CN114723492A - Enterprise portrait generation method and equipment - Google Patents
Enterprise portrait generation method and equipment Download PDFInfo
- Publication number
- CN114723492A CN114723492A CN202210395252.3A CN202210395252A CN114723492A CN 114723492 A CN114723492 A CN 114723492A CN 202210395252 A CN202210395252 A CN 202210395252A CN 114723492 A CN114723492 A CN 114723492A
- Authority
- CN
- China
- Prior art keywords
- buyer
- enterprise
- commodity
- portrait
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000011161 development Methods 0.000 description 9
- 230000018109 developmental process Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/0282—Rating or review of business operators or products
-
- 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]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a method and equipment for generating an enterprise portrait. The problem of current enterprise portrait be difficult to provide accurate intelligent information recommendation for the user is solved. Generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information; determining the portrait of the purchased commodity of the associated buyer matched with the commodity information according to the commodity information issued by the supplier; determining a buyer enterprise set corresponding to the image of the commodity purchased by the associated buyer and a corresponding buyer enterprise image set; comparing data in the purchasing merchant enterprise portrait collection with a preset standard enterprise portrait data table to obtain a grade result corresponding to the purchasing merchant enterprise portrait, and determining a comprehensive score corresponding to the purchasing merchant enterprise portrait according to the grade result; according to the comprehensive score, ordering the enterprises of the buyers; and pushing the information of the buyer enterprises to the suppliers according to the sorting result.
Description
Technical Field
The application relates to the technical field of enterprise portrait, in particular to a method and equipment for generating enterprise portrait.
Background
The enterprise image refers to that information of an enterprise is researched based on a specific scene, and a characteristic label of the enterprise is extracted, so that accurate analysis of the enterprise is achieved.
In recent years, with the development of industrial internet, enterprise images are gradually applied to product supply and demand platforms to serve users. The enterprise portrait is used as a data analysis tool for quickly and accurately analyzing information such as enterprise behavior patterns and habits, and a foundation is laid for accurate marketing, content recommendation and improvement of user experience of a product supply and demand platform.
In the application of the product supply and demand platform, accurate customers or potential customers are difficult to locate through enterprise figures, and accurate intelligent information recommendation is difficult to provide for users.
Disclosure of Invention
The embodiment of the application provides a method and equipment for generating an enterprise portrait, which are used for solving the problem that the existing enterprise portrait is difficult to provide accurate intelligent information recommendation for a user.
The embodiment of the application adopts the following technical scheme:
the embodiment of the application provides an enterprise portrait generation method. Generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information of the buyer enterprise; according to the commodity information issued by the supplier, determining the image of the commodity purchased by the associated buyer matched with the commodity information from the image of the commodity purchased by the buyer; determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set; comparing data in the purchasing enterprise portrait set with data in a preset standard enterprise portrait data table to obtain grade results corresponding to different types of data in the purchasing enterprise portrait respectively, and determining comprehensive scores corresponding to the purchasing enterprise portrait respectively according to the grade results; according to the comprehensive score, ordering the enterprises of the buyers; and pushing information of one or more buyer enterprises to the supplier according to the sorting result.
According to the embodiment of the application, the portrait of the purchased commodity of the buyer is generated through the commodity browsing record and the purchasing record of the buyer enterprise, and the commodity required by the buyer enterprise can be accurately obtained, so that the information of the buyer is pushed to a supplier selling the commodity, and accurate recommendation information is provided for the supplier enterprise. And generating a buyer enterprise portrait according to the public information of the buyer enterprise, and preferentially recommending the buyer with high score to a corresponding supplier according to the comprehensive score of the portrait of the commodity purchased by the buyer, thereby further mining the data in the enterprise portrait, narrowing the range of the pushed buyer enterprise and enabling the supplier to obtain accurate buyer enterprise information.
In one implementation of the present application, generating an image of a purchased commodity of a buyer according to a commodity browsing record and a purchasing record of a buyer enterprise specifically includes: generating an image of the purchased commodity of the buyer according to the commodity browsing record of the buyer enterprise within the first preset time length and the commodity purchasing record of the buyer enterprise within the second preset time length; the image of the purchased commodity of the buyer at least comprises one or more items of commodity category, commodity name, commodity origin, commodity quantity interval and commodity price interval.
In one implementation of the present application, generating a buyer enterprise portrait according to public information of a buyer enterprise specifically includes: constructing a buyer enterprise portrait corresponding to the buyer enterprise according to the registration information of the buyer enterprise on the current platform and the public information of the buyer enterprise on the third-party platform; the buyer enterprise representation at least comprises one or more of enterprise basic information, enterprise financial conditions, industry attributes, enterprise development potential and enterprise tax credit conditions.
In an implementation manner of the present application, after constructing a buyer enterprise representation corresponding to a buyer enterprise, the method further includes: comparing the enterprise basic information of the buyer enterprise with the enterprise basic information in the preset standard enterprise portrait data table to determine a scale grade result of the buyer enterprise; comparing the enterprise financial condition of the buyer enterprise with the enterprise financial condition in the preset standard enterprise portrait data table to determine the financial grade result of the buyer enterprise; comparing the industry attribute of the buyer enterprise with the industry attribute in a preset standard enterprise portrait data table to determine the production capacity grade result of the buyer enterprise in the industry; and comparing the enterprise tax payment credit condition of the buyer enterprise with the enterprise tax payment credit condition in the preset standard enterprise portrait data table to determine a credit level result of the buyer enterprise.
The grade result of the buyer enterprise is determined from multiple aspects, so that the comprehensive strength of the current buyer enterprise is comprehensively determined. And then the buyer enterprises with high comprehensive strength are pushed to the supplier enterprises, so that the enterprise information received by the buyer enterprises better meets the requirements of the buyer enterprises, and the successful transaction is promoted.
In an implementation manner of the present application, determining, according to the grade result, a comprehensive score corresponding to each of the buyer enterprise images respectively specifically includes: determining grade values respectively corresponding to different grade results; wherein, the magnitude of the grade numerical value respectively corresponding to two grade results with adjacent grades is a multiple relation; and according to a preset rule, calculating the corresponding grade value of each purchasing enterprise portrait in the purchasing enterprise portrait set to obtain the corresponding comprehensive score of each purchasing enterprise portrait.
In one implementation of the present application, determining a representation of a purchased commodity of an associated purchaser matched to commodity information from a representation of the purchased commodity of the purchaser according to commodity information issued by a supplier specifically includes: determining a plurality of first keywords in the commodity information; the keywords at least comprise any one or more of commodity category keywords, commodity name keywords, commodity origin keywords and commodity price keywords; screening a plurality of second keywords related to the first keywords from images of commodities purchased by a plurality of buyers in the current platform, and forming a first image set by the images of the commodities purchased by the buyers corresponding to the second keywords respectively; acquiring images of commodities purchased by a plurality of buyers in the first image set, wherein the images correspond to the minimum values in commodity price intervals respectively; using the image of the commodity purchased by the buyer corresponding to the minimum value in the commodity price interval larger than the commodity price key word as a second image set; and acquiring the maximum value of the commodity quantity interval corresponding to the portrait of each buyer commodity in the second portrait set, sorting the portrait of the buyer commodity in the second portrait set according to the maximum value of the commodity quantity interval, and taking the portrait of the buyer commodity with the serial number less than or equal to the first preset value as the portrait of the associated buyer commodity.
According to the method and the device, the portrait of the commodity purchased by the buyer related to the first keyword is determined through the first keyword in the commodity information issued by the buyer, so that the buyer enterprise which is willing to purchase the commodity is selected. Narrowing the scope of the recommended buyer enterprises. In addition, the enterprise that is the client of the supplier is selected according to the price and the quantity of the commodity purchased by the enterprise of the buyer. By analyzing the enterprise portrait, the recommended enterprise information is more accurate, and the transaction success rate is improved.
In an implementation manner of the present application, in the commodity information, a plurality of first keywords are determined, which specifically include: carrying out word segmentation processing on the commodity information to obtain a plurality of words to be detected; comparing each word to be tested with a preset commodity category corpus to determine a word to be tested with the highest similarity value of any word in the preset commodity category corpus, and taking the word to be tested as a first keyword; comparing each word to be detected with the preset commodity name corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity name corpus, and taking the word to be detected as a first keyword; and comparing each word to be detected with the preset commodity place of production corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity place of production corpus, and taking the word to be detected as a first keyword.
In an implementation manner of the present application, in the portrait of a commodity purchased by a plurality of buyers in a current platform, a plurality of second keywords associated with a plurality of first keywords are screened out, and portraits of the commodity purchased by the plurality of buyers respectively corresponding to the plurality of second keywords form a first portrait set, which specifically includes: screening a plurality of first data which are the same as the commodity category key words from data corresponding to images of commodities purchased by a plurality of buyers in the current platform; screening a plurality of second data with similarity values larger than a second preset value with the commodity name keywords; screening out a plurality of third data which are the same as the commodity place of production keywords or belong to the same province and city as the commodity place of production keywords; and counting the images of the purchased commodities of the buyer simultaneously containing any one of the first data, any one of the second data and any one of the third data, and taking the counted images of the purchased commodities of the buyer as a first image set.
In one implementation manner of the present application, before generating the portrait of the purchased goods of the buyer according to the goods browsing record and the purchasing record of the buyer enterprise, and generating the portrait of the buyer enterprise according to the public information of the buyer enterprise, the method further includes: detecting public information corresponding to a buyer enterprise; when key information is detected to be missing, wrong or repeated in the public information, the public information with the key information missing, wrong or repeated part is removed; under the condition that the public information is detected to be correct, the correct public information is established into a correction data set; when the absence, error or scrambling of the secondary information is detected in the public information, the data of the absence, error or scrambling of the secondary information is corrected based on the corrected data set.
The embodiment of the application provides a generating equipment of enterprise portrait, includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information of the buyer enterprise; according to the commodity information issued by the supplier, determining the image of the commodity purchased by the associated buyer matched with the commodity information from the image of the commodity purchased by the buyer; determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set; comparing data in the purchasing enterprise portrait set with data in a preset standard enterprise portrait data table to obtain grade results corresponding to different types of data in the purchasing enterprise portrait respectively, and determining comprehensive scores corresponding to the purchasing enterprise portrait respectively according to the grade results; according to the comprehensive score, ordering the enterprises of the buyers; and pushing information of one or more buyer enterprises to the supplier according to the sorting result.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects: according to the embodiment of the application, the portrait of the purchased commodity of the buyer is generated through the commodity browsing record and the purchasing record of the buyer enterprise, and the commodity required by the buyer enterprise can be accurately obtained, so that the information of the buyer is pushed to a supplier selling the commodity, and accurate recommendation information is provided for the supplier enterprise. And generating a buyer enterprise portrait according to the public information of the buyer enterprise, and preferentially recommending the buyer with high score to a corresponding supplier according to the comprehensive score of the portrait of the commodity purchased by the buyer, thereby further mining the data in the enterprise portrait, narrowing the range of the pushed buyer enterprise and enabling the supplier to obtain high-quality buyer enterprise information.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. On the attached sheet
In the figure:
FIG. 1 is a flowchart of a method for generating an enterprise representation according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an enterprise representation generating device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a method and equipment for generating an enterprise portrait.
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
With the development of the industrial internet, enterprise images are gradually applied to product supply and demand platforms to serve users. The enterprise portrait is used as a data analysis tool for quickly and accurately analyzing information such as enterprise behavior patterns and habits, and a foundation is laid for accurate marketing, content recommendation and improvement of user experience of a product supply and demand platform.
In the application of the product supply and demand platform, a user needs to locate an accurate client or a potential client, so that an enterprise needs to be accurately represented, and accurate information recommendation can be performed for the user. The existing enterprise portrait method is single in form, deep data mining is difficult to conduct, and valuable intelligent information recommendation is difficult to provide for users.
In order to solve the above problem, embodiments of the present application provide a method and an apparatus for generating and applying an enterprise portrait. The commodity browsing record and the purchasing record of the buyer enterprise are used for generating the portrait of the commodity purchased by the buyer, so that the commodity required by the buyer enterprise can be accurately acquired. Thereby pushing the information of the buyer to the supplier that sold the good. And the embodiment of the application generates the portrait of the buyer enterprise according to the public information of the buyer enterprise, and preferentially recommends the buyer with high score to the corresponding supplier according to the comprehensive score of the portrait of the commodity purchased by the buyer, thereby further narrowing the range of the pushed buyer enterprise and enabling the supplier to obtain more accurate information of the buyer enterprise.
The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for generating an enterprise portrait according to an embodiment of the present disclosure. As shown in FIG. 1, the method for generating and applying the enterprise portrait comprises the following steps:
s101, generating an enterprise portrait and an application system, generating the portrait of the purchased commodities of the buyer according to the commodity browsing records and the purchasing records of the buyer enterprise, and generating the enterprise portrait of the buyer according to the public information of the buyer enterprise.
In one embodiment of the present application, an image of a buyer's purchased merchandise is generated based on the buyer's enterprise's inventory browsing history over a month and inventory purchasing history over a half year period.
Specifically, browsing records and purchasing records of the buyer in the current purchasing platform are obtained. And generating an image of the purchased commodity of the buyer enterprise according to the commodity type, the commodity name, the commodity origin and the commodity price in the browsing record and the commodity type, the commodity name, the commodity origin, the commodity price and the commodity quantity purchased in the purchasing record.
The image of the purchased product of the purchaser includes at least one or more items of a product type, a product name, a product origin, a product quantity interval, and a product price interval.
In one embodiment of the application, a buyer enterprise representation corresponding to the buyer enterprise is constructed according to the registration information of the buyer enterprise on the current platform and the public information of the buyer enterprise on the third-party platform.
Specifically, the registration information of the buyer enterprise on the current platform and all information registered by the buyer enterprise on the industrial and commercial enterprises are obtained. Such as company name, unified social credit code, dates of establishment, residences, registered capital, real estate, scope of business, registration authorities, registration status, stakeholder information, high-management information, risk event statistics, intellectual property, upstream and downstream relationship maps, etc. And constructing a buyer enterprise portrait corresponding to the buyer enterprise according to the acquired information of the buyer enterprise.
In one embodiment of the application, public information corresponding to a buyer enterprise is detected. And when the key information is detected to be missing, wrong or repeated in the public information, rejecting the public information with the missing, wrong or repeated key information. And in the case that the public information is detected to be correct, the correct public information is constructed into a correction data set. When the presence of the missing, erroneous, or scrambled secondary information in the public information is detected, the data with the missing, erroneous, or scrambled secondary information is corrected based on the corrected data set.
It should be noted that the procurement merchant enterprise representation includes at least one or more of enterprise basic information, enterprise financial status, industry attributes, enterprise development potential, and enterprise tax credit status.
S102, according to the commodity information issued by the supplier, the image of the commodity purchased by the related buyer matched with the commodity information is determined from the image of the commodity purchased by the buyer.
In one embodiment of the application, commodity information issued by a supplier is obtained, and a plurality of first keywords are determined in the commodity information. The first keywords at least comprise any one or more of commodity category keywords, commodity name keywords, commodity origin keywords and commodity price keywords.
Specifically, the commodity information is subjected to word segmentation processing to obtain a plurality of words to be tested. And comparing each word to be detected with the preset commodity category corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity category corpus, and taking the word to be detected as a first keyword. And comparing each word to be detected with the preset commodity name corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity name corpus, and taking the word to be detected as a first keyword. And comparing each word to be detected with a preset commodity place of production corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity place of production corpus, and taking the word to be detected as a first keyword.
For example, the commodity information about the computer issued by the supplier is subjected to word segmentation processing to obtain the waiting words of the computer, the electronic product, the Shandong and the black. And comparing the obtained words to be detected with a preset commodity category corpus, a preset commodity name corpus and a preset commodity place corpus respectively to determine that the categories are a plurality of first keywords of electronic products, the commodity names are computers, the commodity places are Shandong and the like.
It should be noted that the first keyword in the embodiment of the present application is not limited to three types, namely, a commodity category, a commodity name, and a commodity origin. According to the practical application situation, the words to be tested with other characteristics such as commodity shape, commodity color and the like can be added as the first key words.
In one embodiment of the application, a plurality of second keywords related to a plurality of first keywords are screened out from images of commodities purchased by a plurality of buyers in a current platform, and the images of the commodities purchased by the plurality of buyers corresponding to the plurality of second keywords respectively form a first image set.
Specifically, a plurality of first data identical to the commodity category keywords are screened out from data corresponding to images of commodities purchased by a plurality of buyers in the current platform. And screening a plurality of second data with similarity value of more than 90% with the commodity name keyword. And screening a plurality of third data which are the same as the commodity place of production keywords or belong to the same province and city as the commodity place of production keywords. And counting the images of the purchased commodities of the buyer simultaneously containing any one of the first data, any one of the second data and any one of the third data, and taking the counted images of the purchased commodities of the buyer as a first image set.
For example, after a plurality of first keywords having a category of electronic products, a product name of computer, and a product origin of Shandong are specified, a plurality of first data having a keyword as an electronic product are screened from data corresponding to images of products purchased by a purchaser in a current platform. And screening a plurality of second data with the similarity value of the keywords to the computer being more than 90%, such as: computer, notebook, etc. And screening a plurality of third data, such as third data of Jinan, Qingdao and the like, of which the producing area is Shandong or each urban area in Shandong province. Counting the image of the purchased commodity of the buyer which simultaneously comprises any first data, any second data and any third data. For example, a first image set is a picture of a purchased commodity of a purchaser having three keywords of electronic product, computer, and south of the province, or a picture of a purchased commodity of a purchaser having three keywords of electronic product, computer, and east of Shandong.
In one embodiment of the application, images of commodities purchased by a plurality of buyers in the first image set are acquired, and the images respectively correspond to the minimum values in the commodity price intervals. And using the minimum value in the commodity price interval larger than the commodity price key word as a second image set, wherein the corresponding image of the commodity purchased by the buyer is used as the second image set.
Specifically, the images of the purchased commodities of each buyer in the first image set are respectively obtained, and the minimum values in the commodity price intervals respectively correspond to, for example, the minimum values are 5000 yuan, 6000 yuan and 7000 yuan. The commodity price keyword in the commodity information issued by the supplier is 5500 yuan, and at this time, images of commodities purchased by the buyer corresponding to 6000 yuan and 7000 yuan are taken as a second image set.
In one embodiment of the application, the maximum value of the commodity quantity interval corresponding to each image of the commodity purchased by the buyer in the second image set is obtained, the images of the commodity purchased by the buyer in the second image set are sorted according to the maximum value of the commodity quantity interval, and the image of the commodity purchased by the buyer with the serial number less than or equal to 20 is used as the image of the commodity purchased by the related buyer.
Specifically, the maximum values of the plurality of acquired commodity quantity sections are arranged in order from large to small, and the images of the commodities purchased by the buyers corresponding to the first 20 maximum values are used as the images of the commodities purchased by the associated buyers.
In the embodiment of the present application, it is preferable that the images of the purchased products of the purchaser corresponding to the first 20 maximum values are taken as the images of the purchased products of the related purchaser. The embodiment of the application can change the number of the portrait of the commodity purchased by the associated buyer according to the actual application condition.
S103, determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set.
In one embodiment of the application, the buyer enterprises corresponding to the images of the commodities purchased by each associated buyer are determined, and a buyer enterprise set is constructed. And determining the enterprise portrait of each buyer enterprise in the buyer enterprise set, which corresponds to each buyer enterprise, so as to construct a buyer enterprise portrait set.
And S104, comparing the data in the buyer enterprise portrait set with the data in a preset standard enterprise portrait data table to obtain the grade results respectively corresponding to the different types of data in the buyer enterprise portrait, and determining the comprehensive score respectively corresponding to each buyer enterprise portrait according to the grade results.
In one embodiment of the present application, the enterprise basic information of the buyer enterprise is compared with the enterprise basic information in the preset standard enterprise portrait data table to determine the scale level result of the buyer enterprise. And comparing the enterprise financial condition of the buyer enterprise with the enterprise financial condition in the preset standard enterprise portrait data table to determine the financial grade result of the buyer enterprise. And comparing the industry attribute of the buyer enterprise with the industry attribute in the preset standard enterprise portrait data table to determine the production capacity grade result of the buyer enterprise in the industry. And comparing the enterprise development potential of the buyer enterprise with the enterprise development potential in the preset standard enterprise portrait data table to determine the development potential grade result of the buyer enterprise. And comparing the enterprise tax payment credit condition of the buyer enterprise with the enterprise tax payment credit condition in the preset standard enterprise portrait data table to determine a credit level result of the buyer enterprise.
Specifically, the preset standard enterprise portrait data table includes a plurality of enterprise scale data information, a plurality of enterprise financial status data information, a plurality of production capacity data information, a plurality of enterprise development potential data information, and a plurality of enterprise tax payment credit status data information. For example, the enterprise scale data information includes multiple levels of 0-100 employees, 101-200 employees, 201-500 employees, 501-1000 employees, etc., the level result corresponding to 0-100 employees is first level, the level result corresponding to 101-200 employees is second level, the level result corresponding to 201-500 employees is third level, and the level result corresponding to 501-1000 employees is fourth level, and the enterprise scale is graded according to the number of employees. And the higher the grade result, the larger the enterprise size.
In one embodiment of the present application, respective grade values corresponding to different grade results are determined. And the magnitude of the grade numerical value respectively corresponding to two grade results with adjacent grades is a multiple relation. And according to a preset rule, calculating the corresponding grade value of each purchasing enterprise portrait in the purchasing enterprise portrait set to obtain the corresponding comprehensive score of each purchasing enterprise portrait.
Specifically, different grade results correspond to different grade values, for example, one grade corresponds to 5 points, two grades corresponds to 10 points, three grades corresponds to 20 points, and four grades corresponds to 40 points. And determining the grading results of a plurality of categories corresponding to each buyer enterprise image. For example, the scale grade result corresponding to any buyer enterprise portrait is two grades, the grade value is 10 points, the corresponding financial grade result is three grades, the grade value is 20 points, the production capacity grade result is three grades, the grade value is 20 points, the development potential grade result is two grades, the grade value is 10 points, the credit grade result is three grades, the grade value is 20 points, and the grade values corresponding to the grade results are added to obtain the comprehensive score of the enterprise of 80 points.
Furthermore, each purchasing enterprise portrait in the purchasing enterprise portrait collection is added with a plurality of corresponding grade values to obtain a comprehensive score value corresponding to each purchasing enterprise portrait.
And S105, sequencing the enterprises of the buyer according to the comprehensive score.
In one embodiment of the present application, a respective composite score is assigned to each of the obtained set of buyer enterprise images. The buyer enterprises in the buyer enterprise representation collection are sorted. And acquiring the serial number of the buyer enterprise from high to low according to the comprehensive score.
And S106, pushing the information of one or more buyer enterprises to the supplier according to the sorting result.
In one embodiment of the subject application, serial number 1-10 of the buyer enterprise is pushed to the supplier based on the serial number of the buyer enterprise.
It should be noted that, in the embodiment of the present application, preferably, 10 buyer enterprises before the serial number are pushed to the supplier. The number of the pushed purchasers can be adjusted according to the actual application condition.
Fig. 2 is a schematic structural diagram of an enterprise portrait generation and application device according to an embodiment of the present disclosure.
As shown in FIG. 2, an enterprise representation generation apparatus includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information of the buyer enterprise;
according to commodity information issued by a supplier, determining a portrait of a commodity purchased by a related buyer matched with the commodity information from the portrait of the commodity purchased by the buyer;
determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set;
comparing the data in the buyer enterprise portrait set with the data in a preset standard enterprise portrait data table to obtain the grade results corresponding to different types of data in the buyer enterprise portrait respectively, and determining the comprehensive score corresponding to each buyer enterprise portrait respectively according to the grade results;
sorting the buyer enterprises according to the comprehensive scores;
and pushing information of one or more buyer enterprises to the suppliers according to the sorting result.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus, device, and non-volatile computer storage medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to the partial description of the method embodiments for relevant points.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the embodiments of the present application pertain. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for generating an enterprise representation, the method comprising:
generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information of the buyer enterprise;
according to commodity information issued by a supplier, determining a portrait of a commodity purchased by a related buyer matched with the commodity information from the portrait of the commodity purchased by the buyer;
determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set;
comparing the data in the buyer enterprise portrait set with the data in a preset standard enterprise portrait data table to obtain the grade results corresponding to different types of data in the buyer enterprise portrait respectively, and determining the comprehensive score corresponding to each buyer enterprise portrait respectively according to the grade results;
sorting the buyer enterprises according to the comprehensive scores;
and pushing information of one or more buyer enterprises to the suppliers according to the sorting result.
2. The method for generating an enterprise representation as claimed in claim 1, wherein the generating of the representation of the purchased goods of the buyer according to the goods browsing record and the purchasing record of the buyer enterprise comprises:
generating an enterprise commodity portrait according to the commodity browsing record of the buyer enterprise within a first preset time length and the commodity purchasing record within a second preset time length;
the image of the purchased commodity of the buyer at least comprises one or more items of commodity category, commodity name, commodity origin, commodity quantity interval and commodity price interval.
3. The method for generating an enterprise representation as claimed in claim 1, wherein the generating of the buyer enterprise representation based on the public information of the buyer enterprise comprises:
constructing a buyer enterprise portrait corresponding to the buyer enterprise according to the registration information of the buyer enterprise on the current platform and the public information of the buyer enterprise on a third-party platform;
the enterprise information representation at least comprises one or more of enterprise basic information, enterprise financial conditions, industry attributes and enterprise tax credit conditions.
4. A method of generating an enterprise representation as claimed in claim 3, wherein after constructing a corresponding buyer enterprise representation for said buyer enterprise, said method further comprises:
comparing the enterprise basic information of the buyer enterprise with the enterprise basic information in the preset standard enterprise portrait data table to determine a scale grade result of the buyer enterprise;
comparing the enterprise financial condition of the buyer enterprise with the enterprise financial condition in the preset standard enterprise portrait data table to determine the financial grade result of the buyer enterprise;
comparing the industry attribute of the buyer enterprise with the industry attribute in the preset standard enterprise portrait data table to determine the production capacity grade result of the buyer enterprise in the industry;
and comparing the enterprise tax payment credit condition of the buyer enterprise with the enterprise tax payment credit condition in the preset standard enterprise portrait data table to determine a credit level result of the buyer enterprise.
5. The method for generating an enterprise representation as claimed in claim 1, wherein said determining a composite score corresponding to each buyer enterprise representation according to said ranking result comprises:
determining grade values respectively corresponding to different grade results; the two grade results with adjacent grades respectively correspond to grade numerical values in a multiple relation;
and calculating the grade values respectively corresponding to each enterprise information portrait in the buyer enterprise portrait set according to preset rules to obtain the comprehensive score respectively corresponding to each buyer enterprise portrait.
6. The method of claim 1, wherein the step of determining from the representation of the purchased goods from the buyer, a representation of the purchased goods from the buyer that matches the goods information based on the goods information published by the supplier, comprises:
determining a plurality of first keywords in the commodity information; the keywords at least comprise any one or more of commodity category keywords, commodity name keywords, commodity origin keywords and commodity price keywords;
screening a plurality of second keywords related to the first keywords from images of commodities purchased by a plurality of buyers in the current platform, and forming a first image set by the images of the commodities purchased by the plurality of buyers corresponding to the second keywords respectively;
acquiring images of commodities purchased by a plurality of buyers in the first image set, wherein the images correspond to the minimum values in commodity price intervals respectively;
using the minimum value in the commodity price interval which is larger than the commodity price key word and the corresponding image of the commodity purchased by the buyer as a second image set;
and acquiring the maximum value of a commodity quantity interval corresponding to the portrait of each buyer commodity in the second portrait set, sequencing the portrait of the buyer commodity in the second portrait set according to the maximum value of the commodity quantity interval, and taking the portrait of the buyer commodity with the serial number less than or equal to a first preset value as the portrait of the related buyer commodity.
7. The method for generating an enterprise portrait according to claim 6, wherein the determining a plurality of first keywords in the commodity information specifically includes:
performing word segmentation processing on the commodity information to obtain a plurality of words to be detected;
comparing each word to be detected with a preset commodity category corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity category corpus, and taking the word to be detected as a first keyword; and
comparing each word to be detected with a preset commodity name corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity name corpus, and taking the word to be detected as a first keyword; and
and comparing each word to be detected with a preset commodity place corpus to determine a word to be detected with the highest similarity value with any word in the preset commodity place corpus, and taking the word to be detected as a first keyword.
8. The method as claimed in claim 6, wherein the step of screening out a plurality of second keywords associated with the plurality of first keywords from the images of the products purchased by the buyers in the current platform, and forming a first image set from the images of the products purchased by the buyers respectively corresponding to the plurality of second keywords comprises:
screening a plurality of first data which are the same as the commodity category keywords from data corresponding to images of commodities purchased by a plurality of buyers in the current platform; and
screening out a plurality of second data with similarity values larger than a second preset value with the commodity name keywords; and
screening out a plurality of third data which are the same as the commodity place of production keywords or belong to the same province and city as the commodity place of production keywords;
and counting enterprise commodity images simultaneously containing any one of the first data, any one of the second data and any one of the third data, and taking the counted images of the commodities purchased by the buyer as a first image set.
9. The method of claim 1, wherein before generating the representation of the buyer's purchased goods based on the goods viewing records and the purchasing records of the buyer's business, and generating the representation of the buyer's business based on the public information of the buyer's business, the method further comprises:
detecting the public information corresponding to the buyer enterprises;
when key information is detected to be missing, wrong or repeated in the public information, the public information with the missing, wrong or repeated key information is removed;
under the condition that the public information is detected to be correct, the correct public information is established into a correction data set;
and when detecting that the public information has secondary information missing, errors or garbled codes, correcting the data with the secondary information missing, errors or garbled codes according to the correction data set.
10. An enterprise representation generation device, comprising:
at least one processor; and (c) a second step of,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
generating an image of the purchased commodity of the buyer according to the commodity browsing record and the purchasing record of the buyer enterprise, and generating an image of the buyer enterprise according to the public information of the buyer enterprise;
according to commodity information issued by a supplier, determining a portrait of a commodity purchased by a related buyer matched with the commodity information from the portrait of the commodity purchased by the buyer;
determining a buyer enterprise image set corresponding to the image of the commodity purchased by the associated buyer, and acquiring a buyer enterprise image set corresponding to the buyer enterprise set;
comparing the data in the buyer enterprise portrait set with the data in a preset standard enterprise portrait data table to obtain the grade results corresponding to different types of data in the buyer enterprise portrait respectively, and determining the comprehensive score corresponding to each buyer enterprise portrait respectively according to the grade results;
sorting the buyer enterprises according to the comprehensive scores;
and pushing information of one or more buyer enterprises to the suppliers according to the sorting result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210395252.3A CN114723492A (en) | 2022-04-15 | 2022-04-15 | Enterprise portrait generation method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210395252.3A CN114723492A (en) | 2022-04-15 | 2022-04-15 | Enterprise portrait generation method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114723492A true CN114723492A (en) | 2022-07-08 |
Family
ID=82243367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210395252.3A Pending CN114723492A (en) | 2022-04-15 | 2022-04-15 | Enterprise portrait generation method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114723492A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115827934A (en) * | 2023-02-21 | 2023-03-21 | 四川省计算机研究院 | Enterprise portrait intelligent analysis system and method based on unified social credit code |
| CN116071092A (en) * | 2023-03-20 | 2023-05-05 | 浪潮云洲(山东)工业互联网有限公司 | Prefabricated vegetable tracing method, system and equipment based on blockchain |
-
2022
- 2022-04-15 CN CN202210395252.3A patent/CN114723492A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115827934A (en) * | 2023-02-21 | 2023-03-21 | 四川省计算机研究院 | Enterprise portrait intelligent analysis system and method based on unified social credit code |
| CN115827934B (en) * | 2023-02-21 | 2023-05-09 | 四川省计算机研究院 | Enterprise portrait intelligent analysis system and method based on unified social credit code |
| CN116071092A (en) * | 2023-03-20 | 2023-05-05 | 浪潮云洲(山东)工业互联网有限公司 | Prefabricated vegetable tracing method, system and equipment based on blockchain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CN114723492A (en) | Enterprise portrait generation method and equipment | |
| CN103577988A (en) | Method and device for recognizing specific user | |
| CN102985939A (en) | Art evaluation engine and method for automatic development of an art index | |
| CN115456745A (en) | Small and micro enterprise portrait construction method and device | |
| CN111695979A (en) | Method, device and equipment for analyzing relation between raw material and finished product | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| Alfatih et al. | The effect of service quality on customer satisfaction of an Indonesian e-commerce website | |
| CN116611796A (en) | Exception detection method and device for store transaction data | |
| CN115496440B (en) | Determination method and device for stock quantity of second hand vehicle | |
| US7970711B2 (en) | Warranty management system and method | |
| CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
| CN115374082A (en) | Tax-related database analysis method, equipment and storage medium | |
| CN114169926A (en) | Commodity data analysis method, system, device and medium based on user comments | |
| CN103020855A (en) | Bad commodity distinguishing method and system based on user purchasing behavior | |
| JPH0934873A (en) | Customer classification method and system | |
| Janamarta et al. | Effect Of Ease of Use and Trust on Purchase Decisions Through Online Shopping Sites | |
| CN116308466B (en) | Data information acquisition and intelligent analysis method, system, equipment and storage medium | |
| Kotsokechagia | Predictive model for customer satisfaction in e-commerce | |
| CN115187387A (en) | Identification method and equipment for risk merchant | |
| CN116934418B (en) | Abnormal order detection and early warning method, system, equipment and storage medium | |
| TWI769385B (en) | Method and system for screening potential purchasers of financial products | |
| Paramadina et al. | An Information System for Metal Product Sales: Pasarlogam. com | |
| EP4138021A1 (en) | Method of scoring and valuing data for exchange | |
| US20220335485A1 (en) | Partner fee recommendation service |
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 |