71results about How to "Realize intelligent interaction" patented technology

The invention discloses an interactive intelligent inputting method based on video images. The interactive intelligent method based on the video images is capable of enabling a user to achieve non-contact type operations. Through collecting information like motion paths, speed and acceleration of two hands of the user, the input function of an entity keyboard is achieved, and the collected information is outputted in the mode of characters for upper layer software to invoke and achieve customized application. The non-contact type intelligent inputting method based on the video images is capable of further achieving dynamic adjustment of the operation range of the virtualized keyboard according to the change of the motion range of the two hands of the user. When the two hands of the user are arranged in the working area of an image collection device, a displaying device displays the relative positions of the virtualized keyboard and virtualized fingers of the user, the user can achieve the corresponding operations of the buttons of the virtualized keyboard through the pressing actions of the fingers. In view of being compatible with habits of pressing the keyboard of all kinds of users, the device using the interactive intelligent method based on the video images provides a supervising function of the inputting of the virtualized keyboard, and corrects differences of accuracy brought by all kinds of actions which are not the keyboard inputting action. The non-contact type intelligent inputting method based on the video images is characterized in that a user does not need any auxiliary positioning areas and auxiliary positioning objects for inputting, and the inputting action can be achieved at any position inside the working area of the image collection device. The interactive intelligent method based on the video images is low in cost, wide in applicability, and intelligently interactive. The invention further provides the realizing device based on the interactive intelligent method based on the video images.

The invention relates to a customer service system in the electric power field, especially a power customer interdynamic service system based on an instant messaging (IM) tool. The system comprises an integrated fee-paying access management platform, a marketing business application module, a short message platform, a third party payment platform, a rechargeable card system and a remote monitoring management platform, and is characterized by also comprising a WeChat client, a power WeChat application and a WeChat service platform; the WeChat client is a WeChat client application issued by Tencent company; the WeChat service platform is an customized electric power WeChat service platform based on a WeChat public platform; the power WeChat application is power public number service; the WeChat service platform and the integrated fee-paying access management platform are integrated; the power WeChat application accesses to the integrated fee-paying access management platform through the WeChat service platform, interacts with a marketing business application and a short message platform system, and is integrated with the third party payment platform to realize user fee-paying and power purchase payment.

The invention discloses an intelligent interactive aquarium display system. The intelligent interactive aquarium display system comprises an aquarium, a touch interactive screen, an image collecting component and an interactive data processing component. The touch interactive screen is fixed to the outer surface of the aquarium. The touch interactive screen and the image collecting component are connected with the interactive data processing component. The touch interactive screen receives the selection operation on aquarium fishes in the aquarium and generates position information. The image collecting component collects an overall image of the interior of the current aquarium in real time. The interactive data processing component receives the position information and the overall image to recognize the selected target aquarium fishes, and the preset interactive information corresponding to the target aquarium fishes is displayed on the touch interactive screen. The intelligent interactive aquarium display system has the advantages of being simple and compact in structure, capable of achieving intelligent interaction with spectators, good in displaying effect and high in interestingness.

The invention discloses a terminal and an intelligent shooting method thereof. The method comprises: image data in a preview state are obtained; a position of an important feature in the obtained image data in the preview state is compared with a preset region; when the position of the important feature in the obtained image data in the preview state is not in the preset region, the shot person is prompted to adjust the position; and otherwise, shooting is carried out. According to the invention, the image data in the preview state are obtained and the position of the important feature in the obtained image data in the preview state is compared with the preset region; and when the position of the important feature in the obtained image data in the preview state is not in the preset region, the shot person is prompted to adjust the position. Therefore, intelligent interaction between the terminal and the shot person is realized on the auto shooting condition, so that the shooting can realize the satisfying effect.

A broadcasting and reading control method based on intelligent interaction and electronic equipment are disclosed. The method comprises the following steps that the electronic equipment detects a voice control command which is input by a user and is used for making the electronic equipment broadcast new vocabularies through a voice mode; and the electronic equipment is controlled to execute a target operation matching with the voice control command. In the invention, the intelligent interaction between the user and the electronic equipment can be realized, and the user can control the broadcasting and reading state of the electronic equipment so that the flexibility of broadcasting and reading is increased.

The invention discloses a robot and an interactive control method for the robot. The robot comprises a detector, a central control element and a feedback device; the detector is arranged on a machine body of the robot and is used for detecting an interactive operation; the central control element is used for controlling the feedback device to execute a feedback behaviour according to the interactive operation and a detector position corresponding to the interactive operation; the feedback device is used for executing the feedback behaviour. Through the scheme, the robot can realize human-machine intelligent interaction based on an interaction operation behaviour which is triggered on the machine body and an interactive operation position, so that the robot interaction is not limited to voice and the trigger interaction to a display screen; the interaction forms of the robot are expanded.

The invention discloses a digital signage terminal and wechat interaction method, interaction system and servers thereof. The method comprises following steps that: digital signage terminals receive and display two-dimension code pictures and product information sent by a digital signage server; when sensing that users scan the two-dimension code pictures, a wechat server sends the products corresponding to the two-dimension code pictures and the unique identifiers of the digital signage terminals to the digital signage server; the digital signage server pushes data related to the corresponding products to the digital signage terminal; and when detecting that the users purchase the corresponding products, the wechat server sends the purchase records of the corresponding products and the unique identifiers of the digital signage terminals to the digital signage server. According to the method, the system and the servers of the invention, the products and the digital signage terminals are bound; when the users scan the codes, the digital signage server finds the digital signage terminals of which codes are scanned by the users according to the unique identifiers of the digital signage terminals; some information is automatically pushed and displayed at the digital signage terminals; and the intelligent interaction of the digital signage terminals and the wechat is realized.

The invention belongs to the technical field of water production, and provides a method and a system for intelligently interacting and controlling the water making equipment. The method comprises thesteps of collecting water drinking characteristic data and the user biological characteristic information corresponding to the drinking water characteristic data by water making equipment, wherein thedrinking water characteristic data comprise the water drinking time, the water drinking volume, the water drinking frequency, the water drinking temperature, and the water drinking speed; sending thewater drinking characteristic data and the user biological characteristic information to an intelligent control center, and carrying out classification statistics on the drinking water feature data according to the user biological characteristic information by the intelligent control center; sending the classification statistics result to a server, analyzing the classification statistics result by the server to obtain the water drinking rule information, pushing the control information by the customer service at the background according to the water drinking rule information, and realizing the control of the water making process according to the control information. By means of the method and the device, the health data of the scientific and effective water drinking behaviors of differentuser groups can be obtained. Meanwhile, the intelligent interaction of the water making equipment can be controlled.

The invention provides an emotion state adjusting system aiming at online learning, which realizes intelligent interaction between online learners and online learning system. The system comprises an acquisition module, which is used for acquiring physiological signals and facial expression images when the user is on line learning, and uploading the physiological signals and facial expression images to an emotion recognition module, an emotion recognition module which is used for analyzing the received physiological signal and facial expression image of the user and predicting the emotion stateof the user to the learning material, an emotion adjusting module which is used for adjusting the learning material according to the preset emotion adjusting strategy if the user's emotion state is not in the preset optimal learning state. The invention relates to the technical field of intelligent service.

The embodiment of the invention discloses an information interaction method, a device, a computer device and a storage medium. The method comprises the following steps: acquiring a face image of a user when detecting that the user enters a set environment; according to the face image, obtaining the identity characteristic information of the user, wherein, the identity characteristic information comprises age attribute information and/or user identity information; determining auxiliary reference information according to the identity characteristic information and/or the current system time; according to the identity characteristic information and the auxiliary reference information, the interaction information matched with the user is determined, and the interaction information is presentedin at least one media form in the setting environment. The technical proposal provided by the embodiment of the invention realizes the intelligent interaction of the information of the user in the setting environment, does not require the user to carry out additional input operation, improves the initiative of the information interaction, makes the interactive information more intelligent, and improves the user's use experience.

The invention discloses a safety knowledge graph construction method and a system for a smart power plant. The method comprises the following steps: firstly, collecting data and constructing a knowledge model, and classifying, cleaning and storing the data according to the knowledge model; performing knowledge extraction on the unseparated data of the entity, and constructing a knowledge graph by using a knowledge extraction result and the separated data of the entity; and finally, applying the constructed knowledge graph to different scenes. The invention further discloses a system using the method. Compared with the prior art, the knowledge extraction method based on the features can perform entity extraction more accurately, and relationship extraction can be performed more quickly and accurately by encoding entities and sentences and utilizing a CNN method. The knowledge graph constructed by the invention comprehensively considers the current application situation and demand of safety management of the power enterprise, can effectively reduce the safety risk of the production link of the power plant, is convenient for the enterprise to realize intelligent management in power production, and guarantees the production safety of the power plant.

The invention discloses a dialogue processing method, a model training method and related equipment. The dialogue processing method comprises the steps of obtaining at least one piece of user input data; extracting an intention and an entity of the at least one piece of user input data; inputting the intention and the entity into a dialogue processing model for processing to obtain reply data matched with the user input data; and feeding back the reply data to the user. According to the scheme, the accuracy of interaction between the equipment and the user can be improved.

The invention relates to a voice-interaction-based intelligent control method for a transformer substation and a distribution station. Voice control of a transformer substation and a distribution station is realized through a voice interaction system. The method comprises the following steps that: S1, a voice sensor acquires a voice instruction and inputs the voice instruction into the voice interaction system; S2, the voice interaction system judges whether the voice instruction is a valid voice instruction or not, if so, the S3 is executed, and if not, a voice broadcasting device broadcastsand notifies that the voice instruction is an invalid instruction; S3, the voice interaction system judges the voice instruction type and executes the corresponding operation, wherein the voice instruction types include question and answer types, system control types and equipment control types; and S4, the voice broadcasting device broadcasts and notifies an operation result. Compared with the prior art, the voice-interaction-based intelligent control method has the following advantages: the hands of the personnel is liberated, the management automation degree and the interaction timeliness of the transformer substation and distribution station are improved and the like.

The invention relates to a local accent speech recognition system based on an embedded mobile device. The system comprises a model training module, a feature extraction module and a pattern matching module which are integrated on an embedded mobile device. The model training module is used for collecting and training local accent speech to get an entry model of local accent. The feature extraction module is used for extracting the speech features of an input local accent. The pattern matching module is used for carrying out speech matching calculation on the speech features according to the entry model to get a speech recognition result. The local accent speech recognition system based on an embedded mobile device of the invention can improve the recognition rate of dialectal speech, reduce the difficulty of learning and training during speech recognition used by dialect speakers, and reduce the workload of learning and training. Meanwhile, the system introduces the speech recognition technology to a variety of embedded mobile devices, and can realize intelligent interaction.

The invention discloses cloud computing and network convergence of a smart bonsai based on a wireless sensor network. A base, an embedded system and a pot body are included. The bottom of the pot body is equipped with a pressure sensor. Different positions of the left side inner wall are equipped with temperature and humidity sensors. A water storage cabin, a water pump cabin and an embedded system cabin are arranged in the bottom. The left side inner wall of the water storage cabin is equipped with a water level sensor. The water pump cabin is internally equipped with a micro water pump whose left side lower end is connected to a water inlet pipe, and the upper end is connected to a water outlet pipe. The control system cabin is internally equipped with a control system based on a single chip microcomputer. The single chip microcomputer is electrically connected to the micro pump, a WiFi communication module, a power supply module, a control panel, a pressure sensor, the temperature and humidity sensors and the water level sensor. The control panel is equipped with indication lamps, a display screen and an input area. The network fusion of wireless sensors and the automatic management of the smart bonsai are achieved, and a problem that people have not time to look after a bonsai is solved.

The embodiment of the invention provides a business object operation method and device, and electronic equipment. The method comprises the following steps that: obtaining first figure behavior data; generating a first business object control instruction corresponding to the first figure behavior data; sending the first business object control instruction to a second terminal to enable the second terminal to display a business object on the basis of the first business object control instruction; receiving the first business object control instruction sent from the first terminal; generating a second business object control instruction corresponding to second figure behavior data, wherein the second figure behavior data is obtained through the second terminal; and on the basis of the first business object control instruction and the second business object control instruction, displaying the business object. By use of the embodiment of the invention, an interaction way between terminals is enriched, interaction flexibility is improved, and the interaction requirements of a first terminal user and/ or second terminal user can be met.

The invention discloses an entity recognition model generation method and device, electronic equipment and a storage medium, and relates to the technical field of natural language processing, deep learning and voice interaction. According to the specific scheme, the method comprises the following steps: training the entity recognition target model by acquiring second standard data for the target entity category, therefore, the entity identification target model only has the capability of identifying the target entity category, and the entity identification capability of the entity identification target model is minimized, so that other entity identification capabilities can be effectively prevented from being stolen from the entity identification target model, and the security is improved.Because the entity identification target model only has the capability of identifying the target entity category, the complexity is low, and the occupied storage space is small, so the entity identification target model can run locally in the intelligent equipment to provide a dialogue entity identification service. Therefore, resources of the cloud server can be saved, intelligent interaction can still be realized under the condition that the cloud server cannot be requested, and the availability is high.

The invention discloses a classroom live-action reproduction interactive teaching system based on a robot projection function. The classroom live-action reproduction interactive teaching system is composed of a voice control module, an image control module, a remote shooting terminal, a communication module, an interface module, an interaction control module and a main control MCU. The voice control module, image control module, the communication module, the interface module and the interaction control module are connected with the main control MCU respectively and electrically; and the remoteshooting terminal and the main control MCU are in communication connection by the communication module. According to the system disclosed by the invention, the system not only serves as an image acquisition device but also serves as a remote projection device to carry out classroom live-action reproduction device; and the system also has the good interaction performance.

The invention provides a smart home voice control recognition method based on an Ad-Hoc Network, and belongs to the technical field of smart home voice control. The smart home voice control recognition method based on the Ad-Hoc Network comprises the following steps: S1, a voice acquisition part is adopted to acquire a voice signal sent by a user; S2, a control part is adopted to obtain a plurality of voice signals through the Ad-Hoc Network part and obtain keyword information from the voice signal; S3, the control part is adopted to acquire regulation and control equipment information and equipment action information in the keyword information, and acquire first priority information from the regulation and control equipment information and second priority information from the equipment action information; and S4, the control part is adopted to control the regulation and control equipment to execute equipment actions through the Ad-Hoc Network part in sequence from high priority to lowpriority according to the first priority information and the second priority information. According to the invention, intelligent interaction with a voice device is realized, the equipment action ofthe regulation and control equipment is rapidly executed, and the efficiency is high.

The invention discloses an electric vehicle charging pile load interactive control system which comprises an interactive system main station, client interactive terminals and charging pile terminals,and is characterized in that the interactive system main station is in electric signal connection with the charging pile terminals and the client interactive terminals, and the charging pile terminalsare in electric signal connection with a transformer and switches; the transformer is in electric signal connection with the switches, the switches are in electric signal connection with the chargingpiles, and the number of the client turntable terminals and the number of the charging piles are both multiple. From the perspective of an intelligent power grid, the supply and demand relationship can be balanced, and the reliability of the system is improved; from the perspective of users, economic returns and benefits can be obtained by adjusting or changing the modes of using and purchasing electric power; from the perspective of the environment, energy conservation and emission reduction are facilitated, and increasingly serious energy crisis is relieved.

The invention relates to the technical field of artificial intelligence customer service and intelligent voice analysis, and particularly discloses a text customer service interaction method for the power industry based on NLP, and the method specifically comprises the following steps: step 1, preprocessing voice data; step 2, performing voice recognition, and naturally generating a question-answering system; step 3, generating a semantic database; step 4, semantic matching; step 5, generating characters by a natural language processing method; step 6, outputting the characters .Intelligent voice text interaction is adopted, so that the communication efficiency and experience of customers can be improved, the labor cost is reduced, and high research value is achieved.

The invention discloses an exchange interaction method, which comprises the following steps: when a wake-up instruction is detected, a connection channel of a first robot corresponding to the wake-upinstruction is activated, and whether there is a connection request triggered based on the connection channel is detected; if there is a connection request, a connection between a terminal corresponding to the connection request and the first robot is established, and a corresponding access interface is displayed on a display interface of the terminal to facilitate interaction between the terminaland the first robot on the basis of the access interface. The invention also discloses an exchange interaction device, equipment and a computer readable storage medium. The connection channel is activated through the wake-up instruction, and the interaction connection between the terminal and the robot is established on the basis of the connection channel. Then, human-computer interaction is achieved through the terminal for users. The interaction process is performed on the access interface, thereby effectively improving the anti-interference ability and realizing intelligent interaction.

The invention discloses an interaction mode determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the first behavior data of a target object if the target object is located in a data collection region, determining interaction feature data of the target object according to the first behavior data, and determining a target interaction mode corresponding to the target object according to the interaction feature data. According to the technical scheme, the technical effects of enriching the information interaction modes, improvingthe information interaction efficiency and improving the information interaction experience of the target object are achieved.