33results about How to "With artificial intelligence" patented technology

The invention relates to high optical spectral image technique without harm to agricultural products. It can reflect the appearance of the agriculture products like color, shape, texture, dimension, scar and son on, and internal features like hardness, protein content and connected with knowledge base and experience of experts to make judgment. It can make quick, accurate, timely judgment of products, controlling the overall production with guarantee of the agriculture quality.

Images of farm animal products taken by CCD camera through image acquisition card are transferred to computer. Under certain condition (temperature, humidity and flow rate), smells emitted from farm animal products through mini pump with no oil are sucked into reaction chamber, where signals are generated by array of gas sensor. The said signals through conditioning circuit, A / D acquisition card are transferred to computer. Computer for simulating human brain to treat vision data and smell data carries out syncretizing and pattern recognition processing. Combining with experts' knowledge in knowledge base as well as experiences, computer makes judgment for qualities of garden spgarden stuff, meat and corns etc. synthetically.

The embodiment of the invention discloses an NPC (Non-Player Character) behavior decision method. The method comprises the following steps of initializing attribute set information of an NPC; obtaining a triggering event of the NPC through a sensor; determining a willing target of the NPC according to the corresponding relationship between the triggering event and the willing target; finding the attribute set information matched with the willing target; generating at least willing target option according to the matched attribute set information; determining a behavior plan according to the willing target option and the willing target option weight; executing the behavior plan; and correcting the willing target of the NPC according to the feedback of the behavior plan. The NPC in the game can realize the artificial intelligence; and the thinking mode and the behavior action similar to the human are realized. The novelty and the interestingness of the game are enhanced, so that a game player can gain good game experience, and the game dependency of the player is enhanced.

The invention relates to a CTC station autonomous controlling machine with a self-learning system. The station autonomous controlling machine comprises a central communication module, an operation processing module, a schedule receiving and storing module, a round-robin scheduling module, a code bit processing and bus number tracking module, an automatic routing decision module, an interlocked logic check output module and an acquisition / output module, wherein the central communication module is connected with the operation processing module and the schedule receiving and storing module respectively; the operation processing module, the round-robin scheduling module and the code bit processing and bus number tracking module are all connected with the automatic routing decision module; the automatic routing decision module is connected with the interlocked logic check output module, and the interlocked logic check output module is connected with the acquisition / output module; and the acquisition / output module is connected with the code bit processing and bus number tracking module. The CTC station autonomous controlling machine with the self-learning system has improved automation, certain artificial intelligence, and improved accuracy and efficiency during use at a station of a busy mainline.

The invention discloses an image content retrieval system which is characterized by comprising 1) a segmentation subsystem, 2) an image area characteristic extraction unit and 3) a calculation and comparison subsystem, wherein the segmentation subsystem is used for respectively segmenting the training image and testing image into n examples and comprises A) an FCM segmentation unit and B) a pyramid segmentation unit, wherein the FCM segmentation unit is used for respectively performing area segmentation on the training image and the testing image by employing a fuzzy C-means and the pyramid segmentation unit is used for performing image segmentation on the training image and the testing image on the basis of a space pyramid matching mechanism by employing a cvPrySegmentation function; the image area characteristic extraction unit is used for extracting the color, texture, CENTRIST characteristics and each type of mean characteristic vectors of each example; and the calculation and comparison subsystem adopts a multi-example learning and diverse density sparse learning method, describes the image contents from the multiple nonlocal form characteristic angles and fulfills the retrieval aim. The method is easily realized through programming, has a certain artificial intelligence and provides algorithmic reference for the image understanding.

The invention relates to a sensory evaluation method for predicting fermented yogurt based on a BP neural network, having the following benefits: adopting a computer system with objective mechanical measurement as input and subjective sensory evaluation as output and realizing prediction via the accurate value measured by the instrument, thus not only reducing human input and lowering the evaluation cost, but also rapidly and accurately determining sensory evaluation result of fermented yogurt in real time. The method realizes that physicochemical index measurement replaces sensory evaluation detection and follows the development direction of the food industry. The method of the invention is simple and convenient, low in realization cost, easy for operation and result analysis, suitable for predicting preference sensory evaluation of various food after adaptability modification and wide in application field.

The present invention relates to a method for forecasting organoleptic investigation of quality and structure of smoked-and-cooked sausage based on BP NN, which employs computer system making the objective mechanical measurement as input, subjective organoleptic investigation as output to forecast by nicety value detected by apparatus, which not only liberates labour force, eliminates disturb of subjective factors of human, but also determines rapidly and exactly the quality and structure index of smoked-and-cooked sausage in real time to realize the mechanical measurement replacing of organoleptic investigation measurement entirely or partially, and follows the development directions of food industry.

The invention relates to an intelligent chatting robot control method and control device. The control method includes the following steps: acquiring a user input statement of a first user, and matching the user input statement with statements in a chatting database to acquire a first chatting statement having a maximum matching degree greater than a preset value in the chatting database; using the next chatting statement as a robot output statement to be fed back to the first user if the next chatting statement exists in the first chatting statement; using the user input statement of the first user as a new topic robot output statement to be sent to N second users if the next chatting statement does not exist in the first chatting statement, receiving reply statements returned by the N second users, and using the reply statements as robot output statements of the first user to be fed back to the first user. The invention also provides a corresponding intelligent chatting robot control device. The method and the device can allow a chatting robot to possess artificial intelligences, and can improve the Turing test passing rate.

The invention discloses a current-based intelligent compensation control method used on polishing and grinding equipment. The method comprises the following steps: pre-setting the range of the working current value to be from A to B, wherein A is the minimum and B is the maximum; detecting the actual working current value C in real time; and comparing the actual working current value with the pre-set working current value: if the actual working current value is within the pre-set range of working current value from A to B, dispensing with compensation, if the actual working current value is less than the minimum A, increasing the actual working current value C by controlling a grinding head of the polishing and grinding equipment to feed, when the increased actual working current value C is within the pre-set range of working current value from A to B, dispensing with compensation, and if the actual working current value is more than the maximum current value B, decreasing the actual working current value C by controlling the grinding head of the polishing and grinding equipment to withdraw, and when the decreased actual working current value C is within the pre-set range of working current value from A to B, dispensing with compensation. The method disclosed by the invention has the characteristic of artificial intelligence and has good automatic compensation effect.

The invention discloses a method of utilizing shapes, sizes and lines to sort dried fruits. The method comprises the following steps: manually feeding materials and discharging materials and scattering areca catechus into single bodies by a driving type rotary material discharging device after the materials are fed; detecting the areca catechu in a rotating mode; imaging and collecting, wherein anindustrial camera in an imaging detection box shoots image information of 24 areca catechus for 8 times and sends the image information to an image processing system; recognizing shapes, sizes and lines of the areca catechus through the image processing system, comparing with models, utilizing a classifying mechanism to remove the areca catechus meeting the model characteristics, conveying the areca catechus not meeting the model characteristics to the next grade and repeating the step D; utilizing a PLC to control the classifying mechanism to discharge different grades of areca catechus outof set channel opening. According to the method disclosed by the invention, driving type rotary material discharging and rotary material overflowing are utilized, the areca catechus or red dates are rotated at 360 degrees by a driving type rotary cup, and the areca catechus or the red dates are nondestructively classified according to the shapes, the sizes and the lines; the classifying device canremove the areca catechus or the red dates at a high speed, and outlet grades can be set at will.

The invention relates to a controlling device for dyestripping and doffing materials automatically and heterogeneity mixing, which comprises the mechanical structure system and the controlling system, wherein the mechanical structure system primarily comprises a bay, an automatic positioning dyestripping and outing-film apparatus, an mechanical arm for self-feeding and mixing, a rotating and supporting mechanism for vessel location, a renovating mechanism and a fixed connecting beam; the controlling system primarily comprises a multi-axis motion controlling card, a interface board, a controlling motor, a electromotor drive, a continuous current dynamo, a sensor, a relay and a computer. Said invention can stimulate several different complicated movements.

The invention discloses an automatic balancing device for an easy open lid production line. A manipulator module is arranged above the center of a module, and a left storage stacking module and a right storage stacking module are arranged on the left and on the right of the manipulator module respectively. A lid inlet conveying module is arranged in front of the module, the front end is connectedinto a lid inlet pipe cage of a front working procedure, and the rear section is located on the right side below the manipulator module. A lid outlet conveying module is arranged behind the module, the front section is located on the left side below the manipulator module, and the rear section is connected with a rear process glue-injection machine lid inlet pipe cage. A tray conveying module is arranged on the lowest layer of the manipulator module, a conveying chain of the tray conveying module penetrates the lower side of the left storage stacking module and the lower side of the right storage stacking module and passes through the lower side of the rear section of the lid inlet conveying module and the lower side of the rear section of the lid outlet conveying module. A temporary storage tank is installed beside the right side of the front section of the lid outlet conveying module and between the rear section of the lid inlet conveying module and the front section of the lid outlet conveying module, and the tray conveying module is exposed out of the area where a lid is stored or gripped from a tray by the manipulator module. The automatic balancing device promotes productionefficiency maximization and saves manpower expenditures.

The invention provides a cloud platform communication system. A bidirectional publishing / subscribing mode and a cluster consistency management method are provided to ensure real-time message communication between leaders of the cloud platform software robots and people. and consistency of intra-cluster messages. According to the cloud platform resource scheduling actual situation of a data center,an election method is provided so that cloud platform resource scheduling management intelligence is improved. A resource scheduling management method is provided, the automatic operation and maintenance capacity of the system is improved by achieving a cloud platform resource scheduling system of the robot technology, and the workload of maintenance personnel is reduced.

The invention discloses a finger guessing game robot system. The finger guessing game robot system is used for interactively playing a finger guessing game with people. The finger guessing game robot system mainly comprises a finger guessing determining unit, a robot body, a computer master control unit and a confront number output unit. The finger guessing determining unit determines correspondingly finger throwing output information according to finger throwing input information generated by a people finger guessing movement and / or voice, wherein the finger throwing output information comprises a confront finger guessing movement and / or a confront number. The robot body is provided with a finger guessing movement displaying part for displaying the confront finger guessing movement. The computer master control unit determines appropriate time for displaying the confront finger guessing movement of the finger guessing movement displaying part of the robot body, and gives out a corresponding instruction to control the finger guessing movement displaying part of the robot body according to the finger throwing output information determined by the finger guessing determining unit, so that the robot body can conduct the confront finger guessing movement within the appropriate time. The confront number output unit outputs at least one confront number in a voice mode according to the finger throwing output information determined by the finger guessing determining unit.

The invention relates to a breaker capable of tracking load change to automatically set a rated value. The breaker comprises an electric tripping mechanism, a reclosing mechanism and an electronic control system, wherein the electronic control system comprises an MCU, a keyboard, a display, a first A / D converter, a second A / D converter, a current sampling sensor, a voltage sampling sensor, a program storage, a strategy controller and a data storage. The breaker has the advantages that the rated value of the breaker is automatically set by the electronic control system, and the rated current Irof the breaker is allowed to constantly track the load change and be timely changed to the optimal value; the safety of load equipment and electric lines is sensitively, safely and reliably protected, and electric fire possibly caused by various causes is avoided.

The invention discloses a method and device for enabling household electrical appliances to express emotions, and an air conditioner. The method comprises the following steps: carrying out the classification of emotions through motions, coding the motions, enabling the motions to be corresponding to the functions of the household electric appliances and / or the behavior information, recognizing user's voice and / or emotions reflected in a text, sequentially querying the corresponding motions, the corresponding codes, the corresponding functions of the household electric appliances and / or the behaviors according to the emotions of a user, generating a control command, executing the control command, and feeding back the emotions expressed by the household electric appliances through the functions of the household electric appliances and / or the behaviors. The device comprises a classification module, a coding module, a corresponding module, a recognition module, and a transmitting module. The air conditioner comprises the above device. The device has a function of capturing the human natural language, overturns the conventional functions of household electric appliances, enables the household electric appliances to have artificial intelligence, and achieves the purposes of converting the human natural language into an air conditioner control command and enabling the household electric appliances to feed back the emotions according to the human natural language.

The invention relates to a stage performance virtual entertainment training system. The system comprises a server, a screen end, a wearing end, an audio input end and a floor end, and the screen end,the wearing end, the audio input end and the floor end are in communication connection with the server. The server comprises a screen background template library, a human body model library, a virtualmanagement module, a limb information processing module, a limb information database, a voice processing module, a voice information database, a position information processing module and a positioninformation database. The screen end comprises a digital screen, an audio power amplifier module and a screen communication interface. The invention further discloses a stage performance virtual entertainment training method. The method comprises the steps of performance data uploading, data virtual simulation, virtual simulation output and the like. According to the stage performance virtual entertainment training system and method, an entertainment training scheme for simulating stage performance is provided for a user in a virtual reality mode, and the characteristics of artificial intelligence and virtual reality are achieved.

The invention discloses an intelligent identity information identification method based on an RFID technique. The method is characterized by comprising the following steps of creating multiple subsystems, wherein each subsystem includes an RFID reader, a super terminal, an MCU module, a distributed database chip and an image collecting module; connecting the subsystems with a host system through interchangers; carrying out an RFID label reading operation through the RFID readers, and reading and sending the RFID label information to the MCU modules; collecting physiological image information of a user in real time through the image collecting modules, and sending the user's physiological image information collected in real time to the MCU modules in a pixel image sequence dataflow mode; parsing personal identity information and personal permission information which are reserved on an RFID label through the MCU modules; searching the distributed database chips through the MCU modules todetermine whether or not information in accordance with the personal identity information reserved on the RFID label is stored; if yes, carrying out permission information analysis. The intelligent identity information identification method can be widely applied to various industrial and mining enterprises, schools, institutions and other fields.

The invention relates to a controlling device for dyestripping and doffing materials automatically and heterogeneity mixing, which comprises the mechanical structure system and the controlling system, wherein the mechanical structure system primarily comprises a bay, an automatic positioning dyestripping and outing-film apparatus, an mechanical arm for self-feeding and mixing, a rotating and supporting mechanism for vessel location, a renovating mechanism and a fixed connecting beam; the controlling system primarily comprises a multi-axis motion controlling card, a interface board, a controlling motor, a electromotor drive, a continuous current dynamo, a sensor, a relay and a computer. Said invention can stimulate several different complicated movements.

The invention discloses a gate control device with artificial intelligence, and relates to the technical field of gate control. The gate control device comprises a collecting unit used for collectinggate information and a gate control unit which is connected with the collecting unit, receives the gate information collected by the collecting unit and is used for controlling actions of a motor of agate; the gate information at least comprises water level in front of the gate, water level behind the gate, gate action rate, gate position and motor operating power used for driving the gate; and agate opening instruction or a gate closing instruction sent to the motor by the gate control unit is required to meet preset conditions. According to the gate control device with artificial intelligence, the operating condition of the gate can be automatically monitored, the gate information at the gate is collected by the collecting unit in real time, then the real-time gate information is processed, that is, the real-time gate information is subjected to fitting processing with historical operating information, a safe operating boundary is acquired, boundary judgment is performed in an operating process in real time, the gate is ensured to operate in a safe area, the gate can be automatically operated, and unmanned operation is realized.

The invention discloses a special hotel member system based on enterprise WeChat. The system comprises a cloud server, a member marketing unit, a positioning module, a member communication unit, a timing pushing module, an enterprise WeChat number, an artificial intelligence module, an authority module, an information sorting and gathering module, a link module, a key information extraction unit, a member registration module, a database, a data analysis module, an account password module, an emergency contact module, a customer service personal WeChat and tabulation module. The beneficial effects of the application are that real-time contact with the customer can be carried out based on the enterprise WeChat, the enterprise WeChat is utilized to reach the hotel check-in customer, and in combination with the member label data and the member check-in condition, the hotel merchant can provide personalized services for the customer and carry out precise marketing in the chatting process with the customer, so that the hotel operation efficiency and the user check-in experience are improved.

The invention discloses a biological culture system with artificial intelligence. The biological culture system comprises a plurality of biological culture units applied to biological culture and a server used for carrying out data interaction with the biological culture units, wherein the server comprises an AI module used for learning according to data transmitted to the server by the biologicalculture units and controlling the biological culture units according to learning results. The biological culture system with artificial intelligence is capable of autonomously learning through big data.