CN109493104A - A kind of method and system of Intelligent visiting - Google Patents
A kind of method and system of Intelligent visiting Download PDFInfo
- Publication number
- CN109493104A CN109493104A CN201811063331.4A CN201811063331A CN109493104A CN 109493104 A CN109493104 A CN 109493104A CN 201811063331 A CN201811063331 A CN 201811063331A CN 109493104 A CN109493104 A CN 109493104A
- Authority
- CN
- China
- Prior art keywords
- visit
- intelligent
- subelement
- business rule
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 42
- 239000000284 extract Substances 0.000 claims abstract description 12
- 238000009472 formulation Methods 0.000 claims abstract description 9
- 239000000203 mixture Substances 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 108010001267 Protein Subunits Proteins 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 17
- 238000003860 storage Methods 0.000 description 15
- 238000012549 training Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 229940034610 toothpaste Drugs 0.000 description 8
- 239000000606 toothpaste Substances 0.000 description 8
- 230000009471 action Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000008186 active pharmaceutical agent Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000013361 beverage Nutrition 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a kind of methods of Intelligent visiting, comprising: obtains business personnel and visits image information;Extract the characteristic information of described image;According to the image feature information of the extraction, the characteristic attribute in described image information is identified;Obtain the visit business rule that enterprise formulates in service enabler;According to the visit business rule that the enterprise formulates, judge whether the characteristic attribute of the identification meets the visit business rule of the formulation;The invention also discloses a kind of Intelligent visit systems;The present invention realizes Intelligent visiting, visit is made to operate simpler convenience, improve working efficiency, complete visit business with achieving the effect that fast and flexible by obtaining image and carrying out feature extraction and Attribute Recognition to its image;It is compared by the characteristic attribute to identification with visit business rule, and its result is returned or saved, achieved the effect that statistical data, reduced cost of labor, further improved working efficiency.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of method and system of Intelligent visiting.
Background technique
A kind of important component of shops's visit as profession person's action that disappears fastly, disappearing fastly, industry is generally deposited
It needs to visit a large amount of shops, market and supermarket in, business personnel, at this point, business personnel needs to count company SKU or competing product
SKU but since there are many SKU quantity on the market, is led in the quantity, paving goods situation, visit situation etc. of shops, market and supermarket
It causes the visit place of business personnel very intensive, along with the SKU of different marketing regions concern is different, leads to the visit work of business personnel
It measures very big.
Now in the art, business personnel is in the method that shops, store and supermarket are visited: when visit acquisition, passing through bat
Row picture archiving is shone into, then business personnel manually checks the relevant information of SKU.The shortcomings that this method is trouble complicated for operation,
Cost of labor is increased, working efficiency is low, completes visit vocational work with being unable to fast and flexible.
Summary of the invention
The present invention provides a kind of method and system of Intelligent visiting, to solve trouble complicated for operation, people in practical operation
Work is at high cost, ineffective problem, realizes easy to operate, reduction cost of labor, the quick visit that work efficiency is high.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides a kind of Intelligent visiting methods, comprising:
It obtains business personnel and visits image information;
Extract the characteristic information of described image;
According to the image feature information of the extraction, the characteristic attribute in described image information is identified;
Obtain the visit business rule that enterprise formulates in service enabler;
According to the visit business rule that the enterprise formulates, judge whether the characteristic attribute of the identification meets the formulation
Visit business rule.
Preferably, the acquisition business personnel visits image information, comprising:
Obtain the picture of the input;
Determine the described image information for including in the picture.
Preferably, the characteristic information for extracting described image, comprising:
Image is pre-processed;
Using feature extraction network model, pretreated characteristics of image is extracted.
Preferably, the pretreatment includes equalization, cuts, scaling.
Preferably, the feature extraction network model includes the model or InceptionV2 of ResNet algorithm
The model of algorithm.
Preferably, the image feature information according to the extraction identifies the feature in described image information
Attribute, comprising:
Using target detection model, the characteristic attribute in described image information is identified.
Preferably, the target detection model includes model or RFCN algorithm based on FasterRCNN algorithm
Model.
It is preferably, described to obtain the visit business rule that enterprise formulates in service enabler, comprising:
Corresponding visit business rule is inquired according to current enterprise ID, is stored in current operating environment.
Preferably, the visit business rule formulated according to the enterprise, judges the knowledge another characteristic category
Whether property meets the visit business rule of the formulation, comprising:
Judgement is compared with the visit business rule according to the characteristic attribute for including in described image information respectively;
According to request type, the comparison result is returned to or is saved as in real time statistical data.
Preferably, the characteristic attribute of the identification includes the classification, quantity and profile information of SKU.
A kind of Intelligent visit system, including acquiring unit, extraction unit, recognition unit, configuration unit, analytical unit,
The acquiring unit is used to obtain the image information of input;
The extraction unit extracts the characteristic information of described image;
The recognition unit is used for the image feature information according to the extraction, identifies the feature category in described image information
Property;
The configuration unit is used to obtain the visit business rule that enterprise formulates in service enabler;
The analytical unit is used for the visit business rule formulated according to the enterprise, judges the characteristic attribute of the identification
Whether the visit business rule of the formulation is met.
Preferably, the acquiring unit includes obtaining subelement and determining subelement,
The picture for obtaining subelement and being used to obtain the input;
The determining subelement is for determining the described image information for including in the picture.
Preferably, the extraction unit includes pre-processing subelement and extraction subelement,
The pretreatment subelement is used to carry out pretreatment operation to image;
The extraction subelement is used to use feature extraction network model, extracts pretreated characteristics of image.
Preferably, the pretreatment operation includes equalization, cuts, scaling.
Preferably, the feature extraction network model includes the model or InceptionV2 of ResNet algorithm
The model of algorithm.
Preferably, the recognition unit includes identification subelement, and the identification subelement using target for being examined
Model is surveyed, identifies the characteristic attribute in described image information.
Preferably, the target detection model includes model or RFCN algorithm based on FasterRCNN algorithm
Model.
Preferably, the configuration unit includes storing sub-units, and the storing sub-units are used for according to current enterprise
Industry ID inquires corresponding visit business rule, is stored in current operating environment.
Preferably, the analytical unit include judgment sub-unit and processing subelement,
The judgment sub-unit is for respectively according to the characteristic attribute and the visit industry for including in described image information
Judgement is compared in business rule;
The processing subelement is used to return to or save as in real time statistical number for the comparison result according to request type
According to.
Preferably, the characteristic attribute of the identification includes the classification, quantity and profile information of SKU.
Compared with the prior art, the embodiment of the present invention has the following beneficial effects:
1, it by obtaining image and carrying out feature extraction and Attribute Recognition to its image, realizes Intelligent visiting, grasps visit
Make simpler convenience, improves working efficiency, complete visit business with achieving the effect that fast and flexible.
2, it is compared by characteristic attribute to identification and visit business rule, and its result is returned or saved, reached
The effect for having arrived statistical data, reduces cost of labor, further improves working efficiency.
Detailed description of the invention
Fig. 1: for the flow diagram of Intelligent visiting method in the embodiment of the present invention;
Fig. 2: for the flow diagram of Intelligent visiting method and step S1 in the embodiment of the present invention;
Fig. 3: for the flow diagram of Intelligent visiting method and step S2 in the embodiment of the present invention;
Fig. 4: for the flow diagram of Intelligent visiting method and step S5 in the embodiment of the present invention;
Fig. 5: for the legend 1 for visiting acquisition in the embodiment of the present invention;
Fig. 6: for the legend 2 for visiting acquisition in the embodiment of the present invention;
Fig. 7: for the structural schematic diagram of Intelligent visit system in the embodiment of the present invention;
Fig. 8: for a kind of electronic equipment structural schematic diagram for executing Intelligent visiting method in the embodiment of the present invention.
Wherein, the appended drawing reference of Figure of description is as follows:
501, memory;502, processor;503, interface arrangement;504, input unit;505, display device;506, it communicates
Device;507, loudspeaker;508, microphone.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is please referred to, the preferred embodiment of the present invention provides a kind of Intelligent visiting method, comprising:
S1 obtains business personnel and visits image information;
S2 extracts the characteristic information of described image;
S3 identifies the characteristic attribute in described image information according to the image feature information of the extraction;
S4 obtains the visit business rule that enterprise formulates in service enabler;
It is described to judge whether the characteristic attribute of the identification meets according to the visit business rule that the enterprise formulates by S5
The visit business rule of formulation.
By obtaining image and carrying out feature extraction and Attribute Recognition to its image, realizes Intelligent visiting, operate visit
Simpler convenience improves working efficiency, complete visit business with achieving the effect that fast and flexible.
Referring to Fig. 2, in the present embodiment, the step S1 includes:
S11 obtains the picture of the input;
S12 determines the described image information for including in the picture.
Referring to Fig. 3, in the present embodiment, the step S2 includes:
S21 pre-processes image;
S22 extracts pretreated characteristics of image using feature extraction network model.
In the present embodiment, pretreatment includes equalization, cuts, scaling in the step S21.
In the present embodiment, the feature extraction network model in the step S22 include ResNet algorithm model or
The model of InceptionV2 algorithm.
In the present embodiment, the step S3 includes: to identify the feature in described image information using target detection model
Attribute.
In the present embodiment, the target detection model includes model or RFCN algorithm based on FasterRCNN algorithm
Model.
In the present embodiment, the step S4 includes: to inquire corresponding visit business rule, storage according to current enterprise ID
In current operating environment.
Referring to Fig. 4, in the present embodiment, the step S5 includes:
S51 is compared according to the characteristic attribute for including in described image information with the visit business rule respectively
Judgement;
The comparison result is returned to or is saved as in real time statistical data according to request type by S52.
In the present embodiment, the characteristic attribute of the identification includes the classification, quantity and profile information of SKU.
The specific implementation process of this method embodiment is as follows:
It referring to figure 5 and figure 6, is the supermarket's commodity visited in the present embodiment, wherein Fig. 5 is beverage, and Fig. 6 is toothpaste.
The image information is obtained to beverage shown in fig. 5 and toothpaste shown in fig. 6 first in supermarket, business personnel is needing
Application software is logged in the case where connection network, to the shops under enterprise, the superfine terminal of quotient, is taken pictures to SKU display, and on
Reach server.
System obtains the Fig. 5 and Fig. 6 for being uploaded to server, carries out feature extraction to Fig. 5 and Fig. 6 and identifies the class of SKU
Not, the profile information of quantity and each SKU.
Using ResNet algorithm model and InceptionV2 algorithm model is based on, the SKU for including in Fig. 5 and Fig. 6 is extracted
Characteristic pattern.
Then using FasterRCNN algorithm model is based on, the classification, quantity of SKU and profile letter in image information are identified
Breath.
Based on algorithm model, first acquisition training data, pre-prepd training data, training data packet are specifically obtained
The multiple images and the corresponding markup information of each image of multiple SKU are included, the data format of training data can be TFRecord.
According to training data, parameter in training image feature extraction algorithm model and object classification location algorithm model,
It can be in the frame of server-side operation artificial intelligence learning system, using feature extraction algorithm and algorithm of target detection to acquisition
Training data is trained, and obtains corresponding algorithm parameter record file.Wherein, the frame of artificial intelligence learning system is
Tensorflow, Caffe or Torch.
Tensorflow frame can be run in server-side, using ResNet algorithm and FasterRCNN algorithm to training number
According to being trained, and the Parameter File based on ResNet algorithm and FasterRCNN algorithm being obtained, Parameter File is ckpt file,
Freeze the parameter that ResNet algorithm and FasterRCNN algorithm are obtained in training, and exports the calculation that can be finally deployed in server end
Method model.
Specifically, can be in the frame of server-side operation artificial intelligence learning system, call parameters are freezed, model exports
API, generate finally can service model.
Tensorflow frame can be run in server-side, be freezed using parameter, model export API, generation can finally take
The model of businessization, model file format are pb.
Due to enterprise's dialing plan in the visited network being arranged based on operation system, mainly there is the basis of enterprise when newly-built enterprise customer
Parameter configuration (being stored in the form of JSON) and corresponding JavaScript script, are handled, underlying parameter is matched for subsequent analysis
Setting is the business name that can specify SKU, unit and whether be competing product, and JavaScript script can specify calculate it is each
The area accounting or quantity accounting of SKU, and the relative position in picture.
Service enabler can obtain corresponding basic parameter configuration and JavaScript script according to enterprise, each enterprise
Basic parameter configuration and JavaScript script are all different, all dynamic are supported to modify and accomplish to come into force immediately.
By the enterprise business rule of acquisition, analysis processing is done in conjunction with obtained result data, including basic data (such as:
SKU classification, quantity and profile information) and according to the data that configuration information generates, basic parameter configuration is specified SKU area accounting
Just belong to greater than 30% " background detection qualified ", and JavaScript script can calculate corresponding SKU area accounting, and with match
The value set compares, and analyzes the result data of " whether background detection is qualified ".
Based on the analysis results, it returns data to user and stores the data to database.Data, which return to user, to be had
Two kinds of forms, one is directly return the result data by HTTP request and store to database;One is only storages to arrive data
Library, downstream industry can obtain corresponding data again according to picture.
Finally, identify in Fig. 5 include SKU quantity be 12, the profile information of classification 1 and SKU;Wherein each drink
Expect SKU are as follows: drinks 1, quantity 12.Identify to include SKU quantity 26, the profile information of classification 6 and SKU in Fig. 6;
Wherein each toothpaste SKU from top to bottom, from left to right, successively are as follows: toothpaste 1, quantity 11;Toothpaste 2, quantity 4;Toothpaste 3, quantity 6;
Toothpaste 4, quantity 3;Toothpaste 5, quantity 2.
From the foregoing, it will be observed that this specification embodiment provides the determination method for the industry Intelligent visiting that disappears fastly.It is inputted by obtaining
Image information, and identify the classification, quantity and profile information for the SKU for including in the image information.Then, according to the class of SKU
Not, whether qualified the visit business rule that quantity and profile information and enterprise formulate, analyze the secondary visit business.To make
The visit situation of business personnel in quick, convenient, the accurate Geostatistics analysis institute of energy such as Enterprises Leader, supervisor compass of competency.
Corresponding with the above-mentioned determination method of industry Intelligent visiting that disappears fastly referring to Fig. 7, this specification additionally provides a kind of fast
The system of the determination method of the industry that disappears Intelligent visiting, the system include acquiring unit, extraction unit, recognition unit, configuration unit,
Analytical unit,
The acquiring unit is used to obtain the image information of input;
The extraction unit extracts the characteristic information of described image;
The recognition unit is used for the image feature information according to the extraction, identifies the feature category in described image information
Property;
The configuration unit is used to obtain the visit business rule that enterprise formulates in service enabler;
The analytical unit is used for the visit business rule formulated according to the enterprise, judges the characteristic attribute of the identification
Whether the visit business rule of the formulation is met.
In the present embodiment, the acquiring unit includes obtaining subelement and determining subelement,
The picture for obtaining subelement and being used to obtain the input;
The determining subelement is for determining the described image information for including in the picture.
In the present embodiment, the extraction unit includes pre-processing subelement and extraction subelement,
The pretreatment subelement is used to carry out pretreatment operation to image;
The extraction subelement is used to use feature extraction network model, extracts pretreated characteristics of image.
In the present embodiment, the pretreatment operation includes equalization, cuts, scaling.
In the present embodiment, the feature extraction network model includes the model or InceptionV2 of ResNet algorithm
The model of algorithm.
In the present embodiment, the recognition unit includes identification subelement, and the identification subelement using target for being examined
Model is surveyed, identifies the characteristic attribute in described image information.
In the present embodiment, the target detection model includes model or RFCN algorithm based on FasterRCNN algorithm
Model.
In the present embodiment, the configuration unit includes storing sub-units, and the storing sub-units are used for according to current enterprise
Industry ID inquires corresponding visit business rule, is stored in current operating environment.
In the present embodiment, the analytical unit include judgment sub-unit and processing subelement,
The judgment sub-unit is for respectively according to the characteristic attribute and the visit industry for including in described image information
Judgement is compared in business rule;
The processing subelement is used to return to or save as in real time statistical number for the comparison result according to request type
According to.
In the present embodiment, the characteristic attribute of the identification includes the classification, quantity and profile information of SKU.
The combined use of the system acquiring unit, extraction unit, recognition unit, configuration unit and analytical unit, makes user
Can quick, convenient, accurately analyze and determine whether business personnel visits behavior qualified.
Referring to Fig. 8, for a kind of electronic equipment structural block diagram for executing the method for the present invention.
According to Fig.8, which includes memory 501 and processor 502, which refers to for storing
It enables, which is operated for control processor 502 to execute above-mentioned one kind and disappear fastly the design side of industry Intelligent visit system
Method.
The processor 502 can be central processor CPU, Micro-processor MCV etc.;The memory 501 includes ROM (read-only
Memory), RAM (random access memory), the nonvolatile memory of hard disk etc.;In addition to this, according to Fig.8,
The electronic equipment further includes interface arrangement 503, input unit 504, display device 505, communication device 506, loudspeaker 507, wheat
Gram wind 508.
Although multiple devices are shown in FIG. 8, electronic equipment of the present invention can only relate to part dress therein
It sets: processor 501, memory 502, display device 505.
Above-mentioned communication device 506 has been able to carry out wired or wireless communication;Interface arrangement 503 connects including earphone jack, USB
Mouthful;Input unit 504 may include touch screen, key;Display device 505 is liquid crystal display, touch display screen.
Electronic equipment of the invention for example can be the electronic products such as mobile phone, tablet computer.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Divide cross-reference, each embodiment focuses on the differences from other embodiments, but those skilled in the art
Member is it should be understood that the various embodiments described above can according to need exclusive use or be combined with each other.In addition, for device
For embodiment, since it is corresponding with embodiment of the method, so describing fairly simple, related place is implemented referring to method
The explanation of the corresponding part of example.System embodiment described above is only schematical, wherein being used as separation unit
The module of explanation may or may not be physically separated.
The present invention can be device, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.Meter
Calculation machine readable storage medium storing program for executing can be the tangible device that can keep and store the instruction used by instruction execution equipment.Computer
Readable storage medium storing program for executing for example can be but be not limited to: storage device electric, magnetic storage apparatus, light storage device, electromagnetism storage are set
Standby, semiconductor memory apparatus or above-mentioned any appropriate combination.The more specific example of computer readable storage medium is (non-
The list of exhaustion) it include: portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable
Formula programmable read only memory (EPROM or flash memory), static random access memory (SRAM), the read-only storage of Portable compressed disk
Device (CD-ROM), memory stick, floppy disk, mechanical coding equipment, is for example stored thereon with beating for instruction at digital versatile disc (DVD)
Hole card or groove internal projection structure and above-mentioned any appropriate combination.Computer readable storage medium used herein above
It is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations pass through waveguide or other biographies
The electromagnetic wave (for example, the light pulse for passing through fiber optic cables) that defeated medium is propagated or the electric signal transmitted by electric wire.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing operation of the present invention can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language of object-oriented, such as
Smalltalk, C++ etc., and conventional procedural programming languages, such as " C " language or similar programming language.Computer can
Reader instruction can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind, including office
Domain net (LAN) or wide area network (WAN), are connected to subscriber computer, or, it may be connected to outer computer (such as using because
Spy nets service provider to connect by internet).In some embodiments, pass through the shape using computer-readable program instructions
State information comes personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or programmable
Logic array (PLA), which can execute computer-readable program instructions, to realize various aspects of the invention.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or block diagram describes various aspects of the invention.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.These computer-readable program instructions can
To be supplied to the processor of general purpose computer, special purpose computer or other programmable data processing units, to produce one kind
Machine produces reality so that these instructions are when executed by a processor of a computer or other programmable data processing device
The device of function action specified in one or more boxes in existing flowchart and or block diagram.It can also be these computers
Readable program instructions store in a computer-readable storage medium, these instructions are so that computer, programmable data processing unit
And/or other equipment work in a specific way, thus, the computer-readable medium for being stored with instruction then includes a manufacture,
It includes the instruction of the various aspects of function action specified in one or more boxes in implementation flow chart and/or block diagram.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other equipment, be made
It obtains and executes series of operation steps in computer, other programmable data processing units or other equipment, to generate computer
The process of realization, so that the instruction executed in computer, other programmable data processing units or other equipment is realized
Function action specified in one or more boxes in flowchart and or block diagram.
The flow chart and block diagram in the drawings show the system of multiple embodiments according to the present invention, method and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.It is right
For those skilled in the art it is well known that, by hardware mode realize, by software mode realize and pass through software and
It is all of equal value that the mode of combination of hardware, which is realized,.
Particular embodiments described above has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that the above is only a specific embodiment of the present invention, the protection being not intended to limit the present invention
Range.It particularly points out, to those skilled in the art, all within the spirits and principles of the present invention, that is done any repairs
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (20)
1. a kind of Intelligent visiting method characterized by comprising
It obtains business personnel and visits image information;
Extract the characteristic information of described image;
According to the image feature information of the extraction, the characteristic attribute in described image information is identified;
Obtain the visit business rule that enterprise formulates in service enabler;
According to the visit business rule that the enterprise formulates, judge whether the characteristic attribute of the identification meets visiing for the formulation
Visit business rule.
2. Intelligent visiting method as described in claim 1, which is characterized in that the acquisition business personnel visits image information, packet
It includes:
Obtain the picture of the input;
Determine the described image information for including in the picture.
3. Intelligent visiting method as described in claim 1, which is characterized in that the characteristic information for extracting described image, packet
It includes:
Image is pre-processed;
Using feature extraction network model, pretreated characteristics of image is extracted.
4. Intelligent visiting method as claimed in claim 3, which is characterized in that the pretreatment includes equalization, cuts, contracting
It puts.
5. Intelligent visiting method as claimed in claim 3, which is characterized in that the feature extraction network model includes
The model of ResNet algorithm or the model of InceptionV2 algorithm.
6. Intelligent visiting method as described in claim 1, which is characterized in that described to be believed according to the characteristics of image of the extraction
Breath identifies the characteristic attribute in described image information, comprising:
Using target detection model, the characteristic attribute in described image information is identified.
7. Intelligent visiting method as claimed in claim 6, which is characterized in that the target detection model includes being based on
The model of FasterRCNN algorithm or the model of RFCN algorithm.
8. Intelligent visiting method as described in claim 1, which is characterized in that enterprise formulated in the acquisition service enabler visits
Visit business rule, comprising:
Corresponding visit business rule is inquired according to current enterprise ID, is stored in current operating environment.
9. Intelligent visiting method as described in claim 1, which is characterized in that the visit business formulated according to the enterprise
Rule, judges whether the characteristic attribute of the identification meets the visit business rule of the formulation, comprising:
Judgement is compared with the visit business rule according to the characteristic attribute for including in described image information respectively;
According to request type, the comparison result is returned to or is saved as in real time statistical data.
10. such as the described in any item Intelligent visiting methods of claim 1-9, which is characterized in that the characteristic attribute packet of the identification
Include the classification, quantity and profile information of SKU.
11. a kind of Intelligent visit system, which is characterized in that including acquiring unit, extraction unit, recognition unit, configuration unit, divide
Unit is analysed,
The acquiring unit is used to obtain the image information of input;
The extraction unit extracts the characteristic information of described image;
The recognition unit is used for the image feature information according to the extraction, identifies the characteristic attribute in described image information;
The configuration unit is used to obtain the visit business rule that enterprise formulates in service enabler;
The analytical unit is used for the visit business rule formulated according to the enterprise, judge the identification characteristic attribute whether
Meet the visit business rule of the formulation.
12. Intelligent visit system as claimed in claim 11, which is characterized in that the acquiring unit include obtain subelement and
Determine subelement,
The picture for obtaining subelement and being used to obtain the input;
The determining subelement is for determining the described image information for including in the picture.
13. Intelligent visit system as claimed in claim 11, which is characterized in that the extraction unit includes pretreatment subelement
With extract subelement,
The pretreatment subelement is used to carry out pretreatment operation to image;
The extraction subelement is used to use feature extraction network model, extracts pretreated characteristics of image.
14. Intelligent visit system as claimed in claim 13, which is characterized in that the pretreatment operation includes equalization, cuts out
It cuts, scale.
15. Intelligent visit system as claimed in claim 13, which is characterized in that the feature extraction network model includes
The model of ResNet algorithm or the model of InceptionV2 algorithm.
16. Intelligent visit system as claimed in claim 11, which is characterized in that the recognition unit includes identification subelement,
The identification subelement is used to use target detection model, identifies the characteristic attribute in described image information.
17. Intelligent visit system as claimed in claim 16, which is characterized in that the target detection model includes being based on
The model of FasterRCNN algorithm or the model of RFCN algorithm.
18. Intelligent visit system as claimed in claim 11, which is characterized in that the configuration unit includes storing sub-units,
The storing sub-units are used to inquire corresponding visit business rule according to current enterprise ID, are stored in current operating environment.
19. Intelligent visit system as claimed in claim 11, which is characterized in that the analytical unit include judgment sub-unit and
Subelement is handled,
The judgment sub-unit according to the characteristic attribute and the visit business that include in described image information for advising respectively
Judgement is then compared;
The processing subelement is used to return to or save as in real time statistical data for the comparison result according to request type.
20. such as the described in any item Intelligent visit systems of claim 11-19, which is characterized in that the characteristic attribute of the identification
Classification, quantity and profile information including SKU.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811063331.4A CN109493104A (en) | 2018-09-12 | 2018-09-12 | A kind of method and system of Intelligent visiting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811063331.4A CN109493104A (en) | 2018-09-12 | 2018-09-12 | A kind of method and system of Intelligent visiting |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493104A true CN109493104A (en) | 2019-03-19 |
Family
ID=65690444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811063331.4A Pending CN109493104A (en) | 2018-09-12 | 2018-09-12 | A kind of method and system of Intelligent visiting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493104A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110941687A (en) * | 2019-10-16 | 2020-03-31 | 浙江口碑网络技术有限公司 | Method and device for generating visit report |
CN115564372A (en) * | 2022-09-07 | 2023-01-03 | 广州市玄武无线科技股份有限公司 | Processing method and device for terminal visit flow |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105630915A (en) * | 2015-12-21 | 2016-06-01 | 山东大学 | Method and device for classifying and storing pictures in mobile terminals |
CN105701519A (en) * | 2014-12-10 | 2016-06-22 | 株式会社理光 | Realogram scene analysis of images: superpixel scene analysis |
CN106886795A (en) * | 2017-02-17 | 2017-06-23 | 北京维弦科技有限责任公司 | Object identification method based on the obvious object in image |
CN107045641A (en) * | 2017-04-26 | 2017-08-15 | 广州图匠数据科技有限公司 | A kind of identification of pallets method based on image recognition technology |
CN107742117A (en) * | 2017-11-15 | 2018-02-27 | 北京工业大学 | A kind of facial expression recognizing method based on end to end model |
AU2018100321A4 (en) * | 2018-03-15 | 2018-04-26 | Chen, Jinghan Mr | Person ReID method based on metric learning with hard mining |
CN108509976A (en) * | 2018-02-12 | 2018-09-07 | 北京佳格天地科技有限公司 | The identification device and method of animal |
-
2018
- 2018-09-12 CN CN201811063331.4A patent/CN109493104A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701519A (en) * | 2014-12-10 | 2016-06-22 | 株式会社理光 | Realogram scene analysis of images: superpixel scene analysis |
CN105630915A (en) * | 2015-12-21 | 2016-06-01 | 山东大学 | Method and device for classifying and storing pictures in mobile terminals |
CN106886795A (en) * | 2017-02-17 | 2017-06-23 | 北京维弦科技有限责任公司 | Object identification method based on the obvious object in image |
CN107045641A (en) * | 2017-04-26 | 2017-08-15 | 广州图匠数据科技有限公司 | A kind of identification of pallets method based on image recognition technology |
CN107742117A (en) * | 2017-11-15 | 2018-02-27 | 北京工业大学 | A kind of facial expression recognizing method based on end to end model |
CN108509976A (en) * | 2018-02-12 | 2018-09-07 | 北京佳格天地科技有限公司 | The identification device and method of animal |
AU2018100321A4 (en) * | 2018-03-15 | 2018-04-26 | Chen, Jinghan Mr | Person ReID method based on metric learning with hard mining |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110941687A (en) * | 2019-10-16 | 2020-03-31 | 浙江口碑网络技术有限公司 | Method and device for generating visit report |
CN115564372A (en) * | 2022-09-07 | 2023-01-03 | 广州市玄武无线科技股份有限公司 | Processing method and device for terminal visit flow |
CN115564372B (en) * | 2022-09-07 | 2023-10-24 | 广州市玄武无线科技股份有限公司 | Terminal visit flow processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107105031A (en) | Information-pushing method and device | |
CN107679475B (en) | Store monitoring and evaluating method and device and storage medium | |
CN105678591A (en) | Video-analysis-based commercial intelligent operation decision-making support system and method | |
CN104954410A (en) | Message pushing method, device thereof and server | |
CN107315824A (en) | Method and apparatus for generating thermodynamic chart | |
CN110647522A (en) | Data mining method, device and system | |
CN108228835B (en) | Method and apparatus for handling video | |
CN110009379A (en) | A kind of building of site selection model and site selecting method, device and equipment | |
CN109388548A (en) | Method and apparatus for generating information | |
CN110377522A (en) | The test method for scene of trading, calculates equipment and medium at device | |
CN110349013A (en) | Risk control method and device | |
CN107506376A (en) | Obtain the client of information point data in region | |
CN108182457A (en) | For generating the method and apparatus of information | |
CN109993544A (en) | Data processing method, system, computer system and computer readable storage medium | |
CN109493104A (en) | A kind of method and system of Intelligent visiting | |
CN109102324A (en) | Model training method, the red packet material based on model are laid with prediction technique and device | |
CN108830980A (en) | Security protection integral intelligent robot is received in Study of Intelligent Robot Control method, apparatus and attendance | |
CN107291774A (en) | Error sample recognition methods and device | |
CN108898604A (en) | Method and apparatus for handling image | |
WO2014124279A1 (en) | Customer experience management for an organization | |
CN109711917A (en) | Information-pushing method and device | |
CN110334620A (en) | Appraisal procedure, device, storage medium and the electronic equipment of quality of instruction | |
CN107291835A (en) | A kind of recommendation method and apparatus of search term | |
CN109522399A (en) | Method and apparatus for generating information | |
US20130006705A1 (en) | Small business intelligence tool |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |
|
RJ01 | Rejection of invention patent application after publication |