CN112700268A - Downstream enterprise recommendation method and system based on commodity code similarity comparison - Google Patents

Downstream enterprise recommendation method and system based on commodity code similarity comparison Download PDF

Info

Publication number
CN112700268A
CN112700268A CN202011578080.0A CN202011578080A CN112700268A CN 112700268 A CN112700268 A CN 112700268A CN 202011578080 A CN202011578080 A CN 202011578080A CN 112700268 A CN112700268 A CN 112700268A
Authority
CN
China
Prior art keywords
enterprise
industry
downstream
commodity
commodity code
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011578080.0A
Other languages
Chinese (zh)
Inventor
刘芬
王志刚
刘雅婷
李瑞祥
林文辉
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.)
Aisino Corp
Original Assignee
Aisino Corp
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 Aisino Corp filed Critical Aisino Corp
Priority to CN202011578080.0A priority Critical patent/CN112700268A/en
Publication of CN112700268A publication Critical patent/CN112700268A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • 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
    • G06Q30/04—Billing or invoicing
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/12—Accounting
    • G06Q40/123—Tax preparation or submission

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Cash Registers Or Receiving Machines (AREA)

Abstract

The invention discloses a downstream enterprise recommendation method based on commodity code similarity comparison, which comprises the following steps: constructing a downstream industrial chain of the industry according to the value-added tax invoice data, the enterprise information and a preset rule, and determining an important downstream industry of the industry; determining a main operation commodity code set of a target enterprise and a main purchase commodity code set of a candidate enterprise corresponding to the target enterprise; calculating to obtain a commodity code similarity set; recommending downstream enterprises for the target enterprises according to the commodity code similarity set; according to the invention, by constructing a downstream industrial chain of an industry, the analysis dimension is expanded from an enterprise level to an industry level, and more new customers can be mined; the method has the advantages that high-quality downstream enterprises are recommended for the target enterprises based on the commodity similarity, the calculation is simple and quick, the target enterprises can be helped to expand customer groups, the market is expanded, marketing strategies are implemented more efficiently and accurately, and the income is increased.

Description

Downstream enterprise recommendation method and system based on commodity code similarity comparison
Technical Field
The invention relates to the field of downstream enterprise recommendation, in particular to a downstream enterprise recommendation method and system based on commodity code similarity comparison.
Background
With the vigorous development of economy, the competition of various industries is more and more intense, and especially, the resources of customers are more and more controversial; on the basis of maintaining the existing customers, market expansion is an important means for enterprises to obtain larger market share and continue to make profit.
However, for most enterprises, the needs of the enterprises in the downstream industries of the industry cannot be known, and potential customers cannot be well mined; currently, there is no effective method for recommending high-quality downstream enterprises for target enterprises in the prior art.
According to the invention, based on the value-added tax invoice data and the goods detail data, a downstream industrial chain of the industry is constructed, the analysis dimension is expanded from an enterprise level to an industry level, a client group of a target enterprise can be expanded from an enterprise range with direct transaction to downstream enterprises of other enterprises in the same industry, more new clients are mined, and meanwhile, the blindness of searching clients from the whole enterprise range is avoided; from the commodity coding angle, the similarity between the main business commodity of the target enterprise and the main business commodity of the candidate enterprise is calculated, high-quality downstream enterprises are recommended for the target enterprise based on the similarity, the calculation is simple and quick, the target enterprise can be helped to expand a client group, the market is expanded, the marketing strategy is implemented more efficiently and accurately, and the income increase is realized.
Disclosure of Invention
In order to solve the problem that an effective method is lacked to recommend high-quality downstream enterprises to target enterprises in the background art, the invention provides a downstream enterprise recommendation method based on commodity code similarity comparison, which comprises the following steps:
constructing a downstream industrial chain of the industry according to the value-added tax invoice data, the enterprise information and a preset rule, and determining an important downstream industry of the industry;
determining a main business commodity code set of a target enterprise;
determining a candidate enterprise corresponding to the target enterprise and a main purchased commodity code set of the candidate enterprise according to a downstream industrial chain of the industry;
calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set;
and recommending downstream enterprises for the target enterprises according to the commodity code similarity set.
Further, according to the value-added tax invoice data, the enterprise information and the preset rule, a downstream industry chain of the industry is constructed, and the determination of important downstream industries of the industry comprises the following steps:
enumerating all expected downstream industries of the upstream industry according to the value-added tax invoice data and the enterprise information;
calculating the transaction total amount T of all the expected downstream industries and the upstream industries and the transaction amount A of each expected downstream industry and the upstream industriesn(N ═ 1,2,3...., N) and arranged in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry;
n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1.
Further, the determining the main marketing commodity code set of the target enterprise comprises:
calculating the total sales Q of all commodities of the target enterprise;
calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1.
Further, the determining, according to the downstream industry chain of the industry, the candidate enterprise corresponding to the target enterprise and the primary purchased product code set of the candidate enterprise includes:
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps, and determining the main purchased commodity code sets of all the candidate enterprises;
y is a positive integer, CyR is more than 0, and R is more than 0 and less than 1.
Further, the calculating a product code similarity set according to the primary operation product code set and the primary purchase product code set includes:
combining the main business commodities and the main purchase commodities of all enterprises pairwise, and calculating the coding similarity of each pair of the main business commodities and the main purchase commodities to obtain a commodity coding similarity set;
the code similarity of each pair of the main commercial goods and the main purchased goods is the ratio of the continuous same digit of the two goods codes from the 1 st digit to the total digit of the goods codes.
Further, recommending downstream enterprises for the target enterprise according to the commodity code similarity set includes:
for each candidate enterprise, combining the main purchased commodities and the main operated commodities of the target enterprise pairwise, determining the similarity of each pair of commodity codes according to the commodity code similarity set, and taking the highest value of the commodity code similarity as the recommendation similarity of the candidate enterprise and the target enterprise;
and recommending the candidate enterprises with the recommendation similarity exceeding the threshold to the target enterprise as high-quality downstream enterprises according to a preset threshold.
A downstream enterprise recommendation system based on item code similarity comparison, the system comprising:
one end of the data acquisition unit is connected with the commodity code similarity comparison unit and the downstream enterprise recommendation unit; the data acquisition unit is used for acquiring and sending value-added tax invoice data and enterprise information to the commodity code similarity comparison unit and the downstream enterprise recommendation unit;
the commodity code similarity comparison unit is connected with the downstream enterprise recommendation unit at one end; the commodity code similarity comparison unit is used for constructing a downstream industrial chain of an industry according to the value-added tax invoice data, enterprise information and a preset rule, determining an important downstream industry of the industry, determining a main operation commodity code set of a target enterprise, determining a candidate enterprise corresponding to the target enterprise and a main purchase commodity code set of the candidate enterprise according to the downstream industrial chain of the industry, and calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set; the commodity code similarity comparison unit is further used for sending the main operation commodity code set of the target enterprise, the main purchase commodity code set of the candidate enterprise and the commodity code similarity set to the downstream enterprise recommendation unit;
and the downstream enterprise recommending unit is used for recommending the downstream enterprises for the target enterprises according to the value-added tax invoice data, the enterprise information, the main operation commodity code set of the target enterprises, the main purchase commodity code set of the candidate enterprises and the commodity code similarity set.
Further, the product code similarity comparison unit includes:
a downstream industrial chain building module, wherein one end of the downstream industrial chain building module is connected with the main purchased commodity code determining integrated module; the downstream industry chain building module is used for building a downstream industry chain of the industry according to the value-added tax invoice data, the enterprise information and the preset rule and determining an important downstream industry of the industry;
determining a main operation commodity code integration module, wherein one end of the main operation commodity code integration module is connected with a commodity code similarity integration module; the main business commodity code determining and integrating module is used for determining a main business commodity code set of a target enterprise and sending the main business commodity code set of the target enterprise to the commodity code similarity determining and integrating module;
determining a main purchased commodity code integration module, wherein one end of the main purchased commodity code integration module is connected with the commodity code similarity integration module; the main purchased product code determining and integrating module is used for determining a candidate enterprise corresponding to the target enterprise and a main purchased product code set of the candidate enterprise according to a downstream industrial chain of the industry and sending the main purchased product code set of the candidate enterprise to the commodity code similarity determining and integrating module;
and the commodity code similarity set determining module is used for calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set.
Further, according to the value-added tax invoice data, the enterprise information and the preset rule, a downstream industry chain of the industry is constructed, and the determination of important downstream industries of the industry comprises the following steps:
enumerating all expected downstream industries of the upstream industry according to the value-added tax invoice data and the enterprise information;
calculating the transaction total T of all the expected downstream industries and the upstream industries and each expected downstream industry and the upstream industryTransaction amount A of upstream industryn(N ═ 1,2,3...., N) and arranged in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry;
n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1.
Further, the determining the main marketing commodity code set of the target enterprise comprises:
calculating the total sales Q of all commodities of the target enterprise;
calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1.
Further, the determining, according to the downstream industry chain of the industry, the candidate enterprise corresponding to the target enterprise and the primary purchased product code set of the candidate enterprise includes:
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps, and determining the main purchased commodity code sets of all the candidate enterprises;
y is a positive integer, CyR is more than 0, and R is more than 0 and less than 1.
Further, the calculating the set of similarity degrees of the product codes includes:
combining the main business commodities and the main purchase commodities of all enterprises pairwise, and calculating the coding similarity of each pair of the main business commodities and the main purchase commodities to obtain a commodity coding similarity set;
the code similarity of each pair of the main commercial goods and the main purchased goods is the ratio of the continuous same digit of the two goods codes from the 1 st digit to the total digit of the goods codes.
Further, the recommending downstream enterprises for the target enterprise includes:
for each candidate enterprise, combining the main purchased commodities and the main operated commodities of the target enterprise pairwise, determining the similarity of each pair of commodity codes according to the commodity code similarity set, and taking the highest value of the commodity code similarity as the recommendation similarity of the candidate enterprise and the target enterprise;
and recommending the candidate enterprises with the recommendation similarity exceeding the threshold to the target enterprise as high-quality downstream enterprises according to a preset threshold.
The invention has the beneficial effects that: the technical scheme of the invention provides a downstream enterprise recommendation method based on commodity code similarity comparison, which comprises the following steps: constructing a downstream industrial chain of the industry according to the value-added tax invoice data, the enterprise information and a preset rule, and determining an important downstream industry of the industry; determining a main operation commodity code set of a target enterprise and a main purchase commodity code set of a candidate enterprise corresponding to the target enterprise; calculating to obtain a commodity code similarity set; recommending downstream enterprises for the target enterprises according to the commodity code similarity set; according to the invention, based on the value-added tax invoice data and the goods detail data, a downstream industrial chain of the industry is constructed, the analysis dimension is expanded from an enterprise level to an industry level, a client group of a target enterprise can be expanded from an enterprise range with direct transaction to downstream enterprises of other enterprises in the same industry, more new clients are mined, and meanwhile, the blindness of searching clients from the whole enterprise range is avoided; from the commodity coding angle, the similarity between the main business commodity of the target enterprise and the main business commodity of the candidate enterprise is calculated, high-quality downstream enterprises are recommended for the target enterprise based on the similarity, the calculation is simple and quick, the target enterprise can be helped to expand a client group, the market is expanded, the marketing strategy is implemented more efficiently and accurately, and the income increase is realized.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a flowchart of a downstream enterprise recommendation method based on commodity code similarity comparison according to an embodiment of the present invention;
fig. 2 is a structural diagram of a downstream enterprise recommendation system based on commodity code similarity comparison according to an embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Fig. 1 is a flowchart of a downstream enterprise recommendation method based on commodity code similarity comparison according to an embodiment of the present invention. As shown in fig. 1, the method includes:
step 110, constructing a downstream industrial chain of the industry; constructing a downstream industrial chain of the industry according to the value-added tax invoice data, the enterprise information and a preset rule, and determining an important downstream industry of the industry;
specifically, in the present example, based on the value-added tax invoice data and the enterprise information, the industry information of the seller enterprise and the buyer enterprise is respectively obtained and marked as the upstream industry and the downstream industry; for example, if business a is the selling party, business B is the purchasing party, and business B is the 6210, then the upstream business is 5224 and the downstream business is 6210;
each pair of seller identification numbers and buyer identification numbers in the invoice data determine the transaction relationship between the upstream industry and the downstream industry; the method comprises the following steps that a plurality of expected downstream industries exist in one upstream industry, and in order to recommend high-quality downstream enterprises, a plurality of important downstream industries are selected according to preset rules;
calculating the transaction total amount T of all the expected downstream industries and the upstream industries and the transaction amount A of each expected downstream industry and the upstream industriesn(N ═ 1,2,3...., N) and arranged in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry; n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1; in this example, t is 0.8, for example, downstream industries of industry A have B, C, D, and the proportion of transaction amount with industries B, C, D is 50%, 30% and 20% of total transaction amount of industry A, respectively, since 50% + 30%>80%, so the important downstream industries of industry a are B and C.
Step 120, determining a main operation commodity code set of the target enterprise; the actual operation range of each enterprise is very wide, so that the variety of the sold commodities is various, and the invention only analyzes the main and operation commodities of the enterprise; the method comprises the following specific steps:
calculating the total sales Q of all the commodities of the target enterprise, wherein the commodities are defined by commodity codes
Calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1; specifically, in this example, q is 0.8, that is, the commodities which are arranged in a descending order and whose accumulated result is greater than or equal to 80% of the total sales amount are the main commodities of the target enterprise, and the commodity codes of the main commodities of the target enterprise together form the main commodity code set of the target enterprise.
Step 130, determining candidate enterprises and a main purchased commodity code set thereof; determining a candidate enterprise corresponding to the target enterprise and a main purchased commodity code set of the candidate enterprise according to a downstream industrial chain of the industry;
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps until the main purchased commodities of all the candidate enterprises are determined;
further, determining a main purchased commodity code set of all candidate enterprises;
y is a positive integer, CyR is more than 0, and R is more than 0 and less than 1; in this example, r is 0.8.
Step 140, determining a commodity code similarity set; combining the main business commodities and the main purchase commodities of all enterprises pairwise, and calculating the coding similarity of each pair of the main business commodities and the main purchase commodities to obtain a commodity coding similarity set;
specifically, in order to avoid repeated calculation and improve the enterprise recommendation speed, the main operation commodities of all enterprises and the main purchase commodities of all enterprises are considered to be combined pairwise, the similarity of each pair of main operation commodity and main purchase commodity codes is calculated in an off-line mode, and only the inquiry is needed after the storage without calculation;
the code similarity of each pair of the main commercial goods and the main purchased goods is the ratio of the continuous same digit of the two goods codes from the 1 st digit to the total digit of the goods codes; for example, the product code 1 is "1010112070000000000", the product code 2 is "1010113010000000000", and the product code is composed of 19-digit arabic numerals, so that the similarity between the two product codes is 6/19.
150, recommending high-quality downstream enterprises; for each candidate enterprise, combining the main purchased commodities and the main operated commodities of the target enterprise pairwise, determining the similarity of each pair of commodity codes according to the commodity code similarity set, and taking the highest value of the commodity code similarity as the recommendation similarity of the candidate enterprise and the target enterprise;
recommending the candidate enterprises with the recommendation similarity exceeding a threshold value to the target enterprise as high-quality downstream enterprises according to a preset threshold value; if too many enterprises meet the conditions, setting the recommended quantity W, and recommending the W enterprises with the maximum similarity value.
Fig. 2 is a structural diagram of a downstream enterprise recommendation system based on commodity code similarity comparison according to an embodiment of the present invention. As shown in fig. 2, the system includes:
a data obtaining unit 210, wherein one end of the data obtaining unit 210 is connected with a commodity code similarity comparing unit 220 and a downstream enterprise recommending unit 230; the data acquiring unit 210 is configured to acquire and send value-added tax invoice data and enterprise information to the commodity code similarity comparing unit 220 and the downstream enterprise recommending unit 230.
A product code similarity comparison unit 220, wherein one end of the product code similarity comparison unit 220 is connected with the downstream enterprise recommendation unit 230; the commodity code similarity comparison unit 220 is configured to construct a downstream industry chain of an industry according to the value-added tax invoice data, the enterprise information and a preset rule, determine an important downstream industry of the industry, determine a main operation commodity code set of a target enterprise, determine a candidate enterprise corresponding to the target enterprise and a main purchase commodity code set of the candidate enterprise according to the downstream industry chain of the industry, and calculate a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set; the product code similarity comparing unit 220 is further configured to send the main operation product code set of the target enterprise, the main purchased product code set of the candidate enterprise, and the product code similarity set to the downstream enterprise recommending unit 230;
a downstream industry chain building module 2201, wherein one end of the downstream industry chain building module 2201 is connected with the main purchased product code determining integration module 2203; the downstream industry chain building module 2201 is used for building a downstream industry chain of the industry according to the value-added tax invoice data, the enterprise information and the preset rule, and determining an important downstream industry of the industry;
a main operation commodity code integration module 2202 is determined, and one end of the main operation commodity code integration module 2202 is connected with a commodity code similarity integration module 2204; the determine primary operation commodity code set module 2202 is configured to determine a primary operation commodity code set of a target enterprise and send the primary operation commodity code set of the target enterprise to the determine commodity code similarity set module 2204;
determining a main purchased commodity code integration module 2203, wherein one end of the main purchased commodity code integration module 2203 is connected with the commodity code similarity integration module 2204; the main purchased product code aggregation determining module 2203 is configured to determine, according to a downstream industry chain of the industry, a candidate enterprise corresponding to the target enterprise and a main purchased product code aggregation of the candidate enterprise, and send the main purchased product code aggregation of the candidate enterprise to the commodity code similarity determining module 2204;
a product code similarity aggregation determining module 2204, wherein the product code similarity aggregation determining module 2204 is configured to calculate a product code similarity aggregation according to the primary operation product code aggregation and the primary purchase product code aggregation.
And the downstream enterprise recommending unit 230 is configured to recommend a downstream enterprise to the target enterprise according to the value-added tax invoice data, the enterprise information, the main operation commodity code set of the target enterprise, the main purchase commodity code set of the candidate enterprise, and the commodity code similarity set.
Further, according to the value-added tax invoice data, the enterprise information and the preset rule, a downstream industry chain of the industry is constructed, and the determination of important downstream industries of the industry comprises the following steps:
enumerating all expected downstream industries of the upstream industry according to the value-added tax invoice data and the enterprise information;
calculating the transaction total amount T of all the expected downstream industries and the upstream industries and the transaction amount A of each expected downstream industry and the upstream industriesn(N ═ 1,2,3...., N) and arranged in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry;
n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1; in this example, t is 0.8, for example, downstream industries of industry A have B, C, D, and the proportion of transaction amount with industries B, C, D is 50%, 30% and 20% of total transaction amount of industry A, respectively, since 50% + 30%>80%, so the important downstream industries of industry a are B and C.
Further, the determining the main marketing commodity code set of the target enterprise comprises:
calculating the total sales Q of all commodities of the target enterprise;
calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1; specifically, in this example, q is 0.8, that is, the commodities which are arranged in a descending order and whose accumulated result is greater than or equal to 80% of the total sales amount are the main commodities of the target enterprise, and the commodity codes of the main commodities of the target enterprise together form the main commodity code set of the target enterprise.
Further, the determining, according to the downstream industry chain of the industry, the candidate enterprise corresponding to the target enterprise and the primary purchased product code set of the candidate enterprise includes:
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps, and determining the main purchased commodity code sets of all the candidate enterprises;
y is a positive integer, CyR is more than 0, and R is more than 0 and less than 1; and r is 0.8.
Further, the calculating the set of similarity degrees of the product codes includes:
combining the main business commodities and the main purchase commodities of all enterprises pairwise, and calculating the coding similarity of each pair of the main business commodities and the main purchase commodities to obtain a commodity coding similarity set;
specifically, in order to avoid repeated calculation and improve the enterprise recommendation speed, the main operation commodities of all enterprises and the main purchase commodities of all enterprises are considered to be combined pairwise, the similarity of each pair of main operation commodity and main purchase commodity codes is calculated in an off-line mode, and only the inquiry is needed after the storage without calculation;
the code similarity of each pair of the main commercial goods and the main purchased goods is the ratio of the continuous same digit of the two goods codes from the 1 st digit to the total digit of the goods codes; for example, the product code 1 is "1010112070000000000", the product code 2 is "1010113010000000000", and the product code is composed of 19-digit arabic numerals, so that the similarity between the two product codes is 6/19.
Further, the recommending downstream enterprises for the target enterprise includes:
for each candidate enterprise, combining the main purchased commodities and the main operated commodities of the target enterprise pairwise, determining the similarity of each pair of commodity codes according to the commodity code similarity set, and taking the highest value of the commodity code similarity as the recommendation similarity of the candidate enterprise and the target enterprise;
recommending the candidate enterprises with the recommendation similarity exceeding a threshold value to the target enterprise as high-quality downstream enterprises according to a preset threshold value; if too many enterprises meet the conditions, setting the recommended quantity W, and recommending the W enterprises with the maximum similarity value.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Reference to step numbers in this specification is only for distinguishing between steps and is not intended to limit the temporal or logical relationship between steps, which includes all possible scenarios unless the context clearly dictates otherwise.
Moreover, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the disclosure and form different embodiments. For example, any of the embodiments claimed in the claims can be used in any combination.
Various component embodiments of the disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. The present disclosure may also be embodied as device or system programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present disclosure may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several systems, several of these systems may be embodied by one and the same item of hardware.
The foregoing is directed to embodiments of the present disclosure, and it is noted that numerous improvements, modifications, and variations may be made by those skilled in the art without departing from the spirit of the disclosure, and that such improvements, modifications, and variations are considered to be within the scope of the present disclosure.

Claims (10)

1. A downstream enterprise recommendation method based on commodity code similarity comparison is characterized by comprising the following steps:
constructing a downstream industrial chain of the industry according to the value-added tax invoice data, the enterprise information and a preset rule, and determining an important downstream industry of the industry;
determining a main business commodity code set of a target enterprise;
determining a candidate enterprise corresponding to the target enterprise and a main purchased commodity code set of the candidate enterprise according to a downstream industrial chain of the industry;
calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set;
and recommending downstream enterprises for the target enterprises according to the commodity code similarity set.
2. The method of claim 1, wherein the downstream industry chain of industries is constructed according to the value-added tax invoice data, the enterprise information and the preset rules, and the determining important downstream industries of the industries comprises:
enumerating all expected downstream industries of the upstream industry according to the value-added tax invoice data and the enterprise information;
calculating the transaction total amount T of all the expected downstream industries and the upstream industries and the transaction amount A of each expected downstream industry and the upstream industriesn(N-1, 2,3 … …, N) and in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry;
n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1.
3. The method of claim 1, wherein determining the set of hosted commodity codes for the target enterprise comprises:
calculating the total sales Q of all commodities of the target enterprise;
calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1.
4. The method of claim 1, wherein the determining the candidate business corresponding to the target business and the set of product codes for the candidate business according to the downstream industry chain of the industry comprises:
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps, and determining the main purchased commodity code sets of all the candidate enterprises;
y is a positive integer, CyR is more than 0, R is more than 0 and less than1。
5. The method according to claim 1, wherein the calculating a product code similarity set according to the primary operation product code set and the primary purchase product code set comprises:
combining the main business commodities and the main purchase commodities of all enterprises pairwise, and calculating the coding similarity of each pair of the main business commodities and the main purchase commodities to obtain a commodity coding similarity set;
the code similarity of each pair of the main commercial goods and the main purchased goods is the ratio of the continuous same digit of the two goods codes from the 1 st digit to the total digit of the goods codes.
6. A downstream enterprise recommendation system based on commodity code similarity comparison is characterized in that the system comprises:
one end of the data acquisition unit is connected with the commodity code similarity comparison unit and the downstream enterprise recommendation unit; the data acquisition unit is used for acquiring and sending value-added tax invoice data and enterprise information to the commodity code similarity comparison unit and the downstream enterprise recommendation unit;
the commodity code similarity comparison unit is connected with the downstream enterprise recommendation unit at one end; the commodity code similarity comparison unit is used for constructing a downstream industrial chain of an industry according to the value-added tax invoice data, enterprise information and a preset rule, determining an important downstream industry of the industry, determining a main operation commodity code set of a target enterprise, determining a candidate enterprise corresponding to the target enterprise and a main purchase commodity code set of the candidate enterprise according to the downstream industrial chain of the industry, and calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set; the commodity code similarity comparison unit is further used for sending the main operation commodity code set of the target enterprise, the main purchase commodity code set of the candidate enterprise and the commodity code similarity set to the downstream enterprise recommendation unit;
and the downstream enterprise recommending unit is used for recommending the downstream enterprises for the target enterprises according to the value-added tax invoice data, the enterprise information, the main operation commodity code set of the target enterprises, the main purchase commodity code set of the candidate enterprises and the commodity code similarity set.
7. The system according to claim 6, wherein the commodity code similarity comparison unit includes:
a downstream industrial chain building module, wherein one end of the downstream industrial chain building module is connected with the main purchased commodity code determining integrated module; the downstream industry chain building module is used for building a downstream industry chain of the industry according to the value-added tax invoice data, the enterprise information and the preset rule and determining an important downstream industry of the industry;
determining a main operation commodity code integration module, wherein one end of the main operation commodity code integration module is connected with a commodity code similarity integration module; the main business commodity code determining and integrating module is used for determining a main business commodity code set of a target enterprise and sending the main business commodity code set of the target enterprise to the commodity code similarity determining and integrating module;
determining a main purchased commodity code integration module, wherein one end of the main purchased commodity code integration module is connected with the commodity code similarity integration module; the main purchased product code determining and integrating module is used for determining a candidate enterprise corresponding to the target enterprise and a main purchased product code set of the candidate enterprise according to a downstream industrial chain of the industry and sending the main purchased product code set of the candidate enterprise to the commodity code similarity determining and integrating module;
and the commodity code similarity set determining module is used for calculating to obtain a commodity code similarity set according to the main operation commodity code set and the main purchase commodity code set.
8. The system of claim 6, wherein the downstream industry chain of industries is constructed according to the value-added tax invoice data, the enterprise information and the preset rules, and the determining important downstream industries of the industries comprises:
enumerating all expected downstream industries of the upstream industry according to the value-added tax invoice data and the enterprise information;
calculating the transaction total amount T of all the expected downstream industries and the upstream industries and the transaction amount A of each expected downstream industry and the upstream industriesn(N ═ 1,2,3...., N) and arranged in descending order;
accumulating the transaction amounts of each expected downstream industry and the upstream industry which are arranged in a descending order one by one until the accumulated result is greater than or equal to tT, and determining the industry corresponding to the accumulated value as the important downstream industry of the upstream industry;
n is a positive integer, AnT is more than 0, and T is more than 0 and less than 1.
9. The system of claim 6, wherein determining the set of hosted commodity codes for the target enterprise comprises:
calculating the total sales Q of all commodities of the target enterprise;
calculating the sales amount B of each commodity of the target enterprisem(M ═ 1, 2...., M) and arranged in descending order;
accumulating sales of each commodity in descending order one by one until the accumulation result is greater than or equal to qQ, wherein the commodity corresponding to the accumulated value is the main operation commodity of the target enterprise, and determining the main operation commodity code set of the target enterprise;
m is a positive integer, BmQ is more than 0, and Q is more than 0 and less than 1.
10. The system of claim 6, wherein the determining the candidate business corresponding to the target business and the set of product codes for the candidate business according to the downstream industry chain of the industry comprises:
determining all enterprises in all important downstream industries of the industry where the target enterprise is located as the candidate enterprises according to the downstream industry chain of the industry;
calculating the total R of all purchased commodities of any candidate enterprise;
calculate the amount of money C of each commodity it purchasesy(Y1, 2.... Y) in descending order;
accumulating the sum of each commodity purchased in descending order one by one until the accumulated result is greater than or equal to rR, wherein the commodity corresponding to the accumulated value is the main commodity purchased by the candidate enterprise;
repeating the steps, and determining the main purchased commodity code sets of all the candidate enterprises;
y is a positive integer, CyR is more than 0, and R is more than 0 and less than 1.
CN202011578080.0A 2020-12-28 2020-12-28 Downstream enterprise recommendation method and system based on commodity code similarity comparison Pending CN112700268A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011578080.0A CN112700268A (en) 2020-12-28 2020-12-28 Downstream enterprise recommendation method and system based on commodity code similarity comparison

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011578080.0A CN112700268A (en) 2020-12-28 2020-12-28 Downstream enterprise recommendation method and system based on commodity code similarity comparison

Publications (1)

Publication Number Publication Date
CN112700268A true CN112700268A (en) 2021-04-23

Family

ID=75512511

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011578080.0A Pending CN112700268A (en) 2020-12-28 2020-12-28 Downstream enterprise recommendation method and system based on commodity code similarity comparison

Country Status (1)

Country Link
CN (1) CN112700268A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254664A (en) * 2021-05-14 2021-08-13 震坤行工业超市(上海)有限公司 Enterprise-oriented item recommendation method and device and storage medium
CN113742587A (en) * 2021-09-07 2021-12-03 海粟智链(青岛)科技有限公司 Internet popularization method suitable for industrial products
CN114329196A (en) * 2021-12-27 2022-04-12 杭州金线连科技有限公司 Information pushing method and device, electronic equipment and storage medium

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254664A (en) * 2021-05-14 2021-08-13 震坤行工业超市(上海)有限公司 Enterprise-oriented item recommendation method and device and storage medium
CN113254664B (en) * 2021-05-14 2022-05-24 震坤行工业超市(上海)有限公司 Enterprise-oriented item recommendation method and device and storage medium
CN113742587A (en) * 2021-09-07 2021-12-03 海粟智链(青岛)科技有限公司 Internet popularization method suitable for industrial products
CN113742587B (en) * 2021-09-07 2024-01-12 海粟智链(青岛)科技有限公司 Internet popularization method suitable for industrial products
CN114329196A (en) * 2021-12-27 2022-04-12 杭州金线连科技有限公司 Information pushing method and device, electronic equipment and storage medium
CN114329196B (en) * 2021-12-27 2022-07-19 杭州金线连科技有限公司 Information pushing method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
Kapoor et al. Tweetboost: Influence of social media on nft valuation
CN112700268A (en) Downstream enterprise recommendation method and system based on commodity code similarity comparison
US20200272917A1 (en) Method, apparatus, and computer program product for determining a provider return rate
CN110009372B (en) User risk identification method and device
US20150332414A1 (en) System and method for predicting items purchased based on transaction data
US20180165759A1 (en) Systems and Methods for Identifying Card-on-File Payment Account Transactions
US20160267406A1 (en) Systems and Methods for Rating Merchants
CN110111179B (en) Drug combination recommendation method and device and computer readable storage medium
US20150332284A1 (en) System and method for determining service intervals based on transaction data
US20090287536A1 (en) Method for determining consumer purchase behavior
US20210241293A1 (en) Apparatuses, computer-implemented methods, and computer program products for improved model-based determinations
US20150332292A1 (en) System and method for monitoring market information for deregulated utilities based on transaction data
US20230297552A1 (en) System, Method, and Computer Program Product for Monitoring and Improving Data Quality
WO2021087137A1 (en) Systems and methods for procurement cost forecasting
Aditi et al. The role of e-services, quality system and perceived value on customer satisfaction: an empirical study on Indonesian SMEs
Fresard et al. The incentives for vertical mergers and vertical integration
CN112669053A (en) Fraud group identification method, device, equipment and medium based on sales data
US11334895B2 (en) Methods, systems, and apparatuses for detecting merchant category code shift behavior
CN110428281B (en) Method and device for jointly determining peer-to-peer resource quantity aiming at multiple associated products
US20150254651A1 (en) Optimizing financial transactions network flow
US20170178164A1 (en) Systems and Methods for Use in Processing Transaction Data
US20230177544A1 (en) Methods and systems for determining a travel propensity configured for use in the generation of a supply index indicative of a quality of available supply
US20220391934A1 (en) Methods and systems for generating a supply index indicative of a quality of available supply of merchant promotions
CN114219547B (en) Method, device, equipment and storage medium for determining store ordering amount
US20200027142A1 (en) System and method for marketing through division of product groups

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