CN109784026A - Vegetable recommended method and device, medium and equipment based on living things feature recognition - Google Patents
Vegetable recommended method and device, medium and equipment based on living things feature recognition Download PDFInfo
- Publication number
- CN109784026A CN109784026A CN201910003253.7A CN201910003253A CN109784026A CN 109784026 A CN109784026 A CN 109784026A CN 201910003253 A CN201910003253 A CN 201910003253A CN 109784026 A CN109784026 A CN 109784026A
- Authority
- CN
- China
- Prior art keywords
- vegetable
- facial image
- dish information
- recommended method
- histogram
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of vegetable recommended method and device, medium and equipment based on living things feature recognition, are related to field of artificial intelligence.The vegetable recommended method comprise determining that first order dishes equipment transmission the first facial image and the first dish information corresponding with the first facial image；Obtain second order dishes equipment transmission the second facial image；If the second facial image is matched with the first facial image, it is determined that the second dish information similar with the first dish information；Second dish information is sent to second to order dishes equipment.The disclosure can provide personalized vegetable recommendation service to eater.
Description
Technical field
This disclosure relates to which field of artificial intelligence, pushes away in particular to a kind of vegetable based on living things feature recognition
Recommend method, vegetable recommendation apparatus, storage medium and electronic equipment based on living things feature recognition.
Background technique
With the development and the improvement of people's living standards of society, one table delicacies delicacy of enjoyment is had become very general at the restaurant
Time thing.When people eat at the restaurant, ordering dishes is a necessary link, and many restaurants have been carried out with electronics point at present
The form of meal is ordered dishes, for example, eater can obtain the electronic menu in restaurant by scanning the two-dimensional code, in addition, some meal
Shop is also provided with plate, so that eater is ordered food using the electronic menu on plate.
Electronic menu can also show the preferential of restaurant in addition to the vegetable comprising some traditionally on paper menus, price, picture
The information such as activity, the dish information recommended, the advance notice of new vegetable.However, currently, electronic menu be user recommend vegetable it is identical,
The difference of eater can not be embodied, the vegetable of recommendation cannot preferably agree with the demand of having dinner of eater.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of vegetable recommended method based on living things feature recognition, is known based on biological characteristic
Other vegetable recommendation apparatus, storage medium and electronic equipment, and then the limit due to the relevant technologies is overcome at least to a certain extent
It can not recommend the dish information agreed with it caused by system and defect for different eaters.
According to one aspect of the disclosure, a kind of vegetable recommended method based on living things feature recognition is provided, comprising: determine
First order dishes equipment transmission the first facial image and the first dish information corresponding with the first facial image；Obtain second point
The second facial image that dish equipment is sent；If the second facial image is matched with the first facial image, it is determined that with the first vegetable
Similar second dish information of information；Second dish information is sent to second to order dishes equipment.
Optionally, the first facial image is stored in a customer image library；Wherein, vegetable recommended method further include: such as
The second facial image of fruit is mismatched with the face images in customer image library including the first facial image, it is determined that
The attributive character of second facial image；Wherein, attributive character includes age information and/or gender information；It will be with attributive character pair
The dish information answered is sent to second and orders dishes equipment.
Optionally, will dish information corresponding with attributive character to be sent to the second equipment of ordering dishes include: from each acquisition of information
Platform obtains the dish information for having the put vegetable of client of attributive character；If the put vegetable of the client for having attributive character
Dish information meets default initial recommendation requirement, then dish information is sent to second and ordered dishes equipment.
Optionally, vegetable recommended method further include: be sent to the corresponding dish information of the specialties of current slot
Second orders dishes equipment；And/or determine that it is more than one that number and all vegetables are selected in a preset time by the ratio of number
The corresponding dish information of target vegetable is sent to second and ordered dishes equipment by the vegetable of default ratio as target vegetable.
Optionally, the second dish information corresponds to one or more of the taste of vegetable, price, dish amount and believes with the first vegetable
It is similar to cease corresponding vegetable.
Optionally, vegetable recommended method further include: the histogram of the first facial image of building is as the first histogram, and structure
The histogram of the second facial image is built as the second histogram；Calculate the similarity of the first histogram and the second histogram；Wherein,
If the similarity of the first histogram and the second histogram is greater than the first preset threshold, the second facial image and the first face figure
As matching.
Optionally, vegetable recommended method further include: extract the first facial image using the convolutional neural networks after a training
Feature vector as first eigenvector；The feature vector of the second facial image is extracted as second using convolutional neural networks
Feature vector；Calculate the cosine similarity of first eigenvector and second feature vector；Wherein, if calculated cosine is similar
Degree is greater than the second preset threshold, then the second facial image is matched with the first facial image.
According to one aspect of the disclosure, a kind of vegetable recommendation apparatus based on living things feature recognition is provided, which pushes away
Recommending device may include first information determining module, the second data obtaining module, dish information determining module and the first transmission mould
Block.
Specifically, first information determining module be determined for first order dishes equipment transmission the first facial image and
The first dish information corresponding with the first facial image；Second data obtaining module can be used for obtaining second order dishes equipment transmission
The second facial image；It is matched if dish information determining module can be used for the second facial image with the first facial image,
Determine the second dish information similar with the first dish information；First sending module can be used for for the second dish information being sent to
Second orders dishes equipment.
Optionally, the first facial image is stored in a customer image library；Wherein, vegetable recommendation apparatus can also include
Attributive character determining module and the second sending module.
Specifically, if attributive character determining module can be used for including first in the second facial image and customer image library
Face images including facial image mismatch, it is determined that the attributive character of the second facial image；Wherein, attributive character
Including age information and/or gender information；Second sending module can be used for sending dish information corresponding with attributive character
It orders dishes equipment to second.
Optionally, the second sending module may include vegetable acquiring unit and vegetable transmission unit.
Specifically, vegetable acquiring unit can be used for obtaining the client institute point for having attributive character from each information acquisition platform
The dish information of vegetable；If the dish information for the put vegetable of client that vegetable transmission unit can be used for having attributive character is full
Dish information is then sent to second and ordered dishes equipment by the default initial recommendation requirement of foot.
Optionally, vegetable recommendation apparatus can also include third sending module and/or the 4th sending module.
Specifically, third sending module can be used for for the corresponding dish information of the specialties of current slot being sent to
Second orders dishes equipment；4th sending module is determined for being selected number and all vegetables in a preset time by number
Ratio is more than the vegetable of a default ratio as target vegetable, and the corresponding dish information of target vegetable is sent to second and is ordered dishes
Equipment.
Optionally, the second dish information corresponds to one or more of the taste of vegetable, price, dish amount and believes with the first vegetable
It is similar to cease corresponding vegetable.
Optionally, dish information determining module may include histogram construction unit and histogram similarity calculated.
Specifically, histogram construction unit can be used for constructing the histogram of the first facial image as the first histogram,
And the histogram of the second facial image is constructed as the second histogram；Histogram similarity calculated can be used for calculating first
The similarity of histogram and the second histogram；Wherein, if the similarity of the first histogram and the second histogram is greater than first in advance
If threshold value, then the second facial image is matched with the first facial image.
Optionally, dish information determining module may include fisrt feature extraction unit, second feature extraction unit and spy
Levy similarity calculated.
Specifically, fisrt feature extraction unit can be used for extracting the first face using the convolutional neural networks after a training
The feature vector of image is as first eigenvector；Second feature extraction unit can be used for extracting the using convolutional neural networks
The feature vector of two facial images is as second feature vector；Characteristic similarity computing unit can be used for calculating fisrt feature to
The cosine similarity of amount and second feature vector；Wherein, if calculated cosine similarity is greater than the second preset threshold, the
Two facial images are matched with the first facial image.
According to one aspect of the disclosure, a kind of storage medium is provided, computer program, computer program are stored thereon with
The vegetable recommended method based on living things feature recognition of above-mentioned any one is realized when being executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor；And memory, for storing
The executable instruction of processor；Wherein, processor is configured to execute the base of above-mentioned any one via executable instruction is executed
In the vegetable recommended method of living things feature recognition.
In the technical solution provided by some embodiments of the present disclosure, determine first order dishes equipment transmission the first face
Image and the first dish information corresponding with the first facial image, obtain second order dishes equipment transmission the second facial image,
If the second facial image is matched with the first facial image, it is determined that the second dish information similar with the first dish information, and
Second dish information is sent to second to order dishes equipment.On the one hand, the disclosure can provide personalized vegetable to eater and push away
Recommend service；On the other hand；For eater, without the clicking operation of any menu, the dish being consistent with itself can be obtained
Product are recommended.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 diagrammatically illustrates the flow chart of vegetable recommended method according to an exemplary embodiment of the present disclosure；
Fig. 2 diagrammatically illustrates the block diagram of vegetable recommendation apparatus according to an exemplary embodiment of the present disclosure；
Fig. 3 diagrammatically illustrates the block diagram of the vegetable recommendation apparatus of the another exemplary embodiment according to the disclosure；
Fig. 4 diagrammatically illustrates the block diagram of the second sending module according to an exemplary embodiment of the present disclosure；
Fig. 5 diagrammatically illustrates the block diagram of the vegetable recommendation apparatus according to the another exemplary embodiment of the disclosure；
Fig. 6 diagrammatically illustrates the block diagram of the vegetable recommendation apparatus of another illustrative embodiments according to the disclosure；
Fig. 7 diagrammatically illustrates the block diagram of dish information determining module according to an exemplary embodiment of the present disclosure；
Fig. 8 diagrammatically illustrates the box of the dish information determining module of the another exemplary embodiment according to the disclosure
Figure；
Fig. 9 shows the schematic diagram of storage medium according to an exemplary embodiment of the present disclosure；And
Figure 10 diagrammatically illustrates the block diagram of electronic equipment according to an exemplary embodiment of the present disclosure.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all steps.For example, the step of having
It can also decompose, and the step of having can merge or part merges, therefore the sequence actually executed is possible to according to the actual situation
Change.
Term " first " described in the disclosure, " second ", " third ", " the 4th " merely to distinguish purpose, reference
Object may be the same or different.
It is described below to be realized by a server based on the vegetable recommended method of living things feature recognition, that is,
It says, which can execute each step of the vegetable recommended method of the disclosure, and in this case, the vegetable of the disclosure pushes away
Recommending device can be only fitted in the server.In addition, the server can be deployed in the dining room using method of disclosure and device
It is interior, however, the server can also be that disengaging is right in the third-party server of dining room hardware environment, this illustrative embodiment
This does not do particular determination.
Although in addition, using face characteristic as biological characteristic in following description, however, those skilled in the art are easy
Understand, is also based on the biological characteristic such as fingerprint recognition, iris recognition to construct content described in the disclosure, this
It should also be as the inventive concept for belonging to the disclosure.
Fig. 1 diagrammatically illustrates the vegetable recommended method based on living things feature recognition of the illustrative embodiments of the disclosure
Flow chart.With reference to Fig. 1, the vegetable recommended method of the disclosure be may comprise steps of:
S12. determine first order dishes equipment transmission the first facial image and the first dish corresponding with the first facial image
Product information.
According to some embodiments of the present disclosure, equipment of ordering dishes can be the plate of dining room offer, in such a case, it is possible to
In advance in plate typing dining room each dish information.Dish information can be, but not limited to menu name, vegetable type, vegetable
It is one or more in picture, vegetable price, wherein vegetable type may refer to the style of cooking of vegetable, for example, Guangdong dishes, Sichuan cuisine, Shandong
Dish, Shan dish, Zhejiang dish etc., also may refer to the taste of vegetable, for example, sweet tea, vinegar-pepper, sour-sweet etc. partially.In addition, may be used also in dish information
To include historic customer (eater) to information such as the evaluations, marking, sales volume (by a number) of the vegetable.
According to other embodiments of the disclosure, equipment of ordering dishes can also be the terminal (for example, mobile phone) that client is held.Example
Such as, when to be ordered dishes, client can scan the two dimensional code on dining table by mobile phone, to enter interface of ordering dishes.
Step S12 will be illustrated so that dining room provides plate as an example below.
When first client is ordered dishes by plate, the camera of plate is opened, and shoots the face of the first client currently to order dishes
First facial image can be sent to server as the first facial image, plate by image.In addition, plate can be with customer in response
Put vegetable is determined in operation when ordering dishes, and is sent to service for the dish information of put vegetable as the first dish information
Device.That is, server can determine the facial image of the first client currently to order dishes and the vegetable letter of put vegetable
Breath.
According to some embodiments of the present disclosure, the facial image of client can be stored into a customer image library, the figure
It is deposited as the mapping relations or the mapping relations that can also be stored with customer image and put vegetable in library can store to another
Store up space.
S14. obtain second order dishes equipment transmission the second facial image.
Under another scene, when the second client starts to order, the second equipment of ordering dishes that the second client uses can be acquired
The facial image of second client is sent to server as the second facial image, and by the second facial image.
In the illustrative embodiments of the disclosure, the second equipment of ordering dishes can be and order dishes that equipment is different to be set from first
It is standby.However, it is understood that the second equipment of ordering dishes with the first equipment of ordering dishes can be same equipment.
S16. if the second facial image is matched with the first facial image, it is determined that similar with the first dish information second
Dish information.
It should be noted that the first facial image described in the disclosure can be and determine before obtaining the second facial image
The facial image of any client.
Server can be compared with the second facial image with the first facial image.
According to some embodiments of the present disclosure, the histogram that can use image is compared two facial images.Tool
Body, firstly, server can construct the histogram of the first facial image as the first histogram, and server can construct
The histogram of second facial image is as the second histogram；Then, server can calculate the first histogram and the second histogram
Similarity as image comparison result.
Specifically, firstly, server can respectively to above-mentioned two image carry out HSV (Hue, Saturation, Value,
Tone, saturation degree, lightness) format conversion；Then, the histogram of the result building image after server can be converted based on format
Figure, and histogram is normalized；Next, server can calculate the similarity between two histograms.
If the similarity of the first histogram and the second histogram is greater than the first preset threshold, the first face can be determined
Image is matched with the second facial image, that is to say, that above-mentioned first client and the second client are same people.Wherein, if by complete
Exactly the same to be denoted as 1, then the range of the first preset threshold can be, for example, between 0.85 to 1.
According to some embodiments of the present disclosure, can the face that is included to two images of the mode based on deep learning into
Row compares.Specifically, firstly, server can extract the feature of the first facial image using the convolutional neural networks after a training
Vector can extract the feature vector of the second facial image as the as first eigenvector using the convolutional neural networks
Two feature vectors；Then, server can calculate the cosine similarity of first eigenvector and second feature vector as image
Comparison result.
Furthermore it is also possible to be trained using the sample after handmarking to the convolutional neural networks.The disclosure is to above-mentioned
The structure and training process of convolutional neural networks are not done specifically limited.
If calculated cosine similarity is greater than the second preset threshold, the first facial image and the second people can be determined
Face image matching, that is to say, that above-mentioned first client and the second client are same people.Wherein, it is defined as in cosine similarity
In the case where taking 0 to 1, the range of the second preset threshold can be, for example, between 0.9 to 1.
In the case where determining the second facial image and the matched situation of the first facial image, server can be determined and the first dish
Similar second dish information of product information.Similar can mean specifically, described herein: the second dish information corresponds to vegetable
One or more of taste, price, dish amount can vegetable corresponding with the first dish information it is similar.For example, the first dish information
Information comprising pork fried with sugar & vinegar dressing, then the second dish information may include the information such as sweet and sour spareribs, a sweet and sour ball, squirrel fish.Example again
Such as, most vegetable price is 30 to 40 yuan in the first dish information, then may include its in menu in the second dish information
His corresponding dish information of 30 to 40 yuan of vegetables.
S18. the second dish information second is sent to order dishes equipment.
The mark of second dish information can be sent to second and ordered dishes and set by server after determining the second dish information
It is standby, so that the second equipment of ordering dishes shows the second dish information on interface.
Other embodiments of the disclosure are described below.
According to some embodiments of the present disclosure, after step S14 obtains the second facial image, if the second facial image with
Face images in customer image library including the first facial image mismatch, then can determine the second facial image
Attributive character, wherein attributive character may include age information and/or the gender information that the second facial image corresponds to client,
For example, attributive character is the male between 20 years old to 30 years old.Specifically, can be by different from above-mentioned convolutional neural networks another
One convolutional neural networks determine age information and/or the gender information of client, specifically, can be using largely with markd
Sample training network model, to achieve the purpose that age information and/or gender information determine, to this in this illustrative embodiment
Do not do particular determination.
Next, can determine dish information according to the attributive character of the second facial image, and will determine in this case
Dish information out is sent to second and orders dishes equipment.Specifically, can be from each information acquisition platform (for example, cuisines forum, discussion bar
Deng) dish information for having the put vegetable of client of the attributive character is obtained, if the client institute for having the attributive character
The dish information for selecting vegetable meets default initial recommendation requirement, then the dish information can be sent to second and ordered dishes equipment.Its
In, presetting initial recommendation requirement can be such as are as follows: these vegetables are selected number greater than 200 times, evaluation of the client to these vegetables
Higher than the average level, etc. of vegetable evaluation, the disclosure requires not doing specifically limited to default initial recommendation.
According to other embodiments of the disclosure, server can also be by the corresponding vegetable of the specialties of current slot
Information is sent to second and orders dishes equipment.For example, current slot is in the happy festival time such as mid-autumn, the Dragon Boat Festival, dining room may make corresponding
Vegetable, in this case, if there is client has dinner in the period, then server can believe the corresponding vegetable of these vegetables
Breath recommends client.It orders dishes equipment furthermore it is also possible to which the vegetable of current slot discount is sent to second.
According to other embodiments of the disclosure, server can also determine interior number and all dishes of being ordered of a preset time
The ratio that product are selected number is more than that the vegetable of a default ratio is sent out as target vegetable, and by the corresponding dish information of target vegetable
It send to second and orders dishes equipment.Wherein it is possible to set preset time to one month, and 0.1 is set by default ratio, that is,
It says, it is if number and all vegetables that a vegetable is selected are more than 0.1 by the ratio of number, the vegetable is true in one month
It is set to target vegetable, is sent to second and orders dishes equipment.
In addition, for example the corresponding vegetable of the most preset quantity of number (for example, 5) a vegetable can also will be selected in one week
Information is sent to second and orders dishes equipment.
It, may be only whithin a period of time to the same class vegetable interest based on client according to other embodiments of the disclosure
The considerations of, in the case where determining the second facial image and the matched situation of the first facial image, if the of the non-selected recommendation of client
The corresponding vegetable of two dish informations, but order dishes second and select third dish information in equipment, then third vegetable can be believed
Breath the first dish information of substitution is stored.As a result, when the client has dinner next time, it can believe to the lead referral third vegetable
Vegetable as manner of breathing.Alternatively, the first dish information and third dish information are stored simultaneously, it, can when having dinner next time so as to the client
Simultaneously to lead referral vegetable similar with the first dish information and vegetable similar with third dish information.
In conclusion the vegetable recommended method according to the disclosure based on living things feature recognition.On the one hand, the disclosure can be to
Eater provides personalized vegetable recommendation service；On the other hand；For eater, the click without any menu is grasped
Make, can be obtained the vegetable being consistent with itself and recommend.
It should be noted that although describing each step of method in the disclosure in the accompanying drawings with particular order, this is simultaneously
Undesired or hint must execute these steps in this particular order, or have to carry out the ability of step shown in whole
Realize desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps,
And/or a step is decomposed into execution of multiple steps etc..
Further, a kind of vegetable recommendation apparatus based on living things feature recognition is additionally provided in this example embodiment.
Fig. 2 diagrammatically illustrates the block diagram of the vegetable recommendation apparatus of the illustrative embodiments of the disclosure.With reference to Fig. 2,
Vegetable recommendation apparatus 2 according to an exemplary embodiment of the present disclosure may include first information determining module 21, the second information
Obtain module 23, dish information determining module 25 and the first sending module 27.
Specifically, first information determining module 21 be determined for first order dishes equipment transmission the first facial image with
And the first dish information corresponding with the first facial image；Second data obtaining module 23 can be used for obtaining second and order dishes equipment
The second facial image sent；If dish information determining module 25 can be used for the second facial image and the first facial image
Match, it is determined that the second dish information similar with the first dish information；First sending module 27 can be used for believing the second vegetable
Breath is sent to second and orders dishes equipment.
According to an exemplary embodiment of the present disclosure, the first facial image is stored in a customer image library；With reference to Fig. 3,
Vegetable recommendation apparatus 3 may include attributive character determining module 31 and the second sending module 33 compared to vegetable recommendation apparatus 2.
Specifically, if attributive character determining module 31 can be used for including the in the second facial image and customer image library
Face images including one facial image mismatch, it is determined that the attributive character of the second facial image；Wherein, attribute is special
Sign includes age information and/or gender information；Second sending module 33 can be used for dish information corresponding with attributive character
Second is sent to order dishes equipment.
According to an exemplary embodiment of the present disclosure, with reference to Fig. 4, the second sending module 33 may include vegetable acquiring unit
401 and vegetable transmission unit 403.
Specifically, vegetable acquiring unit 401 can be used for obtaining the client for having attributive character from each information acquisition platform
The dish information of put vegetable；If the dish for the put vegetable of client that vegetable transmission unit 403 can be used for having attributive character
Product information meets default initial recommendation requirement, then dish information is sent to second and ordered dishes equipment.
According to an exemplary embodiment of the present disclosure, with reference to Fig. 5, vegetable recommendation apparatus 5 is compared to vegetable recommendation apparatus 2, also
It may include third sending module 51.
Specifically, third sending module 51 can be used for sending the corresponding dish information of the specialties of current slot
It orders dishes equipment to second.
According to an exemplary embodiment of the present disclosure, with reference to Fig. 6, vegetable recommendation apparatus 6 is compared to vegetable recommendation apparatus 2, also
It may include the 4th sending module 61.
Specifically, the 4th sending module 61 is determined for being selected number and all vegetables in a preset time by point
Several ratio, which is more than the vegetable of a default ratio, is sent to second as target vegetable, and by the corresponding dish information of target vegetable
It orders dishes equipment.
According to an exemplary embodiment of the present disclosure, the second dish information corresponds to the taste of vegetable, price, one in dish amount
Or multiple vegetables corresponding with the first dish information are similar.
According to an exemplary embodiment of the present disclosure, with reference to Fig. 7, dish information determining module 25 may include histogram building
Unit 701 and histogram similarity calculated 703.
Specifically, histogram construction unit 701 can be used for constructing the histogram of the first facial image as the first histogram
Figure, and the histogram of the second facial image is constructed as the second histogram；Histogram similarity calculated 703 can be used for counting
Calculate the similarity of the first histogram and the second histogram；Wherein, if the similarity of the first histogram and the second histogram is greater than
First preset threshold, then the second facial image is matched with the first facial image.
According to an exemplary embodiment of the present disclosure, with reference to Fig. 8, dish information determining module 25 may include that fisrt feature mentions
Take unit 801, second feature extraction unit 803 and characteristic similarity computing unit 805.
Specifically, fisrt feature extraction unit 801 can be used for extracting first using the convolutional neural networks after a training
The feature vector of facial image is as first eigenvector；Second feature extraction unit 803 can be used for using convolutional Neural net
Network extracts the feature vector of the second facial image as second feature vector；Characteristic similarity computing unit 805 can be used for counting
Calculate the cosine similarity of first eigenvector and second feature vector；Wherein, if calculated cosine similarity is greater than second
Preset threshold, then the second facial image is matched with the first facial image.
According to the vegetable recommendation apparatus based on living things feature recognition of the disclosure.On the one hand, the disclosure can be to eater
Personalized vegetable recommendation service is provided；On the other hand；Clicking operation for eater, without any menu
The vegetable being consistent with itself is obtained to recommend.
Since each functional module and the above method of the program analysis of running performance device of embodiment of the present invention are invented
It is identical in embodiment, therefore details are not described herein.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 9, describing the program product for realizing the above method of embodiment according to the present invention
900, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 1000 of this embodiment according to the present invention is described referring to Figure 10.The electricity that Figure 10 is shown
Sub- equipment 1000 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in Figure 10, electronic equipment 1000 is showed in the form of universal computing device.The component of electronic equipment 1000 can
To include but is not limited to: at least one above-mentioned processing unit 1010, connects not homologous ray at least one above-mentioned storage unit 1020
The bus 1030 of component (including storage unit 1020 and processing unit 1010), display unit 1040.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 1010
Row, so that various according to the present invention described in the execution of the processing unit 1010 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 1010 can execute step S12 as shown in fig. 1 to step
S18。
Storage unit 1020 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 10201 and/or cache memory unit 10202, it can further include read-only memory unit (ROM) 10203.
Storage unit 1020 can also include program/utility with one group of (at least one) program module 10205
10204, such program module 10205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 1030 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 1000 can also be with one or more external equipments 1100 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 1000 communicate, and/or with make
The electronic equipment 1000 can with it is one or more of the other calculating equipment be communicated any equipment (such as router, modulation
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 1050.Also, electronic equipment 1000
Network adapter 1060 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public affairs can also be passed through
Common network network, such as internet) communication.As shown, network adapter 1060 passes through its of bus 1030 and electronic equipment 1000
The communication of its module.It should be understood that although not shown in the drawings, other hardware and/or software can be used in conjunction with electronic equipment 1000
Module, including but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (10)
1. a kind of vegetable recommended method based on living things feature recognition characterized by comprising
Determine first order dishes equipment transmission the first facial image and the first vegetable corresponding with first facial image letter
Breath；
Obtain second order dishes equipment transmission the second facial image；
If second facial image is matched with first facial image, it is determined that similar with first dish information
Second dish information；
Second dish information is sent to described second to order dishes equipment.
2. vegetable recommended method according to claim 1, which is characterized in that first facial image is stored to a visitor
In the image library of family；Wherein, the vegetable recommended method further include:
If all faces in second facial image and the customer image library including first facial image
Image mismatches, it is determined that the attributive character of second facial image；Wherein, the attributive character includes age information
And/or gender information；
Dish information corresponding with the attributive character is sent to described second to order dishes equipment.
3. vegetable recommended method according to claim 2, which is characterized in that will vegetable letter corresponding with the attributive character
Breath is sent to the described second equipment of ordering dishes
The dish information for having the put vegetable of client of the attributive character is obtained from each information acquisition platform；
If the dish information of the put vegetable of client for having the attributive character meets default initial recommendation requirement, will
The dish information is sent to described second and orders dishes equipment.
4. vegetable recommended method according to any one of claim 1 to 3, which is characterized in that the vegetable recommended method
Further include:
The corresponding dish information of the specialties of current slot is sent to described second to order dishes equipment；And/or
It determines in a preset time and is selected the vegetable conduct that the ratio that number is selected number with all vegetables is more than a default ratio
Target vegetable, and the corresponding dish information of the target vegetable is sent to described second and is ordered dishes equipment.
5. vegetable recommended method according to claim 1, which is characterized in that second dish information corresponds to the mouth of vegetable
One or more of taste, price, dish amount vegetable corresponding with first dish information are similar.
6. vegetable recommended method according to claim 1, which is characterized in that the vegetable recommended method further include:
The histogram of first facial image is constructed as the first histogram, and constructs the histogram of second facial image
As the second histogram；
Calculate the similarity of first histogram Yu second histogram；
Wherein, if the similarity of first histogram and second histogram is greater than the first preset threshold, described the
Two facial images are matched with first facial image.
7. vegetable recommended method according to claim 1, which is characterized in that the vegetable recommended method further include:
The feature vector of first facial image is extracted as first eigenvector using the convolutional neural networks after a training；
The feature vector of second facial image is extracted as second feature vector using the convolutional neural networks；
Calculate the cosine similarity of the first eigenvector Yu the second feature vector；
Wherein, if calculated cosine similarity is greater than the second preset threshold, second facial image and described first
Facial image matching.
8. a kind of vegetable recommendation apparatus based on living things feature recognition characterized by comprising
First information determining module, for determine first order dishes equipment transmission the first facial image and with first face
Corresponding first dish information of image；
Second data obtaining module, for obtain second order dishes equipment transmission the second facial image；
Dish information determining module, if matched for second facial image with first facial image, it is determined that with
Similar second dish information of first dish information；
First sending module is ordered dishes equipment for second dish information to be sent to described second.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that the computer program is executed by processor
Vegetable recommended method described in Shi Shixian any one of claims 1 to 7 based on living things feature recognition.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to come described in any one of perform claim requirement 1 to 7 via the execution executable instruction
The vegetable recommended method based on living things feature recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910003253.7A CN109784026A (en) | 2019-01-03 | 2019-01-03 | Vegetable recommended method and device, medium and equipment based on living things feature recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910003253.7A CN109784026A (en) | 2019-01-03 | 2019-01-03 | Vegetable recommended method and device, medium and equipment based on living things feature recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109784026A true CN109784026A (en) | 2019-05-21 |
Family
ID=66499881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910003253.7A Pending CN109784026A (en) | 2019-01-03 | 2019-01-03 | Vegetable recommended method and device, medium and equipment based on living things feature recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109784026A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569384A (en) * | 2019-09-09 | 2019-12-13 | 深圳市乐福衡器有限公司 | AI scanning method |
| CN110570000A (en) * | 2019-07-31 | 2019-12-13 | 大众问问(北京)信息科技有限公司 | ordering method, device and equipment |
-
2019
- 2019-01-03 CN CN201910003253.7A patent/CN109784026A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570000A (en) * | 2019-07-31 | 2019-12-13 | 大众问问(北京)信息科技有限公司 | ordering method, device and equipment |
| CN110570000B (en) * | 2019-07-31 | 2022-04-26 | 大众问问(北京)信息科技有限公司 | Ordering method, device and equipment |
| CN110569384A (en) * | 2019-09-09 | 2019-12-13 | 深圳市乐福衡器有限公司 | AI scanning method |
| CN110569384B (en) * | 2019-09-09 | 2021-02-26 | 深圳市乐福衡器有限公司 | AI scanning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | “snap-n-eat” food recognition and nutrition estimation on a smartphone | |
| US9977980B2 (en) | Food logging from images | |
| US10474705B2 (en) | Iterative image search algorithm informed by continuous human-machine input feedback | |
| Mezgec et al. | Mixed deep learning and natural language processing method for fake-food image recognition and standardization to help automated dietary assessment | |
| CN107862018B (en) | Recommendation method and device for food cooking method | |
| US20190213416A1 (en) | Electronic device and method for processing information associated with food | |
| US20160063692A1 (en) | Automated Food Recognition and Nutritional Estimation With a Personal Mobile Electronic Device | |
| KR102209741B1 (en) | Electronic device and method for processing information associated with food | |
| US20140214618A1 (en) | In-store customer scan process including nutritional information | |
| KR102164652B1 (en) | Detailed Food Order System Using Chatbot | |
| CN110223757A (en) | The recommended method of recipe scheme, device, medium, electronic equipment | |
| CN109784185A (en) | Client's food and drink evaluation automatic obtaining method and device based on micro- Expression Recognition | |
| US10991029B2 (en) | Background content suggestion for combination with identified items | |
| CN115280422A (en) | Food recommendation method and device, storage medium and electronic equipment | |
| CN109784026A (en) | Vegetable recommended method and device, medium and equipment based on living things feature recognition | |
| CN117350825B (en) | Shopping guide method and system based on large language model | |
| CN107851183A (en) | System and method for providing recipe | |
| CN112464013A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN109683711B (en) | Product display method and device | |
| KR102326540B1 (en) | Methods for management of nutrition and disease using food images | |
| CN108876532A (en) | A kind of information processing method and device, electronic equipment, readable storage medium storing program for executing | |
| WO2020075418A1 (en) | Information processing device, information processing method, and program | |
| US20210217074A1 (en) | Systems and methods for providing a style recommendation | |
| JP2018082766A (en) | Diagnostic system, diagnostic method and program | |
| EP3929931A1 (en) | Dish nutritional value estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: Shenzhen one ledger Intelligent Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |