CN111861606A - Vehicle type heat degree calculation method and device, electronic equipment and storage medium - Google Patents
Vehicle type heat degree calculation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111861606A CN111861606A CN201910354567.1A CN201910354567A CN111861606A CN 111861606 A CN111861606 A CN 111861606A CN 201910354567 A CN201910354567 A CN 201910354567A CN 111861606 A CN111861606 A CN 111861606A
- Authority
- CN
- China
- Prior art keywords
- vehicle type
- heat
- feature
- target vehicle
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 22
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 51
- 230000032683 aging Effects 0.000 claims description 41
- 230000008569 process Effects 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 description 6
- 238000012847 principal component analysis method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008676 import Effects 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
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
- 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
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a vehicle type heat calculation method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring relevant characteristics aiming at a target vehicle type, wherein the relevant characteristics comprise at least one of the following characteristics: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type; determining a heat weight corresponding to each of the relevant features; and calculating the heat of the target vehicle type based on the relevant features and the corresponding heat weight. According to the method and the device, when the heat degree of the target vehicle type is calculated, data of multiple dimensions such as data of transaction events aiming at the target vehicle type, data of release events aiming at the target vehicle type, data of query events aiming at the target vehicle type and the like are used as calculation bases, and therefore the accuracy of the calculated vehicle type heat degree can be improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for calculating a vehicle type heat, an electronic device, and a storage medium.
Background
The automobile platform can show the heat value of each automobile type to the user, so that the user can be provided with reference when the user needs to buy. In the related art, the automobile platform ranks the vehicle type popularity by counting the click rate of all users for each vehicle type in the platform. However, the heat of the vehicle model calculated according to the click rate of the user alone cannot accurately reflect the actual demand of the user on the vehicle model, so that misleading may be caused to the user, and the user experience is poor.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for calculating a vehicle type heat, an electronic device, and a storage medium.
In order to achieve the above purpose, the present application provides the following technical solutions:
according to a first aspect of the present application, a method for calculating a vehicle type heat is provided, which includes:
acquiring relevant characteristics aiming at a target vehicle type, wherein the relevant characteristics comprise at least one of the following characteristics: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type;
determining a heat weight corresponding to each of the relevant features;
And calculating the heat of the target vehicle type based on the relevant features and the corresponding heat weight.
Optionally, the obtaining of relevant features for the target vehicle type includes:
acquiring relevant information of the target vehicle type in a preset dimension, wherein the preset dimension comprises at least one of the following: transaction information, release information and query information;
and performing dimension reduction processing on the related information to obtain related characteristics aiming at the target vehicle type.
Optionally, the method further includes:
when the data missing rate of any information in the related information is within a first preset range, supplementing the missing data by using the median of the any information;
when the data loss rate of any one of the related information exceeds the upper limit value of the first preset range, deleting the any one of the related information;
when the data missing rate of any one of the related information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm;
and screening abnormal values in the related information, and deleting the screened abnormal values.
Optionally, the determining the heat weight corresponding to each feature in the relevant features includes:
Determining the aging weight of each feature in the related features; the aging weight of any feature is in negative correlation with the corresponding time interval, and the time interval of any feature is the time interval from the occurrence time of the event corresponding to any feature to the current time;
determining importance weights of all the characteristics in the related characteristics by using an analytic hierarchy process;
and determining a heat weight corresponding to each feature in the related features based on the aging weight and the importance weight.
Optionally, the aging weight of the target feature is calculated by the following formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
Optionally, the method further includes:
acquiring the reference heat degree of the third-party trusted platform for the target vehicle type;
checking the calculated heat according to the reference heat;
and when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes the verification.
According to a second aspect of the present application, there is provided a vehicle type heat calculation device, including:
A feature acquisition unit that acquires a relevant feature for a target vehicle type, the relevant feature including at least one of: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type;
a determining unit that determines a heat weight corresponding to each of the relevant features;
and the calculating unit is used for calculating the heat of the target vehicle type based on the relevant characteristics and the corresponding heat weight.
Optionally, the feature obtaining unit is specifically configured to:
acquiring relevant information of the target vehicle type in a preset dimension, wherein the preset dimension comprises at least one of the following: transaction information, release information and query information;
and performing dimension reduction processing on the related information to obtain related characteristics aiming at the target vehicle type.
Optionally, the method further includes:
the processing unit is used for complementing the missing data by adopting the median of any information when the data missing rate of any information in the related information is within a first preset range;
when the data loss rate of any one of the related information exceeds the upper limit value of the first preset range, deleting the any one of the related information;
When the data missing rate of any one of the related information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm;
and screening abnormal values in the related information, and deleting the screened abnormal values.
Optionally, the determining unit is specifically configured to:
determining the aging weight of each feature in the related features; the aging weight of any feature is in negative correlation with the corresponding time interval, and the time interval of any feature is the time interval from the occurrence time of the event corresponding to any feature to the current time;
determining importance weights of all the characteristics in the related characteristics by using an analytic hierarchy process;
and determining a heat weight corresponding to each feature in the related features based on the aging weight and the importance weight.
Optionally, the aging weight of the target feature is calculated by the following formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
Optionally, the method further includes:
the heat acquisition unit is used for acquiring the reference heat of the third-party trusted platform for the target vehicle type;
The checking unit is used for checking the calculated heat according to the reference heat;
and when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes the verification.
According to a third aspect of the present application, there is provided an electronic device comprising:
a processor;
a memory for storing processor-executable instructions;
wherein, the processor implements the vehicle type heat calculation method according to any one of the above embodiments by executing the executable instructions.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method for calculating the vehicle type heat as described in any one of the above embodiments.
According to the technical scheme, when the heat degree of the target vehicle type is calculated, data of multiple dimensions such as data of transaction events aiming at the target vehicle type, data of release events aiming at the target vehicle type, data of query events aiming at the target vehicle type and the like are used as calculation bases, and therefore the accuracy of the calculated vehicle type heat degree can be improved. Furthermore, the heat weight is determined by integrating the aging weight and the importance weight of each characteristic, so that the determined heat weight is more comprehensive. Meanwhile, based on the principle that the actual demand of the user is reduced along with the increase of time, the aging weight of any feature is set to be in negative correlation with the time interval between the occurrence time of the event corresponding to the feature and the current time, so that the finally calculated heat weight can more accurately reflect the actual demand of the current user on the target vehicle type, and the accuracy of the vehicle type heat is improved.
Drawings
Fig. 1 is a flowchart illustrating a method for calculating a vehicle type heat according to an exemplary embodiment of the present application.
Fig. 2 is a flowchart illustrating another method for calculating a vehicle type heat according to an exemplary embodiment of the present application.
Fig. 3 is a flowchart illustrating a method for verifying vehicle type heat according to an exemplary embodiment of the present application.
Fig. 4 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.
Fig. 5 is a block diagram of a device for calculating a vehicle type heat degree according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for calculating a vehicle type heat degree according to an exemplary embodiment of the present application. As shown in fig. 1, the method may be applied to a background server of an automobile platform, and may include the following steps:
102, acquiring relevant characteristics aiming at a target vehicle type, wherein the relevant characteristics comprise at least one of the following characteristics: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type.
In this embodiment, when the relevant features for the target vehicle type are obtained, the relevant information of the target vehicle type in the preset dimension may be obtained first, and then the dimension reduction processing may be performed on the relevant information to obtain the relevant features for the target vehicle type. Wherein the preset dimension may include at least one of: transaction information, release information, and inquiry information.
For example, the transaction information may be a sales amount, a purchase price, a minimum price, a guide price, a maximum price, a transaction time, a payment settlement time, an amount of a payment settlement, etc. of the target vehicle type; the release information can be the time, release price, release area and the like of the target vehicle type released by the vehicle manufacturer; the query information can be search data, vehicle searching data, telephone consultation quantity, click quantity, vehicle type detail page visit quantity, vehicle type detail page sharing quantity and the like aiming at the target vehicle type. Of course, the specific content of the preset dimension can be flexibly set by a developer according to the actual situation, and the application does not limit the specific content.
The relevant information can be subjected to dimensionality reduction by adopting a principal component analysis method (also called principal component analysis), so that the dimensionality reduction effect is achieved. Specifically, the plurality of related information can be combined into a few pieces of mutually independent integrated information (i.e., principal components), wherein each principal component can reflect most of the original information and contains information that is not repeated. For example, after the relevant information of the target vehicle model in the preset dimension is acquired, the variables with higher relevance in the relevant information can be converted into mutually independent or irrelevant variables through a principal component analysis method, and usually, a few new variables (i.e., principal components) which are less than the original variables and can explain the variables contained in most information are selected. The correlation between each variable can be calculated by using a principal component analysis method, and the variable with higher correlation is replaced by other variables through linear weighting, so that the variable in the correlation information is reduced from high dimension to low dimension, and the subsequent calculation amount is reduced.
In this embodiment, before performing the dimension reduction processing on the related information, the related information may be supplemented, deleted, predicted, and cleaned. As an exemplary embodiment, when the data missing rate of any information in the related information is within a first preset range, the missing data is complemented with the median of the any information; when the data loss rate of any one piece of related information exceeds the upper limit value of a first preset range, deleting the any one piece of information; when the data loss rate of any one piece of relevant information is lower than the lower limit value of a first preset range, predicting the lost data by using a machine learning algorithm; and screening abnormal values in the related information, and deleting the screened abnormal values.
And 104, determining the heat weight corresponding to each feature in the related features.
In this embodiment, the thermal weight of a feature may be measured from its timeliness and importance, respectively. In consideration of the fact that the demand preference of a user for a certain type of vehicle type decreases with the increase of time, the aging weight of any feature can be set to be in negative correlation with the corresponding duration interval (the duration interval of any feature is the duration from the occurrence time of an event corresponding to the feature to the current time). Taking the example that a user inquires a target vehicle type, the user inquires detailed information of the target vehicle type at a certain time in the past, and the larger the time interval from the time, the smaller the actual demand and preference of the user for the vehicle type may be; in other words, the closer the time when the user queries the target vehicle model is to the current time, the greater the actual demand and preference of the user for the target vehicle model may be. Therefore, when determining the heat of the target vehicle model, adding the above-mentioned measure based on the "time decay" can improve the calculation accuracy of the heat value.
For example, the age weight of the target feature may be calculated by the following formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to said relevant features。
For the importance weight of the relevant features, an Analytic Hierarchy Process (AHP) may be used to determine the importance weight of each feature in the relevant features (the specific process of calculating the importance weight by the Analytic hierarchy process is described in detail below). Further, after determining the aging weight and the importance weight of each feature in the related features, the heat weight corresponding to each feature may be determined based on the aging weight and the importance weight. For example, the time-based weight and the importance weight are multiplied to obtain the heat weight, or the time-based weight and the importance weight are weighted and further multiplied to obtain the heat weight. Of course, this application is not so limited.
And 106, calculating the heat of the target vehicle type based on the relevant features and the corresponding heat weight.
In this embodiment, after the heat degree of the target vehicle model is calculated, the calculated heat degree may be further checked to determine whether the calculated heat degree is accurate. As an exemplary embodiment, a reference heat degree for the target vehicle type counted by the trusted platform of the third party may be obtained (for example, a reference heat degree calculated by purchasing data, consulting data, and the like of all customers manually collected in the 4S store for the target vehicle type may be obtained), and then the calculated heat degree is verified according to the reference heat degree; and when the error between the calculated heat and the reference heat is within a second preset range, judging that the calculated heat passes the verification.
According to the technical scheme, when the heat degree of the target vehicle type is calculated, data of multiple dimensions such as data of transaction events aiming at the target vehicle type, data of release events aiming at the target vehicle type, data of query events aiming at the target vehicle type and the like are used as calculation bases, and therefore the accuracy of the calculated vehicle type heat degree can be improved. Furthermore, the heat weight is determined by integrating the aging weight and the importance weight of each characteristic, so that the determined heat weight is more comprehensive. Meanwhile, based on the principle that the actual demand of the user is reduced along with the increase of time, the aging weight of any feature is set to be in negative correlation with the time interval between the occurrence time of the event corresponding to the feature and the current time, so that the finally calculated heat weight can more accurately reflect the actual demand of the current user on the target vehicle type, and the accuracy of the vehicle type heat is improved.
For the convenience of understanding, the calculation scheme of the vehicle type heat of the present application is described in detail below with reference to examples.
Referring to fig. 2, fig. 2 is a flowchart illustrating another vehicle type heat calculation method according to an exemplary embodiment of the present application. As shown in fig. 2, the method may be applied to a background server of an automobile platform, and may include the following steps:
And step 202, acquiring relevant information of the target vehicle type.
In this embodiment, the sales data table of each vehicle type in each vehicle platform (including the third party platform and the local platform) can be crawled through a crawler technology (e.g., the scrapy technology of python). Wherein the crawled fields may include: month, brand, vehicle series, vehicle type, import mode, sales volume, etc. For example, as shown in table 1:
TABLE 1
Further, vehicle type related data of the vehicle platform are obtained, wherein the vehicle type related data comprise a vehicle type data table, transaction event data aiming at the vehicle type, release event data aiming at the vehicle type, query event data aiming at the vehicle type and the like. Wherein, the motorcycle type data table can include: vehicle type code, brand, vehicle series, vehicle type, import style, description, lowest price, guide price, highest quote price, purchase price, member price, interior trim configuration, appearance color, interior trim color, vehicle parameters, and the like. The data of the transaction event for the vehicle model (hereinafter, simply referred to as a transaction data table) may include: order id, buyer id, seller id, vehicle type code, brand, vehicle type, vehicle family, quote, payment due time, payment due amount, creation time, etc. The data of the distribution event for the vehicle model (hereinafter, referred to as a distribution data table) may include: vehicle manufacturer id, vehicle type code, release price, release time, release province, release city, release district, etc. The data of the query event for the vehicle type (hereinafter, referred to as a vehicle finding data table) may include: vehicle manufacturer id, vehicle type code, vehicle searching price, vehicle searching province, vehicle searching city, vehicle searching district and county, vehicle searching time and the like.
Based on the acquisition of the sales data table, the vehicle type data table, the transaction data table, the release data table and the vehicle searching data table, association can be performed through a vehicle type code, and the data tables are fused through left join (namely, connection Query) statements in Structured Query Language (SQL) (the vehicle type data table is used as a main table). The fused related information mainly comprises: the system comprises a date, a brand, a vehicle system, a vehicle type code, an import mode, a description, a lowest price, a highest price, interior configuration, an appearance color, an interior color, a distribution number, a member distribution number, a distribution average price, a member distribution average price, a vehicle searching number, a member vehicle searching number, a vehicle source information telephone consultation number, a vehicle source detail page access number, a vehicle source detail sharing number, a vehicle type sales amount and the like.
And step 204, completing, deleting, predicting and cleaning the related information.
In this embodiment, before performing the dimension reduction processing on the related information, the related information may be supplemented, deleted, predicted, and cleaned. The upper limit value and the lower limit value of the first preset range can be flexibly set according to actual conditions, and the upper limit value and the lower limit value are not limited in the application.
For example, the completion and purge rules may be: for the related information with the data missing rate of more than 80%, deleting the related information; for the relevant information with the data missing rate between 40% and 80%, complementing the missing value by using the median of the relevant information; for the relevant information with the data missing rate of less than 40%, predicting missing values by using a random forest algorithm; in addition, a box separation method can be adopted to screen abnormal point data in the related information, and the abnormal point data can be deleted.
And step 206, performing dimension reduction processing on the related information.
In this embodiment, a principal component analysis (also called principal component analysis) may be used to perform dimensionality reduction on the related information, thereby achieving the effect of reducing dimensionality. Specifically, the plurality of related information can be combined into a few pieces of mutually independent integrated information (i.e., principal components), wherein each principal component can reflect most of the original information and contains information that is not repeated. For example, after the relevant information of the target vehicle model in the preset dimension is acquired, the variables with higher relevance in the relevant information can be converted into mutually independent or irrelevant variables through a principal component analysis method, and usually, a few new variables (i.e., principal components) which are less than the original variables and can explain the variables contained in most information are selected. The correlation between each variable can be calculated by using a principal component analysis method, and the variable with higher correlation is replaced by other variables through linear weighting, so that the variable in the correlation information is reduced from high dimension to low dimension, and the subsequent calculation amount is reduced.
For example, the correlation between the highest price of the vehicle model and the guiding price and the purchasing price is high, so the highest price of the vehicle model can be weighted by the guiding price and the purchasing price to replace the highest price of the vehicle model, for example, the highest price of the vehicle model is the coefficient 1 × the guiding price + the coefficient 2 × the purchasing price + the constant; wherein the coefficient 1 is a correlation coefficient between the guide price and the highest price of the vehicle type; the coefficient 2 is a correlation coefficient between the purchase price and the highest price of the vehicle type.
As an example, the following correlation characteristics can be obtained based on the dimension reduction processing for the correlation information: the number of vehicle source visits, the number of vehicle source releases, the number of telephone calls, the number of vehicle source shares, the number of vehicle seeks in deposit, the number of vehicle seeks releases, the number of vehicle model sales, etc.
In step 208, the aging weight and the importance weight are determined.
In this embodiment, the thermal weight of a feature may be measured from its timeliness and importance, respectively. In consideration of the fact that the demand preference of a user for a certain type of vehicle type decreases with the increase of time, the aging weight of any feature can be set to be in negative correlation with the corresponding duration interval (the duration interval of any feature is the duration from the occurrence time of an event corresponding to the feature to the current time). Taking the example that a user inquires a target vehicle type, the user inquires detailed information of the target vehicle type at a certain time in the past, and the larger the time interval from the time, the smaller the actual demand and preference of the user for the vehicle type may be; in other words, the closer the time when the user queries the target vehicle model is to the current time, the greater the actual demand and preference of the user for the target vehicle model may be. Therefore, when determining the heat of the target vehicle model, adding the above-mentioned measure based on the "time decay" can improve the calculation accuracy of the heat value.
For example, the age weight of the target feature may be calculated by the following formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
By way of example, the earliest moment of occurrence can be understood as: each type of vehicle corresponds to a plurality of relevant characteristics, and the event corresponding to each relevant characteristic exists at the occurrence moment; the earliest moment of occurrence is the smallest moment of all the moments of occurrence. For example, in a vehicle model 2018, a bmax 6 flagship edition, the earliest occurrence time among all relevant features recorded in a home platform is 1 month and 1 day in 2017 (for example, the first relevant feature of the vehicle model recording system is the sales number of the vehicle model, the earliest occurrence time is the time of the first vehicle model sold), and the current time is 3 months and 24 days in 2019; then the age weight for the feature that occurred on day 1, 23 of 2019 is: 1- (2019/3/24-2019/1/23)/(2019/3/24-2017/1/1) 60/812 0.926.
For the importance weight of the related features, an Analytic Hierarchy Process (AHP) can be used to determine the importance weight of each feature in the related features. In the above example, the relevant features are processed by the following steps:
1) Based on the above-mentioned relevant features, the comparison importance between the features is obtained (for example, a developer may set a preliminary value according to an empirical value first, and then adjust the value), as shown in table 2:
TABLE 2
2) Calculating importance weights WI (weight) of the respective features
The importance weight WI is the power of kelvin/sum (power of kelvin); the term "n-th power" is understood to mean that a value obtained by multiplying the importance of each row of any data is n-th power-opened.
| Multiplication by rows | Power of n | WI | AWI | AWI/WI | |
| Number of vehicle source visits | 16 | 2.208179027 | 0.25 | 1.25 | 5 |
| Number of vehicle source issues | 16 | 2.208179027 | 0.25 | 1.25 | 5 |
| Telephone number of consultations | 16 | 2.208179027 | 0.25 | 1.25 | 5 |
| Number of sharing between vehicle sources | 0.125 | 0.552044757 | 0.0625 | 0.5625 | 9 |
| Number of vehicles to be searched | 0.125 | 0.552044757 | 0.0625 | 0.5625 | 9 |
| Number of vehicle searching issues | 0.125 | 0.552044757 | 0.0625 | 0.5625 | 9 |
| Number of car model sales | 0.125 | 0.552044757 | 0.0625 | 0.5625 | 9 |
TABLE 3
Taking the number of vehicle source accesses in table 3 as an example, the operation process of "multiplication by rows" is: 1.00 × 1.00 × 1.00 × 2.00 × 2.00 × 2.00 × 2.00 ═ 16; the operation process of "opening the power n" (taking n as 3.5 as an example, the value of n can be flexibly adjusted according to actual conditions) is as follows:
similarly, the calculation process for the other data is similar to the above process. Then, the importance weight WI of the car source visit number is 2.208179027/(2.208179027+2.208179027+2.208179027+0.552044757+0.552044757+0.552044757+0.552044757) is 0.25. Similarly, the importance weights of the data such as the number of vehicle source issues, the number of telephone inquiries, the number of vehicle source shares, the number of fixed-deposit vehicle searches, the number of vehicle searching issues, the number of vehicle model sales, etc. can be obtained according to the above calculation process, and are not described herein again.
3) Performing a consistency check
A check coefficient CR (Consistency Ratio) is introduced to determine whether the calculated importance weight WI passes the Consistency check. If CR is <0.1, the calculated importance weight WI can be considered to pass the consistency check; otherwise, the CR may be calculated again after further adjusting the relevant parameters (e.g., the comparison importance between the data, the value of n, etc.). Where CI (Consistency Index) is (AVERGE (AWI/WI) -k) × (k-1), AVERGE represents the number of averages, and k represents the order (i.e., the number of data, where k is 7 in this embodiment); the RI (RandomIndex, random consistency index) adopts the standard values shown in table 4 (different standards for consistency check are different, and the value of RI is slightly different); AWI (all weight, total rank weight) sum (importance weight of data × comparative importance).
| Order of the scale | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
| RI | 0 | 0 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 | 1.49 |
TABLE 4
For example: AWI ═ 1.0 × 0.25+1.0 × 0.25+1 × 0.25+2 × 0.625+2 × 0.625+2 × 0.625+2 × 0.625 ═ 1.25; AVERGE (AWI/WI) ═ 7.286 (5+5+5+9+9+ 9)/7; CI (7.286-7) × (7-1) ═ 1.714; then, CR 1.714/1.32 1.299> 0.1; therefore, it can be determined that the WI calculated as described above fails the consistency check. Furthermore, the comparison importance among the data can be adjusted, and then the WI is calculated according to the calculation process and the consistency check is carried out until the WI calculated according to the comparison importance among the adjusted data passes the consistency check.
For example, the importance weights of the features calculated by the above-described analytic hierarchy process are shown in table 5:
TABLE 5
And step 210, determining a heat weight according to the aging weight and the importance weight.
In this embodiment, after the aging weight and the importance weight of each feature in the related features are determined, the heat weight corresponding to each feature may be determined based on the aging weight and the importance weight. For example, the time-based weight and the importance weight are multiplied to obtain the heat weight, or the time-based weight and the importance weight are weighted and further multiplied to obtain the heat weight. Of course, this application is not so limited.
For example, the heat weight of feature 1 is 1 × the importance weight 1.
And step 212, calculating the heat of the target vehicle type.
In the above example, the heat of the target vehicle type is equal to the time efficiency weight of the number of vehicle source visits × the importance weight of the number of vehicle source visits × the number of vehicle source visits + the time efficiency weight of the number of vehicle source releases × the importance weight of the number of vehicle source releases × the number of vehicle source releases … … + the time efficiency weight of the number of vehicle types × the importance weight of the number of vehicle source releases × the number of vehicle type releases.
According to the technical scheme, when the heat degree of the target vehicle type is calculated, data of multiple dimensions such as data of transaction events aiming at the target vehicle type, data of release events aiming at the target vehicle type, data of query events aiming at the target vehicle type and the like are used as calculation bases, and therefore the accuracy of the calculated vehicle type heat degree can be improved. Furthermore, the heat weight is determined by integrating the aging weight and the importance weight of each characteristic, so that the determined heat weight is more comprehensive. Meanwhile, based on the principle that the actual demand of the user is reduced along with the increase of time, the aging weight of any feature is set to be in negative correlation with the time interval between the occurrence time of the event corresponding to the feature and the current time, so that the finally calculated heat weight can more accurately reflect the actual demand of the current user on the target vehicle type, and the accuracy of the vehicle type heat is improved.
As an exemplary embodiment, after the heat degree of the target vehicle model is calculated, the calculated heat degree may be further checked to determine whether the calculated heat degree is accurate. Referring to fig. 3, fig. 3 is a flowchart illustrating a method for checking vehicle type popularity according to an exemplary embodiment of the present application. As shown in fig. 3, the method may be applied to a background server of an automobile platform, and may include the following steps:
In this embodiment, a reference heat degree for the target vehicle type counted by the trusted third-party platform may be obtained (for example, a reference heat degree calculated by purchasing data, consulting data, and the like of all customers manually collected in the 4S store for the target vehicle type may be obtained), and then the calculated heat degree is verified according to the reference heat degree; when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes verification; the specific values of the upper limit value and the lower limit value of the second preset range can be flexibly set according to the actual situation, which is not limited in the present application.
At step 304, an error from the reference heat is calculated.
For example, assuming that the reference heat acquired for a certain vehicle is 7, the heat of the vehicle calculated by the embodiment shown in fig. 2 is 6.5; the error is (7-6.5)/7-7%. Of course, other ways of calculating the error may be used, for example, directly taking the difference between the calculated heat value and the reference heat value as the error, and then the corresponding preset range is the error range for controlling the difference.
In step 306, if the error is within the predetermined range (i.e., the second predetermined range), go to step 308, otherwise go to step 310.
In step 308, it is determined that the calculated heat passes the verification.
In step 310, it is determined that the calculated heat has not passed the verification.
In the above example, assuming that the predetermined range is 0 to 10%, the calculated heat may be determined to pass the verification since the error 7% calculated in the step 304 is within 0 to 10%.
Fig. 4 shows a schematic block diagram of a master-based-side electronic device according to an exemplary embodiment of the present application. Referring to fig. 4, at the hardware level, the electronic device includes a processor 402, an internal bus 404, a network interface 406, a memory 408 and a non-volatile memory 410, but may also include hardware required for other services. The processor 402 reads a corresponding computer program from the non-volatile memory 410 into the memory 408 and then runs the computer program to form a calculation device of the vehicle type heat on a logic level. Of course, besides the software implementation, the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Referring to fig. 5, in a software implementation, the device for calculating the vehicle popularity may include:
a feature acquisition unit 51 that acquires a relevant feature for a target vehicle type, the relevant feature including at least one of: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type;
a determining unit 52 that determines a heat weight corresponding to each of the relevant features;
and a calculating unit 53 for calculating the heat of the target vehicle type based on the correlation features and the corresponding heat weights.
Optionally, the feature obtaining unit 51 is specifically configured to:
acquiring relevant information of the target vehicle type in a preset dimension, wherein the preset dimension comprises at least one of the following: transaction information, release information and query information;
and performing dimension reduction processing on the related information to obtain related characteristics aiming at the target vehicle type.
Optionally, the method further includes:
a processing unit 54, configured to, when a data loss rate of any one of the related information is within a first preset range, complement the missing data with a median of the any information;
when the data loss rate of any one of the related information exceeds the upper limit value of the first preset range, deleting the any one of the related information;
When the data missing rate of any one of the related information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm;
and screening abnormal values in the related information, and deleting the screened abnormal values.
Optionally, the determining unit 52 is specifically configured to:
determining the aging weight of each feature in the related features; the aging weight of any feature is in negative correlation with the corresponding time interval, and the time interval of any feature is the time interval from the occurrence time of the event corresponding to any feature to the current time;
determining importance weights of all the characteristics in the related characteristics by using an analytic hierarchy process;
and determining a heat weight corresponding to each feature in the related features based on the aging weight and the importance weight.
Optionally, the aging weight of the target feature is calculated by the following formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
Optionally, the method further includes:
the heat obtaining unit 55 is used for obtaining the reference heat of the third-party trusted platform for the target vehicle type;
A verification unit 56 that verifies the calculated heat degree according to the reference heat degree;
and when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes the verification.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium, for example a memory, comprising instructions executable by a processor of the above vehicle type heat calculation apparatus to implement the method as described in any of the above embodiments, such that the method may comprise: acquiring relevant characteristics aiming at a target vehicle type, wherein the relevant characteristics comprise at least one of the following characteristics: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type; determining a heat weight corresponding to each of the relevant features; and calculating the heat of the target vehicle type based on the relevant features and the corresponding heat weight.
The non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc., which is not limited in this application.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (14)
1. A vehicle type heat calculation method is characterized by comprising the following steps:
acquiring relevant characteristics aiming at a target vehicle type, wherein the relevant characteristics comprise at least one of the following characteristics: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type;
determining a heat weight corresponding to each of the relevant features;
and calculating the heat of the target vehicle type based on the relevant features and the corresponding heat weight.
2. The method of claim 1, wherein the obtaining relevant features for a target vehicle type comprises:
acquiring relevant information of the target vehicle type in a preset dimension, wherein the preset dimension comprises at least one of the following: transaction information, release information and query information;
And performing dimension reduction processing on the related information to obtain related characteristics aiming at the target vehicle type.
3. The method of claim 2, further comprising:
when the data missing rate of any information in the related information is within a first preset range, supplementing the missing data by using the median of the any information;
when the data loss rate of any one of the related information exceeds the upper limit value of the first preset range, deleting the any one of the related information;
when the data missing rate of any one of the related information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm;
and screening abnormal values in the related information, and deleting the screened abnormal values.
4. The method of claim 1, wherein determining a heat weight corresponding to each of the relevant features comprises:
determining the aging weight of each feature in the related features; the aging weight of any feature is in negative correlation with the corresponding time interval, and the time interval of any feature is the time interval from the occurrence time of the event corresponding to any feature to the current time;
Determining importance weights of all the characteristics in the related characteristics by using an analytic hierarchy process;
and determining a heat weight corresponding to each feature in the related features based on the aging weight and the importance weight.
5. The method of claim 4, wherein the aging weight for the target feature is calculated by the formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
6. The method of claim 1, further comprising:
acquiring the reference heat degree of the third-party trusted platform for the target vehicle type;
checking the calculated heat according to the reference heat;
and when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes the verification.
7. A vehicle type heat calculation device is characterized by comprising:
a feature acquisition unit that acquires a relevant feature for a target vehicle type, the relevant feature including at least one of: data of transaction events for the target vehicle type, data of release events for the target vehicle type, and data of query events for the target vehicle type;
A determining unit that determines a heat weight corresponding to each of the relevant features;
and the calculating unit is used for calculating the heat of the target vehicle type based on the relevant characteristics and the corresponding heat weight.
8. The apparatus according to claim 7, wherein the feature obtaining unit is specifically configured to:
acquiring relevant information of the target vehicle type in a preset dimension, wherein the preset dimension comprises at least one of the following: transaction information, release information and query information;
and performing dimension reduction processing on the related information to obtain related characteristics aiming at the target vehicle type.
9. The apparatus of claim 8, further comprising:
the processing unit is used for complementing the missing data by adopting the median of any information when the data missing rate of any information in the related information is within a first preset range;
when the data loss rate of any one of the related information exceeds the upper limit value of the first preset range, deleting the any one of the related information;
when the data missing rate of any one of the related information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm;
And screening abnormal values in the related information, and deleting the screened abnormal values.
10. The apparatus according to claim 7, wherein the determining unit is specifically configured to:
determining the aging weight of each feature in the related features; the aging weight of any feature is in negative correlation with the corresponding time interval, and the time interval of any feature is the time interval from the occurrence time of the event corresponding to any feature to the current time;
determining importance weights of all the characteristics in the related characteristics by using an analytic hierarchy process;
and determining a heat weight corresponding to each feature in the related features based on the aging weight and the importance weight.
11. The apparatus of claim 10, wherein the aging weight for the target feature is calculated by the formula:
wherein gamma represents the aging weight of the target feature;
dnowrepresents the current time;
dtrepresenting the occurrence time of an event corresponding to the target feature;
dstartrepresenting the earliest moment of occurrence of all events corresponding to the relevant feature.
12. The apparatus of claim 7, further comprising:
the heat acquisition unit is used for acquiring the reference heat of the third-party trusted platform for the target vehicle type;
The checking unit is used for checking the calculated heat according to the reference heat;
and when the error between the calculated heat degree and the reference heat degree is within a second preset range, judging that the calculated heat degree passes the verification.
13. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the method of any one of claims 1-6 by executing the executable instructions.
14. A computer-readable storage medium having stored thereon computer instructions, which, when executed by a processor, carry out the steps of the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910354567.1A CN111861606A (en) | 2019-04-29 | 2019-04-29 | Vehicle type heat degree calculation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910354567.1A CN111861606A (en) | 2019-04-29 | 2019-04-29 | Vehicle type heat degree calculation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111861606A true CN111861606A (en) | 2020-10-30 |
Family
ID=72965340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910354567.1A Pending CN111861606A (en) | 2019-04-29 | 2019-04-29 | Vehicle type heat degree calculation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861606A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009116510A (en) * | 2007-11-05 | 2009-05-28 | Fujitsu Ltd | Attention degree calculation device, attention degree calculation method, attention degree calculation program, information providing system and information providing device |
| CN106845731A (en) * | 2017-02-20 | 2017-06-13 | 重庆邮电大学 | A kind of potential renewal user based on multi-model fusion has found method |
| CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
| CN109086299A (en) * | 2018-06-19 | 2018-12-25 | 北京至信普林科技有限公司 | Analyze quality of data method |
| CN109558988A (en) * | 2018-12-13 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of electric car energy consumption prediction technique and system based on big data fusion |
-
2019
- 2019-04-29 CN CN201910354567.1A patent/CN111861606A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009116510A (en) * | 2007-11-05 | 2009-05-28 | Fujitsu Ltd | Attention degree calculation device, attention degree calculation method, attention degree calculation program, information providing system and information providing device |
| CN106845731A (en) * | 2017-02-20 | 2017-06-13 | 重庆邮电大学 | A kind of potential renewal user based on multi-model fusion has found method |
| CN109086299A (en) * | 2018-06-19 | 2018-12-25 | 北京至信普林科技有限公司 | Analyze quality of data method |
| CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
| CN109558988A (en) * | 2018-12-13 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of electric car energy consumption prediction technique and system based on big data fusion |
Non-Patent Citations (2)
| Title |
|---|
| 林丽娜;魏德志;: "一种基于时间序列网络舆情热点事件发现模型", 太原师范学院学报(自然科学版), no. 03, 25 September 2016 (2016-09-25) * |
| 陈麓屹;周斌彬;徐萍;: "虚拟社区话题热度评估算法研究", 浙江树人大学学报(自然科学版), no. 01, 15 March 2015 (2015-03-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5662620B2 (en) | Content information recommendation based on user behavior | |
| US10885591B1 (en) | Pre-calculated insurance premiums with wildcarding | |
| US9031967B2 (en) | Natural language processing system, method and computer program product useful for automotive data mapping | |
| US20130166488A1 (en) | Personalized information pushing method and device | |
| KR102410777B1 (en) | An apparatus for improving way of product recommendation and a method thereof | |
| CN110889737A (en) | Method and device for recommending rental roommates, server and storage medium | |
| US20220321681A1 (en) | System and method of reciprocal data sharing | |
| US11675848B2 (en) | Optimizing response creation and delivery for lending queries | |
| US20110320367A1 (en) | Method to Appraise a Patent Asset and a System to Recommend Action to Owner | |
| CN115018106A (en) | Anomaly analysis method, device, equipment and computer-readable storage medium | |
| CN112115370A (en) | Recommendation method and device, computer-readable storage medium and electronic device | |
| CN111861606A (en) | Vehicle type heat degree calculation method and device, electronic equipment and storage medium | |
| CN105430073A (en) | Message pushing method and system based on user behaviors | |
| US10235719B2 (en) | Centralized GAAP approach for multidimensional accounting to reduce data volume and data reconciliation processing costs | |
| CN114862291A (en) | Data asset value evaluation system, method, device and medium | |
| CN114387085A (en) | Method and device for processing pipeline data, computer equipment and storage medium | |
| CN113689170A (en) | Pricing processing method and device for delivery order and computer equipment | |
| US20210027317A1 (en) | Inventory and structure finder | |
| US8175937B2 (en) | Systems, methods and computer programs for financial data evaluation | |
| US7844515B1 (en) | Net present value forecast for life-time value financial processing in a relational database management system | |
| US7835959B1 (en) | Future value attrition for life-time value financial processing in a relational database management system | |
| US7844526B1 (en) | Net present value attrition for Life-Time Value financial processing in a relational database management system | |
| CN109300049A (en) | Calculation method, terminal device and the medium of declaration form loan interest | |
| US20230274304A1 (en) | Merging a two or more multi-level user structures into a multi-line user structure and simulating sponsorship of new members | |
| US20220261666A1 (en) | Leveraging big data, statistical computation and artificial intelligence to determine a likelihood of object renunciation prior to a resource event |
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 |