CN113450169A - Method and system for processing vehicle recommendation information, computer equipment and storage medium - Google Patents

Method and system for processing vehicle recommendation information, computer equipment and storage medium Download PDF

Info

Publication number
CN113450169A
CN113450169A CN202010229460.7A CN202010229460A CN113450169A CN 113450169 A CN113450169 A CN 113450169A CN 202010229460 A CN202010229460 A CN 202010229460A CN 113450169 A CN113450169 A CN 113450169A
Authority
CN
China
Prior art keywords
vehicle
behavior information
information
preference value
vehicle type
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
Application number
CN202010229460.7A
Other languages
Chinese (zh)
Inventor
杨笑锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Dasouche Auto Service Co ltd
Original Assignee
Hangzhou Dasouche Auto Service Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Dasouche Auto Service Co ltd filed Critical Hangzhou Dasouche Auto Service Co ltd
Priority to CN202010229460.7A priority Critical patent/CN113450169A/en
Publication of CN113450169A publication Critical patent/CN113450169A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Acoustics & Sound (AREA)
  • Human Resources & Organizations (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Signal Processing (AREA)
  • Child & Adolescent Psychology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)

Abstract

The invention discloses a method, a system, computer equipment and a storage medium for processing vehicle recommendation information, wherein the method comprises the following steps: receiving behavior information of a vehicle purchasing user acquired by a camera device; inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type; through a collaborative filtering algorithm, vehicle type information preferred by the vehicle purchasing user is determined according to the preference value, and the determined vehicle type information is sent to the terminal, so that the problem of low conversion rate of the vehicle purchasing cable in the processing method of the vehicle recommendation information is solved.

Description

Method and system for processing vehicle recommendation information, computer equipment and storage medium
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method, a system, a computer device, and a storage medium for processing vehicle recommendation information.
Background
With the continuous improvement of the living standard and the performance of the automobile, the consumption demand of people on the automobile is more and more vigorous. In the related technology, a user decides whether to purchase a vehicle or not mainly according to parameters and prices of the vehicle and a public praise of the vehicle type, but because the experience and the interest of the user on the vehicle type are not referred to, the user finds that the vehicle type is not really favored by the vehicle after purchasing the vehicle, and the accurate recommendation of the vehicle cannot be realized; meanwhile, for the user who does not buy the vehicle, the real preference of the user cannot be accurately excavated, so that the recommended vehicle type cannot be efficiently delivered.
Aiming at the problem that the conversion rate of the vehicle purchasing cable is low in a processing method of vehicle recommendation information in the related art, an effective solution is not provided at present.
Disclosure of Invention
The invention provides a method and a system for processing vehicle recommendation information, computer equipment and a storage medium, aiming at the problem that the conversion rate of a vehicle purchasing cable is low in a method for processing the vehicle recommendation information in the related art.
According to an aspect of the present invention, there is provided a method for processing vehicle recommendation information, the method including:
receiving behavior information of a vehicle purchasing user acquired by a camera device;
inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type;
and determining vehicle type information preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm, and sending the determined vehicle type information to a terminal.
In one embodiment, after the behavior information of the vehicle purchasing user acquired by the camera device is received and before the behavior information is input into a pre-trained vehicle type preference value prediction model, the method further includes:
calling an emotion recognition interface to analyze expression data in the behavior information and acquiring an expression recognition result;
converting the voice data in the behavior information into text data, analyzing the text data through a TF-IDF algorithm, and acquiring a voice recognition result;
and fusing the expression recognition result and the voice recognition result to the behavior information.
In one embodiment, the inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain the preference value of the vehicle purchasing user for the vehicle type includes:
inputting the behavior information into the prediction model, and dividing the behavior information into a training data set and a testing data set;
training the prediction model according to the training data set and the test data set through an XGBOOST algorithm, and acquiring the preference value output by the prediction model.
In one embodiment, the determining, by a collaborative filtering algorithm, vehicle model information preferred by the vehicle purchasing user according to the preference value includes:
acquiring the vehicle type ID matched with the preference value, and calculating the similarity between other vehicle types in a vehicle type database and the vehicle type ID;
according to the product of the preference value and the similarity, acquiring the corresponding preference value of the vehicle purchasing user to each vehicle type in the vehicle type database;
arranging the corresponding preference values in a reverse order, determining the vehicle models with the corresponding preference values in the top N, and pushing the vehicle information serving as recommendation information to the vehicle purchasing user; wherein N is a positive integer.
In one embodiment, after the behavior information of the vehicle purchasing user acquired by the camera device is received and before the behavior information is input into a pre-trained vehicle type preference value prediction model, the method further includes:
acquiring behavior information after data filling under the condition that the behavior information has a missing value;
according to a boxchart detection method, abnormal data detection is carried out on the behavior information after the data filling; and acquiring the behavior information filled with the median under the condition that the behavior information has abnormal data.
In one embodiment, after the obtaining of the behavior information after the filling of the median is performed in the case that the abnormal data exists in the behavior information, the method further includes:
and mapping the numerical data in the behavior information according to a conversion function to obtain normalized behavior information.
In one embodiment, the determining, by a collaborative filtering algorithm, the vehicle model preferred by the vehicle purchasing user according to the preference value includes:
and acquiring the vehicle purchasing budget of the vehicle purchasing user, determining the vehicle type preferred by the vehicle purchasing user through a collaborative filtering algorithm according to the vehicle purchasing budget and the preference value, and pushing the vehicle type as recommendation information to the vehicle purchasing user.
According to another aspect of the present invention, there is provided a processing system of vehicle recommendation information, the system including a terminal, a camera, and a processor:
the camera device detects a car purchasing user and sends the acquired behavior information of the car purchasing user to the processor;
the processor inputs the behavior information into a pre-trained vehicle type preference value prediction model to calculate and obtain a preference value of the vehicle purchasing user for the vehicle type;
and the processor determines the vehicle type information preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm, and sends the determined vehicle type information to the terminal.
In one embodiment, the processor is further configured to invoke an emotion recognition interface to analyze expression data in the behavior information and obtain an expression recognition result;
the processor converts the voice data in the behavior information into text data, analyzes the text data through a TF-IDF algorithm and obtains a voice recognition result;
and the processor fuses the expression recognition result and the voice recognition result to the behavior information.
In one embodiment, the processor is further configured to input the behavior information into the predictive model and divide the behavior information into a training data set and a testing data set;
and the processor trains the prediction model according to the training data set and the test data set through an XGBOOST algorithm and acquires the preference value output by the prediction model.
According to another aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods described above when executing the computer program.
According to another aspect of the invention, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of any of the methods described above.
By adopting the vehicle recommendation information processing method, the system, the computer equipment and the storage medium, behavior information of the vehicle purchasing user acquired by the camera device is received; inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type; through a collaborative filtering algorithm, vehicle type information preferred by the vehicle purchasing user is determined according to the preference value, and the determined vehicle type information is sent to the terminal, so that the problem of low conversion rate of the vehicle purchasing cable in the processing method of the vehicle recommendation information is solved.
Drawings
FIG. 1 is a diagram illustrating an application scenario of a processing method according to an embodiment of the present invention;
FIG. 2 is a first flowchart of a method for processing vehicle recommendation information according to an embodiment of the present invention;
FIG. 3 is a flowchart II of a processing method of vehicle recommendation information according to an embodiment of the invention;
FIG. 4 is a flowchart III of a processing method of vehicle recommendation information according to an embodiment of the invention;
FIG. 5 is a fourth flowchart of a processing method of vehicle recommendation information according to an embodiment of the invention;
FIG. 6 is a fifth flowchart of a method for processing vehicle recommendation information according to an embodiment of the invention;
FIG. 7 is a sixth flowchart of a method for processing vehicle recommendation information according to an embodiment of the present invention;
FIG. 8 is a block diagram of a vehicle recommendation processing system according to an embodiment of the present invention;
fig. 9 is a block diagram of the inside of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the embodiment, an application scenario of a vehicle recommendation information processing method is provided, and fig. 1 is a schematic diagram of an application scenario of a processing method according to an embodiment of the present invention, as shown in fig. 1, in the application environment, a terminal 12 communicates with a server 14 through a network. The server 14 receives the behavior information of the vehicle purchasing user acquired by the camera device, acquires a preference value of the vehicle purchasing user for the vehicle type according to the behavior information, and determines the vehicle type preferred by the vehicle purchasing user according to the preference value; the server 14 pushes the vehicle model as recommendation information to the terminal 12. The terminal 12 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 14 may be implemented by an independent server or a server cluster composed of a plurality of servers.
In the present embodiment, a method for processing vehicle recommendation information is provided, and fig. 2 is a first flowchart of a method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 2, the method includes the following steps:
step S202, receiving behavior information of the vehicle purchasing user acquired by the camera device; wherein, 4 to 8 camera devices, such as probe cameras, are usually installed near each model booth in the automobile experience hall; the camera devices can record behavior information of the vehicle purchasing user at the vehicle model exhibition position, and the behavior information mainly comprises behavior data, voice data, expression data, experienced vehicle model data and the like of the vehicle purchasing user; the behavior data of the car purchasing user in the experience hall mainly comprises the stay time, the touch time, the car entering experience times and the like, and is shown in table 1:
TABLE 1 data sheet of behavior of user for purchasing car
User ID Experience shop ID Exhibition vehicle ID Length of dwell time Duration of touch … Number of times of vehicle entering
The voice data mainly includes inquiry questions of the car-buying user, communication of mood emotion, and car-entering experience voice data, etc., as shown in table 2:
TABLE 2 Voice data sheet for vehicle-purchasing users
User ID Experience shop ID Exhibition vehicle ID Speech segment ID Question asking … Exchange the voice
The expression data mainly comprises visiting vehicle expression data, entering vehicle body experience data and the like, and is shown in table 3:
TABLE 3 subscriber data sheet for purchasing car
User ID Experience shop ID Exhibition vehicle ID Time Visiting vehicle expression … Incoming vehicle body test surface condition
And meanwhile, acquiring user information filled by a vehicle purchasing user, wherein the user information mainly comprises data such as user name, gender, age, province and city area, telephone, vehicle purchasing budget, favorite brand and the like. Data of vehicle types are obtained from a database, and the data mainly comprise brands, vehicle series, vehicle types, guide prices, lowest prices, import modes, heat degrees and the like corresponding to the vehicles, as shown in table 4:
TABLE 4 subscriber information sheet for car purchase
User ID Sex Age (age) Province and city Telephone set Favorite brand … Heat of vehicle type
Through experience hall ID, user ID, exhibition car ID enter the car and associate, gather the data into a table, as shown in Table 5:
table 5 behavior information summary table
User ID Experience shop ID Exhibition vehicle ID Length of dwell time Duration of touch … Heat of vehicle type
Step S204, inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type; the prediction model can be trained according to the behavior information through algorithms such as XGBOOST and the like; the acquired data in table 5 is input to the prediction model, and finally the preference value is output.
Step S206, determining the vehicle type preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm; the method comprises the steps that vehicle types are sorted according to preference values of vehicle types of vehicle purchasing users through a collaborative filtering algorithm, corresponding vehicle types are output, and vehicle types interested by the users are sorted and output according to similarity among the vehicle types; in addition, the processor may push the determined vehicle type as recommendation information to the vehicle purchasing user through the terminal 12.
Through the steps S202 to S206, the acquired behavior information of the vehicle purchasing user is trained, the preference value of the vehicle purchasing user is calculated and acquired, determining the vehicle type preferred by the vehicle purchasing user according to the preference value, deeply mining the real emotional preference of the vehicle type of the user by acquiring the vehicle purchasing user in front of the vehicle experience hall for viewing the vehicle, the body action, the browsing duration and the like, as well as the expression data and the driving behavior data of the driving vehicle in the driving experience process, recommending based on the emotional preference of the vehicle purchasing user to different vehicle types and the vehicle purchasing information of the vehicle purchasing user, therefore, the preference of the vehicle purchasing user on the vehicle type is accurately mined and recommended accurately, the vehicle purchasing cable transaction rate is improved, the problem of low vehicle purchasing cable conversion rate in the vehicle recommendation information processing method is effectively solved, and the vehicle purchasing experience of the user is effectively improved.
In one embodiment, a method for processing vehicle recommendation information is provided, and fig. 3 is a second flowchart of a method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 3, the method includes the following steps:
step S302, calling an emotion recognition interface to analyze expression data in the behavior information and acquiring an expression recognition result; the text data can be analyzed through a TF-IDF (term frequency-inverse document frequency) algorithm in Natural Language Processing (NLP), and a voice recognition result is obtained; calculating the user car-watching tag data and the incoming car body test condition data; the car-viewing expression data of the car-purchasing user can be stored in the server 14 in a picture form, and for car-viewing expression data analysis of the car-purchasing user, the car-viewing picture can be acquired from the database, and Application Programming Interface (API) of emotion recognition of providers such as microsoft and the like is called to recognize task emotion data in the picture.
Step S304, converting the voice data in the behavior information into text data, converting the voice data of the car-buying user into the text data by calling the voice conversion character interface of suppliers such as science news flyers and the like, and extracting a text theme model and question emotion by using a TF-IDF algorithm.
And S306, the expression recognition result and the voice recognition result are fused to the behavior information, so that the real emotional preference of the vehicle purchasing user on the vehicle type is further accurately analyzed, and the accuracy of the processing method of the vehicle recommendation information is improved.
In one embodiment, a method for processing vehicle recommendation information is provided, and fig. 4 is a flowchart illustrating a third method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 4, the method includes the following steps:
step S402, dividing the behavior information into a training data set and a testing data set; the behavior information is divided into a plurality of parts in a crossed manner, wherein the plurality of parts are randomly selected as training data sets, and the rest parts are used as testing data sets; for example, the train _ test _ split () method of the sklern packet in python language may be called to randomly divide the behavior information into 10 parts, 7 as a training data set and 3 as a testing data set.
Step S404, acquiring the training model according to the training data set and the test data set through an XGBOOST algorithm; for example, an SVM class svm.svc (). fit () method in the sklern packet can be called to train the model, and the accuracy of the model is improved by adjusting the sample _ weight attribute parameter; then, svm.svc (). predict () method can be called to output the calculation result and return the preference value of the vehicle-purchasing user for the vehicle type.
Through the steps S402 to S404, the behavior information is trained through the XGBOOST algorithm, the preference value of the vehicle purchasing user to the vehicle type is obtained, effective analysis of the behavior information is achieved, and therefore processing efficiency of vehicle recommendation information is improved.
In one embodiment, a method for processing vehicle recommendation information is provided, and fig. 5 is a fourth flowchart of a method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 5, the method includes the following steps:
step S502, obtaining the vehicle type ID matched with the preference value, and calculating the similarity between other vehicle types in the vehicle type database and the vehicle type ID; for example, the emotional preference value of the vehicle-purchasing user A for the vehicle type C1 is 0.98, and the emotional preference value of A for C1 is shown in Table 6:
TABLE 6 Emotion preference value data sheet
Figure BDA0002428852930000081
All vehicle type data are acquired from the vehicle type database stored in the server 14, the similarity between other vehicle types in the vehicle type database and C1 is calculated, and the reverse order output is performed, as shown in table 7:
TABLE 7 vehicle type similarity data sheet
Figure BDA0002428852930000082
Step S504, according to the product of the preference value and the similarity, the corresponding preference value of the vehicle purchasing user to each vehicle type in the vehicle type database is obtained; wherein the corresponding preference value is calculated from the data in table 6 and table 7, as shown in formula 1:
corresponding preference value × similarity formula 1
Step S506, arranging the corresponding preference values in a reverse order, determining the vehicle type with the corresponding preference values in the top N, and pushing the vehicle information as recommendation information to the vehicle purchasing user; wherein N is a positive integer; for example, in the case where N is set to 5, a vehicle model with the corresponding preference value ranked in the top five is selected and recommended to the vehicle purchasing user; through the steps S502 to S504, the recommendable vehicle type is determined according to the similarity between the vehicle types and the emotion preference value, and therefore the vehicle type corresponding to the vehicle is recommended to the vehicle purchasing user in a self-adaptive mode.
In one embodiment, a method for processing vehicle recommendation information is provided, and fig. 6 is a flowchart five of a method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 6, the method includes the following steps:
step S602, acquiring the behavior information after data filling under the condition that the behavior information has a missing value; the method can use a descriptor () method of the pandas package in the python language to check whether each attribute data in the behavior information has a missing value, and if the missing value exists, the missing data is processed; the missing data processing is mainly judged according to the type of the attribute data, and if the attribute data type is a character type, mode filling is used; if the attribute data type is a numerical type, filling by using a median; for example, in the case where there is a missing value in the age data in the behavior information, the median of the age data may be selected to fill in the missing value.
Step S604, according to a Box-plot (Box-plot) detection method, abnormal data detection is carried out on the behavior information filled with the data; acquiring the behavior information filled with the median under the condition that the behavior information has abnormal data; processing is performed according to data distribution in the behavior information, for example, abnormal data is obtained when the data distribution is more than 0.95 or less than 0.05 in the box diagram; usually, a median filling method is adopted for processing abnormal data, if the age data of the car purchasing user is greater than 90, the age data can be considered as abnormal data, and the abnormal data is replaced according to the median of the age data.
In addition, data conversion can be carried out on data in the behavior information, and character type data in the attribute data are mainly converted into numerical type data, so that the processor can better identify the attribute data in the behavior information; for example, the gender value of the car-buying user is converted as follows: the gender values of the user before conversion are male and female, and the gender data values after conversion are 0 and 1.
Through the steps S602 to S604, the data in the behavior information is processed, and the phenomenon of data missing or abnormity in the process of inputting the training model is avoided, so that the efficiency and the accuracy of the processing method of the vehicle recommendation information are effectively improved.
In one embodiment, a method for processing vehicle recommendation information is provided, and fig. 7 is a flowchart of a sixth method for processing vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 7, the method includes the following steps:
step S702, mapping the numerical data in the behavior information according to a conversion function to obtain normalized behavior information; wherein, the normalization operation of the numerical data is mainly to map the numerical data into a [0, 1] data interval; for example, the numerical data is processed according to a normalization formula, as shown in formula 2:
Figure BDA0002428852930000101
wherein D isx,iIndicates the i-th value, D, corresponding to the attribute xx,maxRepresents the maximum value, D, of the attribute xx,minRepresents the minimum value in the attribute x; through the normalization processing, the behavior information after the data processing can better adapt to the output of the training model, and meanwhile, the calculation error is reduced, so that the accuracy of the processing method of the vehicle recommendation information is further improved.
In one embodiment, a method for processing vehicle recommendation information is provided, which includes the following steps:
step S802, acquiring the vehicle purchasing budget of the vehicle purchasing user, determining the vehicle type preferred by the vehicle purchasing user through a collaborative filtering algorithm according to the vehicle purchasing budget and the preference value, and pushing the vehicle type as recommendation information to the vehicle purchasing user; the vehicle recommendation method and the system have the advantages that the vehicle purchasing budget of the vehicle purchasing user is considered, so that the vehicle recommendation is more in line with the actual situation and expectation of the vehicle purchasing user, and the vehicle purchasing experience of the vehicle purchasing user is further improved.
It should be understood that, although the steps in the flowcharts of fig. 2 to 7 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
In the present embodiment, a processing system for vehicle recommendation information is provided, and fig. 8 is a block diagram of a configuration of a processing system for vehicle recommendation information according to an embodiment of the present invention, as shown in fig. 8, the system includes a camera 82 and a processor 84:
the camera 82 detects a car purchasing user, and sends the acquired behavior information of the car purchasing user to the processor 84;
the processor 84 inputs the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type;
the processor 84 determines vehicle type information preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm, and transmits the determined vehicle type information to the terminal.
Through the embodiment, the behavior information of the car purchasing user acquired by the camera device 82 is trained through the processor 84, the emotion preference value of the car purchasing user is calculated and acquired, the processor 84 determines the vehicle type preferred by the car purchasing user according to the emotion preference value, the real emotion preference of the car purchasing user on the vehicle type is deeply mined by acquiring the car purchasing user's car-viewing expression, limb action, browsing duration and the like in front of each vehicle type in the car experience hall and the expression data and driving behavior data of the driving vehicle in the driving experience process, and the car purchasing information of the user and different vehicle type emotion preferences are recommended based on the user, so that the car purchasing line contract rate is improved, the problem of low conversion rate of the car purchasing line in the processing method of the vehicle recommendation information is effectively solved, and the car purchasing experience of the user is also effectively improved.
In one embodiment, the processor 84 is further configured to invoke an emotion recognition interface to analyze the expression data in the behavior information and obtain an expression recognition result;
the processor 84 converts the voice data in the behavior information into text data, analyzes the text data through a TF-IDF algorithm, and obtains a voice recognition result;
the processor 84 fuses the expression recognition result and the voice recognition result to the behavior information.
In one embodiment, the processor 84 is further configured to divide the behavioral information into a training data set and a testing data set;
the processor 84 obtains the preference value output by the prediction model according to the training data set and the testing data set through the XGBOOST algorithm.
In one embodiment, the processor 84 is further configured to obtain a vehicle type ID matching the preference value, and calculate similarity between other vehicle types in the vehicle type database and the vehicle type ID;
the processor 84 obtains the corresponding preference value of the vehicle purchasing user for each vehicle type in the vehicle type database according to the product of the preference value and the similarity;
the processor 84 arranges the corresponding preference values in a reverse order, determines the vehicle type with the corresponding preference values arranged in the top N digits, and pushes the vehicle information as recommendation information to the vehicle purchasing user; wherein N is a positive integer.
In one embodiment, the processor 84 is further configured to obtain the behavior information after data padding if the behavior information has a missing value;
the processor 84 performs abnormal data detection on the behavior information after the data filling according to a boxmap detection method; and acquiring the behavior information filled with the median when the behavior information has abnormal data.
In one embodiment, the processor 84 is further configured to map the numerical data in the behavior information according to a conversion function to obtain normalized behavior information.
In one embodiment, the processor 84 is further configured to obtain a vehicle purchasing budget of the vehicle purchasing user, determine a vehicle type preferred by the vehicle purchasing user through a collaborative filtering algorithm according to the vehicle purchasing budget and the preference value, and push the vehicle type to the vehicle purchasing user as recommendation information.
In one embodiment, a computer device is provided, and the computer device may be a server, and fig. 9 is a structural diagram of the inside of the computer device according to the embodiment of the present invention, as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing behavior information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a vehicle recommendation information processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the vehicle recommendation information processing method provided in the above embodiments.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps in the vehicle recommendation information processing method provided by the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method for processing vehicle recommendation information, the method comprising:
receiving behavior information of a vehicle purchasing user acquired by a camera device;
inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type;
and determining vehicle type information preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm, and sending the determined vehicle type information to a terminal.
2. The method according to claim 1, wherein after receiving behavior information of a vehicle-purchasing user acquired by the camera device and before inputting the behavior information into a vehicle type preference value prediction model trained in advance, the method further comprises:
calling an emotion recognition interface to analyze expression data in the behavior information and acquiring an expression recognition result;
converting the voice data in the behavior information into text data, analyzing the text data through a TF-IDF algorithm, and acquiring a voice recognition result;
and fusing the expression recognition result and the voice recognition result to the behavior information.
3. The method of claim 1, wherein the inputting the behavior information into a pre-trained vehicle type preference value prediction model to obtain the preference value of the vehicle purchasing user for the vehicle type comprises:
inputting the behavior information into the prediction model, and dividing the behavior information into a training data set and a testing data set;
training the prediction model according to the training data set and the test data set through an XGBOOST algorithm, and acquiring the preference value output by the prediction model.
4. The method of claim 1, wherein the determining vehicle model information preferred by the purchasing user according to the preference value through a collaborative filtering algorithm comprises:
acquiring the vehicle type ID matched with the preference value, and calculating the similarity between other vehicle types in a vehicle type database and the vehicle type ID;
according to the product of the preference value and the similarity, acquiring the corresponding preference value of the vehicle purchasing user to each vehicle type in the vehicle type database;
arranging the corresponding preference values in a reverse order, determining the vehicle models with the corresponding preference values in the top N, and pushing the vehicle information serving as recommendation information to the vehicle purchasing user; wherein N is a positive integer.
5. The method according to claim 1, wherein after receiving behavior information of a vehicle-purchasing user acquired by the camera device and before inputting the behavior information into a vehicle type preference value prediction model trained in advance, the method further comprises:
acquiring behavior information after data filling under the condition that the behavior information has a missing value;
according to a boxchart detection method, abnormal data detection is carried out on the behavior information after the data filling; and acquiring the behavior information filled with the median under the condition that the behavior information has abnormal data.
6. The method according to claim 5, wherein after obtaining the behavior information after filling the median in the case of the abnormal data in the behavior information, the method further comprises:
and mapping the numerical data in the behavior information according to a conversion function to obtain normalized behavior information.
7. The method of any one of claims 1 to 6, wherein the determining, by a collaborative filtering algorithm, the vehicle model preferred by the purchasing user according to the preference value comprises:
and acquiring the vehicle purchasing budget of the vehicle purchasing user, determining the vehicle type preferred by the vehicle purchasing user through a collaborative filtering algorithm according to the vehicle purchasing budget and the preference value, and pushing the vehicle type as recommendation information to the vehicle purchasing user.
8. A processing system of vehicle recommendation information is characterized in that the system comprises a terminal, a camera device and a processor:
the camera device detects a car purchasing user and sends the acquired behavior information of the car purchasing user to the processor;
the processor inputs the behavior information into a pre-trained vehicle type preference value prediction model to obtain a preference value of the vehicle purchasing user for the vehicle type;
and the processor determines the vehicle type information preferred by the vehicle purchasing user according to the preference value through a collaborative filtering algorithm, and sends the determined vehicle type information to the terminal.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN202010229460.7A 2020-03-27 2020-03-27 Method and system for processing vehicle recommendation information, computer equipment and storage medium Pending CN113450169A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010229460.7A CN113450169A (en) 2020-03-27 2020-03-27 Method and system for processing vehicle recommendation information, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010229460.7A CN113450169A (en) 2020-03-27 2020-03-27 Method and system for processing vehicle recommendation information, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113450169A true CN113450169A (en) 2021-09-28

Family

ID=77807811

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010229460.7A Pending CN113450169A (en) 2020-03-27 2020-03-27 Method and system for processing vehicle recommendation information, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113450169A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114564655A (en) * 2021-12-23 2022-05-31 北京中交兴路信息科技有限公司 Collaborative filtering-based vehicle recommendation method, device, equipment and storage medium
CN114971123A (en) * 2021-11-29 2022-08-30 广东轻工职业技术学院 Convenient and effective automobile evaluation method and system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446635A (en) * 2018-03-19 2018-08-24 西北大学 It is a kind of to obtain Collaborative Filtering Recommendation System and method using EEG signals auxiliary preference
CN109064265A (en) * 2018-07-13 2018-12-21 惠龙易通国际物流股份有限公司 Purchase vehicle recommended method and system based on the network platform
CN109685611A (en) * 2018-12-15 2019-04-26 深圳壹账通智能科技有限公司 A kind of Products Show method, apparatus, computer equipment and storage medium
CN110249360A (en) * 2017-02-01 2019-09-17 三星电子株式会社 Device and method for recommended products
US10475105B1 (en) * 2018-07-13 2019-11-12 Capital One Services, Llc Systems and methods for providing improved recommendations
CN110458663A (en) * 2019-08-06 2019-11-15 上海新共赢信息科技有限公司 A kind of vehicle recommended method, device, equipment and storage medium
US10482523B1 (en) * 2019-07-09 2019-11-19 Capital One Services, Llc Methods and systems for providing purchase recommendations based on responses to inquiries on product attributes

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110249360A (en) * 2017-02-01 2019-09-17 三星电子株式会社 Device and method for recommended products
CN108446635A (en) * 2018-03-19 2018-08-24 西北大学 It is a kind of to obtain Collaborative Filtering Recommendation System and method using EEG signals auxiliary preference
CN109064265A (en) * 2018-07-13 2018-12-21 惠龙易通国际物流股份有限公司 Purchase vehicle recommended method and system based on the network platform
US10475105B1 (en) * 2018-07-13 2019-11-12 Capital One Services, Llc Systems and methods for providing improved recommendations
CN109685611A (en) * 2018-12-15 2019-04-26 深圳壹账通智能科技有限公司 A kind of Products Show method, apparatus, computer equipment and storage medium
US10482523B1 (en) * 2019-07-09 2019-11-19 Capital One Services, Llc Methods and systems for providing purchase recommendations based on responses to inquiries on product attributes
CN110458663A (en) * 2019-08-06 2019-11-15 上海新共赢信息科技有限公司 A kind of vehicle recommended method, device, equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
梁策: "宾利推出新App用面部识别帮你选择合适车型", 《HTTPS://SOCIALBETA.COM/T/97894》, 19 November 2015 (2015-11-19), pages 1 - 2 *
陈果等: "基于人脸识别的商品推荐系统的设计与实现", 《计算机时代》, no. 11, 15 November 2018 (2018-11-15), pages 56 - 59 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114971123A (en) * 2021-11-29 2022-08-30 广东轻工职业技术学院 Convenient and effective automobile evaluation method and system
CN114564655A (en) * 2021-12-23 2022-05-31 北京中交兴路信息科技有限公司 Collaborative filtering-based vehicle recommendation method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN109345374B (en) Risk control method and device, computer equipment and storage medium
CN109729383B (en) Double-recording video quality detection method and device, computer equipment and storage medium
WO2021027317A1 (en) Relationship network-based attribute information processing method and device, computer apparatus, and storage medium
US11188928B2 (en) Marketing method and apparatus based on deep reinforcement learning
CN109783730A (en) Products Show method, apparatus, computer equipment and storage medium
WO2020253357A1 (en) Data product recommendation method and apparatus, computer device and storage medium
CN110738545A (en) Product recommendation method and device based on user intention identification, computer equipment and storage medium
CN112395979B (en) Image-based health state identification method, device, equipment and storage medium
CN111079056A (en) Method, device, computer equipment and storage medium for extracting user portrait
CN112395500B (en) Content data recommendation method, device, computer equipment and storage medium
CN112035611B (en) Target user recommendation method, device, computer equipment and storage medium
CN110750523A (en) Data annotation method, system, computer equipment and storage medium
CN110020022B (en) Data processing method, device, equipment and readable storage medium
CN113157863A (en) Question and answer data processing method and device, computer equipment and storage medium
CN111159570B (en) Information recommendation method and server
CN114461871B (en) Recommendation model training method, object recommendation device and storage medium
CN113450169A (en) Method and system for processing vehicle recommendation information, computer equipment and storage medium
CN112287068A (en) Artificial intelligence-based inquiry dialogue data processing method and device
CN110163151B (en) Training method and device of face model, computer equipment and storage medium
CN111782782B (en) Consultation reply method and device for intelligent customer service, computer equipment and storage medium
CN113420203A (en) Object recommendation method and device, electronic equipment and storage medium
CN109003193B (en) Method, device, computer equipment and storage medium for predicting insurance risk
CN110717094A (en) Information recommendation method and device, computer equipment and storage medium
CN110750628A (en) Session information interaction processing method and device, computer equipment and storage medium
CN111161009A (en) Information pushing method and device, computer 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210928