CN114943279A - Method, device and system for predicting bidding cooperative relationship - Google Patents
Method, device and system for predicting bidding cooperative relationship Download PDFInfo
- Publication number
- CN114943279A CN114943279A CN202210471354.9A CN202210471354A CN114943279A CN 114943279 A CN114943279 A CN 114943279A CN 202210471354 A CN202210471354 A CN 202210471354A CN 114943279 A CN114943279 A CN 114943279A
- Authority
- CN
- China
- Prior art keywords
- similarity
- information
- tenderer
- tenderers
- bidder
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
- G06F40/295—Named entity recognition
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a method, equipment and a system for predicting bidding cooperative relationship. The prediction method comprises the following steps: acquiring a first similarity between any two tenderers and a second similarity between any two bidders; determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships; and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity. According to the technical scheme, probability information of cooperation between the tenderer and the bidder is predicted based on the first similarity between the two tenderers, the second similarity between the two bidders and the historical cooperative relationship between the tenderer and the bidder, so that the accuracy of prediction of the cooperative relationship between the tenderers and the bidder is effectively improved, then recommendation operation of the tenderer and the bidder is conveniently performed based on the probability information, and the practicability of the method is further improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method, a device, and a system for predicting a bidding cooperative relationship.
Background
Currently, in the field of bidding technology, there are few schemes for predicting the cooperative relationship between the tenderers, and there are few prediction schemes that predict based on some historical statistics of the cooperative relationship, such as: if supplier A and enterprise A have historically worked M times, and enterprise A have historically worked N times, then if M > N, then the likelihood of cooperation of A and B may be considered greater than the likelihood of cooperation of A and C.
However, the operation of predicting the collaboration based on the direct historical collaboration data is simple and rough, and the number of the parties involved in the direct collaboration is small, so the implementation of predicting the collaboration is poor in practicability and applicability.
Disclosure of Invention
The embodiment of the application provides a method, equipment and a system for predicting a bidding cooperative relationship, which can improve the practicability of predicting the bidding cooperative relationship and ensure the application range of the prediction method.
In a first aspect, an embodiment of the present application provides a method for predicting a bidding partnership, including:
acquiring a first similarity between any two tenderers and a second similarity between any two bidders;
determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships;
and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
In a second aspect, an embodiment of the present application provides a device for predicting bidding partnership, including:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first similarity between any two tenderers and a second similarity between any two tenderers;
the first determination module is used for determining the historical cooperative relationship between the tenderer and the bidder and the third similarity between any two historical cooperative relationships;
and the first processing module is used for predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method for predicting a bidding partnership as described above in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, which makes a computer implement the method for predicting a bidding partnership shown in the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer program product, including: a computer program, which, when executed by a processor of an electronic device, causes the processor to perform the steps of the method for predicting a bidding partnership as described above in the first aspect.
In a sixth aspect, an embodiment of the present invention provides a method for predicting an association relationship, including:
acquiring a first similarity between any two first-class objects and a second similarity between any two second-class objects;
determining historical association relations between the first class of objects and the second class of objects and a third similarity between any two historical association relations;
and predicting probability information of the first class of objects and the second class of objects to be associated based on the first similarity, the second similarity and the third similarity.
In a seventh aspect, an embodiment of the present invention provides an apparatus for predicting an association relationship, including:
the second acquisition module is used for acquiring a first similarity between any two first-class objects and a second similarity between any two second-class objects;
the second determining module is used for determining the historical incidence relation between the first class of objects and the second class of objects and the third similarity between any two historical incidence relations;
and the second processing module is used for predicting probability information of the association between the first class of objects and the second class of objects based on the first similarity, the second similarity and the third similarity.
In an eighth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method for predicting the association relationship as shown in the sixth aspect.
In a ninth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, and the computer program enables a computer to execute a method for predicting an association relationship shown in the above sixth aspect.
In a tenth aspect, an embodiment of the present invention provides a computer program product, including: a computer program that, when executed by a processor of an electronic device, causes the processor to execute the steps in the method for predicting an association shown in the sixth aspect.
In an eleventh aspect, an embodiment of the present invention provides a system for predicting a bidding partnership, including:
the system comprises a request end, a prediction device and a display device, wherein the request end is used for displaying an interactive interface for predicting the cooperation relationship between a tenderer and a bidder, acquiring a plurality of tenderers and a plurality of bidders through the interactive interface and transmitting the plurality of tenderers and the plurality of bidders to the prediction device;
the prediction device is in communication connection with the request terminal and is used for receiving the plurality of tenderers and the plurality of bidders sent by the request terminal and acquiring a first similarity between any two tenderers and a second similarity between any two bidders; determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships; predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity, and sending the probability information of cooperation between the tenderer and the bidder to the request terminal;
and the request end is used for displaying probability information of cooperation between the tenderer and the bidder through the interactive interface.
According to the technical scheme provided by the embodiment of the application, the historical cooperative relationship between the tenderer and the bidder and the third similarity between any two historical cooperative relationships are determined by acquiring the first similarity between any two tenderers and the second similarity between any two bidders, and then the probability information of cooperation between the tenderer and the bidder is predicted based on the first similarity, the second similarity and the third similarity.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram illustrating a scenario of a method for predicting bidding partnership provided in an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for predicting bidding partnership provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating a process of obtaining a first similarity between any two tenderers and a second similarity between any two tenderers according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart illustrating a process for determining a third similarity between any two historical relationships according to an embodiment of the present application;
FIG. 4a is a schematic diagram of a construction bipartite graph according to an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating another method for predicting bidding partnership provided by an embodiment of the present application;
FIG. 6 is a flowchart illustrating a method for predicting bidding partnership in accordance with an exemplary embodiment of the present application;
FIG. 7 is a diagram illustrating a method for predicting bidding relations according to an exemplary embodiment of the present application;
fig. 8 is a flowchart illustrating a method for predicting an association relationship according to an embodiment of the present disclosure;
FIG. 9 is a schematic structural diagram of a device for predicting bidding partnership provided in an embodiment of the present application;
FIG. 10 is a schematic structural diagram of an electronic device corresponding to the apparatus for predicting bidding partnership shown in FIG. 9;
fig. 11 is a schematic structural diagram of an incidence relation predicting apparatus according to an embodiment of the present disclosure;
fig. 12 is a schematic structural diagram of an electronic device corresponding to the association relationship prediction apparatus shown in fig. 11;
fig. 13 is a schematic structural diagram of a system for predicting bidding partnership provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a" and "an" typically include at least two, but do not exclude the inclusion of at least one.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good 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 good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of additional like elements in the article or system in which the element is included.
In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.
In order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the following description is provided for the related technologies: in the field of bidding technology, there are few solutions for predicting the partnership between the bidders on the market, and there are few prediction solutions based on some historical statistics of the partnership, for example: if supplier A and enterprise A have historically worked M times, and enterprise A have historically worked N times, then if M > N, then the likelihood of cooperation of A and B may be considered greater than the likelihood of cooperation of A and C. However, the operation of predicting the collaboration based on only the direct historical collaboration data is relatively simple and rough, and the number of the parties involved in the direct collaboration is small, so the implementation of predicting the collaboration is not practical and meaningful.
In addition, the related art also provides another prediction method for realizing the cooperative relationship based on the collaborative filtering U2I2U algorithm of the user, for example: supplier A's business collaborates with first party business B, which has collaborated with supplier C, which has collaborated with first party business D, so that A and D can be considered as having a potential partnership even though A has not historically collaborated with first party business D.
The method for predicting the cooperative relationship by the collaborative filtering algorithm solves the problem of sparse historical cooperative relationship to a certain extent, but also has some problems in accuracy rate, which is particularly serious in the recommendation field of the bidding field. For example, supplier a is a supplier for IT services, and has been already collaborating with a certain hospital B about items for IT service purchase, while hospital B often collaborates with a certain medicine supplier C about items for medicine purchase, and C often collaborates with other hospital suppliers D, and IT is not suitable to recommend the first party D to supplier a directly.
In order to solve the above technical problem, the present embodiment provides a method, an apparatus, and a computer storage medium for predicting a bidding partnership. Referring to fig. 1, the main implementation of the method for predicting the bidding partnership is a device for predicting the bidding partnership, and the device for predicting the bidding partnership can be in communication connection with a request end to implement the operation for predicting the bidding partnership.
The requesting end may be any computing device with certain data transmission capability, and in specific implementation, the requesting end may be a mobile phone, a personal computer PC, a tablet computer, a set application program, and the like. In addition, the basic structure of the request side may include: at least one processor. The number of processors depends on the configuration and type of the requesting end. The request end may also include a Memory, which may be volatile, such as RAM, or non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or may include both types. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. Besides the processing unit and the memory, the request side also includes some basic configurations, such as a network card chip, an IO bus, a display component, some peripheral devices, and the like. Alternatively, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like. Other peripheral devices are well known in the art and will not be described in detail herein.
The device for predicting a bid-inviting partnership is a device capable of providing a prediction service of a bid-inviting partnership in a network virtual environment, and generally refers to a device for performing information planning and a prediction operation of a bid-inviting partnership using a network. In terms of physical implementation, the forecasting device for bidding partnership can be any device capable of providing computing services, responding to service requests, and performing processing, such as: can be cluster servers, regular servers, cloud hosts, virtual centers, and the like. The forecasting device for bidding cooperative relationship mainly comprises a processor, a hard disk, a memory, a system bus and the like, and is similar to a general computer architecture.
In the above embodiment, the requesting end may be in network connection with the forecasting apparatus in bidding partnership, and the network connection may be wireless or wired. If the requesting end is in communication connection with the prediction device of the bidding partnership, the network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), WiMax, 5G, and 6G.
In the embodiment of the application, a request end can acquire a plurality of tenderers and a plurality of bidders required for carrying out a cooperative relation prediction operation, and specifically, can acquire a plurality of tenderers and a plurality of bidders for carrying out the cooperative relation prediction operation based on an execution operation input by a user; alternatively, the requesting end may obtain a plurality of tenderers and a plurality of bidders for performing the partnership prediction operation by accessing a preset area. After the request terminal acquires the plurality of tenderers and the plurality of bidders needing to be subjected to the partnership prediction operation, the plurality of tenderers and the plurality of bidders needing to be subjected to the partnership prediction operation may be transmitted to the prediction device, so that the prediction device may acquire the plurality of tenderers and the plurality of bidders needing to be subjected to the partnership prediction operation and perform analysis processing on the plurality of tenderers and the plurality of bidders needing to be subjected to the partnership prediction operation.
The forecasting device for the bidding cooperative relationship is used for acquiring a first similarity between any two tenderers and a second similarity between any two tenderers, specifically, acquiring a plurality of tenderers and a plurality of bidders sent by a request end, analyzing any two tenderers to acquire the first similarity between any two tenderers, and similarly, analyzing any two bidders to acquire the second similarity between any two bidders.
In order to accurately predict the cooperation relationship between the tenderer and the bidder, besides the first similarity and the second similarity, the historical cooperation relationship between the tenderer and the bidder and the third similarity between any two historical cooperation relationships can be determined, then probability information of cooperation between the tenderer and the bidder can be predicted based on the first similarity, the second similarity and the third similarity, specifically, a machine learning model for predicting the cooperation probability of the tenderer and the bidder is trained in advance, and after the first similarity, the second similarity and the third similarity are obtained, the first similarity, the second similarity and the third similarity can be input into the machine learning model, so that the probability information output by the machine learning model can be obtained.
According to the technical scheme provided by the embodiment, the historical cooperative relationship between the tenderer and the bidder and the third similarity between any two historical cooperative relationships are determined by acquiring the first similarity between any two tenderers and the second similarity between any two bidders, and then the probability information of cooperation between the tenderer and the bidder is predicted based on the first similarity, the second similarity and the third similarity.
The following describes a method, an apparatus, and a computer storage medium for predicting bidding partnership provided in various embodiments of the present application in an exemplary application scenario. The features of the embodiments and examples described below may be combined with each other without conflict between the embodiments.
FIG. 2 is a schematic flowchart illustrating a method for predicting partnering relations according to an embodiment of the present disclosure; referring to fig. 2, the present embodiment provides a method for predicting tendering relations, and the implementation subject of the method may be a device for predicting tendering relations, wherein the device for predicting tendering relations may be implemented as software or a combination of software and hardware. Specifically, the method for predicting the bidding cooperative relationship may include:
step S201: a first similarity between any two tenderers and a second similarity between any two bidders are obtained.
Step S202: historical partnerships between the tenderers and the bidders and a third similarity between any two historical partnerships are determined.
Step S203: and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
The following is a detailed description of specific implementation processes and implementation effects of the above steps:
step S201: a first similarity between any two tenderers and a second similarity between any two bidders are obtained.
In the application scenario of bidding, there are multiple tenderers and multiple bidders, and different tenderers may correspond to the same or different bidding items. In order to accurately predict the bidding cooperative relationship, a first similarity between any two tenderers and a second similarity between any two tenderers may be obtained, where the first similarity may identify a similarity between the two tenderers in terms of bidding items, business management categories, and the like, and the second similarity may identify a similarity between the two tenderers in terms of bidding items, business management categories, and the like.
In this embodiment, a specific implementation manner of obtaining the first similarity between any two tenderers and the second similarity between any two tenderers is not limited, for example: the first similarity between any two tenderers and the second similarity between any two tenderers can be stored in a preset area, and when the tendering and bidding cooperative relationship needs to be predicted, the first similarity between any two tenderers and the second similarity between any two tenderers can be obtained by accessing the preset area. Or, the first similarity and the second similarity may be stored in a third device, and when the bidding partnership is required to be predicted, the first similarity between any two bidders and the second similarity between any two bidders may be actively or passively acquired through the third device.
In addition, the acquiring order of the first similarity and the second similarity in this embodiment is not limited, for example: first similarity between any two tenderers can be obtained, and then second similarity between any two bidders can be obtained; or the second similarity between any two bidders can be obtained first, and then the first similarity between any two tenderers can be obtained; alternatively, the first similarity between any two tenderers and the second similarity between any two bidders may be obtained simultaneously, and those skilled in the art may set or select them according to a specific application scenario or application requirement.
Step S202: historical partnerships between the tenderers and the bidders and a third similarity between any two historical partnerships are determined.
In the field of bidding, the cooperation relationship between the bidder and the bidder is not only related to the first similarity between any two bidders and the second similarity between any two bidders, but also related to the historical cooperation relationship between the bidder and the bidder, for example, the historical cooperation relationship 1 is that the category of cooperation between the bidder a and the bidder B is a building category, and the number of cooperation times is 4; the historical cooperation relation 2 is that the cooperation category of the tenderer A and the bidder C is an IT category, and the cooperation times are 2 times; the category of the historical cooperative relationship 3 in which the bidder a and the bidder D cooperate is a building category, and the number of cooperating times is 5, it is obvious that the similarity between the historical cooperative relationship 1 and the historical cooperative relationship 2 is different from the similarity between the historical cooperative relationship 1 and the historical cooperative relationship 3. Therefore, in order to be able to accurately perform the operation of predicting the tendering-bidding cooperative relationship, in addition to acquiring the first similarity between any two tenderers and the second similarity between any two tenderers, the historical cooperative relationship between the tenderers and the bidders and the third similarity between any two historical cooperative relationships may be determined.
In some examples, the historical partnerships between the tenderer and the bidder may be stored in a preset area, at which point determining the historical partnerships between the tenderer and the bidder may include: the historical cooperative relationship between the tenderer and the bidder can be obtained by accessing the preset area. In still other examples, determining historical partnerships between the tenderer and bidders may include: acquiring historical bid-winning announcements corresponding to the tenderers and/or bidders through a preset database or a preset data platform; after the historical winning bid announcements are acquired, the historical cooperative relationship between the tenderer and the bidder can be determined based on the historical winning bid announcements.
After determining the historical partnerships between the tenderers and the bidders, any two historical partnerships may be analyzed to determine a third similarity between any two historical partnerships. In some examples, determining a third degree of similarity between any two historical partnerships may include: and acquiring cooperation characterization vectors (including cooperation categories, cooperation amount, cooperation times and the like) corresponding to any two historical cooperation relations, and determining a third similarity of any two historical cooperation relations based on the cooperation characterization vectors. Specifically, the machine learning model for determining the third similarity between any two historical relationships is trained in advance, and in this case, determining the third similarity between any two historical relationships may include: and acquiring a machine learning model for any two historical cooperative relations, and inputting any two historical cooperative relations into the machine learning model, so that the third similarity of any two historical cooperative relations output by the machine learning model can be obtained.
In other examples, since the number of historical partnerships between different bidders may be high, any two historical partnerships may include the following four categories: the two historical cooperative relationships comprise the same tenderer, the two historical cooperative relationships comprise the same bidder, the two historical cooperative relationships comprise the same tenderer and bidder, and the two historical cooperative relationships comprise different tenderers and bidders. When the cooperation relationship between the tenderer and the bidder is predicted, because the influence degree of the two historical cooperation relationships comprising different tenderers and different bidders on the prediction of the cooperation relationship between the tenderer and the bidder is small, the calculation operation of the similarity of the historical cooperation relationships is not needed. At this time, determining the third degree of similarity between any two historical partnerships may include: determining any two historical partnerships including different tenderers and different bidders based on all historical partnerships; and acquiring a third similarity between any two historical cooperative relations except any two historical cooperative relations comprising different tenderers and different bidders, so that the data quantity with smaller influence degree on the prediction of the cooperative relations can be filtered, and the quality and efficiency of calculating the third similarity can be improved.
Step S203: and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
After the first similarity, the second similarity and the third similarity are obtained, the first similarity, the second similarity and the third similarity may be analyzed to predict probability information of cooperation between the tenderer and the bidder. In some examples, predicting probability information that the tenderer cooperates with the bidder based on the first similarity, the second similarity, and the third similarity may include: and acquiring a machine learning model for analyzing and processing the first similarity, the second similarity and the third similarity, and inputting the first similarity, the second similarity and the third similarity into the machine learning model, so that probability information of cooperation between the tenderer and the bidder output by the machine learning model can be acquired.
In other examples, predicting probability information that the tenderer cooperates with the bidder based on the first similarity, the second similarity, and the third similarity may include: acquiring weight information corresponding to the first similarity, the second similarity and the third similarity respectively; and carrying out weighted summation on the first similarity, the second similarity and the third similarity based on the weight information corresponding to the first similarity, the second similarity and the third similarity respectively to obtain probability information of cooperation between the tenderer and the bidder.
Specifically, since the first similarity is used to represent the degree of similarity between any two tenderers, the second similarity is used to represent the degree of similarity between any two tenderers, and the third similarity is used to represent the degree of similarity between any two historical cooperative relationships, in the process of predicting the tendering and bidding cooperative relationships, the degrees of influence of the first similarity, the second similarity, and the third similarity on probability information of the tendering and bidding cooperative relationships are different, therefore, weight information corresponding to the first similarity, the second similarity, and the third similarity may be obtained first, and the weight information may be configured in advance, or may be configured according to application requirements or design requirements of a user.
After the weight information corresponding to the first similarity, the second similarity and the third similarity is acquired, the first similarity, the second similarity and the third similarity may be weighted and summed based on the weight information corresponding to the first similarity, the second similarity and the third similarity, so that probability information of cooperation between the tenderer and the bidder may be acquired.
The method for predicting tendering and bidding cooperative relationship provided by this embodiment obtains a first similarity between any two tenderers and a second similarity between any two tenderers, then determines a historical cooperative relationship between the tenderers and a third similarity between any two historical cooperative relationships, and predicts probability information of cooperation between the tenderers and the bidders based on the first similarity, the second similarity and the third similarity, because the probability information is determined by the first similarity, the second similarity and the third similarity, not only is the accuracy of predicting the tendering and bidding cooperative relationship improved, but also the prediction method does not limit whether there is a direct cooperative relationship between the tenderers and the bidders, thereby effectively expanding the application range of the prediction method, and in addition, after obtaining the probability information of cooperation between the tenderers and the bidders, and recommendation operation of the tenderer and the bidder can be carried out based on the probability information, so that the practicability of the prediction method is further improved.
FIG. 3 is a schematic flow chart illustrating a process of obtaining a first similarity between any two tenderers and a second similarity between any two tenderers according to an embodiment of the present disclosure; on the basis of the foregoing embodiment, referring to fig. 3, this embodiment provides an implementation manner for obtaining the first similarity and the second similarity based on the characterization information corresponding to the tenderer and the characterization information corresponding to the bidder, and specifically, the obtaining the first similarity between any two tenderers and the second similarity between any two bidders in this embodiment may include:
step S301: and acquiring first characterization information corresponding to each tenderer and second characterization information corresponding to each bidder, wherein the first characterization information is at least used for identifying the operating characteristics of the tenderer, and the second characterization information is at least used for identifying the operating characteristics of the bidder.
Different tenderers correspond to different first characterization information, different bidders correspond to different second characterization information, and the first characterization information and the second characterization information may include at least one of: enterprise categories, business areas, patent information, recruitment information, historical bid-winning announcements, it is understood that the first characterizing information and the second characterizing information may include not only the information content described above, but also other information, such as: the first characterization information and the second characterization information may also include enterprise profile information, enterprise credit information, and the like.
The first similarity may be determined based on the first characterization information of the tenderers, and the second similarity is determined based on the second characterization information of the bidders, so that the first similarity of any two tenderers and the second similarity of any two bidders may be accurately obtained, the first characterization information corresponding to each tenderer and the second characterization information corresponding to each bidder may be obtained first, specifically, the first characterization information corresponding to each tenderer and the second characterization information corresponding to each bidder may be stored in a preset database or a preset data platform, and the first characterization information corresponding to each tenderer and the second characterization information corresponding to each bidder may be obtained by accessing the preset database and the preset data platform.
Step S302: and determining the first similarity based on the first characterization information corresponding to any two tenderers.
After the first characterization information corresponding to any two tenderers is acquired, the first characterization information corresponding to any two tenderers may be analyzed to determine the first similarity. In some examples, a machine learning model for obtaining similarity of any two token information is trained in advance, and after first token information corresponding to any two tenderers is obtained, the first token information corresponding to any two tenderers may be input into the machine learning model, so that the first similarity output by the machine learning model may be obtained.
In other examples, determining the first similarity based on the first characterizing information corresponding to each of any two tenderers may include: acquiring a first characterization vector corresponding to the first characterization information; and determining the first similarity based on the first characterization vectors corresponding to any two tenderers.
After the first characterization information corresponding to any two tenderers is obtained, the first characterization information may be processed by using a text forwarding algorithm or a preset machine learning model to obtain a first characterization vector corresponding to the first characterization information, and it can be understood that different first characterization information may correspond to different first characterization vectors.
In other examples, obtaining the first token vector corresponding to the first token information may include: performing word segmentation processing on the first representation information to obtain a plurality of keywords corresponding to the first representation information; determining word vectors corresponding to the plurality of keywords respectively; and determining a first characterization vector based on the word vectors corresponding to all the keywords.
After the first representation information is obtained, word segmentation processing can be performed on the first representation information, so that a plurality of keywords corresponding to the first representation information can be obtained, and the plurality of keywords can be at least one part of the first representation information; then, the plurality of keywords may be analyzed to determine word vectors corresponding to the plurality of keywords, and it is understood that different keywords may correspond to different word vectors. After the word vectors corresponding to all the keywords are obtained, the word vectors corresponding to all the keywords may be analyzed to determine a first characterization vector, and in some examples, the word vectors corresponding to all the keywords may be spliced to obtain the first characterization vector.
When the first token vector is determined based on the word vectors corresponding to all the keywords, because the character lengths of all the generated keywords may be different, the token dimensions of the word vectors corresponding to the obtained keywords are different, at this time, in order to ensure the quality and efficiency of obtaining the first token vector, whether the dimensions of the word vectors of all the keywords are aligned or not may be detected first, when the word vectors of all the keywords are not aligned, the word vectors of all the keywords may be aligned first, and then the word vectors corresponding to all the keywords may be spliced, so that the first token vector may be obtained.
In other examples, determining the first token vector based on the word vectors corresponding to all the keywords may include: acquiring weight information corresponding to the word vectors; and carrying out weighted summation on the word vectors based on the weight information to obtain a first characterization vector.
Because different word vectors are used for representing the importance degrees of different keywords, in order to accurately improve the accuracy and reliability of determining the first representation vector, the weight information corresponding to the word vectors may be obtained, and specifically, the obtaining of the weight information corresponding to the word vectors may include: acquiring weight information corresponding to the keywords, wherein different keywords can correspond to the same or different weight information, and then determining the weight information corresponding to the keywords as the weight information of corresponding word vectors. Or, obtaining the weight information corresponding to the word vector may include: acquiring word frequency and reverse file frequency corresponding to each keyword; and determining weight information corresponding to the word vector based on the word frequency and the reverse file frequency, wherein the weight information is positively correlated with the word frequency and the reverse file frequency.
Specifically, after the first representation information is obtained, the word frequency and the reverse file frequency corresponding to each keyword may be obtained based on the historical bulletin information corresponding to the first representation information, where the word frequency may be (the number of occurrences of the keyword in an article)/(the number of occurrences of the keyword with the largest number of occurrences in the article), and the reverse text frequency may represent the reciprocal of the frequency of occurrences of the keyword in all the articles. After the word frequency and the inverse text frequency are obtained, the word frequency and the inverse text frequency may be processed to obtain the word frequency and the inverse file frequency, for example: the word frequency and the inverse text frequency may be weighted and summed to obtain the word frequency and the inverse text frequency.
After the word frequency and the reverse text frequency are obtained, the weight information corresponding to the word vector can be determined based on the word frequency and the reverse file frequency, the weight information is positively correlated with the word frequency and the reverse file frequency, specifically, the mapping relation between the word frequency and the reverse file frequency and the weight information is configured in advance, and then the weight information corresponding to the word vector can be determined according to the word frequency and the reverse file frequency and the mapping relation, so that the accuracy and reliability of determining the weight information are effectively ensured; after the weight information is acquired, the word vectors may be subjected to weighted summation based on the weight information, so that the first token vector may be stably obtained.
Step S303: and determining a second similarity based on the second characterization information corresponding to any two bidders.
Wherein, based on the second characterization information corresponding to any two bidders, determining the second similarity may include: acquiring a second characterization vector corresponding to the second characterization information; and determining a second similarity based on the second characterization vectors corresponding to any two bidders.
In some examples, obtaining a second token vector corresponding to the second token information may include: performing word segmentation processing on the second representation information to obtain a plurality of keywords corresponding to the second representation information; determining word vectors corresponding to the keywords respectively; and determining a second characterization vector based on the word vectors corresponding to all the keywords.
In some examples, determining the second token vector based on the word vectors corresponding to all the keywords includes: acquiring weight information corresponding to the word vectors; and carrying out weighted summation on the word vectors based on the weight information to obtain a second characterization vector.
Obtaining the weight information corresponding to the word vector may include: acquiring word frequency and reverse file frequency corresponding to each keyword; and determining weight information corresponding to the word vector based on the word frequency and the reverse file frequency, wherein the weight information is positively correlated with the word frequency and the reverse file frequency.
Specifically, the specific implementation manner and implementation effect for determining the second similarity in this embodiment are similar to the specific implementation manner and implementation effect for determining the first similarity in the foregoing embodiment, and specific reference may be made to the above statements, and details are not repeated here.
It should be noted that the execution sequence of step S302 and step S303 in this embodiment is not limited to the execution sequence described in the above embodiment, and those skilled in the art may configure the steps according to specific application scenarios or application requirements, for example: step S302 may be performed after step S303, or step S302 may be performed simultaneously with step S303.
In this embodiment, by obtaining the first characterization information corresponding to each tenderer and the second characterization information corresponding to each bidder, then determining the first similarity based on the first characterization information corresponding to any two tenderers, and determining the second similarity based on the second characterization information corresponding to any two bidders, the accuracy and reliability of determining the first similarity and the second similarity are effectively achieved, and then accurately predicting the bidding cooperative relationship based on the obtained first similarity and the obtained second similarity, so that the practicability of the method is further improved.
FIG. 4 is a schematic flow chart illustrating a process for determining a third similarity between any two historical relationships according to an embodiment of the present application; on the basis of the foregoing embodiment, referring to fig. 4, this embodiment provides an implementation manner of determining a third similarity between any two historical relationships by using a bipartite graph, and specifically, the determining the third similarity between any two historical relationships in this embodiment may include:
step S401: and constructing a bipartite graph based on the historical cooperative relationship between the tenderer and the bidder, wherein the bipartite graph comprises a cooperative edge used for identifying the historical cooperative relationship between the tenderer and the bidder, and the cooperative edge corresponds to the cooperative feature.
After obtaining the historical cooperative relationship between the tenderer and the bidder, analyzing the historical cooperative relationship between the tenderer and the bidder to construct a bipartite graph, as shown in fig. 4a, a cooperative edge for identifying the historical cooperative relationship between the tenderer and the bidder may be included in the constructed bipartite graph, and the cooperative edge corresponds to a cooperative feature, which may include at least one of: category of cooperation, number of times of cooperation, amount of cooperation.
Step S402: and determining a third similarity between any two historical cooperative relations based on the cooperative features corresponding to the cooperative edges.
Since the cooperative sides correspond to the cooperative features for identifying the historical cooperative relationships, and different cooperative sides may correspond to different cooperative features, in order to accurately acquire the third similarity between any two historical cooperative relationships, after the historical cooperative relationships between the tenderer and the bidder are acquired, the third similarity may be determined based on the cooperative features corresponding to any two cooperative sides. Specifically, determining the third similarity between any two historical cooperative relationships based on the cooperative features corresponding to the cooperative edges may include: determining a cooperation feature vector corresponding to the cooperation edge; and determining the third similarity based on the cooperation feature vectors between any two historical cooperation relations, in some examples, obtaining cosine similarity between the cooperation feature vectors corresponding to any two historical cooperation relations, and determining the cosine similarity as the third similarity, thereby effectively ensuring the accuracy and reliability of determining the third similarity.
In the embodiment, the bipartite graph is constructed based on the historical cooperative relationship between the tenderer and the bidder, and then the third similarity between any two historical cooperative relationships is determined based on the cooperative features corresponding to the cooperative edges, so that the accuracy and reliability of determining the third similarity are effectively ensured, and the accuracy and reliability of predicting the tendering and bidding cooperative relationship based on the third similarity can be improved.
FIG. 5 is a flowchart illustrating another exemplary method for predicting a bidding partnership provided in an embodiment of the present application; on the basis of the above embodiment, referring to fig. 5, after predicting probability information of cooperation between the tenderer and the bidder, in order to improve the practicability of the method, a recommendation operation of the tenderer may be performed for the bidder based on the probability information, and at this time, the method in this embodiment may further include:
step S501: among the plurality of tenderers, at least one target tenderer cooperating with a bidder is determined based on the probability information.
After obtaining probability information that the tenderer cooperates with the bidder, at least one target tenderer cooperating with the bidder may be determined based on the probability information among the plurality of tenderers, and in some examples, determining the at least one target tenderer cooperating with the bidder based on the probability information may include: ranking all tenderers based on the probability information to obtain ranking information; and determining the top N tenderers in the sequencing information as at least one target tenderer.
Specifically, after obtaining probability information that the tenderers cooperate with the bidders, all the tenderers may be ranked based on the probability information to obtain ranking information, and then the top N tenderers in the ranking information may be determined as at least one target tenderer.
In other examples, ranking all of the tenderers based on the probability information, obtaining ranking information may include: comparing the probability information with a preset threshold value; when the probability information is greater than or equal to a preset threshold value, sequencing the corresponding tenderers based on the probability information to obtain sequencing information; and when the probability information is smaller than the preset threshold value, neglecting to sequence the tenderers corresponding to the probability information.
Step S502: recommending at least one target tenderer to the bidder.
After the at least one target tenderer is acquired, the at least one target tenderer may be recommended to the bidder, and specifically, the recommending the at least one target tenderer to the bidder may include: and generating recommendation information corresponding to the at least one target tenderer respectively, and then sending the recommendation information to the bidder.
Similarly, after predicting probability information of cooperation between the tenderer and the bidder, in order to improve the practicability of the method, the tenderer may also perform a recommending operation based on the probability information, and specifically, the method in this embodiment may include: among the plurality of bidders, determining at least one target bidder cooperating with the tenderer based on the probability information, and then recommending the at least one target bidder to the tenderer may include: the recommendation information corresponding to each target bidder is generated and then sent to the tenderer, so that recommendation operation of the tenderer and the bidder can be effectively realized based on the prediction probability of cooperation between the tenderer and the bidder.
In the embodiment, after the probability information of cooperation between the tenderer and the bidder is predicted, at least one target tenderer cooperating with the bidder is determined based on the probability information in the plurality of tenderers, and then the at least one target tenderer is recommended to the bidder, so that the tenderer with higher cooperation probability can be effectively recommended to the bidder, the cooperation probability is favorably improved, the quality and the efficiency of tendering and bidding operations are favorably improved, and the practicability of the method is further improved.
When the method is applied specifically, a supplier is taken as a bidder, and a first-party enterprise is taken as a tenderer, the embodiment of the application provides a method for predicting the business-computer cooperative relationship based on the multi-similarity auxiliary path probability, and the method can respectively consider the factors of the auxiliary text feature similarity between any two suppliers in a bipartite graph, the auxiliary text feature similarity between any two first-party enterprises and the category similarity between cooperative relationship edges when the path probability is utilized to calculate the cooperative relationship prediction between the supplier and the first-party enterprise, so that the purposes of more accurate cooperative relationship prediction and recommendation are achieved. Specifically, referring to fig. 6, the prediction method may include the following steps:
step 1: and extracting historical cooperative relationships.
The cooperative relationship between the supplier and the first-party enterprise is extracted from the massive bid-winning announcements, the bid-winning and bidding behaviors of the supplier can be used as the cooperative relationship, and specifically, the fields of the tenderer, the bid-winning party, the bidder, the tender object and the like can be extracted on the marked data by using some general Natural Language Processing (NLP) entity extraction models. After the extraction is completed, for each winning bid publication, one or more of the suppliers and the tenderer's partnerships are obtained.
And 2, step: and constructing a history cooperation bipartite graph.
And constructing a bipartite graph by using the extracted collaboration relationship, as shown in fig. 7, wherein a solid line in the graph can identify that a true historical collaboration relationship exists between the supplier and the tenderer, for the bipartite graph, a left node of the bipartite graph may be the supplier (corresponding to the bidder), a right node of the bipartite graph may be the tenderer, and if a historical collaboration relationship exists between the supplier and the tenderer, the two nodes in the graph are connected into a collaboration edge, each collaboration edge may further include some collaboration features, and the collaboration features may include at least one of the following: the number of successful bids, the amount of the bid, the category of the bid, etc. If there are multiple cooperative relationships between the two nodes, the historical information may be summarized and counted as the characteristics of the cooperative edge, such as: a cooperative edge may be characterized as a nested dictionary of a form similar to: { traffic class: { winning number of wins: 10 times, the accumulated amount of winning a bid: 1kw yuan, building type: { winning number of wins: 5 times, the accumulated amount of winning a bid: 2kw element … }.
In addition, after obtaining the historical partnership, a preliminary partnership prediction recommendation can be made based on a collaborative filtering algorithm, specifically, as can be seen from fig. 7, the supplier 2 and the supplier 3 both collaborate with the tenderer B, while the tenderer a collaborates with the supplier 1 and the supplier 2, although the tenderer a does not directly collaborate with the supplier 3 in history, the tenderer a and the supplier 3 can be considered to have a potential partnership directly by using the principle of collaborative filtering. Similarly, although the supplier 4 does not directly cooperate with the tenderer a, the supplier 4 cooperates with the tenderer C at the same time as the supplier 2, so that the tenderer a and the supplier 4 can also be considered to have a potential cooperation relationship, and the supplier is marked as U, and the tenderer is marked as I, which is a U-I-U-I recall scheme.
In addition, in the above implementation step, the bipartite graph is processed by a collaborative filtering algorithm, and it can be considered that both the supplier 3 and the supplier 4 have potential partnerships with the supplier a, as indicated by the dotted line in fig. 7, and both companies have a partnerships derived by having a common partnering unit with the supplier 2. The probabilities of the partnerships of the suppliers 3 and 4 and the tenderer a are the same without considering the weight difference of the cooperative edge.
However, although it can be determined from the perspective of collaborative filtering of the bipartite graph that both the supplier 2 and the supplier 4 have collaborated with the tenderer C, the domain of collaboration is completely different, and thus the deduced collaboration is unreliable, or even if the domain of collaboration between the supplier 2 and the supplier 4 with the tenderer C is the same, a more quantitative method is needed to compare which of the supplier 3 and the supplier 4 has a closer potential collaboration with the tenderer a, so as to better perform the recommendation operation of the collaboration. Based on this, the similarity between suppliers, the similarity between tenderers, and the similarity between any two cooperative edges can be effectively utilized to assist in collaborative filtering of the cooperative relationship, and at this time, the similarity between the suppliers and the suppliers, and the similarity between the tenderers and the tenderers need to be calculated respectively, which is detailed in step 3 and step 4.
And step 3: and calculating the similarity of the text topics between the suppliers to obtain the similarity between the suppliers.
For the supplier node or the tenderer node included in the bipartite graph, the supplier node or the tenderer node may correspond to a plurality of additional text auxiliary information, in particular, the text auxiliary information may help to characterize a topic to which the enterprise belongs, and specifically, the text auxiliary information may include, but is not limited to: enterprise category information, business scope, patent information, recruitment information, historical bid-winning announcements, and the like; the text auxiliary information can be called fields, and each text field can characterize the text as a vector feature with a corresponding length or a fixed length by using some technical means of NLP.
For example: for the text representation of the enterprise operation range, words can be firstly segmented for the text of the operation range, then the word frequency-reverse file frequency TFIDF characteristics of each word are calculated, for the words of the operation range of each enterprise, after keywords ranked in the top N number are extracted according to the TFIDF characteristics, pre-trained word vectors such as a natural language processing generic algorithm or a Bidirectional encoding representation algorithm (Bert) based on a transform algorithm are utilized, weighted summation is carried out on the word vectors of the keywords according to the TFIDF characteristics, and the text subject vector representation of the current enterprise operation range is obtained.
For the text topic vector representations of other domains, similar methods can be adopted to obtain topic text vector representations of different domains such as an operation domain, a patent domain, a recruitment domain, a history bid-winning domain and the like, and then the main text vector representations of all the domains can be subjected to weighted summation or directly spliced according to certain experience, so that a text topic representation vector for the whole enterprise can be finally obtained.
After the text theme characterization vectors corresponding to the suppliers are obtained, the text theme characterization vectors corresponding to any two suppliers can be processed by using a cosine similarity isovector similarity calculation method to obtain the similarity between the suppliers.
After the similarity between any two suppliers is obtained, the multiple similarities can be analyzed and compared to realize the recommended operation of the suppliers. For example, if the similarity between the supplier 2 and the supplier 3 is Sim (2,3), and the similarity between the supplier 2 and the supplier 4 is Sim (2,4), if Sim (2,3) > Sim (2,4), the comparison result based on Sim (2,3) > Sim (2,4) can be considered as follows without considering other additional factors: the fact E1 that the supplier 2 and the supplier 3 have a co-partner unit is more stable than the fact E2 that the supplier 2 and the supplier 4 have a co-partner unit, that is, although the supplier 2 and the supplier 4 have a co-partner unit C, it is highly probable that E2 is an incident and the similarity probability in the field of cooperation is lower than that of E1. Based on this, when the supplier 2 is found to have a history of cooperation with the tenderer a, the supplier 3 may be preferentially recommended to the tenderer a.
Based on the principle of collaborative filtering, if the calculated similarity Sim (a, B) between the tenderer a and the tenderer B is greater than the similarity Sim (a, C) between a and C, the potential partnership between the supplier 3 and the tenderer a should be tighter than the potential partnership between the supplier 4 and the tenderer a without considering additional other factors, as seen from the other half of the bipartite graph.
And 4, step 4: and calculating the similarity of the text topics between the tenderers to obtain the similarity between the tenderers.
In this embodiment, the specific implementation manner and implementation effect of step 4 are similar to those of step 3, and reference may be made to the above statements specifically, which are not described herein again.
And 5: and calculating the similarity of any two cooperative edges based on the cooperative category to obtain the similarity of the cooperative edges.
When the bipartite graph is constructed, the cooperative edges in the bipartite graph correspond to the cooperative features. To simplify the calculation, based on the similarity calculation of the feature participation edges related to the statistical number of the cooperation categories, assuming that the enumerated categories of the cooperation categories are M categories, the feature of the cooperation relationship edge between the supplier i and the tenderer a is { category 1: C1 times, category 2: C2 times, …, category M: Cm times }, then the feature of this edge Eia can be represented as [ C1, C2, …, Cm ]. After the feature vector of each cooperative relationship edge is obtained, the similarity between the cooperative relationship edge and the cooperative relationship edge may be calculated by using methods such as cosine similarity, and it should be noted that the feature vector of the edge participating in the calculation may be after global normalization.
As shown in fig. 7, the similarity Sim between the feature vectors of the two cooperating edges E2B and E3B (E2B, E3B), and the similarity Sim between the feature vectors of the two cooperating edges E2C and E4C (E2C, E4C) are calculated, respectively. If Sim (E2B, E3B) > Sim (E2C, E4C), it means that the event of supplier 2 and supplier 3 cooperating with the tenderer B simultaneously is more stable than the event of supplier 2 and supplier 4 cooperating with the tenderer C simultaneously, because supplier 2 and supplier 3 are likely to cooperate with the tenderer B in similar fields, and supplier 2 and supplier 4, although both cooperating with the tenderer C, are likely not co-operative events in the same field, are accidental events, and have no causal relationship.
Step 6: and calculating probability information of cooperation between the suppliers and the tenderer based on the similarity among the suppliers, the similarity among the tenderers and the similarity of the cooperation edges.
After the similarity among the suppliers, the similarity among the tenderers and the similarity of the cooperation edges are obtained, the similarity among the suppliers, the similarity among the tenderers and the similarity of the cooperation edges can be analyzed and processed to calculate probability information of cooperation between the suppliers and the tenderers. Specifically, in order to implement a recommended recall path of U1-I1-U2-I2, the probability of cooperation between U1 and I2 is represented as P (U1, I2) _1 ═ w1 ═ Sim (EU1, I1, EU2, I1) + w2 × Sim (U1, U2) + w3 × Sim (I1, I2). W1, w2, and w3 may be weights defined by scene requirements or application requirements, or weights obtained by training optimization according to actual training data, Sim (EU1, I1, EU2, I1) is used to identify similarity between any two cooperative edges, Sim (U1, U2) is used to identify similarity between suppliers, and Sim (I1, I2) is used to identify similarity between tenderers.
In some examples, if there are multiple paths between U1 and I2, then the overall joint probability P (U1, I2) ═ Σ P (U1, I2) _ I may be obtained, and then the overall joint probability may be determined as the target probability information for the cooperation of the supplier and the tenderer.
And 7: potential partnerships are inferred based on probabilistic information of the cooperation of the supplier with the tenderer.
After obtaining probability information of cooperation between the supplier and the tenderer, a cooperation potential relationship between the supplier and the tenderer can be deduced based on the probability information, and specifically, a potential cooperation relationship probability between any one supplier j and one tenderer k is represented as P (Uj, Ik). If P (Uj1, Ik) > P (Uj2, Ik), it is stated that the cooperation relationship between the supplier j1 and the tenderer k is greater than the cooperation relationship between the supplier j2 and the tenderer k, so that top n potential tenderer customers can be recommended to each supplier according to actual needs and probability information, or after obtaining the probability information, the probability information can be analyzed and compared with a threshold value, and the cooperation systems exceeding the threshold value can be recommended as potential cooperation relationships, for example: suppliers with potential partnerships may be recommended for the tenderer, or tenderers with potential partnerships may be recommended to the suppliers, which may improve the accuracy and reliability of the inference of partnerships.
The application embodiment provides a scheme for jointly optimizing potential cooperation probability prediction based on U-I-U-I path probability calculation by comprehensively considering the similarity among suppliers, the similarity among tenderers and the similarity of cooperation edges, and the scheme can effectively eliminate the problems of field deviation and error conduction caused by the divergence of the demand of the tenderers in the field of tenderer and tenderer opportunity recommendation, so that the potential cooperation relationship is established between the suppliers U and the tenderers I without direct historical cooperation relationship more accurately, the general cooperation between the suppliers and the tenderers can be quantitatively identified more accurately, the practicability of the technical scheme is further improved, and the market popularization and application are facilitated.
Fig. 8 is a flowchart illustrating a method for predicting an association relationship according to an embodiment of the present disclosure; referring to fig. 8, the present embodiment provides a method for predicting an association relationship, where an execution subject of the method is a device for predicting an association relationship, where the device for predicting an association relationship may be implemented as software or a combination of software and hardware; the method for predicting the association relationship in this embodiment may include:
step S801: and acquiring a first similarity between any two first-class objects and a second similarity between any two second-class objects.
Any two first-class objects and any two second-class objects in different application scenes can be different, for example: in an application scenario of e-commerce transaction, the first class object may be a user with potential transaction probability, and the second class object may be commodity information with potential transaction probability; in an application scenario of article pushing, a first class of objects may be article information to be pushed, and a second class of objects may be users with potential article viewing probabilities.
Step S802: and determining historical association relations between the first class of objects and the second class of objects and a third similarity between any two historical association relations.
Step S803: and predicting probability information of the first class of objects and the second class of objects for association based on the first similarity, the second similarity and the third similarity.
In addition, in this embodiment, the specific implementation manner and implementation effect of the steps S801 to S803 are similar to those of the steps S201 to S203 in the embodiment, and the above statements may be specifically referred to, and are not repeated herein.
It should be noted that the method in this embodiment may also include the method in the embodiment shown in fig. 1 to 7, and for the part not described in detail in this embodiment, reference may be made to the relevant description of the embodiment shown in fig. 1 to 7. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 1 to 7, and are not described herein again.
Application scenario 1: the first type objects include a commodity a, a commodity b, a commodity c and a commodity d, the second type objects include a user a, a user b and a user c, and then a first similarity between any two first type objects and a second similarity between any two second type objects can be obtained, for example: the first similarity may include: sim1(a, b), sim1(a, c), sim1(a, d), sim1(b, c), sim1(b, d), and sim1(c, d), the second similarity may comprise: sim2 (A, B), sim2 (A, C). Meanwhile, historical association relations between the first class of objects and the second class of objects and a third similarity between any two historical association relations can also be determined, and the third similarity can include: sim1(a, a), sim1(b, b), sim1(c, c), and so on, after the first similarity, the second similarity, and the third similarity are obtained, probability information that the first class object is associated with the second class object may be determined based on the first similarity, the second similarity, and the third similarity. For example: for the user B, the probability information of the commodity b and the commodity d is determined to be higher, so that the commodity b and the commodity d can be recommended to the user B based on the probability information; similarly, for the user c, if the probability information of the commodity a and the commodity d is high, the commodity a and the commodity d can be recommended to the user c, so that the commodity recommendation operation is effectively realized.
Application scenario 2: the first class of objects includes an article a, an article b, and an article c, and the second class of objects includes a user a, a user b, and a user c, and then a first similarity between any two first class of objects and a second similarity between any two second class of objects can be obtained, for example: the first similarity may include: sim1(a, b), sim1(a, c), and sim1(b, c), the second similarity may include: sim2 (a, b), sim2 (a, c). Meanwhile, historical association relations between the first class of objects and the second class of objects and a third similarity between any two historical association relations can also be determined, and the third similarity can include: sim1(a, a), sim1(b, b), sim1(c, c), and so on, after the first similarity, the second similarity, and the third similarity are obtained, probability information of the first class object being associated with the second class object may be determined based on the first similarity, the second similarity, and the third similarity. For example: for the user B, the probability information of the article b is determined to be higher, so that the article b can be recommended to the user B based on the probability information; similarly, for the user c, if the probability information of the article a and the article c is higher, the article a and the article c can be recommended to the user c, so that the recommendation operation of the article is effectively realized.
According to the prediction method of the incidence relation provided by the embodiment, the historical incidence relation between the first class object and the second class object and the third similarity between any two historical incidence relations are determined by obtaining the first similarity between any two first class objects and the second similarity between any two second class objects, and the probability information of the incidence relation between the first class object and the second class object is predicted based on the first similarity, the second similarity and the third similarity.
FIG. 9 is a schematic flow chart illustrating an apparatus for predicting bidding partnership provided in an embodiment of the present application; referring to fig. 9, the present embodiment provides a device for predicting a bidding partnership, which is used for performing the method for predicting a bidding partnership shown in fig. 2, and in particular, the device for predicting a bidding partnership may include:
the first obtaining module 11 is configured to obtain a first similarity between any two tenderers and a second similarity between any two bidders;
the first determining module 12 is configured to determine a historical cooperative relationship between the tenderer and the bidder and a third similarity between any two historical cooperative relationships;
and the first processing module 13 is configured to predict probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
In some examples, when the first obtaining module 11 obtains a first similarity between any two tenderers and a second similarity between any two tenderers, the first obtaining module 11 is configured to: acquiring first characterization information corresponding to each tenderer and second characterization information corresponding to each bidder, wherein the first characterization information is at least used for identifying the operating characteristics of the corresponding tenderer, and the second characterization information is at least used for identifying the operating characteristics of the corresponding bidder; determining a first similarity based on first characterization information corresponding to any two tenderers; and determining a second similarity based on the second characterization information corresponding to any two bidders.
In some examples, the first characterization information and the second characterization information include at least one of: enterprise category, business scope, patent information, recruitment information, historical bid-winning announcements.
In some examples, when the first obtaining module 11 determines the first similarity based on the first characterizing information corresponding to each of any two tenderers, the first obtaining module 11 is configured to: acquiring a first characterization vector corresponding to the first characterization information; and determining the first similarity based on the first characterization vectors corresponding to any two tenderers.
In some examples, when the first obtaining module 11 obtains the first token vector corresponding to the first token information, the first obtaining module 11 is configured to: performing word segmentation processing on the first representation information to obtain a plurality of keywords corresponding to the first representation information; determining word vectors corresponding to the plurality of keywords respectively; and determining a first characterization vector based on the word vectors corresponding to all the keywords.
In some examples, when the first obtaining module 11 determines the first token vector based on the word vectors corresponding to all the keywords, the first obtaining module 11 is configured to: acquiring weight information corresponding to the word vectors; and carrying out weighted summation on the word vectors based on the weight information to obtain a first characterization vector.
In some examples, when the first obtaining module 11 obtains the weight information corresponding to the word vector, the first obtaining module 11 is configured to: acquiring word frequency and reverse file frequency corresponding to each keyword; and determining weight information corresponding to the word vector based on the word frequency and the reverse file frequency, wherein the weight information is positively correlated with the word frequency and the reverse file frequency.
In some examples, when the first determination module 12 determines the third degree of similarity between any two historical partnerships, the first determination module 12 is configured to perform: constructing a bipartite graph based on historical cooperative relationship between the tenderer and the bidder, wherein the bipartite graph comprises a cooperative edge used for identifying the historical cooperative relationship between the tenderer and the bidder, and the cooperative edge corresponds to cooperative features; and determining a third similarity between any two historical cooperative relations based on the cooperative features corresponding to the cooperative edges.
In some examples, the collaboration feature includes at least one of: category of cooperation, number of times of cooperation, amount of cooperation.
In some examples, when the first processing module 13 predicts probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity, the first processing module 13 is configured to perform: acquiring weight information corresponding to the first similarity, the second similarity and the third similarity respectively; and performing weighted summation on the first similarity, the second similarity and the third similarity based on the weight information corresponding to the first similarity, the second similarity and the third similarity respectively to obtain probability information of cooperation between the tenderer and the bidder.
In some examples, after predicting probability information that the tenderer cooperates with the bidder, the first processing module 13 in the embodiment is configured to perform: determining, among the plurality of tenderers, at least one target tenderer cooperating with a bidder based on the probability information; recommending at least one target tenderer to the bidder.
In some examples, when the first processing module 13 determines at least one target bidder cooperating with the bidder based on the probability information, the first processing module 13 is configured to perform: ranking all tenderers based on the probability information to obtain ranking information; and determining the top N tenderers in the sequencing information as at least one target tenderer.
In some examples, when the first processing module 13 ranks all the tenderers based on the probability information, and obtains the ranking information, the first processing module 13 is configured to perform: comparing the probability information with a preset threshold value; when the probability information is greater than or equal to a preset threshold value, sequencing the corresponding tenderers based on the probability information to obtain sequencing information; and when the probability information is smaller than the preset threshold value, neglecting to sequence the tenderers corresponding to the probability information.
The method of the embodiment shown in fig. 1-7 can be performed by the bidding partnership prediction apparatus shown in fig. 9, and reference may be made to the related description of the embodiment shown in fig. 1-7 for a part of this embodiment not described in detail. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 1 to 7, and are not described herein again.
In one possible design, the structure of the bidding partnership prediction apparatus shown in fig. 9 may be implemented as an electronic device, which may be a cluster server, a conventional server, a cloud host, a virtual center, or the like. As shown in fig. 10, the electronic device may include: a first processor 21 and a first memory 22. Wherein the first memory 22 is used for storing a program of a corresponding electronic device to execute the method for predicting partaking relations provided in the embodiments shown in fig. 1-7, and the first processor 21 is configured to execute the program stored in the first memory 22.
The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 21, are capable of performing the steps of: acquiring a first similarity between any two tenderers and a second similarity between any two bidders; determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships; and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
Further, the first processor 21 is also used to execute all or part of the steps in the embodiments shown in fig. 1-7.
The electronic device may further include a first communication interface 23, which is used for the electronic device to communicate with other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for an electronic device, which includes a program for executing the method for predicting a bidding partnership in the method embodiments shown in fig. 1 to 7.
Furthermore, an embodiment of the present invention provides a computer program product, including: a computer program which, when executed by a processor of an electronic device, causes the processor to perform a method of predicting a bidding partnership in an embodiment of the method illustrated in figures 1-7.
Fig. 11 is a schematic structural diagram of an incidence relation predicting apparatus according to an embodiment of the present disclosure; referring to fig. 11, the present embodiment provides an incidence relation predicting apparatus, configured to perform the incidence relation predicting method shown in fig. 8, specifically, the incidence relation predicting apparatus may include:
a second obtaining module 31, configured to obtain a first similarity between any two first-class objects and a second similarity between any two second-class objects;
a second determining module 32, configured to determine historical association relationships between the first class of objects and the second class of objects, and a third similarity between any two historical association relationships;
and the second processing module 33 is configured to predict probability information of the first class of object being associated with the second class of object based on the first similarity, the second similarity, and the third similarity.
The method of the embodiment shown in fig. 8 can be performed by the device for predicting association shown in fig. 11, and reference may be made to the related description of the embodiment shown in fig. 8 for a part not described in detail in this embodiment. The implementation process and technical effect of the technical solution refer to the description in the embodiment shown in fig. 8, and are not described herein again.
In one possible design, the structure of the association prediction apparatus shown in fig. 11 may be implemented as an electronic device. As shown in fig. 12, the electronic device may include: a second processor 41 and a second memory 42. The second memory 42 is used for storing a program of the corresponding electronic device for executing the method for predicting the association provided in the embodiment shown in fig. 8, and the second processor 41 is configured to execute the program stored in the second memory 42.
The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the second processor 41, are capable of performing the steps of: acquiring a first similarity between any two first-class objects and a second similarity between any two second-class objects; determining historical incidence relations between the first class of objects and the second class of objects and a third similarity between any two historical incidence relations; and predicting probability information of the first class of objects and the second class of objects for association based on the first similarity, the second similarity and the third similarity.
Further, the second processor 41 is also used to execute all or part of the steps in the embodiment shown in fig. 8. The electronic device may further include a second communication interface 43 for communicating with other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for an electronic device, which includes a program for executing the method for predicting an association relationship in the method embodiment shown in fig. 8.
Furthermore, an embodiment of the present invention provides a computer program product, including: a computer program which, when executed by a processor of an electronic device, causes the processor to carry out the method of predicting an association in the method embodiment shown in fig. 8.
Fig. 13 is a schematic structural diagram of a bidding partnership prediction system according to an embodiment of the present application, and referring to fig. 13, the present embodiment provides a bidding partnership prediction system for accurately predicting bidding partnership, the prediction system includes: a request end 51 and a prediction device 52 which is connected with the request end 51 in a communication way;
the request end 51 may be any computing device with certain data transmission capability, and in particular, the request end 51 may be a mobile phone, a personal computer PC, a tablet computer, a set application program, and the like. In addition, the basic structure of the request terminal 51 may include: at least one processor. The number of processors depends on the configuration and type of the requesting end 51. The request end 51 may also include a Memory, which may be volatile, such as a RAM, or non-volatile, such as a Read-Only Memory (ROM), a flash Memory, or both. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. In addition to the processing unit and the memory, the request end 51 also includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices. Alternatively, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like.
The prediction device 52 is a device capable of providing a prediction service of the bidding partnership in a network virtual environment, and generally refers to a device for performing information planning and a prediction operation of the bidding partnership using a network. In physical implementation, the prediction device 52 may be any device capable of providing a computing service, responding to a service request, and performing processing, such as: can be cluster servers, regular servers, cloud hosts, virtual centers, and the like. Specifically, the request end 51 and the prediction device 52 are configured to perform the following steps:
the requesting terminal 51 is configured to display an interactive interface for predicting a cooperative relationship between the tenderer and the bidder, obtain a plurality of tenderers and a plurality of bidders through the interactive interface, and send the plurality of tenderers and the plurality of bidders to the predicting device 52.
A predicting device 52, configured to receive the plurality of tenderers and the plurality of bidders sent by the requesting terminal 51, and obtain a first similarity between any two tenderers and a second similarity between any two bidders; determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships; based on the first similarity, the second similarity, and the third similarity, probability information of cooperation between the tenderer and the bidder is predicted, and the probability information of cooperation between the tenderer and the bidder is transmitted to the requesting terminal 51.
And the request end 51 is used for displaying probability information of cooperation between the tenderer and the bidder through an interactive interface.
The bidding partnership prediction system shown in fig. 13 may also perform the method of the embodiment shown in fig. 1-7, and reference may be made to the related description of the embodiment shown in fig. 1-7 for a part of the embodiment not described in detail. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 1 to 7, and are not described herein again.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described technical solutions and/or portions thereof that contribute to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein (including but not limited to disk storage, CD-ROM, optical storage, etc.).
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the scope of the technical solutions of the embodiments of the present application.
Claims (12)
1. A method for predicting bidding partnership, comprising:
acquiring a first similarity between any two tenderers and a second similarity between any two bidders;
determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships;
and predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity.
2. The method of claim 1, wherein obtaining a first similarity between any two tenderers and a second similarity between any two bidders comprises:
acquiring first characterization information corresponding to each tenderer and second characterization information corresponding to each bidder, wherein the first characterization information is at least used for identifying the operating characteristics of the corresponding tenderer, and the second characterization information is at least used for identifying the operating characteristics of the corresponding bidder;
determining the first similarity based on first characterization information corresponding to any two tenderers;
and determining the second similarity based on the second characterization information corresponding to any two bidders.
3. The method of claim 2, wherein determining the first similarity based on the first characterization information corresponding to each of any two tenderers comprises:
acquiring a first characterization vector corresponding to the first characterization information;
and determining the first similarity based on the first characterization vectors corresponding to any two tenderers.
4. The method of claim 3, wherein obtaining a first token vector corresponding to the first token information comprises:
performing word segmentation processing on the first representation information to obtain a plurality of keywords corresponding to the first representation information;
determining word vectors corresponding to the plurality of keywords respectively;
and determining the first characterization vector based on the word vectors corresponding to all the keywords.
5. The method of claim 4, wherein determining the first token vector based on the word vectors corresponding to all the keywords comprises:
acquiring weight information corresponding to the word vectors;
and carrying out weighted summation on the word vectors based on the weight information to obtain the first characterization vector.
6. The method of claim 4, wherein obtaining weight information corresponding to the word vector comprises:
acquiring word frequency and reverse file frequency corresponding to each keyword;
and determining weight information corresponding to the word vector based on the word frequency and the reverse file frequency, wherein the weight information is positively correlated with the word frequency and the reverse file frequency.
7. The method of claim 1, wherein determining a third similarity between any two historical partnerships comprises:
constructing a bipartite graph based on historical cooperative relationship between the tenderer and the bidder, wherein the bipartite graph comprises a cooperative edge used for identifying the historical cooperative relationship between the tenderer and the bidder, and the cooperative edge corresponds to cooperative features;
and determining a third similarity between any two historical cooperative relations based on the cooperative features corresponding to the cooperative edges.
8. The method of claim 1, wherein after predicting probability information that the tenderer will collaborate with the bidder, the method further comprises:
determining, among a plurality of tenderers, at least one target tenderer cooperating with the bidder based on the probability information;
recommending the at least one targeted bidder to the bidder.
9. The method of claim 8, wherein determining at least one target bidder that cooperates with the bidder based on the probability information comprises:
sequencing all tenderers based on the probability information to obtain sequencing information;
and determining the top N tenderers in the sequencing information as the at least one target tenderer.
10. The method of claim 9, wherein ranking all tenderers based on the probability information, obtaining ranking information, comprises:
comparing the probability information with a preset threshold value;
when the probability information is larger than or equal to a preset threshold value, sequencing the corresponding tenderers based on the probability information to obtain sequencing information;
and when the probability information is smaller than a preset threshold value, neglecting to sequence the tenderers corresponding to the probability information.
11. An electronic device, comprising: a memory, a processor; wherein the memory is to store one or more computer instructions that when executed by the processor implement a method of predicting a bidding partnership as recited in any one of claims 1-10.
12. A system for predicting a bidding partnership, comprising:
the system comprises a request terminal, a prediction device and a display device, wherein the request terminal is used for displaying an interactive interface for predicting the cooperative relationship between tenderers and bidders, acquiring a plurality of tenderers and bidders through the interactive interface and sending the tenderers and bidders to the prediction device;
the predicting device is in communication connection with the request end and is used for receiving the plurality of tenderers and the plurality of bidders sent by the request end and acquiring first similarity between any two tenderers and second similarity between any two bidders; determining historical cooperative relationships between the tenderer and the bidder and a third similarity between any two historical cooperative relationships; predicting probability information of cooperation between the tenderer and the bidder based on the first similarity, the second similarity and the third similarity, and sending the probability information of cooperation between the tenderer and the bidder to the request terminal;
and the request end is used for displaying probability information of cooperation between the tenderer and the bidder through the interactive interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210471354.9A CN114943279A (en) | 2022-04-28 | 2022-04-28 | Method, device and system for predicting bidding cooperative relationship |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210471354.9A CN114943279A (en) | 2022-04-28 | 2022-04-28 | Method, device and system for predicting bidding cooperative relationship |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114943279A true CN114943279A (en) | 2022-08-26 |
Family
ID=82907106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210471354.9A Pending CN114943279A (en) | 2022-04-28 | 2022-04-28 | Method, device and system for predicting bidding cooperative relationship |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114943279A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116342234A (en) * | 2023-05-26 | 2023-06-27 | 山东纵横易购产业互联网有限公司 | Method for realizing automatic bidding purchasing aiming at goods |
CN117495515B (en) * | 2023-12-29 | 2024-04-05 | 优材优建(青岛)供应链科技有限公司 | Bid intelligent matching method, system, computer equipment and storage medium |
-
2022
- 2022-04-28 CN CN202210471354.9A patent/CN114943279A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116342234A (en) * | 2023-05-26 | 2023-06-27 | 山东纵横易购产业互联网有限公司 | Method for realizing automatic bidding purchasing aiming at goods |
CN116342234B (en) * | 2023-05-26 | 2023-08-29 | 山东纵横易购产业互联网有限公司 | Method for realizing automatic bidding purchasing aiming at goods |
CN117495515B (en) * | 2023-12-29 | 2024-04-05 | 优材优建(青岛)供应链科技有限公司 | Bid intelligent matching method, system, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2992563C (en) | Method and system for applying probabilistic topic models to content in a tax environment to improve user satisfaction with a question and answer customer support system | |
US20210081567A1 (en) | Monitoring data sharing and privacy policy compliance | |
US10360631B1 (en) | Utilizing artificial intelligence to make a prediction about an entity based on user sentiment and transaction history | |
US11188720B2 (en) | Computing system including virtual agent bot providing semantic topic model-based response | |
CN106649681B (en) | Data processing method, device and equipment | |
CN114943279A (en) | Method, device and system for predicting bidding cooperative relationship | |
US11205138B2 (en) | Model quality and related models using provenance data | |
US20200412682A1 (en) | Feedback enabled network curation of relevant content thread | |
Liu et al. | Extracting, ranking, and evaluating quality features of web services through user review sentiment analysis | |
US11853948B2 (en) | Methods and systems for managing risk with respect to potential customers | |
US11122141B2 (en) | Managing or modifying online content according to cognitively identified creator and organization relationships | |
US11055345B2 (en) | Constructing, evaluating, and improving a search string for retrieving images indicating item use | |
US20200169588A1 (en) | Methods and systems for managing distribution of online content based on content maturity | |
CN115983902A (en) | Information pushing method and system based on user real-time event | |
US20220358152A1 (en) | Model performance through text-to-text transformation via distant supervision from target and auxiliary tasks | |
CN115129945A (en) | Graph structure contrast learning method, equipment and computer storage medium | |
CN115238676A (en) | Method and device for identifying hot spots of bidding demands, storage medium and electronic equipment | |
CN114253957A (en) | Data processing method, related device, storage medium and computer program product | |
CN113052509A (en) | Model evaluation method, model evaluation apparatus, electronic device, and storage medium | |
CN113837843A (en) | Product recommendation method, device, medium and electronic equipment | |
US10891664B2 (en) | System and method for facilitating non-parametric weighted correlation analysis | |
US11645329B2 (en) | Constructing, evaluating, and improving a search string for retrieving images indicating item use | |
CN111915339A (en) | Data processing method, device and equipment | |
US11914733B2 (en) | Timing for user data erasure requests | |
US11928153B2 (en) | Multimedia linked timestamp validation detection |
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 |