CN112884362A - Intelligent supplier matching method, device, equipment and storage medium - Google Patents
Intelligent supplier matching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112884362A CN112884362A CN202110294124.5A CN202110294124A CN112884362A CN 112884362 A CN112884362 A CN 112884362A CN 202110294124 A CN202110294124 A CN 202110294124A CN 112884362 A CN112884362 A CN 112884362A
- Authority
- CN
- China
- Prior art keywords
- information
- matching
- search
- supplier
- target
- 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 51
- 238000005516 engineering process Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 26
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000009849 deactivation Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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]
- G06Q30/0605—Supply or demand aggregation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a supplier intelligent matching method, a supplier intelligent matching device, supplier intelligent matching equipment and a storage medium, wherein the method comprises the following steps: acquiring a search term and matching mode information in a supplier matching request; then, performing vocabulary reconstruction on the search terms according to the matching mode information to obtain target search terms; searching for information of a to-be-selected provider corresponding to a target search term through a knowledge graph technology; and finally, screening the information of the to-be-selected supplier to obtain the information of the target supplier. According to the invention, the retrieval requirements under different conditions can be met by performing vocabulary reconstruction on the retrieval words through the matching mode information, and meanwhile, the information of the to-be-selected provider corresponding to the target retrieval word is searched through the knowledge map technology, so that the matching result is more comprehensive, the retrieval range is wider, in addition, the information of the to-be-selected provider is automatically screened after being obtained, and the manual screening operation of a user is also reduced.
Description
Technical Field
The invention relates to the technical field of data matching, in particular to an intelligent matching method, device, equipment and storage medium for suppliers.
Background
With the rapid development of the e-commerce platform, when a buyer purchases a product, the buyer can search and screen a satisfactory supplier on the transaction platform to conduct a transaction. In the prior art, a buyer can search in a search bar based on the name of a supplier/product and obtain related information of the corresponding product under the condition that the name of the supplier or the name of the product needing to be purchased is known in advance.
However, in most cases, the buyer can only use the customized query term to search the product concerned or to be purchased by himself on the transaction platform, and then find the information of the corresponding supplier through the product information to obtain the related information of the product operated by the supplier. Moreover, the suppliers obtained in this way are often not the best or the suppliers meeting the needs of the buyers, and further manual screening is needed.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a supplier intelligent matching method, a supplier intelligent matching device, a supplier intelligent matching equipment and a storage medium, and aims to solve the technical problem that suppliers matched by the existing supplier matching technology cannot better meet the requirements of buyers.
In order to achieve the above object, the present invention provides a supplier intelligent matching method, including the following steps:
acquiring a search term and matching mode information in a supplier matching request;
performing vocabulary reconstruction on the search word according to the matching mode information to obtain a target search word;
searching the information of the to-be-selected provider corresponding to the target search term through a knowledge graph technology;
and screening the information of the suppliers to be selected to obtain the information of the target suppliers.
Preferably, the step of performing vocabulary reconstruction on the search term according to the matching pattern information to obtain a target search term includes:
acquiring a matching mode corresponding to the matching mode information;
when the matching mode is accurate matching, performing word segmentation on the search word, and performing stop word removal on the segmented search word to obtain a plurality of search words;
reading a first type of search terms from the search terms according to a preset product industry classification table, and taking the rest search terms as second type of search terms;
and determining a target search term according to the first type of search term and the second type of search term.
Preferably, the step of performing vocabulary reconstruction on the search term according to the matching pattern information to obtain a target search term includes:
acquiring a matching mode corresponding to the matching mode information;
when the matching mode is fuzzy matching, judging whether the search word contains an enterprise identifier;
if not, splitting the search words to obtain a plurality of search words;
reading a first type of search terms from the search terms according to a preset product industry classification table, and acquiring near-meaning term words corresponding to the rest search terms;
taking the rest search vocabulary and the similar meaning word vocabulary as a second type search word;
and determining a target search term according to the first type of search term and the second type of search term.
Preferably, the target search term comprises a first type search term and a second type search term;
the step of searching for the information of the to-be-selected provider corresponding to the target search term through the knowledge graph technology comprises the following steps:
searching for alternative supplier information corresponding to the first type of search term through a knowledge graph technology;
acquiring product supply information corresponding to the alternative supplier information;
and selecting information of a supplier to be selected from the information of the alternative suppliers according to the second type of search words and the product supply information.
Preferably, the step of searching for alternative provider information corresponding to the first category of search terms through a knowledge graph technology includes:
determining product industry information according to the first type of search words, wherein the industry information comprises industry information and product information;
searching a corresponding target industry knowledge graph in a pre-constructed industry knowledge graph library according to the industry information;
and traversing the target industry knowledge graph according to the product information, and determining alternative supplier information according to the traversal result.
Preferably, before the step of obtaining the search term and the matching pattern information in the supplier matching request, the method further includes:
acquiring enterprise information corresponding to different industries;
establishing an initial industry knowledge graph according to the enterprise information and the industry to which each enterprise belongs in the enterprise information;
constructing a product knowledge graph corresponding to each enterprise according to the operation range information of each enterprise;
and fusing the product knowledge graph and the initial industry knowledge graph to obtain a fused industry knowledge graph, and storing the fused industry knowledge graph to an industry knowledge graph library.
Preferably, the step of screening the information of the candidate suppliers to obtain the information of the target supplier includes:
acquiring order data and capacity data of a product supplier corresponding to the information of the supplier to be selected within a preset time period;
and screening the information of the to-be-selected supplier according to the order data and the capacity data to obtain the information of the target supplier.
In addition, in order to achieve the above object, the present invention further provides a supplier intelligent matching apparatus, including:
the request analysis module is used for acquiring search terms and matching mode information in the supplier matching request;
the vocabulary reconstruction module is used for performing vocabulary reconstruction on the search word according to the matching mode information to obtain a target search word;
the information matching module is used for searching the information of the suppliers to be selected corresponding to the target search term through a knowledge graph technology;
and the information screening module is used for screening the information of the to-be-selected supplier to obtain the information of the target supplier.
In addition, in order to achieve the above object, the present invention further provides a supplier intelligent matching device, including: a memory, a processor, and a vendor intelligent match program stored on the memory and executable on the processor, the vendor intelligent match program configured to implement the steps of the vendor intelligent match method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having a supplier intelligent matching program stored thereon, wherein the supplier intelligent matching program, when executed by a processor, implements the steps of the supplier intelligent matching method as described above.
The invention obtains the search terms and the matching mode information in the supplier matching request; then, performing vocabulary reconstruction on the search terms according to the matching mode information to obtain target search terms; searching for information of a to-be-selected provider corresponding to a target search term through a knowledge graph technology; and finally, screening the information of the to-be-selected supplier to obtain the information of the target supplier. According to the invention, the retrieval requirements under different conditions can be met by performing vocabulary reconstruction on the retrieval words through the matching mode information, and meanwhile, the information of the to-be-selected provider corresponding to the target retrieval word is searched through the knowledge map technology, so that the matching result is more comprehensive, the retrieval range is wider, the information of the to-be-selected provider is automatically screened after being obtained, and the manual screening operation of a user is also reduced.
Drawings
FIG. 1 is a schematic diagram of a configuration of a vendor intelligent matching device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating a first embodiment of a supplier intelligent matching method according to the present invention;
FIG. 3 is a schematic diagram of knowledge graph fusion according to a first embodiment of the supplier intelligent matching method;
FIG. 4 is a flowchart illustrating a second embodiment of a supplier intelligent matching method according to the present invention;
FIG. 5 is a flowchart illustrating a third embodiment of the intelligent supplier matching method according to the present invention;
fig. 6 is a block diagram of a first embodiment of a supplier intelligent matching device according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a provider intelligent matching device of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the vendor smart matching device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of the vendor intelligent match device, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and a vendor smart matching program.
In the vendor intelligent matching device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the provider intelligent matching device of the present invention may be disposed in the provider intelligent matching device, and the provider intelligent matching device calls the provider intelligent matching program stored in the memory 1005 through the processor 1001 and executes the provider intelligent matching method provided by the embodiment of the present invention.
An embodiment of the present invention provides an intelligent matching method for a provider, and referring to fig. 2, fig. 2 is a schematic flow diagram of a first embodiment of the intelligent matching method for a provider according to the present invention.
In this embodiment, the intelligent matching method for suppliers includes the following steps:
step S10: acquiring a search term and matching mode information in a supplier matching request;
it should be noted that the execution main body of the method embodiment of the present invention may be a computing service device with data processing, network communication and program running functions, such as a mobile terminal, e.g., a mobile phone, a tablet computer, a personal computer, etc., or may be other electronic products with similar functions, which is not limited in this embodiment. In this step, the supplier matching request may be triggered by the buyer or the user based on the mobile terminal or an application program with a data search function loaded on the mobile terminal.
In a specific implementation, a user can input a search term through a search box on a human-computer interaction interface of the mobile terminal to trigger a supplier matching request. Of course, when performing the vendor matching, the user may also select a corresponding matching mode (e.g., exact matching, fuzzy matching) according to the user's own requirement. The matching mode information contains the matching mode currently selected by the user or the corresponding identification information, and the identification information is used for determining the matching mode. In this embodiment, the search term may be a word or text composed of a plurality of characters, may be a string of pure numbers or letters, or may be a segment of characters.
It is to be understood that exact matching refers to a degree of precision given to the match according to the conditions or requirements set forth; fuzzy matching refers to giving an approximate degree of matching depending on given conditions or requirements. The matched content is precisely matched in a more detailed, specific and accurate manner, and the content enables the satisfaction degree of the user to be higher; the fuzzy matching is more extensive and rough, and the content is not high enough to satisfy the user, but is wide in range. The method for providing the intelligent matching of the suppliers for the users can enable the users to select a proper mode to match the suppliers according to the requirements of the users, and compared with the existing mode of searching only by fuzzy matching, the method for providing the intelligent matching of the suppliers can serve the users more humanizedly.
Step S20: performing vocabulary reconstruction on the search word according to the matching mode information to obtain a target search word;
it should be noted that in this embodiment, the term reconstruction may be performed by splitting, replacing synonyms or synonyms, splicing, and/or reordering the terms according to a set rule based on the matching pattern information. For example, for the search term "automotive mechanical drawing software", if the matching pattern corresponding to the matching pattern information is fuzzy matching, the "automotive mechanical drawing software" may be first split into "automotive industry", "mechanical" and "drawing software", and then reordered to obtain the target search term "drawing software-mechanical-automotive industry". Of course, this is by way of example only and not a specific limitation on lexical reconstruction. The specific way of reconstructing the vocabulary in the embodiment and the following embodiments may be determined according to actual situations, for example, when reordering the split vocabulary, the weight or priority (which may be preset) of the vocabulary may also be considered.
Step S30: searching the information of the to-be-selected provider corresponding to the target search term through a knowledge graph technology;
it should be understood that a Knowledge Graph (Knowledge Graph), which is called Knowledge domain visualization or Knowledge domain mapping map in the book intelligence world, is a series of various graphs displaying the relationship between the Knowledge development process and the structure, describes Knowledge resources and their carriers by using visualization technology, and mines, analyzes, constructs, draws, and displays Knowledge and their interrelations.
It will be appreciated that any business may determine its industry or sub-industry depending on the extent of the business or the products/services sold. In the specific implementation of the embodiment, the industry knowledge graph can be constructed according to the structural relationship of industry-sub industry-enterprise information-operation range-product information, and then the corresponding supplier information can be searched through the pre-constructed industry knowledge graph based on the search word input by the user, so that the quick search of the supplier information can be realized, and the accuracy of the supplier matching result can be ensured.
It should be noted that the supplier information may include the name, address, product/service website link, product information (sales, price, etc. details), and the like of the product supplier.
Step S40: and screening the information of the suppliers to be selected to obtain the information of the target suppliers.
It should be understood that, in practical applications, there may be a plurality of candidate provider information, for example, a user wants to purchase a drawing software, 5 to 10 candidate providers (information) may be retrieved according to the above steps, and in order to avoid and reduce the user spending too much time on manually selecting the candidate provider information, the embodiment may automatically screen the candidate provider information to obtain the target provider information.
Specifically, the screening of the information of the candidate suppliers in this embodiment may be implemented according to the matching mode in the matching mode information. For example, the search term input by the user is "mechanical design", and if the matching mode is exact matching, the information of the supplier to be selected is strictly screened (referring to a search mode in which the search term is completely the same as a certain field in the resource library) according to the search term "mechanical design", so as to obtain the target information of the supplier "xxx mechanical design limited company"; if the matching mode is fuzzy matching, the information of the supplier to be selected is screened according to the search term 'mechanical design', and the obtained target information of the supplier can be 'xxx mechanical design company Limited', also can be 'xx design research institute-mechanical engineering institute', and also can be 'xx mechanical research design institute company Limited'.
Of course, the filtering manner of the information of the candidate providers in this embodiment may also be implemented according to the browsing history of the user. For example, the historical browsing information of the user may be obtained first, and then the currently obtained information of the candidate providers (enterprise a, enterprise B, enterprise C, etc.) is screened according to the provider information (enterprise a, enterprise B) in the historical browsing information, so as to obtain the target provider information, that is, the information corresponding to enterprise a and enterprise B.
Further, in this embodiment, the screening of the information of the to-be-selected provider may be implemented by combining browsing history information of the user with a matching pattern in the matching pattern information.
Further, in order to ensure that the supplier searched by the user can meet the product purchase demand of the user, step S40 in this embodiment may further include: acquiring order data and capacity data of a product supplier corresponding to the information of the supplier to be selected within a preset time period; and screening the information of the to-be-selected supplier according to the order data and the capacity data to obtain the information of the target supplier.
The preset time period may be set by the user, the order data may be the number of product orders of the product supplier within the preset time period, the order delivery date, and the like, and the capacity data may be the number of products that the supplier can produce or the service that the supplier can provide in the existing production scale. In a specific implementation, the acquisition of the target provider information can be implemented according to whether the order in the order data is saturated or not and whether the capacity meets the supply demand or not. Under the same condition, the supplier information with moderate order quantity and capacity meeting the requirement is preferentially selected as the target supplier information.
In the embodiment, the search terms and the matching mode information in the supplier matching request are obtained; then, performing vocabulary reconstruction on the search terms according to the matching mode information to obtain target search terms; searching for information of a to-be-selected provider corresponding to a target search term through a knowledge graph technology; and finally, screening the information of the to-be-selected supplier to obtain the information of the target supplier. According to the embodiment, the retrieval requirements under different conditions can be met by performing vocabulary reconstruction on the retrieval words through the matching mode information, meanwhile, the information of the to-be-selected provider corresponding to the target retrieval word is searched through the knowledge map technology, so that the matching result is more comprehensive, the retrieval range is wider, the information of the to-be-selected provider is automatically screened after being acquired, and the manual screening operation of a user is reduced.
Further, in order to ensure the accuracy of the matching result of the supplier, the intelligent matching method for the supplier provided by this embodiment further includes, before the step S10, the construction of an industry knowledge graph:
step S01: acquiring enterprise information corresponding to different industries;
it should be noted that, in order to generate the industry knowledge graph, an industry classification table may be established according to national economy industry classification and codes (GB/4754 plus 2011), and then enterprise information in each industry may be obtained according to the industry names recorded in the industry classification table, where the enterprise information may include information such as legal representatives, enterprise names, business registration numbers, registration addresses, and operation ranges of enterprises, and in this embodiment, the enterprise information may be stored in a database and then represented in the industry knowledge graph in a manner of linking database, or may be represented in the form of a table.
It can be understood that, in this embodiment, the enterprise information may be obtained from an enterprise management system corresponding to an industrial and commercial administration office, or may be obtained from a database corresponding to an application program or a client having enterprise information query, which is not limited in this embodiment.
Step S02: establishing an initial industry knowledge graph according to the enterprise information and the industry to which each enterprise belongs in the enterprise information;
it can be understood that after the enterprise information is obtained, the operation information, the product information and the information of the affiliated segment industry (sub-industry) corresponding to each enterprise can be determined, and then an initial industry knowledge graph is constructed according to the information. For example, the initial industry knowledge graph may be constructed according to the architecture of "industry-sub industry-enterprise information".
Specifically, the industry to which the enterprise belongs can be divided according to the national economy industry classification and the code (GB/4754-.
Step S03: constructing a product knowledge graph corresponding to each enterprise according to the operation range information of each enterprise;
it should be understood that for an enterprise, the products sold or services provided by the enterprise should be basically the products or services registered in the business domain. Therefore, when the product knowledge graph corresponding to the enterprise is constructed, the method can be realized based on the architecture of 'enterprise information-operation range-product information' according to the operation range information recorded by the enterprise in the business bureau.
Step S04: and fusing the product knowledge graph and the initial industry knowledge graph to obtain a fused industry knowledge graph, and storing the fused industry knowledge graph to an industry knowledge graph library.
It should be noted that, the product knowledge graph and the initial industry knowledge graph are fused, and the industry-sub-industry-enterprise information and the enterprise information-business range-product information are spliced to obtain the fused industry knowledge graph of the architecture of the industry-sub-industry-enterprise information-business range-product information. As shown in fig. 3, fig. 3 is a schematic view of knowledge graph fusion according to a first embodiment of the supplier intelligent matching method of the present invention.
Of course, when the knowledge graph is merged, the product information may include commodity information of a business that is not noted in the business scope, for example, information of a commodity sold by a company.
In the embodiment, the industry knowledge graph is constructed in the above manner, and then the matching of the suppliers is performed based on the industry knowledge graph, so that the matching result accuracy is ensured, and meanwhile, the matching efficiency of the suppliers is improved.
Referring to fig. 4, fig. 4 is a flowchart illustrating a supplier intelligent matching method according to a second embodiment of the present invention.
Based on the first embodiment, in this embodiment, the step S20 may include:
step S201: acquiring a matching mode corresponding to the matching mode information;
it should be noted that the matching mode in this embodiment may be an exact match or a fuzzy match, or may be another search mode customized by the search engine platform. This embodiment is not limited in this regard.
Step S202: when the matching mode is accurate matching, performing word segmentation on the search word, and performing stop word removal on the segmented search word to obtain a plurality of search words;
it should be understood that, since the precision of the exact match search is higher than that of the fuzzy search, in order to avoid that the result of the exact match search is null or the search fails when the user inputs a certain word or long sentence, in this embodiment, when the matching mode is exact match, the search term is segmented, and the segmented search term is de-segmented to obtain a plurality of search terms. For example, the vocabulary obtained after word segmentation of "free drawing software for mechanical drawing" is: mechanical/drawing/free/drawing/software, the vocabulary obtained after the stop words is: mechanical/charting/free/charting/software.
Of course, in this embodiment, the search term after the word segmentation may not only be used to stop the word, but also be used to remove words that do not affect the search result, and the removal of the words may be implemented according to a pre-established vocabulary. In addition, in this embodiment, before splitting the search term, it may be determined whether the search term includes the enterprise identifier, and if the search term includes the enterprise identifier, the enterprise identifier is taken as a whole and is not split, so as to ensure the accuracy of the search result, for example, the "electronic game bus" as the enterprise identifier cannot be split into two vocabularies without special meaning, i.e., "electronic game" and "bus".
Step S203: reading a first type of search terms from the search terms according to a preset product industry classification table, and taking the rest search terms as second type of search terms;
it should be noted that the preset product industry classification table can be made according to the national economic industry classification and code (GB/4754 + 2011). For example, machines belong to the C manufacturing industry, and software belongs to the G information transmission, software and information technology services industry.
In a specific implementation, the first category of search terms may be read from the search terms according to a preset product industry classification table, and then the remaining terms are used as the second category of search terms, for example, "mechanical/drawing/free/drawing/software" in "mechanical/drawing/free/drawing/software" is used as the first category of search terms, and then "drawing, free" is used as the second category of search terms.
Step S204: and determining a target search term according to the first type of search term and the second type of search term.
It should be noted that, in this embodiment, the default weights or the retrieval priorities of the first category of search terms and the second category of search terms are different, and the weight or the retrieval priority of the first category of search terms is higher than that of the second category of search terms.
In this embodiment, the target search term may be composed of a first type search term and a search priority corresponding to the first type search term, and a second type search term and a search priority corresponding to the second type search term. During retrieval, the data (to be screened) corresponding to the first category of retrieval words is retrieved preferentially, and then the data (to be screened) retrieved previously is screened secondarily according to the second category of retrieval words.
In the embodiment, the matching mode corresponding to the matching mode information is obtained; when the matching mode is accurate matching, performing word segmentation on the search word, and performing word removal and stop on the segmented search word to obtain a plurality of search words; reading a first type of search terms from the search terms according to a preset product industry classification table, and taking the rest search terms as second type of search terms; and determining a target search term according to the first type search term and the second type search term. The target search term determining method provided by this embodiment can perform vocabulary reconstruction on a search term input by a user according to different matching modes, perform word segmentation and word deactivation on the search term when the matching mode is an accurate matching mode, classify the search term into a first type search term and a second type search term according to a preset product industry classification table, and determine the target search term according to the first type search term and the second type search term, thereby ensuring the accuracy of subsequent search results.
Referring to fig. 5, fig. 5 is a schematic flow chart of a third embodiment of the supplier intelligent matching method according to the present invention.
Based on the first embodiment, in this embodiment, the step S20 may include:
step S201': acquiring a matching mode corresponding to the matching mode information;
it should be noted that the matching mode in this embodiment may be an exact match or a fuzzy match, or may be another search mode customized by the search engine platform. This embodiment is not limited in this regard.
Step S202': when the matching mode is fuzzy matching, judging whether the search word contains an enterprise identifier;
it should be noted that, because the requirement on the precision of the search result by the fuzzy matching is a little relatively low, in this embodiment, the search term can be directly split. The enterprise identification can be the name, name abbreviation or business registration number of the enterprise. Certainly, in this embodiment, before splitting the search term, it is further determined whether the search term includes the enterprise identifier, and if the search term includes the enterprise identifier, the enterprise identifier is taken as a whole and is not split, so as to ensure the accuracy of the search result, for example, the "electronic game bus" as the enterprise identifier cannot be split into two vocabularies without special meaning, i.e., "electronic game" and "bus".
Step S203': if not, splitting the search words to obtain a plurality of search words;
it can be understood that when the search term does not contain the enterprise identification, the search term can be directly split to obtain a plurality of search words. Since the matching mode in this embodiment is fuzzy matching, it is not necessary to stop the vocabulary after being split, but in order to improve the accuracy of the final matching result, the operation of stopping the vocabulary may be increased.
Step S204': reading a first type of search terms from the search terms according to a preset product industry classification table, and acquiring near-meaning term words corresponding to the rest search terms;
step S205': taking the rest search vocabulary and the similar meaning word vocabulary as a second type search word;
it should be noted that the preset product industry classification table can be made according to the national economic industry classification and code (GB/4754 + 2011). For example, machines belong to the C manufacturing industry, and software belongs to the G information transmission, software and information technology services industry.
In a specific implementation, the first category of search terms may be read from the search terms according to a predetermined product industry classification table.
In addition, when the matching pattern is fuzzy matching, the search range is expanded. The embodiment will also obtain the similar meaning words corresponding to the remaining search words, for example, obtain the similar meaning words "drawing, not charging" corresponding to the remaining words "drawing, free", etc., and then use these similar meaning words and the remaining search words together as the second type of search words "drawing, not charging, free".
Step S206': and determining a target search term according to the first type of search term and the second type of search term.
Similar to the second embodiment, in this embodiment, the default weights or the retrieval priorities of the first type of search terms and the second type of search terms are different, and the weights or the retrieval priorities of the first type of search terms are higher than those of the second type of search terms.
In this embodiment, the target search term may be composed of a first type search term and a search priority corresponding to the first type search term, and a second type search term and a search priority corresponding to the second type search term. During retrieval, the data (to be screened) corresponding to the first category of retrieval words is retrieved preferentially, and then the data (to be screened) retrieved previously is screened secondarily according to the second category of retrieval words.
Further, in this embodiment, the step S30 may include:
step S301: searching for alternative supplier information corresponding to the first type of search term through a knowledge graph technology;
it should be understood that, since the first category search term is read according to the preset product industry classification table, when acquiring the supplier information, the alternative supplier information in different industries can be searched through the knowledge graph technology based on different industries.
Further, in order to ensure accuracy of the supplier matching. The embodiment can determine product industry information according to the first type of search term, wherein the industry information comprises industry information and product information; searching a corresponding target industry knowledge graph in a pre-constructed industry knowledge graph library according to the industry information; and traversing the target industry knowledge graph according to the product information, and determining alternative supplier information according to the traversal result.
It should be understood that, since the first category of search terms are obtained according to the preset product industry classification table, the first category of search terms are basically words with high correlation degree with industry information, and the product industry information can be determined according to the first category of search terms.
Step S302: acquiring product supply information corresponding to the alternative supplier information;
it should be noted that the product supply information may be sales information of a product sold for a certain period of time, product details of the sold product, and the like. The product supply information in this embodiment may be obtained from an official website corresponding to the supplier.
Step S303: and selecting information of a supplier to be selected from the information of the alternative suppliers according to the second type of search words and the product supply information.
It should be understood that there may be many suppliers selling the same product or service, and further screening may be required according to the second category of search terms more relevant to the product inputted by the user in order to ensure that the finally retrieved supplier information meets the user's requirements.
In the embodiment, the matching mode corresponding to the matching mode information is obtained; when the matching mode is fuzzy matching, judging whether the search word contains an enterprise identifier; if not, splitting the search terms to obtain a plurality of search terms; reading a first type of search terms from the search terms according to a preset product industry classification table, and acquiring near-meaning term words corresponding to the rest search terms; taking the rest search words and the similar meaning word words as second class search words; and determining a target search term according to the first type search term and the second type search term. The target search term determining method provided by this embodiment can perform vocabulary reconstruction on a search term input by a user according to different matching modes, perform word segmentation and word deactivation on the search term when the matching mode is fuzzy matching, classify the search term into a first class search term according to a preset product industry classification table, acquire a near-meaning term word corresponding to the remaining search term, use the remaining search term and the near-meaning term as a second class search term, and determine the target search term according to the first class search term and the second class search term, thereby ensuring wider coverage of subsequent search results.
In addition, an embodiment of the present invention further provides a storage medium, where a supplier intelligent matching program is stored on the storage medium, and the supplier intelligent matching program, when executed by a processor, implements the steps of the supplier intelligent matching method described above.
Referring to fig. 6, fig. 6 is a block diagram illustrating a first embodiment of a supplier intelligent matching apparatus according to the present invention.
As shown in fig. 6, the supplier intelligent matching apparatus provided in the embodiment of the present invention includes:
a request analysis module 601, configured to obtain a search term and matching mode information in a provider matching request;
a vocabulary reconstructing module 602, configured to perform vocabulary reconstruction on the search term according to the matching mode information, to obtain a target search term;
the information matching module 603 is configured to search for information of a candidate provider corresponding to the target search term through a knowledge graph technology;
the information screening module 604 is configured to screen the information of the candidate providers to obtain information of target providers.
In the embodiment, the search terms and the matching mode information in the supplier matching request are obtained; then, performing vocabulary reconstruction on the search terms according to the matching mode information to obtain target search terms; searching for information of a to-be-selected provider corresponding to a target search term through a knowledge graph technology; and finally, screening the information of the to-be-selected supplier to obtain the information of the target supplier. According to the embodiment, the retrieval requirements under different conditions can be met by performing vocabulary reconstruction on the retrieval words through the matching mode information, meanwhile, the information of the to-be-selected provider corresponding to the target retrieval word is searched through the knowledge map technology, so that the matching result is more comprehensive, the retrieval range is wider, the information of the to-be-selected provider is automatically screened after being acquired, and the manual screening operation of a user is reduced.
Based on the first embodiment of the supplier intelligent matching device, a second embodiment of the supplier intelligent matching device is provided.
In this embodiment, the vocabulary reconstructing module 602 is further configured to obtain a matching pattern corresponding to the matching pattern information; when the matching mode is accurate matching, performing word segmentation on the search word, and performing stop word removal on the segmented search word to obtain a plurality of search words; reading a first type of search terms from the search terms according to a preset product industry classification table, and taking the rest search terms as second type of search terms; and determining a target search term according to the first type of search term and the second type of search term.
As an implementation manner, the vocabulary reconstructing module 602 is further configured to obtain a matching pattern corresponding to the matching pattern information; when the matching mode is fuzzy matching, judging whether the search word contains an enterprise identifier; if not, splitting the search words to obtain a plurality of search words; reading a first type of search terms from the search terms according to a preset product industry classification table, and acquiring near-meaning term words corresponding to the rest search terms; taking the rest search vocabulary and the similar meaning word vocabulary as a second type search word; and determining a target search term according to the first type of search term and the second type of search term.
As an implementation manner, the information matching module 603 is further configured to search, by using a knowledge graph technology, for alternative provider information corresponding to the first category of search terms; acquiring product supply information corresponding to the alternative supplier information; and selecting information of a supplier to be selected from the information of the alternative suppliers according to the second type of search words and the product supply information.
As an implementation manner, the information matching module 603 is further configured to determine product industry information according to the first category of search terms, where the industry information includes industry information and product information; searching a corresponding target industry knowledge graph in a pre-constructed industry knowledge graph library according to the industry information; and traversing the target industry knowledge graph according to the product information, and determining alternative supplier information according to the traversal result.
As an embodiment, the supplier intelligent matching device further comprises: the map building module is used for acquiring enterprise information corresponding to different industries; establishing an initial industry knowledge graph according to the enterprise information and the industry to which each enterprise belongs in the enterprise information; constructing a product knowledge graph corresponding to each enterprise according to the operation range information of each enterprise; and fusing the product knowledge graph and the initial industry knowledge graph to obtain a fused industry knowledge graph, and storing the fused industry knowledge graph to an industry knowledge graph library.
As an implementation manner, the information filtering module 604 is further configured to obtain order data and capacity data of a product provider corresponding to the information of the candidate provider within a preset time period; and screening the information of the to-be-selected supplier according to the order data and the capacity data to obtain the information of the target supplier.
Other embodiments or specific implementation manners of the provider intelligent matching device of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A supplier intelligence matching method, the method comprising:
acquiring a search term and matching mode information in a supplier matching request;
performing vocabulary reconstruction on the search word according to the matching mode information to obtain a target search word;
searching the information of the to-be-selected provider corresponding to the target search term through a knowledge graph technology;
and screening the information of the suppliers to be selected to obtain the information of the target suppliers.
2. The intelligent supplier matching method according to claim 1, wherein the step of performing vocabulary reconstruction on the search term according to the matching pattern information to obtain a target search term comprises:
acquiring a matching mode corresponding to the matching mode information;
when the matching mode is accurate matching, performing word segmentation on the search word, and performing stop word removal on the segmented search word to obtain a plurality of search words;
reading a first type of search terms from the search terms according to a preset product industry classification table, and taking the rest search terms as second type of search terms;
and determining a target search term according to the first type of search term and the second type of search term.
3. The intelligent supplier matching method according to claim 1, wherein the step of performing vocabulary reconstruction on the search term according to the matching pattern information to obtain a target search term comprises:
acquiring a matching mode corresponding to the matching mode information;
when the matching mode is fuzzy matching, judging whether the search word contains an enterprise identifier;
if not, splitting the search words to obtain a plurality of search words;
reading a first type of search terms from the search terms according to a preset product industry classification table, and acquiring near-meaning term words corresponding to the rest search terms;
taking the rest search vocabulary and the similar meaning word vocabulary as a second type search word;
and determining a target search term according to the first type of search term and the second type of search term.
4. The intelligent matching method for suppliers according to claim 2 or 3, wherein the target search term comprises a first kind of search term and a second kind of search term;
the step of searching for the information of the to-be-selected provider corresponding to the target search term through the knowledge graph technology comprises the following steps:
searching for alternative supplier information corresponding to the first type of search term through a knowledge graph technology;
acquiring product supply information corresponding to the alternative supplier information;
and selecting information of a supplier to be selected from the information of the alternative suppliers according to the second type of search words and the product supply information.
5. The intelligent supplier matching method according to claim 4, wherein the step of searching for alternative supplier information corresponding to the first category of search terms through a knowledge graph technology comprises:
determining product industry information according to the first type of search words, wherein the industry information comprises industry information and product information;
searching a corresponding target industry knowledge graph in a pre-constructed industry knowledge graph library according to the industry information;
and traversing the target industry knowledge graph according to the product information, and determining alternative supplier information according to the traversal result.
6. The intelligent provider matching method of claim 1, wherein said step of obtaining a term and matching pattern information in a provider matching request is preceded by the method further comprising:
acquiring enterprise information corresponding to different industries;
establishing an initial industry knowledge graph according to the enterprise information and the industry to which each enterprise belongs in the enterprise information;
constructing a product knowledge graph corresponding to each enterprise according to the operation range information of each enterprise;
and fusing the product knowledge graph and the initial industry knowledge graph to obtain a fused industry knowledge graph, and storing the fused industry knowledge graph to an industry knowledge graph library.
7. The intelligent supplier matching method according to claim 1, wherein the step of screening the information of the suppliers to be selected to obtain the information of the target suppliers comprises:
acquiring order data and capacity data of a product supplier corresponding to the information of the supplier to be selected within a preset time period;
and screening the information of the to-be-selected supplier according to the order data and the capacity data to obtain the information of the target supplier.
8. A vendor intelligent matching apparatus, the apparatus comprising:
the request analysis module is used for acquiring search terms and matching mode information in the supplier matching request;
the vocabulary reconstruction module is used for performing vocabulary reconstruction on the search word according to the matching mode information to obtain a target search word;
the information matching module is used for searching the information of the suppliers to be selected corresponding to the target search term through a knowledge graph technology;
and the information screening module is used for screening the information of the to-be-selected supplier to obtain the information of the target supplier.
9. A vendor intelligent matching device, said device comprising: a memory, a processor, and a vendor intelligent match program stored on the memory and executable on the processor, the vendor intelligent match program configured to implement the steps of the vendor intelligent match method as recited in any one of claims 1 to 7.
10. A storage medium having stored thereon a vendor intelligent matching program, which when executed by a processor implements the steps of the vendor intelligent matching method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294124.5A CN112884362A (en) | 2021-03-18 | 2021-03-18 | Intelligent supplier matching method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110294124.5A CN112884362A (en) | 2021-03-18 | 2021-03-18 | Intelligent supplier matching method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112884362A true CN112884362A (en) | 2021-06-01 |
Family
ID=76041289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110294124.5A Pending CN112884362A (en) | 2021-03-18 | 2021-03-18 | Intelligent supplier matching method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112884362A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651022A (en) * | 2012-03-31 | 2012-08-29 | 奇智软件（北京）有限公司 | Searching method and device |
| US20170024657A1 (en) * | 2015-07-21 | 2017-01-26 | Yp Llc | Fuzzy autosuggestion for query processing services |
| CN109857938A (en) * | 2019-01-30 | 2019-06-07 | 杭州太火鸟科技有限公司 | Searching method, searcher and computer storage medium based on company information |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
| CN110516047A (en) * | 2019-09-02 | 2019-11-29 | 湖南工业大学 | The search method and searching system of knowledge mapping based on packaging field |
| CN110765275A (en) * | 2019-10-14 | 2020-02-07 | 平安医疗健康管理股份有限公司 | Search method, search device, computer equipment and storage medium |
| US20200302359A1 (en) * | 2019-03-22 | 2020-09-24 | Wipro Limited | Method and system for determining a potential supplier for a project |
| CN112148885A (en) * | 2020-09-04 | 2020-12-29 | 上海晏鼠计算机技术股份有限公司 | Intelligent searching method and system based on knowledge graph |
| CN112256887A (en) * | 2020-10-28 | 2021-01-22 | 福建亿榕信息技术有限公司 | Intelligent supply chain management method based on knowledge graph |
| CN112380420A (en) * | 2020-11-11 | 2021-02-19 | Vidaa美国公司 | Searching method and display device |
| CN112396437A (en) * | 2020-12-03 | 2021-02-23 | 北京中电普华信息技术有限公司 | Trade contract verification method and device based on knowledge graph |
-
2021
- 2021-03-18 CN CN202110294124.5A patent/CN112884362A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102651022A (en) * | 2012-03-31 | 2012-08-29 | 奇智软件（北京）有限公司 | Searching method and device |
| US20170024657A1 (en) * | 2015-07-21 | 2017-01-26 | Yp Llc | Fuzzy autosuggestion for query processing services |
| CN109857938A (en) * | 2019-01-30 | 2019-06-07 | 杭州太火鸟科技有限公司 | Searching method, searcher and computer storage medium based on company information |
| US20200302359A1 (en) * | 2019-03-22 | 2020-09-24 | Wipro Limited | Method and system for determining a potential supplier for a project |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
| CN110516047A (en) * | 2019-09-02 | 2019-11-29 | 湖南工业大学 | The search method and searching system of knowledge mapping based on packaging field |
| CN110765275A (en) * | 2019-10-14 | 2020-02-07 | 平安医疗健康管理股份有限公司 | Search method, search device, computer equipment and storage medium |
| CN112148885A (en) * | 2020-09-04 | 2020-12-29 | 上海晏鼠计算机技术股份有限公司 | Intelligent searching method and system based on knowledge graph |
| CN112256887A (en) * | 2020-10-28 | 2021-01-22 | 福建亿榕信息技术有限公司 | Intelligent supply chain management method based on knowledge graph |
| CN112380420A (en) * | 2020-11-11 | 2021-02-19 | Vidaa美国公司 | Searching method and display device |
| CN112396437A (en) * | 2020-12-03 | 2021-02-23 | 北京中电普华信息技术有限公司 | Trade contract verification method and device based on knowledge graph |
Non-Patent Citations (4)
| Title |
|---|
| 孙雨生;常凯月;朱礼军;: "大规模知识图谱及其应用研究", 情报理论与实践, no. 11, 27 November 2018 (2018-11-27) * |
| 时雨;古天龙;宾辰忠;孙彦鹏;: "基于知识图谱的旅游景点问答系统", 桂林电子科技大学学报, no. 04, 25 August 2018 (2018-08-25) * |
| 杨荣;翟社平;王志文;: "基于知识图谱的信息查询系统设计与实现", 计算机与数字工程, no. 04, 20 April 2020 (2020-04-20) * |
| 阮光册;樊宇航;夏磊;: "知识图谱在实体检索中的应用研究综述", 图书情报工作, no. 14, 20 July 2020 (2020-07-20) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110286974B (en) | Application configuration method, device, equipment and storage medium based on H5 page | |
| CN112907333B (en) | Intelligent matching method, device and equipment based on block chain and storage medium | |
| US20030171942A1 (en) | Contact relationship management system and method | |
| US11138248B2 (en) | Understanding user product queries in real time without using any rules | |
| CN109857938B (en) | Searching method and searching device based on enterprise information and computer storage medium | |
| CN111552870A (en) | Object recommendation method, electronic device and storage medium | |
| US9384278B2 (en) | Methods and systems for assessing excessive accessory listings in search results | |
| US10599760B2 (en) | Intelligent form creation | |
| CN112184290A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| US11367117B1 (en) | Artificial intelligence system for generating network-accessible recommendations with explanatory metadata | |
| CN111324786A (en) | Method and device for processing consultation problem information | |
| CN110362702B (en) | Picture management method and equipment | |
| US8577814B1 (en) | System and method for genetic creation of a rule set for duplicate detection | |
| CN114328632A (en) | User data analysis method and device based on bitmap and computer equipment | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN117541355A (en) | Commodity information display method and system | |
| CN111026963A (en) | Data query method and device, and configuration information setting method and device | |
| US20180025359A1 (en) | Customer journey optimized pre-fetching | |
| US10621208B2 (en) | Category name extraction device, category name extraction method, and category name extraction program | |
| CN108345600B (en) | Management of search application, data search method and device thereof | |
| CN112884362A (en) | Intelligent supplier matching method, device, equipment and storage medium | |
| CN112528096B (en) | Enterprise analysis method, storage medium and electronic equipment | |
| US10430775B1 (en) | Validation and lookup techniques for rule-based data categorization | |
| CN112148939A (en) | Data processing method and device and electronic equipment | |
| KR20190094656A (en) | Searching service method and device for shopping mall |
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 |