CN109583909A - Houseclearing discriminating method, device, equipment and medium based on image recognition - Google Patents
Houseclearing discriminating method, device, equipment and medium based on image recognition Download PDFInfo
- Publication number
- CN109583909A CN109583909A CN201811255694.8A CN201811255694A CN109583909A CN 109583909 A CN109583909 A CN 109583909A CN 201811255694 A CN201811255694 A CN 201811255694A CN 109583909 A CN109583909 A CN 109583909A
- Authority
- CN
- China
- Prior art keywords
- house
- houseclearing
- feature
- picture
- dwelling
- 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 42
- 238000003860 storage Methods 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 10
- 230000000717 retained effect Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 10
- 238000012790 confirmation Methods 0.000 description 6
- 230000008094 contradictory effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000013011 mating Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000011800 void material Substances 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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Finance (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of houseclearing discriminating method, device, computer equipment and storage medium based on image recognition, the present invention relates to field of image recognition, which comprises obtains the houseclearing in all houses in letting agency website;Houseclearing includes house picture;The house picture in same house is inputted into preset dwelling feature identification model, and image recognition is carried out to the house picture in the house by dwelling feature identification model, and obtain the output of dwelling feature identification model the house all house pictures in dwelling feature;Judge whether the houseclearing in the house is false according to the dwelling feature in the house;In falseness, house deceptive information is prompted.The present invention can judge whether houseclearing is false according to dwelling feature, and then prompt to need to look for by the letting agency website authenticity of the user in the room houseclearing;The time that user browses invalid room, false room information is shortened, the experience that user looks for room is greatly promoted.
Description
Technical field
The present invention relates to field of image recognition, and in particular to a kind of houseclearing discriminating method based on image recognition, dress
It sets, computer equipment and storage medium.
Background technique
Currently, the transaction due to house is frequent, house property medium is by letting agency website and looks for room APP (computer application
Program) houseclearing of house for sale is provided, in general, all can include house indoor in the houseclearing that letting agency provides
As-built information, geographical location, room construction of outdoor picture, house etc..But part letting agency is to attract user,
Houseclearing often is shown by the way of usurping other house pictures and the false house picture of manufacture, so that house
The phenomenon that actual conditions are not inconsistent with graph text information is very serious, and the experience for bringing user is very bad.And some letting agencies are
The authenticity for guaranteeing houseclearing, puts into a large amount of manpowers, using manually shooting picture, verification property ownership certificate, in time electricity at the scene
The house property information etc. of words and wechat tracking client, the cost paid are very high.
Summary of the invention
The embodiment of the present invention provide a kind of houseclearing discriminating method based on image recognition, device, computer equipment and
Storage medium, the present invention can shorten the time that user browses invalid room, false room information, greatly promote the body that user looks for room
It tests.
A kind of houseclearing discriminating method based on image recognition, comprising:
Obtain the houseclearing in all houses in letting agency website;The houseclearing includes house picture;
The house picture in same house is inputted into preset dwelling feature identification model, and passes through the dwelling feature
Identification model carries out image recognition to the house picture in the house, and obtains being somebody's turn to do for the dwelling feature identification model output
Dwelling feature in all house pictures in house;
Judge whether the houseclearing in the house is false according to the dwelling feature in the house;
When houseclearing in the house is false, house deceptive information is prompted.
A kind of houseclearing screening device based on image recognition, comprising:
Module is obtained, for obtaining the houseclearing in all houses in letting agency website;The houseclearing includes
House picture;
Identification module for the house picture in same house to be inputted preset dwelling feature identification model, and leads to
It crosses the dwelling feature identification model and image recognition is carried out to the house picture in the house, and obtain the dwelling feature and know
Dwelling feature in all house pictures in the house of other model output;
Judgment module judges whether the houseclearing in the house is false for the dwelling feature according to the house;
When cue module for the houseclearing in the house is false, house deceptive information is prompted.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer-readable instruction run on device, the processor are realized above-mentioned based on image knowledge when executing the computer-readable instruction
The step of other houseclearing discriminating method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer-readable instruction, institute
State the step of above-mentioned houseclearing discriminating method based on image recognition is realized when computer-readable instruction is executed by processor.
Houseclearing discriminating method, device, computer equipment and storage medium provided by the invention based on image recognition,
The houseclearing in letting agency website can be obtained automatically, and the house picture in houseclearing is carried out by image recognition
Identification, to extract the dwelling feature in the house picture, to judge that the houseclearing is according to the dwelling feature
No falseness, and then prompt to need to look for by the letting agency website authenticity of the user in the room houseclearing;Meanwhile the present invention
The repetition houseclearing in letting agency website can also be removed, the time that user browses invalid room, false room information is shortened,
Greatly promote the experience that user looks for room.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the application environment schematic diagram of the houseclearing discriminating method in one embodiment of the invention based on image recognition;
Fig. 2 is the flow chart of the houseclearing discriminating method in one embodiment of the invention based on image recognition;
Fig. 3 is the flow chart of the step S30 of the houseclearing discriminating method in one embodiment of the invention based on image recognition;
Fig. 4 is the process of the step S30 of the houseclearing discriminating method in further embodiment of this invention based on image recognition
Figure;
Fig. 5 is the process of the step S30 of the houseclearing discriminating method in yet another embodiment of the invention based on image recognition
Figure;
Fig. 6 is the flow chart of the houseclearing discriminating method in further embodiment of this invention based on image recognition;
Fig. 7 is the flow chart of the step S60 of the houseclearing discriminating method in one embodiment of the invention based on image recognition;
Fig. 8 is the process of the step S60 of the houseclearing discriminating method in further embodiment of this invention based on image recognition
Figure;
Fig. 9 is the functional block diagram of the houseclearing screening device in one embodiment of the invention based on image recognition;
Figure 10 is the principle of the judgment module of the houseclearing screening device in one embodiment of the invention based on image recognition
Block diagram;
Figure 11 is the original of the judgment module of the houseclearing screening device in further embodiment of this invention based on image recognition
Manage block diagram;
Figure 12 is the original of the judgment module of the houseclearing screening device in yet another embodiment of the invention based on image recognition
Manage block diagram;
Figure 13 is the functional block diagram of the houseclearing screening device in further embodiment of this invention based on image recognition;
Figure 14 is the principle of the deduplication module of the houseclearing screening device in one embodiment of the invention based on image recognition
Block diagram;
Figure 15 is the original of the deduplication module of the houseclearing screening device in further embodiment of this invention based on image recognition
Manage block diagram;
Figure 16 is the schematic diagram of computer equipment in one embodiment of the invention.
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 some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Houseclearing discriminating method provided by the invention based on image recognition, can be applicable in the application environment such as Fig. 1,
Wherein, client (computer equipment) is communicated by network with server.Wherein, client (computer equipment) include but
It is not limited to various personal computers, laptop, smart phone, tablet computer, camera and portable wearable device.
Server can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, a kind of houseclearing discriminating method based on image recognition is provided, with the party
Method is illustrated for applying the server in Fig. 1, comprising the following steps:
S10 obtains the houseclearing in all houses in letting agency website;The houseclearing includes house picture.
Wherein, the letting agency website refers to that (Application is calculated by the website for managing letting agency's business or APP
Machine application program).In the letting agency website, the houseclearing comprising multiple houses;Understandably, the institute in same house
There is the unique identification associated storage of houseclearing Yu the house.Wherein, the houseclearing includes the text in house picture and house
Word illustrates, the house picture refers to that the house framework, each room and premises perimeter for showing the house are mating etc.
Picture;The explanatory note in the house refers in the letting agency website for the house in addition to the house picture
Word segment introduction.
In the present embodiment, the false screening conditions reminded with duplicate removal can be increased in the letting agency website, such as
This enters in the step S10 when user selects the screening conditions of false prompting or duplicate removal in the screening conditions.
Preferably, the houseclearing for obtaining all houses in letting agency website specifically: climbed by network
Worm tool crawls the houseclearing in all houses from the letting agency website automatically.Wherein, the web crawlers kit
Include universal network crawler, focused web crawler, increment type web crawlers, one kind of Deep Web Crawler or in which several knots
It closes.;
The house picture in same house is inputted preset dwelling feature identification model, and passes through the house by S20
Feature identification model carries out image recognition to the house picture in the house, and obtains the dwelling feature identification model output
The house all house pictures in dwelling feature.
Wherein, the house picture in same house refers in letting agency website for the same house same
Display area show house picture set, if in the letting agency website, for the same room number house in difference
Display area or the different page occur that there are two different explanations.It is regarded as two different houses at this time (that is, being
Two repeat the house of explanation).
In the present embodiment, image recognition is carried out to the house picture by dwelling feature identification model trained in advance
To obtain the dwelling feature in each house picture, it will be appreciated that ground, the dwelling feature identification model can be exported corresponding to same
(for example, when dwelling feature is floor feature, the dwelling feature identification model can for the possibility probability of multiple types of dwelling feature
Can export the probability that floor is 7 layers is 98%, and floor is that 6 layers of probability is that 2%), server can be by the dwelling feature at this time
Multiple types the maximum type mark of probability value be the house picture in the house the dwelling feature, for example, building
Layer is 98% for 7 layers of probability, at this point, marking the floor feature in the house is 7 layers.Wherein, the training dwelling feature is known
The process of other model are as follows: obtain the house picture sample that multiple (such as 10,000) include same dwelling feature (including different type)
This, and according to the dwelling feature extracted from the house picture sample and the corresponding dwelling feature of house picture sample, instruction
Practice and obtains the dwelling feature identification model.
The dwelling feature includes the characteristics of image that can be embodied in house picture, such as: cell name is (for example, can
To identify cell name from the surrounding enviroment and cell environment figure in house picture), the floor sum described in the house
(floor sum can be identified from picture), house architectural features (are obviously identified by door, toilet, bed, the wall etc. in house
Identification house framework), the feature in each room be (for example, can know that the house is by the quantity of parlor and the door in other rooms
One Room of two rooms, one Room or a room), watermark feature (if the watermark in house image is not the watermark of the letting agency website,
Then illustrate that the house picture not instead of letting agency's number of website real is shot, steal figure), reproduction feature (the house picture
In whether have apparent reproduction lines) etc..The dwelling feature further includes the text being recorded in the text of the house picture
Word feature, the character features be mainly be recorded on each house picture for the house picture explanation (such as explanation should
House picture is the kitchen in the house, balcony, toilet etc.), it certainly also may include the specified otherwise etc. for the house.
S30 judges whether the houseclearing in the house is false according to the dwelling feature in the house.
That is, in the present embodiment, whether judging the houseclearing according to the dwelling feature in the house picture
Falseness, and then when houseclearing is false, user is prompted.
In one embodiment, the dwelling feature includes that the image in the house of the dwelling feature identification model output is special
Sign;As shown in figure 3, the step S30 namely the houseclearing for judging the house according to the dwelling feature in the house
It is whether false, comprising:
S301 obtains the characteristics of image in the dwelling feature in the house, and detecting whether there is in described image feature
Picture usurps feature or picture contradiction feature.
In the present embodiment, the dwelling feature includes the characteristics of image in the house picture.That is, in the present embodiment
Only by the characteristics of image in the dwelling feature come to the houseclearing, whether falseness judges.
The picture usurp feature refer to reproduction lines present in the characteristics of image of the dwelling feature or with the room
The watermark that room intermediary web site is not inconsistent.That is, in the dwelling feature not there are reproduction lines or with the letting agency website
When the watermark of symbol, illustrate the photo that the not described house property medium of the house picture is shot in person, reproduction is clapped from other people
The picture taken the photograph or the picture for directly usurping other websites, therefore there may be false contents for the houseclearing in the house.
The picture contradiction feature refers to that after carrying out image recognition to the house picture, the house of acquisition is special
In the characteristics of image of sign, there are self-contradictory dwelling features;For example, it is same that kitchen is obviously all shown in two house pictures
The cabinet of one position, but the different sample of cabinet in two house pictures.At this point, in the house picture at least one be
False.
S302 confirms the houseclearing in the house for falseness when usurping feature or picture contradiction feature there are picture.
That is, confirmation when usurping feature or picture contradiction feature there are picture in the step S301, the house at this time
Houseclearing may or certainly exist false content, at this time firstly the need of confirming that the houseclearing in the house is in this step
Falseness, and then user is prompted in the step S40.Further, in described image feature and be not present picture
When usurping feature or picture contradiction feature, can by the other embodiments of step S30 it is whether false to the houseclearing into
Row further judgement.
In one embodiment, the dwelling feature includes that the text in the house of the dwelling feature identification model output is special
It seeks peace characteristics of image;As shown in figure 4, the step S30 namely described judging the house according to the dwelling feature in the house
Houseclearing it is whether false, comprising:
S303 obtains character features and characteristics of image in the dwelling feature in the house, detects the dwelling feature
In the character features and described image feature it is whether consistent.
In the present embodiment, the dwelling feature includes the character features and characteristics of image in the house picture, this reality
It applies and needs to confirm jointly with the character features and described image feature whether the houseclearing is false in example.
Whether the character features detected in the dwelling feature are consistent with described image feature, refer to the detection room
The character features extracted in room picture and characteristics of image cell that is whether contradictory, such as being extracted in described image feature
Illustrate in title and room number and the character features it is not identical, at this point it is possible to judge that the houseclearing may be empty
False houseclearing.
S304 confirms the houseclearing in the house for void when the character features and described image feature are not consistent
It is false.
That is, at this time should when confirming that the character features and described image feature are not consistent in the step S303
The houseclearing in house may or certainly exist false content, at this time firstly the need of the house letter for confirming the house in this step
Breath is falseness, and then is prompted in the step S40 user.Further, in the character features and described image
When feature is consistent, it can further be judged by the way that whether the other embodiments of step S30 are false to the houseclearing.
In one embodiment, the dwelling feature includes that the text in the house of the dwelling feature identification model output is special
It seeks peace characteristics of image;The houseclearing further includes saying to the text in the house of extracting from the letting agency website
It is bright;Whether the information that the explanatory note in the house may include the current owner in the house (such as is red in hand, full five
It is unique etc.), the mating situation in periphery (the matched hospital in periphery, school, communal facility etc.), cell information (subdistrict position, house
The features such as affiliated number, unit, floor), the special circumstances in the house are illustrated.
As shown in figure 5, the step S30 namely the room for judging the house according to the dwelling feature in the house
Whether room information is false, comprising:
S305 obtains character features and characteristics of image in the dwelling feature in the house, while obtaining to the house
Explanatory note.
In the present embodiment, the dwelling feature includes the character features and characteristics of image in the house picture, this reality
Apply needed in example in the character features, described image feature and the letting agency website to the explanatory note in the house
Confirm whether the houseclearing is false jointly.
It is whether consistent with the explanatory note in the house to detect the character features in the dwelling feature by S306.
In the present embodiment, it is necessary first to detect in the character features extracted in house picture and the letting agency website
It is whether conflicting to the explanatory note in the house, that is, mentioned in text (i.e. character features) in the house picture
In cell name, house architecture diagram, room number, with the explanatory note in the house being recorded in the letting agency website not
When matching, judge the houseclearing in the house for false houseclearing.For example, illustrating that the house only has a room one in explanatory note
The Room, but show that the house is three living rooms and one sitting room in character features, at this point, the two is conflicting, the houseclearing exists empty
False place.
S307 when the explanatory note in the character features Yu the house is not consistent, confirms the houseclearing in the house
For falseness.
S308 detects the character features or the room when the character features are consistent with the explanatory note in the house
Whether the explanatory note in room is consistent with described image feature.
That is, when the character features are consistent with the explanatory note in the house, illustrate only by the character features with
Temporarily whether the fubaritic houseclearing is false for the explanatory note in the house, at this time can be by detecting the character features
Or the explanatory note in the house and described image feature it is whether consistent, it is whether false to the houseclearing carry out it is further
Judgement.At this point, being by image section (characteristics of image) and word segment (including the character features and room in the house picture
For the explanatory note in the house in room intermediary web site) it compares together, judge whether it is contradictory.
S309, when explanatory note and described image feature in the character features or the house are not consistent, confirmation
The houseclearing in the house is falseness.
That is, when the explanatory note and described image feature that find the character features or the house are contradictory, than
Such as, show that house includes two rooms, one Room in the described image feature in the house picture, but be recorded in letting agency's net
The explanatory note in the house in standing shows that the house is three rooms, two Room, in this way, the text in described image feature and the house is said
It is bright inconsistent, confirm the houseclearing in the house for falseness at this time.Further, the text in character features or the house is said
When bright consistent with described image feature, it can only pass through the figure in the dwelling feature according to the embodiment of step S301-S302
As feature is come to the houseclearing, whether falseness judges.
Preferably, if judging the houseclearing for not judging the house in above embodiments as falseness, by the house
Houseclearing labeled as true.
S40 when the houseclearing in the house is false, prompts house deceptive information.
That is, prompting user, when confirming that the houseclearing in the house is false in step S30 preferably, mentioning
Show the probability in content including houseclearing falseness, it at this time can be special according to the house in the house in the step S30
When sign judges whether the houseclearing in the house is false, the quantity of the false place in the houseclearing is recorded, and according to institute
State the probability that the quantity in place of falseness generates the houseclearing falseness;For example, when having at three in place of the falseness of houseclearing,
The probability that may determine that the houseclearing falseness is 90%.
Houseclearing discriminating method provided by the invention based on image recognition, can obtain automatically in letting agency website
Houseclearing, and the house picture in houseclearing is identified by image recognition, to extract in the house picture
Dwelling feature, to judge whether the houseclearing false according to the dwelling feature, and then prompt to need by should
The authenticity of the user in the room houseclearing is looked for website by letting agency;Meanwhile the present invention can also remove in letting agency website
Repetition houseclearing, shorten the time that user browses invalid room, false room information, greatly promote the experience that user looks for room.
In one embodiment, as shown in fig. 6, after the step S10 namely it is described obtain letting agency website in institute
There is the houseclearing in house;After the houseclearing includes house picture, comprising:
S50 detects whether the similar of the houseclearing that there are more than two houses in the letting agency website
Ratio is more than default similar threshold value.
That is, when the house for finding multiple (two or more) same house types in the letting agency website, and it is multiple
The houseclearing in house has high similarity, and (similar proportion of the houseclearing in more than two houses is more than to preset similar threshold
Value), then re-scheduling is filtered to multiple houses.
Wherein, the houseclearing in the step S50, including the text in the letting agency website for house
Illustrate, also includes after carrying out image recognition to the house picture in house, the house in the house picture of acquisition is special
It levies (including character features and characteristics of image).
S60, when the similar proportion for the houseclearing that there are more than two houses is more than default similar threshold value, according to
Default duplicate removal rule removes houseclearing corresponding at least one described house.
In one embodiment, as shown in fig. 7, in the step S60, the basis presets duplicate removal rule and removes at least one
Houseclearing corresponding to the house includes:
Whether the houseclearing of S601, the more than two houses of detection are falseness, if the houseclearing in the house is
Falseness then removes false houseclearing.That is, false houseclearing will be used as preferential duplicate removal object, if more than two institutes
The houseclearing in house is stated, it can be removed.
Understandably, when whether the houseclearing in the more than two houses of detection is falseness, it is referred to the above reality
Content described in step S10-S40 in example is applied, details are not described herein.
In one embodiment, as shown in figure 8, in the step S60, the basis presets duplicate removal rule and removes at least one
Houseclearing corresponding to the house includes:
S602 obtains the house picture in the houseclearing in more than two houses and from the letting agency
The integrity degree of the explanatory note to the house extracted in website;The integrity degree refers to the information preset in houseclearing
, the item of information includes house location information (location informations such as number, unit, floor belonging to house), cell information, week
The mating situation in side, house framework (house be several Rooms in several rooms), the house picture in each room in house framework and for each room
Between configuration illustrate.If more for above-mentioned each item of information typing, illustrate that the integrity degree of the houseclearing in the house is got over
Height, the highest houseclearing of integrity degree will be retained as houseclearing is retained, other will be by duplicate removal.
Understandably, the item of information in preset houseclearing, can extract from the explanatory note to the house,
It can also be obtained in the dwelling feature from the house picture through image recognition technology identification referring to the step S20,
This is repeated no more.
S603, by the highest houseclearing of the integrity degree of the house picture and the explanatory note, labeled as guarantor
Stay houseclearing;Further, if the integrity degree in two above the above house is the same, a work can be randomly selected at this time
To retain houseclearing;Or detection each item of information illustrates detailed degree, and illustrates the higher houseclearing of detailed degree, will make
Retained to retain houseclearing, other will be by duplicate removal.
S604 removes all rooms retained except houseclearing in the houseclearing in more than two houses
Room information.That is, in this step, duplicate houseclearing is carried out duplicate removal processing.
In one embodiment, the houseclearing further includes the explanatory note in house;After the step S10 further include:
Detect whether the letting agency website matches with the houseclearing in same house in other house property medium websites, and
When mismatching, the houseclearing in the current house of user is prompted not to be inconsistent with other websites.
That is, if there is the same house, the houseclearing in the house and another room in one of house property medium website
When producing the houseclearing mismatch in the house in intermediary web site, user's present case is prompted.
In one embodiment, as shown in figure 9, providing a kind of houseclearing screening device based on image recognition, this is based on
Houseclearing discriminating method one in the houseclearing screening device and above-described embodiment of image recognition based on image recognition is a pair of
It answers.The houseclearing screening device based on image recognition includes:
Module 110 is obtained, for obtaining the houseclearing in all houses in letting agency website;The houseclearing packet
Include house picture;
Identification module 120, for the house picture in same house to be inputted preset dwelling feature identification model, and
Image recognition is carried out by the house picture of the dwelling feature identification model to the house, and obtains the dwelling feature
Dwelling feature in all house pictures in the house of identification model output;
Judgment module 130 judges whether the houseclearing in the house is false for the dwelling feature according to the house;
When cue module 140 for the houseclearing in the house is false, house deceptive information is prompted.Invention provides
The houseclearing screening device based on image recognition, the houseclearing in letting agency website can be obtained automatically, and pass through
Image recognition identifies the house picture in houseclearing, to extract the dwelling feature in the house picture, thus root
Judge whether the houseclearing is false according to the dwelling feature, and then prompts to need to look for room by the letting agency website
The authenticity of user's houseclearing;Meanwhile the present invention can also remove the repetition houseclearing in letting agency website, shorten
User browses the time in invalid room, false room information, greatly promotes the experience that user looks for room.
In one embodiment, the dwelling feature includes that the image in the house of the dwelling feature identification model output is special
Sign;As shown in Figure 10, the judgment module 130 includes:
First acquisition submodule 131, the characteristics of image in the dwelling feature for obtaining the house, detects the figure
Feature or picture contradiction feature are usurped as whether there is picture in feature;
First confirmation submodule 132, for confirming the house when usurping feature or picture contradiction feature there are picture
Houseclearing is falseness.
In one embodiment, the dwelling feature includes that the text in the house of the dwelling feature identification model output is special
It seeks peace characteristics of image;As shown in figure 11, the judgment module 130 includes:
Second acquisition submodule 133, the character features and characteristics of image in the dwelling feature for obtaining the house,
It detects character features in the dwelling feature and whether described image feature is consistent;
Second confirmation submodule 134, for confirming the room when the character features and described image feature are not consistent
The houseclearing in room is falseness.
In one embodiment, the dwelling feature includes that the text in the house of the dwelling feature identification model output is special
It seeks peace characteristics of image;The houseclearing further includes saying to the text in the house of extracting from the letting agency website
It is bright;As shown in figure 12, the judgment module 130 includes:
Third acquisition submodule 135, the character features and characteristics of image in the dwelling feature for obtaining the house,
The explanatory note to the house is obtained simultaneously;
First detection sub-module 136, for detecting the text of the character features in the dwelling feature Yu the house
Whether consistent illustrate;
Third confirms submodule 137, when not consistent for the explanatory note in the character features Yu the house, confirmation
The houseclearing in the house is falseness;
Second detection sub-module 138, for when the character features are consistent with the explanatory note in the house, described in detection
Whether the explanatory note in character features or the house and described image feature are consistent;
4th confirmation submodule 139, in the character features or the house explanatory note and described image it is special
When levying not consistent, confirm the houseclearing in the house for falseness.
In one embodiment, as shown in figure 13, described device further include:
Detection module 150, the room in the letting agency website, detecting whether to there are more than two houses
The similar proportion of room information is more than default similar threshold value;
Deduplication module 160, for being more than default phase in the similar proportion for the houseclearing that there are more than two houses
When like threshold value, according to default duplicate removal rule remove at least one described house corresponding to houseclearing.
In one embodiment, as shown in figure 14, the deduplication module 160 includes:
Third detection sub-module 161, whether the houseclearing for detecting more than two houses is falseness, if described
The houseclearing in house is falseness, then removes false houseclearing.
In one embodiment, as shown in figure 15, the deduplication module 160 includes:
Third acquisition submodule 162, the house picture in houseclearing for obtaining more than two houses
And the integrity degree of the explanatory note to the house extracted from the letting agency website;
Submodule 163 is marked, for by the highest house of the integrity degree of the house picture and the explanatory note
Information, labeled as reservation houseclearing;
Submodule 164 is removed, for removing the reservation houseclearing in the houseclearing in more than two houses
Except all houseclearings.
Specific restriction about the houseclearing screening device based on image recognition may refer to above for based on figure
As the restriction of the houseclearing discriminating method of identification, details are not described herein.The above-mentioned houseclearing based on image recognition screens dress
Modules in setting can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be in the form of hardware
It is embedded in or independently of the storage that in the processor in computer equipment, can also be stored in a software form in computer equipment
In device, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in figure 16.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium be stored with operating system, computer-readable instruction and
Database.The built-in storage provides ring for the operation of operating system and computer-readable instruction in non-volatile memory medium
Border.To realize a kind of houseclearing discriminating method based on image recognition when the computer-readable instruction is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer-readable instruction that can be run on a processor, processor perform the steps of when executing computer-readable instruction
Obtain the houseclearing in all houses in letting agency website;The houseclearing includes house picture;
The house picture in same house is inputted into preset dwelling feature identification model, and passes through the dwelling feature
Identification model carries out image recognition to the house picture in the house, and obtains being somebody's turn to do for the dwelling feature identification model output
Dwelling feature in all house pictures in house;
Judge whether the houseclearing in the house is false according to the dwelling feature in the house;
When houseclearing in the house is false, house deceptive information is prompted.
Computer equipment provided by the invention can obtain the houseclearing in letting agency website automatically, and pass through figure
The house picture in houseclearing is identified as identifying, to extract the dwelling feature in the house picture, thus according to
The dwelling feature judges whether the houseclearing is false, and then prompts to need to look for by the letting agency website use in room
The authenticity of the family houseclearing;Meanwhile the present invention can also remove the repetition houseclearing in letting agency website, shorten
User browses the time in invalid room, false room information, greatly promotes the experience that user looks for room.
In one embodiment, a kind of computer readable storage medium is provided, computer-readable instruction is stored thereon with,
It is performed the steps of when computer-readable instruction is executed by processor
Obtain the houseclearing in all houses in letting agency website;The houseclearing includes house picture;
The house picture in same house is inputted into preset dwelling feature identification model, and passes through the dwelling feature
Identification model carries out image recognition to the house picture in the house, and obtains being somebody's turn to do for the dwelling feature identification model output
Dwelling feature in all house pictures in house;
Judge whether the houseclearing in the house is false according to the dwelling feature in the house;
When houseclearing in the house is false, house deceptive information is prompted.
Computer readable storage medium provided by the invention can obtain the houseclearing in letting agency website automatically,
And the house picture in houseclearing is identified by image recognition, to extract the dwelling feature in the house picture,
To judge whether the houseclearing is false according to the dwelling feature, and then prompt to need through the letting agency website
Look for the authenticity of the user in the room houseclearing;Meanwhile the present invention can also remove the letter of the repetition house in letting agency website
Breath shortens the time that user browses invalid room, false room information, greatly promotes the experience that user looks for room.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer-readable instruction, it is non-volatile that the computer-readable instruction can be stored in one
Property computer-readable storage medium in, the computer-readable instruction is when being executed, it may include as above-mentioned each method embodiment
Process.Wherein, to memory, storage, database or other media used in each embodiment provided by the present invention
Any reference may each comprise non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.It is volatile
Property memory may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM
It is available in many forms, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link DRAM (SLDRAM), the direct RAM of memory bus (RDRAM),
Direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit or module division progress for example, in practical application, can according to need and by above-mentioned function distribution by difference
Functional unit or module complete, i.e., the internal structure of described device is divided into different functional unit or module, with complete
All or part of function described above.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of houseclearing discriminating method based on image recognition characterized by comprising
Obtain the houseclearing in all houses in letting agency website;The houseclearing includes house picture;
The house picture in same house is inputted into preset dwelling feature identification model, and is identified by the dwelling feature
Model carries out image recognition to the house picture in the house, and obtains the house of the dwelling feature identification model output
All house pictures in dwelling feature;The houseclearing for judging the house according to the dwelling feature in the house is
No falseness;
When houseclearing in the house is false, house deceptive information is prompted.
2. the houseclearing discriminating method based on image recognition as described in claim 1, which is characterized in that the dwelling feature
The characteristics of image in the house including dwelling feature identification model output;
The dwelling feature according to the house judges whether the houseclearing in the house is false, comprising:
The characteristics of image in the dwelling feature in the house is obtained, detects in described image feature and usurps spy with the presence or absence of picture
Sign or picture contradiction feature;
When usurping feature or picture contradiction feature there are picture, confirm the houseclearing in the house for falseness.
3. the houseclearing based on image recognition discriminates method for distinguishing as described in claim 1, which is characterized in that the dwelling feature
The character features and characteristics of image in the house including dwelling feature identification model output;
The dwelling feature according to the house judges whether the houseclearing in the house is false, comprising:
The character features and characteristics of image in the dwelling feature in the house are obtained, the text in the dwelling feature is detected
Whether word feature is consistent with described image feature;
When the character features and described image feature are not consistent, confirm the houseclearing in the house for falseness.
4. the houseclearing discriminating method based on image recognition as claimed in claim 3, which is characterized in that the dwelling feature
The character features and characteristics of image in the house including dwelling feature identification model output;The houseclearing further includes certainly
The explanatory note to the house extracted in the letting agency website;
The dwelling feature according to the house judges whether the houseclearing in the house is false, comprising:
The character features and characteristics of image in the dwelling feature in the house are obtained, while obtaining and the text in the house is said
It is bright;
It is whether consistent with the explanatory note in the house to detect the character features in the dwelling feature;
When explanatory note in the character features Yu the house is not consistent, confirm the houseclearing in the house for falseness;
When the character features are consistent with the explanatory note in the house, the text for detecting the character features or the house is said
It is bright whether consistent with described image feature;
When explanatory note and described image feature in the character features or the house are not consistent, the room in the house is confirmed
Room information is falseness.
5. the houseclearing discriminating method based on image recognition as described in claim 1, which is characterized in that the acquisition house
The houseclearing in all houses in intermediary web site;After the houseclearing includes house picture, comprising:
In the letting agency website, detect whether that the similar proportion that there is the houseclearing in more than two houses is more than
Default similar threshold value;
When the similar proportion for the houseclearing that there are more than two houses is more than default similar threshold value, according to default duplicate removal
Rule removes houseclearing corresponding at least one described house.
6. the houseclearing discriminating method based on image recognition as claimed in claim 5, which is characterized in that the basis is default
Duplicate removal rule removes houseclearing corresponding at least one described house
Whether the houseclearing in the more than two houses of detection is that falseness is gone if the houseclearing in the house is falseness
Except false houseclearing.
7. the houseclearing discriminating method based on image recognition as claimed in claim 5, which is characterized in that the basis is default
Duplicate removal rule removes houseclearing corresponding at least one described house
It obtains the house picture in the houseclearing in more than two houses and is mentioned from the letting agency website
The integrity degree of the explanatory note to the house taken;
By the highest houseclearing of the integrity degree of the house picture and the explanatory note, believe labeled as house is retained
Breath;
In the houseclearing in more than two houses, all houseclearings retained except houseclearing are removed.
8. a kind of houseclearing screening device based on image recognition characterized by comprising
Module is obtained, for obtaining the houseclearing in all houses in letting agency website;The houseclearing includes house
Picture;
Identification module for the house picture in same house to be inputted preset dwelling feature identification model, and passes through institute
It states dwelling feature identification model and image recognition is carried out to the house picture in the house, and obtain the dwelling feature identification mould
Dwelling feature in all house pictures in the house of type output;
Judgment module judges whether the houseclearing in the house is false for the dwelling feature according to the house;
When cue module for the houseclearing in the house is false, house deceptive information is prompted.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer-readable instruction of upper operation, which is characterized in that the processor is realized when executing the computer-readable instruction as weighed
Benefit requires the step of houseclearing discriminating method described in 1 to 7 any one based on image recognition.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer-readable instruction, special
Sign is, realizes when the computer-readable instruction is executed by processor and is known as described in any one of claim 1 to 7 based on image
The step of other houseclearing discriminating method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811255694.8A CN109583909A (en) | 2018-10-26 | 2018-10-26 | Houseclearing discriminating method, device, equipment and medium based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811255694.8A CN109583909A (en) | 2018-10-26 | 2018-10-26 | Houseclearing discriminating method, device, equipment and medium based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109583909A true CN109583909A (en) | 2019-04-05 |
Family
ID=65920848
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811255694.8A Pending CN109583909A (en) | 2018-10-26 | 2018-10-26 | Houseclearing discriminating method, device, equipment and medium based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109583909A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111383032A (en) * | 2020-02-12 | 2020-07-07 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
CN112036521A (en) * | 2020-11-09 | 2020-12-04 | 北京沃东天骏信息技术有限公司 | Information consistency detection method, device, equipment and storage medium |
CN113706173A (en) * | 2021-08-31 | 2021-11-26 | 北京五八信息技术有限公司 | Information management method and device, electronic equipment and storage medium |
CN113947676A (en) * | 2021-09-30 | 2022-01-18 | 北京五八信息技术有限公司 | Information processing method and device, electronic equipment and storage medium |
CN116958795A (en) * | 2023-06-30 | 2023-10-27 | 北京房多多信息技术有限公司 | Method and device for identifying flip image, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150032482A1 (en) * | 2013-07-29 | 2015-01-29 | Independent Mitigation and Cleaning/Conservation Network, Inc. | Claim summary and claim watch system and method |
CN106504137A (en) * | 2015-09-03 | 2017-03-15 | 中山市八喜电脑网络有限公司 | Network false information of real estate prosecution system |
CN107749019A (en) * | 2017-10-20 | 2018-03-02 | 上海犀木信息技术有限公司 | A kind of houseclearing gathering system |
KR20180036083A (en) * | 2016-09-30 | 2018-04-09 | 주식회사 유브이알 | Method and system for preventing a registration of a fraudulent product for sale |
-
2018
- 2018-10-26 CN CN201811255694.8A patent/CN109583909A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150032482A1 (en) * | 2013-07-29 | 2015-01-29 | Independent Mitigation and Cleaning/Conservation Network, Inc. | Claim summary and claim watch system and method |
CN106504137A (en) * | 2015-09-03 | 2017-03-15 | 中山市八喜电脑网络有限公司 | Network false information of real estate prosecution system |
KR20180036083A (en) * | 2016-09-30 | 2018-04-09 | 주식회사 유브이알 | Method and system for preventing a registration of a fraudulent product for sale |
CN107749019A (en) * | 2017-10-20 | 2018-03-02 | 上海犀木信息技术有限公司 | A kind of houseclearing gathering system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111383032A (en) * | 2020-02-12 | 2020-07-07 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
CN111383032B (en) * | 2020-02-12 | 2023-11-14 | 北京城市网邻信息技术有限公司 | Method and device for detecting authenticity of house source information |
CN112036521A (en) * | 2020-11-09 | 2020-12-04 | 北京沃东天骏信息技术有限公司 | Information consistency detection method, device, equipment and storage medium |
CN112036521B (en) * | 2020-11-09 | 2021-10-01 | 北京沃东天骏信息技术有限公司 | Information consistency detection method, device, equipment and storage medium |
CN113706173A (en) * | 2021-08-31 | 2021-11-26 | 北京五八信息技术有限公司 | Information management method and device, electronic equipment and storage medium |
CN113947676A (en) * | 2021-09-30 | 2022-01-18 | 北京五八信息技术有限公司 | Information processing method and device, electronic equipment and storage medium |
CN116958795A (en) * | 2023-06-30 | 2023-10-27 | 北京房多多信息技术有限公司 | Method and device for identifying flip image, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109583909A (en) | Houseclearing discriminating method, device, equipment and medium based on image recognition | |
JP5747116B1 (en) | Security system | |
Lombard | Using auto‐photography to understand place: reflections from research in urban informal settlements in Mexico | |
US20090064321A1 (en) | Methods for Providing User Authentication in a Computer Network or System | |
Ruez | “Partitioning the sensible” at Park 51: Ranciére, Islamophobia, and common politics | |
JP2015114828A (en) | Information processing apparatus and information processing program | |
Schreiber | The undocumented everyday: Migrant lives and the politics of visibility | |
JP6523688B2 (en) | Housing information disclosure system and housing information disclosure method using the housing information disclosure system | |
CN107230140A (en) | House lease and vending method and system | |
WO2019200737A1 (en) | Real estate data uploading method and apparatus, computer device, and storage medium | |
KR102462571B1 (en) | Method, server and system for managing building defect | |
CN108446654A (en) | A kind of face recognition method based on image | |
KR102248706B1 (en) | System for intergrated education management based on intelligent image analysis technology and method thereof | |
CN116881967A (en) | Privacy protection method, device and equipment | |
Osorio | Numbers under fire: The challenges of gathering quantitative data in highly violent settings | |
Fast | Dream homes and dead ends in the city: a photo essay experiment | |
AU2019338200A1 (en) | Image management with region-based metadata indexing | |
Young | Seeing like a border city: Refugee politics at the borders of city and nation-state | |
Brigham et al. | Law in politics: Struggles over property and public space on New York City's Lower East Side | |
Van Laun | Bureaucratically missing: Capital punishment, exhumations, and the afterlives of state documents and photographs | |
Conotter et al. | A crowdsourced data set of edited images online | |
Selvaggio | URME Surveillance: performing privilege in the face of automation | |
JPWO2019172326A1 (en) | Information providing devices, information providing methods, programs, and recording media | |
Kagona et al. | STUDENTS’ATTENDANCE MANAGEMENT IN HIGHER INSTITUTIONS USING AZURE COGNITIVE SERVICE AND OPENCV FACE DETECTION & RECOGNITION ATTENDANCE SYSTEM | |
CN111404809B (en) | Method for acquiring unified management authority of intelligent equipment |
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 |