50results about How to "Accurate and efficient identification" patented technology

The invention discloses an intelligent restaurant ordering management system based on a human face recognition technology. The intelligent restaurant ordering management system comprises intelligent devices such as a database module, a data processing module, a wireless communication module, an intelligent ordering table in which a touch screen is embedded, a tableware device in which various sensors are embedded, and a cellphone; the intelligent restaurant ordering management system is characterized in that the human face recognition technology, automatic closed-loop feedback control theory and data digging are combined with the intelligent restaurant ordering management system, and the surrounding temperature and humidity of a member are regulated by use of the automatic closed-loop feedback control theory; the identity of the member is identified by use of the human face recognition technology and the basic information of the member is stored; the data digging technology is used for analyzing the data in database and helping the member order food; as a result, a food material buyer can supplement food materials reasonably, and highly targeted service information can be pushed.

The invention relates to a data recommendation method based on face recognition, a device, a server end and a client end. Acquiring a stored face feature vector corresponding to the user identification according to the user identification; A human face feature vector is extracted from a human face image, whether the extracted human face feature vector matches the stored human face feature vector is judged, and if the extracted human face feature vector matches, recommendation data corresponding to the stored human face feature vector is obtained, and the recommendation data is sent to a smallprogram for display. By using face recognition as the basis of data recommendation, Convenient to use, effectively prevent information leakage problem, can better portray the user portrait, through the combination of small procedures for data recommendation, without installation and uninstallation application, can achieve rapid data analysis and processing, reduce the occupation of resources, reduce the development cost and development threshold, can be widely used in life service scenarios.

The invention discloses an insurance policy analysis method and device, terminal equipment and a storage medium. The method comprises steps that the insurance policy information of each insurance policy is acquired from an insurance policy database; to-be-matched parameters are determined according to the attribute information; for each to-be-matched parameter, traversal of each insurance policy is carried out, and the direct relationship based on the to-be-matched parameters is established between different insurance policies having the same parameter values; the insurance policy identifier information is taken as network nodes, parameter values of the to-be-matched parameters are taken as relationship nodes, the network nodes having the direct relationship are associated with the relationship nodes establishing the direct relationship to construct the insurance policy relationship network; according to the insurance policy relationship network, the gang fraud risk is analyzed. The method is advantaged in that relevance among the different insurance policies is represented through the constructed insurance policy relationship network, identification and early warning of the gang fraud risk can be accurately and efficiently carried out through analyzing the relevance, and the gang fraud risk identification rate is improved.

The invention provides a group of microsatellite markers for identifying parent-child relationships of Chinese Simmental cattle. The group of microsatellite markers includes ten microsatellite markers. The microsatellite markers have the advantages that the markers are high in polymorphism and are not linked with one another, fragments are appropriate in size and interval, and simultaneous detection can be facilitated; combined exclusion probabilities CPE (1), CPE (2) and CPE (3) can respectively reach 0.9960969, 0.999854 and 0.9999997 when the parent-child relationships of the Chinese Simmental cattle are identified by the aid of marker combinations under three different conditions, and accordingly the microsatellite markers are extremely high in detection efficiency; the microsatellite marker combinations can be used for completely and accurately identifying family trees of the Chinese Simmental cattle, accordingly, the Chinese Simmental cattle breeding accuracy can be improved, breeding procedures can be accelerated, and the microsatellite markers have excellent application prospects and economic benefits.

The invention discloses a training and recognition method and device for a visible light fault model of a photovoltaic module. The method comprises the steps of in response to an obtained to-be-detected image, cutting the to-be-detected image; marking pixel coordinates of each piece of image data in the to-be-detected image; in response to the acquired multiple pieces of image data, outputting target object image data in the multiple pieces of image data by a Faster-RCNN training model; judging whether the pixel coordinates of the image data of a certain obstacle are within the range of the pixel coordinates of all photovoltaic module image data or not; and if the pixel coordinates of the image data of a certain obstacle are within the range of the pixel coordinates of all photovoltaic module image data , outputting the pixel coordinates of the image data of the obstacle. By extracting the image features of the photovoltaic module and the bird droppings, the coordinate range of the photovoltaic module and the coordinates of the bird droppings in the detected image are identified, and the overlapped part of the coordinate range and the coordinates of the bird droppings is marked asthe bird droppings covering fault point of the photovoltaic module, so that the identification of the bird droppings shielding fault point of the photovoltaic module is realized.

The invention discloses a method for displaying the driving state of a vehicle, a mobile terminal for displaying the driving state of the vehicle, electronic equipment and a computer storage medium. Only a built-in sensor of the mobile terminal can be used as a signal source without depending on vehicle-mounted equipment, so that the problem of high cost of combined inertial navigation equipment is solved. Meanwhile, through multi-sensor fusion and coordinate system calculation, various driving states of the vehicle can be accurately and efficiently recognized and displayed under the conditionof not depending on the strict fixed position of the mobile terminal. In addition, by displaying the animation of the driving state of the vehicle on the mobile terminal, information related to vehicle driving is provided for a driver more visually.

Belonging to the field of animal molecular genetics, the invention provides an identification method for low-fat broiler chickens by TCF21 gene mRNA expression. Directed at the problem of low-fat broiler chicken identification, the invention provides the identification method for low-fat broiler chickens by TCF21 gene mRNA expression. The method includes the steps of: designing and synthesizing aprimer pair for amplifying the CDS region of TCF21 gene and a primer pair for amplifying the CDS region of TBP gene; extracting the total RNA of abdominal adipose tissues of a to-be-detected broiler chicken and conducting reverse transcription to obtain cDNA; conducting fluorescent quantitative PCR on the abdominal adipose tissue cDNA of the to-be-detected broiler chicken; and when the relative expression of TCF21 gene mRNA in the abdominal adipose tissues of the to-be-detected broiler chicken is smaller than 0.125, identifying the to-be-detected broiler chicken as low-fat broiler chicken, with the relative expression being calculated with TBP gene as the internal reference. The method provided by the invention can be used for low-fat broiler chicken identification.

The invention relates to a quadrotor unmanned aerial vehicle parameter distinguishing method based on an improved shuffled frog leaping algorithm. The shuffled frog leaping algorithm is taken as a basis, a frog leaping rule in the algorithm is improved, the global convergence rate of the shuffled frog leaping algorithm is improved, a fitness function is designed according to quadrotor unmanned aerial vehicle parameters, the computation complexity of the algorithm is reduced, and quadrotor unmanned aerial vehicle parameter distinguishing efficiency is improved. The method exhibits certain universality, and parameter distinguishing for the majority of nonlinear systems with a high coupling degree can be realized.

The invention relates to the technical field of gene engineering, and provides primers for identifying a soybean male sterile line and a method thereof. The primers are disclosed as SEQ ID NO.1 and SEQ ID NO.2. The method comprises the following steps: carrying out PCR (polymerase chain reaction) amplification and BstXI enzyme digestion on the template soybean genome DNA by using the primers; and judging the soybean is the male sterile line if the product only contains one 472bp strip, and judging the soybean is the male fertile line if the product comprises 266bp and 202bp. On the basis of detecting that the soybean male-sterile character is controlled by a pair of recessive single genes, the invention develops a codominant molecular marker for identifying the soybean male sterile line, and provides the primers for identifying the soybean male sterile line and the method thereof. The primers and method can perform efficient accurate identification on the soybean fertility and genotype in any period in the soybean breeding process, thereby providing a new way for molecular identification of the soybean male sterile line.

Embodiments of the invention provide a traffic attack protection method and device, a protection server and a storage medium. The method comprises the following steps of acquiring a message to be sentto a target server under a condition that a traffic attack possibility exists in the target server; at least extracting a load of a message whose source port is not a preset source port from the message to be sent to the target server in order to obtain the load of a message to be matched; matching the load of the message to be matched with fingerprint features of a pre-defined attack message, and determining the attack message from the message to be matched, wherein the determined load of the attack message is provided with a character string corresponding to each key field defined by the fingerprint features; and filtering the attack message. According to the embodiments of the invention, the accuracy of traffic attack protection can be improved, a protection effect of the traffic attack is improved, and the normal service provision of the target server is guaranteed.

The invention discloses a method for identifying a target object based on eye movement scanning. The method comprises the following steps of: reestablishing the shape of the target object by using an eye electric signal acquired when a user scans the boundary of the target object by two eyes; and then calculating a length and a width of the target object, and an angle between the target object and the horizontal direction according to the reestablished target object. The information of the identified target object can be used for controlling external equipment such as artificial hands, artificial limbs and the like, so that human and machine interaction can be realized. Compared with the conventional human-machine interaction method based on eye electric direct control, the method has the advantages that: an indirect control strategy is realized, and the precise and efficient control which cannot be realized in the prior art is achieved.

The invention relates to a parallel arm intelligent silkworm cocoon sorting robot and a silkworm cocoon sorting method. The parallel arm intelligent silkworm cocoon sorting robot comprises a main control system, an image collecting device, a silkworm cocoon conveying system and a parallel arm sorting manipulator, and the collecting end of the image collecting device faces silkworm cocoons conveyed by the silkworm cocoon conveying system; and the execution tail end of the parallel arm sorting manipulator is located above the silkworm cocoon conveying system, and the image collecting device and the parallel arm sorting manipulator are both electrically connected with the control system. According to the parallel arm intelligent silkworm cocoon sorting robot, the parallel arm sorting manipulator is adopted, a negative pressure type suction cup is adopted, accurate silkworm cocoon grabbing is achieved, and secondary damage to silkworm cocoons is avoided; silkworm cocoon images are acquired through an upper camera and a lower camera, so that the recognition accuracy is improved; through a constructed silkworm cocoon classification CNN model based on deep learning, accurate and efficient identification and classification of the silkworm cocoons are realized; and the control system converts the position coordinates of the silkworm cocoons and drives the parallel arm manipulator to act to grab the silkworm cocoons, so that efficient and automatic sorting of the silkworm cocoons is realized.

The invention discloses a primer pair for identifying the low-nornicotine mutant filial generation genotype of tobacco. The primer pair is characterized in that the primer 1 is a sequence as shown inSeq ID No.1, namely 5'GATGAGATGTGTGCATACTTG3', and the primer 2 is a sequence, namely 5'CCAAATTAGAAAAACTCGTACTG3', as shown in Seq ID No.2. The primer pair combined with HRM can be used for screeninga great quantity of filial generation populations, and effectively differentiating non-mutant, mutant hybrid and mutant homozygote, so that materials containing tobacco CYP82E4 mutant genes can be accurately and efficiently identified.

The invention discloses a molecular marking method for predicting and identifying chicken abdominal fat amount and applications, and belongs to the technical field of animal molecular genetics. The molecular marking method for predicting and identifying chicken abdominal fat amount can identify low-fat broilers more accurately and conveniently, and accelerate broiler breeding process. According tothe method, primers are designed according to chicken HBP1 gene SNP site g. -4354T>A upstream 337bp and downstream 27bp sequence; and PCR amplification on chicken genome DNA is carried out accordingto the obtained primers, then forced enzyme digestion on the amplification product by using restriction enzymes is carried out, and polyacrylamide gel electrophoresis separation on enzyme digestion products is carried out to obtain the chicken abdominal fat labeled genotypes. The method is simple to operate, low in cost and high in accuracy, can be used for automatic detection, is an effective molecular marker breeding means, can provide a scientific basis for marker-assisted selection of chickens, and can be used for accelerating the breeding process of the chickens and breeding low-fat broilers meeting market requirements, so that relatively good economic benefits are obtained.

A method for the rapid artificial inoculation in-vitro identification of Batryris elliptica Cocke resistance comprises the following steps: culturing Batryris elliptica Cocke in a culturing container by using a potato and oat starch culturing medium, disinfecting by using an autoclave, and standing for cooling to prepare a culturing medium; acquisition of lily to be measured: taking healthy initial-squaring-stage young lily plants which are not infected with Batryris elliptica Cocke pathogens and must have 6-9 healthy blades, and respectively taking complete lily blades from an upper position, a middle position and a lower position; pathogen acquisition: taking typical infected lily blades, separating and purifying pathogens, identifying the pathogens as Batryris elliptica Cocke, culuring the pathogens on the potato and oat starch culturing medium for 7d, and inoculating the healthy lily blades; inoculating by adopting a mycelium block inoculation process, a spore spray inoculation process or a mechanical inoculation process; wrapping petiole wounds of the pathogen inoculated lily blades with wet cotton, putting the inoculated lily blades in a culture dish, and sprinkling a proper amount of sterile water to carry out moisture retention culture; and investigating the disease infection conditions of the blades at the 3th day, the 5th day, the 7th and the 9th day, observing, and identifying. The Batryris elliptica Cocke resistance of different varieties of lily can be accurately and efficiently identified under controllable conditions through the method.

The invention relates to a qualitative detection method for species germplasm identification by a molecular biological technology, in particular to a specific marker for male and female genetic sex of oplegnathus punctatus, an identification method and a kit. The nucleotide sequences of the specific markers for the chromosomes of the female fish and the male fish of the oplegnathus punctatus are bases shown as SEQ ID NO: 1 (Xfm ID Nm: 1) and SEQ ID NO: 2 (Ym ID Nm: 1). According to the method, a pair of primers is utilized to amplify two DNA fragments of 635bp and 925bp with the difference of 290bp in a genetic male individual, only a single DNA fragment of 635bp is amplified in a genetic female individual, and agarose gel electrophoresis distinguishing can be carried out, so that the time for accurately identifying the genetic sex of the oplegnathus punctatus is shortened, and the sex detection efficiency is improved. The method has important significance and application value in sex identification, high-male offspring seed preparation and family breeding of oplegnathus punctatus.

The invention discloses a visible light stripe code modulation and identification method based on an RGB LED lamp. The method comprises the steps that at a transmitting end, three pulse signals with different phase differences, duty ratios and frequencies are input through PWM modulation, red, green and blue lamp beads of RGB LEDs are controlled to emit light with different flicker frequencies andbrightness respectively, and the different RGB LEDs are endowed with unique IDs; at a receiving end, a CMOS camera is used for shooting an RGB LED image, and the area, the stripe number and the bright and dark stripe duty ratio characteristics of the RGB LED image are extracted through image processing; a classifier is established by utilizing machine learning according to the extracted RGB LED features; and features of the RGB LED image to be judged are extracted, and the classifier is utilized to judge the category to which the RGB LED image belongs so as to realize detection and identification of the light stripes. The method is simple and feasible, can be realized by combining an existing lamp with a smart phone, and has wide market value.

The invention relates to the field of molecular biological detection, in particular to the field of human intestinal bacteria detection. The invention provides a composition for detecting seven intestinal bacteria, including Bifidobacterium (BIF), Streptococcus (STR), Bacteroides (BAC), Lactobacillus (LAC), Clostridium leptum (CLEP), Faecalibacterium (FAE) and Eubacterium rectale (ER), and also provides application of the composition in detecting human intestinal bacteria, a kit comprising the composition and a method for detecting human intestinal bacteria.

A method of quickly identifying whether living citrus are self-compatible comprises the steps of 1, collecting citrus pollen; 2, preparing a citrus pollen germination medium, scattering pollen to themedium, and observing with a microscope whether activity of the pollen is normal; 3, dipping the pollen with normal activity, applying the pollen to stigmas, and covering each flower with a pollination bag; 4, over a certain period of time which is determined according to a citrus species, immobilizing the stigmas in an immobilizing liquid, washing with an ethanol solution, heating by a water bathafter washing to perform softening for a period of time which is determined according to the citrus species, washing the softened stigmas with clear water, and staining with a water-soluble aniline blue solution; and 5, observing germination condition of pollen on the stigmas with a microscope after staining so as to determine whether the citrus are self-compatible. A normalized process to identify whether citrus are self-compatible is provided herein; stigma acquisition time and softening time are provided for different citrus species after pollination; whether citrus plants are self-compatible can be identified efficiently and accurately.

The invention discloses a primer, a kit and a method for identifying cobidae fishes. The identification primer comprises a first primer pair and a second primer pair, the upstream and the downstream of the first primer pair respectively have nucleotide sequences shown as SEQ ID NO.1 and SEQ ID NO.2, and the upstream and the downstream of the second primer pair respectively have nucleotide sequences shown as SEQ ID NO.3 and SEQ ID NO.4. The method for identifying the cobidae fishes comprises the following steps of, S1, acquiring DNA of a cobidae fish sample; s2, carrying out PCR amplification on the DNA obtained in the S1 by using the first primer pair to obtain a first PCR amplification product; s3, performing nested PCR amplification by using the second primer pair, and obtaining a second PCR amplification product by using the first PCR amplification product as a template; s4, performing agarose gel electrophoresis and gel cutting purification on the second PCR amplification product obtained in S3 to obtain a purified second PCR amplification product; and S5, sequencing the purified second PCR amplification product, comparing mitochondrial gene sequences of the known species of the cobidae fishes in an NCBI database according to a base sequence of a sequencing result, and determining the species of the cobidae fish sample.

The invention discloses a method and device for automatically detecting an illegal data modification behavior. The method comprises the steps of extracting database operation information from a business system database and generating a detection database; carrying out illegal modification behavior detection on to-be-detected data in the detection database according to a preset detection rule; and marking the data suspected to be illegally modified and further generating information of informing a manager. According to the detection method, the legality of the data modification behavior can be accurately and efficiently identified and pre-warned by combining the detection rule stored in the detection database and data access connection information on the basis of a logic relationship in the business system database.

An automatic identification method for plate edges is characterized by comprising the following steps: firstly, plate characteristic edges are defined; secondly, defining a feature code for the feature edge of the plate; thirdly, characteristic codes are additionally sprayed or attached to the edge of the two-dimensional code while the identity identification code is sprayed or attached to the plate; fourthly, acquiring two-dimensional code information and feature code information of the plates entering the production line by using a camera; fifthly, decoding the two-dimensional code information and the feature code at the same time; obtaining information of a board pair to be machined, determining whether the information of the board pair to be machined is matched with pre-stored information of a system, obtaining whether the information of a machining edge needing to enter machining is consistent with the pre-stored information through feature code decoding, if yes, continuing to enter a next procedure of the board, and if not, automatically performing board replacement or edge adjustment by the system. The method can improve the identification speed and accuracy of the plate edges on the plate production line, improves the production efficiency, and reduces the production cost.

The invention discloses a molecular marking primer and method for identifying Chinese coastal platycephalus indicus species indeterminate (sp) and platycephalus cultellatus. The sequence of the molecular marking primer Fish F1 is 5'-TCAACCAACCACAAAGACATTGGCAC-3', and the sequence of the molecular marking primer Fish R2 is 5'-ACTTCAGGGTGACCGAAGAATCAGAA-3'. The molecular marking method includes: extracting DNA of platycephalus indicus species indeterminate (sp) and platycephalus cultellatus, and taking the DNA of the two fish as templates for PCR amplification, performing purification and sequencing to the amplification results, and comparing the sequencing results. The molecular marking primer is proper in length, is closely complementary to the sequences of the templates, and is beneficialfor an amplification reaction. The molecular marking method is simple, the identification result is stable, and the repeatability is good. The amplification result of Chinese coastal platycephalus indicus species indeterminate (sp) is consistent, so that the primer and method show high consistency.

The invention relates to a method for identifying Camellia Vietnamese (Camellia Vietnamese), Camellia nobilis (C. osmantha), Camellia frutescens (i.e., Camellia oleifera, C. oleifer var.monosperma) and Camellia oleifera (i.e., Camellia oleifera, C. oleifer). The invention relates to a method for identifying Camellia vietnamese, Camellia nobilis, C. oleifer. According to the method, an amplification primer ycf1-5 and a forward sequence (5 '-3') are adopted, wherein the forward sequence is TGACCTCTTAACCAGTTTTTCCA; and the reverse sequence (5 '-3') is TGGATTATCAAGGGCATTCCGT. The detection kit is used for detecting SNP1, SNP2 and InDel 1. An amplification primer is ZDJ-190, and the forward sequence (5 '-3') of the amplification primer is AAAGAGCGTGGAGGTTCGAG; and the reverse sequence (5 '-3') is GACTGGGTGGTCGAGTCATG and is used for detecting the InDel 2 site. After the amplification product is sequenced, the SNP1 and SNP2 in the product sequence of the camellia fragrant flower germplasm material primer ycf1-5 are shown as' T 'basic groups; if the InDel 1 lacks the TCTTT sequence, the camellia meiocarpa is the camellia meiocarpa. The InDel 2 site is Vietnam camellia oleifera if the'AGTAC 'sequence is deleted, and the InDel 2 site is common camellia oleifera if the'AGTAC' sequence is not deleted. Therefore, the Vietnam camellia oleifera resources, the Camellia odorata resources, the Camellia microcarpa resources and the common Camellia oleifera resources can be effectively detected and identified, and a technical support is provided for classification identification and molecular breeding selection of related Camellia oleifera resources.

The invention relates to a parallel signal processing method and system based on video image recognition. The method comprises the following steps: receiving an audio to be played and a video to be played; target feature recognition is carried out on the video to be played, target features are marked, and a marked frame is determined; placing a playing starting point of the to-be-played audio at the mark frame; and when the audio is played, playing the video at the mark frame. According to the embodiment of the invention, target feature recognition is carried out on the to-be-played video, so that the nodes for voice playing can be effectively controlled according to picture recognition in the video during video playing, the determination of the nodes for voice playing is more accurate, synchronization of video playing and voice playing is realized, and the user experience is improved. The situation that the voice is delayed during video playing or the voice does not accord with an actual playing picture is reduced, and the user experience is improved.

The invention discloses a primer and a method for identifying low phytic acid rice mutant zju-lpa2 filial generation genetypes, wherein the primer is a primer ZHJ1, a primer ZHJ2 or a combination of the ZHJ1 with the primer ZHJ2. The method includes: (1) extracting total DNA (deoxyribonucleic acid) of leaves of rice samples at the seedling stage; (2) with the total DNA serving as a template, performing PCR (polymerase chain reaction) amplification by the aid of the primer in patent claim 1, subjecting amplified products to gel electrophoretic separation, and imaging after dyeing; and (3) judging the genetypes of the rice samples according to electrophoresis results. The primer co-separated from low phytic acid rice mutant zju-lpa2 can detect the leaves of the rice samples at the seedling stage, so that selection efficiency of LPA (low phytic acid) rice varieties can be greatly improved, and LPA rice breeding process is accelerated.

The invention relates to the technical field of artificial intelligence, in particular to a juvenile identification method, device and equipment based on user behavior characteristics. The method comprises the steps: obtaining a software use data set of a to-be-identified person; preprocessing the software use data set; inputting the processed software use data set into a preset behavior feature recognition model to obtain a recognition result; and judging whether the person to be identified is a juvenile or not based on the identification result. Compared with biological information identification and other technologies, the technology does not need a to-be-detected person to actively provide biological information such as a human face and audio, but implicitly uses the use data of the to-be-detected person on the product software, obtains the user behavior characteristics through data analysis, and performs accurate and efficient identification and prediction; compared with a mode ofdirectly using the biological information and voice texts, the method greatly reduces the data ethical risk.