CN116932921B - Personalized recommendation method and related equipment for automobiles - Google Patents
Personalized recommendation method and related equipment for automobiles Download PDFInfo
- Publication number
- CN116932921B CN116932921B CN202311199555.9A CN202311199555A CN116932921B CN 116932921 B CN116932921 B CN 116932921B CN 202311199555 A CN202311199555 A CN 202311199555A CN 116932921 B CN116932921 B CN 116932921B
- Authority
- CN
- China
- Prior art keywords
- scoring
- public praise
- complaint
- index
- aggregate
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 52
- 238000011076 safety test Methods 0.000 claims abstract description 43
- 239000013598 vector Substances 0.000 claims abstract description 25
- 230000002776 aggregation Effects 0.000 claims description 34
- 238000004220 aggregation Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 19
- 230000007246 mechanism Effects 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an automobile personalized recommendation method and related equipment, comprising the following steps: obtaining user scoring data, complaint data and safety test data; extracting satisfaction data to divide the grade of the scoring public praise index and obtaining a scoring public praise aggregate value; extracting risk degree data of various automobiles, calculating the ratio of complaint quantity to sales quantity of various automobiles, constructing a complaint occurrence index grade, and obtaining a complaint quality public praise aggregate value; scoring the safety indexes of various automobiles to construct a safety evaluation grade and obtaining a safety scoring aggregate value; setting the index weights as mean weights, calculating a three-dimensional grading aggregate value, four-dimensional vectors comprising grading public praise, complaint quality public praise, safety grading and three-dimensional grading aggregate mean values, and selecting a preliminary recommended vehicle set based on the four-dimensional vectors; finally, a final recommended vehicle set is screened out from the initial recommended vehicle set; and the automobile recommendation method is convenient and efficient for the user from the aspects of user evaluation, complaints and safety test.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an automobile personalized recommendation method and related equipment.
Background
With the rapid development of socioeconomic performance, highway construction is becoming more popular, and the number of motorists is increasing. At present, in the scheme of recommending automobile purchasing, the traditional method is mainly divided into two types, one is a recommending method based on professionals, by collecting information of demands of users, such as prices, brands, automobile types and the like, and then professional persons familiar with automobile markets give out a plurality of candidates by virtue of personal experience; the second method is that the user learns by himself, the user with the intention of purchasing the vehicle observes the website of each automobile vertical and the 4S shop of different automobiles according to the own demand, and then selects the automobile model which is considered to be suitable by himself.
Since the public has little knowledge about automobiles in the previous years, the first professional-based recommendation method is the mainstream method for acquiring the candidate list of automobile purchasing, however, the problem of the method is that if a third party professional is found, the price is not good, and if a majority of consultants provided by automobile manufacturers are aimed at selling products of the users; another problem is that different professionals may have the same user demand due to personal preference characteristics, and candidate vehicle types given by different professionals are different, and cannot be recommended to the user efficiently.
For the second method of self learning of users, although the threshold of learning new domain knowledge of users becomes lower and lower along with the rapid development of information age, a certain technical barrier still exists between different domain knowledge, the automobile domain contains a large amount of professional technical knowledge due to the numerous involved domains, the ordinary non-background personnel learning cost is higher, and secondly, the time and effort of each user are limited, the learned vehicle model, the learned data and the data observed in 4S shop are limited, so that a certain condition of incomplete data samples exists, and some high-quality vehicle models do not enter a candidate list, namely, the selection made on the limited sample data sometimes ignores the high-quality vehicle models except the sample.
Disclosure of Invention
The invention provides an automobile personalized recommendation method and related equipment, and aims to provide convenient and efficient automobile recommendation for users from the aspects of user evaluation, complaints and safety test.
In order to achieve the above object, the present invention provides an automobile personalized recommendation method, comprising:
step 1, constructing a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set based on user scoring data, complaint data and safety test data in a plurality of target automobile consultation platforms;
step 2, extracting satisfaction data of users in the scoring public praise index set on various automobiles, dividing scoring public praise index levels according to the satisfaction data and obtaining scoring public praise aggregate values;
step 3, extracting risk degree data of various automobiles according to the complaint quality public praise index set, calculating the ratio of complaint quantity to sales quantity of various automobiles in the complaint quality public praise index set, constructing a complaint occurrence index grade according to the ratio of the complaint quantity to the sales quantity, and obtaining a complaint quality public praise aggregate value;
step 4, scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
step 5, setting the index weights of the scoring public praise index set, the complaint quality public praise index set and the safety test evaluation index set as mean weights, and calculating a three-dimensional scoring aggregate value through the mean weights;
step 6, calculating four-dimensional vectors of the aggregate mean values including the score public praise aggregate value, the complaint quality public praise aggregate value, the safety score aggregate value and the three-dimensional score aggregate value according to the mean value weight, and calculating the sorting percentage of the alternative vehicle aggregate mean values and the sorting percentage of the vehicles expected by the user to select a preliminary recommended vehicle set based on the four-dimensional vectors;
and 7, acquiring an expected aggregation value through a constructed recommendation mechanism based on the expected weight of the user personalized index, and screening a final recommended vehicle set from the initial recommended vehicle set based on the expected aggregation value.
Further, step 2 includes:
the method comprises the steps of extracting satisfaction degree data of users to various automobiles in a grading public praise index set, and dividing grading public praise index grades based on a grading index system of a target automobile consultation platform and the satisfaction degree data of the users to the various automobiles into the following steps:
scoring index system based on target automobile consultation platform, satisfaction data of users on various automobiles and scoring public praise index grade to obtain scoring public praise aggregate value：
Wherein,presentation of user scoring public praiseTarget automobile consultation platformIs used for the weight of the (c),，presentation of user scoring public praiseIs provided with a number of platforms of the same type,indicating scoring public praise indexIs used for the weight of the (c),，represents the number of indicators in the scoring indicator system,target automobile consultation platformFor vehicle indexIs used for the grading of the (c) in the (c),。
further, step 3 includes:
constructing a complaint quality public praise grade library based on expert knowledge;
extracting risk degree data of various automobiles according to complaint contents in the complaint quality public praise index set;
the complaint quality public praise index grade is divided based on the complaint quality public praise grade library and the risk degree data as follows:
calculating the ratio of sales volume to complaint volume of various automobiles in the complaint quality public praise index set, and dividing the sales volume complaint measurement level into:
acquiring a complaint quality public praise aggregate value based on a complaint quality public praise index level and a sales complaint measurement levelThe method comprises the following steps:
wherein,target automobile consultation platformIndex in the middle complaint quality public praise index setIs classified into gradesIs used for the number of complaints of (a),，representing the number of platforms providing user complaint dictation,，represents the number of indicators in the complaint quality public praise indicators set,a grade value representing a complaint quality public praise,representing provision of complaint quality public praiseTarget automobile consultation platformIs used for the weight of the (c),public praise index for representing complaint qualityThe weight of the material to be weighed,and expressing the sales volume complaint measure grade, and constructing a calculation formula based on the sales volume and the complaint volume, wherein the calculation formula is as follows:
wherein,indicating sales.
Further, step 4 includes:
scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
scoring the safety indexes of various automobiles in the safety test evaluation index set based on the scoring rate of the safety test indexes to obtain scoring results;
the security assessment grade is constructed based on the scoring result:
acquiring security score aggregate values based on security assessment levelsThe method comprises the following steps:
wherein,representing providing security assessmentTarget automobile consultation platformIs used for the weight of the (c),，representing providing securityFull assessmentIs provided with a number of platforms of the same type,index representing security assessmentIs used for the weight of the (c),，representing the number of indicators in the security test evaluation indicator set,an index weight representing the security assessment is provided,representing a security assessment level value.
Further, the aggregate value of the three-dimensional scoreThe method comprises the following steps:
wherein,、、respectively scoring the weight of the public praise index, the weight of the public praise index of the complaint quality and the weight of the security evaluation index,，。
further, four-dimensional vectorsThe method comprises the following steps:
wherein,representing the aggregate mean of the scored public praise aggregate values,an aggregate mean value representing the aggregate value of the complaint mass public praise,represents an aggregate mean of the aggregate values of the security scores,representing the aggregate mean of the aggregate values of the three-dimensional scores.
Further, selecting the preliminary recommended vehicle set based on the ranking percentage of the aggregate mean of the candidate vehicles and the ranking percentage of the user expected value obtained by the four-dimensional vector comprises:
the ranking percentage of the aggregate average of the candidate vehicles is calculated based on the four-dimensional vector as follows:
wherein,respectively representing the sorting percentages of the candidate vehicles in the scoring public praise aggregation mean value, the complaint quality public praise aggregation mean value, the security scoring aggregation mean value and the three-dimensional aggregation mean value;
the ranking percentage of the user expected value is calculated based on the four-dimensional vector as follows:
wherein,respectively representing the ordering percentages of the vehicle expected by the user in the scoring public praise aggregation mean value, the complaint quality public praise aggregation mean value, the security scoring aggregation mean value and the three-dimensional aggregation mean value;
selecting a preliminary recommended vehicle set based on the sorting percentage of the aggregate mean value of the candidate vehicles acquired by the four-dimensional vector as follows:
wherein,a set of preliminary recommended vehicles is represented,representing a vehicle meeting the constraints.
Further, obtaining a desired aggregation value through a constructed recommendation mechanism based on user personalized index desired weight, and screening a final recommended vehicle set from the preliminary recommended vehicle set based on the desired aggregation value, including:
defining a user personalized index expected weight value;
a recommendation mechanism is formulated based on the user personalized index expected weight value;
calculating expected aggregation values of all automobiles in the primary recommended vehicle set according to a recommendation mechanism;
and acquiring a final recommended vehicle set according to the expected aggregation value.
The invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the personalized recommendation method of the automobile when being executed by a processor.
The invention also provides a terminal device which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the personalized recommendation method of the automobile when executing the computer program.
The scheme of the invention has the following beneficial effects:
the invention constructs a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set based on user scoring data, complaint data and safety test data in a plurality of target automobile consultation platforms; the satisfaction data of the users on various automobiles in the scoring public praise index set are extracted, scoring public praise index grades are divided, and scoring public praise aggregate values are obtained; extracting risk degree data of various automobiles and the ratio of complaint quantity to sales quantity of various automobiles according to a complaint quality public praise index set, constructing a complaint occurrence index grade and acquiring a complaint quality public praise aggregate value; scoring the safety indexes of various automobiles according to the safety test evaluation index set to construct a safety evaluation grade and obtaining a safety scoring aggregate value; setting the index weights of the scoring public praise index set, the complaint quality public praise index set and the safety test evaluation index set as mean weights, and calculating a three-dimensional scoring aggregate value; calculating a four-dimensional vector according to the average weight, and calculating the sorting percentage of the aggregate average of the candidate vehicles and the sorting percentage of the vehicles expected by the user to select a primary recommended vehicle set; acquiring an expected aggregation value through a constructed recommendation mechanism based on user personalized index expected weight, and screening a final recommended vehicle set from the initial recommended vehicle set based on the expected aggregation value; compared with the prior art, the automobile recommendation method and the automobile recommendation system provide convenient and efficient automobile recommendation for users from the aspects of user evaluation, complaints and safety test, and improve the comprehensiveness of automobile recommendation.
Other advantageous effects of the present invention will be described in detail in the detailed description section which follows.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, a locked connection, a removable connection, or an integral connection; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
Aiming at the existing problems, the invention provides an automobile personalized recommendation method and related equipment.
As shown in fig. 1, an embodiment of the present invention provides an automobile personalized recommendation method, including:
step 1, constructing a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set based on user scoring data, complaint data and safety test data in a plurality of target automobile consultation platforms;
step 2, extracting satisfaction data of users in the scoring public praise index set on various automobiles, dividing scoring public praise index levels according to the satisfaction data and obtaining scoring public praise aggregate values;
step 3, extracting risk degree data of various automobiles according to the complaint quality public praise index set, calculating the ratio of complaint quantity to sales quantity of various automobiles in the complaint quality public praise index set, constructing a complaint occurrence index grade according to the ratio of the complaint quantity to the sales quantity, and obtaining a complaint quality public praise aggregate value;
step 4, scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
step 5, setting the index weights of the scoring public praise index set, the complaint quality public praise index set and the safety test evaluation index set as mean weights, and calculating a three-dimensional scoring aggregate value through the mean weights;
step 6, calculating four-dimensional vectors of the aggregate mean values including the score public praise aggregate value, the complaint quality public praise aggregate value, the safety score aggregate value and the three-dimensional score aggregate value according to the mean value weight, and calculating the sorting percentage of the alternative vehicle aggregate mean values and the sorting percentage of the vehicles expected by the user to select a preliminary recommended vehicle set based on the four-dimensional vectors;
and 7, acquiring an expected aggregation value through a constructed recommendation mechanism based on the expected weight of the user personalized index, and screening a final recommended vehicle set from the initial recommended vehicle set based on the expected aggregation value.
Specifically, step 1 includes:
according to the embodiment of the invention, the data of a plurality of target automobile consultation platforms are obtained through a Python tool, for example, the public praise data in a public praise module in an automobile scoring public praise platform is used as user evaluation data, the complaint data in a complaint module in an automobile quality complaint platform is used as user complaint data, and the evaluation data in an evaluation result plate in an automobile safety test platform is used as safety test data to construct a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set, and the scoring public praise index set, the public praise data and the safety test evaluation index set are classified according to automobile types and stored in a local database;
wherein, the scoring public praise index set is:
the complaint quality public praise index set is as follows:
the safety test evaluation index set is as follows:
。
specifically, step 2 includes:
the method comprises the steps of extracting satisfaction data of users to various automobiles in a grading public praise index set, dividing grading public praise index grades based on a grading index system of an automobile grading public praise platform and the satisfaction data of the users to various automobiles, wherein the higher the index grade of the user to the automobile is, the higher the grade of the automobile under the index is, and the grading public praise index grade is:
scoring index system based on automobile scoring public praise platform, satisfaction data of users on various automobiles and scoring public praise index grade to obtain scoring public praise aggregate value：
Wherein,presentation of user scoring public praiseAutomobile scoring public praise platformIs used for the weight of the (c),，presentation of user scoring public praiseIs provided with a number of platforms of the same type,satisfy the following requirements，Indicating scoring public praise indexIs used for the weight of the (c),，represents the number of indicators in the scoring indicator system,satisfy the following requirements，Praise platform for indicating automobile scoringFor scoring public praise indexIs used for the grading of the (c) in the (c),。
specifically, step 3 includes:
constructing a library of complaint quality public praise grades based on expert knowledge, as shown in the following table 1, the higher the grade is, the better the quality public praise is, the lower the risk is:
TABLE 1
Extracting risk degree data of various automobiles according to complaint contents in the complaint quality public praise index set;
the complaint quality public praise index grade is divided based on the complaint quality public praise grade library and the risk degree data as follows:
calculating the ratio of sales volume to complaint volume of various automobiles in a complaint quality public praise index set, dividing the complaint measurement grade of sales volume, wherein the higher the grade is, the lower the complaint index is, and the dividing the complaint measurement grade of sales volume is as follows:
acquiring a complaint quality public praise aggregate value based on a complaint quality public praise index level and a sales complaint measurement levelThe method comprises the following steps:
wherein,platform for representing automobile quality complaintsIndex in the middle complaint quality public praise index setIs classified into gradesIs used in the number of (a) and (b),，，representing the number of platforms providing user complaint dictation,，represents the number of indicators in the complaint quality public praise indicators set,a grade value representing a complaint quality public praise,，representing provision of complaint quality public praiseAutomobile quality complaint platformWeights of (2) satisfy，Public praise index for representing complaint qualityWeights of (2) satisfy，Representing a sales complaint measure class,the calculation formula is constructed based on sales and complaints:
wherein,indicating sales.
Specifically, step 4 includes:
scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
scoring the safety indexes of various automobiles in the safety test evaluation index set based on the scoring rate (0% -100%) of the safety test indexes to obtain scoring results;
based on the grading result, constructing a safety evaluation grade, wherein the higher the grade is, the higher the vehicle safety index is, and the safety evaluation grade is:
acquiring security score aggregate values based on security assessment levelsThe method comprises the following steps:
wherein,representing providing security assessmentAutomobile safety test platformIs used for the weight of the (c),，representing providing security assessmentThe number of platforms of (2) satisfies，Index representing security assessmentIs used for the weight of the (c),，the number of indexes in the safety test evaluation index set is represented, and the requirements are met，Representing security assessmentIs used for the level value of (c),。
specifically, three-dimensional score aggregate valuesThe method comprises the following steps:
wherein,、、respectively scoring the weight of the public praise index, the weight of the public praise index of the complaint quality and the weight of the security evaluation index,，。
specifically, step 6 includes:
the user determines the set of candidate vehicles as:
calculating a four-dimensional vector of an aggregate mean value comprising a scoring public praise aggregate value, a complaint quality public praise aggregate value, a security scoring aggregate value and a three-dimensional scoring aggregate value according to the mean value weight;
homogenizing the weight of the scoring public praise platform:
homogenizing scoring public praise index weights:
the aggregate mean value of the scoring public praise aggregate value is obtained as follows:
homogenizing the weight of an automobile quality complaint platform:
homogenizing the complaint quality public praise index weight:
sales complaint measure weight
The aggregate mean value of the complaint mass public praise aggregate value is obtained as follows:
homogenizing the weight of an automobile safety test platform:
homogenizing the weight of the safety test evaluation index:
the aggregate mean value of the security score aggregate value is obtained as follows:
the aggregate mean of the three-dimensional scoring aggregate values is:
four-dimensional vectorThe method comprises the following steps:
wherein,representing the aggregate mean of the scored public praise aggregate values,an aggregate mean value representing the aggregate value of the complaint mass public praise,represents an aggregate mean of the aggregate values of the security scores,representing an aggregate mean of the three-dimensional degree scoring aggregate values;
after homogenization based on the weights of the platform and the index, the aggregate mean of the candidate vehicles is shown in table 2 below:
TABLE 2
Calculating the sorting percentage of the aggregate mean value of the alternative vehicles based on the four-dimensional vector;
wherein,the ranking percentages of the candidate vehicles in the scoring public praise aggregate mean, the complaint quality public praise aggregate mean, the security scoring aggregate mean and the three-dimensional aggregate mean are respectively shown in the following table 3:
TABLE 3 Table 3
The ranking percentage of the user expected value is calculated based on the four-dimensional vector as follows:
wherein,the ranking percentages of the user expected vehicles in the scoring public praise aggregate mean, the complaint quality public praise aggregate mean, the security scoring aggregate mean and the three-dimensional aggregate mean are respectively shown in the following table 4:
TABLE 4 Table 4
Selecting a preliminary recommended vehicle set based on the sorting percentage of the aggregate mean value of the candidate vehicles acquired by the four-dimensional vector as follows:
wherein,a set of preliminary recommended vehicles is represented,representing a vehicle meeting the constraints.
The specific initial recommended vehicle set in the embodiment of the invention is as follows:
。
specifically, step 7 includes:
the user personalized index expected weight is determined as follows:
the personalized expected weights of the scoring public praise indexes are as follows:；
the personalized expected weights for each scoring public address index are shown in table 5 below:
TABLE 5
The complaint quality public praise index personalized expected weight is as follows:；
the individual expected weights for each complaint quality public-address index are shown in table 6 below:
TABLE 6
The personalized expected weight of the security test evaluation index is as follows:；
the individual expected weights of the individual security test evaluation indexes are shown in table 7 below:
TABLE 7
The personalized expected weight of the sales complaint measure is as follows:；
the three-dimensional degree score aggregate expected weight is:，，；
the personalized expected weights for the three-dimensional score aggregation when scoring the public praise preferences are shown in table 8 below, the personalized expected weights for the three-dimensional score aggregation when complaining quality public praise preferences are shown in table 9 below, and the personalized expected weights for the three-dimensional score aggregation when security assessment preferences are shown in table 10 below:
TABLE 8
TABLE 9
Table 10
The expected aggregate value is obtained as follows:
the personalized expected aggregate values for the candidate vehicles when scoring the public praise preferences are shown in table 11 below, the personalized expected aggregate values for the candidate vehicles when grading the complaint quality public praise preferences are shown in table 12 below, and the personalized expected aggregate values for the candidate vehicles when evaluating the security evaluation preferences are shown in table 13 below:
TABLE 11
Table 12
TABLE 13
The final recommended vehicle set is screened from the preliminary recommended vehicle set based on the expected aggregate value as follows:
when scoring the public praise preference conditions:
when complaint quality is a public praise preference:
when the security assessment preference conditions:
。
the embodiment of the invention constructs a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set based on user scoring data, complaint data and safety test data in a plurality of target automobile consultation platforms; the satisfaction data of the users on various automobiles in the scoring public praise index set are extracted, scoring public praise index grades are divided, and scoring public praise aggregate values are obtained; extracting risk degree data of various automobiles and the ratio of complaint quantity to sales quantity of various automobiles according to a complaint quality public praise index set, constructing a complaint occurrence index grade and acquiring a complaint quality public praise aggregate value; scoring the safety indexes of various automobiles according to the safety test evaluation index set to construct a safety evaluation grade and obtaining a safety scoring aggregate value; setting the index weights of the scoring public praise index set, the complaint quality public praise index set and the safety test evaluation index set as mean weights, and calculating a three-dimensional scoring aggregate value; calculating a four-dimensional vector according to the average weight, and calculating the sorting percentage of the aggregate average of the candidate vehicles and the sorting percentage of the vehicles expected by the user to select a primary recommended vehicle set; acquiring an expected aggregation value through a constructed recommendation mechanism based on user personalized index expected weight, and screening a final recommended vehicle set from the initial recommended vehicle set based on the expected aggregation value; compared with the prior art, the automobile recommendation method and the automobile recommendation system provide convenient and efficient automobile recommendation for users from the aspects of user evaluation, complaints and safety test, and improve the comprehensiveness of automobile recommendation.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the personalized recommendation method of the automobile when being executed by a processor.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the implementation of all or part of the flow of the method of the foregoing embodiments of the present invention may be accomplished by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each of the foregoing method embodiments when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to construct an apparatus/terminal equipment, recording medium, computer memory, read-Only memory (ROm), random access memory (RAm, random Access memory), electrical carrier signal, telecommunications signal, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The embodiment of the invention also provides a terminal device which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the personalized recommendation method of the automobile when executing the computer program.
It should be noted that the terminal device may be a mobile phone, a tablet computer, a notebook computer, an Ultra mobile personal computer (Ultra-mobile Personal Computer), a netbook, a personal digital assistant (PDA, personal Digital Assistant), or the like, and the terminal device may be a station (ST, station) in a WLAN, for example, a cellular phone, a cordless phone, a session initiation protocol (SiP, session initiation Protocol) phone, a wireless local loop (WLL, wireless Local Loop) station, a personal digital processing (PDA, personal Digital Assistant) device, a handheld device having a wireless communication function, a computing device, or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, or the like. The embodiment of the invention does not limit the specific type of the terminal equipment.
The processor may be a central processing unit (CPU, central Processing Unit), but may also be other general purpose processors, digital signal processors (DSP, digital Signal Processor), application specific integrated circuits (ASiC, application Specific integrated Circuit), off-the-shelf programmable gate arrays (FPGA, field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may in some embodiments be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory may in other embodiments also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a Smart media Card (SmC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. Further, the memory may also include both an internal storage unit and an external storage device of the terminal device. The memory is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs, etc., such as program code for the computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present invention, specific functions and technical effects thereof may be found in the method embodiment section, and will not be described herein.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (7)
1. An automobile personalized recommendation method is characterized by comprising the following steps:
step 1, constructing a scoring public praise index set, a complaint quality public praise index set and a safety test evaluation index set based on user scoring data, complaint data and safety test data in a plurality of target automobile consultation platforms;
step 2, extracting satisfaction data of users in the scoring public praise index set on various automobiles, dividing scoring public praise index levels according to the satisfaction data, and obtaining scoring public praise aggregate values;
the satisfaction degree data of the user to various automobiles in the scoring public praise index set is extracted, and the scoring public praise index grade is divided based on the scoring index system of the target automobile consultation platform and the satisfaction degree data of the user to various automobiles:
；
obtaining a scoring public praise aggregate value based on the scoring index system of the target automobile consultation platform, satisfaction data of users on various automobiles and the scoring public praise index grade：
；
Wherein,providing user scoring public praise>Target automobile consultation platform->Weight of->，/>Providing user scoring public praise>Platform number of->Indicating scoring public praise index->Weight of->，Indicating the number of indices in the scoring index system, +.>Indicating target automobile consultation platform->Index for vehicle->Score grade of->；
Step 3, extracting risk degree data of various automobiles according to the complaint quality public praise index set, calculating the ratio of complaint quantity to sales quantity of various automobiles in the complaint quality public praise index set, constructing a complaint occurrence rate index grade according to the ratio of the complaint quantity to sales quantity, and obtaining a complaint quality public praise aggregate value;
constructing a complaint quality public praise grade library based on expert knowledge;
extracting risk degree data of various automobiles according to complaint contents in the complaint quality public praise index set;
dividing the complaint quality public praise index grade based on the complaint quality public praise grade library and the risk degree data into the following steps:
；
calculating the ratio of sales volume to complaint volume of various automobiles in the complaint quality public praise index set, and dividing the sales volume complaint measurement level into:
；
acquiring a complaint quality public praise aggregate value based on the complaint quality public praise index level and the sales volume complaint measure levelThe method comprises the following steps:
；
wherein,indicating target automobile consultation platform->Index in the middle complaint quality public praise index set +.>Is classified into a class->Is>，/>Representing the number of platforms providing user complaint public praise,/->，/>Index number in a public praise index set representing complaint quality, +.>Grade value representing complaint quality public praise,/->Representing providing complaint quality public praise +.>Target automobile consultation platform->Weight of->Indicating complaint quality mouth-piece index +.>Weight(s)>And expressing the sales volume complaint measure grade, and constructing a calculation formula based on the sales volume and the complaint volume, wherein the calculation formula is as follows:
；
wherein,representing sales;
step 4, scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
scoring the safety indexes of various automobiles according to the safety test evaluation index set, constructing a safety evaluation grade according to the scoring of the safety indexes, and acquiring a safety scoring aggregate value;
scoring the safety indexes of various automobiles in the safety test evaluation index set based on the scoring rate of the safety test indexes to obtain scoring results;
constructing a security assessment grade based on the scoring result as follows:
；
acquiring a security score aggregate value based on the security assessment levelThe method comprises the following steps:
；
wherein,representing providing security assessment->Target automobile consultation platform->Weight of->，/>Representing providing security assessment->Platform number of->Index ∈A representing Security assessment>Weight of->，/>Indicating the number of indicators in the safety test evaluation indicator set, < >>Index weight representing security assessment, +.>Representing a security assessment level value;
step 5, setting the index weights of the scoring public praise index set, the complaint quality public praise index set and the security test evaluation index set as mean weights, and calculating a three-dimensional scoring aggregate value through the mean weights;
step 6, calculating four-dimensional vectors comprising the aggregate average values of the scoring public praise aggregate value, the complaint quality public praise aggregate value, the security scoring aggregate value and the three-dimensional scoring aggregate value according to the average value weight, and calculating the sorting percentage of the aggregate average values of the alternative vehicles and the sorting percentage of the vehicles expected by the user to select a primary recommended vehicle set based on the four-dimensional vectors;
and 7, acquiring an expected aggregation value through a constructed recommendation mechanism based on the expected weight of the user personalized index, and screening a final recommended vehicle set from the initial recommended vehicle set based on the expected aggregation value.
2. The method of claim 1, wherein the three-dimensional score aggregate valueThe method comprises the following steps:
；
wherein,、/>、/>respectively scoring the weight of the public praise index, the weight of the public praise index of the complaint quality, the weight of the security evaluation index, and the +.>，/>。
3. The vehicle personalized recommendation method according to claim 2, wherein the four-dimensional vectorThe method comprises the following steps:
；
wherein,aggregate mean representing score public praise aggregate value,/->An aggregate mean value representing the aggregate value of the complaint mass public praise,aggregate mean value representing aggregate value of security score, +.>Representing the aggregate mean of the aggregate values of the three-dimensional scores.
4. The method of claim 3, wherein selecting the preliminary recommended vehicle set based on the ranking percentage of the aggregate average of candidate vehicles and the ranking percentage of the user's expected value obtained from the four-dimensional vector comprises:
the ranking percentage of the aggregate average value of the alternative vehicles is calculated based on the four-dimensional vector as follows:
；
wherein,respectively representing the sorting percentages of the candidate vehicles in the scoring public praise aggregation mean value, the complaint quality public praise aggregation mean value, the security scoring aggregation mean value and the three-dimensional aggregation mean value;
the ranking percentage of the user expected value is calculated based on the four-dimensional vector:
；
wherein,respectively representing the ordering percentages of the vehicle expected by the user in the scoring public praise aggregation mean value, the complaint quality public praise aggregation mean value, the security scoring aggregation mean value and the three-dimensional aggregation mean value;
selecting a preliminary recommended vehicle set based on the sorting percentage of the aggregate mean value of the candidate vehicles acquired by the four-dimensional vector as follows:
；
wherein,representation ofPreliminary recommended vehicle set->Representing a vehicle meeting the constraints.
5. The method of claim 4, wherein obtaining a desired aggregate value by a recommendation mechanism based on a user personalized index desired weight, and screening a final recommended vehicle set from the preliminary recommended vehicle set based on the desired aggregate value, comprises:
defining a user personalized index expected weight value;
formulating a recommendation mechanism based on the user personalized index expected weight value;
calculating expected aggregate values of all automobiles in the primary recommended vehicle set according to the recommendation mechanism;
and acquiring a final recommended vehicle set according to the expected aggregation value.
6. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the car personalized recommendation method according to any one of claims 1 to 5.
7. A terminal 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 car personalization recommendation method according to any one of claims 1 to 5 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311199555.9A CN116932921B (en) | 2023-09-18 | 2023-09-18 | Personalized recommendation method and related equipment for automobiles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311199555.9A CN116932921B (en) | 2023-09-18 | 2023-09-18 | Personalized recommendation method and related equipment for automobiles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116932921A CN116932921A (en) | 2023-10-24 |
| CN116932921B true CN116932921B (en) | 2023-12-12 |
Family
ID=88375783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311199555.9A Active CN116932921B (en) | 2023-09-18 | 2023-09-18 | Personalized recommendation method and related equipment for automobiles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116932921B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9672497B1 (en) * | 2013-11-04 | 2017-06-06 | Snap-On Incorporated | Methods and systems for using natural language processing and machine-learning to produce vehicle-service content |
| CN108647791A (en) * | 2018-03-30 | 2018-10-12 | 中国标准化研究院 | A kind of processing method of multi-source automotive safety information, apparatus and system |
| JP2019061525A (en) * | 2017-09-27 | 2019-04-18 | トッパン・フォームズ株式会社 | Content recommendation system, content recommendation method, and program |
| CN110457589A (en) * | 2019-08-19 | 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 |
| US10796355B1 (en) * | 2019-12-27 | 2020-10-06 | Capital One Services, Llc | Personalized car recommendations based on customer web traffic |
| CN112434945A (en) * | 2020-11-24 | 2021-03-02 | 深圳前海微众银行股份有限公司 | Automobile risk assessment method, device and equipment and computer readable storage medium |
| CN112597500A (en) * | 2020-12-08 | 2021-04-02 | 国汽(北京)智能网联汽车研究院有限公司 | Automobile information security risk assessment method and device, electronic equipment and storage medium |
| CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
| CN114240456A (en) * | 2021-12-10 | 2022-03-25 | 北京质云数据科技有限公司 | Vehicle quality complaint information collection platform based on mobile phone APP |
| CN115204541A (en) * | 2021-04-08 | 2022-10-18 | 广州汽车集团股份有限公司 | Automobile data evaluation method and device, computer equipment and application |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9818088B2 (en) * | 2011-04-22 | 2017-11-14 | Emerging Automotive, Llc | Vehicles and cloud systems for providing recommendations to vehicle users to handle alerts associated with the vehicle |
| US9524522B2 (en) * | 2012-08-31 | 2016-12-20 | Accenture Global Services Limited | Hybrid recommendation system |
| US10023114B2 (en) * | 2013-12-31 | 2018-07-17 | Hartford Fire Insurance Company | Electronics for remotely monitoring and controlling a vehicle |
| US20160364783A1 (en) * | 2014-06-13 | 2016-12-15 | Truecar, Inc. | Systems and methods for vehicle purchase recommendations |
| US20150363865A1 (en) * | 2014-06-13 | 2015-12-17 | Truecar, Inc. | Systems and methods for vehicle purchase recommendations |
| US11367121B2 (en) * | 2020-06-15 | 2022-06-21 | Capital One Services, Llc | Recommendation engine that utilizes travel history to recommend vehicles for customers |
-
2023
- 2023-09-18 CN CN202311199555.9A patent/CN116932921B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9672497B1 (en) * | 2013-11-04 | 2017-06-06 | Snap-On Incorporated | Methods and systems for using natural language processing and machine-learning to produce vehicle-service content |
| JP2019061525A (en) * | 2017-09-27 | 2019-04-18 | トッパン・フォームズ株式会社 | Content recommendation system, content recommendation method, and program |
| CN108647791A (en) * | 2018-03-30 | 2018-10-12 | 中国标准化研究院 | A kind of processing method of multi-source automotive safety information, apparatus and system |
| CN110457589A (en) * | 2019-08-19 | 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 |
| CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
| US10796355B1 (en) * | 2019-12-27 | 2020-10-06 | Capital One Services, Llc | Personalized car recommendations based on customer web traffic |
| CN112434945A (en) * | 2020-11-24 | 2021-03-02 | 深圳前海微众银行股份有限公司 | Automobile risk assessment method, device and equipment and computer readable storage medium |
| CN112597500A (en) * | 2020-12-08 | 2021-04-02 | 国汽(北京)智能网联汽车研究院有限公司 | Automobile information security risk assessment method and device, electronic equipment and storage medium |
| CN115204541A (en) * | 2021-04-08 | 2022-10-18 | 广州汽车集团股份有限公司 | Automobile data evaluation method and device, computer equipment and application |
| CN114240456A (en) * | 2021-12-10 | 2022-03-25 | 北京质云数据科技有限公司 | Vehicle quality complaint information collection platform based on mobile phone APP |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116932921A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105677831B (en) | Method and device for determining recommended merchants | |
| US20050086070A1 (en) | Wireless automobile valuation information service | |
| US11978093B2 (en) | Automated factor generation for decision engines | |
| WO2018192348A1 (en) | Data processing method and device, and server | |
| CN111275470B (en) | Service initiation probability prediction method and training method and device of model thereof | |
| US20080091552A1 (en) | Methods and systems for providing product information to a user | |
| CN108429776B (en) | Network object pushing method, device, client, interaction equipment and system | |
| CN110111090A (en) | A kind of distribution method and device of electronics red packet | |
| CN107943910B (en) | Personalized book recommendation method based on combined algorithm | |
| US20220335359A1 (en) | System and method for comparing enterprise performance using industry consumer data in a network of distributed computer systems | |
| WO2023000491A1 (en) | Application recommendation method, apparatus and device, and computer-readable storage medium | |
| US11966933B2 (en) | System and method for correlating and enhancing data obtained from distributed sources in a network of distributed computer systems | |
| CN111124676A (en) | Resource allocation method and device, readable storage medium and electronic equipment | |
| CN116932921B (en) | Personalized recommendation method and related equipment for automobiles | |
| CN116523548A (en) | Commodity feature information identification method and device | |
| KR102275036B1 (en) | Method and system for providing recommendation information for trading of used cars | |
| CN111626864B (en) | Information pushing method and device, storage medium and electronic device | |
| CN111159575A (en) | Friend making method and device based on mobile banking | |
| Putnam et al. | The Smallest Salable Patent-Practicing Unit (SSPPU): Theory and Evidence | |
| CN111159576B (en) | User classification method, device and system | |
| CN110175271B (en) | Case random ordering method and device | |
| CN115099986A (en) | Vehicle insurance renewal processing method and device and related equipment | |
| CN110162545A (en) | Information-pushing method, equipment, storage medium and device based on big data | |
| CN117952606B (en) | Aggregation payment method, device, equipment and storage medium based on security evaluation | |
| CN117217852B (en) | Behavior recognition-based purchase willingness prediction method and device |
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 |