CN112541072A - Supply and demand information recommendation method and system based on knowledge graph - Google Patents
Supply and demand information recommendation method and system based on knowledge graph Download PDFInfo
- Publication number
- CN112541072A CN112541072A CN202011444487.4A CN202011444487A CN112541072A CN 112541072 A CN112541072 A CN 112541072A CN 202011444487 A CN202011444487 A CN 202011444487A CN 112541072 A CN112541072 A CN 112541072A
- Authority
- CN
- China
- Prior art keywords
- demand
- supply
- information
- entity
- demand information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The invention relates to the technical field of supply and demand information recommendation, and discloses a supply and demand information recommendation method and system based on a knowledge graph, which comprises the following steps: acquiring supply and demand information, extracting entity, relation and attribute triples from the supply and demand information by using a knowledge extraction method, constructing a supply and demand information map according to the triples, and storing the supply and demand information map in a map database; receiving demand information or supply information input by a user, calling the graph database, and searching the supply information matched with the demand information or the demand information matched with the supply information in the supply and demand information graph; and generating a corresponding recommendation list according to the supply information or the demand information obtained by matching, and returning the recommendation list to the user. The invention provides accurate supply and demand information for supply and demand parties based on the knowledge graph, thereby improving the retrieval speed and precision; meanwhile, related supply and demand information is intelligently recommended for both the supply and demand parties based on historical data in the knowledge graph.
Description
Technical Field
The invention belongs to the technical field of supply and demand information recommendation, and particularly relates to a supply and demand information recommendation method and system based on a knowledge graph.
Background
In the information era, the network is a tool which people can not leave in life and work, people can share information in the network to obtain information, and the information sharing and interconnection enable the life and work of people to be convenient. For example, an enterprise acquires information through a network and selects a cost-effective supplier; enterprises can also popularize their products or services through the network to obtain benefits. At the moment, a professional information service platform for providing supply and demand information for both parties of an enterprise is produced.
The existing supply and demand information docking platform is more biased to the form of a comprehensive information service platform, a user can issue demand information as a demand party and also can issue supply information as a supply party, the supply and demand docking mainly comprises two parts of providing accurate demand party information for the supply party and providing accurate supply party information for the demand party, and the mode of acquiring the supply information by the demand party mainly comprises the following steps:
1. the demand side issues demand information, waits for the supplier to bid and provides corresponding supply information. In order to ensure that the demand information can be obtained by more suppliers, the demander generally sets a longer bidding period, so that the time cost of supply and demand docking is higher.
2. And the demander searches the supply information meeting the demand condition by self. The method needs the demander to make a corresponding retrieval scheme based on the existing requirements of the demander to complete the retrieval and screening of the supply information, but as the data volume increases, the demander has to invest more labor cost to complete the work.
Correspondingly, the method for acquiring the demand information by the supplier mainly comprises the following steps:
1. the supplier is invited by the demand side and receives corresponding demand information. This approach requires the requesting party to perform operations such as retrieval to obtain the supplier information and send the invitation.
2. The supplier searches corresponding demand information by itself. The method needs a supplier to pay attention to the demand trend on the platform in real time, a corresponding retrieval scheme is formulated based on the demand direction to be docked, retrieval and screening of demand information are completed, and the supplier has to invest more labor cost to complete the work with the increase of data volume.
3. The supplier pays attention to the corresponding demand type, and when the demander releases new demand information, the platform pushes the demand information to the supplier. The platform generally pushes the demand information to all suppliers paying attention to the category to which the current demand belongs, whether the suppliers are matched with the current demand is not judged, so that a lot of redundant information is pushed, and meanwhile, when the demand information is more and the suppliers pay attention to the category more, the suppliers receive a lot of demand information, so that a lot of time and energy are consumed to screen effective information.
In summary, the existing supply and demand information docking methods are single, that is, supply information is sent according to demand information issued by a user, or demand information is recommended according to the supply information of the user, but whether the sent demand information or the sent supply information are matched is not fully considered, and existing data are not fully utilized to help the user to mine new supply and demand information.
Disclosure of Invention
The invention aims to provide a knowledge graph-based supply and demand information bidirectional recommendation method and system, which are used for solving the technical problems that in the prior art, the supply and demand information docking mode is single, and whether the sent supply and demand information is matched or not is not fully considered.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for bi-directional supply and demand information recommendation based on a knowledge graph, the method comprising:
step 1: acquiring supply and demand information, extracting entity, relation and attribute triples from the supply and demand information by using a knowledge extraction method, constructing a supply and demand information map according to the triples, and storing the supply and demand information map in a map database;
step 2: receiving demand information or supply information input by a user, calling the graph database, and searching the supply information matched with the demand information or the demand information matched with the supply information in the supply and demand information graph;
and step 3: and generating a corresponding recommendation list according to the supply information or the demand information obtained by matching, and returning the recommendation list to the user.
Further, after the step 1, the method further includes:
and 4, step 4: recommending supply information matched with demand information or demand information which may be required by the demand party for the demand party according to the supply and demand information map; and/or
And recommending demand information matched with the supply information for the supplier according to the supply and demand information map.
Further, the step 1 comprises:
step 1.1: acquiring user information, and constructing an enterprise and personal map according to enterprise entities, enterprise attributes, personal entities, personal attributes and the relationship between enterprises and individuals in the user information; constructing an enterprise entity map according to the enterprise information;
step 1.2: acquiring demand information, extracting a demand entity, demand attributes and the relation between the demand and enterprises and individuals, and constructing a demand, enterprise and individual maps;
step 1.3: acquiring supply information, extracting supply entities, supply attributes and the relation between supply and enterprises and individuals, and constructing supply and enterprise and individual maps;
step 1.4: acquiring supply and demand docking record information, extracting a demand entity, a supply entity and a relation between demand and supply, and constructing a supply and demand entity map;
step 1.5: extracting a supply and demand category entity, a supply and demand category attribute, a relationship between supply and demand categories and a relationship between the supply and demand categories and the demand entity and the supply entity according to the demand information and the supply information to construct a supply and demand category and supply and demand entity map;
wherein the supply and demand information graph comprises the business to individual graph, the business entity graph, the demand and business, individual graph, the supply and demand entity graph, and the supply and demand category and supply and demand entity graph;
step 1.6: and storing the supply and demand information map in a map database.
Further, the step 2 comprises:
step 2.1 a: receiving demand information input by a user, extracting a demand entity and demand attributes in the demand information, and determining corresponding supply and demand categories and supply and demand category attributes;
step 2.2 a: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, and eliminating supply and demand type entity nodes with low matching degree until a supply and demand entity set related to the supply and demand type is obtained;
step 2.3 a: calculating the matching degree of the demand attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the demand entity in the supply and demand entity set into the supply entity associated with the demand entity set to obtain a supply entity set with fused matching degree;
the step 3 comprises the following steps:
step 3.1 a: and sequencing the supply entity set according to the matching degree to generate a corresponding supply information list, and returning the supply information list to the user.
Further, the step 2 further comprises:
step 2.1 b: receiving supply information input by a user, extracting a supply entity and supply attributes in the supply information, and determining corresponding supply and demand categories and supply and demand category attributes;
step 2.2 b: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, eliminating supply and demand type entity nodes with low matching degree until the supply and demand type entity nodes extend to supply and demand entities related to the supply and demand type, and then eliminating finished demand entities in the supply and demand entities to obtain a supply and demand entity set;
step 2.3 b: calculating the matching degree of the supply attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the supply entity in the supply and demand entity set into the demand entity associated with the supply and demand entity set to obtain a demand entity set with fused matching degree;
the step 3 comprises the following steps:
step 3.1 b: and sequencing the demand entity set according to the matching degree to generate a corresponding demand information list, and returning the demand information list to the user.
Further, the step 4 comprises:
step 4.1 a: acquiring current demand information, judging whether the current demand information is finished, and if so, finishing the current flow; otherwise, entering a step 4.2 a;
step 4.2 a: retrieving corresponding supply information based on the current demand information and generating a supply information list;
step 4.3 a: extracting the first N pieces of supply information in the supply information list, and adding the first N pieces of supply information into a supply information recommendation list corresponding to the current demand information;
step 4.4 a: repeating the steps 4.1 to 4.3 until a supply information recommendation list of all unfinished demands of the demand side is generated, and then randomly extracting a balanced amount of supply information from all the supply information recommendation lists and adding the supply information into a supply information recommendation summary table;
step 4.5 a: and sending the supply information recommendation summary table to the demand side.
Further, the step 4 further includes:
step 4.1 b: acquiring current supply information and retrieving corresponding demand information based on the current supply information to generate a demand information list;
step 4.2 b: extracting the first N pieces of demand information in the demand information list, and adding the first N pieces of demand information into a demand information recommendation list corresponding to the current supply information;
step 4.3 b: repeating the step 4.1b to the step 4.2b until a demand information recommendation list of all supply information of the supplier is generated, and then randomly extracting a balanced amount of demand information from all the demand information recommendation lists and adding the demand information into a demand information recommendation summary table;
step 4.4 b: and sending the demand information recommendation summary table to the supplier.
Further, the step 4 further includes:
step 4.1 c: acquiring a demand entity vector of the demand party based on the enterprise entity of the demand party;
step 4.2 c: searching a demand entity set of the same type as the demand entity in the supply and demand information map according to the demand entity vector;
step 4.3 c: obtaining an associated business entity set based on the demand entity set;
step 4.4 c: acquiring a demand vector set corresponding to the enterprise entity set, and removing the demand vector of the demand party from the demand vector set to obtain a residual demand vector set of the related enterprise;
step 4.5 c: respectively calculating the matching degree between the enterprise entity vector of the demand party and the enterprise entity vectors in the related enterprise entity sets and the matching degree between the demand vector of the demand party and the residual demand vector sets;
step 4.6 c: combining the matching degree between the entity vectors of the enterprises and the matching degree between the demand vectors in a weight superposition mode, taking the combined matching degree as a recommendation score of the residual demand vectors of each related enterprise, and combining all the residual demand entity vectors of the related enterprises to obtain a preliminary recommendation demand vector list;
step 4.7 c: and sorting the preliminary recommendation demand vector list according to the matching degree scores, extracting the first N pieces of demand information, generating a demand information recommendation list which can be needed by the demand party, and sending the demand information recommendation list to the demand party.
Further, after the step 4.7c, the method further includes:
step 4.8 c: and according to the supply and demand information map, sending the supply information which is successfully matched with the demand information in the demand information recommendation list to the demand party.
The invention also provides a supply and demand information recommendation system based on the knowledge graph, which comprises a memory, a processor and a transceiver which are sequentially connected in a communication manner, wherein the memory is used for storing computer programs, the transceiver is used for receiving and sending messages, and the processor is used for reading the computer programs and executing the supply and demand information recommendation method based on the knowledge graph.
The invention has the beneficial effects that:
1. according to the invention, the supply and demand information of the enterprise is stored in the graph data in a knowledge graph mode, and each data entity node is unique, so that the problem of data redundancy can be effectively avoided; meanwhile, the data is stored in a knowledge graph mode, and when data retrieval is carried out, compared with a traditional relational database, the retrieval speed is effectively improved.
2. When the user searches the supply and demand information, the supply and demand categories corresponding to the supply and demand information are subjected to matching search layer by layer through the knowledge spectrogram subgraphs stored in the graph database, the subgraphs are continuously simplified, the search range is reduced until the corresponding supply and demand entities are obtained, and the searching speed and precision can be improved while the calculation amount is effectively reduced.
3. Based on the current uncompleted demand, the method recommends a matched supply information list for the demand side; recommending a matched outstanding demand information list for the supplier based on the current supply information; based on a knowledge graph formed by accumulated historical data, a demand information list which is possibly needed is recommended for a demand party, and the intellectualization of recommending supply and demand information to supply and demand parties is realized.
Drawings
FIG. 1 is a flow chart of a supply and demand information recommendation method based on knowledge graph in an embodiment of the present invention;
FIG. 2 is a schematic diagram of the structure of an enterprise and personal graph in an embodiment of the invention;
FIG. 3 is a schematic diagram of a business entity graph according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a requirement and enterprise, personal graph structure in an embodiment of the invention;
FIG. 5 is a schematic diagram of the structure of a supply and business, personal graph in an embodiment of the invention;
FIG. 6 is a schematic diagram of a supply and demand map in an embodiment of the present invention;
FIG. 7 is a schematic diagram of the supply and demand categories and supply and demand entities according to an embodiment of the present invention;
FIG. 8 is a schematic flow chart of step 2 in an embodiment of the present invention;
FIG. 9 is another schematic flow chart of step 2 in the embodiment of the present invention;
FIG. 10 is a flow chart of another method for knowledge-graph based supply and demand information recommendation in an embodiment of the present invention;
FIG. 11 is a schematic flow chart of step 4 in the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step are within the scope of protection of the present specification.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It will be understood that when an element is referred to herein as being "connected," "connected," or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Conversely, if a unit is referred to herein as being "directly connected" or "directly coupled" to another unit, it is intended that no intervening units are present. In addition, other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between … …" versus "directly between … …", "adjacent" versus "directly adjacent", etc.).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
Example one
Referring to fig. 1-9 specifically, fig. 1 shows a supply and demand information recommendation method based on a knowledge graph in an embodiment of the present invention, which includes the following steps:
step 1: acquiring supply and demand information, extracting entity, relation and attribute triples from the supply and demand information by using a knowledge extraction method, constructing a supply and demand information map according to the triples, and storing the supply and demand information map in a map database;
in the embodiment of the present invention, step 1 specifically includes:
step 1.1: acquiring user information, and constructing an enterprise and personal map according to enterprise entities, enterprise attributes, personal entities, personal attributes and the relationship between enterprises and individuals in the user information; constructing an enterprise entity map according to the enterprise information; referring specifically to fig. 2 and 3, the business-to-person graph and business entity graph are shown.
In the embodiment of the invention, the category of the enterprise entity is company, and the enterprise attribute comprises enterprise information such as enterprise ID, enterprise name, enterprise type, enterprise geographic position, contact information and the like; the personal entity type is user, the personal attributes are user ID, user name, identification number, contact telephone, mailbox and the like, the relation between the enterprise and the personal comprises that the personal works in the enterprise, and the enterprise entity comprises a plurality of personal entities. Based on the enterprise information, extracting geographical location information such as country, province, city, district and the like in the enterprise attributes, enterprise information such as enterprise type and the like, and relationships among the data items, building new entities and relationships among the entities, and fusing repeated items, as shown in fig. 3.
Step 1.2: acquiring demand information, extracting a demand entity, demand attributes and the relation between the demand and enterprises and individuals, and constructing a demand, enterprise and individual maps;
in the embodiment of the present invention, the Demand entity type is Demand, and the Demand attribute includes Demand information such as Demand ID, Demand name, Demand type, quantity, release date, Demand state, and Demand description, where the Demand information is released by an enterprise as a main body, and is responsible for service docking by a corresponding individual user, as shown in fig. 4, the Demand information is a Demand and an enterprise and individual map structure.
Step 1.3: acquiring supply information, extracting supply entities, supply attributes and the relation between supply and enterprises and individuals, and constructing supply and enterprise and individual maps;
in the embodiment of the present invention, the category of the provisioning entity is supply, the provisioning attribute includes provisioning information such as a provisioning ID, a provisioning name, a provisioning type, a quantity, a price, an address, and a provisioning description, the provisioning information is issued by a business as a main body, and is subjected to business interfacing by a corresponding personal user, as shown in fig. 5, which is a mapping structure of the provisioning and the business and the individual.
Step 1.4: acquiring supply and demand docking record information, extracting a demand entity, a supply entity and a relation between demand and supply, and constructing a supply and demand entity map;
in the embodiment of the present invention, one demand entity may receive information of multiple supply entities, but only one successful docking record is included in the docking record, as shown in fig. 6, which is a schematic structural diagram of a map of the supply and demand entities.
Step 1.5: extracting a supply and demand category entity, a supply and demand category attribute, a relationship between supply and demand categories and a relationship between the supply and demand categories and the demand entity and the supply entity according to the demand information and the supply information to construct a supply and demand category and supply and demand entity map;
in the embodiment of the present invention, the supply and demand category may uniformly define category information of demand and supply based on manual definition and a classification model, and establish a supply and demand category and supply and demand entity map as shown in fig. 7 based on a relationship between the customized supply and demand category and the aforementioned supply entity and demand front.
Wherein the supply and demand information graph comprises the business to individual graph, the business entity graph, the demand and business, individual graph, the supply and demand entity graph, and the supply and demand category and supply and demand entity graph;
step 1.6: and storing the supply and demand information map in a map database.
Step 2: receiving demand information or supply information input by a user, calling the graph database, and searching the supply information matched with the demand information or the demand information matched with the supply information in the supply and demand information graph;
in the embodiment of the present invention, the corresponding matched supply information may be retrieved by receiving the demand information input by the user or the corresponding matched demand information may be retrieved by receiving the supply information input by the user, which specifically includes the following steps:
as shown in fig. 8, an alternative embodiment of step 2 of the present invention includes:
step 2.1 a: receiving demand information input by a user, extracting a demand entity and demand attributes in the demand information, and determining corresponding supply and demand categories and supply and demand category attributes;
in the embodiment of the invention, a user needs to input corresponding information according to a requirement information input format, extract a requirement entity and a requirement attribute in requirement information based on a knowledge extraction technology { NLP (natural language processing), NER (named entity identification) and the like }, and determine a corresponding supply and demand category and a corresponding supply and demand category attribute.
Step 2.2 a: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, and eliminating supply and demand type entity nodes with low matching degree until a supply and demand entity set related to the supply and demand type is obtained;
step 2.3 a: calculating the matching degree of the demand attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the demand entity in the supply and demand entity set into the supply entity associated with the demand entity set to obtain a supply entity set with fused matching degree;
in the embodiment of the present invention, specifically, the supply entity associated with the demand entity is supply information that has an accept _ by with the demand entity, and then the matching degree of the demand entity is used as an increment reference, and is superimposed to the matching degree of the corresponding supply entity in a certain proportion, so as to obtain a supply entity set with the fused matching degree.
As shown in fig. 9, another alternative implementation of embodiment 2 of the present invention includes:
step 2.1 b: receiving supply information input by a user, extracting a supply entity and supply attributes in the supply information, and determining corresponding supply and demand categories and supply and demand category attributes;
step 2.2 b: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, eliminating supply and demand type entity nodes with low matching degree until the supply and demand type entity nodes extend to supply and demand entities related to the supply and demand type, and then eliminating finished demand entities in the supply and demand entities to obtain a supply and demand entity set;
step 2.3 b: and calculating the matching degree of the supply attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the supply entity in the supply and demand entity set into the demand entity associated with the supply and demand entity set to obtain the demand entity set with the fused matching degree.
And step 3: and generating a corresponding recommendation list according to the supply information or the demand information obtained by matching, and returning the recommendation list to the user.
Step 3.1 a: sorting the supply entity set according to the matching degree to generate a corresponding supply information list, and returning the supply information list to the user; or
Step 3.1 b: and sequencing the demand entity set according to the matching degree to generate a corresponding demand information list, and returning the demand information list to the user.
Example two
As shown in fig. 10, another method for recommending supply and demand information based on a knowledge graph in an embodiment of the present invention includes:
step 1: acquiring supply and demand information, extracting entity, relation and attribute triples from the supply and demand information by using a knowledge extraction method, constructing a supply and demand information map according to the triples, and storing the supply and demand information map in a map database;
and 4, step 4: recommending supply information matched with demand information or demand information which may be required by the demand party for the demand party according to the supply and demand information map; and/or
And recommending demand information matched with the supply information for the supplier according to the supply and demand information map.
As shown in fig. 11, in the embodiment of the present invention, recommending, according to the supply and demand information map, supply information matched with demand information for a demand party includes:
step 4.1 a: acquiring current demand information, judging whether the current demand information is finished, and if so, finishing the current flow; otherwise, entering a step 4.2 a;
step 4.2 a: retrieving corresponding supply information based on the current demand information and generating a supply information list;
step 4.3 a: extracting the first N pieces of supply information in the supply information list, and adding the first N pieces of supply information into a supply information recommendation list corresponding to the current demand information;
step 4.4 a: repeating the steps 4.1 to 4.3 until a supply information recommendation list of all unfinished demands of the demand side is generated, and then randomly extracting a balanced amount of supply information from all the supply information recommendation lists and adding the supply information into a supply information recommendation summary table;
step 4.5 a: and sending the supply information recommendation summary table to the demand side.
In an embodiment of the present invention, the recommending, according to the supply and demand information map, demand information matched with supply information for a supplier includes:
step 4.1 b: acquiring current supply information and retrieving corresponding demand information based on the current supply information to generate a demand information list;
step 4.2 b: extracting the first N pieces of demand information in the demand information list, and adding the first N pieces of demand information into a demand information recommendation list corresponding to the current supply information;
step 4.3 b: repeating the step 4.1b to the step 4.2b until a demand information recommendation list of all supply information of the supplier is generated, and then randomly extracting a balanced amount of demand information from all the demand information recommendation lists and adding the demand information into a demand information recommendation summary table;
step 4.4 b: and sending the demand information recommendation summary table to the supplier.
In an embodiment of the present invention, the recommending, for a demander, demand information that may be required by the demander according to the supply and demand information map includes:
step 4.1 c: acquiring a demand entity vector of the demand party based on the enterprise entity of the demand party;
step 4.2 c: searching a demand entity set of the same type as the demand entity in the supply and demand information map according to the demand entity vector;
step 4.3 c: obtaining an associated business entity set based on the demand entity set;
step 4.4 c: acquiring a demand vector set corresponding to the enterprise entity set, and removing the demand vector of the demand party from the demand vector set to obtain a residual demand vector set of the related enterprise;
step 4.5 c: respectively calculating the matching degree between the enterprise entity vector of the demand party and the enterprise entity vectors in the related enterprise entity sets and the matching degree between the demand vector of the demand party and the residual demand vector sets;
step 4.6 c: combining the matching degree between the entity vectors of the enterprises and the matching degree between the demand vectors in a weight superposition mode, taking the combined matching degree as a recommendation score of the residual demand vectors of each related enterprise, and combining all the residual demand entity vectors of the related enterprises to obtain a preliminary recommendation demand vector list;
step 4.7 c: and sorting the preliminary recommendation demand vector list according to the matching degree scores, extracting the first N pieces of demand information, generating a demand information recommendation list which can be needed by the demand party, and sending the demand information recommendation list to the demand party.
Preferably, after the step 4.7c, the method further comprises:
step 4.8 c: and according to the supply and demand information map, sending the supply information which is successfully matched with the demand information in the demand information recommendation list to the demand party.
EXAMPLE III
The embodiment of the invention also provides a supply and demand information recommendation system based on the knowledge graph, and the terminal equipment comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method as described above when executing the computer program.
It should be understood that in the embodiments of the present Application, the Processor may be a central processing unit, and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, it is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.
Claims (10)
1. A supply and demand information recommendation method based on knowledge graph is characterized by comprising the following steps:
step 1: acquiring supply and demand information, extracting entity, relation and attribute triples from the supply and demand information by using a knowledge extraction method, constructing a supply and demand information map according to the triples, and storing the supply and demand information map in a map database;
step 2: receiving demand information or supply information input by a user, calling the graph database, and searching the supply information matched with the demand information or the demand information matched with the supply information in the supply and demand information graph;
and step 3: and generating a corresponding recommendation list according to the supply information or the demand information obtained by matching, and returning the recommendation list to the user.
2. The knowledge-graph-based supply and demand information recommendation method according to claim 1, further comprising, after the step 1:
and 4, step 4: recommending supply information matched with demand information or demand information which may be required by the demand party for the demand party according to the supply and demand information map; and/or
And recommending demand information matched with the supply information for the supplier according to the supply and demand information map.
3. The knowledge-graph-based supply and demand information recommendation method according to claim 1, wherein the step 1 comprises:
step 1.1: acquiring user information, and constructing an enterprise and personal map according to enterprise entities, enterprise attributes, personal entities, personal attributes and the relationship between enterprises and individuals in the user information; constructing an enterprise entity map according to the enterprise information;
step 1.2: acquiring demand information, extracting a demand entity, demand attributes and the relation between the demand and enterprises and individuals, and constructing a demand, enterprise and individual maps;
step 1.3: acquiring supply information, extracting supply entities, supply attributes and the relation between supply and enterprises and individuals, and constructing supply and enterprise and individual maps;
step 1.4: acquiring supply and demand docking record information, extracting a demand entity, a supply entity and a relation between demand and supply, and constructing a supply and demand entity map;
step 1.5: extracting a supply and demand category entity, a supply and demand category attribute, a relationship between supply and demand categories and a relationship between the supply and demand categories and the demand entity and the supply entity according to the demand information and the supply information to construct a supply and demand category and supply and demand entity map;
wherein the supply and demand information graph comprises the business to individual graph, the business entity graph, the demand and business, individual graph, the supply and demand entity graph, and the supply and demand category and supply and demand entity graph;
step 1.6: and storing the supply and demand information map in a map database.
4. The knowledge-graph-based supply and demand information recommendation method according to claim 1, wherein the step 2 comprises:
step 2.1 a: receiving demand information input by a user, extracting a demand entity and demand attributes in the demand information, and determining corresponding supply and demand categories and supply and demand category attributes;
step 2.2 a: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, and eliminating supply and demand type entity nodes with low matching degree until a supply and demand entity set related to the supply and demand type is obtained;
step 2.3 a: calculating the matching degree of the demand attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the demand entity in the supply and demand entity set into the supply entity associated with the demand entity set to obtain a supply entity set with fused matching degree;
the step 3 comprises the following steps:
step 3.1 a: and sequencing the supply entity set according to the matching degree to generate a corresponding supply information list, and returning the supply information list to the user.
5. The knowledge-graph-based supply and demand information recommendation method according to claim 1, wherein the step 2 further comprises:
step 2.1 b: receiving supply information input by a user, extracting a supply entity and supply attributes in the supply information, and determining corresponding supply and demand categories and supply and demand category attributes;
step 2.2 b: searching and matching in the supply and demand information map step by step according to the supply and demand type and the supply and demand type attribute, eliminating supply and demand type entity nodes with low matching degree until the supply and demand type entity nodes extend to supply and demand entities related to the supply and demand type, and then eliminating finished demand entities in the supply and demand entities to obtain a supply and demand entity set;
step 2.3 b: calculating the matching degree of the supply attribute vector of the user and the supply and demand entity attribute vector in the supply and demand entity set, and fusing the matching degree of the supply entity in the supply and demand entity set into the demand entity associated with the supply and demand entity set to obtain a demand entity set with fused matching degree;
the step 3 comprises the following steps:
step 3.1 b: and sequencing the demand entity set according to the matching degree to generate a corresponding demand information list, and returning the demand information list to the user.
6. The knowledge-graph-based supply and demand information recommendation method according to claim 2, wherein the step 4 comprises:
step 4.1 a: acquiring current demand information, judging whether the current demand information is finished, and if so, finishing the current flow; otherwise, entering a step 4.2 a;
step 4.2 a: retrieving corresponding supply information based on the current demand information and generating a supply information list;
step 4.3 a: extracting the first N pieces of supply information in the supply information list, and adding the first N pieces of supply information into a supply information recommendation list corresponding to the current demand information;
step 4.4 a: repeating the steps 4.1 to 4.3 until a supply information recommendation list of all unfinished demands of the demand side is generated, and then randomly extracting a balanced amount of supply information from all the supply information recommendation lists and adding the supply information into a supply information recommendation summary table;
step 4.5 a: and sending the supply information recommendation summary table to the demand side.
7. The knowledge-graph-based supply and demand information recommendation method according to claim 2, wherein the step 4 further comprises:
step 4.1 b: acquiring current supply information and retrieving corresponding demand information based on the current supply information to generate a demand information list;
step 4.2 b: extracting the first N pieces of demand information in the demand information list, and adding the first N pieces of demand information into a demand information recommendation list corresponding to the current supply information;
step 4.3 b: repeating the step 4.1b to the step 4.2b until a demand information recommendation list of all supply information of the supplier is generated, and then randomly extracting a balanced amount of demand information from all the demand information recommendation lists and adding the demand information into a demand information recommendation summary table;
step 4.4 b: and sending the demand information recommendation summary table to the supplier.
8. The knowledge-graph-based supply and demand information recommendation method according to claim 2, wherein the step 4 further comprises:
step 4.1 c: acquiring a demand entity vector of the demand party based on the enterprise entity of the demand party;
step 4.2 c: searching a demand entity set of the same type as the demand entity in the supply and demand information map according to the demand entity vector;
step 4.3 c: obtaining an associated business entity set based on the demand entity set;
step 4.4 c: acquiring a demand vector set corresponding to the enterprise entity set, and removing the demand vector of the demand party from the demand vector set to obtain a residual demand vector set of the related enterprise;
step 4.5 c: respectively calculating the matching degree between the enterprise entity vector of the demand party and the enterprise entity vectors in the related enterprise entity sets and the matching degree between the demand vector of the demand party and the residual demand vector sets;
step 4.6 c: combining the matching degree between the entity vectors of the enterprises and the matching degree between the demand vectors in a weight superposition mode, taking the combined matching degree as a recommendation score of the residual demand vectors of each related enterprise, and combining all the residual demand entity vectors of the related enterprises to obtain a preliminary recommendation demand vector list;
step 4.7 c: and sorting the preliminary recommendation demand vector list according to the matching degree scores, extracting the first N pieces of demand information, generating a demand information recommendation list which can be needed by the demand party, and sending the demand information recommendation list to the demand party.
9. The knowledge-graph-based supply and demand information recommendation method according to claim 8, wherein after the step 4.7c, the method further comprises:
step 4.8 c: and according to the supply and demand information map, sending the supply information which is successfully matched with the demand information in the demand information recommendation list to the demand party.
10. A supply and demand information recommendation system based on a knowledge graph, comprising a memory, a processor and a transceiver which are sequentially connected in a communication manner, wherein the memory is used for storing a computer program, the transceiver is used for sending and receiving messages, and the processor is used for reading the computer program and executing the supply and demand information recommendation method based on the knowledge graph according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011444487.4A CN112541072B (en) | 2020-12-08 | 2020-12-08 | Supply and demand information recommendation method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011444487.4A CN112541072B (en) | 2020-12-08 | 2020-12-08 | Supply and demand information recommendation method and system based on knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112541072A true CN112541072A (en) | 2021-03-23 |
| CN112541072B CN112541072B (en) | 2022-12-02 |
Family
ID=75018334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011444487.4A Active CN112541072B (en) | 2020-12-08 | 2020-12-08 | Supply and demand information recommendation method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541072B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240399A (en) * | 2021-05-31 | 2021-08-10 | 东莞理工学院 | Supply and demand matching method and system for scientific and technological innovation and industrial transformation |
| CN113780786A (en) * | 2021-09-01 | 2021-12-10 | 北京橙色云科技有限公司 | Project requirement matching method and device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383894A (en) * | 2016-09-23 | 2017-02-08 | 深圳市由心网络科技有限公司 | Enterprise supply-demand information matching method and apparatus |
| WO2017041372A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN109522420A (en) * | 2018-11-16 | 2019-03-26 | 广东小天才科技有限公司 | A kind of method and system obtaining learning demand |
| CN110727852A (en) * | 2018-07-16 | 2020-01-24 | Tcl集团股份有限公司 | Method, device and terminal for pushing recruitment recommendation service |
| CN110825887A (en) * | 2019-11-14 | 2020-02-21 | 北京京航计算通讯研究所 | Knowledge graph fusion method |
| CN111177591A (en) * | 2019-12-10 | 2020-05-19 | 浙江工业大学 | Knowledge graph-based Web data optimization method facing visualization demand |
| CN111369318A (en) * | 2020-02-28 | 2020-07-03 | 安徽农业大学 | Commodity knowledge graph feature learning-based recommendation method and system |
| CN111581990A (en) * | 2020-05-14 | 2020-08-25 | 中国银行股份有限公司 | Cross-border transaction matching method and device |
| CN111984873A (en) * | 2020-09-21 | 2020-11-24 | 北京信息科技大学 | Service recommendation system and method |
-
2020
- 2020-12-08 CN CN202011444487.4A patent/CN112541072B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017041372A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN106383894A (en) * | 2016-09-23 | 2017-02-08 | 深圳市由心网络科技有限公司 | Enterprise supply-demand information matching method and apparatus |
| CN110727852A (en) * | 2018-07-16 | 2020-01-24 | Tcl集团股份有限公司 | Method, device and terminal for pushing recruitment recommendation service |
| CN109522420A (en) * | 2018-11-16 | 2019-03-26 | 广东小天才科技有限公司 | A kind of method and system obtaining learning demand |
| CN110825887A (en) * | 2019-11-14 | 2020-02-21 | 北京京航计算通讯研究所 | Knowledge graph fusion method |
| CN111177591A (en) * | 2019-12-10 | 2020-05-19 | 浙江工业大学 | Knowledge graph-based Web data optimization method facing visualization demand |
| CN111369318A (en) * | 2020-02-28 | 2020-07-03 | 安徽农业大学 | Commodity knowledge graph feature learning-based recommendation method and system |
| CN111581990A (en) * | 2020-05-14 | 2020-08-25 | 中国银行股份有限公司 | Cross-border transaction matching method and device |
| CN111984873A (en) * | 2020-09-21 | 2020-11-24 | 北京信息科技大学 | Service recommendation system and method |
Non-Patent Citations (3)
| Title |
|---|
| 张肃等: "基于知识图谱的企业知识服务模型构建研究", 《情报科学》 * |
| 赵紫英等: "基金行业知识图谱的构建与应用", 《金融纵横》 * |
| 阮光册等: "知识图谱在实体检索中的应用研究综述", 《图书情报工作》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240399A (en) * | 2021-05-31 | 2021-08-10 | 东莞理工学院 | Supply and demand matching method and system for scientific and technological innovation and industrial transformation |
| CN113780786A (en) * | 2021-09-01 | 2021-12-10 | 北京橙色云科技有限公司 | Project requirement matching method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112541072B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9432826B2 (en) | Event planning within social networks | |
| US20200036762A1 (en) | Facilitating conversations with automated location mapping | |
| CN107656969A (en) | A kind of information recommendation method and device | |
| US20130024105A1 (en) | Location-based employment search using employer and candidate mobile communication devices | |
| CN112541072B (en) | Supply and demand information recommendation method and system based on knowledge graph | |
| CN103700003A (en) | House online direct renting method and system based on wish conformity matching | |
| AU2013305922A1 (en) | Hierarchical based sequencing machine learning model | |
| CN102903047A (en) | Method and device for releasing commodity information | |
| CN110837917A (en) | Customer visit management system, method, terminal equipment and storage medium | |
| CN102722836A (en) | Automatic bid inviting and bid competing system and method applied to internet | |
| EP2929494A1 (en) | Finding objects or services utilizing a communication link to enlist the help of and reward third parties to help locate the desired object or service | |
| CN107257362B (en) | Method and system for dynamically displaying events and matching chats on map according to attention degree of time | |
| US20200143270A1 (en) | Virtual assistant negotiation system and method thereof | |
| US20210248521A1 (en) | Reservation buying/selling systems and methods | |
| CN110276666A (en) | A kind of real time service method of commerce based on supply and demand both sides | |
| CN108334353A (en) | Skill development system and method | |
| CN106156971B (en) | Logistics resource collaborative relationship information processing method and device | |
| CN104268765A (en) | Demand-driven instant transaction system based on mobile Internet technology | |
| CN111523030B (en) | Newspaper disc information recommendation method and device and computer readable storage medium | |
| CN115757718A (en) | Text generation method and device | |
| US10459936B2 (en) | Information search method and apparatus | |
| CN113761127A (en) | Task processing method and device, electronic equipment and storage medium | |
| CN109801052A (en) | A kind of transfer account method and payment platform | |
| CN108984666A (en) | Data processing method, data processing equipment and server | |
| CN113408832B (en) | Training planning anchoring method and device based on fusion geographic relationship and middle platform |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |