A supply-demand resource pushing method and device based on business opportunity elements and a medium

Abstract

The embodiment of the specification discloses a supply-demand resource pushing method and device based on business opportunity elements, equipment and medium, the method comprises the following steps: acquiring inquiry information uploaded by a demand side client in a preset time period, to determine an initial range of demand resources corresponding to the demand side client based on the inquiry information; calling historical demand resource transaction information of the demand side client, to generate initial business opportunity elements corresponding to the demand side client based on the historical demand resource transaction information and the initial range of demand resources; obtaining an extended demand side client associated with the demand side client according to a preset collaborative filtering strategy, and extracting extended business opportunity elements of the extended demand side client, to determine to-be-pushed business opportunity elements based on the initial business opportunity elements and the extended business opportunity elements; constructing a supply-demand resource portrait according to the to-be-pushed business opportunity elements; and realizing the interactive pushing of the supply-demand resources of the demand side client and the supply side client according to the matching degree of the supply-demand resource portrait and each supplier's preset label.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of data processing, and in particular to a supply-demand resource pushing method based on business opportunity elements, equipment and medium. BACKGROUND

[0002] With the continuous expansion of e-commerce, the number and variety of goods are rapidly increasing, and customers are trapped in a large amount of information, and need to spend a lot of time to find the goods they want to buy. This process of browsing a large amount of irrelevant information and products will undoubtedly make consumers who are overwhelmed by information overload problems continue to flow, so that the demand side cannot quickly and effectively make a purchase decision, and only based on the demand side active search process, so that the supplier may miss possible transactions, resulting in business opportunity loss problem. Therefore, the targeted pushing of supply-demand resources is an important link in the online transaction process.

[0003] In the prior art, when providing business opportunities to suppliers based on business opportunity pushing technology, most business opportunity pushing technologies are based on the subscription relationship between the demand side keywords and business opportunity tags for pushing. When pushing supply-demand resources based on the subscription method, on the one hand, the range of demand resources that the demand side can choose is small, and it is difficult to obtain the corresponding supplier to provide products, on the other hand, the suppliers who do not exist subscription relationship have lost a large number of potential transactions, and cannot timely master the supply-demand resource interaction between the business opportunity and the demand side. SUMMARY

[0004] In order to solve the above technical problems, one or more embodiments of the present specification provide a supply-demand resource pushing method based on business opportunity elements, equipment and medium.

[0005] One or more embodiments of the present specification adopt the following technical solutions:

[0006] One or more embodiments of the present specification provide a supply-demand resource pushing method based on business opportunity elements, and the method comprises:

[0007] Obtaining one or more inquiry information uploaded by a demand side client in a preset time period, to determine an initial range of demand resources corresponding to the demand side client based on the inquiry information;

[0008] Calling historical demand resource transaction information of the demand side client, to generate initial business opportunity elements corresponding to the demand side client based on the historical demand resource transaction information and the initial range of demand resources; wherein the historical demand resource transaction information includes historical inquiry information and transaction commodity basic information;

[0009] According to the preset collaborative filtering strategy, an extended demand-side client associated with the demand-side client is acquired, and an extended business opportunity element of the extended demand-side client is extracted, so as to determine a to-be-pushed business opportunity element based on the initial business opportunity element and the extended business opportunity element;

[0010] According to the to-be-pushed business opportunity element, a supply-demand resource portrait corresponding to the demand-side client is constructed;

[0011] According to the matching degree of the supply-demand resource portrait and each supplier preset label, a matching relationship of a supply-side client corresponding to the demand-side client is established, so as to realize interaction pushing of supply-demand resources of the demand-side client and the supply-side client based on the matching relationship.

[0012] Optionally, in one or more embodiments of the present specification, the initial range of demand resources corresponding to the demand-side client is determined based on the inquiry information, specifically comprising:

[0013] The inquiry information is split based on a preset character length to obtain inquiry information segmentation, the segmentation features of the inquiry information segmentation are acquired, and the segmentation features are input into a preset deep learning model to obtain inquiry keywords of the demand-side client; wherein the segmentation features include part-of-speech features, named entity features;

[0014] According to the semantics of the inquiry keywords, the corresponding extended keywords of each inquiry keyword are retrieved to obtain a keyword set corresponding to the inquiry information based on the inquiry keywords and the extended keywords;

[0015] The keyword set is divided into a first keyword set and a second keyword set; wherein the first keyword set is a keyword set without numbers, and the second keyword set is a keyword set containing numbers;

[0016] The first keyword set is clustered to obtain demand resource attribute information, and the context information of each keyword in the second keyword set is acquired to obtain demand resource price information based on the context information; wherein the demand resource attribute information includes demand resource type, demand resource quantity, and demand resource name; and the demand price information includes expected price range and acceptable price range;

[0017] Based on the demand resource attribute information and the demand price information, the initial range of demand resources corresponding to the demand-side client is determined.

[0018] Optionally, in one or more embodiments of the present specification, the first keyword set is clustered to obtain demand resource attribute information, specifically comprising:

[0019] Obtain the word vectors of each keyword in the first keyword set, and determine the similarity between each keyword based on the distance between the word vectors;

[0020] One or more feature center keywords are determined from the keyword set, and multiple keyword clusters are determined based on the similarity between the feature center keywords and each of the keywords;

[0021] Determine the similarity between each keyword in the keyword cluster. If the similarity is less than a preset threshold, iteratively divide the keyword cluster to obtain a keyword cluster that meets the requirements.

[0022] By integrating the semantic information of each keyword in each keyword cluster, the required resource attribute information is obtained.

[0023] Optionally, in one or more embodiments of this specification, historical demand resource transaction information of the demand-side client is invoked to generate initial business opportunity elements corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources, specifically including:

[0024] The historical demand resource transaction information of the demand side client is invoked to determine the transaction rate, attribute information of each historical demand resource, and corresponding transaction price of each historical demand resource based on the historical demand resource transaction information.

[0025] If the historical demand resource attribute information corresponds to the demand resource attribute information of the initial range of the demand resource, and the transaction rate of the historical demand resource is less than the preset transaction threshold, then the query rate of the demand resource attribute information for a preset time period is obtained.

[0026] The query rate and the transaction rate of historical demand resources are combined based on a preset weight ratio to obtain the probability that business opportunity elements can be generated. If the probability that business opportunity elements can be generated is less than a preset production probability threshold, then the initial extraction of business opportunity elements is not performed.

[0027] If the historical demand resource attribute information corresponds to the demand resource attribute information of the initial range of the demand resources, and the transaction rate of the historical demand resources is greater than a preset threshold, then according to the timestamp corresponding to the historical demand resource attribute information, the average market price corresponding to each demand resource in the historical demand resource attribute information is called.

[0028] Based on the average market price and the corresponding historical transaction prices of demanded resources, determine the price deviation range;

[0029] adjust the initial range of the demand resource based on the price deviation range to obtain a demand resource range, and extract information from the demand resource range according to a preset opportunity announcement template of the supplier client to obtain initial opportunity elements corresponding to the demand client.

[0030] Optionally, in one or more embodiments of the present specification, the extended demand clients associated with the demand client are obtained according to a preset collaborative filtering strategy, and the extended opportunity elements of the extended demand clients are extracted to determine the to-be-pushed opportunity elements based on the initial opportunity elements and the extended opportunity elements, specifically comprising:

[0031] establish a historical scoring matrix of the demand client for each demand resource according to historical demand resource transaction information of the demand client;

[0032] determine the graph data in which the demand client is located, and obtain the extended demand clients in the graph data that match the historical scoring matrix based on a Pearson similarity algorithm; wherein the demand client corresponds to one or more graph data;

[0033] obtain the difference set of the current opportunity elements of the extended demand clients and the initial opportunity elements of the demand client, and take each of the opportunity elements in the difference set as an initial extended opportunity element;

[0034] obtain the historical score corresponding to the initial extended opportunity element, and filter the initial extended opportunity element based on the historical score to obtain an extended opportunity element; wherein the historical score is obtained through the historical scoring matrix of the extended demand client;

[0035] obtain the union of the initial opportunity elements and the extended opportunity elements, and take the union as the to-be-pushed opportunity elements.

[0036] Optionally, in one or more embodiments of the present specification, before obtaining the extended demand clients in the graph data that match the historical scoring matrix based on the Pearson similarity algorithm, the method further comprises:

[0037] extract the connected graph data in the graph data in which the demand client is located, and obtain the valid connected graph data containing the demand client in the connected graph data;

[0038] determine the first extended demand client and the second extended demand client corresponding to the demand client based on the connected relationship of each of the valid connected graph data; wherein the first extended demand client is directly connected with the demand client, and the second extended demand client is indirectly connected with the demand client;

[0039] obtaining an indirect connection path of the second extended demand-side client, to determine a degree of association between the second extended demand-side client and the demand-side client according to a path length of the indirect connection path;

[0040] filtering the second extended demand-side client based on a preset degree of association threshold, to obtain a third extended demand-side client;

[0041] merging the first extended demand-side client and the third extended demand-side client, to determine an extended demand-side client to be matched in the extended demand-side client, so as to obtain an extended demand-side client matched with the historical score matrix in the extended demand-side client to be matched based on a Pearson similarity algorithm.

[0042] Optionally, in one or more embodiments of the present specification, before the matching relationship between the demand-side client and the corresponding supply-side client is established according to the matching degree of the supply-demand resource portrait and the preset label of each supplier, the method further comprises:

[0043] obtaining historical sales information of each supply-side client and business product information uploaded by each supply-side client, to determine a supply product service type corresponding to the supply-side client based on the historical sales information and the business product information; wherein the supply product service type includes wholesale service, retail service and presale service;

[0044] grouping supply content of each supply-side client based on the supply product service type, and establishing a first association relationship between the supply-side client and each supply product service type;

[0045] obtaining business product information and supply range information under each supply product service type, to determine a supply resource limiting label of each supply resource based on the business product information and the supply range information, to establish a second association relationship between the supply resource and the supply resource limiting label under the supply service type;

[0046] determining a description label of each supply resource according to description information of each supply resource uploaded by each supply-side client, to determine a third association relationship between the description label and the supply resource;

[0047] establishing an association knowledge graph of the supply-side client, the supply product service type and the supply resource based on the first association relationship, the second association relationship and the third association relationship.

[0048] Optionally, in one or more embodiments of the present specification, a matching relationship between the demand-side client and the supply-side client corresponding thereto is established according to the matching degree of the supply-demand resource portrait and the preset label of each supplier, and specifically includes:

[0049] obtaining one or more supplier preset labels of the supply-side client corresponding to the supply-demand resource portrait; wherein the supplier preset label includes the supply resource limited label and the description label of the supply resource;

[0050] obtaining the supply-side client corresponding to the supplier preset label according to the association knowledge graph, and obtaining a traceability path between the supply-demand resource portrait and the supply-side client;

[0051] obtaining a historical transaction evaluation consistent with the traceability path based on a preset database, and obtaining the number of first evaluations and the number of second evaluations of the historical transaction evaluation; wherein the first evaluation and the second evaluation correspond to different evaluation score ranges, and the evaluation score range of the first evaluation is greater than the evaluation score range of the second evaluation;

[0052] determining the proportion of the first evaluation and the proportion of the second evaluation based on the number of the first evaluation and the number of the second evaluation, respectively;

[0053] if the proportion of the first evaluation is greater than a preset beneficial proportion and the proportion of the second evaluation is less than a preset harmful proportion, a matching relationship between the demand-side client and the supply-side client corresponding thereto is established.

[0054] One or more embodiments of the present specification provide a supply-demand resource pushing device based on business opportunity elements, the device comprising:

[0055] at least one processor; and

[0056] a memory in communication connection with the at least one processor; wherein

[0057] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0058] obtain one or more inquiry information uploaded by a demand-side client in a preset time period, to determine a demand resource initial range corresponding to the demand-side client based on the inquiry information;

[0059] call the historical demand resource transaction information of the demand side client, to extract the initial business opportunity elements corresponding to the demand side client based on the historical demand resource transaction information and the demand resource initial range; wherein the historical demand resource transaction information includes: historical inquiry information, transaction commodity basic information;

[0060] According to the preset collaborative filtering strategy, an extended demand side client associated with the demand side client is obtained, and an extended business opportunity element of the extended demand side client is extracted, so as to determine a to-be-pushed business opportunity element based on the initial business opportunity element and the extended business opportunity element;

[0061] According to the to-be-pushed business opportunity element, a supply and demand resource portrait corresponding to the demand side client is constructed;

[0062] According to the matching degree of the supply and demand resource portrait and each supplier preset label, a matching relationship of the supplier side client corresponding to the demand side client is established, so as to realize the interactive push of the supply and demand resources of the demand side client and the supplier side client based on the matching relationship.

[0063] One or more embodiments of the present specification provide a non-volatile computer storage medium, which stores computer executable instructions, the computer executable instructions are configured to:

[0064] Obtain one or more inquiry information uploaded by a demand side client in a preset time period, to determine a demand resource initial range corresponding to the demand side client based on the inquiry information;

[0065] Call the historical demand resource transaction information of the demand side client, to extract the initial business opportunity elements corresponding to the demand side client based on the historical demand resource transaction information and the demand resource initial range; wherein the historical demand resource transaction information includes: historical inquiry information, transaction commodity basic information;

[0066] According to the preset collaborative filtering strategy, an extended demand side client associated with the demand side client is obtained, and an extended business opportunity element of the extended demand side client is extracted, so as to determine a to-be-pushed business opportunity element based on the initial business opportunity element and the extended business opportunity element;

[0067] According to the to-be-pushed business opportunity element, a supply and demand resource portrait corresponding to the demand side client is constructed;

[0068] According to the matching degree of the supply and demand resource portrait and each supplier preset label, a matching relationship of the supplier side client corresponding to the demand side client is established, so as to realize the interactive push of the supply and demand resources of the demand side client and the supplier side client based on the matching relationship.

[0069] The at least one technical scheme adopted by the embodiments of the present specification can achieve the following beneficial effects:

[0070] Based on the keyword clustering of the inquiry information, the initial range of demand resources is obtained, avoiding the problem of too small resource range caused by obtaining demand resources based on subscription relationship in the prior art. By obtaining the extended demand side client associated with the demand side client and extracting the extended business opportunity elements of the extended demand side client, the adjustment and expansion of the initial business opportunity elements are realized, so that the number of business opportunities obtained by the supply side client is improved, and the problem of potential business opportunity omission is reduced. By constructing the supply-demand resource portrait corresponding to the demand side client based on the to-be-pushed business opportunity elements, the association relationship between the supply side client and the demand side client can be established based on the matching degree of the supply-demand resource portrait and the preset label of each supplier, so as to speed up the query matching efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present specification, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0072] Figure 1 A flowchart of a supply-demand resource pushing method based on business opportunity elements provided by the embodiments of the present specification;

[0073] Figure 2 An internal structure diagram of a supply-demand resource pushing device based on business opportunity elements provided by the embodiments of the present specification;

[0074] Figure 3 An internal structure diagram of a non-volatile storage medium provided by the embodiments of the present specification. DETAILED DESCRIPTION

[0075] The embodiments of the present specification provide a supply-demand resource pushing method, device and medium based on business opportunity elements.

[0076] In order to enable those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be described clearly and completely in conjunction with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only some of the embodiments of the present specification, not all. Based on the embodiments of the present specification, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present specification.

[0077] AsFigure 1 As shown, a flowchart of a supply-demand resource pushing method based on business opportunity elements is provided in one or more embodiments of the present specification. The method comprises the following steps: Figure 1 As shown, a flowchart of a supply-demand resource pushing method based on business opportunity elements is provided in one or more embodiments of the present specification. The method comprises the following steps:

[0078] S101: Obtain one or more inquiry information uploaded by a demand side client within a preset time period, to determine an initial range of demand resources corresponding to the demand side client based on the inquiry information.

[0079] In order to solve the problem that the resource acquisition range is small and the supply side business opportunity is easy to lose due to the resource pushing based on the subscription relationship only. In one or more embodiments of the present specification, first, one or more inquiry information uploaded by a demand side client within a preset time period is obtained for analysis, so as to determine an initial range of demand resources corresponding to the demand side client according to the inquiry information. For example, it is determined according to the inquiry information that the inquiry object is a clothing product, the inquiry product is a skirt, and the price is 100 yuan, so it can be determined that the initial range of demand resources is women's clothing in the clothing category with a price within a floating range of 100 yuan, realizing the initial locking of the demand resources of the demand side client.

[0080] Specifically, in one or more embodiments of the present specification, the initial range of demand resources corresponding to the demand side client is determined based on the inquiry information, which specifically comprises the following steps:

[0081] Firstly, the inquiry information is split according to the preset character length, so as to obtain inquiry information words corresponding to the inquiry information. Then, the word segmentation features of the inquiry information words are obtained, such as the part-of-speech features, semantic features, named entity features, etc. of the inquiry information analysis, and the word segmentation features are input into the preset deep learning model, so as to obtain the inquiry keywords in the inquiry information of the demand side client. Then, according to the semantics of the inquiry keywords, the expansion keywords corresponding to each inquiry keyword are retrieved, so as to construct a keyword set corresponding to the inquiry information according to the inquiry keywords and the expansion keywords. In order to lock the initial range of demand resource of the demand side client based on the keywords, the keyword set is divided into a first keyword set and a second keyword set in the embodiments of the present specification. It should be noted that the first keyword set is a keyword set without numbers, and the second keyword set is a keyword set containing numbers. Then, the first keyword set is clustered to obtain demand resource attribute information, and the context information of each keyword in the second keyword set is obtained, so as to obtain demand resource price information according to the context information of the position where the keyword is located. It should be noted that the demand resource attribute information includes demand resource type, demand resource quantity, demand resource name, etc. and the demand price information includes expected price range, acceptable price range, etc. Thus, the initial range of demand resource corresponding to the demand side client is determined according to the demand resource attribute information and the demand price information.

[0082] Further, in one or more embodiments of the present specification, the first keyword set is clustered to obtain demand resource attribute information, which includes the following processes:

[0083] Firstly, the word vectors of the keywords in the first keyword set are obtained, and then the similarity between the keywords is determined according to the distance between the word vectors. Then, one or more feature center keywords in the keyword set are determined, so as to determine a plurality of keyword clustering clusters according to the similarity between the feature center keywords and the keywords. Then, the similarity between the keywords in the keyword clustering cluster is obtained based on the distance between the word vectors. If the similarity is less than a preset threshold, the keyword clustering cluster is iteratively divided until the similarity between the keywords in the keyword clustering cluster meets the requirements, and the keyword clustering cluster meeting the requirements is obtained. Then, the semantic information of the keywords in each keyword clustering cluster is fused to obtain the demand resource attribute information. For example, the semantic information of "skirt, skirt length, skirt shape" in a keyword clustering cluster can obtain the attribute information of the skirt demand resource through the fusion of the semantic information of the keywords in the keyword clustering cluster.

[0084] S102: call the historical demand resource transaction information of the demand side client, to generate an initial business opportunity element corresponding to the demand side client based on the historical demand resource transaction information and the demand resource initial range. The historical demand resource transaction information includes historical inquiry information and transaction commodity basic information.

[0085] To accurately speculate the interested resources of the demand client, and provide the supply side with potential business opportunities with high transaction rates, in the embodiments of the present specification, the historical demand resource transaction information of the demand side client is called to enrich and correct the demand resource initial range of the current demand client according to the historical demand resource transaction information obtained by calling, so as to generate an initial business opportunity element corresponding to the demand side client. It can be understood that the historical demand resource transaction information includes historical inquiry information and transaction commodity basic information such as commodity name and commodity price.

[0086] Specifically, in one or more embodiments of the present specification, the historical demand resource transaction information of the demand side client is called to generate an initial business opportunity element corresponding to the demand side client based on the historical demand resource transaction information and the demand resource initial range, which specifically includes the following steps:

[0087] Firstly, the historical demand resource transaction information of the demand side client is called to determine the transaction rate of each historical demand resource, the attribute information of each historical demand resource, and the corresponding historical demand resource transaction price according to the historical demand resource transaction information. If the historical demand resource attribute information corresponds to the demand resource attribute information of the demand resource initial range, and the transaction rate of the historical demand resource is less than a preset transaction threshold, the query rate of the demand side client to the demand resource attribute information within a preset time period is obtained.

[0088] Then, the query rate and the transaction rate of the historical demand resource are combined through a pre-set weight ratio to obtain a business opportunity element generation probability. That is, a pre-set query rate weight ratio W1 and a transaction rate weight ratio W2 are determined, and the business opportunity element generation probability is obtained by combining W1*query rate+W2*transaction rate. If the business opportunity element generation probability is less than a pre-set production probability threshold, the initial business opportunity element is not extracted.

[0089] In another case, if the historical demand resource attribute information corresponds to the demand resource attribute information of the initial range of demand resources, and the transaction rate of the historical demand resources is greater than a preset threshold, then the market average price corresponding to the historical demand resource attribute information is called according to the time stamp corresponding to the historical demand resource attribute information. Then, according to the market average price and the corresponding historical demand resource transaction price, the allowed price deviation range is determined, that is, the price accepted by the demand side client within the price deviation range. Then, the initial range of demand resources is adjusted according to the price deviation range obtained above to obtain a demand resource range, and information extraction is performed on the information in the demand resource range according to the preset opportunity announcement template of the supply side client to obtain the initial opportunity elements corresponding to the demand side client.

[0090] S103: According to the preset collaborative filtering strategy, an extended demand side client associated with the demand side client is obtained, and an extended opportunity element of the extended demand side client is extracted to determine a to-be-pushed opportunity element based on the initial opportunity element and the extended opportunity element.

[0091] In order to expand the potential opportunities of the supply side, avoid economic losses caused by opportunity omission, and save the calculation cost of repeated analysis, in one or more embodiments of the present specification, an extended demand side client associated with the demand side client is obtained according to a preset collaborative filtering strategy. Then, the extended opportunity element of the extended demand side client is extracted to realize the mining and expansion of the opportunity, so as to determine the to-be-pushed opportunity element based on the initial opportunity element and the extended opportunity element.

[0092] Specifically, in one or more embodiments of the present specification, according to the preset collaborative filtering strategy, an extended demand side client associated with the demand side client is obtained, and an extended opportunity element of the extended demand side client is extracted to determine a to-be-pushed opportunity element based on the initial opportunity element and the extended opportunity element, which specifically includes the following steps:

[0093] According to the historical demand resource transaction information of the demand side client, a historical scoring matrix of the demand side client for each demand resource is established. Then, in order to expand the demand resource through a user similar to the user of the demand side client, a graph data in which the demand side client is located is determined in the embodiment of the description, so as to obtain an expanded demand side client matched with the historical scoring matrix in the graph data according to the Pearson similarity algorithm. It should be noted that the demand side client corresponds to one or more graph data, and it should be noted that the Pearson similarity algorithm is an algorithm for calculating the similarity between two variables based on the Pearson correlation coefficient in the prior art, which will not be described in detail here. After obtaining the matched expanded demand side client based on the above process, a difference set of the current opportunity elements of the expanded demand side client and the initial opportunity elements of the demand side client is obtained, so as to take each opportunity element in the difference set as an initial expanded opportunity element. Then, the historical score corresponding to the initial expanded opportunity element is obtained, so as to filter the initial expanded opportunity element according to the historical score and obtain an expanded opportunity element. It should be noted that the historical score is obtained through the historical scoring matrix of the expanded demand side client. After obtaining the expanded opportunity element, the initial opportunity element and the expanded opportunity element are taken as a union set, and the to-be-pushed opportunity element after the expansion of the opportunity element is obtained.

[0094] Further, in one or more embodiments of the description, before the expanded demand side client matched with the historical scoring matrix in the graph data is obtained based on the Pearson similarity algorithm, the method further includes the following process:

[0095] By determining whether there is a connected path between each node in the graph data, the demand side client is extracted in the connected graph data in the graph data, further, it is judged whether there is a demand side client in the connected graph data, so as to extract the effective connected graph data containing the demand side client in the connected graph data. According to the connection relationship of each effective connected graph data, the first extended demand side client corresponding to the demand side client and the second extended demand side client are determined. It should be noted that the first extended demand side client is directly connected with the demand side client, and the second extended demand side client is indirectly connected with the demand side client. Then, the indirect connection path of the second extended demand side client is obtained, so as to determine the association degree between the second extended demand side client and the demand side client according to the path length of the indirect connection path. It can be understood that the path length and the association degree are inversely proportional, that is, the longer the path length is, the lower the association degree is. According to the pre-set association degree threshold, the second extended demand side client is filtered, and the third extended demand side client is obtained. Then, the first extended demand side client and the third extended demand side client are merged, so as to determine the to-be-matched extended demand side client in the extended demand side client, so as to obtain the extended demand side client matched with the historical score matrix in the to-be-matched extended demand side client by the Pearson similarity algorithm in the above steps. At the same time, the calculation cost wasted by directly calculating the similarity of each extended demand side client with connection relationship is reduced, and the business opportunity of the supplier is improved.

[0096] S104: constructing a supply-demand resource portrait corresponding to the demand side client according to the to-be-pushed business opportunity element.

[0097] After obtaining the to-be-pushed business opportunity element based on the above step S103, a supply-demand resource portrait corresponding to the demand side client is constructed according to the obtained to-be-pushed business opportunity element, so as to quickly match the corresponding supplier based on the portrait subsequently, and the establishment efficiency of the supply-demand resource interaction channel is improved.

[0098] S105: establishing a matching relationship of the supplier client corresponding to the demand side client according to the matching degree of the supply-demand resource portrait and each supplier preset label, so as to realize the interaction push of the supply-demand resource of the demand side client and the supplier client based on the matching relationship.

[0099] After the supply-demand resource image is established according to the above step S104, the matching relationship between the demand-side client and the corresponding supply-side client is determined according to the matching degree of the supply-demand resource image and the preset label of each supplier, and the supply-demand resource interaction between the demand-side client and the supply-side client is established according to the determined matching relationship, that is, the demand of the demand-side client is generated as a business opportunity announcement and sent to the supply-side client, and the related demand resource information of the supply-side client is generated as a resource display announcement and sent to the demand-side client, so as to realize the interaction push of the supply-demand resource.

[0100] Specifically, in one or more embodiments of the present specification, before the matching relationship between the demand-side client and the corresponding supply-side client is established according to the matching degree of the supply-demand resource image and the preset label of each supplier, the method further includes the following steps:

[0101] The historical sales information of each supply-side client and the operating product information uploaded by each supply-side client are obtained, so as to determine the corresponding supply product service type of the supply-side client according to the obtained historical sales information and operating product information. It should be noted that the supply product service type includes wholesale service type, retail service type, pre-sale service type, etc. Then, the supply content of each supply-side client is grouped according to the supply product service type, and a first association relationship between the supply-side client and the supply product service type is established. Then, the operating product information and the supply range information under each supply product service type are obtained, so as to determine the supply resource limited label of each supply resource according to the operating product information and the supply range information, and establish a second association relationship between the supply resource and the supply resource limited label under the supply service type. It should be noted that the supply resource limited label limits the limitation conditions of the supply product under each service type of the current supply-side client, such as delivery time, inventory quantity, etc. Then, the description information of each supply resource uploaded by each supply-side client is determined to determine the corresponding description label of each supply resource, and a third association relationship between the description label and the supply resource is established. The first association relationship, the second association relationship and the third association relationship obtained in the above process are connected to generate an association knowledge graph between the supply-side client, the supply product service type and the supply resource, so as to quickly lock the appropriate supply-side client based on the association knowledge graph.

[0102] Further, in one or more embodiments of the present specification, the matching relationship between the demand-side client and the corresponding supply-side client is established according to the matching degree of the supply-demand resource image and the preset label of each supplier, and specifically includes the following steps:

[0103] First, one or more supplier preset tags of a supplier client corresponding to the supply-demand resource portrait are acquired; it should be noted that the supplier preset tags include: supply resource limiting tags, and description tags of the supply resource. Then, a supplier client corresponding to the supplier preset tags is acquired according to the association knowledge graph, and a traceability path corresponding to the supply-demand resource portrait and the supplier client is acquired. Then, in order to enable the demand side to match a supplier with high quality, in the embodiment of the present specification, a historical transaction evaluation same as the traceability path is acquired according to a pre-set database, and the number of first evaluations and the number of second evaluations in the historical transaction evaluation are determined. It should be noted that the first evaluation and the second evaluation correspond to different evaluation score ranges, and the evaluation score range of the first evaluation is greater than the evaluation score range of the second evaluation. Then, according to the number of first evaluations and the number of second evaluations, the proportion of first evaluations and the proportion of second evaluations are respectively determined. If the proportion of first evaluations is greater than a preset beneficial proportion, and the proportion of second evaluations is less than a preset harmful proportion, a matching relationship of the supplier client corresponding to the demand side client is established.

[0104] As shown in Figure 2 , one or more embodiments of the present specification provide an internal structure diagram of a supply-demand resource pushing device based on business opportunity elements. It can be known from Figure 2 that in one or more embodiments of the present specification, a supply-demand resource pushing device based on business opportunity elements, the device comprises:

[0105] at least one processor 201; and

[0106] a memory 202 in communication connection with the at least one processor 201; wherein

[0107] the memory 202 stores instructions executable by the at least one processor 201, and the instructions are executed by the at least one processor 201 to enable the at least one processor 201 to:

[0108] acquire one or more inquiry information uploaded by a demand side client in a preset time period, to determine an initial range of demand resources corresponding to the demand side client based on the inquiry information;

[0109] call historical demand resource transaction information of the demand side client, to extract initial business opportunity elements corresponding to the demand side client based on the historical demand resource transaction information and the initial range of demand resources; wherein the historical demand resource transaction information includes: historical inquiry information, and transaction commodity basic information;

[0110] According to the preset collaborative filtering strategy, an extended demand-side client associated with the demand-side client is acquired, and an extended business opportunity element of the extended demand-side client is extracted, so as to determine a to-be-pushed business opportunity element based on the initial business opportunity element and the extended business opportunity element;

[0111] According to the to-be-pushed business opportunity element, a supply-demand resource portrait corresponding to the demand-side client is constructed;

[0112] According to the matching degree of the supply-demand resource portrait and each supplier preset label, a matching relationship of a supply-side client corresponding to the demand-side client is established, so as to realize interactive pushing of supply-demand resources of the demand-side client and the supply-side client based on the matching relationship.

[0113] As shown in Figure 3 , one or more embodiments of the present specification provide an internal structure diagram of a non-volatile storage medium. It can be known that a non-volatile storage medium stores computer executable instructions 301, and the computer executable instructions 301 can: Figure 3

[0114] acquire one or more inquiry information uploaded by a demand-side client in a preset time period, so as to determine an initial range of demand resources corresponding to the demand-side client based on the inquiry information;

[0115] call historical demand resource transaction information of the demand-side client, so as to extract an initial business opportunity element corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources; wherein the historical demand resource transaction information includes historical inquiry information and transaction commodity basic information;

[0116] According to the preset collaborative filtering strategy, an extended demand-side client associated with the demand-side client is acquired, and an extended business opportunity element of the extended demand-side client is extracted, so as to determine a to-be-pushed business opportunity element based on the initial business opportunity element and the extended business opportunity element;

[0117] According to the to-be-pushed business opportunity element, a supply-demand resource portrait corresponding to the demand-side client is constructed;

[0118] According to the matching degree of the supply-demand resource portrait and each supplier preset label, a matching relationship of a supply-side client corresponding to the demand-side client is established, so as to realize interactive pushing of supply-demand resources of the demand-side client and the supply-side client based on the matching relationship.

[0119] ​The various embodiments in this specification describe the application in progressive stages. Each stage builds upon the previous stages, and each stage can be described in terms of the differences between that stage and the previous stage. For example, the device, apparatus, and non-transitory computer storage medium embodiments are described more quickly because they are substantially similar to the method embodiments. The relevant portions of the method embodiments are referenced.

[0120] The above description describes certain embodiments of the application. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0121] The above description is of one or more embodiments of the application and is not intended to limit the application. Those skilled in the art will be able to make various changes and modifications without departing from the spirit and scope of the one or more embodiments of the application. Any further modifications, equivalents and / or alternatives come within the scope of the claims of the application.

Claims

1. A method for pushing supply and demand resources based on business opportunity elements, characterized in that, The method includes: Obtain one or more inquiry messages uploaded by the demand-side client within a preset time period, and determine the initial range of demand resources corresponding to the demand-side client based on the inquiry messages; The historical demand resource transaction information of the demand-side client is invoked to generate initial business opportunity elements corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources; wherein, the historical demand resource transaction information includes: historical inquiry information and basic information of the transacted goods; According to the preset collaborative filtering strategy, the extended demand-side clients associated with the demand-side client are obtained, and the extended business opportunity elements of the extended demand-side clients are extracted, so as to determine the business opportunity elements to be pushed based on the initial business opportunity elements and the extended business opportunity elements. Based on the elements of the business opportunity to be pushed, construct a supply and demand resource profile corresponding to the demand-side client; Based on the matching degree between the supply and demand resource profiles and the pre-set tags of each supplier, a matching relationship is established between the demand-side client and the corresponding supplier client, so as to realize the interactive push of supply and demand resources between the demand-side client and the supplier client based on the matching relationship.

2. The supply and demand resource push method based on business opportunity elements according to claim 1, characterized in that, Based on the inquiry information, the initial range of demand resources corresponding to the demand-side client is determined, specifically including: The inquiry information is split based on a preset character length to obtain word segments of the inquiry information, and the word segmentation features of the word segments are obtained. The word segmentation features are then input into a preset deep learning model to obtain the inquiry keywords of the demand side client. The word segmentation features include: word class features and named entity features. Based on the semantics of the inquiry keywords, expanded keywords corresponding to each of the inquiry keywords are retrieved, so as to construct a keyword set corresponding to the inquiry information based on the inquiry keywords and the expanded keywords; The keyword set is divided into a first keyword set and a second keyword set; wherein, the first keyword set is a keyword set that does not contain numbers, and the second keyword set is a keyword set that contains numbers; Cluster the first keyword set to obtain demand resource attribute information, and obtain the context information of each keyword in the second keyword set to obtain demand resource price information based on the context information; wherein, the demand resource attribute information includes: demand resource type, demand resource quantity, and demand resource name; the demand price information includes: expected price range and acceptable price range; Based on the demand resource attribute information and the demand price information, the initial range of demand resources corresponding to the demand-side client is determined.

3. The supply and demand resource push method based on business opportunity elements according to claim 2, characterized in that, Clustering the first keyword set to obtain the required resource attribute information, specifically including: Obtain the word vectors of each keyword in the first keyword set, and determine the similarity between each keyword based on the distance between the word vectors; One or more feature center keywords are determined from the keyword set, and multiple keyword clusters are determined based on the similarity between the feature center keywords and each of the keywords; Determine the similarity between each keyword in the keyword cluster. If the similarity is less than a preset threshold, iteratively divide the keyword cluster to obtain a keyword cluster that meets the requirements. By integrating the semantic information of each keyword in each keyword cluster, the required resource attribute information is obtained.

4. The supply and demand resource push method based on business opportunity elements according to claim 2, characterized in that, The system retrieves historical demand resource transaction information from the demand-side client to generate initial business opportunity elements corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources. Specifically, this includes: The historical demand resource transaction information of the demand side client is invoked to determine the transaction rate, attribute information of each historical demand resource, and corresponding transaction price of each historical demand resource based on the historical demand resource transaction information. If the historical demand resource attribute information corresponds to the demand resource attribute information of the initial range of the demand resource, and the transaction rate of the historical demand resource is less than the preset transaction threshold, then the query rate of the demand resource attribute information for a preset time period is obtained. The query rate and the transaction rate of historical demand resources are combined based on a preset weight ratio to obtain the probability that business opportunity elements can be generated. If the probability that business opportunity elements can be generated is less than a preset production probability threshold, then the initial extraction of business opportunity elements will not be performed. If the historical demand resource attribute information corresponds to the demand resource attribute information of the initial range of the demand resources, and the transaction rate of the historical demand resources is greater than a preset threshold, then according to the timestamp corresponding to the historical demand resource attribute information, the average market price corresponding to each demand resource in the historical demand resource attribute information is called. Based on the average market price and the corresponding historical transaction prices of demanded resources, determine the price deviation range; The initial range of demand resources is adjusted based on the price deviation range to obtain the demand resource range. Information is extracted from the demand resource range according to the pre-set business opportunity announcement template of the supplier client to obtain the initial business opportunity elements corresponding to the demand client.

5. The supply and demand resource push method based on business opportunity elements according to claim 1, characterized in that, According to a pre-set collaborative filtering strategy, extended demand-side clients associated with the demand-side client are obtained, and extended opportunity elements of the extended demand-side clients are extracted. Based on the initial opportunity elements and the extended opportunity elements, the opportunity elements to be pushed are determined, specifically including: Based on the historical transaction information of the demand-side clients, a historical rating matrix for each demand-side resource is established. The graph data in which the demand-side client is located is determined, and extended demand-side clients that match the historical rating matrix in the graph data are obtained based on the Pearson similarity algorithm; wherein, the demand-side client corresponds to one or more graph data; Obtain the difference set between the current business opportunity elements of the extended demand-side client and the initial business opportunity elements of the demand-side client, and use each of the business opportunity elements in the difference set as the initial extended business opportunity elements. The historical scores corresponding to the initial extended business opportunity elements are obtained, and the initial extended business opportunity elements are filtered based on the historical scores to obtain extended business opportunity elements; wherein, the historical scores are obtained through the historical score matrix of the extended demand side client; Obtain the union of the initial business opportunity element and the extended business opportunity element, and use the union as the business opportunity element to be pushed.

6. The supply and demand resource push method based on business opportunity elements according to claim 5, characterized in that, Before obtaining the extended demand-side clients in the graph data that match the historical rating matrix based on the Pearson similarity algorithm, the method further includes: Extract the connected graph data from the graph data where the demand-side client is located, and obtain the valid connected graph data containing the demand-side client in the connected graph data; Based on the connectivity relationships of each of the effective connectivity graph data, a first extended demand client and a second extended demand client corresponding to the demand client are determined; wherein, the first extended demand client is directly connected to the demand client, and the second extended demand client is indirectly connected to the demand client; Obtain the indirect connection path of the second extended demand-side client, and determine the degree of association between the second extended demand-side client and the demand-side client based on the path length of the indirect connection path; The second extended demand-side client is filtered based on a preset relevance threshold to obtain the third extended demand-side client; The first extended demand client and the third extended demand client are merged to determine the extended demand clients to be matched among the extended demand clients, so as to obtain the extended demand clients that match the historical rating matrix among the extended demand clients to be matched based on the Pearson similarity algorithm.

7. The supply and demand resource push method based on business opportunity elements according to claim 1, characterized in that, Before establishing the matching relationship between the demand-side client and the supplier-side client based on the matching degree between the supply and demand resource profiles and the pre-set tags of each supplier, the method further includes: The system obtains historical sales information from each supplier's client and information on the products they operate, and determines the type of product service corresponding to each supplier's client based on the historical sales information and the product information. The type of product service includes: wholesale service, retail service, and pre-sale service. Based on the types of supplied products and services, the supply content of each supplier client is grouped, and a first association relationship is established between the supplier client and each type of supplied product and service. Obtain the business product information and supply scope information under each of the aforementioned supply product service types, and determine the supply resource limitation label for each of the aforementioned supply resources based on the business product information and the supply scope information, so as to establish a second association relationship between the supply resources and the supply resource limitation label under the aforementioned supply service type; Based on the description information of each supply resource uploaded by each supplier's client, a description tag for each supply resource is determined, so as to determine the third association relationship between the description tag and the supply resource; Based on the first association, the second association, and the third association, a knowledge graph is established to associate the supplier client, the type of supplied product service, and the supplied resources.

8. The supply and demand resource push method based on business opportunity elements according to claim 7, characterized in that, Based on the matching degree between the supply and demand resource profiles and the pre-set tags of each supplier, a matching relationship is established between the demand-side client and the corresponding supplier-side client, specifically including: Obtain one or more supplier preset tags from the supplier client corresponding to the supply and demand resource profile; wherein, the supplier preset tags include: the supply resource limitation tag and the supply resource description tag; Based on the associated knowledge graph, obtain the supplier client corresponding to the supplier's pre-set tags, and obtain the traceability path corresponding to the supply and demand resource profile and the supplier client; Based on a pre-set database, historical transaction evaluations consistent with the traceability path are obtained, and the number of first evaluations and the number of second evaluations of the historical transaction evaluations are obtained; wherein, the first evaluation and the second evaluation correspond to different evaluation score ranges, and the evaluation score range of the first evaluation is greater than the evaluation score range of the second evaluation. Based on the number of the first evaluation and the number of the second evaluation, the proportion of the first evaluation and the proportion of the second evaluation are determined respectively. If the first evaluation percentage is greater than the preset beneficial percentage and the second evaluation percentage is less than the preset harmful percentage, then a matching relationship is established between the demand-side client and the corresponding supply-side client.

9. A supply and demand resource push device based on business opportunity elements, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Obtain one or more inquiry messages uploaded by the demand-side client within a preset time period, and determine the initial range of demand resources corresponding to the demand-side client based on the inquiry messages; The historical demand resource transaction information of the demand-side client is invoked to extract initial business opportunity elements corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources; wherein, the historical demand resource transaction information includes: historical inquiry information and basic information of the transacted goods; According to the preset collaborative filtering strategy, the extended demand-side clients associated with the demand-side client are obtained, and the extended business opportunity elements of the extended demand-side clients are extracted, so as to determine the business opportunity elements to be pushed based on the initial business opportunity elements and the extended business opportunity elements. Based on the elements of the business opportunity to be pushed, construct a supply and demand resource profile corresponding to the demand-side client; Based on the matching degree between the supply and demand resource profiles and the pre-set tags of each supplier, a matching relationship is established between the demand-side client and the corresponding supplier client, so as to realize the interactive push of supply and demand resources between the demand-side client and the supplier client based on the matching relationship.

10. A non-volatile storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are capable of: Obtain one or more inquiry messages uploaded by the demand-side client within a preset time period, and determine the initial range of demand resources corresponding to the demand-side client based on the inquiry messages; The historical demand resource transaction information of the demand-side client is invoked to extract initial business opportunity elements corresponding to the demand-side client based on the historical demand resource transaction information and the initial range of demand resources; wherein, the historical demand resource transaction information includes: historical inquiry information and basic information of the transacted goods; According to the preset collaborative filtering strategy, the extended demand-side clients associated with the demand-side client are obtained, and the extended business opportunity elements of the extended demand-side clients are extracted, so as to determine the business opportunity elements to be pushed based on the initial business opportunity elements and the extended business opportunity elements. Based on the elements of the business opportunity to be pushed, construct a supply and demand resource profile corresponding to the demand-side client; Based on the matching degree between the supply and demand resource profiles and the pre-set tags of each supplier, a matching relationship is established between the demand-side client and the corresponding supplier client, so as to realize the interactive push of supply and demand resources between the demand-side client and the supplier client based on the matching relationship.

Images