CN110704726A - Data pushing method based on neural network and related equipment thereof - Google Patents
Data pushing method based on neural network and related equipment thereof Download PDFInfo
- Publication number
- CN110704726A CN110704726A CN201910763035.3A CN201910763035A CN110704726A CN 110704726 A CN110704726 A CN 110704726A CN 201910763035 A CN201910763035 A CN 201910763035A CN 110704726 A CN110704726 A CN 110704726A
- Authority
- CN
- China
- Prior art keywords
- user
- car
- information
- basic
- preset
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Feedback Control In General (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and provides a data pushing method based on a neural network and related equipment thereof, wherein the data pushing method based on the neural network comprises the following steps: acquiring a keyword when detecting that the user behavior of an operating user meets a preset condition; carrying out priority matching on the keywords to obtain corresponding priority; matching the keywords carrying the priority levels with the description information in the user set library, and selecting the user sets with the same matching as the data types to be identified; importing the type of the data to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information; and sending the information of the recommended vehicle trader to an operation user, and sending the basic information of the user to the recommended vehicle trader. According to the technical scheme, data pushing is automatically carried out on the car dealer and the operation user according to the key words, manual intervention is avoided, and therefore the data pushing efficiency and accuracy are improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a data pushing method based on a neural network and related equipment thereof.
Background
At present, data pushing methods aiming at the users and the car dealers in the market are single, mainly random pushing is carried out, pertinence is weak, pushing cannot be carried out in combination with the needs of the users, so that the pushing accuracy is not high, the situation of inaccurate pushing exists, the users cannot accurately acquire the car dealers information meeting the requirements when needing to buy the cars, the car dealers cannot accurately acquire the users meeting the requirements, and the car dealers cannot accurately push proper car information for the users.
Disclosure of Invention
The embodiment of the invention provides a data pushing method based on a neural network and related equipment thereof, and aims to solve the problem that a user and a driver cannot accurately acquire information meeting the requirements of the user and the driver in a random data pushing mode.
A data pushing method based on a neural network comprises the following steps:
when detecting that the user behavior of an operating user meets a preset condition in a car selling webpage, acquiring a keyword in the car selling webpage, wherein the operating user comprises user basic information;
performing priority matching on the keywords to obtain the corresponding priority of the keywords;
matching the keywords carrying the priority levels with the description information in the user set library, and selecting the user set corresponding to the description information with the same matching as the data type to be identified;
importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information;
and establishing an incidence relation between the recommended car dealer and the basic user information, sending the car dealer information of the recommended car dealer to the operation user, and sending the basic user information to the recommended car dealer.
A data pushing device based on the data between a user and a vehicle dealer comprises:
the system comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring a keyword in a car selling webpage when detecting that the user behavior of an operating user in the car selling webpage meets a preset condition, and the operating user comprises user basic information;
the priority level determining module is used for performing priority level matching on the keywords to obtain the priority levels corresponding to the keywords;
the first matching module is used for matching the keywords carrying the priority levels with the description information in the user set library and selecting the user set corresponding to the description information with the same matching as the data type to be identified;
the identification module is used for importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information;
and the sending module is used for establishing an association relationship between the recommended car dealer and the basic user information, sending the car dealer information of the recommended car dealer to the operation user, and sending the basic user information to the recommended car dealer.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the neural network-based data pushing method when executing the computer program.
A computer-readable storage medium, which stores a computer program that, when being executed by a processor, implements the steps of the above-mentioned neural network-based data push method.
According to the data pushing method based on the neural network and the related equipment, the priority level corresponding to the obtained keyword is obtained by matching the priority level of the obtained keyword, the keyword carrying the priority level is matched with the description information in the user collection library, the data type to be identified is obtained, the data type to be identified is led into a pre-trained vehicle dealer recommendation model, a recommended vehicle dealer carrying vehicle dealer information is output, the association relation between the recommended vehicle dealer and the basic information of the user is established, the vehicle dealer information of the recommended vehicle dealer is sent to the operation user, and the basic information of the user is sent to the recommended vehicle dealer. Therefore, data pushing is automatically carried out on the car dealer and the operation user according to the keywords, the basic information of the user can be quickly and accurately sent to the proper recommended car dealer, the car dealer information is sent to the operation user, manual intervention is avoided, the data pushing efficiency and accuracy can be effectively improved, the searching efficiency and accuracy of the operation user are further improved, and the car dealer pushing accuracy is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a flowchart of a data pushing method based on a neural network according to an embodiment of the present invention;
fig. 2 is a flowchart of step S1 in the data pushing method based on the neural network according to the embodiment of the present invention;
fig. 3 is a flowchart of step S12 in the data pushing method based on the neural network according to the embodiment of the present invention;
FIG. 4 is a flow chart of a neural network-based data pushing method according to an embodiment of the present invention, in which multidimensional features and composite features are combined as basic features;
fig. 5 is a flowchart of step S71 in the data pushing method based on the neural network according to the embodiment of the present invention;
fig. 6 is a flowchart of step S2 in the data pushing method based on the neural network according to the embodiment of the present invention;
FIG. 7 is a schematic diagram of a data pushing device based on data between a user and a vehicle dealer according to an embodiment of the present invention;
fig. 8 is a block diagram of a basic mechanism of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The data processing method provided by the application is applied to the server side, and the server side can be realized by an independent server or a server cluster formed by a plurality of servers. In an embodiment, as shown in fig. 1, a data pushing method based on a neural network is provided, which includes the following steps:
s1: and when detecting that the user behavior of the operating user meets a preset condition in the car selling webpage, acquiring a keyword in the car selling webpage, wherein the operating user comprises user basic information.
In the embodiment of the present invention, the user behavior may include, but is not limited to, that the user browses a web page on a computer device, and the computer device may be a smart phone, a notebook, a palm computer, or an advertisement machine; the preset condition may be that the duration of the user browsing the car-selling webpage reaches a set threshold, or the number of browsing car-selling links reaches a set threshold, and the like. The user basic information includes user personal information and user location information.
Specifically, when it is detected that the user behavior of the operation user is that the duration of browsing the car selling webpage reaches a set threshold, or the number of the car selling links reaches a set threshold, or the number of the browsing car selling links reaches a set threshold, the keyword in the car selling webpage is obtained from the preset database. The preset database is a database which is specially used for storing keywords in the car selling webpage browsed by the operation user.
It should be noted that, because an operating user who does not have a definite intention compares certain types of car selling webpage contents in a car selling webpage for a long time before selecting a psychometric vehicle product, or browses different car selling links in a short time to select the psychometric vehicle product, and the like, such user behaviors can be used as operating users who have car purchasing intentions, some irrelevant users can be effectively screened out by identifying the user behaviors, and the mining efficiency of the operating users is improved.
S2: and matching the priority levels of the keywords to obtain the corresponding priority levels of the keywords.
Specifically, the priority level corresponding to each keyword is obtained by obtaining the occurrence frequency corresponding to each keyword and matching the occurrence frequency corresponding to each keyword with the frequency interval corresponding to the priority level.
S3: matching the keywords carrying the priority levels with the description information in the user set library, and selecting the user set corresponding to the description information with the same matching as the data type to be identified.
In the embodiment of the present invention, the keyword carrying the priority level refers to a keyword containing the priority level, for example, a class a brand. Different user sets and description information corresponding to the user sets are pre-stored in a user set library, wherein the user sets comprise at least 2 keywords with priority levels preset by a user. For example, there is a user set of "brand name a, price level B, city X level C", and its corresponding descriptive information is "brand name a, price level B, city X level C".
Specifically, the keywords with the priority levels are matched with the description information in the user set library, and if the keywords with the priority levels are matched with the description information in the user set library to be the same, the user set corresponding to the description information is used as the data type to be identified.
For example, the keywords carrying the priority levels are: grade a brand, grade B price level; the description information of the user set inventory corresponding to the user set Q1 is 'A-level brand and B-level price level', the description information corresponding to the user set Q2 is 'A-level price level and B-level brand', the keywords with the priority levels are matched with the description information, the obtained keywords with the priority levels are the same as the description information corresponding to the user set Q1, and therefore the user set Q1 is used as the type of data to be identified.
S4: and importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information.
In the embodiment of the invention, the vehicle dealer recommendation model refers to a convolutional neural network model used for matching recommended vehicle dealers. The pre-trained vehicle dealer recommendation model can quickly and accurately output recommended vehicle dealers carrying vehicle dealer information corresponding to the data types to be recognized according to the input data types to be recognized. The information of the vehicle dealer comprises a recommended vehicle type, a network sale link of the vehicle dealer, a vehicle dealer address, a vehicle dealer contact way and the like.
Specifically, the data type to be identified is directly imported into a pre-trained carrier recommendation model, and the carrier recommendation model can quickly and accurately judge a recommended carrier carrying carrier information corresponding to the data type to be identified according to the input data type to be identified and output the recommended carrier.
Further, when the vehicle dealer recommendation model identifies recommended vehicle dealers of a plurality of different vehicle dealer addresses, further screening is carried out according to user position information in the user basic information, and if the description information corresponding to the user set serving as the data type to be identified does not contain the position information, the identified recommended vehicle dealers are randomly selected to be output; and if the description information corresponding to the user set as the data type to be identified contains the position information, selecting the recommended vehicle dealer at the vehicle dealer address closest to the position information of the user for outputting.
It should be noted that, in the training process of the vehicle dealer recommendation model, the convolutional neural network model is initialized to obtain an initial model, then sample data prepared in advance for training is imported into the initial model to calculate forward output, then a prediction error between the forward output and a preset target value is calculated, and finally, according to the prediction error, an error back propagation algorithm is used for adjusting initial parameters of each network layer in the initial model to obtain the vehicle dealer recommendation model.
S5: and establishing an incidence relation between the recommended car dealer and the basic information of the user, sending the car dealer information of the recommended car dealer to the operation user, and sending the basic information of the user to the recommended car dealer.
In the embodiment of the invention, the association relationship between the recommended car dealer and the basic information of the user is established, so that the server side can execute information push according to the association relationship, and the accuracy and efficiency of information push are improved. The information of the recommended car dealers is sent to the operation user, so that the operation user can be helped to know the information of the car dealers suitable for the operation user in time, and the car purchasing success rate of the operation user is improved; the basic information of the user is sent to the recommended car dealer, so that the recommended car dealer can be helped to set a car selling service guide for the operation user in advance, and the selling success rate of the recommended car dealer is improved.
Specifically, according to the recommended car dealer obtained in step S4, an association relationship is established between the recommended car dealer and the user basic information, the car dealer information of the recommended car dealer is sent to the operation user in a preset push manner, and the user basic information is sent to the recommended car dealer in a preset push manner. The preset pushing mode can be specifically in a short message form, and can also be set according to the actual requirements of the user.
In the embodiment, the priority levels corresponding to the obtained keywords are obtained by matching the priority levels of the obtained keywords, the keywords carrying the priority levels are matched with the description information in the user set library to obtain the data types to be identified, the data types to be identified are imported into a pre-trained vehicle dealer recommendation model, a recommended vehicle dealer carrying vehicle dealer information is output, the association relationship between the recommended vehicle dealer and the basic information of the user is established, the vehicle dealer information of the recommended vehicle dealer is sent to the operation user, and the basic information of the user is sent to the recommended vehicle dealer. Therefore, data pushing is automatically carried out on the car dealer and the operation user according to the keywords, the basic information of the user can be quickly and accurately sent to the proper recommended car dealer, the car dealer information is sent to the operation user, manual intervention is avoided, the data pushing efficiency and accuracy can be effectively improved, the searching efficiency and accuracy of the operation user are further improved, and the car dealer pushing accuracy is further improved.
In an embodiment, as shown in fig. 2, in step S1, when it is detected that the user behavior of the operating user satisfies the preset condition in the car selling webpage, the acquiring the keyword in the car selling webpage includes the following steps:
s11: and when detecting that the user behavior of the operating user meets a preset condition to be detected, acquiring the information of the user intention to purchase the vehicle.
Specifically, when it is detected that the user behavior of the operating user meets a preset condition to be tested, user car-buying intention information of the operating user is acquired from a preset intention library, wherein the preset intention library is a database specially used for storing the user car-buying intention information selected by the operating user when browsing a car-selling webpage.
The user car-buying intention information is car-buying intention information that the user is operated to inquire on the car-selling webpage, and the car-buying intention information may be, but is not limited to, a car-buying budget, a location distance of a 4s store, an intention brand, intention brand preference, car model preference, service expectation, and the like.
S12: and carrying out data cleaning on the user purchase intention information to obtain basic characteristics.
In the embodiment of the invention, some invalid data irrelevant to subsequent calculation exist in the user car purchasing intention information, so that the data of the user car purchasing intention information needs to be cleaned, the invalid data is eliminated, the invalid data is prevented from being redundantly calculated, and the efficiency of the subsequent calculation can be improved. The underlying features typically include branding, prices, offers, and the like.
Specifically, data cleaning is carried out on the user car purchasing intention information according to the preset filtering condition, the user car purchasing intention information meeting the preset filtering condition is deleted, the user car purchasing intention information not meeting the preset filtering condition is reserved, and the reserved user car purchasing intention information is used as basic characteristics. The preset filtering condition may be, but not limited to, a browsing time of the operation user on the car-selling webpage, a browsing content of the car-selling webpage, user car-purchasing intention information filled in by the car-selling webpage, and the like, and the specific preset filtering condition may be set according to an actual situation of a specific service.
S13: and matching the basic characteristics with preset characteristics.
Specifically, the basic features are matched with preset features, wherein the preset features may specifically be brand offers, price levels, and the like.
S14: and if the basic characteristic is the same as the preset characteristic, determining the basic characteristic which is the same as the preset characteristic as the target characteristic.
In the embodiment of the present invention, the basic feature is matched with the preset feature according to step S13, and if the basic feature is the same as the preset feature, the basic feature is determined as the target feature.
For example, if there are basic features of "brand information", "sales price range", and "comfort level", respectively, and the preset feature is "brand information", the "brand information", "sales price range", and "comfort level" are respectively matched with the "brand information", and the "brand information" is obtained as the target feature.
S15: and integrating all target characteristics to obtain keywords.
Specifically, according to the target features obtained in step S14, all the target features are integrated according to a preset rule, so as to obtain the keywords after the integration. The preset rule is a set rule for synthesizing the target features according to the actual requirements of the user.
For example, if there are brand a and B price for the target feature, the keyword obtained by integrating the target feature according to the preset rule is brand a at price B.
In this embodiment, the basic features are obtained by performing data cleaning on the obtained user car-purchasing intention information, the target features are obtained by matching the basic features with preset features, and finally the target features are integrated to obtain the keywords. Therefore, the corresponding keywords can be accurately extracted according to the information of the intention of the user to purchase the car, the accuracy of the subsequently utilized keywords is ensured, and the accuracy of the subsequent data push is further ensured.
In one embodiment, as shown in fig. 3, the step S12 of performing data cleansing on the user car purchase intention information to obtain the basic features includes the following steps:
s121: matching the user car purchasing intention information with preset filtering conditions.
Specifically, the car purchasing intention information is matched with preset filtering conditions.
S122: and if the user car purchasing intention information is the same as the preset filtering condition, deleting the user car purchasing intention information.
In the embodiment of the present invention, the car-buying intention information is matched with the preset filtering condition in step S121, and if the matching result is that the car-buying intention information of the user is identical to the preset filtering condition, it indicates that the car-buying intention information of the user conforms to the preset filtering condition, that is, the filtering qualification is reached, so the car-buying intention information of the user identical to the preset filtering condition is deleted.
S123: and if the user car purchasing intention information is not the same as the preset filtering condition, determining the user car purchasing intention information as the basic characteristic.
Specifically, the car-buying intention information is matched with the preset filtering condition in step S121, if the matching result is that the car-buying intention information of the user is not identical to the preset filtering condition, it indicates that the car-buying intention information of the user is not identical to the preset filtering condition, that is, the filtering qualification is not reached, so that the car-buying intention information of the user, which is not identical to the preset filtering condition, is retained, and the retained car-buying intention information of the user is determined as the basic feature.
In this embodiment, part of the user car-buying intention information is filtered in a manner of matching the user car-buying intention information with a preset filtering condition, and the reserved user car-buying intention information is used as a basic feature. Therefore, the effective screening of the user car purchasing intention information is realized, the accuracy of the extracted basic characteristics is ensured, and the accuracy of subsequent data pushing and the accuracy of searching of the operating user are further ensured.
In this embodiment, after step S13, the data pushing method based on the neural network further includes the following steps:
s6: and if the basic characteristic is different from the preset characteristic, replacing the basic characteristic with the preset characteristic, and taking the replaced basic characteristic as the target characteristic.
In the embodiment of the present invention, the basic feature is matched with the preset feature according to step S13, and if the matching result is that the basic feature is not the same as the preset feature, the basic feature is imported into a preset replacement library for replacement processing to obtain a replaced basic feature, and the basic feature is used as the target feature.
It should be noted that, when the preset replacement library detects a basic feature, it is determined whether a basic feature different from the preset feature exists in all the basic features, and if the basic feature different from the preset feature exists, the basic feature is deleted; meanwhile, judging whether preset features different from the basic features exist in all the preset features, and if the preset features different from the basic features exist, generating the basic features same as the preset features; namely, after the basic features are subjected to replacement processing by a preset replacement library, the basic features which are the same as the preset features are obtained.
The preset replacement library is a database specially used for performing replacement processing on the basic features.
For example, if there are basic features: A. b, C, D, E, the preset characteristics are: C. d, E, F, G, importing the basic features into a preset replacement library, judging whether the basic features different from the preset features exist in all the basic features when the basic features are detected by the preset replacement library, and deleting the basic features A and the basic features B if the basic features A and the basic features B are different from the preset features; meanwhile, judging whether preset features different from the basic features exist in all the preset features or not, if the obtained preset features F and the obtained preset features G are different from the basic features, generating the basic features same as the preset features F and the preset features G, and obtaining the basic features F and the basic features G; finally, after the basic features are imported into a preset replacement library for replacement processing, the obtained basic features are respectively as follows: C. d, E, F, G are provided.
In this embodiment, when the basic feature is different from the preset feature, the basic feature is replaced with the preset feature, and the replaced basic feature is used as the target feature. Therefore, the basic characteristics are further processed under the condition that the basic characteristics are different from the preset characteristics, and the accuracy of obtaining the target characteristics is ensured.
In an embodiment, the basic features include user features and non-user features, as shown in fig. 4, after step S12 and before step S13, the data push method based on the neural network further includes the following steps:
s71: and performing dimension increasing processing on the user characteristics to obtain the multi-dimensional characteristics.
In the embodiment of the invention, the user characteristics are characteristic information related to the user in the car-selling webpage, such as car-buying intention information of the user, browsing contents of the user in the car-selling webpage and the like. Because the user features belong to the low-dimensional features, the pre-trained vehicle-dealer recommendation model is not suitable for identifying the low-dimensional features, if the low-dimensional features are subsequently and directly used for leading into the pre-trained vehicle-dealer recommendation model for identification, the identification effect of the pre-trained vehicle-dealer recommendation model is affected, and the identification accuracy is affected, so that the user features need to be processed into multi-dimensional features in order to improve the accuracy.
Specifically, user characteristics are obtained from a user characteristic library, and the user characteristics are led into a preset dimension-increasing port to be subjected to dimension-increasing processing, so that multidimensional characteristics subjected to dimension-increasing processing are obtained. The preset dimension-increasing port is a processing port which is specially used for processing user features into multi-dimensional features. The user feature library refers to a database which is specially used for storing user features.
S72: and performing data combination on the non-user characteristics according to the preset related characteristics to obtain the composite characteristics.
In the embodiment of the invention, the non-user characteristics refer to characteristic information irrelevant to the user in the automobile-selling webpage, such as preferential tendency, service rating, service cycle matching, price level rating and other webpage contents.
Specifically, non-user features are obtained from a non-user feature library, all the non-user features are matched with preset relevant features, the non-user features matched with the preset relevant features are selected and led into a preset combination port to be combined with data, and composite features after data combination are obtained.
The non-user feature library refers to a database dedicated to storing non-user features.
The preset relevant features refer to relevant features for confirming the setting of user service requirements, and the preset non-user feature library comprises non-user features which are the same as the preset relevant features.
The preset combination port refers to an execution port which is specially used for carrying out data combination on non-user characteristics.
S73: combining the multi-dimensional features and the composite features as basic features.
Specifically, the multi-dimensional feature in step S71 and the composite feature in step S72 are combined to obtain a combined base feature. For example, combining multidimensional feature J and composite feature K, the resulting base features include J and K.
In this embodiment, the user features are processed into multi-dimensional features, the non-user features are processed into composite features, and the multi-dimensional features and the composite features are combined to serve as basic features. Therefore, the user characteristics and the non-user characteristics are preprocessed, the preprocessed characteristics are combined to serve as basic characteristics, the data types of the subsequent basic characteristics can be suitable for the vehicle dealer recommendation model, and the accuracy of vehicle dealer recommendation model identification is guaranteed.
In an embodiment, as shown in fig. 5, in step S71, performing the dimension-raising process on the user feature to obtain the multidimensional feature includes the following steps:
s711: and carrying out nonlinear transformation on the user characteristics by using a preset kernel function to obtain nonlinear characteristics.
In the embodiment of the invention, the nonlinear characteristic after the nonlinear transformation processing is obtained by directly utilizing the preset kernel function to carry out the nonlinear transformation on the user characteristic.
The preset kernel function refers to a function specially used for performing nonlinear transformation on the user characteristics.
S712: and performing coding operation on the nonlinear features to obtain the multidimensional features.
Specifically, an encoding operation is performed on the nonlinear features obtained in step S711 according to a preset encoding manner, a dummy variable of the nonlinear features is obtained by performing the encoding operation, and the dummy variable is set as a corresponding multidimensional vector, that is, the set multidimensional vector is a multidimensional feature. The preset encoding mode may specifically be one-hot (one-hot) encoding, and may also be set according to the actual needs of the user.
Preferably, the preset encoding mode adopted by the proposal is one-hot encoding.
It should be noted that one-hot encoding is also called unique hot encoding and one-bit effective encoding. The method is to use an N-bit status register to encode N states, each state having its own independent register bit and only one of which is active at any one time. For example, suppose we have four samples, each sample has three features, and suppose a user feature has 4 value states, we use 4 state bits to represent the feature, and one-hot encoding is to ensure that only 1 bit of a single feature in each sample is in state 1, and the others are all 0. The dummy variable coding refers to any method of removing one status bit, for example, 4 status bits are enough to reflect 5 categories of information when the characteristics of a certain user are known, for example, the user positions are respectively valued by housewives, white collars, workers, farmers and individual users, and when the first four status bits [0,0,0,0] are used, the status bits can be expressed as the individual users. Simply because for a sample of a study he is neither housewife, white collar, worker, farmer, then he can default to an individual household.
In this embodiment, the user characteristics are subjected to nonlinear transformation to obtain nonlinear characteristics, and then the nonlinear characteristics are subjected to encoding operation to obtain multidimensional characteristics. Therefore, the user characteristics are processed into the multidimensional characteristics, the multidimensional characteristics are guaranteed to be suitable for application of a subsequent vehicle-dealer recommendation model, and accuracy of vehicle-dealer recommendation model identification is further improved.
In an embodiment, as shown in fig. 6, the step S2 of performing priority matching on the keywords to obtain the corresponding priority of the keywords includes the following steps:
s21: and acquiring the occurrence frequency of the keywords from the historical data table.
In the embodiment of the present invention, according to the keywords obtained in step S1, each keyword is matched with the description information in the historical data table, and if the matching is successful, the frequency corresponding to the description information successfully matched is obtained from the historical data table as the occurrence frequency of the keyword. The historical data table is a database which is specially used for storing the description information and the frequency of occurrence of the description information, and the description information which is the same as the keyword in correspondence exists in the historical data table.
S22: and matching the occurrence frequency with a frequency interval in a preset frequency library, and if the occurrence frequency is in the frequency interval, taking the priority level corresponding to the frequency interval as the priority level corresponding to the keyword.
Specifically, according to the occurrence frequency of the keyword obtained in step S21, the occurrence frequency of the keyword is matched with a frequency interval in a preset frequency library, if the occurrence frequency of the keyword exists in the frequency interval, it indicates that the occurrence frequency of the keyword is matched with the frequency interval, and the priority level corresponding to the frequency interval is used as the priority level corresponding to the keyword. The preset frequency library is a database specially used for storing the frequency interval and the priority level corresponding to the frequency interval.
For example, if there are frequency intervals of [1, 30 ], [30, 100) and [100, + ∞ ") in the preset frequency library, the corresponding priority levels are first, second and third, respectively; the occurrence frequency of the existing keyword is 25, the occurrence frequency 25 is matched with each frequency interval, and the occurrence frequency 25 in the frequency interval [1, 30) is obtained, so that the priority level corresponding to the frequency interval [1, 30) is equal to the priority level corresponding to the keyword, namely the priority level corresponding to the keyword is equal to one.
In this embodiment, the priority level corresponding to the keyword is obtained by matching the frequency of occurrence of the keyword with the frequency interval. Therefore, the priority levels corresponding to the keywords can be quickly and accurately obtained, and the accuracy of matching the keywords carrying the priority levels with the description information in the follow-up process is guaranteed.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, a device is provided, and the data pushing device based on the user and the vehicle dealer corresponds to the data pushing method based on the neural network in the above embodiment one to one. As shown in fig. 7, the data pushing device based on the data between the user and the vehicle dealer includes a first obtaining module 71, a priority level determining module 72, a first matching module 73, an identifying module 74 and a sending module 75. The functional modules are explained in detail as follows:
the first obtaining module 71 is configured to obtain a keyword in the car selling webpage when it is detected that a user behavior of an operating user meets a preset condition in the car selling webpage, where the operating user includes user basic information;
a priority level determining module 72, configured to perform priority level matching on the keywords to obtain priority levels corresponding to the keywords;
the first matching module 73 is configured to match the keywords with the priority levels with the description information in the user set library, and select a user set corresponding to the same matching description information as a data type to be identified;
the identification module 74 is used for importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information;
the sending module 75 is configured to establish an association relationship between the recommended car dealer and the basic information of the user, send the car dealer information of the recommended car dealer to the operation user, and send the basic information of the user to the recommended car dealer.
Further, the first obtaining module 71 includes:
the second acquisition submodule is used for acquiring the information of the intention of the user to purchase the car when detecting that the user behavior of the operating user meets the preset condition to be detected;
the data cleaning submodule is used for carrying out data cleaning on the user car purchasing intention information to obtain basic characteristics;
the second matching submodule is used for matching the basic characteristics with the preset characteristics;
the target characteristic determining submodule is used for determining the basic characteristic which is the same as the preset characteristic as the target characteristic if the basic characteristic is the same as the preset characteristic;
and the integration processing submodule is used for integrating all the target characteristics to obtain the keywords.
Further, the data cleansing submodule includes:
the third matching unit is used for matching the user car purchasing intention information with the preset filtering condition;
the third matching same unit is used for deleting the user car purchasing intention information if the user car purchasing intention information is the same as the preset filtering condition;
and the third matching different unit is used for determining the user car purchasing intention information as the basic characteristic if the user car purchasing intention information is different from the preset filtering condition.
Further, the pushing device based on the data between the user and the vehicle dealer further comprises:
and the second matching different module is used for replacing the basic characteristic with the preset characteristic if the basic characteristic is different from the preset characteristic, and taking the replaced basic characteristic as the target characteristic.
Further, the pushing device based on the data between the user and the vehicle dealer further comprises:
the dimension increasing module is used for performing dimension increasing processing on the user characteristics to obtain multi-dimensional characteristics;
the data combination module is used for carrying out data combination on the non-user characteristics according to preset related characteristics to obtain composite characteristics;
and the combining module is used for combining the multi-dimensional features and the composite features as basic features.
Further, the dimension-increasing module comprises:
the nonlinear transformation submodule is used for carrying out nonlinear transformation on the user characteristics by utilizing a preset kernel function to obtain nonlinear characteristics;
and the coding submodule executes coding operation on the nonlinear characteristic to obtain the multidimensional characteristic.
Further, the priority level determination module 72 includes:
the third acquisition sub-module is used for acquiring the occurrence frequency of the keywords from the historical data table;
and the fourth matching submodule is used for matching the occurrence frequency with a frequency interval in a preset frequency library, and if the occurrence frequency is in the frequency interval, taking the priority level corresponding to the frequency interval as the priority level corresponding to the keyword.
Some embodiments of the present application disclose a computer device. Referring specifically to fig. 8, a basic structure block diagram of a computer device 90 according to an embodiment of the present application is shown.
As illustrated in fig. 8, the computer device 90 includes a memory 91, a processor 92, and a network interface 93 communicatively connected to each other through a system bus. It is noted that only a computer device 90 having components 91-93 is shown in FIG. 8, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 91 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 91 may be an internal storage unit of the computer device 90, such as a hard disk or a memory of the computer device 90. In other embodiments, the memory 91 may also be an external storage device of the computer device 90, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 90. Of course, the memory 91 may also include both internal and external memory units of the computer device 90. In this embodiment, the memory 91 is generally used for storing an operating system installed in the computer device 90 and various types of application software, such as program codes of the data pushing method based on the neural network. Further, the memory 91 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 92 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 92 is typically used to control the overall operation of the computer device 90. In this embodiment, the processor 92 is configured to execute the program code stored in the memory 91 or process data, for example, execute the program code of the data pushing method based on the neural network.
The network interface 93 may include a wireless network interface or a wired network interface, and the network interface 93 is generally used to establish a communication connection between the computer device 90 and other electronic devices.
The present application provides another embodiment, which is to provide a computer-readable storage medium storing a recommended driver information entry program, where the recommended driver information entry program is executable by at least one processor to cause the at least one processor to perform any one of the steps of the neural network-based data pushing method.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a computer device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
Finally, it should be noted that the above-mentioned embodiments illustrate only some of the embodiments of the present application, and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A data pushing method based on a neural network is characterized by comprising the following steps:
when detecting that the user behavior of an operating user meets a preset condition in a car selling webpage, acquiring a keyword in the car selling webpage, wherein the operating user comprises user basic information;
performing priority matching on the keywords to obtain the corresponding priority of the keywords;
matching the keywords carrying the priority levels with the description information in the user set library, and selecting the user set corresponding to the description information with the same matching as the data type to be identified;
importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information;
and establishing an incidence relation between the recommended car dealer and the basic user information, sending the car dealer information of the recommended car dealer to the operation user, and sending the basic user information to the recommended car dealer.
2. The data pushing method based on the neural network as claimed in claim 1, wherein the step of obtaining the keywords in the car-selling webpage when it is detected that the user behavior of the operating user satisfies the preset condition in the car-selling webpage comprises:
when detecting that the user behavior of the operating user meets a preset condition to be detected, acquiring the information of the user's intention to purchase the car;
carrying out data cleaning on the user car purchasing intention information to obtain basic characteristics;
matching the basic features with preset features;
if the basic feature is the same as the preset feature, determining the basic feature which is the same as the preset feature as a target feature;
and integrating all the target characteristics to obtain the keywords.
3. The data pushing method based on the neural network as claimed in claim 2, wherein the step of performing data cleaning on the user car purchasing intention information to obtain the basic features comprises:
matching the user car purchasing intention information with preset filtering conditions;
if the user car purchasing intention information is the same as the preset filtering condition, deleting the user car purchasing intention information;
and if the user car purchasing intention information is not the same as the preset filtering condition, determining the user car purchasing intention information as a basic characteristic.
4. The neural network-based data pushing method according to claim 2, wherein after the matching of the basic features with the preset features, the neural network-based data pushing method further comprises:
and if the basic characteristic is different from the preset characteristic, replacing the basic characteristic with the preset characteristic, and taking the replaced basic characteristic as a target characteristic.
5. The data pushing method based on the neural network as claimed in claim 2, wherein the basic features include user features and non-user features, and after the data cleaning is performed on the user car purchasing intention information to obtain the basic features and before the matching is performed on the basic features and the preset features, the data pushing method based on the neural network further includes:
performing dimension increasing processing on the user characteristics to obtain multi-dimensional characteristics;
performing data combination on the non-user characteristics according to preset relevant characteristics to obtain composite characteristics;
combining the multi-dimensional features and composite features as the base features.
6. The data pushing method based on the neural network as claimed in claim 5, wherein the step of performing the dimension-raising processing on the user feature to obtain the multidimensional feature comprises:
carrying out nonlinear transformation on the user characteristics by using a preset kernel function to obtain nonlinear characteristics;
and executing coding operation on the nonlinear features to obtain the multidimensional features.
7. The data pushing method based on the neural network as claimed in claim 1, wherein the step of performing priority matching on the keywords to obtain the corresponding priority of the keywords comprises:
acquiring the occurrence frequency of the keywords from a historical data table;
and matching the occurrence frequency with a frequency interval in a preset frequency library, and if the occurrence frequency is in the frequency interval, taking the priority level corresponding to the frequency interval as the priority level corresponding to the keyword.
8. A data pushing device based on the data between a user and a vehicle dealer is characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is used for acquiring a keyword in a car selling webpage when detecting that the user behavior of an operating user in the car selling webpage meets a preset condition, and the operating user comprises user basic information;
the priority level determining module is used for performing priority level matching on the keywords to obtain the priority levels corresponding to the keywords;
the first matching module is used for matching the keywords carrying the priority levels with the description information in the user set library and selecting the user set corresponding to the description information with the same matching as the data type to be identified;
the identification module is used for importing the data type to be identified into a pre-trained vehicle dealer recommendation model for identification to obtain a recommended vehicle dealer with vehicle dealer information;
and the sending module is used for establishing an association relationship between the recommended car dealer and the basic user information, sending the car dealer information of the recommended car dealer to the operation user, and sending the basic user information to the recommended car dealer.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the neural network-based data pushing method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the neural network-based data pushing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910763035.3A CN110704726B (en) | 2019-08-19 | 2019-08-19 | Data pushing method based on neural network and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910763035.3A CN110704726B (en) | 2019-08-19 | 2019-08-19 | Data pushing method based on neural network and related equipment thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110704726A true CN110704726A (en) | 2020-01-17 |
| CN110704726B CN110704726B (en) | 2023-07-28 |
Family
ID=69193221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910763035.3A Active CN110704726B (en) | 2019-08-19 | 2019-08-19 | Data pushing method based on neural network and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110704726B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933172A (en) * | 2015-06-30 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Information pushing method and device based on user searching behavior |
| US9531827B1 (en) * | 2011-06-14 | 2016-12-27 | Urban Airship, Inc. | Push notification delivery system with feedback analysis |
| CN107657480A (en) * | 2017-09-08 | 2018-02-02 | 广州悦鸿方生物科技有限公司 | Based on the system for selling the progress information gathering of equipment user's information and/or push |
| CN108710634A (en) * | 2018-04-08 | 2018-10-26 | 平安科技（深圳）有限公司 | A kind of method for pushing and terminal device of document of agreement |
-
2019
- 2019-08-19 CN CN201910763035.3A patent/CN110704726B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9531827B1 (en) * | 2011-06-14 | 2016-12-27 | Urban Airship, Inc. | Push notification delivery system with feedback analysis |
| CN104933172A (en) * | 2015-06-30 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Information pushing method and device based on user searching behavior |
| CN107657480A (en) * | 2017-09-08 | 2018-02-02 | 广州悦鸿方生物科技有限公司 | Based on the system for selling the progress information gathering of equipment user's information and/or push |
| CN108710634A (en) * | 2018-04-08 | 2018-10-26 | 平安科技（深圳）有限公司 | A kind of method for pushing and terminal device of document of agreement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110704726B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110825957B (en) | Deep learning-based information recommendation method, device, equipment and storage medium | |
| CN107688987A (en) | Electronic installation, insurance recommendation method and computer-readable recording medium | |
| CN108876213B (en) | Block chain-based product management method, device, medium and electronic equipment | |
| CN110474903B (en) | Trusted data acquisition method and device and block link point | |
| CN111680165A (en) | Information matching method and device, readable storage medium and electronic equipment | |
| CN111160624A (en) | User intention prediction method, user intention prediction device and terminal equipment | |
| CN106600082A (en) | Processing method and device of task in service system, and service system construction system | |
| CN111858922A (en) | Service side information query method and device, electronic equipment and storage medium | |
| CN111461827A (en) | Product evaluation information pushing method and device | |
| CN103593444A (en) | Network keyword recognition processing method and device | |
| CN108427700B (en) | Electronic device, user grouping method and computer readable storage medium | |
| CN110275880B (en) | Data analysis method, device, server and readable storage medium | |
| CN111125076A (en) | Big data based medicine universal name cleaning method and system, server and medium | |
| CN108595580B (en) | News recommendation method, device, server and storage medium | |
| CN110634018A (en) | Feature depiction method, recognition method and related device for lost user | |
| US10579752B2 (en) | Generating a model based on input | |
| CN105069639A (en) | Agricultural product quality tracing method and device | |
| CN110704726A (en) | Data pushing method based on neural network and related equipment thereof | |
| CN116010707A (en) | Commodity price anomaly identification method, device, equipment and storage medium | |
| CN112686732B (en) | Abnormal address data identification method, device, equipment and medium | |
| CN104537546A (en) | Product quality monitoring method and device as well as product quality verification method and device | |
| CN114757201A (en) | Method for identifying delivery address, storage medium and processor | |
| US10063646B2 (en) | Content distribution system, content distribution method, and non-transitory computer readable storage medium | |
| US9489628B2 (en) | Rule-based inference system and an inference method | |
| CN110348190B (en) | User equipment attribution judging method and device based on user operation behaviors |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |