CN115098766A - Electronic bidding transaction platform bidding information recommendation method and system - Google Patents
Electronic bidding transaction platform bidding information recommendation method and system Download PDFInfo
- Publication number
- CN115098766A CN115098766A CN202210590392.6A CN202210590392A CN115098766A CN 115098766 A CN115098766 A CN 115098766A CN 202210590392 A CN202210590392 A CN 202210590392A CN 115098766 A CN115098766 A CN 115098766A
- Authority
- CN
- China
- Prior art keywords
- keyword
- user
- data
- information
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for recommending bidding information of an electronic bidding trading platform, wherein the method comprises the steps of receiving target announcement information on the trading platform, carrying out matching search by combining a preset keyword lexicon based on the target announcement information, and acquiring first keyword data of the target announcement information; when the matching search result is empty, generating second keyword data of the target announcement information based on the analysis of the target announcement information; analyzing an interest degree parameter of each keyword to the user based on first keyword data or second keyword data of the target announcement information, wherein the interest degree parameter of each keyword to the user is obtained based on interest degree labels of the user to the keywords; and recommending the target notice information to the user based on the interestingness ranking. The invention realizes the quick and intelligent matching of the two acquiring and supplying parties, helps the two bidding and inviting parties to obtain effective information, and ensures efficient and accurate trading behavior.
Description
Technical Field
The invention relates to the technical field of bidding, in particular to a method and a system for recommending bidding information of an electronic bidding trading platform
Background
The bidding and the bidding are taken as wide and universal market trading behaviors, the monopoly of the industry and the blockade of the area are broken, the electronic bidding and the bidding enable the bidding behaviors to be fairer, fair and open, the gray zone of the industry is reduced, the manpower, the material resources and the financial resources are saved, and the cost reduction and the efficiency improvement are realized. With the electronization of the bidding service and the enterprise purchasing service, various electronic bidding transaction platforms emerge, and various enterprise independent transaction platforms emerge to form the phenomenon of information overload, so that the bidding information on the internet is more, messy and mixed, namely, the bidding announcement publishing platforms are more, the format of the bidding announcement is disordered, the content and distribution of the bidding announcement are disordered, and the quick and effective information acquisition of the bidding persons is hindered.
For the bidder, on one hand, the bidder who has collaborated past is relied on, and on the other hand, the bidder actively bids. For bidders, on one hand, the bidders actively search whether the bidders concerned by themselves release items, and on the other hand, the bidders search for relevant products hosted by themselves on various electronic bidding platforms, thereby finding appropriate bidding opportunities. The bidding parties have the problems of missing bidding information, difficult registration, insufficient bidders, inappropriate bidders and the like.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for recommending bid information of an electronic bid transaction platform, which effectively improve the rapid intelligent matching of a buyer and a supplier.
In a first aspect, the invention provides a bid information recommendation method for an electronic bid transaction platform, which includes:
receiving target announcement information on a trading platform, and performing matching search by combining a preset keyword lexicon based on the target announcement information to obtain first keyword data of the target announcement information;
when the matching search result is empty, generating second keyword data of the target announcement information based on the analysis of the target announcement information;
analyzing an interest degree parameter of each keyword to the user based on first keyword data or second keyword data of the target announcement information, wherein the interest degree parameter of each keyword to the user is obtained based on interest degree labels of the user to the keywords;
and recommending the target notice information to the user based on the interestingness ranking.
In some embodiments, the performing matching search based on the target advertisement information in combination with a preset keyword lexicon to obtain first keyword data of the target advertisement information includes:
extracting keyword labels based on historical announcement information, and establishing a preset keyword lexicon based on the extracted keywords;
carrying out data cleaning on the target notice information, and removing a company name, a region name and a person name in the target notice;
and matching and searching in a preset keyword word bank based on the cleaned target announcement information to obtain first keyword data of the target announcement information.
In some embodiments, the generating the second keyword data of the target advertisement information based on analyzing the target advertisement information itself includes:
based on the historical bulletin information, calculating high-frequency words appearing in the historical bulletin through a first preset algorithm, and establishing a white list word library based on the high-frequency words;
obtaining verbs and nouns in the target announcement information by utilizing a second preset algorithm based on the cleaned target announcement information to form a first verb and noun set;
filtering verbs and nouns in the first verb and noun set by adopting a white list word library to form a second verb and noun set;
and combining the verbs and the nouns in the second verb-noun set to form second keyword data.
In some embodiments, the analyzing the interestingness parameter of each keyword to the user based on the first keyword data or the second keyword data of the target advertisement information includes:
acquiring a mapping relation between a pre-established operation behavior of a user on the announcement information and the interestingness of the user on the announcement information;
extracting first keyword data or second keyword data for historical bulletin information;
acquiring interest parameters of different keyword data of the historical bulletin information from the user based on the operation behavior of the user on the bulletin information in the historical record and the mapping relation;
constructing a user keyword interest portrait based on interest degree parameters of different keyword data of the historical bulletin information of the user;
and comparing and analyzing the first keyword data or the second keyword data of the target announcement information and the interest portrait of the user keyword, and analyzing the fusion interest degree parameter of each keyword to the user.
In some embodiments, the obtaining, based on the operation behavior of the user on the advertisement information in the history record and the mapping relationship, a user interest parameter for different keyword data of the history advertisement information includes:
acquiring a first interestingness parameter of the user on different keyword data of the historical announcement information based on the operation behavior of the user on the announcement information in the historical record and the mapping relation;
dividing different keywords with the same first interestingness parameter into the same set, recording the keywords as a first set, and labeling the first interestingness parameter for the first set;
performing text semantic recognition and classification based on keywords in the same first set to obtain a plurality of first subclasses in the same first set;
performing similarity analysis based on the first subclasses in all the first sets, and performing secondary analysis on different first subclasses of different sets to correct the belonged sets of the different first subclasses of the different sets when the similarity of the different first subclasses distributed in the different sets is smaller than a first preset similarity threshold;
and labeling a second interestingness parameter for the keywords in the set based on the first interestingness parameter labeled by the set based on the corrected set.
In some embodiments, the secondarily analyzing the first subclass and the second subclass to modify the belonged sets of the first subclass and the second subclass when the similarity of the first subclass and the second subclass distributed in the two different sets is smaller than a first preset similarity threshold includes:
based on first subclasses in all the first sets, acquiring time of a user for operating announcement information of a source to which a keyword belongs in different first subclasses for different first subclasses distributed in different sets, of which the similarity is smaller than a first preset similarity threshold, and counting frequency of the user for operating announcement information of the source to which the keyword belongs in the different first subclasses in the same time period;
determining modified sets distributed on different first subclasses of different sets, wherein the similarity is smaller than a first preset similarity threshold value, based on the time and frequency data of the operation behaviors;
and merging the distribution with the similarity smaller than a first preset similarity threshold in different first subclasses of different sets, and classifying the merged distribution into the corrected set.
In some embodiments, the constructing the user keyword interest representation based on the user interest parameters of different keyword data of the historical bulletin information includes:
sorting the keyword data according to the time of the operation behavior of the user on the announcement information corresponding to the keyword data;
for the sorted keyword data, the interestingness parameter is used as first labeled data, the time data is used as second labeled data, the keyword data are classified based on the announcement information type represented by the keyword data to generate third labeled data, a user keyword interest portrait is generated based on the first labeled data, the second labeled data and the third labeled data, and the user keyword interest portrait is displayed on the screenThe weight of each keyword in the user keyword interest portrait is determined based on the first labeled data, the second labeled data and the third labeled data, and the weight of each keyword in the user keyword interest portrait is as follows:wherein, ω is 0 Is a weight base value, t is the current second label data, n is the number of keyword data having the same third label data, t s Is the second label data of the s-th keyword data among the keyword data having the same third label data, t 0 Is the decay factor of the user's keyword interests over time.
In some embodiments, the comparing and analyzing the first keyword data or the second keyword data based on the target announcement information and the user keyword interest representation, and analyzing the fused interestingness parameter of each keyword to the user includes:
acquiring keywords in a keyword interest image of a user and weights of the keywords;
searching the keyword data in the user keyword interest portrait based on the first keyword data or the second keyword data, wherein the times and the positions of the keyword data in the user keyword interest portrait are searched;
and calculating a fusion interest degree parameter of the keyword data to the user based on the weight of the keyword at the position appearing in the user keyword interest portrait.
In a second aspect, the present invention provides a bid information recommendation system for an electronic bid transaction platform, including:
the system comprises a first keyword acquisition unit, a first search unit and a second search unit, wherein the first keyword acquisition unit is used for receiving target announcement information on a trading platform, performing matching search by combining a preset keyword lexicon based on the target announcement information and acquiring first keyword data of the target announcement information;
the second keyword acquisition unit is used for generating second keyword data of the target notice information based on the analysis of the target notice information when the matching search result is empty;
the user interest degree parameter calculating unit is used for analyzing interest degree parameters of each keyword to the user based on first keyword data or second keyword data of the target notice information, and the interest degree parameters of each keyword to the user are obtained based on interest degree labels of the user to the keywords;
and the information recommending unit is used for recommending the target notice information to the user based on the interestingness sorting.
In a third aspect, the present invention provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the recommendation method as described in the first aspect.
The method and the system for recommending the bid information of the electronic bid transaction platform have the following beneficial effects that: according to the method, the extraction effectiveness of the characteristic data of the target announcement information is improved, meanwhile, the target announcement information and the users are analyzed based on the keyword data of the target announcement information and the interestingness parameter of each keyword to the users, and the bid inviting and bidding information recommendation result is obtained.
Drawings
FIG. 1 is a schematic flow chart of a method for recommending bid information of an electronic bid transaction platform in an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating analysis of a fused interestingness parameter of each keyword of target advertisement information to a user in an embodiment of the present application;
FIG. 3 is a schematic flowchart illustrating a process of obtaining interestingness parameters of different keyword data of historical bulletin information of a user in the embodiment of the present application;
fig. 4 is a schematic structural diagram of a bid information recommendation system of an electronic bid transaction platform in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
The embodiment of the application provides a method for recommending bidding information of an electronic bidding transaction platform, which comprises the following steps:
and 4, recommending the target notice information to the user based on the interestingness ranking.
In the embodiment of the application, the extraction effectiveness of the characteristic data of the target announcement information is improved through two keyword data acquisition methods, meanwhile, the target announcement information and the users are analyzed based on the keyword data of the target announcement information and the interestingness parameter of each keyword to the users, and the bid inviting and bidding information recommendation result is obtained.
Further, in step 1, performing matching search based on the target advertisement information and a preset keyword lexicon to obtain first keyword data of the target advertisement information, including:
extracting keyword labels based on historical announcement information, and establishing a preset keyword lexicon based on the extracted keywords;
carrying out data cleaning on the target notice information, and removing a company name, a region name and a person name in the target notice;
and matching and searching in a preset keyword word bank based on the cleaned target announcement information to obtain first keyword data of the target announcement information.
In the embodiment of the application, the keyword word bank is constructed based on historical data, and words in the target announcement information are matched and searched in the preset keyword word bank, so that word segmentation and keyword screening of the target announcement information are realized.
Further, in the step 2, generating the second keyword data of the target advertisement information based on analyzing the target advertisement information itself includes:
based on historical bulletin information, calculating high-frequency words appearing in the historical bulletins through a first preset algorithm, and establishing a white list word bank based on the high-frequency words, wherein the first preset algorithm is realized based on an ITF algorithm;
acquiring verbs and nouns in the target announcement information by utilizing a second preset algorithm based on the cleaned target announcement information to form a first verb and noun set, wherein the second preset algorithm is realized based on a Harvey large word segmenter;
filtering and screening verbs and nouns in the first verb and noun set by adopting a white list word library to form a second verb and noun set;
and combining the verbs and the nouns in the second action and noun set to form second keyword data.
In the embodiment of the application, another method for extracting second keyword data of target announcement information is provided for the condition that keyword data in the target announcement information cannot be obtained by keyword matching of preset keyword lexicons established in advance for the target announcement information, when a white list lexicon is established by high-frequency words in historical announcement information, dynamic terms in the target announcement information are extracted and filtered in real time, words in the white list lexicon are reserved, a second dynamic term set and second keyword data are formed, the success rate and the comprehensiveness of extracting the keyword data from the target announcement information are improved, in one implementation mode, the first keyword data and the second keyword data can be respectively extracted from the target announcement information by two keyword extraction methods, and accurate extraction of the target announcement information is achieved.
Further, in step 3, analyzing the interestingness parameter of each keyword to the user based on the first keyword data or the second keyword data of the target advertisement information includes:
and step 35, comparing and analyzing the first keyword data or the second keyword data of the target notice information and the interest pictures of the keywords of the user, and analyzing the fusion interest degree parameter of each keyword to the user.
In the embodiment of the application, the keyword interest portrait of the user is generated based on different interest degree data of the user through the historical announcement information and the operation behavior of the user on the announcement information in the historical record, and whether the target announcement information is recommended to the user is further analyzed based on the keyword interest portrait of the user.
Further, in the step 33, obtaining the interest level parameters of the user for different keyword data of the historical advertisement information based on the operation behavior of the user for the advertisement information in the historical record and the mapping relationship includes:
It can be understood that when the user operates the announcement information historically, different interest levels of the same type of announcement information in different periods may occur, for example, the user is most interested in engineering buildings and building material decorations in a certain period of time, and often operates the bidding, and then the user is most interested in power electronics in a certain period of time, and often operates the bidding, and the user is not interested in engineering buildings and building material decorations as much as the power electronics, and only clicks and browses the operation.
For the situation, different keywords having the same first interestingness parameter are classified into the same set in the present application, and the keywords in the same first set are further classified into a plurality of first sub-classes, and it is measured whether the type and the similar type corresponding to each first sub-class will appear in a plurality of different first sets at the same time, and if so, the types and the similar types corresponding to the first sub-classes appearing in a plurality of different first sets at the same time are merged and re-classified into the modified belonging set. It can be understood that, in the embodiment of the present application, the interestingness parameter of the user for obtaining different keyword data of the historical announcement information is updated in real time based on the operation behavior recently occurred by the user, so that the dynamic classification of the interestingness parameter of the user keyword is realized. Furthermore, a user keyword interest portrait is constructed based on interest degree parameters of different keyword data of the historical bulletin information of the user, the constructed user keyword interest portrait is dynamically changed in real time, and real-time performance and effectiveness of construction of the user keyword interest portrait are achieved.
Further, in step 334, when the similarity of the first subclass and the second subclass distributed in the two different sets is smaller than the first preset similarity threshold, performing secondary analysis on the first subclass and the second subclass to correct the belonged sets of the first subclass and the second subclass, including:
step 3341, based on the first subclasses in all the first sets, for different first subclasses distributed in different sets and having a similarity smaller than a first preset similarity threshold, acquiring time when a user operates the announcement information of the source to which the keyword belongs in the different first subclasses, and counting frequency when the user operates the announcement information of the source to which the keyword belongs in the different first subclasses in the same time period;
step 3342, determining modified sets distributed in different first subclasses of different sets, of which the similarity is smaller than a first preset similarity threshold, based on the time and frequency data of the operation behavior;
step 3343, merging the distribution with similarity smaller than the first preset similarity threshold in different first subclasses of different sets, and classifying the merged distribution into the modified set.
It can be understood that, the modified belonged sets distributed in different first subclasses of different sets, where the similarity is smaller than the first preset similarity threshold, determined based on the time and frequency data of the occurrence of the operation behavior may be the modified belonged sets of the first subclasses, where the frequency data of the same time period is larger as the time is closer to the current time, the recent interest degree of the user in the category of the keyword is closer to the current time, and the operation behavior of the user shows the interest degree of the user as the frequency data of the same time period is larger.
Further, in step 34, constructing a user keyword interest representation based on the interest parameters of the user for different keyword data of the historical advertisement information, including:
step 341, sorting the keyword data according to the time of the user operating the announcement information corresponding to the keyword data;
step 342, regarding the sorted keyword data, classifying the keyword data based on the announcement information type represented by the keyword data and generating third label data based on the interestingness parameter as first label data and the time data as second label data, and generating a user keyword interest representation based on the first label data, the second label data and the third label data, wherein the weight of each keyword in the user keyword interest representation is determined based on the first label data, the second label data and the third label data, and the weight of each keyword in the user keyword interest representation is:wherein, ω is 0 Is a weight base value, t is the current second label data, n is the number of keyword data having the same third label data, t s Is the second label data of the s-th keyword data among the keyword data having the same third label data, t 0 Is the decay factor of the user's keyword interests over time.
Further, in the step 35, performing comparative analysis on the first keyword data or the second keyword data of the target advertisement information and the user keyword interest representation, and analyzing a fusion interest degree parameter of each keyword to the user, includes:
step 351, acquiring keywords in the user keyword interest image and the weights of the keywords;
step 352, searching the keyword data in the user keyword interest portrait based on the first keyword data or the second keyword data for the occurrence frequency and the occurrence position of the keyword data in the user keyword interest portrait;
and 353, calculating a fusion interest degree parameter of the keyword data to the user based on the weight of the keyword at the position appearing in the user keyword interest portrait.
Based on the method for recommending the bid information of the electronic bid transaction platform, the embodiment of the application further provides a system for recommending the bid information of the electronic bid transaction platform, and the system comprises:
the system comprises a first keyword acquisition unit, a first search unit and a second search unit, wherein the first keyword acquisition unit is used for receiving target announcement information on a trading platform, performing matching search by combining a preset keyword lexicon based on the target announcement information and acquiring first keyword data of the target announcement information;
the second keyword acquisition unit is used for generating second keyword data of the target notice information based on the analysis of the target notice information when the matching search result is empty;
the user interest degree parameter calculating unit is used for analyzing interest degree parameters of each keyword to the user based on first keyword data or second keyword data of the target notice information, and the interest degree parameters of each keyword to the user are obtained based on interest degree labels of the user to the keywords;
and the information recommending unit is used for recommending the target notice information to the user based on the interestingness sorting.
The specific limitations of the electronic bidding transaction platform bidding information recommendation system can be referred to the above limitations on the electronic bidding transaction platform bidding information recommendation method, which are not described herein again. Each unit in the electronic bidding trading platform bidding information recommendation system can be wholly or partially realized by software, hardware and a combination thereof. The units may be embedded in hardware or independent from a processor in the computer device, or may be stored in a memory in the computer device in software, so that the processor can call and execute operations corresponding to the units.
Based on the method for recommending the bid information by the electronic bid transaction platform, an embodiment of the present application further provides a computer readable storage medium, on which a program is stored, where the program is executed by a processor to implement the method for recommending the bid information by the electronic bid transaction platform.
Specifically, the computer-readable storage medium includes: permanent and non-permanent, removable and non-removable media may be tangible devices that retain and store instructions for use by an instruction execution apparatus. The computer-readable storage medium includes: electronic memory devices, magnetic memory devices, optical memory devices, electromagnetic memory devices, semiconductor memory devices, and any suitable combination of the foregoing.
The present invention is not limited to the above-described embodiments, and various modifications made by those skilled in the art without inventive skill from the above-described conception fall within the scope of the present invention.
Claims (10)
1. A bid information recommendation method for an electronic bid transaction platform is characterized by comprising the following steps:
receiving target announcement information on a trading platform, and performing matching search by combining a preset keyword lexicon based on the target announcement information to obtain first keyword data of the target announcement information;
when the matching search result is empty, generating second keyword data of the target announcement information based on the analysis of the target announcement information;
analyzing an interest degree parameter of each keyword to the user based on first keyword data or second keyword data of the target announcement information, wherein the interest degree parameter of each keyword to the user is obtained based on interest degree labels of the user to the keywords;
and recommending the target announcement information to the user based on the interestingness ranking.
2. The method for recommending bidding information of an electronic bidding transaction platform according to claim 1, wherein the step of performing a matching search based on the target advertisement information in combination with a preset keyword lexicon to obtain first keyword data of the target advertisement information comprises:
extracting keyword labels based on historical announcement information, and establishing a preset keyword lexicon based on the extracted keywords;
carrying out data cleaning on the target notice information, and removing a company name, a region name and a person name in the target notice;
and matching and searching in a preset keyword word bank based on the cleaned target announcement information to obtain first keyword data of the target announcement information.
3. The method for recommending bid information of an electronic bid trading platform according to claim 1, wherein the generating of the second keyword data of the target advertisement information based on analyzing the target advertisement information itself comprises:
based on the historical announcement information, calculating high-frequency words appearing in the historical announcement through a first preset algorithm, and establishing a white list word bank based on the high-frequency words;
obtaining verbs and nouns in the target announcement information by utilizing a second preset algorithm based on the cleaned target announcement information to form a first verb and noun set;
filtering and screening verbs and nouns in the first verb and noun set by adopting a white list word library to form a second verb and noun set;
and combining the verbs and the nouns in the second verb-noun set to form second keyword data.
4. The method as claimed in claim 1, wherein the analyzing the interest parameter of each keyword for the user based on the first keyword data or the second keyword data of the target advertisement information comprises:
acquiring a mapping relation between pre-established operation behaviors of a user on the announcement information and the interest degree of the user on the announcement information;
extracting first keyword data or second keyword data for historical bulletin information;
acquiring interest parameters of different keyword data of the historical bulletin information from the user based on the operation behavior of the user on the bulletin information in the historical record and the mapping relation;
constructing a user keyword interest portrait based on interest degree parameters of different keyword data of the historical bulletin information of the user;
and comparing and analyzing the first keyword data or the second keyword data of the target announcement information and the interest portrait of the user keyword, and analyzing the fusion interest degree parameter of each keyword to the user.
5. The method for recommending bidding information of an electronic bidding transaction platform according to claim 1, wherein the step of obtaining the interestingness parameter of the user in relation to different keyword data of the historical bulletin information based on the operation behavior of the user on the bulletin information in the historical record and the mapping relationship comprises:
acquiring a first interestingness parameter of the user on different keyword data of the historical bulletin information based on the operation behavior of the user on the bulletin information in the historical record and the mapping relation;
dividing different keywords with the same first interestingness parameter into the same set, recording the keywords as a first set, and labeling the first interestingness parameter for the first set;
performing text semantic recognition and classification based on keywords in the same first set to obtain a plurality of first subclasses in the same first set;
performing similarity analysis based on the first subclasses in all the first sets, and performing secondary analysis on different first subclasses of different sets to correct the belonged sets of the different first subclasses of the different sets when the similarity of the different first subclasses distributed in the different sets is smaller than a first preset similarity threshold;
and labeling a second interestingness parameter for the keywords in the set based on the first interestingness parameter labeled by the set based on the corrected set.
6. The method for recommending bidding information of an electronic bidding trading platform according to claim 5, wherein the secondary analysis of the first and second subclasses to modify the belonging sets of the first and second subclasses when the similarity of the first and second subclasses distributed in the two different sets is less than a first preset similarity threshold comprises:
based on first subclasses in all the first sets, acquiring time of a user for operating announcement information of a source to which a keyword belongs in different first subclasses for different first subclasses distributed in different sets, of which the similarity is smaller than a first preset similarity threshold, and counting frequency of the user for operating announcement information of the source to which the keyword belongs in the different first subclasses in the same time period;
determining modified sets distributed on different first subclasses of different sets, wherein the similarity is smaller than a first preset similarity threshold value, based on the time and frequency data of the operation behaviors;
and merging the distribution with the similarity smaller than a first preset similarity threshold in different first subclasses of different sets, and classifying the distribution into the corrected set.
7. The method for recommending bidding information of an electronic bidding transaction platform according to claim 4, wherein the constructing a user keyword interest representation based on the interest parameters of the user in different keyword data of the historical bulletin information comprises:
sorting the keyword data according to the time of the operation behavior of the user on the announcement information corresponding to the keyword data;
for the sorted keyword data, the interestingness parameter is used as first labeled data, the time data is used as second labeled data, the keyword data are classified based on the announcement information type represented by the keyword data to generate third labeled data, a user keyword interest portrait is generated based on the first labeled data, the second labeled data and the third labeled data, the weight of each keyword in the user keyword interest portrait is determined based on the first labeled data, the second labeled data and the third labeled data, and the weight of each keyword in the user keyword interest portrait is as follows:wherein, ω is 0 Is a weight base value, t is the current second label data, n is the number of keyword data having the same third label data, t s Is the second label data of the s-th keyword data among the keyword data having the same third label data, t 0 Is a decay factor of the user's keyword interests over time.
8. The method as claimed in claim 4, wherein the step of comparing the first keyword data or the second keyword data based on the target advertisement information with the user keyword interest representation to analyze the fused interest degree parameter of each keyword to the user comprises:
acquiring keywords in a keyword interest image of a user and weights of the keywords;
searching the keyword data in the user keyword interest portrait based on the first keyword data or the second keyword data, wherein the times and the positions of the keyword data in the user keyword interest portrait are searched;
and calculating a fusion interest degree parameter of the keyword data to the user based on the weight of the keyword at the position appearing in the user keyword interest portrait.
9. An electronic bidding transaction platform bidding information recommendation system, comprising:
the system comprises a first keyword acquisition unit, a first search unit and a second search unit, wherein the first keyword acquisition unit is used for receiving target announcement information on a trading platform, performing matching search by combining a preset keyword lexicon based on the target announcement information and acquiring first keyword data of the target announcement information;
the second keyword acquisition unit is used for generating second keyword data of the target notice information based on the analysis of the target notice information when the matching search result is empty;
the user interest degree parameter calculating unit is used for analyzing interest degree parameters of each keyword to the user based on first keyword data or second keyword data of the target notice information, and the interest degree parameters of each keyword to the user are obtained based on interest degree labels of the user to the keywords;
and the information recommending unit is used for recommending the target notice information to the user based on the interestingness sorting.
10. A computer-readable storage medium on which a program is stored, which program, when being executed by a processor, is adapted to carry out the recommendation method according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210590392.6A CN115098766B (en) | 2022-05-26 | 2022-05-26 | Bidding information recommendation method and system for electronic bidding transaction platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210590392.6A CN115098766B (en) | 2022-05-26 | 2022-05-26 | Bidding information recommendation method and system for electronic bidding transaction platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115098766A true CN115098766A (en) | 2022-09-23 |
CN115098766B CN115098766B (en) | 2023-05-30 |
Family
ID=83288274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210590392.6A Active CN115098766B (en) | 2022-05-26 | 2022-05-26 | Bidding information recommendation method and system for electronic bidding transaction platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115098766B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115905489A (en) * | 2022-11-21 | 2023-04-04 | 广西建设职业技术学院 | Method for providing bid and bid information search service |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165348A (en) * | 2018-08-21 | 2019-01-08 | 麦格创科技(深圳)有限公司 | A kind of bidding information recommendation method, system and server |
CN110059246A (en) * | 2019-03-15 | 2019-07-26 | 安徽省优质采科技发展有限责任公司 | Intelligent match system |
CN110148043A (en) * | 2019-03-01 | 2019-08-20 | 安徽省优质采科技发展有限责任公司 | The bid and purchase information recommendation system and recommended method of knowledge based map |
WO2020057022A1 (en) * | 2018-09-18 | 2020-03-26 | 深圳壹账通智能科技有限公司 | Associative recommendation method and apparatus, computer device, and storage medium |
US20210157860A1 (en) * | 2019-04-30 | 2021-05-27 | Beijing Bytedance Network Technology Co., Ltd. | Object recommendation method and apparatus, storage medium and terminal device |
-
2022
- 2022-05-26 CN CN202210590392.6A patent/CN115098766B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165348A (en) * | 2018-08-21 | 2019-01-08 | 麦格创科技(深圳)有限公司 | A kind of bidding information recommendation method, system and server |
WO2020057022A1 (en) * | 2018-09-18 | 2020-03-26 | 深圳壹账通智能科技有限公司 | Associative recommendation method and apparatus, computer device, and storage medium |
CN110148043A (en) * | 2019-03-01 | 2019-08-20 | 安徽省优质采科技发展有限责任公司 | The bid and purchase information recommendation system and recommended method of knowledge based map |
CN110059246A (en) * | 2019-03-15 | 2019-07-26 | 安徽省优质采科技发展有限责任公司 | Intelligent match system |
US20210157860A1 (en) * | 2019-04-30 | 2021-05-27 | Beijing Bytedance Network Technology Co., Ltd. | Object recommendation method and apparatus, storage medium and terminal device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115905489A (en) * | 2022-11-21 | 2023-04-04 | 广西建设职业技术学院 | Method for providing bid and bid information search service |
CN115905489B (en) * | 2022-11-21 | 2023-11-17 | 广西建设职业技术学院 | Method for providing bidding information search service |
Also Published As
Publication number | Publication date |
---|---|
CN115098766B (en) | 2023-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7627559B2 (en) | Context-based key phrase discovery and similarity measurement utilizing search engine query logs | |
CN106919619B (en) | Commodity clustering method and device and electronic equipment | |
US7996440B2 (en) | Extraction of attributes and values from natural language documents | |
Cheng et al. | Multimedia features for click prediction of new ads in display advertising | |
US8521745B2 (en) | Extraction of attributes and values from natural language documents | |
US20220405607A1 (en) | Method for obtaining user portrait and related apparatus | |
CN109325179B (en) | Content promotion method and device | |
CN108777701B (en) | Method and device for determining information audience | |
WO2010081238A1 (en) | Method and system for document classification | |
CN105809478B (en) | Labeling method and system for advertisement label | |
CN108415961A (en) | A kind of advertising pictures recommendation method and device | |
CN110674620A (en) | Target file generation method, device, medium and electronic equipment | |
CN111782793A (en) | Intelligent customer service processing method, system and equipment | |
CN113516496A (en) | Advertisement conversion rate pre-estimation model construction method, device, equipment and medium thereof | |
CN114201680A (en) | Method for recommending marketing product content to user | |
JP2002189925A (en) | Advertisement managing server on internet | |
CN115098766B (en) | Bidding information recommendation method and system for electronic bidding transaction platform | |
CN110427545B (en) | Information pushing method and system | |
US20040098271A1 (en) | Method and system for tracking the lifecycles of technology items | |
CN113837824A (en) | Information pushing method and system | |
KR102404247B1 (en) | Customer management system | |
CN112328881A (en) | Article recommendation method and device, terminal device and storage medium | |
CN112182244A (en) | Brand knowledge graph construction method and device and terminal | |
CN110990692A (en) | Data processing method and device based on portrait analysis | |
CN114996579A (en) | Information pushing method and device, electronic equipment and computer readable medium |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 201, Building A11, Financial Port Center, No. 4872 Huizhou Avenue, Baohe District, Hefei City, Anhui Province, 230092 Applicant after: Anhui High Quality Mining Technology Development Co.,Ltd. Address before: Room 401, Yunhui Pavilion Commercial Complex, Intersection of Baohe Avenue and Wangnan Road, Baohe District, Hefei City, Anhui Province 230041 Applicant before: Anhui High Quality Mining Technology Development Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |