CN110598089A - Voice assistant method and system based on environmental information processing - Google Patents
Voice assistant method and system based on environmental information processing Download PDFInfo
- Publication number
- CN110598089A CN110598089A CN201810521245.7A CN201810521245A CN110598089A CN 110598089 A CN110598089 A CN 110598089A CN 201810521245 A CN201810521245 A CN 201810521245A CN 110598089 A CN110598089 A CN 110598089A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- cloud service
- service platform
- search result
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to a voice service method and a system based on environmental information processing, comprising the following steps: carrying out voice communication with a user; according to the voice communication, a search request is obtained, and a cloud service platform obtains first environment information of the user through at least one of a plurality of mobile computing devices carried and/or worn by the user; when the search request is obtained, the cloud service platform further obtains the biological characteristics of the user through at least one of the mobile computing devices; identifying different users according to different biological characteristics, and correspondingly acquiring pre-stored configuration information of the users corresponding to the biological characteristics; the cloud service platform generates a second search result containing the preference of the user in the first environment information and the configuration information based on the first environment information and the configuration information of the user; and the cloud service platform provides the first search result and the second search result to the user together in a voice interaction mode.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a voice assistant method and system based on environmental information processing.
Background
The revolution of the information-oriented era brings great convenience to people, and the popularization of portable mobile terminals represented by smart phones redefines the production and living modes of people. And the interaction mode of human and machine is also continuously innovated, wherein the voice recognition technology is continuously developed along with the popularization of intelligent terminals. Speech recognition technology is a technology that enables a machine to convert speech signals into corresponding text or commands by recognizing and understanding human speech.
The existing voice recognition technology is mainly applied to a voice assistant of an intelligent terminal, the voice assistant is an intelligent mobile phone application, and the problem solving of a user for help is realized through intelligent interaction of intelligent conversation and instant question and answer.
However, the existing voice assistant cannot distinguish different people according to different voices, and any person can only have the same answer to the same question, so that the existing voice assistant is not intelligent, humanized and lively.
Chinese patent publication No. CN105957525A discloses an interactive method of voice assistant and user equipment, including: acquiring the biological characteristics of a user; according to the biological characteristics, obtaining pre-stored voice interaction information corresponding to the biological characteristics; and carrying out voice communication with the user according to the voice interaction information. The embodiment of the invention also discloses the user equipment. The embodiment of the invention can acquire different voice interaction information aiming at the biological characteristics of different users, and therefore, voice communication is carried out, thereby improving the intellectualization, humanization and entertainment of the scheme. However, the patent can not provide more accurate search results for the user in combination with the environmental conditions of the user.
Chinese patent publication No. CN103167106B discloses a mobile terminal control device based on environmental information, which includes: the storage module is used for storing a plurality of external environmental conditions and functional operation commands corresponding to the external environmental conditions in advance; the environment information acquisition module is used for acquiring external environment information of the mobile terminal; the environment information analysis module is used for receiving the external environment information and judging the external environment condition met by the external environment information; and the control module is used for receiving the judgment result of the environment information analysis module, calling a function operation command corresponding to the external environment condition met by the external environment information from the storage module, and controlling the mobile terminal to start or prohibit the corresponding function through the called function operation command. The inconvenience that mode switching brought has only been carried out through the manual work among the prior art has been solved in this application. However, this patent does not give targeted results to the user's preferences.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a voice assistant method and system based on environmental information processing. According to the method, the system and the device, the mark event is tracked, the surrounding environment information is acquired when the mark event occurs, the biological characteristics of the user are identified, the user preference based on the mark event under the environment information is analyzed for different users, the accuracy of providing search service for the cloud service platform is improved, and the user experience is greatly improved.
According to a preferred embodiment, a voice service method based on environment information processing includes: carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and a cloud service platform generates a first search result according to the search request of the user;
when the search request is obtained, the cloud service platform obtains first environment information of the user through at least one of a plurality of mobile computing devices carried and/or worn by the user;
when the search request is obtained, the cloud service platform further obtains the biological characteristics of the user through at least one of the mobile computing devices; identifying different users according to different biological characteristics, and acquiring pre-stored configuration information of the users corresponding to the biological characteristics, wherein the configuration information at least comprises age information, place of birth information, place of residence information, sex information and hobby information of the users; performing voice communication with the user according to the configuration information of the user;
the cloud service platform generates a second search result containing the preference of the user in the first environment information and the configuration information, which is identified in a fitting manner, based on the first environment information and the configuration information of the user;
the cloud service platform provides the first search result and the second search result to the user together in a voice interaction mode;
the cloud service platform screens merchants which are located in a coverage area near a real-time position of the user and can provide services corresponding to at least part of the first search result and/or the second search result, and provides information of at least part of the merchants to the user in a voice mode; when the user determines to go to one of the merchants, the detailed information of the merchant is pushed, and the user is asked whether to reserve the merchant through the cloud service platform;
when the user moves, the navigation route is provided for the user in a voice broadcast mode, and meanwhile the coverage area moves along the navigation route in a correlated mode along with the real-time position so as to dynamically push the information of at least part of other merchants beside the navigation route.
According to a preferred embodiment, the configuration information of the user is configured in the following manner:
tracking online activity of a user by at least one of a number of mobile computing devices carried and/or worn by the user to obtain a correlated marker event;
acquiring and identifying the biological characteristics of the user through at least one of the plurality of mobile computing devices when at least one mark event occurs, and recording first environment information of the user when the mark event occurs;
the cloud service platform finds out the configuration information of the user based on the identified biological characteristics of the user, processes the mark event and the first environment information corresponding to the mark event, analyzes the preference of the user for the corresponding mark event under the corresponding environment information, and updates the configuration information of the user accordingly.
According to a preferred embodiment, the cloud service platform is configured to:
after the cloud service platform generates a first search result and a second search result, acquiring content reactions of a user to displayed parts of the first search result and the second search result;
and dynamically adjusting the display sequence of the undisplayed parts of the subsequently provided first search result and the second search result according to the reaction so as to fit the requirement of the user on the first search result or the second search result.
According to a preferred embodiment, the reaction is identified by the user's action on the displayed portions of the first and second search results in combination with at least one of the following collected information:
voice information of the user collected by at least one of the number of mobile computing devices through its voice interaction element during user communication with the number of mobile computing devices for content of the first search result and the second search result;
the reaction is a gesture and a physical action of the user captured by at least one of the number of mobile computing devices through its motion sensor during the user's browsing of the content of the displayed portions of the first and second search results.
According to a preferred embodiment, the user's time-dependent geographic location information is tracked by at least one of the number of mobile computing devices;
the cloud service platform establishes a track model based on a moving track for the user in a space-time database based on the geographic position information;
the cloud service platform predicts at least one predicted destination to which the user arrives to go based on the track model and the configuration information of the user;
the cloud service platform generates a third search result containing a preference which is in accordance with the second environment information of the user at the predicted destination according to the second environment information of the predicted destination and the configuration information of the user;
and the cloud service platform provides the third search result for the user in a voice interaction mode.
According to a preferred embodiment, the second environment information is obtained as follows:
when the search request is obtained, obtaining the current position and the movement condition of the user and analyzing a first time length required by the user from the current position to the predicted destination;
under the condition that the first time is less than or equal to a first time threshold, the cloud service platform acquires real-time environment information of a predicted destination as second environment information through at least one of a plurality of mobile intelligent devices of a user at the predicted destination after acquiring a search request and before providing a third search result;
under the condition that the first time length is larger than a first time threshold value, the cloud service platform acquires real-time environment information of a predicted destination and predicts second environment information when a user reaches the predicted destination based on the real-time environment information and historical environment information of the predicted destination;
wherein at least one of the user's number of mobile smart devices may be configured to: the real-time environment information of the predicted destination is acquired only in a bright screen state where the authorization of the user is obtained and the user is prompted through a corresponding indicator lamp when the real-time environment information of the predicted destination is acquired.
According to a preferred embodiment, the cloud service platform presents a movement track created based on geographic position information for the user on a GIS map through at least one of the mobile computing devices, labels a corresponding mark event and first environment information corresponding to a corresponding specific time on the movement track in an associated manner, and labels a corresponding preference weight index at the corresponding mark event in an associated manner, wherein the preference weight index represents a weight of the corresponding mark event on the analysis of the preference of the user for the corresponding mark event under the corresponding environment information, and the cloud service platform provides modification authority of the preference weight index for the user so that the user can modify the preference weight index within a preset modification range;
wherein the cloud service platform is configured to: and providing the modification authority for the user only in a preset time range after the corresponding mark event occurs, and canceling the modification authority after the preset time range is exceeded.
According to a preferred embodiment, the environmental information includes at least one of environmental properties, time information, light information, location conditions, humidity information, ambient temperature information, and sound information.
According to a preferred embodiment, the online activity comprises at least one of an email, web content, instant messaging, browsing history, online games, and online transactions; the biometric characteristic includes at least one of voiceprint information, fingerprint information, and iris characteristic information.
According to a preferred embodiment, the present invention also discloses a voice service system based on environmental information processing, comprising: carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and a cloud service platform generates a first search result according to the search request of the user;
when the search request is obtained, the cloud service platform obtains first environment information of the user through at least one of a plurality of mobile computing devices carried and/or worn by the user, and meanwhile, the cloud service platform also obtains biological characteristics of the user through at least one of the plurality of mobile computing devices; according to the biological characteristics, pre-stored configuration information of the user corresponding to the biological characteristics is obtained;
the cloud service platform generates a second search result containing the preference which is in accordance with the first environment information and the configuration information of the user based on the first environment information and the configuration information of the user;
and the cloud service platform provides the first search result and the second search result to the user together in a voice interaction mode.
The invention provides a voice assistant method and system based on environmental information processing, which at least have the following advantages:
(1) according to the method and the device, the configuration information of different users is identified by collecting and identifying the biological characteristics of the users, so that targeted service can be provided according to the preferences of different users, and the requirements of different users are met.
(2) The invention realizes man-machine interaction in a voice communication mode, liberates the hands of a user, and is suitable for use scenes such as driving and the like which are inconvenient for the user to slide or press for operation.
(2) According to the method, the mark event is tracked, the surrounding environment information is acquired when the mark event occurs, the cloud service platform analyzes the preference of the user for the mark event under the environment information, the accuracy of providing search service by the cloud service platform is improved, and the user experience is greatly improved;
(3) according to the invention, the second environment information required for providing the third search result is acquired through the plurality of mobile intelligent devices carried by the user, so that the deployment amount of monitoring equipment can be reduced, the feasibility and the search satisfaction of the invention are improved under the condition of utilizing the existing resources, and the user experience is further improved;
(4) according to the method, the mobile track and the label on the GIS map are used for quickly and accurately helping the user to recall the current environmental condition, and the preference weight index is artificially modified in combination with the understanding of the preference of the user, so that the second search result and/or the third search result are more accurate; in addition, the invention also sets the preset time range capable of being modified, and under the condition that the preset time range is exceeded, the cloud service platform 10 cancels the modification authority of the preference weight index of the user, so that the reduction of the searching precision caused by the random modification of the preference weight index by the user is prevented, and the searching quality is ensured.
Drawings
FIG. 1 is a block schematic diagram of a preferred embodiment of the system of the present invention; and
FIG. 2 is a schematic flow diagram of a preferred embodiment of the method of the present invention.
List of reference numerals
10: cloud service platform 20: mobile computing device
30: mobile intelligent equipment
Detailed Description
The following detailed description is made with reference to fig. 1 and 2.
Example 1
The embodiment discloses a voice service method based on environmental information processing, and under the condition of not causing conflict or contradiction, the whole and/or part of the contents of the preferred implementation modes of other embodiments can be used as a supplement of the embodiment. Preferably, the method may be implemented by the system of the present invention and/or other alternative modules. For example, the method of the present invention is implemented by using various modules in the system of the present invention.
According to an alternative embodiment, the method may comprise at least one of the following steps:
carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and the cloud service platform 10 generates a first search result according to the search request of the user;
while acquiring the search request, the cloud service platform 10 acquires first environment information of the user through at least one of a plurality of mobile computing devices 20 carried and/or worn by the user;
while acquiring the search request, the cloud service platform 10 further acquires the biometric features of the user through at least one of the mobile computing devices 20; identifying different affiliated users according to different biological characteristics, and correspondingly acquiring pre-stored configuration information of the users corresponding to the biological characteristics, wherein the configuration information at least comprises age information, place of birth information, place of residence information, sex information and hobby information of the users; performing voice communication with the user according to the configuration information of the user;
the cloud service platform 10 generates a second search result containing a preference fitting the user in the first environment information and the configuration information based on the first environment information and the configuration information of the user;
the cloud service platform 10 provides the first search result and the second search result to the user together in a voice interaction manner.
The cloud service platform 10 screens out merchants which are located in a coverage area near a real-time position of the user and can provide services corresponding to at least part of the first search result and/or the second search result, and provides information of at least part of the merchants to the user in a voice mode; when the user determines to go to one of the merchants, the detailed information of the merchant is pushed and the user is asked whether to reserve the merchant through the cloud service platform 10;
when the user goes to the merchant, the navigation route is provided for the user in a voice broadcasting mode, and meanwhile, the coverage area moves along the navigation route in a correlated mode along with the real-time position so as to dynamically push the information of at least part of other merchants located beside the navigation route.
Preferably, before the cloud service platform 10 acquires the first environment information, the plurality of mobile computing devices 20 process the first environment information to extract a first environment parameter corresponding to the second environment information, and the cloud service platform 10 acquires the first environment parameter to acquire the first environment information. As the first context information may include audio, video and pictures. The amount of data is large and privacy may be involved, so that the cloud service platform 10 only obtains the first environment parameter can reduce communication overhead and prevent privacy data leakage.
According to another alternative embodiment, referring to fig. 2, the method may comprise at least one of the following steps:
step S100: acquiring the biological characteristics of a user; according to the biological characteristics, pre-stored user configuration information corresponding to the biological characteristics is obtained;
step S200: tracking, by at least one of the number of mobile computing devices 20 moving with the user, time-related geographic location information of the user during a period of time;
step S300: while tracking the geographic location information of the user, synchronously tracking, by at least one of the number of mobile computing devices 20, online activity at the user and time-registering with the geographic location information;
step S400: processing the time-dependent geographic location information and online activity to analyze the user's preferences and/or habits for the flagged events under the respective environmental information over the time period and to update the user configuration information accordingly;
step S500: acquiring a search request including expected information input by the user through voice communication, and generating a first search result by the cloud service platform 10 according to the search request of the user;
step S600: while obtaining a search request input by a user and including search parameters corresponding to desired information, obtaining current geographic location information of the user through at least one of a plurality of mobile computing devices 20 carried and/or worn by the user to determine current environmental information, and generating a second search result including information associated with the current environmental information and preferences and/or habits of the user based on the current environmental information and user configuration information;
step S700: the cloud service platform 10 provides the first search result and the second search result to the user together.
According to a preferred embodiment, the configuration information of the user is configured in the following manner: tracking online activity of a user by at least one of a number of mobile computing devices 20 carried and/or worn by the user to obtain a relevant flagged event;
upon occurrence of at least one marker event, a biometric of the user is obtained and identified by at least one of the number of mobile computing devices 20, and first context information of the user at the time of the marker event is recorded.
The cloud service platform 10 finds out the configuration information of the user based on the identified biological characteristics of the user, and processes the mark event and the first environment information corresponding to the mark event, so as to analyze the preference of the user for the corresponding mark event under the corresponding environment information and update the configuration information of the user accordingly.
Preferably, assuming that the user currently using at least one of the mobile computing devices 20 for voice communication is a young man, the man utters a voice prompt "how much it is today's weather" at 8 o ' clock 30 m monday morning of the last week, the mobile computing device 20 recognizes and returns "today's weather is sunny and the temperature is 25 to 29 degrees celsius", then the man asks "how strong the ultraviolet light is", and the mobile computing device 20 recognizes and returns "strong ultraviolet light, suggesting to wear sunglasses". Mobile computing device 20 may update the user's configuration information for the preferences of the question. Then, at 8 o' clock 30 m the morning on monday of the week, the man again utters the voice prompt "how to weather today" at which time the mobile computing device 20 will automatically retrieve the past historical communication log information. The content of direct recovery is 'the rain gust is accompanied today, the temperature is 22 to 26 ℃, and the ultraviolet rays are weak'. At this point, the user is finished communicating with the mobile computing device.
According to a preferred embodiment, the cloud service platform 10 is configured to: after the cloud service platform 10 generates the first search result and the second search result, acquiring content reactions of the displayed parts of the first search result and the second search result from the user; and dynamically adjusting the display sequence of the undisplayed parts of the subsequently provided first search result and the second search result according to the reaction so as to fit the requirement of the user on the first search result or the second search result.
According to a preferred embodiment, the reaction is identified by the user's action on the displayed portions of the first and second search results in combination with at least one of the following collected information: voice information of the user collected by at least one of the number of mobile computing devices 20 through its voice interaction element during user interaction with the number of mobile computing devices 20 for the content of the first search result and the second search result; the reaction is a gesture and a physical action of the user captured by at least one of the number of mobile computing devices 20 through its motion sensor during the user's browsing of the content of the displayed portions of the first and second search results.
According to a preferred embodiment, the reactions may include likes, neutrality, and dislikes. Preferably, the cloud service platform 10 can also assign different grades for like, neutral and dislike respectively. For example, like, neutral, and dislike may have two levels, respectively. When the user searches for music, if "all play and save" is replied to the ten pieces of classical music that have been displayed, and "all play" is replied to the ten pieces of rock music that have been displayed, classical music is assigned as a first level of liking and rock music is assigned as a second level of liking. If the displayed ten jazz music is replied to "play the top five," it is assigned a neutral first rank. If the displayed ten heavy metal pieces of music are replied to "play first", they are assigned to a neutral second level. If "skip" is replied to the ten pieces of country music that have been displayed, it is assigned as a disliked first rank. If ten punk music that has been displayed are returned "not being displayed," they are assigned a second level of dislikes.
According to a preferred embodiment, the user's time-dependent geographic location information is tracked by at least one of the number of mobile computing devices 20; the cloud service platform 10 establishes a track model based on a moving track for the user in a space-time database based on the geographic position information;
the cloud service platform 10 predicts at least one predicted destination to which the user arrives to go based on the track model and the configuration information of the user; the cloud service platform 10 generates a third search result containing a preference which is in accordance with the second environment information of the user at the predicted destination according to the second environment information of the predicted destination and the configuration information of the user; and the cloud service platform 10 provides the third search result to the user in a voice interaction manner.
According to a preferred embodiment, the second environment information is obtained as follows: when the search request is obtained, obtaining the current position and the movement condition of the user and analyzing a first time length required by the user from the current position to the predicted destination; in the case that the first time period is less than or equal to the first time threshold, the cloud service platform 10, after obtaining the search request and before providing the third search result, obtains real-time environment information of the predicted destination as second environment information through at least one of the mobile smart devices 30 of the users located at the predicted destination; under the condition that the first time length is larger than a first time threshold value, the cloud service platform 10 acquires real-time environment information of a predicted destination and predicts second environment information when a user arrives at the predicted destination based on the real-time environment information and historical environment information of the predicted destination;
preferably, before the cloud service platform 10 acquires the second environment information, at least one of the mobile smart devices 30 processes the second environment information to extract a second environment parameter corresponding to the second environment information, and the cloud service platform 10 acquires the second environment parameter to indirectly acquire the second environment information. As the second context information may include audio, video and pictures. This results in a large amount of data and may involve privacy, so that the cloud service platform 10 only obtains the second environment parameters can reduce communication overhead and prevent private data leakage.
Preferably, at least one of the user's several mobile smart devices 30 may be configured to: the real-time environment information of the predicted destination is acquired only in a bright screen state where the authorization of the user is obtained and the user is prompted through a corresponding indicator lamp when the real-time environment information of the predicted destination is acquired.
According to a preferred embodiment, the cloud service platform 10 presents a movement track created based on geographic location information for the user on a GIS map through at least one of the mobile computing devices 20, and labels a corresponding flag event and first environment information corresponding to a corresponding specific time on the movement track in an associated manner, and labels a corresponding preference weight index at the corresponding flag event in an associated manner, wherein the preference weight index represents a weight of the corresponding flag event on analyzing a preference of the user for the corresponding flag event under the corresponding environment information, and the cloud service platform 10 provides a modification authority of the preference weight index for the user, so that the user can modify the preference weight index within a predetermined modification range; wherein the cloud service platform 10 is configured to: and providing the modification authority for the user only in a preset time range after the corresponding mark event occurs, and canceling the modification authority after the preset time range is exceeded.
According to a preferred embodiment, the environmental information includes at least one of environmental properties, time information, light information, location conditions, humidity information, ambient temperature information, and sound information.
Preferably, the environmental property is of a custom environmental type. For example, the environmental property may be classified as at least one of a workplace, a road, a sporting venue, an entertainment venue, a tourist attraction, and a residential venue. Preferably, the time information, the light information, the location condition, the humidity information, the ambient temperature information, and the sound information may be classified and counted according to the size of the dynamically changing particle size. Preferably, the granularity gradually becomes smaller as the amount of information for analyzing the preference of the user obtained by the cloud service platform 10 is larger. Preferably, the size of the granularity may vary in steps according to the number of pieces of information. For example, taking time information as an example, when the corresponding information amount is less than 100, the classification statistics can be performed according to the morning, afternoon, evening and late night. The morning may correspond to 06: 00-12: 00, which may correspond to 12: 00-18: 00, evening may correspond to 18: 00-24: 00, late at night may correspond to 00: 00-06: 00. the flag events performed by the user at 12:45 may be used to analyze the user's preferences in the afternoon. When the corresponding information amount is more than 100 and less than 1000, the classification and statistics can be carried out according to twelve hours, namely the classification and statistics can be carried out according to son, ugly, tiger, fourth of twelve earthly branches, twelve heaves, six branches, noon, unfinished, Shen, you, and Hai. And when the corresponding information quantity is more than 1000 and less than 10000, performing classification statistics according to hours. When the corresponding information amount is more than 10000 pieces, classification statistics can be carried out according to minutes. For another example, the sound information is divided into musical tones and noises. The musical tones can be classified and counted according to the type and decibel level of the played music. The noise can be counted in decibel scale.
According to a preferred embodiment, the online activity comprises at least one of an email, web content, instant messaging, browsing history, online games, and online transactions; the biometric characteristic includes at least one of voiceprint information, fingerprint information, and iris characteristic information.
Preferably, the event may include various online events performed by the user on the network. Such as at least one of playing music, playing video, online gaming, physical product transactions, and virtual product transactions. And what marks the event is specific trace content customized by the cloud service provider. For example, specifically, the cloud service platform 10 only tracks one or more events, which are mark events. As another example, more specifically, the cloud service platform 10 only tracks the mark events of playing music to provide personalized services for music.
Preferably, the flag event may include an event type and an event attribute. The event type and the event attribute may be specified by the cloud service platform 10. For example, the event type may include at least one of browsing a web page, playing music, playing a video, an online game, a physical product transaction, and a virtual product transaction. When the event type is playing music, its corresponding event attribute may include at least one of a music name, a tone color, a music genre, a singer, and an album. The physical product transaction is, for example, at least one of a restaurant checkout, purchasing accessories, purchasing books, purchasing beverages, purchasing takeoffs. The virtual product transaction is, for example, at least one of a stock transaction, a bond transaction, a bulk commodity transaction, and a virtual currency transaction.
Preferably, the voiceprint information is sound wave spectrum information carrying speech information displayed by the electro-acoustic instrument. The voiceprint is not only specific, but also has the characteristic of relative stability. After the adult, the voice of the human can be kept relatively stable and unchanged for a long time.
Preferably, the fingerprint information is the image data that the fingerprint of the person is stored in a certain way (e.g. stamping or scanning) so that the person can browse, review or compare, and analyze when necessary.
Preferably, the iris feature information is information for extracting an iris portion of a human eye, and the iris is an annular portion located between a black pupil and a white sclera, and includes a plurality of detailed features of spots, filaments, crowns, stripes, crypts, and the like, which are staggered with each other. And the iris will remain unchanged throughout life span after it is formed during the fetal development stage. These features determine the uniqueness of the iris features and also the uniqueness of the identification. Therefore, the iris feature of the eye can be used as an identification target for each person.
Preferably, the cloud service platform 10 may be a server or a server cluster.
According to a preferred embodiment, the number of mobile computing devices 20 and/or the number of mobile smart devices 30 may be at least one of a smartphone, smart glasses, a smart bracelet, a smart watch, a smart headset, and smart apparel.
Preferably, the number of mobile computing devices 20 may include smartphones and smart glasses. For example, the cloud service platform 10 is configured to track online activity for flagged events related to playing video. When a user browses a webpage on the smart phone and then browses a video, the user plays the video on the smart phone, and at the moment, the smart phone tracks a mark event related to the played video. At this time, the smart glasses acquire second environment information where the user is located when the video is played. The cloud service platform 10 obtains the mark event and the second environment information, and analyzes the mark event and the second environment information to obtain that the user likes to watch the information video under the environment condition. When the user searches for the video next time, a first search result composed of all videos is prepared for the user. If the second environmental condition of the user is the same as and/or similar to the environmental condition, providing a second search result composed of the information video for the user, and then providing the first search result and the second search result together for the user. Preferably, the cloud service platform 10 may determine a flag event associated with the search request according to the search request, thereby providing search and/or push services.
Example 2
The embodiment discloses a voice service system based on environmental information processing, which comprises: carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and the cloud service platform 10 generates a first search result according to the search request of the user; when the search request is obtained, the cloud service platform 10 obtains first environment information of the user through at least one of the mobile computing devices 20 carried and/or worn by the user, and meanwhile, the cloud service platform 10 also obtains a biological feature of the user through at least one of the mobile computing devices 20; identifying different users according to different biological characteristics, and correspondingly acquiring pre-stored configuration information of the users corresponding to the biological characteristics, wherein the configuration information at least comprises age information, place of birth information, place of residence information, sex information and hobby information of the users; performing voice communication with the user according to the configuration information of the user; the cloud service platform 10 generates a second search result containing a preference fitting the user in the first environment information and the configuration information based on the first environment information and the configuration information of the user; the cloud service platform 10 provides the first search result and the second search result to the user together in a voice interaction manner.
The cloud service platform 10 screens out merchants which are located in a coverage area near a real-time position of the user and can provide services corresponding to at least part of the first search result and/or the second search result, and provides information of at least part of the merchants to the user in a voice mode; when the user determines to go to one of the merchants, the detailed information of the merchant is pushed and the user is asked whether to reserve the merchant through the cloud service platform 10;
when the user moves, the navigation route is provided for the user in a voice broadcast mode, and meanwhile the coverage area moves along the navigation route in a correlated mode along with the real-time position so as to dynamically push the information of at least part of other merchants beside the navigation route.
It should be noted that the above-mentioned embodiments are exemplary, and that those skilled in the art, having benefit of the present disclosure, may devise various arrangements that are within the scope of the present disclosure and that fall within the scope of the invention. It should be understood by those skilled in the art that the present specification and figures are illustrative only and are not limiting upon the claims. The scope of the invention is defined by the claims and their equivalents.
Claims (10)
1. A voice service method based on environmental information processing is characterized by comprising the following steps: carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and a cloud service platform (10) generates a first search result according to the search request of the user;
while obtaining the search request, the cloud service platform (10) obtains first environment information of the user through at least one of a plurality of mobile computing devices (20) carried and/or worn by the user;
while obtaining the search request, the cloud service platform (10) further obtains the biometric features of the user through at least one of the mobile computing devices (20); identifying different users according to different biological characteristics, and correspondingly acquiring pre-stored configuration information of the users corresponding to the biological characteristics, wherein the configuration information at least comprises age information, place of birth information, place of residence information, sex information and hobby information of the users; performing voice communication with the user according to the configuration information of the user;
the cloud service platform (10) generates a second search result containing a preference for the identified user in the first environment information and the configuration information based on the first environment information and the configuration information of the user;
the cloud service platform (10) provides the first search result and the second search result to the user together in a voice interaction mode.
The cloud service platform (10) acquires the real-time position of the user under the condition that at least one of the mobile computing devices (20) is started to perform real-time positioning;
the cloud service platform (10) screens merchants which are located in the coverage area near the real-time position of the user and can provide services corresponding to at least part of the first search result and/or the second search result, and provides information of at least part of the merchants to the user in a voice mode; when the user determines to go to one of the merchants, pushing the detailed information of the merchant and inquiring whether the user reserves the merchant through the cloud service platform (10);
when the user moves, the navigation route is provided for the user in a voice broadcast mode, and meanwhile the coverage area moves along the navigation route in a correlated mode along with the real-time position so as to dynamically push the information of at least part of other merchants beside the navigation route.
2. The voice service method based on environment information processing according to claim 1, wherein the configuration information of the user is configured in the following manner:
tracking online activity of a user by at least one of a number of mobile computing devices (20) carried and/or worn by the user to obtain a correlated marker event;
obtaining and identifying, by at least one of the number of mobile computing devices (20), a biometric of the user upon occurrence of at least one marker event, and recording first context information of the user at the time of occurrence of the marker event;
the cloud service platform (10) correspondingly finds out the configuration information of the user based on the identified biological characteristics of the user, processes the mark event and the first environment information corresponding to the mark event, analyzes the preference of the user for the corresponding mark event under the corresponding environment information, and updates the configuration information of the user accordingly.
3. The voice service method based on environmental information processing according to claim 2, wherein the cloud service platform (10) is configured to:
after the cloud service platform (10) generates the first search result and the second search result, acquiring content reactions of the displayed parts of the first search result and the second search result of the user;
and dynamically adjusting the display sequence of the undisplayed parts of the subsequently provided first search result and the second search result according to the reaction so as to fit the requirement of the user on the first search result or the second search result.
4. The environmental information processing-based voice service method according to claim 3, wherein the reaction is recognized by the user's operation behavior on the displayed portions of the first search result and the second search result in combination with at least one of the collected following information:
voice information of the user collected by at least one of the number of mobile computing devices (20) through its voice interaction element during user communication with the number of mobile computing devices (20) for the content of the first search result and the second search result;
the reaction is a gesture and a physical action of the user captured by at least one of the number of mobile computing devices (20) through its motion sensor during the user's browsing of the content of the displayed portions of the first and second search results.
5. The context information processing-based voice service method according to claim 4, wherein the user's time-dependent geographic location information is tracked by at least one of the number of mobile computing devices (20);
the cloud service platform (10) establishes a track model based on a movement track for the user in a space-time database based on the geographic position information;
the cloud service platform (10) predicts at least one predicted destination for the user to arrive at based on the trajectory model and the configuration information of the user;
the cloud service platform (10) generates a third search result which is in accordance with the second environment information preference of the user at the predicted destination according to the second environment information of the predicted destination and the configuration information of the user;
and the cloud service platform (10) provides the third search result to the user in a voice interaction mode.
6. The voice service method based on environment information processing as claimed in claim 5, wherein the second environment information is obtained as follows:
when the search request is obtained, obtaining the current position and the movement condition of the user and analyzing a first time length required by the user from the current position to the predicted destination;
in the case that the first time is less than or equal to a first time threshold, the cloud service platform (10) acquires real-time environment information of a predicted destination as second environment information through at least one of a plurality of mobile intelligent devices (30) of users at the predicted destination after acquiring the search request and before providing the third search result;
under the condition that the first time length is larger than a first time threshold value, the cloud service platform (10) acquires real-time environment information of a predicted destination and predicts second environment information when a user arrives at the predicted destination based on the real-time environment information and historical environment information of the predicted destination;
wherein at least one of the user's number of mobile smart devices (30) may be configured to: the real-time environment information of the predicted destination is acquired only in a bright screen state where the authorization of the user is obtained and the user is prompted through a corresponding indicator lamp when the real-time environment information of the predicted destination is acquired.
7. The voice service method based on the context information processing as claimed in claim 6, the cloud service platform (10) presents a movement track created based on geographic position information for the user on a GIS map through at least one of the plurality of mobile computing devices (20) and labels corresponding mark events and first environment information corresponding to corresponding specific time on the movement track in an associated manner, the corresponding preference weight index is marked at the corresponding mark event in an associated manner, the preference weight index represents the weight of the corresponding mark event on the preference of the analysis user for the corresponding mark event under the corresponding environment information, and the cloud service platform (10) provides the modification authority of the preference weight index for the user so that the user can modify the preference weight index within a preset modification range;
wherein the cloud service platform (10) is configured to: and providing the modification authority for the user only in a preset time range after the corresponding mark event occurs, and canceling the modification authority after the preset time range is exceeded.
8. The method of one of claims 1 to 7, wherein the environmental information comprises at least one of environmental properties, time information, light information, location conditions, humidity information, ambient temperature information, and sound information.
9. The method of one of the claims 1 to 7, wherein the online activity comprises at least one of an email, web content, instant messaging, browsing history, online games and online transactions; the biometric characteristic includes at least one of voiceprint information, fingerprint information, and iris characteristic information.
10. A voice service system based on environmental information processing, comprising: carrying out voice communication with a user; according to the voice communication, a search request including expected information input by the user is obtained, and a cloud service platform (10) generates a first search result according to the search request of the user;
while obtaining the search request, the cloud service platform (10) obtains first environment information of the user through at least one of a plurality of mobile computing devices (20) carried and/or worn by the user;
meanwhile, the cloud service platform (10) also acquires the biological characteristics of the user through at least one of the plurality of mobile computing devices (20); according to the biological characteristics, pre-stored configuration information of the user corresponding to the biological characteristics is obtained;
the cloud service platform (10) generates a second search result containing the preference of the user in the first environment information and the configuration information based on the first environment information and the configuration information of the user;
the cloud service platform (10) provides the first search result and the second search result to the user together in a voice interaction mode.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111047024.9A CN113761369A (en) | 2018-05-25 | 2018-05-25 | Search system and method based on environmental information processing |
| CN202111046591.2A CN113761368A (en) | 2018-05-25 | 2018-05-25 | Personalized service recommendation system and method based on environmental information |
| CN201810521245.7A CN110598089A (en) | 2018-05-25 | 2018-05-25 | Voice assistant method and system based on environmental information processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810521245.7A CN110598089A (en) | 2018-05-25 | 2018-05-25 | Voice assistant method and system based on environmental information processing |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111046591.2A Division CN113761368A (en) | 2018-05-25 | 2018-05-25 | Personalized service recommendation system and method based on environmental information |
| CN202111047024.9A Division CN113761369A (en) | 2018-05-25 | 2018-05-25 | Search system and method based on environmental information processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110598089A true CN110598089A (en) | 2019-12-20 |
Family
ID=68848756
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111046591.2A Withdrawn CN113761368A (en) | 2018-05-25 | 2018-05-25 | Personalized service recommendation system and method based on environmental information |
| CN201810521245.7A Withdrawn CN110598089A (en) | 2018-05-25 | 2018-05-25 | Voice assistant method and system based on environmental information processing |
| CN202111047024.9A Withdrawn CN113761369A (en) | 2018-05-25 | 2018-05-25 | Search system and method based on environmental information processing |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111046591.2A Withdrawn CN113761368A (en) | 2018-05-25 | 2018-05-25 | Personalized service recommendation system and method based on environmental information |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111047024.9A Withdrawn CN113761369A (en) | 2018-05-25 | 2018-05-25 | Search system and method based on environmental information processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN113761368A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115827840A (en) * | 2022-11-28 | 2023-03-21 | 同舟智慧(威海)科技发展有限公司 | Artificial intelligence reply method based on particle swarm algorithm under semi-supervised clustering target |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561284A (en) * | 2008-04-17 | 2009-10-21 | 北京灵图软件技术有限公司 | Method, device and system for editing navigation track |
| CN103699643A (en) * | 2013-12-25 | 2014-04-02 | 三星电子（中国）研发中心 | Transaction recording implementation method and device in mobile terminal |
| CN104239465A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Scene information-based searching method and device |
| CN105302898A (en) * | 2015-10-23 | 2016-02-03 | 天津车之家科技有限公司 | Click model-based searching and ranking method and device |
| CN107204194A (en) * | 2017-05-27 | 2017-09-26 | 冯小平 | Determine user's local environment and infer the method and apparatus of user view |
-
2018
- 2018-05-25 CN CN202111046591.2A patent/CN113761368A/en not_active Withdrawn
- 2018-05-25 CN CN201810521245.7A patent/CN110598089A/en not_active Withdrawn
- 2018-05-25 CN CN202111047024.9A patent/CN113761369A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101561284A (en) * | 2008-04-17 | 2009-10-21 | 北京灵图软件技术有限公司 | Method, device and system for editing navigation track |
| CN103699643A (en) * | 2013-12-25 | 2014-04-02 | 三星电子（中国）研发中心 | Transaction recording implementation method and device in mobile terminal |
| CN104239465A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术（北京）有限公司 | Scene information-based searching method and device |
| CN105302898A (en) * | 2015-10-23 | 2016-02-03 | 天津车之家科技有限公司 | Click model-based searching and ranking method and device |
| CN107204194A (en) * | 2017-05-27 | 2017-09-26 | 冯小平 | Determine user's local environment and infer the method and apparatus of user view |
Non-Patent Citations (1)
| Title |
|---|
| AI科技评论: "《https://cloud.tencent.com/developer/article/1059211》", 13 March 2018 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115827840A (en) * | 2022-11-28 | 2023-03-21 | 同舟智慧(威海)科技发展有限公司 | Artificial intelligence reply method based on particle swarm algorithm under semi-supervised clustering target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761368A (en) | 2021-12-07 |
| CN113761369A (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10785203B2 (en) | Methods, systems, and media for presenting information related to an event based on metadata | |
| US10819811B2 (en) | Accumulation of real-time crowd sourced data for inferring metadata about entities | |
| US11590981B2 (en) | Shared mobility service passenger matching based on passenger attributes | |
| US10572476B2 (en) | Refining a search based on schedule items | |
| US9626695B2 (en) | Automatically presenting different user experiences, such as customized voices in automated communication systems | |
| JP4037081B2 (en) | Information selection apparatus and method, information selection reproduction apparatus, and computer program for information selection | |
| KR20180015586A (en) | Method for recommending music for various situations and apparatus using the same | |
| US20160171109A1 (en) | Web content filtering | |
| CN102782733A (en) | Methods and arrangements employing sensor-equipped smart phones | |
| KR20020093852A (en) | System and method for voice access to internet-based information | |
| CN110164415A (en) | A kind of recommended method based on speech recognition, device and medium | |
| CN110020148A (en) | A kind of information recommendation method, device and the device for information recommendation | |
| CN109151548A (en) | Interface alternation method and device | |
| CN110222256A (en) | A kind of information recommendation method, device and the device for information recommendation | |
| CN110530383A (en) | A kind of running route recommendation method and system based on GPS navigation | |
| CN105159990B (en) | A kind of method and apparatus of media data grading control | |
| CN110110204A (en) | A kind of information recommendation method, device and the device for information recommendation | |
| CN110598089A (en) | Voice assistant method and system based on environmental information processing | |
| US20220351730A1 (en) | Method and system providing service based on user voice | |
| CN110162710A (en) | Information recommendation method and device under input scene | |
| US20220293096A1 (en) | User-oriented actions based on audio conversation | |
| CN115866339A (en) | Television program recommendation method and device, intelligent device and readable storage medium | |
| CN113536028A (en) | Music recommendation method and device | |
| CN110598088A (en) | Searching method and system based on environmental information | |
| CN108829760A (en) | A kind of searching method and system based on environmental information |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191220 |