CN113807921A - Data commodity recommendation method and device, electronic equipment and computer readable storage medium - Google Patents

Data commodity recommendation method and device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN113807921A
CN113807921A CN202111095034.XA CN202111095034A CN113807921A CN 113807921 A CN113807921 A CN 113807921A CN 202111095034 A CN202111095034 A CN 202111095034A CN 113807921 A CN113807921 A CN 113807921A
Authority
CN
China
Prior art keywords
value
buyer
seller
data
transaction 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.)
Granted
Application number
CN202111095034.XA
Other languages
Chinese (zh)
Other versions
CN113807921B (en
Inventor
洪博然
庄梓琦
杜自然
邵雷
董传晔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yi Chengqi
Shenzhen Shujuwan District Big Data Research Institute
Original Assignee
Yi Chengqi
Shenzhen Shujuwan District Big Data Research Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yi Chengqi, Shenzhen Shujuwan District Big Data Research Institute filed Critical Yi Chengqi
Priority to CN202111095034.XA priority Critical patent/CN113807921B/en
Publication of CN113807921A publication Critical patent/CN113807921A/en
Application granted granted Critical
Publication of CN113807921B publication Critical patent/CN113807921B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a data commodity recommendation method, a data commodity recommendation device, an electronic device and a nonvolatile computer readable storage medium. The data commodity recommendation method comprises the following steps: acquiring transaction data of a buyer and transaction data of a seller; inputting transaction data of the buyer into an AI model to obtain a first Shapril value; inputting the transaction data of the buyer and the transaction data of the seller into an AI model to obtain a second Shapril value; obtaining the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and acquiring a recommendation list according to the influence value. The data commodity recommendation method can acquire transaction data of a buyer and transaction data of a seller, and acquire the influence value according to the transaction data of the buyer and the transaction data of the seller, so that the recommendation list is acquired according to the influence value to assist in matching transactions, benefits of both parties of the transaction are maximized as much as possible, and transaction contribution rate is improved.

Description

Data commodity recommendation method and device, electronic equipment and computer readable storage medium
Technology neighborhood
The present application relates to the field of big data and artificial intelligence technologies, and in particular, to a data commodity recommendation method, a data commodity recommendation apparatus, an electronic device, and a non-volatile computer-readable storage medium.
Background
With the maturity and development of big data technology, big data is more and more widely applied to business, and the demand of big data transaction is increasing. The big data is different from the entity commodity, so that the value of the big data is difficult to evaluate, and the values of different big data commodities to different types of industry fields and application scenes are different, so that the transaction matching between buyers and sellers is difficult to effectively carry out.
Disclosure of Invention
The embodiment of the application provides a data commodity recommending method, a data commodity recommending device, electronic equipment and a nonvolatile computer readable storage medium.
The data commodity recommendation method in the embodiment of the application comprises the following steps: acquiring transaction data of a buyer and transaction data of a seller; inputting transaction data of the buyer into an AI model to obtain a first Shapril value; inputting the transaction data of the buyer and the transaction data of the seller into an AI model to obtain a second Shapril value; obtaining the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and acquiring a recommendation list according to the influence value.
The data commodity recommending device comprises an obtaining module, an AI processing module and a recommending module. The acquisition module is used for acquiring transaction data of a buyer and transaction data of a seller. The AI processing module is configured to input the buyer's transaction data into an AI model to obtain a first salpril value. The AI processing module is further configured to input the buyer's transaction data and the seller's transaction data into an AI model to obtain a second salpril value. The AI processing module is further configured to obtain an influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value. And the recommending module is used for acquiring a recommending list according to the influence value.
The electronic device of the embodiment of the application comprises one or more processors, a memory; and one or more programs, wherein the one or more programs are stored in the memory and executed by the one or more processors. The processor is configured to: acquiring transaction data of a buyer and transaction data of a seller; inputting transaction data of the buyer into an AI model to obtain a first Shapril value; inputting the transaction data of the buyer and the transaction data of the seller into an AI model to obtain a second Shapril value; obtaining the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and acquiring a recommendation list according to the influence value.
A non-transitory computer-readable storage medium containing a computer program according to an embodiment of the present application, which, when executed by one or more processors, causes the processors to implement a data item recommendation method according to an embodiment of the present application. The data commodity recommendation method comprises the following steps: acquiring transaction data of a buyer and transaction data of a seller; inputting transaction data of the buyer into an AI model to obtain a first Shapril value; inputting the transaction data of the buyer and the transaction data of the seller into an AI model to obtain a second Shapril value; obtaining the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and acquiring a recommendation list according to the influence value.
The data commodity recommending method, the data commodity recommending device, the electronic equipment and the nonvolatile computer readable storage medium can acquire transaction data of a buyer and transaction data of a seller, and acquire an influence value according to the transaction data of the buyer and the transaction data of the seller, so that a recommendation list is acquired according to the influence value to assist in matching transactions, benefits of two transaction parties are maximized as much as possible, and transaction contribution rate is improved.
Additional aspects and advantages of embodiments of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart diagram of a data good recommendation method according to some embodiments of the present application;
FIG. 2 is a schematic structural diagram of an electronic device according to some embodiments of the present application;
FIG. 3 is a schematic block diagram of a data good recommender according to some embodiments of the present application;
FIG. 4 is a schematic flow chart diagram of a data good recommendation method according to some embodiments of the present application;
FIG. 5 is a schematic flow chart diagram of a data good recommendation method according to some embodiments of the present application;
FIG. 6 is a schematic flow chart diagram of a data good recommendation method in accordance with certain embodiments of the present application;
FIG. 7 is a schematic flow chart diagram of a data good recommendation method in accordance with certain embodiments of the present application;
FIG. 8 is a schematic flow chart diagram of a data good recommendation method in accordance with certain embodiments of the present application;
FIG. 9 is a schematic flow chart diagram of a data good recommendation method according to some embodiments of the present application;
FIG. 10 is a schematic diagram of a connection between a computer-readable storage medium and a processor according to some embodiments of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the embodiments of the present application.
The embodiment of the application provides a data commodity recommendation method. Referring to fig. 1, a data commodity recommendation method according to an embodiment of the present application includes:
01: acquiring transaction data of a buyer and transaction data of a seller;
02: inputting transaction data of a buyer into an AI model to obtain a first Shapril value;
03: inputting transaction data of the buyer and transaction data of the seller into the AI model to obtain a second Shapril value;
04: acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and
05: and acquiring a recommendation list according to the influence value.
Referring to fig. 2, an electronic device 100 is further provided in the present embodiment, where the electronic device 100 includes one or more processors 30 and a memory 20; and one or more programs, where the one or more programs are stored in memory 20 and executed by one or more processors 30. For example, the processor 30 may be configured to perform methods 01, 02, 03, 04, and 05, i.e., the processor 30 may be configured to: acquiring transaction data of a buyer and transaction data of a seller; inputting transaction data of a buyer into an AI model to obtain a first Shapril value; inputting transaction data of the buyer and transaction data of the seller into the AI model to obtain a second Shapril value; acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and acquiring a recommendation list according to the influence value.
The electronic device 100 may be a mobile phone, a tablet computer, a desktop computer, a notebook computer, a smart watch, a server, etc., which are not listed here. As shown in fig. 2, in the embodiment of the present application, the electronic device 100 is a mobile phone as an example, and it is understood that the specific form of the electronic device 100 is not limited to the mobile phone.
Referring to fig. 3, the present embodiment further provides a data commodity recommendation device 10. Referring to fig. 2, in some embodiments, the data commodity recommendation device 10 may be applied to the electronic device 100. The data commodity recommendation device 10 includes an acquisition module 11, an AI processing module 12, and a recommendation module 13. The obtaining module 11 is used for implementing the method in 01, the AI processing module 12 is used for implementing the methods in 02, 03 and 04, and the recommending module 13 is used for implementing the method in 05. That is, the obtaining module 11 is used for obtaining transaction data of a buyer and transaction data of a seller. The AI processing module 12 is configured to input transaction data of the buyer into the AI model to obtain a first salpril value; inputting transaction data of the buyer and transaction data of the seller into the AI model to obtain a second Shapril value; and acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value. The recommending module 13 is configured to obtain a recommending list according to the influence value.
The electronic device 100 and the data commodity recommendation device 10 may be used to build a data commodity transaction platform, and the data commodity transaction platform may obtain a recommendation list by applying the data commodity recommendation method and provide the recommendation list to an object participating in data transaction.
In one embodiment, the transaction data of the buyer may include one or more of a purchase bid, a purchase amount, a purchase time, and a purchase data type of the buyer. The transaction data for the seller may include one or more of a selling price, a selling amount, a selling time, and a selling data type of the seller.
The first value of salpril is used to evaluate the projected revenue for a buyer in the overall buyer pool. Assuming that the first value of salpril is V1(Bi), V1(Bi) can be determined by equation 1.
Equation 1:
Figure BDA0003268909190000041
wherein, Bi is shownShowing the ith buyer, N is the buyer group composed of all buyers, S is the buyer group composed of different buyers, S is the subset of N, N is the number of all buyers, B (S) is the contribution degree of the group S, and B (S \ Bi } is the contribution degree of the group S after removing Bi from the buyers.
Figure BDA0003268909190000042
Representing the predicted revenue weight of the buyer Bi in the buyer group S. [ B (S) -B (S \ Bi })]Represents the contribution degree of the buyer Bi in the buyer group S.
For example, n-3 indicates that the first salpril value is calculated from the transaction data of 3 buyers. Suppose three buyers are B1, B2, B3, respectively. The group that buyer B1 may constitute includes: s1 ═ B1, S2 ═ B1, B2, and S3 ═ B1, B2, B3. After the contribution degrees of the buyer B1 in the groups S1, S2 and S3 are respectively calculated, the 3 contribution degrees are summed to obtain the predicted profit of the buyer B1, namely V1 (B1).
In one embodiment, B (S) may be determined based on transaction data of the buyers comprised by the group S. For example, S2 ═ { B1, B2}, B (S2) ═ K (K)B1+KB2)×QB1，B2. Wherein, KB1、KB2The purchase amounts corresponding to buyer B1 and buyer B2, respectively, are weighted bids obtained according to the purchase bid of buyer B1 and the purchase bid of buyer B2, and B (S2) can reflect the degree of contribution to the big data transaction when buyer B1 and buyer B2 both participate in the big data transaction. For another example, S1 ═ { B1}, B (S2) ═ KB1×QB1. Wherein, KB1Is the purchase amount, Q, of buyer B1B1Is a purchase bid for buyer B1. The method for calculating the contribution degree b (S) of the buyer group S is not limited to the calculation method illustrated in the present embodiment, and is not limited herein.
Similarly, B (S \ i }) may be determined from the transaction data of the buyers contained in the group S \ i }. For example, if S2 ═ B1, B2, and S2\ B1} indicates that the buyer B1 is removed from the group S2, then S2\ B1 ═ B2}, B (S2\ B2} can be determined according to the transaction data of the buyer B2, and the calculation method can refer to the calculation method of B (S), and will not be described herein again.
The second value of salpril is used to evaluate the expected revenue of a transaction for a buyer and a seller in a group of all buyers and sellers. Assuming that the second salpril value is V2(Bi n Cj), V2(Bi n Cj) can be determined by equation 2.
Equation 2:
Figure BDA0003268909190000043
where Cj represents the jth seller, and M is the group of all sellers and sellers. M is the number of all combinations of the seller and the buyer in the group M of all the sellers and sellers, for example, M { B1, B2, C1, C2}, where M ═ 4 is determined by excluding the combination B1 ≠ B2 excluding the buyer and the combination C1 & ' C2 excluding the seller and the combination C2, B1 & ' C1, B1 & ' C2, B2 & ' C1, B2 & ' C2. T is a distinct group consisting of at least 1 buyer and at least 1 seller, T is a subset of M. U (T) is the contribution of the group T, and U (T \ Bi ^ Cj }) is the contribution of the group T after the combination of the buyer Bi and the seller Cj is removed.
Figure BDA0003268909190000051
Representing the projected revenue weight of the combination of buyer Bi and seller Cj in the population T. [ U (T) -U (T \ Bi n Cj })]Represents the contribution degree of the combination of the buyer Bi and the seller Cj in the group T.
In one embodiment, u (t) may be computationally derived using a federal learning model. For example, the buyer data includes a purchase bid QBiAnd purchase amount KBiThe seller data includes selling price QCjAnd sales KCj. Can offer Q a purchaseBiAnd selling price QCjInput Federal learning model training to obtain an estimated transaction price QijAnd the purchase amount KBiAnd sales KCjInput Federal learning model training to obtain estimated transaction amount KijWherein Bi is equal to T, Cj is equal to T, and the specific training process is not described herein. According to an estimated transaction price QijAnd estimating the transaction amount KijThe contribution u (T) of the population T can be obtained.
In yet another embodiment, the purchase bid Q can be based onBiAnd selling price QCjUsing regression modelsType acquisition estimated trading price QijAnd according to purchase amount KBiAnd sales KCjObtaining an estimated transaction amount K using a regression modelijTo base on the estimated trading price QijAnd estimating the transaction amount KijThe contribution u (T) of the population T is obtained.
Similar to the method for obtaining U (T), the contribution U (T \ Bi n Cj } of the group T \ Bi n Cj) can be obtained according to the transaction data of the buyer and the seller and the transaction data of the corresponding group T \ Bi n Cj, and the details are not repeated herein.
The influence value is used to evaluate the influence of the transaction data of the seller on the transaction data of the buyer, i.e. the contribution of the seller Cj in the combination Bi ≈ Cj composed of the seller Cj and the buyer Bi. Assuming that the influence value is V3(Bi, Cj), V3(Bi, Cj) becomes V2(Bi ≠ Cj) -V1 (Bi).
In this way, for the buyer, the contribution degree of each seller in the seller group to the transaction combination formed by the seller and the buyer can be obtained by using the influence value, so as to help the buyer to select the transaction object, to perform transaction with the seller with the larger influence value, and to increase the expected income for the buyer.
For example, the influence value V3(B1, C1) is the contribution degree of the seller C1 in the transaction combination of the buyer B1 and the seller C1, the influence value V3(B1, C2) is the contribution degree of the seller C2 in the transaction combination of the buyer B1 and the seller C2, and the buyer B1 can select the transaction object according to the size of the influence value V3(B1, C1) and the influence value V3(B1, C2).
Similarly, for the seller, the influence value can be used to obtain the contribution degree of the seller to each buyer in the buyer group so as to help the seller to select the transaction object. The larger the influence value of the seller on the buyer is, the higher the expected profit provided to the buyer is, the more willing the buyer is to buy the data of the seller, and the higher transaction contribution rate can be ensured when the seller selects the buyer with the larger influence value to conduct the transaction.
For example, the influence value V3(B1, C1) is the degree of contribution of the seller C1 to the transaction combination of the seller C1 and the buyer B1, the influence value V3(B2, C1) is the degree of contribution of the seller C1 to the transaction combination of the seller C1 and the buyer B2, and the seller C1 can select the transaction object according to the sizes of the influence values V3(B1, C1) and V3(B2, C1).
Further, embodiments of the present application form a recommendation list based on the impact values to assist in matching transactions. In one embodiment, the recommendation list may include a recommendation list that recommends data goods (i.e., seller goods) to the buyer. In yet another embodiment, the recommendation list may include a recommendation list that recommends the buyer to the seller.
In summary, the data commodity recommendation method, the data commodity recommendation apparatus 10, and the electronic device 100 according to the embodiments of the present application can acquire transaction data of a buyer and transaction data of a seller, and acquire an influence value according to the transaction data of the buyer and the transaction data of the seller, so as to acquire a recommendation list according to the influence value to assist in matching transactions, thereby maximizing benefits of both parties of the transaction as much as possible, and improving a transaction promotion rate.
Referring to fig. 4, in some embodiments, 05: obtaining a recommendation list according to the influence value, comprising:
051: acquiring a first recommendation list according to the influence value, wherein the first recommendation list is used for recommending data commodities; and/or
052: and acquiring a second recommendation list according to the influence value, wherein the second recommendation list is used for recommending the transaction object.
Referring to fig. 2, in some embodiments, the processor 30 may also be used to perform the methods in 051 and 052, i.e., the processor 30 may also be used to: acquiring a first recommendation list according to the influence value, wherein the first recommendation list is used for recommending data commodities; and/or acquiring a second recommendation list according to the influence value, wherein the second recommendation list is used for recommending the transaction object.
Referring to fig. 3, in some embodiments, the recommending module 13 can also be used to implement the methods in 051 and 052, that is, the recommending module 13 can also be used to: acquiring a first recommendation list according to the influence value, wherein the first recommendation list is used for recommending data commodities; and/or acquiring a second recommendation list according to the influence value, wherein the second recommendation list is used for recommending the transaction object.
Specifically, the first recommendation list is used for recommending data commodities of different sellers to the same buyer, and the sellers in the first recommendation list are sellers whose influence values are calculated by the buyer. For example, the buyer B1 and the sellers C1, C2 and C3 respectively calculate the influence values, and if there are influence values V3(B1 and C1), V3(B1 and C2) and V3(B1 and C3), the first recommendation list may include the sellers C1, C2 and C3.
Similarly, the second recommendation list is used to recommend a buyer object of the transaction to the seller, and the buyer in the second recommendation list is the buyer whose influence value has been calculated with the seller, which is not described herein again.
Further, referring to fig. 5, in some embodiments, 051: obtaining a first recommendation list according to the influence value, including:
511: acquiring a first label, wherein the first label is a label corresponding to the current buyer;
512: acquiring a plurality of second labels, wherein the second labels correspond to a plurality of sellers;
513: selecting the second label matched with the first label from a plurality of second labels to serve as a second selected label, wherein each second selected label corresponds to a selected seller;
514: selecting a first influence value corresponding to the selected seller from the plurality of influence values; and
515: and generating a first recommendation list according to the first influence value.
Referring to fig. 2, in some embodiments, the processor 30 may be further configured to perform the methods of 511, 512, 513, 514, and 515, that is, the processor 30 may be further configured to: acquiring a first label, wherein the first label is a label corresponding to the current buyer; acquiring a plurality of second labels, wherein the second labels correspond to a plurality of sellers; selecting the second label matched with the first label from a plurality of second labels to serve as a second selected label, wherein each second selected label corresponds to a selected seller; selecting a first influence value corresponding to the selected seller from the plurality of influence values; and generating a first recommendation list according to the first influence value.
Referring to fig. 3, in some embodiments, the recommending module 13 can also be used to implement the methods 511, 512, 513, 514 and 515, that is, the recommending module 13 can also be used to: acquiring a first label, wherein the first label is a label corresponding to the current buyer; acquiring a plurality of second labels, wherein the second labels correspond to a plurality of sellers; selecting the second label matched with the first label from a plurality of second labels to serve as a second selected label, wherein each second selected label corresponds to a selected seller; selecting a first influence value corresponding to the selected seller from the plurality of influence values; and generating a first recommendation list according to the first influence value.
Specifically, the type of the tag may be an application industry of the big data, an application scene of the big data, or the like. For example, the label corresponding to buyer B1 is finance and the label corresponding to buyer B2 is property.
In some embodiments, the same buyer may correspond to a plurality of different first labels, for example, the first label corresponding to buyer B1 includes property and transportation. Similarly, the same seller may correspond to a plurality of different second tags, without limitation.
And if any one of the second labels can be matched with any one of the first labels, the second label is considered to be matched with the first label.
The first impact value may include a plurality, 515: and generating a first recommendation list according to the first influence value, namely generating the first recommendation list according to the set of the first influence values corresponding to all the selected sellers.
The following exemplifies a scenario of generating the first recommendation list.
For example, if the first label corresponding to buyer B1 is property and transportation, the second label corresponding to seller C1 is property, the second label corresponding to seller C2 is transportation and finance, and the second label corresponding to seller C3 is finance, the second label corresponding to seller C1 and the second label corresponding to seller C2 can be matched with the first label corresponding to buyer B1. Thus, seller C1 and seller C2 are the selected sellers.
Among the influence values V3(B1, C1), V3(B1, C2), and V3(B1, C3), V3(B1, C1) and V3(B1, C2) are influence values of the selected seller, and V3(B1, C1) and V3(B1, C2) are taken as first influence values, thereby generating a first recommendation list from the first influence values.
Further, referring to fig. 6, in some embodiments, 515: generating a first recommendation list according to the first influence value, comprising:
5151: acquiring a preset first threshold value;
5152: comparing the first impact value to a first threshold;
5153: listing the selected seller corresponding to the first influence value higher than the first threshold value into a first recommendation list; and
5154: and sorting the selected sellers in the first recommendation list according to the influence values from large to small.
Referring to fig. 2, in some embodiments, the processor 30 may be further configured to perform the methods of 5151, 5152, 5153, and 5154, that is, the processor 30 may further be configured to: acquiring a preset first threshold value; comparing the first impact value to a first threshold; listing the selected seller corresponding to the first influence value higher than the first threshold value into a first recommendation list; and sorting the selected sellers in the first recommendation list according to the influence values from large to small.
Referring to fig. 3, in some embodiments, the recommending module 13 can also be used to implement the methods in 5151, 5152, 5153 and 5154, that is, the recommending module 13 can also be used to: acquiring a preset first threshold value; comparing the first impact value to a first threshold; listing the selected seller corresponding to the first influence value higher than the first threshold value into a first recommendation list; and sorting the selected sellers in the first recommendation list according to the influence values from large to small.
Among these, method 515 may only perform method 5154: sorting the selected sellers in the first recommendation list according to the influence values from big to small; the methods of 5151, 5152, 5153 and 5154 can also be performed sequentially, without limitation.
Method 5152: the first impact value is compared with a first threshold value, in particular each of all first impact values is compared with a first threshold value.
The following exemplifies a scenario of generating the first recommendation list.
For example, the first influence values include influence values V3(B1, C1), V3(B1, C2), and V3(B1, C3), where V3(B1, C1) is 50, V3(B1, C2) is 70, V3(B1, C3) is 90, the first threshold value is 60, the first influence values above the first threshold value are V3(B1, C2) and V3(B1, C3), and V3(B1, C3) > V3(B1, C2), sellers C3 and C2 are included in the first recommendation list, and sorted in order of seller C3 preceding seller C2.
Referring to fig. 7, in some embodiments, 052: obtaining a second recommendation list according to the influence value, wherein the second recommendation list comprises:
521: acquiring a third label, wherein the third label is a label corresponding to the current seller;
522: acquiring a plurality of fourth labels, wherein the fourth labels correspond to a plurality of buyers;
523: selecting the fourth label matched with the third label from the plurality of fourth labels to be used as a fourth selected label, wherein each fourth selected label corresponds to one selected buyer;
524: selecting a second influence value corresponding to the selected buyer from the plurality of influence values; and
525: and generating a second recommendation list according to the second influence value.
Referring to fig. 2, in some embodiments, the processor 30 may be further configured to perform the methods of 521, 522, 523, 524, and 525, that is, the processor 30 may further be configured to: acquiring a third label, wherein the third label is a label corresponding to the current seller; acquiring a plurality of fourth labels, wherein the fourth labels correspond to a plurality of buyers; selecting the fourth label matched with the third label from the plurality of fourth labels to be used as a fourth selected label, wherein each fourth selected label corresponds to one selected buyer; selecting a second influence value corresponding to the selected buyer from the plurality of influence values; and generating a second recommendation list according to the second influence value.
Referring to fig. 3, in some embodiments, the recommending module 13 can also be used to implement the methods in 521, 522, 523, 524, and 525, that is, the recommending module 13 can also be used to: acquiring a third label, wherein the third label is a label corresponding to the current seller; acquiring a plurality of fourth labels, wherein the fourth labels correspond to a plurality of buyers; selecting the fourth label matched with the third label from the plurality of fourth labels to be used as a fourth selected label, wherein each fourth selected label corresponds to one selected buyer; selecting a second influence value corresponding to the selected buyer from the plurality of influence values; and generating a second recommendation list according to the second influence value.
Referring to fig. 5, the method for obtaining the third tag and the method for obtaining the fourth tag are similar to the method for obtaining the first tag and the method for obtaining the second tag, and are not repeated here.
The following exemplifies a scenario of generating the second recommendation list.
For example, if the third label corresponding to the seller C1 is property and transportation, the fourth label corresponding to the buyer B1 is property, the fourth label corresponding to the buyer B2 is transportation and finance, and the fourth label corresponding to the buyer B3 is finance, the fourth label corresponding to the buyer B1 and the fourth label corresponding to the buyer B2 can correspond to the third label corresponding to the seller C1. Thus, buyer B1 and buyer B1 are selected buyers.
Among the influence values V3(B1, C1), V3(B2, C1), and V3(B3, C1), V3(B1, C1) and V3(B2, C1) are influence values corresponding to the selected buyer, and V3(B1, C1) and V3(B2, C1) are taken as second influence values, thereby generating a second recommendation list according to the second influence values.
Further, referring to fig. 8, in some embodiments, 525: generating a second recommendation list according to the second influence value, comprising:
5251: acquiring a preset second threshold value;
5252: comparing the second impact value to a second threshold;
5253: listing the selected buyers corresponding to the second influence values higher than the second threshold value into a second recommendation list; and
5254: and sorting the selected buyers in the second recommendation list from large to small according to the influence values.
Referring to fig. 2, in some embodiments, the processor 30 may be further configured to perform the methods 5251, 5252, 5253 and 5254, that is, the processor 30 may be further configured to: acquiring a preset second threshold value; comparing the second impact value to a second threshold; listing the selected buyers corresponding to the second influence values higher than the second threshold value into a second recommendation list; and sorting the selected buyers in the second recommendation list from large to small according to the influence values.
Referring to fig. 3, in some embodiments, the recommending module 13 can also be used to implement the methods of 5251, 5252, 5253 and 5254, that is, the recommending module 13 can also be used to: acquiring a preset second threshold value; comparing the second impact value to a second threshold; listing the selected buyers corresponding to the second influence values higher than the second threshold value into a second recommendation list; and sorting the selected buyers in the second recommendation list from large to small according to the influence values.
Among other things, only method 5254 may be performed in method 525: sorting the selected buyers in the second recommendation list from large to small according to the influence values; the methods of 5251, 5252, 5253 and 5254 can also be performed sequentially, without limitation.
The following exemplifies a scenario of generating the second recommendation list.
For example, the second influence values include influence values V3(B1, C1), V3(B2, C1), and V3(B3, C1), where V3(B1, C1) is 50, V3(B2, C1) is 70, V3(B3, C1) is 90, and the second threshold value is 60, the second influence values higher than the second threshold value are V3(B2, C1) and V3(B3, C1), and V3(B3, C1) > V3(B2, C1), and the second recommendation list includes buyer B3 and buyer B2, and is sorted in order after buyer B3 and B2.
In summary, the data commodity recommendation method, the data commodity recommendation apparatus 10 and the electronic device 100 according to the embodiments of the present application can provide the first recommendation list and the second recommendation list for the buyer and the seller involved in the transaction, so as to recommend the buyer and the seller with the tags matching based on the corresponding industry, scene and the like of the buyer and the seller, and the recommended buyer and seller are sorted from large to small according to the influence value to be used as the recommendation reference for the transaction, thereby facilitating the maximization of the profit of the buyer and seller and facilitating the transaction.
Referring to fig. 9, in some embodiments, the data commodity recommendation method further includes:
06: and acquiring reference pricing according to the influence value.
Referring to fig. 2, in some embodiments, the processor 30 may be further configured to perform the method of 06, that is, the processor 30 may further be configured to: and acquiring reference pricing according to the influence value.
Referring to fig. 3, in some embodiments, the recommending module 13 may also be configured to implement the method in 06, that is, the recommending module 13 may also be configured to: and acquiring reference pricing according to the influence value.
The larger the influence value of the seller on the buyer is, the larger the value of the seller (data commodity of the seller) on the buyer is, and the price can be appropriately increased for the seller.
In one embodiment, the impact values may be weighted and normalized to obtain a price factor, with the seller initially setting a base selling price. After the seller obtains the price factor according to the influence value of the seller on the buyer, the data transaction platform can provide the product of the basic selling price and the price factor as reference pricing for the seller when the seller transacts with the buyer. For example, when the basic selling price of the seller C1 is 100 ten thousand, the influence value V3(B1, C1) of the seller C1 on the buyer B1 is 50, and the price factor α obtained after weighting and normalizing the influence value V3(B1, C1) is 5%, when the seller C1 trades with the buyer B1, the data transaction platform may provide 105 ten thousand as reference pricing to the seller C1 to win the profit for the seller C1.
Referring to fig. 10, one or more non-transitory computer-readable storage media 300 containing a computer program 301 according to an embodiment of the present disclosure, when the computer program 301 is executed by one or more processors 30, may enable the processor 30 to perform the data commodity recommendation method according to any one of the above embodiments, for example, one or more of steps 01, 02, 03, 04, 05, 06, 051, 052, 511, 512, 513, 514, 515, 5151, 5152, 5153, 5154, 521, 522, 523, 524, 525, 5251, 5252, 5253, and 5254 are implemented.
For example, the computer program 301, when executed by the one or more processors 30, causes the processors 30 to perform the steps of:
01: acquiring transaction data of a buyer and transaction data of a seller;
02: inputting transaction data of a buyer into an AI model to obtain a first Shapril value;
03: inputting transaction data of the buyer and transaction data of the seller into the AI model to obtain a second Shapril value;
04: acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and
05: and acquiring a recommendation list according to the influence value.
As another example, the computer program 301, when executed by the one or more processors 30, causes the processors 30 to perform the steps of:
01: acquiring transaction data of a buyer and transaction data of a seller;
02: inputting transaction data of a buyer into an AI model to obtain a first Shapril value;
03: inputting transaction data of the buyer and transaction data of the seller into the AI model to obtain a second Shapril value;
04: acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and
051: acquiring a first recommendation list according to the influence value, wherein the first recommendation list is used for recommending data commodities;
052: acquiring a second recommendation list according to the influence value, wherein the second recommendation list is used for recommending the transaction object;
06: and acquiring reference pricing according to the influence value.
In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example" or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and brought together by those skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (10)

1. A data commodity recommendation method, comprising:
acquiring transaction data of a buyer and transaction data of a seller;
inputting transaction data of the buyer into an AI model to obtain a first Shapril value;
inputting the transaction data of the buyer and the transaction data of the seller into an AI model to obtain a second Shapril value;
obtaining the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and
and acquiring a recommendation list according to the influence value.
2. The data commodity recommendation method according to claim 1, wherein said obtaining a recommendation list according to the influence value comprises:
acquiring a first recommendation list according to the influence value, wherein the first recommendation list is used for recommending data commodities; and/or
And acquiring a second recommendation list according to the influence value, wherein the second recommendation list is used for recommending the transaction object.
3. The data commodity recommendation method according to claim 2, wherein said obtaining a first recommendation list according to the influence value comprises:
acquiring a first label, wherein the first label is a label corresponding to a current buyer;
obtaining a plurality of second labels, wherein the second labels correspond to a plurality of sellers;
selecting a matching one of the second labels from the plurality of second labels as a second selected label, each of the second selected labels corresponding to a selected seller;
selecting a first influence value corresponding to the selected seller from a plurality of influence values; and
and generating the first recommendation list according to the first influence value.
4. The data item recommendation method of claim 3, wherein said generating the first recommendation list according to the first impact value comprises:
acquiring a preset first threshold value;
comparing the first impact value to the first threshold;
listing the selected seller corresponding to the first impact value above the first threshold in the first recommendation list; and
and sorting the selected sellers in the first recommendation list from large to small according to influence values.
5. The data commodity recommendation method according to claim 2, wherein said obtaining a second recommendation list according to the influence value comprises:
acquiring a third label, wherein the third label is a label corresponding to the current seller;
acquiring a plurality of fourth labels, wherein the fourth labels correspond to a plurality of buyers;
selecting the fourth label matched with the third label from the plurality of fourth labels to be used as a fourth selected label, wherein each fourth selected label corresponds to a selected buyer;
selecting a second influence value corresponding to the selected buyer from the plurality of influence values; and
and generating the second recommendation list according to the second influence value.
6. The data item recommendation method of claim 5, wherein said generating the second recommendation list according to the second impact value comprises:
acquiring a preset second threshold value;
comparing the second impact value to the second threshold;
listing the selected buyer corresponding to the second impact value above the second threshold value in the second recommendation list; and
and sorting the selected buyers in the second recommendation list from large to small according to influence values.
7. The data commodity recommendation method according to claim 1, further comprising:
and acquiring reference pricing according to the influence value.
8. A data merchandise recommendation device, comprising:
the acquisition module is used for acquiring transaction data of a buyer and transaction data of a seller;
an AI processing module for inputting the buyer's transaction data into an AI model to obtain a first Shapril value;
the AI processing module is further configured to input transaction data of the buyer and transaction data of the seller into an AI model to obtain a second Shapril value;
the AI processing module is further used for acquiring the influence value of the transaction data of the seller on the transaction data of the buyer according to the first salpril value and the second salpril value; and
and the recommending module is used for acquiring a recommending list according to the influence value.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors, memory; and
one or more programs, wherein the one or more programs are stored in the memory and executed by the one or more processors, the programs comprising instructions for performing the data good recommendation method of any of claims 1-7.
10. A non-transitory computer readable storage medium containing a computer program which, when executed by one or more processors, causes the processors to implement the data item recommendation method of any one of claims 1-7.
CN202111095034.XA 2021-09-17 2021-09-17 Data commodity recommendation method and device, electronic equipment and computer readable storage medium Active CN113807921B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111095034.XA CN113807921B (en) 2021-09-17 2021-09-17 Data commodity recommendation method and device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111095034.XA CN113807921B (en) 2021-09-17 2021-09-17 Data commodity recommendation method and device, electronic equipment and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN113807921A true CN113807921A (en) 2021-12-17
CN113807921B CN113807921B (en) 2023-11-24

Family

ID=78895854

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111095034.XA Active CN113807921B (en) 2021-09-17 2021-09-17 Data commodity recommendation method and device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN113807921B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913290A (en) * 2016-07-01 2016-08-31 中国传媒大学 Commodity matching recommending method and recommending system
CN107633416A (en) * 2016-07-18 2018-01-26 阿里巴巴集团控股有限公司 A kind of recommendation methods, devices and systems of business object
CN111199428A (en) * 2020-01-03 2020-05-26 江苏苏宁物流有限公司 Commodity recommendation method and device, storage medium and computer equipment
CN111681051A (en) * 2020-06-08 2020-09-18 上海汽车集团股份有限公司 Purchasing intention degree prediction method, device, storage medium and terminal
CN112380453A (en) * 2021-01-15 2021-02-19 腾讯科技（深圳）有限公司 Article recommendation method and device, storage medium and equipment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913290A (en) * 2016-07-01 2016-08-31 中国传媒大学 Commodity matching recommending method and recommending system
CN107633416A (en) * 2016-07-18 2018-01-26 阿里巴巴集团控股有限公司 A kind of recommendation methods, devices and systems of business object
CN111199428A (en) * 2020-01-03 2020-05-26 江苏苏宁物流有限公司 Commodity recommendation method and device, storage medium and computer equipment
CN111681051A (en) * 2020-06-08 2020-09-18 上海汽车集团股份有限公司 Purchasing intention degree prediction method, device, storage medium and terminal
CN112380453A (en) * 2021-01-15 2021-02-19 腾讯科技（深圳）有限公司 Article recommendation method and device, storage medium and equipment

Also Published As

Publication number Publication date
CN113807921B (en) 2023-11-24

Similar Documents

Publication Publication Date Title
Hsu et al. What drives purchase intention for paid mobile apps?–An expectation confirmation model with perceived value
Sinha et al. The impact of discrete bidding and bidder aggressiveness on sellers' strategies in open English auctions: Reserves and covert shilling
CN110111179B (en) Drug combination recommendation method and device and computer readable storage medium
US20200250751A1 (en) Method, system, and computer trading platform for valuing and exchanging flatted shares of a private company
CN109711866B (en) Bank advertisement putting method, device and system
Prasetyo et al. An influence analysis of product quality, brand image, and price on the decision to buy Toshiba laptop (A study on students of economics Faculty of Semarang University)
CN114549142B (en) Online bidding auction information processing method and system
US20080154662A1 (en) System and method for generating a maximum utility slate of advertisements for online advertisement auctions
CN114331543A (en) Advertisement propagation method for large-scale crowd orientation and dynamic scene matching
Ray et al. Supplier behavior modeling and winner determination using parallel MDP
US11551194B2 (en) System to facilitate exchange of data segments between data aggregators and data consumers
Chen et al. Managing the personalized order-holding problem in online retailing
CN112200215B (en) Label feature extraction method and device, storage medium and electronic equipment
KR20200041714A (en) System and method for overseas cooperative purchase
Nangoy et al. Analysis of chatbot-based image classification on Social Commerce line@ platform
CN112669053A (en) Fraud group identification method, device, equipment and medium based on sales data
CN113807921B (en) Data commodity recommendation method and device, electronic equipment and computer readable storage medium
CN113744009A (en) Target object output method and device, computer readable medium and electronic equipment
CN110766478A (en) Method and device for improving user connectivity
Kang Optimal stopping problem with double reservation value property
Gershkov et al. Revenue maximizing mechanisms with strategic customers and unknown demand: Name-your-own-price
Bohte et al. Competitive market-based allocation of consumer attention space
CN113379493A (en) Article recall method and device, storage medium and electronic equipment
US20090150278A1 (en) System and method for optimizing the reserve price and allocation of web page placements in an online keyword auction using generalized trade reduction
KR102489348B1 (en) System for predicting idle unused asset transaction price among parties and mehtod performing thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant