when the coincidence degree of the video fragment stored in the intelligent terminal and a part of pictures in the acquired video reaches a threshold value;
for example, when the overlap ratio of the video clip stored in the intelligent terminal and a part of the picture in the acquired video reaches 90% after the artificial intelligence is compared with the acquired video through the video clip stored in the intelligent terminal, the artificial intelligence is changed from a standby state to a working state;
when the artificial intelligence is awakened, the video analysis module 100 analyzes the acquired video segment containing the awakening gesture, extracts the person who makes the awakening gesture and determines the person as an awakening person, then the artificial intelligence locks the awakening person, and controls the video analysis module 100 and the audio analysis module 200 to respectively acquire face information, action information and audio information of the awakening person through a video acquisition device and an audio acquisition device;
the awakening words are preset in specific voice segments in artificial intelligence, and the method for acquiring the awakening action is to lock awakened people through the acquired tones and tones of the specific voice segments;
for example, the awakening word can be a wisdom classmate, and when a person speaks the wisdom classmate, the artificial intelligence is awakened;
when needing attention, the awakening words are voice segments of the abnormal words, so that artificial intelligence is prevented from being awakened by mistake;
the audio analysis module 200 in the artificial intelligence acquires external audio in real time through a connected audio acquisition device and compares the external audio with a built-in audio clip frame by frame, and when the matching degree of the acquired audio and the audio clip reaches a preset value, the artificial intelligence is switched from a standby state to a working state;
for example, the audio segment is a wisdom classmate, the audio acquisition device sends the audio acquired from the outside to the audio analysis module 200, the audio analysis module 200 converts the audio into a fluctuating form to be compared with the waveform of the audio segment containing the wisdom classmate, and when the coincidence ratio of the two reaches 90%, the artificial intelligence is awakened;
when the artificial intelligence is awakened, the audio analysis module 200 analyzes the sound source position of the audio containing the awakening word and records the tone information of the person who utters the awakening word, the video analysis module 100 aims at the sound source position by controlling the acquisition direction of the video acquisition module, the video acquisition device captures the video of the person who utters the awakening word, when the awakening person utters the sound again, the audio acquisition analysis module 200 compares the tone information of the audio acquired by the audio acquisition device with the recorded tone information, meanwhile, the video analysis module 100 analyzes the person who moves in the mouth in the video acquired by the video acquisition module and determines the person as the awakening person, and the video analysis module 100 and the audio analysis module 200 respectively acquire the face information, the action information and the audio information of the awakening person through the video acquisition device and the audio acquisition device;
in some examples, the audio acquisition device includes at least two sets of acquisition modules, and the audio analysis module 200 draws a circle with a radius value corresponding to the volume of the acquired audio by analyzing the volume of the audio acquired by each acquisition module, where an area where an intersection of the circle is located is a sound source position;
the awakening instruction is a command sent by a control end preset at the upper layer of the artificial intelligence, the artificial intelligence program can lock awakening personnel by locking a person operating the control end,
for example, in an interactive environment of a client class, a control end of the client sends a wakeup instruction to artificial intelligence, a wakeup person sends interactive information to the control end through an interactive tool for operating the client, such as a keyboard, a mouse, a touch screen, and the like, the control end sends the received interactive information to the artificial intelligence, when the artificial intelligence receives the wakeup instruction, the video analysis module 100 acquires a person operating the interactive tool by controlling the video acquisition device and determines the person as the wakeup person, and the video analysis module 100 and the audio analysis module 200 acquire face information, action information, and audio information of the wakeup person through the video acquisition device and the audio acquisition device respectively;
the artificial intelligence acquires biological information of awakening personnel through an image acquisition device and an audio acquisition device, wherein the biological information comprises but is not limited to face information, tone and tone information, and the artificial intelligence searches a built-in response database by taking the acquired biological information as search information and calls an exclusive response strategy stored in the response database;
as shown in fig. 2 and fig. 3, a response database 500 is further disposed in the artificial intelligence, the response database 500 is stored in the intelligent terminal, and the response database 500 includes an exclusive response database 510 and a general response database 520;
as shown in fig. 3, the dedicated response policy is stored in a dedicated response database 510 dedicated to a specific awakening person, the dedicated response database 510 uses the biological information of the awakening person as the search information, the dedicated response database 510 is stored in an artificial intelligence response database 500, and after the artificial intelligence obtains the biological information of the awakening person, the response database 500 is searched through the biological information and matched with the dedicated response database 510;
the exclusive response strategy gives different responses according to the interactive information sent by the awakening personnel under different situations;
as shown in fig. 2, as a preferred mode of the present invention, the artificial intelligence further includes an emotion analyzing module 300, the emotion analyzing module 300 is configured to analyze an emotion of a waking person, a plurality of different sets of dedicated response strategies are preset in the dedicated response database 510 according to emotion information of the waking person, and the artificial intelligence gives different responses to the same interaction information under different emotions;
as shown in fig. 4, the response strategy in the dedicated response database 510 is classified into negative emotion, calm emotion and active emotion according to emotion, and the classification of negative emotion can be further classified into angry emotion and fallen emotion; the emotion analysis module 300 analyzes the emotion of the awakened person by analyzing the face information and the tone information of the awakened person, and analyzes the response strategy according to the analyzed emotion under the emotion grouping;
in some examples, the face information and tone information of the awakened person under a calm emotion are preset in the emotion analysis module 300, when the eyebrow spacing of the awakened person is captured by the emotion analysis module 300 relative to the eyebrow spacing under the calm emotion, the emotion analysis module 300 judges that the emotion of the awakened person is in a negative emotion, and when the tone of the awakened person is higher, the emotion of the awakened person can be further judged to be around an angry emotion under the condition that the emotion of the awakened person is in a negative emotion; different classifications are set in the exclusive response database 510 according to different emotions;
when the emotion analysis module 300 captures the eyebrow height of the awakened person relative to the eyebrow pitch under calm emotion, the emotion analysis module 300 judges that the emotion of the awakened person is in positive emotion;
the setting of the exclusive response strategy can enable the artificial intelligence to select different response strategies when different awakening personnel are awakened, and meanwhile, the artificial intelligence can have different response strategies when the same awakening personnel are in different situations, so that the intelligent degree of the artificial intelligence is improved;
further, when the artificial intelligence is not matched with the exclusive response strategy of the awakening person, the artificial intelligence acquires the response strategy from the general response database 520 for interaction.
As another preferred embodiment of the invention, the interaction mode of the invention can be performed by gesture interaction, voice interaction and text interaction, thereby improving the convenience of artificial intelligence interaction;
a semantic analysis module 400 and a semantic database 600 are arranged in the artificial intelligence, wherein the semantic analysis module 400 analyzes the semantics of the awakening person from the video information acquired from the video analysis module 100, the voice information acquired from the audio analysis module 200 and the character information input by the awakening person, and retrieves the response action from the response database 500 according to the acquired semantics;
in some examples, the semantic database 600 includes a gesture database 610, a voice database 620 and a word database 630, the gesture database 610 stores basic gesture and corresponding semantics, the voice database 620 stores corresponding semantics of different audio segments, the word database 630 stores corresponding semantics of different text messages, and the artificial intelligence obtains semantics of a person to be woken up by comparing the gesture, audio segments and text messages stored in the gesture database 610, the voice database 620 and the word database 630;
under the gesture interaction scene, the artificial intelligence analyzes interaction information transmitted by the awakening person by acquiring sign language actions of the awakening person, acquires and decomposes sign language video segments of the awakening person into sign language basic actions which are matched with the sign language basic actions stored in the language database to obtain semantics to be expressed by the awakening person, and the artificial intelligence makes response actions according to the semantics to be expressed by the awakening person;
it should be noted that in the interactive scenario of question-answering, artificial intelligence responds by video output to the combination of basic actions of the adversary;
under the voice interaction scene, the artificial intelligence acquires the voice fragment of the awakening person and analyzes the keywords in the voice fragment, obtains the semantics through the retrieval of the keywords in the voice database 620, matches the response strategy in the response database 500 through the acquired semantics, and makes a response through a video, action or voice mode after the artificial intelligence acquires the response strategy;
it should be noted that, in the interactive scenario of question-answering, artificial intelligence makes a voice response through the voice response in the voice database 620 by matching the response voice with the response policy acquired in the response database 500 and through the audio playing device;
under the situation of character interaction, a person is awakened to input a sentence, artificial intelligence extracts a keyword from the sentence and matches semantics in the character database 630, and the artificial intelligence acquires a response strategy from the response database 500 according to the matched semantics;
the artificial intelligence further comprises a response output module 700, the response output module 700 is used for outputting response actions, and the response output module 700 is connected with a video output device, an audio output device and a mechanical arm of the intelligent terminal.
In summary, the embodiment provided by the invention matches different response strategies for different awakening persons, and makes different response actions according to the moods or the situations of the awakening persons, so that the artificial intelligence realizes the improvement of individuation and intelligence when making the response actions.
An artificial intelligence interaction system, comprising:
the acquisition module is used for acquiring the awakening action, the biological information of the awakened person and the interactive information sent by the awakened person;
the acquisition module comprises a video acquisition device, an audio acquisition device, a touch screen, a mouse, a keyboard and other devices capable of inputting information;
the information processing module is used for analyzing information containing awakening actions, biological information of awakened persons and interactive information sent by the awakened persons;
the information processing module compares the video and audio acquired by the acquisition module with a preset video segment and a preset audio segment when the artificial intelligence is in a standby state, and analyzes whether the video and the audio contain awakening actions or not;
the information processing module analyzes the video and the audio acquired by the acquisition module when the artificial intelligence is awakened, extracts biological information and interactive information of awakened persons in the video and the audio and matches an answer strategy according to the biological information and the interactive information;
the storage module is used for storing a response strategy;
in some examples, the storage module is a memory;
and the response module finishes response action by calling the response strategy in the storage module.
A computer device comprises a processor, a storage module, an input unit, an output unit and a computer program which is stored in the processor and can run in the processor, wherein the computer program can realize the steps of the artificial intelligence interaction method when running, the input unit comprises but is not limited to a video acquisition module, an audio acquisition module, a touch screen, a keyboard and a mouse, the output module comprises but is not limited to a video output module, an audio output module and an execution end, and the execution end comprises but is not limited to an intelligent home and a vehicle;
the processor may be a central processing unit, but may also be other general purpose processors, digital signal processors, application specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the computer apparatus and connects the various parts of the overall user terminal using various interfaces and lines.
A storage medium having stored therein a computer program which, when executed by a processor, is operable to carry out the steps of the artificial intelligence interaction method described above.
The processor may be a central processing unit, but may also be other general purpose processors, digital signal processors, application specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the computer apparatus and connects the various parts of the overall user terminal using various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement various functions of the computer device by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one magnetic disk storage device, a flash memory device, or other volatile solid state storage device.
The modules/units integrated by the computer device may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunications signal, software distribution medium, etc.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An artificial intelligence interaction method is applied to an intelligent terminal, and is characterized by comprising the following steps:
acquiring a wake-up action, wherein the wake-up action comprises a wake-up gesture, a wake-up word and a wake-up instruction;
determining a awakening person through an awakening action, and acquiring biological information of the awakening person, wherein the biological information at least comprises face information, action information and audio information of the awakening person;
and matching and outputting an exclusive response strategy of the awakening person according to the acquired biological information, wherein the exclusive response strategy is to preset a plurality of groups of different response actions according to the biological information of the awakening person.
2. The artificial intelligence interaction method of claim 1, wherein the specific assurance of acquiring the wake-up action comprises at least one of:
acquiring a video, comparing the video with a preset video clip, and switching from a standby state to a working state when the matching degree of the acquired video and the video clip reaches a preset value;
acquiring an audio frequency, comparing the audio frequency with a preset audio frequency fragment, and switching from a standby state to a working state when the matching degree of the acquired audio frequency and the audio frequency fragment reaches a preset value;
and switching the standby state into the working state when the wake-up instruction of the upstream control end is acquired.
3. The artificial intelligence interaction method of claim 2, wherein the specific step of determining to wake up the person through the wake-up action comprises at least one of:
the method comprises the steps that a person who makes a wakeup gesture in a video clip containing the wakeup gesture acquired by a video acquisition device is determined as a wakeup person, and biological information of the wakeup person is acquired through the video acquisition device and an audio acquisition device;
the method comprises the steps that a person who speaks the awakening word in an audio clip containing the awakening word acquired by an audio acquisition device serves as an awakening person, meanwhile, the video acquisition device and the audio acquisition device are matched to capture the person who speaks the awakening word and determine the person as the awakening person, and biological information of the awakening person is acquired through the video acquisition device and the audio acquisition device;
the method comprises the steps of obtaining a person operating a control end through a video acquisition device, determining the person as a awakening person, and acquiring biological information of the awakening person through the video acquisition device and an audio acquisition device.
4. The artificial intelligence interaction method of claim 3, wherein the step of determining to wake up the person comprises:
the position of the sound source containing the awakening words is obtained through the audio acquisition device, and people at the position of the sound source are obtained through the video acquisition device and serve as awakening personnel.
5. The artificial intelligence interaction method of claim 1, wherein the step of matching a dedicated response policy of a waking person comprises:
and taking the acquired biological information as search information to search a built-in response database, and calling a special response strategy stored in the response database.
6. The artificial intelligence interaction method of claim 5, wherein the step of matching a proprietary response policy further comprises:
analyzing the emotion of the awakened person according to the acquired biological information;
acquiring interactive information sent by awakening personnel, and retrieving an exclusive response strategy corresponding to the awakening personnel at the moment based on the interactive information;
invoking a response action corresponding to the emotion of the awakening person in the exclusive response strategy;
and outputting the response action.
7. The artificial intelligence interaction method of claim 1, further comprising:
and when the exclusive response strategy of the awakening personnel is not matched, calling the response strategy stored in the general response database and outputting the response strategy.
8. An artificial intelligence interaction system, comprising:
the acquisition module is used for acquiring the awakening action, the biological information of the awakened person and the interactive information sent by the awakened person;
the information processing module is used for analyzing information containing awakening actions, biological information of awakened persons and interactive information sent by the awakened persons;
the storage module is used for storing a response strategy;
and the response module finishes response action by calling the response strategy pinched by the storage module.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor for implementing the steps of the method according to any one of claims 1-7 when executing a computer program stored in a memory.
10. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110152305.4A CN112965590A (en) | 2021-02-03 | 2021-02-03 | Artificial intelligence interaction method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110152305.4A CN112965590A (en) | 2021-02-03 | 2021-02-03 | Artificial intelligence interaction method, system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112965590A true CN112965590A (en) | 2021-06-15 |
Family
ID=76275026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110152305.4A Pending CN112965590A (en) | 2021-02-03 | 2021-02-03 | Artificial intelligence interaction method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112965590A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965864A (en) * | 2021-09-28 | 2022-01-21 | 武汉左点科技有限公司 | Intelligent interaction method and device for hearing aid |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110265021A (en) * | 2019-07-22 | 2019-09-20 | 深圳前海微众银行股份有限公司 | Personalized speech exchange method, robot terminal, device and readable storage medium storing program for executing |
| CN110689889A (en) * | 2019-10-11 | 2020-01-14 | 深圳追一科技有限公司 | Man-machine interaction method and device, electronic equipment and storage medium |
-
2021
- 2021-02-03 CN CN202110152305.4A patent/CN112965590A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110265021A (en) * | 2019-07-22 | 2019-09-20 | 深圳前海微众银行股份有限公司 | Personalized speech exchange method, robot terminal, device and readable storage medium storing program for executing |
| CN110689889A (en) * | 2019-10-11 | 2020-01-14 | 深圳追一科技有限公司 | Man-machine interaction method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965864A (en) * | 2021-09-28 | 2022-01-21 | 武汉左点科技有限公司 | Intelligent interaction method and device for hearing aid |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107632706B (en) | Application data processing method and system of multi-modal virtual human | |
| EP3617946B1 (en) | Context acquisition method and device based on voice interaction | |
| CN106202165B (en) | Intelligent learning method and device for man-machine interaction | |
| CN109656512A (en) | Exchange method, device, storage medium and terminal based on voice assistant | |
| WO2021135685A1 (en) | Identity authentication method and device | |
| EP3896598A1 (en) | Method deciding whether to reject audio for processing and corresponding device and storage medium | |
| CN107515900B (en) | Intelligent robot and event memo system and method thereof | |
| KR20080063480A (en) | Semantic visual search engine | |
| CN108682414A (en) | Sound control method, voice system, equipment and storage medium | |
| CN108595406B (en) | User state reminding method and device, electronic equipment and storage medium | |
| CN110544468B (en) | Application awakening method and device, storage medium and electronic equipment | |
| JP2021176093A (en) | Selective detection of visual clue for automated assistant | |
| CN112908325B (en) | Voice interaction method and device, electronic equipment and storage medium | |
| WO2022037600A1 (en) | Abstract recording method and apparatus, and computer device and storage medium | |
| CN108345612A (en) | A kind of question processing method and device, a kind of device for issue handling | |
| CN112364799A (en) | Gesture recognition method and device | |
| CN110825164A (en) | Interaction method and system based on wearable intelligent equipment special for children | |
| CN116340778B (en) | Medical large model construction method based on multiple modes and related equipment thereof | |
| CN114268747A (en) | Interview service processing method based on virtual digital people and related device | |
| CN110706707A (en) | Method, apparatus, device and computer-readable storage medium for voice interaction | |
| CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
| CN112965590A (en) | Artificial intelligence interaction method, system, computer equipment and storage medium | |
| CN111444321B (en) | Question answering method, device, electronic equipment and storage medium | |
| CN111210824A (en) | Voice information processing method and device, electronic equipment and storage medium | |
| CN110674482B (en) | Multi-scene application computer |
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 |