CN112927084A - Trading enterprise recommendation method, device, equipment and medium - Google Patents
Trading enterprise recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN112927084A CN112927084A CN202110377104.4A CN202110377104A CN112927084A CN 112927084 A CN112927084 A CN 112927084A CN 202110377104 A CN202110377104 A CN 202110377104A CN 112927084 A CN112927084 A CN 112927084A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- buyer
- transaction
- seller
- recommendation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 15
- 230000001186 cumulative effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000002860 competitive effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
- 230000001052 transient effect Effects 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
-
- 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
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a trading enterprise recommendation method, device, equipment and medium. The method comprises the following steps: acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period; obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters; determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data; and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion. Therefore, the recommendation list is generated by comprehensively considering information such as the transaction parameters, the purchase proportion and the like, the recommendation accuracy and effectiveness are enhanced, the transaction success rate is further improved, and the experience of enterprise users of the purchasing and selling parties is improved.
Description
Technical Field
The invention relates to the field of data mining, in particular to a trading enterprise recommendation method, device, equipment and medium.
Background
Currently, large-scale purchase and sale transactions between enterprises are generally performed through a proprietary B2B (Business to Business) e-commerce platform, and the purchase and sale behaviors between enterprises are greatly different from the purchase behaviors of a common single user, for example, for a purchasing enterprise user with relatively mature and stable Business, the purchase behavior has certain stability and continuity, and the conversion cost of purchasing by a conversion provider is often high, that is, the purchase saving cost is not enough to offset the conversion cost. In the prior art, some e-commerce platforms, music sharing platforms, movie sharing platforms and the like generally capture user interests for personalized recommendation by acquiring user information, user search and browse, user comments, user purchase, user social contact and other data and the like, but the recommendation modes have a certain effect on recommendation based on discovering personal user interests, but the recommendation effect is reduced when the e-commerce platform is actually applied to the B2B e-commerce platform. Therefore, how to improve the efficiency of B2B e-commerce platform business enterprise recommendation is a problem that needs to be solved urgently.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus, a device and a medium for recommending a business enterprise, which can improve the accuracy and effectiveness of recommendation of a B2B e-commerce recommendation platform. The specific scheme is as follows:
in a first aspect, the present application discloses a business enterprise recommendation method, including:
acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period;
obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters;
determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data;
and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion.
Optionally, the obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters includes:
grouping the transaction parameters according to the seller enterprises to obtain the transaction parameters corresponding to each seller enterprise, and calculating to obtain the parameter average value of various transaction parameters corresponding to each seller enterprise;
and generating a value score of each transaction parameter according to the magnitude relation between each transaction parameter and the corresponding parameter average value, and obtaining a purchasing party value score of the purchasing party enterprise relative to the selling party enterprise based on the value score of each transaction parameter.
Optionally, the determining, according to the transaction data, a purchase proportion of the buyer enterprise in different seller enterprises for the target type product includes:
determining the transaction amount of the target type product purchased by the buyer enterprise at different seller enterprises according to the transaction data;
determining the total transaction amount of the buyer enterprise aiming at the target type product according to the transaction data;
and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products based on the transaction amount and the total transaction amount.
Optionally, the transaction parameters include a latest transaction time interval, a cumulative transaction number, a cumulative transaction amount, and an average transaction time interval.
Optionally, the determining a recommended list of transaction enterprises for each seller enterprise from the buyer enterprises based on the buyer value score and the purchase proportion includes:
calculating similarity between different seller enterprises based on the buyer value scores of the buyer enterprises relative to the seller enterprises;
and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchasing proportion.
Optionally, the determining a recommended list of transaction enterprises for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchase proportion includes:
calculating recommendation scores of the buyer enterprises based on the similarity, the buyer value scores and the purchase proportion, and generating a first group of enterprise recommendation lists for the seller enterprises according to the recommendation scores;
generating a second group of enterprise recommendation lists for the seller enterprises according to the size relation between the latest transaction time interval and the average transaction time interval in the transaction parameters;
and obtaining the transaction enterprise recommendation list based on the first group of enterprise recommendation lists and the second group of enterprise recommendation lists.
Optionally, the transaction enterprise recommendation method further includes:
calculating a recommendation score for the seller enterprise based on the buyer value score and the purchase share;
and generating a sales party enterprise recommendation list for the purchasing party enterprise according to the recommendation score of the sales party enterprise.
In a second aspect, the present application discloses a transaction enterprise recommendation device, comprising:
the data acquisition module is used for acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period;
the buyer value score determining module is used for obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters;
the purchase proportion determining module is used for determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data;
and the recommendation list determining module is used for determining a transaction enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchase proportion.
In a third aspect, the present application discloses an electronic device, comprising:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the transaction enterprise recommendation method.
In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program; wherein the computer program when executed by the processor implements the aforementioned trading enterprise recommendation method.
In the application, transaction data of a buyer enterprise and a seller enterprise in a preset time period are obtained; obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters; determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data; and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion. Therefore, value scoring is carried out on the purchasing party enterprises by using the transaction parameters obtained by the transaction data, a transaction enterprise recommendation list is generated for each selling party enterprise by combining the purchase occupation ratios of the purchasing party enterprises in different selling party enterprises aiming at the target type products, and the recommendation list is generated by comprehensively considering the information such as the transaction parameters, the purchase occupation ratios and the like, so that the recommendation effectiveness and the recommendation function of the B2B electronic commerce recommendation platform are enhanced, the transaction success rate is further improved, and the user experience of the purchasing and selling party enterprises is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a business enterprise recommendation method provided herein;
FIG. 2 is a flowchart of a particular business enterprise recommendation method provided herein;
FIG. 3 is a flowchart of a particular business enterprise recommendation method provided herein;
FIG. 4 is a flowchart of a particular business enterprise recommendation method provided herein;
FIG. 5 is a schematic structural diagram of a transaction enterprise recommendation device provided in the present application;
fig. 6 is a block diagram of an electronic device provided in the present application.
Detailed Description
In the prior art, some e-commerce platforms, music sharing platforms, movie sharing platforms and the like generally capture user interests for personalized recommendation by acquiring user information, user search and browse, user comments, user purchase, user social contact and other data and the like, but the recommendation modes have a certain effect on recommendation based on discovering personal user interests, but the recommendation effect is reduced when the e-commerce platform is actually applied to the B2B e-commerce platform. In order to overcome the technical problems, the application provides a trading enterprise recommendation method which can improve the recommendation effectiveness of a B2B e-commerce recommendation platform.
The embodiment of the application discloses a trading enterprise recommendation method, and referring to fig. 1, the method can comprise the following steps:
step S11: and acquiring transaction data of the buyer enterprise and the seller enterprise within a preset time period.
In this embodiment, first, transaction data of a buyer enterprise and an seller enterprise within a preset time period is obtained, where the transaction data includes, but is not limited to, information such as transaction time, transaction goods, and transaction amount. Namely, information of transaction time, transaction goods, transaction amount and the like of transactions between a buyer enterprise and a seller enterprise in a past period of time is acquired.
Step S12: and obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters.
In this embodiment, after the transaction data is obtained, the transaction parameters of the seller enterprise and the buyer enterprise are determined according to the transaction data, and a buyer value score of the buyer enterprise relative to the seller enterprise is obtained according to the transaction parameters, that is, a value score of the seller enterprise on the corresponding buyer enterprise is obtained. The transaction parameters include, but are not limited to, a last transaction time interval, a cumulative transaction number, a cumulative transaction amount, and an average transaction time interval. Integrating the transaction data to obtain transaction parameters of four aspects of a latest transaction time Interval, an accumulated transaction number, an accumulated transaction amount and an average transaction time Interval, namely an Interval (Recency) from the latest transaction time of the buyer and the seller to the current time point, accumulated transaction number (Frequency) of the buyer and the seller and accumulated transaction amount (money) of the buyer and the seller, calculating and determining an average transaction time Interval (Interval) of the buyer and the seller by considering the action of time effect in recommendation, obtaining an MI RFclient subdivision model according to the transaction parameters, and dividing each buyer of the seller into finer granularity, thereby measuring the client value and the client profit creating capability through the RFMI client subdivision model.
And then, according to the determined transaction parameters, namely the RFMI client subdivision model, carrying out expert scoring which is more objective for the seller to the buyer by the seller. For example, if the last transaction time interval of a certain purchasing party is small, it indicates that a transaction has occurred recently, the accumulated transaction times are large, the average transaction time interval is small, it indicates that the transaction is frequent, and the accumulated transaction amount is small, it can be determined that the purchasing enterprise is a high-quality client of the corresponding selling enterprise, and at this time, the purchasing value score of the purchasing enterprise is high relative to the corresponding selling enterprise.
Step S13: and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data.
In this embodiment, after the transaction data is obtained, the purchase ratios of the buyer enterprise to various target types of products in different seller enterprises are determined according to the transaction data, that is, the purchase ratios of the buyer enterprise to the target types of products in different seller enterprises can be obtained according to the total purchase amount of the buyer enterprise to the target types of products and the purchase amounts of the target types of products in different seller enterprises, and the purchase ratios can represent the interest or preference degrees of the buyer enterprise to the target types of products sold by the seller enterprise.
Step S14: and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion.
In this embodiment, after the purchasing party value score and the purchase proportion are obtained, based on the purchasing party value score and the purchase proportion, a matching transaction enterprise is screened out for each seller enterprise from the purchasing party enterprises, and a transaction enterprise recommendation list is generated. Specifically, the similarity between different sellers and enterprises can be obtained according to the buyer value score, the corresponding recommendation score is calculated by using a preset recommendation score formula according to the detail degree, the buyer value score and the purchase proportion, and then the transaction enterprise recommendation list is generated according to the recommendation score.
As can be seen from the above, in this embodiment, transaction data of the buyer enterprise and the seller enterprise within a preset time period is obtained; obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters; determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data; and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion. Therefore, value scoring is carried out on the purchasing party enterprises by using the transaction parameters obtained by the transaction data, a transaction enterprise recommendation list is generated for each selling party enterprise by combining the purchase occupation ratios of the purchasing party enterprises in different selling party enterprises aiming at the target type products, and the recommendation list is generated by comprehensively considering the information such as the transaction parameters, the purchase occupation ratios and the like, so that the recommendation effectiveness and the recommendation function of the B2B electronic commerce recommendation platform are enhanced, the transaction success rate is further improved, and the user experience of the purchasing and selling party enterprises is improved.
The embodiment of the application discloses a specific trading enterprise recommendation method, and as shown in fig. 2, the method can include the following steps:
step S21: and acquiring transaction data of the buyer enterprise and the seller enterprise within a preset time period.
Step S22: and obtaining the transaction parameters of the seller enterprises and the buyer enterprises according to the transaction data, grouping the transaction parameters according to the seller enterprises to obtain the transaction parameters corresponding to each seller enterprise, and calculating to obtain the parameter average value of various transaction parameters corresponding to each seller enterprise.
In this embodiment, the transaction parameters may include a latest transaction time interval, a cumulative transaction number, a cumulative transaction amount, and an average transaction time interval. I.e. for each square siEach buyer b of the selleruFour fields below on the buyer granularity for buyer subdivision analysis, including last transaction time intervalAccumulating transaction timesAccumulated transaction amountAnd average transaction time intervalObtaining an RFMI parameter table; then based on the selling and purchasing party RFMI parameter table, aiming at each selling party siBy carrying out the polymerization to give all their suppliersAverage of The average may also use a median.
Step S23: and generating a value score of each transaction parameter according to the magnitude relation between each transaction parameter and the corresponding parameter average value, and obtaining a purchasing party value score of the purchasing party enterprise relative to the selling party enterprise based on the value score of each transaction parameter.
In this embodiment, a value score of each transaction parameter is generated according to a magnitude relationship between each transaction parameter and the corresponding parameter average value, and a buyer value score of the buyer enterprise relative to the seller enterprise is obtained based on the value score of each transaction parameter. Specifically, after obtaining the average value of the parameters, theMaking a comparison, a value score for each transaction parameter The value scores can be set respectively in the following ways: when in useTime of flightTaking 1, and taking 0 in other cases;time of flightTaking 1, and taking 0 in other cases;time of flightTaking 1, and taking 0 in other cases;time of flightTake 1 for the rest cases and 0 for the rest cases. Thereby adding to the selling party RFMI table Four field values;theoretically have a total of 24The seller s can be divided into 16 different combination types according to the client subdivision model in data mining and the attention degree of different indexes in the actual business sceneiAll the purchasing clients buPush buttonThe different combination types are divided into premium customers, potential customers, attrition customers, etc. I.e. different score values are set for different combination typesTo indicate the square of the pin siTo the buyer buThe degree of preference. For example, whenWhen b is greater thanuAnd siRecently, the transaction amount is low and the transaction is frequent, and b can be considereduIs s isiOf a good quality client, at this timeLarge value, the same reason isWhen it is, b can be identifieduIs s isiOf lost unimportant customers, whenThe value is small. Then, for each square siAll ofStandardized setting is carried out, and the value range is set to be [0, 1%]In the meantime. Then will beAdded to the above-mentioned on-market RFMI tables.
Step S24: and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data.
In this embodiment, the determining, according to the transaction data, a purchase proportion of the buyer enterprise in different seller enterprises with respect to the target type product may include: determining the transaction amount of the target type product purchased by the buyer enterprise at different seller enterprises according to the transaction data; determining the total transaction amount of the buyer enterprise aiming at the target type product according to the transaction data; and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products based on the transaction amount and the total transaction amount. It will be appreciated that for each of the purchasers buIntegrating the transaction data of different traded commodities to obtain the buyer b in the time perioduAnd square of the pin siTarget type product c of transactionpAmount of transaction, and buyer b in the perioduTarget type product c of transactionpThe total amount of the transaction is calculated to obtain the purchasing proportion so as to characterize the purchasing party buCounter square siGoods cpThe purchase percentage calculation formula is as follows:
Step S25: and calculating the similarity between different seller enterprises based on the buyer value scores of the buyer enterprises relative to the seller enterprises.
In this embodiment, the similarity between different marketer enterprises is calculated according to the buyer value score of the buyer enterprise relative to the marketer enterprise. Namely, the Pearson correlation coefficient (Pearson correlation coefficient) between different marketer enterprises is calculated according to the buyer value scores of different marketer enterprises by a plurality of marketer enterprises. In particular, according to the score obtainedsbCalculating the square of the sale siAnd sjIs used to describe siAnd sjThe similarity degree calculation formula is as follows:
wherein the content of the first and second substances,respectively representing and selling square si、sjThe aggregate of all the buyer enterprises having transaction behaviors,respectively representing squares of pins si、sjThe average value of all the buyer enterprises with transaction behaviors is scored, and in actual deployment,andthe aggregate may be based on the transaction amountAndmaking appropriate scaling, e.g. taking only the square si、sjThe transaction behavior is over-transacted and is in order from large to small according to the transaction amountOrdering a predetermined number of sets of purchasing enterprises, correspondingAndalso correspondingly atAndthe average value calculation was performed above. According to sim(s)i,sj) Can obtain the sum square siSet of most similar K squares, denoted N(s)i,K)。
Step S26: and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchasing proportion.
In this embodiment, the determining a recommended list of transaction enterprises for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score, and the purchase ratio may include: calculating recommendation scores of the buyer enterprises based on the similarity, the buyer value scores and the purchase proportion, and generating a first group of enterprise recommendation lists for the seller enterprises according to the recommendation scores; generating a second group of enterprise recommendation lists for the seller enterprises according to the size relation between the latest transaction time interval and the average transaction time interval in the transaction parameters; and obtaining the transaction enterprise recommendation list based on the first group of enterprise recommendation lists and the second group of enterprise recommendation lists.
As shown in fig. 3, calculating recommendation scores of the buyer enterprises according to the similarity, the buyer value score and the purchase percentage, and generating a first group of enterprise recommendation lists for the seller enterprises according to the recommendation scores; specifically, the seller is marked according to the similarity, the buyer value score and the purchase ratioiRecommending buyer buRecommendation score ofWill recommend scoring with the seller siTarget type product cpWhen the change occurs, the calculation formula of the recommendation score is as follows:
it will be appreciated that the square of the pin siRecommending buyer buRecommendation score ofDepending not only on the buyer value score, but also on the purchase proportion. The value score for the buyer represents the seller siThrough with sjTo the buyer buCan be considered as a seller siTo the buyer buSubjective interest, if trading is to be generated, the buyer b is also requireduFor product cpThe purchase proportion is also determined by the seller sjAnd square of the pin siAssociated with this, when the buyer's value score is greater than the purchase percentage, it is the seller siRecommending buyer buRecommendation score ofAnd the recommendation method is also large, so that the recommendation is performed by comprehensively considering the purchase proportion and the value score of the buyer, the recommendation efficiency can be improved, and the actual transaction behavior is promoted to occur. According to the recommendation score, is the seller siAnd generating a first group of enterprise recommendation lists of the preliminary recommendation list, wherein the lists are sorted from high to low according to the scores, and the first group of enterprise recommendation lists obtained according to the transaction parameters and the purchase proportion comprise the buyer enterprises with the long-tail effect on the seller enterprises. The first group of business recommendation lists is obtained for the seller siRecommended list of newly expandable purchasing enterprise users, i.e. newly expandable purchasing enterprise users are likely to serve as competitor sellers sjIs based on the premium or potential buyer enterprise customersCompeting sellers sjMay be the seller siProviding effective market information while at the same time will be based on the seller siGenerates a recommendation result and recommends the recommendation result to the seller sjTo avoid creating a recommendation imbalance. Therefore, to maintain the square sjThe own high quality and potential buyer enterprise users keep the recommendation balance and maintain the fairness of the B2B electronic commerce recommendation platform. In addition, the reminder s can be reminded when the time interval of the latest transaction exceeds the preset timejSelf-owned high-quality and potential buyer enterprise users, go key point reminding sjOwn high-quality and potential buyer enterprise user buForming a second group of enterprise recommendation lists of the recommendation lists;
Then, combining the first group of enterprise recommendation lists and the second group of enterprise recommendation lists to generate an off-seller siThe recommendation list of transaction enterprises:
wherein the content of the first and second substances,a roster is recommended for a first group of businesses,a roster is recommended for the second group of businesses.
For the specific process of the step S21, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
As can be seen from the above, in this embodiment, transaction parameters of the seller enterprises and the buyer enterprises are obtained according to the transaction data, the transaction parameters are grouped according to the seller enterprises to obtain transaction parameters corresponding to each seller enterprise, and a parameter average value of various types of transaction parameters corresponding to each seller enterprise is calculated; and generating a value score of each transaction parameter according to the magnitude relation between each transaction parameter and the corresponding parameter average value, obtaining a purchasing party value score of the purchasing enterprise relative to the selling party enterprise based on the value score of each transaction parameter, and calculating the similarity between different selling party enterprises based on the purchasing party value score of the purchasing enterprise relative to the selling party enterprise. And determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchasing proportion. Therefore, the transaction data are effectively mined in multiple aspects, the data mining result is used for describing the transaction viscosity of both sellers and buyers for recommendation, and the recommendation effectiveness problem in the B2B e-commerce recommendation platform can be effectively solved. And in the case of recommending the buyer enterprises for the seller enterprise users, the transaction viscosity of the seller parties depends on the seller parties, and the transaction viscosity of the buyer enterprises is generally dominated by the buyer parties, so that the similarity of the seller enterprises is calculated through the value score of the buyer parties, and the recommendation accuracy is improved.
In combination with the above embodiments, the present application discloses a specific business enterprise recommendation method, as shown in fig. 4, the method may include the following steps:
step S31: and acquiring transaction data of the buyer enterprise and the seller enterprise within a preset time period.
Step S32: and obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters.
Step S33: and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data.
Step S34: and calculating the recommendation score of the seller enterprise based on the buyer value score and the purchase proportion, and generating a seller enterprise recommendation list for the buyer enterprise according to the recommendation score of the seller enterprise.
In this embodiment, for example, as shown in fig. 3, similarity between different marketer enterprises is calculated according to the buyer value score of a buyer enterprise relative to a marketer enterprise, then a recommendation score of the marketer enterprise is calculated according to the similarity, the buyer value score and the purchase percentage, and a marketer enterprise recommendation list is generated for the buyer enterprise according to the recommendation score of the marketer enterprise. The above is the buyer buRecommending sellers siIs recorded as a recommendation score ofThe recommendation score of the seller enterprise can be compared with the recommendation score of the buyer enterpriseThe formula for calculating the seller enterprise recommendation score is as follows:
wherein the content of the first and second substances,to and from the buyer buThe set of all the sellers who have traded occur,can be arranged in a manner similar to that described aboveThe arrangement of (1). According toAs a buyer buGenerating a sales party enterprise recommendation list
For the specific processes of the above steps S31 to S33, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
As can be seen from the above, in this embodiment, the recommendation score of the seller enterprise is calculated based on the buyer value score and the purchase percentage, and a seller enterprise recommendation list is generated for the buyer enterprise according to the recommendation score of the seller enterprise. Therefore, the seller enterprise recommendation list is generated based on the buyer value score and the purchasing proportion, and the buyer enterprise can be helped to expand the purchasing range on the basis of the embodiment, promote fair competition and form an effective competitive market. When the buyer enterprises are recommended for the seller enterprise users, the buyer customers of other seller enterprises in a competitive relationship are probably recommended, and the competition is promoted to a certain extent; when the seller enterprise is recommended for the buyer enterprise user, the method can help the buyer enterprise to expand the purchasing range, improve the bargaining capability of the buyer enterprise and promote competition to a certain extent.
Correspondingly, the embodiment of the present application further discloses a transaction enterprise recommendation device, as shown in fig. 5, the device includes:
the data acquisition module 11 is used for acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period;
a buyer value score determining module 12, configured to obtain transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtain a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters;
a purchase proportion determining module 13, configured to determine, according to the transaction data, a purchase proportion of the buyer enterprise in different seller enterprises for the target type product;
and a recommendation list determining module 14, configured to determine a recommendation list of transaction enterprises from the buyer enterprises for each seller enterprise based on the buyer value score and the purchase proportion.
As can be seen from the above, in this embodiment, transaction data of the buyer enterprise and the seller enterprise within a preset time period is obtained; obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters; determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data; and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion. Therefore, value scoring is carried out on the purchasing party enterprises by using the transaction parameters obtained by the transaction data, a transaction enterprise recommendation list is generated for each selling party enterprise by combining the purchase occupation ratios of the purchasing party enterprises in different selling party enterprises aiming at the target type products, and the recommendation list is generated by comprehensively considering the information such as the transaction parameters, the purchase occupation ratios and the like, so that the recommendation effectiveness and the recommendation function of the B2B electronic commerce recommendation platform are enhanced, the transaction success rate is further improved, and the user experience of the purchasing and selling party enterprises is improved.
In some embodiments, the buyer value score determination module 12 may specifically include:
the parameter average value calculating unit is used for grouping the transaction parameters according to the seller enterprises to obtain the transaction parameters corresponding to each seller enterprise, and calculating to obtain the parameter average value of various transaction parameters corresponding to each seller enterprise;
and the buyer value score calculating unit is used for generating a value score of each transaction parameter according to the magnitude relation between each transaction parameter and the corresponding parameter average value, and obtaining the buyer value score of the buyer enterprise relative to the seller enterprise based on the value score of each transaction parameter.
In some specific embodiments, the purchase proportion determining module 13 may specifically include:
the transaction amount calculation unit is used for determining the transaction amount of the target type product purchased by the purchasing enterprise in different selling enterprises according to the transaction data;
the total transaction amount calculation unit is used for determining the total transaction amount of the buyer enterprise aiming at the target type product according to the transaction data;
and the purchase proportion calculation unit is used for determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type product based on the transaction amount and the total transaction amount.
In some embodiments, the transaction parameters may include a last transaction time interval, a cumulative number of transactions, a cumulative transaction amount, and an average transaction time interval.
In some specific embodiments, the recommendation list determining module 14 may specifically include:
the similarity calculation unit is used for calculating the similarity between different seller enterprises based on the buyer value scores of the buyer enterprises relative to the seller enterprises;
and the transaction enterprise recommendation list determining unit is used for determining a transaction enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchase proportion.
In some specific embodiments, the transaction enterprise recommendation list determining unit may specifically include:
the first group of enterprise recommendation list determining unit is used for calculating recommendation scores of the buyer enterprises based on the similarity, the buyer value scores and the purchasing proportion and generating a first group of enterprise recommendation lists for the seller enterprises according to the recommendation scores;
a second group of enterprise recommendation list determining unit, configured to generate a second group of enterprise recommendation lists for the seller enterprises according to a size relationship between the latest transaction time interval and the average transaction time interval in the transaction parameters;
and the list combining unit is used for obtaining the transaction enterprise recommended list based on the first group of enterprise recommended lists and the second group of enterprise recommended lists.
In some embodiments, the transaction enterprise recommendation device may specifically include:
the seller enterprise recommendation list determining module is used for calculating recommendation scores of the seller enterprises based on the buyer value scores and the purchase percentage; and generating a sales party enterprise recommendation list for the purchasing party enterprise according to the recommendation score of the sales party enterprise.
Further, the embodiment of the present application also discloses an electronic device, which is shown in fig. 6, and the content in the drawing cannot be considered as any limitation to the application scope.
Fig. 6 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present disclosure. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein, the memory 22 is used for storing a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the transaction enterprise recommendation method disclosed in any of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide a working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol applicable to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to obtain external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
In addition, the memory 22 is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., the resources stored thereon include an operating system 221, a computer program 222, data 223 including transaction data, etc., and the storage manner may be a transient storage or a permanent storage.
The operating system 221 is used for managing and controlling each hardware device and the computer program 222 on the electronic device 20, so as to realize the operation and processing of the mass data 223 in the memory 22 by the processor 21, and may be Windows Server, Netware, Unix, Linux, and the like. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the business enterprise recommendation method performed by the electronic device 20 disclosed in any of the foregoing embodiments.
Further, an embodiment of the present application further discloses a computer storage medium, where computer-executable instructions are stored in the computer storage medium, and when the computer-executable instructions are loaded and executed by a processor, the steps of the transaction enterprise recommendation method disclosed in any of the foregoing embodiments are implemented.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The method, the device, the equipment and the medium for recommending the transaction enterprise provided by the invention are described in detail, specific examples are applied in the description to explain the principle and the implementation mode of the invention, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for recommending a business, comprising:
acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period;
obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data, and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters;
determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data;
and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchasing proportion.
2. The trading enterprise recommendation method of claim 1, wherein said deriving a buyer value score for the buyer enterprise relative to the seller enterprise based on the trading parameters comprises:
grouping the transaction parameters according to the seller enterprises to obtain the transaction parameters corresponding to each seller enterprise, and calculating to obtain the parameter average value of various transaction parameters corresponding to each seller enterprise;
and generating a value score of each transaction parameter according to the magnitude relation between each transaction parameter and the corresponding parameter average value, and obtaining a purchasing party value score of the purchasing party enterprise relative to the selling party enterprise based on the value score of each transaction parameter.
3. The method of claim 1, wherein the determining the purchase proportion of the buyer enterprise in different seller enterprises for the target type product according to the transaction data comprises:
determining the transaction amount of the target type product purchased by the buyer enterprise at different seller enterprises according to the transaction data;
determining the total transaction amount of the buyer enterprise aiming at the target type product according to the transaction data;
and determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products based on the transaction amount and the total transaction amount.
4. The trading enterprise recommendation method of claim 1, wherein the trading parameters include a last trading time interval, a cumulative number of trades, a cumulative trading amount, and an average trading time interval.
5. The method of claim 4, wherein the determining a recommendation list of traded businesses from the buyer businesses for each seller business based on the buyer value score and the purchase proportion comprises:
calculating similarity between different seller enterprises based on the buyer value scores of the buyer enterprises relative to the seller enterprises;
and determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchasing proportion.
6. The trading enterprise recommendation method of claim 5, wherein determining a trading enterprise recommendation list for each seller enterprise from the buyer enterprises based on the similarity, the buyer value score and the purchase proportion comprises:
calculating recommendation scores of the buyer enterprises based on the similarity, the buyer value scores and the purchase proportion, and generating a first group of enterprise recommendation lists for the seller enterprises according to the recommendation scores;
generating a second group of enterprise recommendation lists for the seller enterprises according to the size relation between the latest transaction time interval and the average transaction time interval in the transaction parameters;
and obtaining the transaction enterprise recommendation list based on the first group of enterprise recommendation lists and the second group of enterprise recommendation lists.
7. The trading enterprise recommendation method of any one of claims 1-6, further comprising:
calculating a recommendation score for the seller enterprise based on the buyer value score and the purchase share;
and generating a sales party enterprise recommendation list for the purchasing party enterprise according to the recommendation score of the sales party enterprise.
8. A transaction enterprise recommendation device, comprising:
the data acquisition module is used for acquiring transaction data of a buyer enterprise and a seller enterprise within a preset time period;
the buyer value score determining module is used for obtaining transaction parameters of the seller enterprise and the buyer enterprise according to the transaction data and obtaining a buyer value score of the buyer enterprise relative to the seller enterprise based on the transaction parameters;
the purchase proportion determining module is used for determining the purchase proportion of the buyer enterprise in different seller enterprises aiming at the target type products according to the transaction data;
and the recommendation list determining module is used for determining a transaction enterprise recommendation list for each seller enterprise from the buyer enterprises based on the buyer value score and the purchase proportion.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the trading enterprise recommendation method of any one of claims 1 to 7.
10. A computer-readable storage medium for storing a computer program; wherein the computer program when executed by the processor implements the trading enterprise recommendation method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110377104.4A CN112927084A (en) | 2021-04-08 | 2021-04-08 | Trading enterprise recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110377104.4A CN112927084A (en) | 2021-04-08 | 2021-04-08 | Trading enterprise recommendation method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112927084A true CN112927084A (en) | 2021-06-08 |
Family
ID=76173700
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110377104.4A Pending CN112927084A (en) | 2021-04-08 | 2021-04-08 | Trading enterprise recommendation method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112927084A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000054821A (en) * | 2000-06-27 | 2000-09-05 | 박창영 | B2B e-comerce system by value evaluation and method thereof |
US20150025995A1 (en) * | 2013-07-19 | 2015-01-22 | Ebay Inc. | Generating recommendations based on transaction data |
CN108427695A (en) * | 2017-08-04 | 2018-08-21 | 平安科技(深圳)有限公司 | Method and application server are recommended by enterprise |
CN108765052A (en) * | 2018-04-20 | 2018-11-06 | 网易无尾熊(杭州)科技有限公司 | Electric business recommendation/method for pushing and device, storage medium and computing device |
CN109300003A (en) * | 2018-09-17 | 2019-02-01 | 平安科技(深圳)有限公司 | Enterprise's recommended method, device, computer equipment and storage medium |
CN111242720A (en) * | 2019-12-30 | 2020-06-05 | 航天信息股份有限公司 | Method and system for recommending suppliers for shopping providers |
CN112418758A (en) * | 2020-11-17 | 2021-02-26 | 国网电子商务有限公司 | Method and system for intelligently recommending carriers to shippers |
-
2021
- 2021-04-08 CN CN202110377104.4A patent/CN112927084A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000054821A (en) * | 2000-06-27 | 2000-09-05 | 박창영 | B2B e-comerce system by value evaluation and method thereof |
US20150025995A1 (en) * | 2013-07-19 | 2015-01-22 | Ebay Inc. | Generating recommendations based on transaction data |
CN108427695A (en) * | 2017-08-04 | 2018-08-21 | 平安科技(深圳)有限公司 | Method and application server are recommended by enterprise |
CN108765052A (en) * | 2018-04-20 | 2018-11-06 | 网易无尾熊(杭州)科技有限公司 | Electric business recommendation/method for pushing and device, storage medium and computing device |
CN109300003A (en) * | 2018-09-17 | 2019-02-01 | 平安科技(深圳)有限公司 | Enterprise's recommended method, device, computer equipment and storage medium |
CN111242720A (en) * | 2019-12-30 | 2020-06-05 | 航天信息股份有限公司 | Method and system for recommending suppliers for shopping providers |
CN112418758A (en) * | 2020-11-17 | 2021-02-26 | 国网电子商务有限公司 | Method and system for intelligently recommending carriers to shippers |
Non-Patent Citations (2)
Title |
---|
王文贤;金阳;陈道斌;: "基于RFM模型的个人客户忠诚度研究", 金融论坛, no. 03 * |
赵晓煜;黄小原;曹忠鹏;: "基于顾客交易数据的协同过滤推荐方法", 东北大学学报(自然科学版), no. 12, pages 1792 - 1795 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | The role of social networks in online shopping: information passing, price of trust, and consumer choice | |
EP2304619B1 (en) | Correlated information recommendation | |
Putsis Jr et al. | Buying or just browsing? The duration of purchase deliberation | |
Hartline | Bayesian mechanism design | |
JP6753578B2 (en) | Methods and equipment for selecting and recommending presentation targets on electronic distribution platforms | |
US11321724B1 (en) | Product evaluation system and method of use | |
JP6440661B2 (en) | Determination device, determination method, and determination program | |
McKie et al. | How do consumers choose between multiple product generations and conditions? An empirical study of iPad sales on eBay | |
CN111080409A (en) | Computer device, method, equipment and medium for pushing information | |
CN112528153B (en) | Content recommendation method, device, apparatus, storage medium, and program product | |
JP5957164B1 (en) | Information processing apparatus, information processing method, and information processing program | |
KR101509131B1 (en) | Method for providing evaluation of online seller | |
CN110347924A (en) | Fruits and vegetables market management system and fruit-vegetable information method for pushing | |
EP2524345A1 (en) | Attribute aggregation for standard product unit | |
WO2016157427A1 (en) | Information processing device, information processing method, and information processing program | |
JP2012150563A (en) | Product recommendation device, method, and program | |
JP2007041869A (en) | Investment support system and method | |
JP6397092B1 (en) | Distribution apparatus, distribution method, and distribution program | |
JP2020086675A (en) | Information processing device, information processing method, and information processing program | |
US11568471B2 (en) | Systems and methods for listing an item | |
Jiao et al. | A framework for reputation bootstrapping based on reputation utility and game theories | |
JP5824601B1 (en) | Information processing apparatus, information processing method, and information processing program | |
US20130275249A1 (en) | Best price discovery with buyer commitment | |
CN112927084A (en) | Trading enterprise recommendation method, device, equipment and medium | |
JP6305595B1 (en) | Information providing apparatus, information providing method, and information providing program |
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 |