CN109902713A - Building recommended method, equipment, storage medium and device based on data analysis - Google Patents
Building recommended method, equipment, storage medium and device based on data analysis Download PDFInfo
- Publication number
- CN109902713A CN109902713A CN201910047134.1A CN201910047134A CN109902713A CN 109902713 A CN109902713 A CN 109902713A CN 201910047134 A CN201910047134 A CN 201910047134A CN 109902713 A CN109902713 A CN 109902713A
- Authority
- CN
- China
- Prior art keywords
- building
- target
- recommended
- information
- data analysis
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 230000014509 gene expression Effects 0.000 description 8
- 229910052742 iron Inorganic materials 0.000 description 7
- 235000012054 meals Nutrition 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of building recommended method, equipment, storage medium and devices based on data analysis, this method comprises: obtaining multiple target requirement information of target user, target requirement information is ranked up from big to small according to target weight, obtains list of requirements；The target requirement information of the preset quantity of front will be come in list of requirements as target dimensions；The building information to be recommended for obtaining multiple buildings to be recommended scores to each building to be recommended from target dimensions according to building information to be recommended, and each building to be recommended of acquisition is corresponding to estimate building score value；Target building is chosen from building to be recommended according to preset rules according to building score value is estimated, and target building information is pushed into target user.It is analyzed based on data, building to be recommended is scored according to user demand as dimensions, and recommend target building to improve efficiency and accuracy that building is recommended so that the target building recommended more meets user demand to user based on scoring.
Description
Technical field
The present invention relates to the technical field of data processing more particularly to it is a kind of based on data analysis building recommended method,
Equipment, storage medium and device.
Background technique
Currently, the mode that building is recommended all is to judge building quality according to building information by manual analysis building information,
Building is manually recommended into user, efficiency is lower, standard also disunity, the building many times recommended and user demand matching degree
Also not high, poor user experience.Therefore, the efficiency and accuracy for how improving building recommendation are a technical problem to be solved urgently.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of building recommended methods based on data analysis, equipment, storage medium
And device, it is intended to the low technical problem of solution building is recommended in the prior art low efficiency and accuracy.
To achieve the above object, the present invention provides a kind of building recommended method based on data analysis, described to be based on data
The building recommended method of analysis the following steps are included:
Multiple target requirement information of target user are obtained, from big to small according to target weight by the target requirement information
It is ranked up, obtains list of requirements；
The target requirement information of the preset quantity of front will be come in the list of requirements as target dimensions；
The building information to be recommended for obtaining multiple buildings to be recommended is commented according to the building information to be recommended from the target
Fractional dimension scores to each building to be recommended, and each building to be recommended of acquisition is corresponding to estimate building score value；
It estimates building score value according to described and chooses target building from the building to be recommended according to preset rules, and by institute
It states the corresponding target building information of target building and pushes to the target user.
Preferably, the multiple target requirement information for obtaining target user, by the target requirement information according to target
Weight is ranked up from big to small, obtains list of requirements, comprising:
The multiple target requirement information for obtaining target user, cluster the target requirement information, obtain multiple need
Seek cluster；
Each demand cluster is ranked up from big to small according to the target weight, obtains by the target weight for obtaining each demand cluster
Obtain list of requirements；
The target requirement information of the preset quantity that front will be come in the list of requirements as target dimensions,
Include:
The demand cluster of the preset quantity of front will be come in the list of requirements as target dimensions.
Preferably, the building score value of estimating includes the corresponding target dimension score value of each target dimensions；
It is described to estimate building score value according to and choose target building from the building to be recommended according to preset rules, and
The corresponding target building information of the target building is pushed into the target user, comprising:
According to the corresponding target dimension score value of each target dimensions and the target weight, each building to be recommended is calculated
The target score of disk；
The highest building to be recommended of the target score is chosen from the building to be recommended as target building, and by institute
It states the corresponding target building information of target building and pushes to the target user.
Preferably, the building information to be recommended for obtaining multiple buildings to be recommended, according to the building information to be recommended
It scoring from the target dimensions each building to be recommended, each building to be recommended of acquisition is corresponding to estimate building score value,
Include:
The building information to be recommended for obtaining multiple buildings to be recommended passes through default scoring according to the building information to be recommended
Model scores to each building to be recommended from the target dimensions, obtains the corresponding building of estimating of each building to be recommended and divides
Value.
Preferably, the building information to be recommended for obtaining multiple buildings to be recommended, according to the building information to be recommended
It is scored from the target dimensions each building to be recommended by default Rating Model, it is corresponding to obtain each building to be recommended
Estimate building score value before, it is described based on data analysis building recommended method further include:
History building Transaction Information is obtained, the history building of each history building is extracted from the history building Transaction Information
Disk information and corresponding history building score value；
The sample scoring number of history dimensions is generated according to the history building information and corresponding history building score value
According to；
Convolutional neural networks model is trained according to the sample score data, default comment is obtained according to training result
Sub-model.
Preferably, the target weight for obtaining each demand cluster, from big to small according to the target weight by each demand cluster
It is ranked up, obtains list of requirements, comprising:
Transmit weight parameter options are to target UE, so that the target user is selected based on the weight parameter option
Select the target weight of each demand cluster；
The target weight for receiving each demand cluster that the target UE is sent, each demand cluster is weighed according to the target
Weight is ranked up from big to small, obtains list of requirements.
Preferably, the multiple target requirement information for obtaining target user, cluster the target requirement information,
Obtain multiple demand clusters, comprising:
The multiple target requirement information for obtaining target user, calculate the similarity between each target requirement information；
Each target requirement information is clustered by affine propagation clustering algorithm according to the similarity, obtains multiple need
Seek cluster.
In addition, to achieve the above object, the present invention also proposes a kind of building recommendation apparatus based on data analysis, the base
Include memory, processor and be stored on the memory and can be in the processor in the building recommendation apparatus of data analysis
Upper operation based on data analysis building recommended program, it is described based on data analysis building recommended program be arranged for carrying out as
The step of building recommended method based on data analysis described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, it is stored with and is based on the storage medium
The building recommended program of data analysis, the building recommended program based on data analysis are realized when being executed by processor as above
The step of described building recommended method based on data analysis.
In addition, to achieve the above object, the present invention also proposes a kind of building recommendation apparatus based on data analysis, the base
Include: in the building recommendation apparatus of data analysis
Module is obtained, for obtaining multiple target requirement information of target user, by the target requirement information according to mesh
Mark weight is ranked up from big to small, obtains list of requirements；
Module is chosen, for the target requirement information using the preset quantity of front is come in the list of requirements as target
Dimensions；
Grading module is believed for obtaining the building information to be recommended of multiple buildings to be recommended according to the building to be recommended
Breath scores to each building to be recommended from the target dimensions, obtains the corresponding building of estimating of each building to be recommended and divides
Value；
Pushing module chooses mesh from the building to be recommended according to preset rules for estimating building score value according to
Building is marked, and the corresponding target building information of the target building is pushed into the target user.
In the present invention, by obtaining multiple target requirement information of target user, by the target requirement information according to mesh
Mark weight is ranked up from big to small, obtains list of requirements, the target of the preset quantity of front will be come in the list of requirements
Demand information obtains the building information to be recommended of multiple buildings to be recommended, according to the building to be recommended as target dimensions
Disk information scores to each building to be recommended from the target dimensions, and each building to be recommended of acquisition is corresponding to estimate building
Score value is analyzed based on data, building to be recommended is scored according to user demand as dimensions, without artificial right one by one
Each building to be recommended is analyzed, and each building data analysis efficiency is improved, so that improving building recommends efficiency；It is estimated according to described
Building score value chooses target building according to preset rules from the building to be recommended, and by the corresponding target of the target building
Building information pushes to the target user, recommends target building to user based on scoring, so that the target building recommended more accords with
User demand is closed, the accuracy that building is recommended is improved.
Detailed description of the invention
Fig. 1 is the building recommendation apparatus based on data analysis for the hardware running environment that the embodiment of the present invention is related to
Structural schematic diagram；
Fig. 2 is the flow diagram for the building recommended method first embodiment analyzed the present invention is based on data；
Fig. 3 is the flow diagram for the building recommended method second embodiment analyzed the present invention is based on data；
Fig. 4 is the flow diagram for the building recommended method 3rd embodiment analyzed the present invention is based on data；
Fig. 5 is the structural block diagram for the building recommendation apparatus first embodiment analyzed the present invention is based on data.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is that the building based on data analysis for the hardware running environment that the embodiment of the present invention is related to pushes away
Recommend device structure schematic diagram.
As shown in Figure 1, should may include: processor 1001, such as centre based on the building recommendation apparatus that data are analyzed
It manages device (Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, storage
Device 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include showing
Display screen (Display), optional user interface 1003 can also include standard wireline interface and wireless interface, for user interface
1003 wireline interface can be USB interface in the present invention.Network interface 1004 optionally may include standard wireline interface,
Wireless interface (such as Wireless Fidelity (WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random of high speed
Memory (Random Access Memory, RAM) memory is accessed, stable memory (Non-volatile is also possible to
Memory, NVM), such as magnetic disk storage.Memory 1005 optionally can also be the storage independently of aforementioned processor 1001
Device.
It is pushed away it will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted to based on the building that data are analyzed
The restriction for recommending equipment may include perhaps combining certain components or different component cloth than illustrating more or fewer components
It sets.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and the building recommended program based on data analysis.
In building recommendation apparatus based on data analysis shown in Fig. 1, network interface 1004 is mainly used for connection backstage
Server carries out data communication with the background server；User interface 1003 is mainly used for connecting user equipment；It is described to be based on
The building recommendation apparatus of data analysis calls the building based on data analysis stored in memory 1005 by processor 1001
Recommended program, and execute the building recommended method provided in an embodiment of the present invention based on data analysis.
Based on above-mentioned hardware configuration, the embodiment for the building recommended method analyzed the present invention is based on data is proposed.
Referring to Fig. 2, Fig. 2 is the flow diagram for the building recommended method first embodiment analyzed the present invention is based on data,
It is proposed that the present invention is based on the building recommended method first embodiments that data are analyzed.
In the first embodiment, it is described based on data analysis building recommended method the following steps are included:
Step S10: multiple target requirement information of target user are obtained, by the target requirement information according to target weight
It is ranked up from big to small, obtains list of requirements.
It should be understood that the executing subject of the present embodiment is the building recommendation apparatus based on data analysis, wherein institute
Stating the building recommendation apparatus based on data analysis can be the electronic equipments such as PC or server.The target user is often referred to
There are a personnel of house-purchase demand, the target requirement information is that the target user is mating to the house of purchase and periphery etc.
Demand, for example, near-earth iron, traffic convenience, shopping it is convenient and have a meal conveniently, public bus network mostly with the information such as school district room.It can be preparatory
The demand information of a large number of users is carried out the pretreatment such as duplicate removal, generates the acquisition of house-purchase demand by the demand information for obtaining a large number of users
List, by sending the user equipment of the house-purchase demand acquisition list to the target user, so that target user's base
In the target requirement information that the house-purchase list of requirements selects oneself to pay close attention to, to collect multiple targets of the target user
Demand information.
It in the concrete realization, can be by the way that multiple weight parameter options be arranged to each target requirement information, by the weight
Parameter options are shown, and are selected for the target user, to obtain the target weight；Alternatively, in the house-purchase demand
Each demand information is corresponding in acquisition list shows the weight parameter option, then user can be based on house-purchase demand acquisition column
The multiple demand informations and the weight parameter option listed in table are selected, and the target weight is obtained.The weight ginseng
Number option can be identified by score value, such as: 100% indicates the important demand of very important demand, 80% expression, 60% table
Show that important demand, 40% indicate general important demand and 20% expression general requirements.It can also be more choosings
Item setting or the setting of other options, the present embodiment are without restriction to this.
Step S20: the target requirement information that the preset quantity of front will be come in the list of requirements scores as target
Dimension.
It will be appreciated that some edge demands are to building if the quantity of the target requirement information of the target user is various
Screening reference value it is not high, can be not considered, the user demand that the preset quantity of front is come in the list of requirements is
The target user compares the demand of concern, as scoring point, can more embody the actual demand of the target user.It is described
List of requirements is ranked up from big to small according to the target weight, illustrates to come the important journey of the target requirement information of more front
It spends higher, then can will come the target requirement information of the preset quantity of front in the list of requirements as target dimensions,
So that the target requirement for the preset quantity that the scoring of building to be recommended can most be paid close attention to from the target user is commented
Point, each building to be recommended of acquisition estimates building score value and can embody the target requirement that the target user compares concern.
In the concrete realization, the preset quantity can be according to the target requirement information content in the list of requirements come really
It is fixed, for example, setting 3 for the preset quantity when target requirement quantity in the list of requirements is more than or equal to 3；Institute
It, can be directly using the target requirement quantity in the list of requirements as institute when stating the target requirement quantity in list of requirements less than 3
Preset quantity is stated, the preset quantity can also be configured according to previous empirical value, and the present embodiment is without restriction to this.
For example, the target requirement in the list of requirements is successively are as follows: school district room, near-earth iron, convenient and shopping of having a meal
Convenient, the preset quantity is set as 3, then can facilitate school district room, near-earth iron and having a meal as the target dimensions.
Step S30: obtaining the building information to be recommended of multiple buildings to be recommended, according to the building information to be recommended from institute
It states target dimensions to score to each building to be recommended, each building to be recommended of acquisition is corresponding to estimate building score value.
It should be noted that the building to be recommended is usually city or the target user where the target user
The building on sale in specified purchase city.The building information to be recommended includes the title of building, the geographical location of building, counterpart
School, the plot ratio of building, the specific location in every building and the auxiliary facility of the number of plies, the traffic condition on periphery and periphery in building
Etc. information.By matching the target requirement information of the target user with the building information to be recommended, described in acquisition
Matching degree between target requirement information and each building information to be recommended.Specifically, by the building information to be recommended according to institute
It states target dimensions to classify, obtains the corresponding dimension building information of each target dimensions, each target scores respectively
The dimension building information and target requirement information of dimension are matched, to obtain the dimension building information of each target dimensions
And the matching degree between target requirement information, it can be using the matching degree as the dimension of the target dimensions of each building to be recommended
Score value, the dimension score values of each target dimensions constitute described in estimate building score value.The matching degree is higher, illustrates to correspond to
Building to be recommended most matched with the demand of the target user, can be using the highest building to be recommended of the matching degree as target
Building pushes to the target user.
It should be understood that can also be by establishing basic model, the basic model can be convolutional neural networks model etc.,
A large amount of history building Transaction Information is obtained, the history building of each history building is extracted from the history building Transaction Information
Information and corresponding history building score value can analyze the history building information and the history building score value, by institute
It states history building and the corresponding history building score value is classified according to history dimensions, obtain history dimensions
Sample score data, the sample score data include the history dimension building information and corresponding history of each history dimensions
Dimension score value.And the sample score data is inputted into the convolutional neural networks model and is trained, it is obtained according to training result
Rating Model must be preset, then can be scored and be tieed up from the target according to the building information to be recommended by the default Rating Model
Degree scores to each building to be recommended, obtains that each building to be recommended is corresponding to estimate building score value, described to estimate building score value
Including the corresponding target dimension score value of each target dimensions.
Step S40: it estimates building score value according to described and chooses target building from the building to be recommended according to preset rules
Disk, and the corresponding target building information of the target building is pushed into the target user.
In the concrete realization, if by the matching between the dimension building information and target requirement information of each target dimensions
The dimension score value of the target dimensions as each building to be recommended is spent, the dimension score value of each target dimensions constitutes institute
It states and estimates building score value, the preset rules can be using the highest building to be recommended of the matching degree as the target building
Disk.If by the default Rating Model according to the building information to be recommended from the target dimensions to each building to be recommended
Disk scores, and each building to be recommended of acquisition is corresponding to estimate building score value, and the building score value of estimating includes each target scoring
The corresponding target dimension score value of dimension can calculate the corresponding target dimension score value of each target dimensions and the target weight
The target score of each building to be recommended, the preset rules can be using the highest building to be recommended of the target score as institute
State target building.The target building is the most matched building to be recommended of actual demand with the target user, then can obtain
The target building information is pushed to the target user, so that the target by the target building information of the target building
User is based on the target building information and understands in depth to the target building.
In the present embodiment, by obtain target user multiple target requirement information, by the target requirement information according to
Target weight is ranked up from big to small, obtains list of requirements, the mesh of the preset quantity of front will be come in the list of requirements
Demand information is marked as target dimensions, the building information to be recommended of multiple buildings to be recommended is obtained, according to described to be recommended
Building information scores to each building to be recommended from the target dimensions, and each building to be recommended of acquisition is corresponding to estimate building
Disk score value is analyzed based on data, building to be recommended is scored according to user demand as dimensions, is not necessarily to manually one by one
Each building to be recommended is analyzed, each building data analysis efficiency is improved, so that improving building recommends efficiency；According to described pre-
Estimate building score value and choose target building from the building to be recommended according to preset rules, and by the corresponding mesh of the target building
Mark building information pushes to the target user, recommends target building to user based on scoring, so that the target building recommended is more
Meet user demand, improves the accuracy that building is recommended.
Referring to Fig. 3, Fig. 3 is the flow diagram for the building recommended method second embodiment analyzed the present invention is based on data,
Based on above-mentioned first embodiment shown in Fig. 2, the second embodiment for the building recommended method analyzed the present invention is based on data is proposed.
In a second embodiment, the step S10, comprising:
Step S101: multiple target requirement information of target user are obtained, the target requirement information is clustered, is obtained
Obtain multiple demand clusters.
It will be appreciated that usually have several target requirement information expressions in the target requirement information is a kind of demand class
Type can then cluster the target requirement information, obtain multiple demand clusters.For example, near-earth iron, traffic convenience and public transport line
Multiple target requirement information about traffic such as road can cluster as a demand cluster: traffic convenience.The demand cluster may include:
Have a good transport service, school district room, plot ratio are low and monovalent 10,000 within etc..
Step S102: obtaining the target weight of each demand cluster, by each demand cluster according to the target weight from big to small into
Row sequence, obtains list of requirements.
It should be understood that in order to enable the actual demand of user can be more in line with to the scoring of each building to be recommended, it can
By carrying out data interaction with the target user, the target weight of each demand cluster is obtained.It can be to the setting pair of each demand cluster
The weight parameter option is sent to the target UE of the target user, the target by the weight parameter option answered
User equipment can be smart phone, personal computer, tablet computer or laptop etc., specifically can be logical by mail etc.
It interrogates class application and pushes the corresponding weight parameter option of each demand cluster, so that the target user is selected based on the weight parameter
Type is chosen, and the corresponding target weight of each demand cluster is obtained.The weight parameter option can be identified by score value, than
Such as: 100% indicates that the important demand of the important demand of very important demand, 80% expression, 60% expression, 40% indicate
General important demand and 20% expression general requirements.It can also be more option settings or the setting of other options, this
Embodiment is without restriction to this.The building recommendation apparatus based on data analysis receives the target UE and sends
Each demand cluster target weight, the target weight reflects the significance level of each demand cluster, and the target weight is bigger, explanation
Significance level is higher, then can be ranked up from big to small each demand cluster according to the target weight, obtain the list of requirements.
In the present embodiment, the step S102, comprising: Transmit weight parameter options to target UE, so that the target user
The target weight of each demand cluster is selected based on the weight parameter option；Receive each demand cluster that the target UE is sent
Target weight, each demand cluster is ranked up from big to small according to the target weight, obtain list of requirements.
In a second embodiment, the step S20, comprising:
Step S201: the demand cluster of the preset quantity of front will be come in the list of requirements as target dimensions.
In the concrete realization, if the quantity of the demand cluster of the target user is various, sieve of some edge demands to building
It selects reference value not high, can be not considered, the demand cluster that the preset quantity of front is come in the list of requirements is the mesh
The demand that mark user compares concern can more embody the actual demand of the target user as dimensions.The demand
List is ranked up from big to small according to the target weight, and the significance level for illustrating to come the more demand cluster of front is higher, then
The demand cluster of the preset quantity of front can will be come in the list of requirements as the target dimensions, so as to be recommended
The demand cluster for the preset quantity that the scoring of building can most be paid close attention to from the target user scores, acquisition respectively wait push away
Recommend estimating building score value and capable of embodying the target requirement that the target user compares concern for building.The preset quantity can root
Determined according to the quantity of the demand cluster in the list of requirements, for example, the demand number of clusters amount in the list of requirements be greater than etc.
When 3,3 are set by the preset quantity；It, can be directly by the demand when demand cluster in the list of requirements is less than 3
As the preset quantity, the preset quantity can also be configured demand cluster in list according to previous empirical value, this
Embodiment is without restriction to this.
In a second embodiment, the building score value of estimating includes the corresponding target dimension score value of each target dimensions,
The step S40, comprising:
Step S401: it according to the corresponding target dimension score value of each target dimensions and the target weight, calculates
The target score of each building to be recommended.
It should be understood that by the corresponding target dimension score value of each target dimensions respectively multiplied by the corresponding mesh
Weight is marked, and is added up each product obtained is calculated, the target score of each building to be recommended is obtained.
Such as: the target dimensions is have a good transport service, school district room and plot ratio are low, and each target dimensions are corresponding
The target weight is followed successively by 80%, 60% and 40%, each target dimensions total score is 100 points, the building to be recommended
Including building A to be recommended, building B to be recommended and building C to be recommended.The corresponding target dimension score value point of building A to be recommended
Wei not be 80 points, 80 points and 60 points, the corresponding target dimension score value of building B to be recommended is respectively 80 points, 60 points and 60 points, to
Recommending the corresponding target dimension score value of building C is respectively 60 points, 80 points and 80 points.The target score of building A to be recommended are as follows:
80*80%+80*60%+60*40%=152 points, the target score of building A to be recommended are as follows: 80*80%+60*60%+60*
40%=124 points, the target score of building C to be recommended are as follows: 60*80%+80*60%+80*40%=128 points.
Step S402: the highest building to be recommended of the target score is chosen from the building to be recommended as target building
Disk, and the corresponding target building information of the target building is pushed into the target user.
It should be noted that the highest building to be recommended of target score is the practical need for being best suitable for the target user
The building asked then is chosen the highest building to be recommended of the target score from the building to be recommended and is pushed as target building
To the target user, the accuracy of building recommendation can be improved, promote user experience.Obtain the corresponding institute of the target building
State target building information, the target building information include the title of the target building, the target building geographical location,
The counterpart school of the target building, the plot ratio of the target building, in the target building specific location in every building and
The information such as the auxiliary facility of the number of plies, the traffic condition on target building periphery and periphery.The target building information is pushed away
It send to the target user, so that the target user understands the target building in depth, to decide whether to buy
The target building.
For example, in the above example, in building A, the building B to be recommended and the building C to be recommended to be recommended
In, the target score 152 of the building A to be recommended is divided for highest, can be using the building A to be recommended as the target building
Disk, obtains the building information of the building A to be recommended, and the building information of the building A to be recommended is sent to the target
User.
In a second embodiment, the demand cluster that the preset quantity of front will be come in the list of requirements scores as target
Dimension, so that the demand cluster for the preset quantity that the scoring of building to be recommended can most be paid close attention to from the target user is commented
Point, each building to be recommended of acquisition estimates building score value and can embody the target requirement that the target user compares concern；Root
According to the corresponding target dimension score value of each target dimensions and the target weight, the target point of each building to be recommended is calculated
Value, chooses the highest building to be recommended of the target score as target building from the building to be recommended, and by the mesh
The corresponding target building information of mark building pushes to the target user, and the highest building to be recommended of target score is most to accord with
The building of the actual demand of the target user is closed, the accuracy that building is recommended is improved, promotes user experience.
Referring to Fig. 4, Fig. 4 is the flow diagram for the building recommended method 3rd embodiment analyzed the present invention is based on data,
Based on above-mentioned second embodiment shown in Fig. 3, the 3rd embodiment for the building recommended method analyzed the present invention is based on data is proposed.
In the third embodiment, the step S30, comprising:
Step S301: obtaining the building information to be recommended of multiple buildings to be recommended, logical according to the building information to be recommended
It crosses default Rating Model to score to each building to be recommended from the target dimensions, it is corresponding to obtain each building to be recommended
Estimate building score value.
It should be understood that the building to be recommended is usually that city or the target user where the target user refer to
Order the building on sale for buying city.The building information to be recommended includes the title of building, the geographical location of building, counterpart
School, the plot ratio of building, the specific location in every building and the auxiliary facility of the number of plies, the traffic condition on periphery and periphery in building
Etc. information.It can be by establishing basic model, the basic model can be convolutional neural networks model etc., obtain a large amount of history
Building Transaction Information extracts the history building information of each history building from the history building Transaction Information and corresponding goes through
History building score value can analyze the history building information and the history building score value, by the history building and right
The history building score value answered is classified according to history dimensions, obtains the sample score data of history dimensions,
The sample score data include each history dimensions history dimension building information and corresponding history dimension score value.And it will
The sample score data inputs the convolutional neural networks model and is trained, and obtains default scoring mould according to training result
Type, then can by the default Rating Model according to the building information to be recommended from the target dimensions to each to be recommended
Building scores, and each building to be recommended of acquisition is corresponding to estimate building score value, and the building score value of estimating includes that each target is commented
The corresponding target dimension score value of fractional dimension.In the present embodiment, before the step S301, further includes: obtain the transaction of history building
Information extracts the history building information and corresponding history building point of each history building from the history building Transaction Information
Value；The sample score data of history dimensions is generated according to the history building information and corresponding history building score value；Root
Convolutional neural networks model is trained according to the sample score data, default Rating Model is obtained according to training result.
In the third embodiment, the step S101, comprising:
The multiple target requirement information for obtaining target user, calculate the similarity between each target requirement information；
Each target requirement information is clustered by affine propagation clustering algorithm according to the similarity, obtains multiple need
Seek cluster.
It will be appreciated that can segment to each target requirement information, the TF-IDF value of word is calculated as word feature, it will be each
Target requirement information is expressed as term vector, calculates the COS distance between term vector as similar between each target requirement information
Degree.TF-IDF is actually: TF*IDF, TF word frequency (Term Frequency), the reverse document-frequency (Inverse of IDF
Document Frequency)。
It should be noted that affine propagation clustering (Affinity Propagation, the AP) algorithm, is according to data
Similarity between point is clustered, and can be symmetrical, is also possible to asymmetric.The affine propagation clustering algorithm is not
It needs first to determine the number of cluster, but all data points is all regarded as the cluster centre on potential significance.According to each similar
Degree can construct similarity matrix, and using each target requirement information as node, the similarity between each target requirement information is as square
Then the value of battle array is clustered by AP algorithm, obtains multiple demand clusters.
In the third embodiment, the building information to be recommended for obtaining multiple buildings to be recommended, according to the building to be recommended
Information scores to each building to be recommended from the target dimensions by default Rating Model, obtains each building to be recommended
It is corresponding to estimate building score value, it is based on machine learning, can be improved the accuracy and efficiency of scoring, to improve building recommendation
Accuracy and efficiency.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is stored on the storage medium and is analyzed based on data
Building recommended program, it is described based on data analysis building recommended program be executed by processor when realize base as described above
In data analysis building recommended method the step of.
In addition, the embodiment of the present invention also proposes a kind of building recommendation apparatus based on data analysis, the base referring to Fig. 5
Include: in the building recommendation apparatus of data analysis
Obtain module 10, for obtaining multiple target requirement information of target user, by the target requirement information according to
Target weight is ranked up from big to small, obtains list of requirements；
Module 20 is chosen, for the target requirement information using the preset quantity of front is come in the list of requirements as mesh
Mark dimensions；
Grading module 30, for obtaining the building information to be recommended of multiple buildings to be recommended, according to the building to be recommended
Information scores to each building to be recommended from the target dimensions, obtains the corresponding building of estimating of each building to be recommended and divides
Value；
Pushing module 40 is chosen from the building to be recommended for estimating building score value according to according to preset rules
Target building, and the corresponding target building information of the target building is pushed into the target user.
It should be understood that the target user is often referred to the personnel of house-purchase demand, the target requirement information is described
Target user's demand mating to the house of purchase and periphery etc., for example, near-earth iron, traffic convenience, shopping is convenient and eats
Meal is convenient, public bus network mostly with the information such as school district room.The demand information that a large number of users can be obtained in advance, by the demand of a large number of users
Information carries out the pretreatment such as duplicate removal, generates house-purchase demand acquisition list, by sending the house-purchase demand acquisition list to described
The user equipment of target user, so that the target requirement that the target user selects oneself to pay close attention to based on the house-purchase list of requirements
Information, to collect multiple target requirement information of the target user.
It in the concrete realization, can be by the way that multiple weight parameter options be arranged to each target requirement information, by the weight
Parameter options are shown, and are selected for the target user, to obtain the target weight；Alternatively, in the house-purchase demand
Each demand information is corresponding in acquisition list shows the weight parameter option, then user can be based on house-purchase demand acquisition column
The multiple demand informations and the weight parameter option listed in table are selected, and the target weight is obtained.The weight ginseng
Number option can be identified by score value, such as: 100% indicates the important demand of very important demand, 80% expression, 60% table
Show that important demand, 40% indicate general important demand and 20% expression general requirements.It can also be more choosings
Item setting or the setting of other options, the present embodiment are without restriction to this.
It will be appreciated that some edge demands are to building if the quantity of the target requirement information of the target user is various
Screening reference value it is not high, can be not considered, the user demand that the preset quantity of front is come in the list of requirements is
The target user compares the demand of concern, as scoring point, can more embody the actual demand of the target user.It is described
List of requirements is ranked up from big to small according to the target weight, illustrates to come the important journey of the target requirement information of more front
It spends higher, then can will come the target requirement information of the preset quantity of front in the list of requirements as target dimensions,
So that the target requirement for the preset quantity that the scoring of building to be recommended can most be paid close attention to from the target user is commented
Point, each building to be recommended of acquisition estimates building score value and can embody the target requirement that the target user compares concern.
In the concrete realization, the preset quantity can be according to the target requirement information content in the list of requirements come really
It is fixed, for example, setting 3 for the preset quantity when target requirement quantity in the list of requirements is more than or equal to 3；Institute
It, can be directly using the target requirement quantity in the list of requirements as institute when stating the target requirement quantity in list of requirements less than 3
Preset quantity is stated, the preset quantity can also be configured according to previous empirical value, and the present embodiment is without restriction to this.
For example, the target requirement in the list of requirements is successively are as follows: school district room, near-earth iron, convenient and shopping of having a meal
Convenient, the preset quantity is set as 3, then can facilitate school district room, near-earth iron and having a meal as the target dimensions.
It should be noted that the building to be recommended is usually city or the target user where the target user
The building on sale in specified purchase city.The building information to be recommended includes the title of building, the geographical location of building, counterpart
School, the plot ratio of building, the specific location in every building and the auxiliary facility of the number of plies, the traffic condition on periphery and periphery in building
Etc. information.By matching the target requirement information of the target user with the building information to be recommended, described in acquisition
Matching degree between target requirement information and each building information to be recommended.Specifically, by the building information to be recommended according to institute
It states target dimensions to classify, obtains the corresponding dimension building information of each target dimensions, each target scores respectively
The dimension building information and target requirement information of dimension are matched, to obtain the dimension building information of each target dimensions
And the matching degree between target requirement information, it can be using the matching degree as the dimension of the target dimensions of each building to be recommended
Score value, the dimension score values of each target dimensions constitute described in estimate building score value.The matching degree is higher, illustrates to correspond to
Building to be recommended most matched with the demand of the target user, can be using the highest building to be recommended of the matching degree as target
Building pushes to the target user.
It should be understood that can also be by establishing basic model, the basic model can be convolutional neural networks model etc.,
A large amount of history building Transaction Information is obtained, the history building of each history building is extracted from the history building Transaction Information
Information and corresponding history building score value can analyze the history building information and the history building score value, by institute
It states history building and the corresponding history building score value is classified according to history dimensions, obtain history dimensions
Sample score data, the sample score data include the history dimension building information and corresponding history of each history dimensions
Dimension score value.And the sample score data is inputted into the convolutional neural networks model and is trained, it is obtained according to training result
Rating Model must be preset, then can be scored and be tieed up from the target according to the building information to be recommended by the default Rating Model
Degree scores to each building to be recommended, obtains that each building to be recommended is corresponding to estimate building score value, described to estimate building score value
Including the corresponding target dimension score value of each target dimensions.
In the concrete realization, if by the matching between the dimension building information and target requirement information of each target dimensions
The dimension score value of the target dimensions as each building to be recommended is spent, the dimension score value of each target dimensions constitutes institute
It states and estimates building score value, the preset rules can be using the highest building to be recommended of the matching degree as the target building
Disk.If by the default Rating Model according to the building information to be recommended from the target dimensions to each building to be recommended
Disk scores, and each building to be recommended of acquisition is corresponding to estimate building score value, and the building score value of estimating includes each target scoring
The corresponding target dimension score value of dimension can calculate the corresponding target dimension score value of each target dimensions and the target weight
The target score of each building to be recommended, the preset rules can be using the highest building to be recommended of the target score as institute
State target building.The target building is the most matched building to be recommended of actual demand with the target user, then can obtain
The target building information is pushed to the target user, so that the target by the target building information of the target building
User is based on the target building information and understands in depth to the target building.
In the present embodiment, by obtain target user multiple target requirement information, by the target requirement information according to
Target weight is ranked up from big to small, obtains list of requirements, the mesh of the preset quantity of front will be come in the list of requirements
Demand information is marked as target dimensions, the building information to be recommended of multiple buildings to be recommended is obtained, according to described to be recommended
Building information scores to each building to be recommended from the target dimensions, and each building to be recommended of acquisition is corresponding to estimate building
Disk score value is analyzed based on data, building to be recommended is scored according to user demand as dimensions, is not necessarily to manually one by one
Each building to be recommended is analyzed, each building data analysis efficiency is improved, so that improving building recommends efficiency；According to described pre-
Estimate building score value and choose target building from the building to be recommended according to preset rules, and by the corresponding mesh of the target building
Mark building information pushes to the target user, recommends target building to user based on scoring, so that the target building recommended is more
Meet user demand, improves the accuracy that building is recommended.
In one embodiment, the building recommendation apparatus based on data analysis further include:
Cluster module gathers the target requirement information for obtaining multiple target requirement information of target user
Class obtains multiple demand clusters；
Sorting module, for obtaining the target weight of each demand cluster, by each demand cluster according to the target weight from greatly to
It is small to be ranked up, obtain list of requirements；
The selection module 20 is also used to the demand cluster using the preset quantity of front is come in the list of requirements as mesh
Mark dimensions.
In one embodiment, the building score value of estimating includes the corresponding target dimension score value of each target dimensions；
The building recommendation apparatus based on data analysis further include:
Computing module is used for according to the corresponding target dimension score value of each target dimensions and the target weight,
Calculate the target score of each building to be recommended；
The pushing module 40 is also used to choose the highest building to be recommended of the target score from the building to be recommended
Disk pushes to the target user as target building, and by the corresponding target building information of the target building.
In one embodiment, institute's scoring module 30 is also used to obtain the building information to be recommended of multiple buildings to be recommended,
Each building to be recommended is commented from the target dimensions by default Rating Model according to the building information to be recommended
Point, each building to be recommended of acquisition is corresponding to estimate building score value.
In one embodiment, the building recommendation apparatus based on data analysis further include:
Extraction module is extracted from the history building Transaction Information and is respectively gone through for obtaining history building Transaction Information
The history building information of history building and corresponding history building score value；
Generation module, for generating history dimensions according to the history building information and corresponding history building score value
Sample score data；
Training module, for being trained according to the sample score data to convolutional neural networks model, according to training
As a result default Rating Model is obtained.
In one embodiment, the building recommendation apparatus based on data analysis further include:
Sending module, for Transmit weight parameter options to target UE, so that the target user is based on described
Weight parameter option selects the target weight of each demand cluster；
The sorting module is also used to receive the target weight for each demand cluster that the target UE is sent, will be each
Demand cluster is ranked up from big to small according to the target weight, obtains list of requirements.
In one embodiment, the computing module is also used to obtain multiple target requirement information of target user, calculates each
Similarity between target requirement information；
The cluster module is also used to each target requirement information according to the similarity through affine propagation clustering algorithm
It is clustered, obtains multiple demand clusters.
The other embodiments or specific implementation of building recommendation apparatus of the present invention based on data analysis can refer to
Above-mentioned each method embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.If listing equipment for drying
Unit claim in, several in these devices, which can be, to be embodied by the same item of hardware.Word first,
Second and the use of third etc. do not indicate any sequence, can be mark by these word explanations.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
(such as read-only memory mirror image (Read Only Memory image, ROM)/random access memory (Random Access
Memory, RAM), magnetic disk, CD) in, including some instructions are used so that terminal device (can be mobile phone, computer,
Server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of building recommended method based on data analysis, which is characterized in that the building recommendation side based on data analysis
Method the following steps are included:
The multiple target requirement information for obtaining target user, the target requirement information is carried out from big to small according to target weight
Sequence obtains list of requirements；
The target requirement information of the preset quantity of front will be come in the list of requirements as target dimensions；
The building information to be recommended for obtaining multiple buildings to be recommended scores from the target according to the building information to be recommended and ties up
Degree scores to each building to be recommended, and each building to be recommended of acquisition is corresponding to estimate building score value；
It estimates building score value according to described and chooses target building from the building to be recommended according to preset rules, and by the mesh
The corresponding target building information of mark building pushes to the target user.
2. the building recommended method as described in claim 1 based on data analysis, which is characterized in that the acquisition target user
Multiple target requirement information, the target requirement information is ranked up from big to small according to target weight, obtain demand column
Table, comprising:
The multiple target requirement information for obtaining target user, cluster the target requirement information, obtain multiple demand clusters；
Each demand cluster is ranked up from big to small according to the target weight, is needed by the target weight for obtaining each demand cluster
Ask list；
The target requirement information of the preset quantity that front will be come in the list of requirements is as target dimensions, packet
It includes:
The demand cluster of the preset quantity of front will be come in the list of requirements as target dimensions.
3. the building recommended method as claimed in claim 2 based on data analysis, which is characterized in that described to estimate building score value
Including the corresponding target dimension score value of each target dimensions；
It is described to estimate building score value according to and choose target building from the building to be recommended according to preset rules, and by institute
It states the corresponding target building information of target building and pushes to the target user, comprising:
According to the corresponding target dimension score value of each target dimensions and the target weight, each building to be recommended is calculated
Target score；
The highest building to be recommended of the target score is chosen from the building to be recommended as target building, and by the mesh
The corresponding target building information of mark building pushes to the target user.
4. the building recommended method as claimed in claim 3 based on data analysis, which is characterized in that the acquisition is multiple wait push away
The building information to be recommended for recommending building, according to the building information to be recommended from the target dimensions to each building to be recommended
It scores, each building to be recommended of acquisition is corresponding to estimate building score value, comprising:
The building information to be recommended for obtaining multiple buildings to be recommended, according to the building information to be recommended by presetting Rating Model
It scores from the target dimensions each building to be recommended, each building to be recommended of acquisition is corresponding to estimate building score value.
5. the building recommended method as claimed in claim 4 based on data analysis, which is characterized in that the acquisition is multiple wait push away
The building information to be recommended for recommending building is scored from the target by default Rating Model according to the building information to be recommended and is tieed up
Degree scores to each building to be recommended, described to be based on data before obtaining that each building to be recommended is corresponding and estimating building score value
The building recommended method of analysis further include:
History building Transaction Information is obtained, the history building letter of each history building is extracted from the history building Transaction Information
Breath and corresponding history building score value；
The sample score data of history dimensions is generated according to the history building information and corresponding history building score value；
Convolutional neural networks model is trained according to the sample score data, default scoring mould is obtained according to training result
Type.
6. the building recommended method based on data analysis as described in any one of claim 2-5, which is characterized in that described to obtain
Each demand cluster is ranked up by the target weight for taking each demand cluster from big to small according to the target weight, obtains list of requirements,
Include:
Transmit weight parameter options are to target UE, so that the target user is based on weight parameter option selection respectively
The target weight of demand cluster；
The target weight for receiving each demand cluster that the target UE is sent, by each demand cluster according to the target weight from
Arrive greatly it is small be ranked up, obtain list of requirements.
7. the building recommended method as claimed in claim 6 based on data analysis, which is characterized in that the acquisition target user
Multiple target requirement information, the target requirement information is clustered, multiple demand clusters are obtained, comprising:
The multiple target requirement information for obtaining target user, calculate the similarity between each target requirement information；
Each target requirement information is clustered by affine propagation clustering algorithm according to the similarity, obtains multiple demands
Cluster.
8. a kind of building recommendation apparatus based on data analysis, which is characterized in that the building recommendation based on data analysis is set
It is standby to include: memory, processor and be stored on the memory and what be run on the processor is analyzed based on data
Building recommended program, it is described based on data analysis building recommended program is executed by the processor when realize such as claim
Described in any one of 1 to 7 based on data analysis building recommended method the step of.
9. a kind of storage medium, which is characterized in that the building recommended program based on data analysis is stored on the storage medium,
The building recommended program based on data analysis is realized as described in any one of claims 1 to 7 when being executed by processor
Based on data analysis building recommended method the step of.
10. a kind of building recommendation apparatus based on data analysis, which is characterized in that the building based on data analysis recommends dress
It sets and includes:
Module is obtained to weigh the target requirement information according to target for obtaining multiple target requirement information of target user
Weight is ranked up from big to small, obtains list of requirements；
Module is chosen, for the target requirement information for coming the preset quantity of front in the list of requirements to score as target
Dimension；
Grading module, for obtaining the building information to be recommended of multiple buildings to be recommended, according to the building information to be recommended from
The target dimensions score to each building to be recommended, and each building to be recommended of acquisition is corresponding to estimate building score value；
Pushing module chooses target building according to preset rules for estimating building score value according to from the building to be recommended
Disk, and the corresponding target building information of the target building is pushed into the target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910047134.1A CN109902713A (en) | 2019-01-17 | 2019-01-17 | Building recommended method, equipment, storage medium and device based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910047134.1A CN109902713A (en) | 2019-01-17 | 2019-01-17 | Building recommended method, equipment, storage medium and device based on data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109902713A true CN109902713A (en) | 2019-06-18 |
Family
ID=66943827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910047134.1A Pending CN109902713A (en) | 2019-01-17 | 2019-01-17 | Building recommended method, equipment, storage medium and device based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109902713A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080407A (en) * | 2019-12-04 | 2020-04-28 | 青梧桐有限责任公司 | House information recommendation method and device, electronic equipment and readable storage medium |
| CN111125556A (en) * | 2019-12-25 | 2020-05-08 | 青梧桐有限责任公司 | Recommendation sorting method and system, electronic device and readable storage medium |
| CN111143714A (en) * | 2019-12-25 | 2020-05-12 | 青梧桐有限责任公司 | Recommendation sorting method and system, electronic device and readable storage medium |
| CN111292170A (en) * | 2020-02-18 | 2020-06-16 | 重庆锐云科技有限公司 | Method, device and storage medium for recommending intention customers for appointed building |
| CN111861514A (en) * | 2020-07-30 | 2020-10-30 | 北京车薄荷科技有限公司 | Personnel recommendation method and personnel recommendation system |
| CN112435091A (en) * | 2020-11-23 | 2021-03-02 | 百果园技术(新加坡)有限公司 | Recommended content selection method, device, equipment and storage medium |
| CN113205383A (en) * | 2021-05-07 | 2021-08-03 | 中山市云经纪网络科技有限公司 | Intelligent house property recommendation method and system |
| CN113962584A (en) * | 2021-10-29 | 2022-01-21 | 重庆汇集源科技有限公司 | Building community rating system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101146288A (en) * | 2007-09-24 | 2008-03-19 | 中兴通讯股份有限公司 | A SMS mobile search method and system |
| CN102737029A (en) * | 2011-04-02 | 2012-10-17 | 腾讯科技（深圳）有限公司 | Searching method and system |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN106649647A (en) * | 2016-12-09 | 2017-05-10 | 北京百度网讯科技有限公司 | Ordering method and device for search results based on artificial intelligence |
-
2019
- 2019-01-17 CN CN201910047134.1A patent/CN109902713A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101146288A (en) * | 2007-09-24 | 2008-03-19 | 中兴通讯股份有限公司 | A SMS mobile search method and system |
| CN102737029A (en) * | 2011-04-02 | 2012-10-17 | 腾讯科技（深圳）有限公司 | Searching method and system |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN106649647A (en) * | 2016-12-09 | 2017-05-10 | 北京百度网讯科技有限公司 | Ordering method and device for search results based on artificial intelligence |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080407A (en) * | 2019-12-04 | 2020-04-28 | 青梧桐有限责任公司 | House information recommendation method and device, electronic equipment and readable storage medium |
| CN111125556A (en) * | 2019-12-25 | 2020-05-08 | 青梧桐有限责任公司 | Recommendation sorting method and system, electronic device and readable storage medium |
| CN111143714A (en) * | 2019-12-25 | 2020-05-12 | 青梧桐有限责任公司 | Recommendation sorting method and system, electronic device and readable storage medium |
| CN111292170A (en) * | 2020-02-18 | 2020-06-16 | 重庆锐云科技有限公司 | Method, device and storage medium for recommending intention customers for appointed building |
| CN111861514A (en) * | 2020-07-30 | 2020-10-30 | 北京车薄荷科技有限公司 | Personnel recommendation method and personnel recommendation system |
| CN111861514B (en) * | 2020-07-30 | 2023-09-12 | 北京车薄荷科技有限公司 | Personnel recommendation method and personnel recommendation system |
| CN112435091A (en) * | 2020-11-23 | 2021-03-02 | 百果园技术(新加坡)有限公司 | Recommended content selection method, device, equipment and storage medium |
| CN112435091B (en) * | 2020-11-23 | 2024-03-29 | 百果园技术(新加坡)有限公司 | Recommended content selection method, device, equipment and storage medium |
| CN113205383A (en) * | 2021-05-07 | 2021-08-03 | 中山市云经纪网络科技有限公司 | Intelligent house property recommendation method and system |
| CN113962584A (en) * | 2021-10-29 | 2022-01-21 | 重庆汇集源科技有限公司 | Building community rating system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902713A (en) | Building recommended method, equipment, storage medium and device based on data analysis | |
| EP3893154A1 (en) | Recommendation model training method and related apparatus | |
| CN102073699B (en) | For improving the method for Search Results, device and equipment based on user behavior | |
| JP5827416B2 (en) | User question processing method and processing system | |
| CN107808314B (en) | User recommendation method and device | |
| US20210382609A1 (en) | Method and device for displaying multimedia resource | |
| CN103150696A (en) | Method and device for selecting potential customer of target value-added service | |
| CN106610970A (en) | Collaborative filtering-based content recommendation system and method | |
| CN110008397A (en) | A kind of recommended models training method and device | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| JP2018077615A (en) | Advertising image generation device, advertising image generation method and program for advertising image generation device | |
| CN111737473B (en) | Text classification method, device and equipment | |
| CN105721629A (en) | User identifier matching method and device | |
| CN111611496A (en) | Product recommendation method and device | |
| CN110874787A (en) | Recommendation model effect evaluation method and related device | |
| CN111159553A (en) | Information pushing method and device, computer equipment and storage medium | |
| CN107346344A (en) | The method and apparatus of text matches | |
| CN114820123A (en) | Group purchase commodity recommendation method, device, equipment and storage medium | |
| CN111460301B (en) | Object pushing method and device, electronic equipment and storage medium | |
| CN106411908A (en) | Recommendation method and device | |
| CN107679887A (en) | A kind for the treatment of method and apparatus of trade company's scoring | |
| CN110334185A (en) | The treating method and apparatus of data in a kind of platform | |
| CN109919805A (en) | Information-pushing method, user equipment, storage medium and device | |
| CN109636530A (en) | Product determination method, product determination device, electronic equipment and computer-readable storage medium | |
| CN115618121B (en) | Personalized information recommendation method, device, equipment and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190618 |